You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by sp...@apache.org on 2016/05/27 15:37:22 UTC
[01/48] hive git commit: HIVE-13800. Disable LLAP UI auth by default.
(Siddharth Seth, reviewed by Sergey Shelukhin) [Forced Update!]
Repository: hive
Updated Branches:
refs/heads/java8 ace92dbc5 -> eaa8ff214 (forced update)
HIVE-13800. Disable LLAP UI auth by default. (Siddharth Seth, reviewed by Sergey Shelukhin)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/d52131d7
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/d52131d7
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/d52131d7
Branch: refs/heads/java8
Commit: d52131d763b8b8d26b6ee81ebac68f8ee9ffdb47
Parents: 3a2a3e1
Author: Siddharth Seth <ss...@apache.org>
Authored: Wed May 25 14:57:26 2016 -0700
Committer: Siddharth Seth <ss...@apache.org>
Committed: Wed May 25 14:57:26 2016 -0700
----------------------------------------------------------------------
common/src/java/org/apache/hadoop/hive/conf/HiveConf.java | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/d52131d7/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
index 3e295fe..b1f37ff 100644
--- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
+++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
@@ -2720,7 +2720,7 @@ public class HiveConf extends Configuration {
"LLAP delegation token lifetime, in seconds if specified without a unit."),
LLAP_MANAGEMENT_RPC_PORT("hive.llap.management.rpc.port", 15004,
"RPC port for LLAP daemon management service."),
- LLAP_WEB_AUTO_AUTH("hive.llap.auto.auth", true,
+ LLAP_WEB_AUTO_AUTH("hive.llap.auto.auth", false,
"Whether or not to set Hadoop configs to enable auth in LLAP web app."),
LLAP_CREATE_TOKEN_LOCALLY("hive.llap.create.token.locally", "hs2",
new StringSet("true", "hs2", "false"),
[20/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/stats_list_bucket.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_list_bucket.q.out b/ql/src/test/results/clientpositive/stats_list_bucket.q.out
new file mode 100644
index 0000000..c34c414
--- /dev/null
+++ b/ql/src/test/results/clientpositive/stats_list_bucket.q.out
@@ -0,0 +1,189 @@
+PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+drop table stats_list_bucket
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+drop table stats_list_bucket
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table stats_list_bucket_1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table stats_list_bucket_1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table stats_list_bucket (
+ c1 string,
+ c2 string
+) partitioned by (ds string, hr string)
+skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
+stored as directories
+stored as rcfile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@stats_list_bucket
+POSTHOOK: query: create table stats_list_bucket (
+ c1 string,
+ c2 string
+) partitioned by (ds string, hr string)
+skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
+stored as directories
+stored as rcfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@stats_list_bucket
+PREHOOK: query: -- Try partitioned table with list bucketing.
+-- The stats should show 500 rows loaded, as many rows as the src table has.
+
+insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
+ select key, value from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
+POSTHOOK: query: -- Try partitioned table with list bucketing.
+-- The stats should show 500 rows loaded, as many rows as the src table has.
+
+insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
+ select key, value from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@stats_list_bucket
+POSTHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@stats_list_bucket
+# col_name data_type comment
+
+c1 string
+c2 string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: stats_list_bucket
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 4812
+ totalSize 5522
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [c1, c2]
+Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=466/c2=val_466, [82, val_82]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=82/c2=val_82, [287, val_287]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=287/c2=val_287}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: -- Also try non-partitioned table with list bucketing.
+-- Stats should show the same number of rows.
+
+create table stats_list_bucket_1 (
+ c1 string,
+ c2 string
+)
+skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
+stored as directories
+stored as rcfile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@stats_list_bucket_1
+POSTHOOK: query: -- Also try non-partitioned table with list bucketing.
+-- Stats should show the same number of rows.
+
+create table stats_list_bucket_1 (
+ c1 string,
+ c2 string
+)
+skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
+stored as directories
+stored as rcfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@stats_list_bucket_1
+PREHOOK: query: insert overwrite table stats_list_bucket_1
+ select key, value from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@stats_list_bucket_1
+POSTHOOK: query: insert overwrite table stats_list_bucket_1
+ select key, value from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@stats_list_bucket_1
+POSTHOOK: Lineage: stats_list_bucket_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: stats_list_bucket_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: desc formatted stats_list_bucket_1
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@stats_list_bucket_1
+POSTHOOK: query: desc formatted stats_list_bucket_1
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@stats_list_bucket_1
+# col_name data_type comment
+
+c1 string
+c2 string
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MANAGED_TABLE
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 4812
+ totalSize 5522
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [c1, c2]
+Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287, [82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: drop table stats_list_bucket
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@stats_list_bucket
+PREHOOK: Output: default@stats_list_bucket
+POSTHOOK: query: drop table stats_list_bucket
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@stats_list_bucket
+POSTHOOK: Output: default@stats_list_bucket
+PREHOOK: query: drop table stats_list_bucket_1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@stats_list_bucket_1
+PREHOOK: Output: default@stats_list_bucket_1
+POSTHOOK: query: drop table stats_list_bucket_1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@stats_list_bucket_1
+POSTHOOK: Output: default@stats_list_bucket_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out b/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out
deleted file mode 100644
index 652acbb..0000000
--- a/ql/src/test/results/clientpositive/str_to_map.q.java1.7.out
+++ /dev/null
@@ -1,220 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-desc function str_to_map
-PREHOOK: type: DESCFUNCTION
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-desc function str_to_map
-POSTHOOK: type: DESCFUNCTION
-str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
-PREHOOK: query: desc function extended str_to_map
-PREHOOK: type: DESCFUNCTION
-POSTHOOK: query: desc function extended str_to_map
-POSTHOOK: type: DESCFUNCTION
-str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
-Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2.
-PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-1
-1
-1
-PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-{"b":"2","a":"1","c":"3"}
-{"b":"2","a":"1","c":"3"}
-{"b":"2","a":"1","c":"3"}
-PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-{"b":"2","a":"1","c":"3"}
-{"b":"2","a":"1","c":"3"}
-{"b":"2","a":"1","c":"3"}
-PREHOOK: query: explain select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'a:1,b:2,c:3' (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map(_col0,',',':')['a'] (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- ListSink
-
-PREHOOK: query: select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-1
-1
-1
-PREHOOK: query: drop table tbl_s2m
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table tbl_s2m
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
-PREHOOK: type: CREATETABLE_AS_SELECT
-PREHOOK: Input: default@src
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl_s2m
-POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
-POSTHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: Input: default@src
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl_s2m
-POSTHOOK: Lineage: tbl_s2m.t SIMPLE []
-PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
-PREHOOK: type: QUERY
-PREHOOK: Input: default@tbl_s2m
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@tbl_s2m
-#### A masked pattern was here ####
-444
-444
-444
-PREHOOK: query: drop table tbl_s2m
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@tbl_s2m
-PREHOOK: Output: default@tbl_s2m
-POSTHOOK: query: drop table tbl_s2m
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@tbl_s2m
-POSTHOOK: Output: default@tbl_s2m
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out b/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out
deleted file mode 100644
index 23b0cbb..0000000
--- a/ql/src/test/results/clientpositive/str_to_map.q.java1.8.out
+++ /dev/null
@@ -1,219 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-desc function str_to_map
-PREHOOK: type: DESCFUNCTION
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-desc function str_to_map
-POSTHOOK: type: DESCFUNCTION
-str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
-PREHOOK: query: desc function extended str_to_map
-PREHOOK: type: DESCFUNCTION
-POSTHOOK: query: desc function extended str_to_map
-POSTHOOK: type: DESCFUNCTION
-str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
-Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2.
-PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-1
-1
-1
-PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-{"a":"1","b":"2","c":"3"}
-{"a":"1","b":"2","c":"3"}
-{"a":"1","b":"2","c":"3"}
-PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 460000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 2760 Basic stats: COMPLETE Column stats: COMPLETE
- ListSink
-
-PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-{"a":"1","b":"2","c":"3"}
-{"a":"1","b":"2","c":"3"}
-{"a":"1","b":"2","c":"3"}
-PREHOOK: query: explain select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-PREHOOK: type: QUERY
-POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: 'a:1,b:2,c:3' (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Transform Operator
- command: cat
- output info:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: str_to_map(_col0,',',':')['a'] (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 3
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 3
- Processor Tree:
- ListSink
-
-PREHOOK: query: select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map(t.ss,',',':')['a']
-from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
-limit 3
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-1
-1
-1
-PREHOOK: query: drop table tbl_s2m
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table tbl_s2m
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
-PREHOOK: type: CREATETABLE_AS_SELECT
-PREHOOK: Input: default@src
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl_s2m
-POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
-POSTHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: Input: default@src
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl_s2m
-PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
-PREHOOK: type: QUERY
-PREHOOK: Input: default@tbl_s2m
-#### A masked pattern was here ####
-POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@tbl_s2m
-#### A masked pattern was here ####
-444
-444
-444
-PREHOOK: query: drop table tbl_s2m
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@tbl_s2m
-PREHOOK: Output: default@tbl_s2m
-POSTHOOK: query: drop table tbl_s2m
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@tbl_s2m
-POSTHOOK: Output: default@tbl_s2m
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/str_to_map.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/str_to_map.q.out b/ql/src/test/results/clientpositive/str_to_map.q.out
new file mode 100644
index 0000000..30c98db
--- /dev/null
+++ b/ql/src/test/results/clientpositive/str_to_map.q.out
@@ -0,0 +1,216 @@
+PREHOOK: query: desc function str_to_map
+PREHOOK: type: DESCFUNCTION
+POSTHOOK: query: desc function str_to_map
+POSTHOOK: type: DESCFUNCTION
+str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
+PREHOOK: query: desc function extended str_to_map
+PREHOOK: type: DESCFUNCTION
+POSTHOOK: query: desc function extended str_to_map
+POSTHOOK: type: DESCFUNCTION
+str_to_map(text, delimiter1, delimiter2) - Creates a map by parsing text
+Split text into key-value pairs using two delimiters. The first delimiter seperates pairs, and the second delimiter sperates key and value. If only one parameter is given, default delimiters are used: ',' as delimiter1 and '=' as delimiter2.
+PREHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 3
+ Processor Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: str_to_map('a=1,b=2,c=3',',','=')['a'] (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select str_to_map('a=1,b=2,c=3',',','=')['a'] from src limit 3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+1
+1
+1
+PREHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3') from src limit 3
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 3
+ Processor Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: str_to_map('a:1,b:2,c:3') (type: map<string,string>)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select str_to_map('a:1,b:2,c:3') from src limit 3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+{"a":"1","b":"2","c":"3"}
+{"a":"1","b":"2","c":"3"}
+{"a":"1","b":"2","c":"3"}
+PREHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 3
+ Processor Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: str_to_map('a:1,b:2,c:3',',',':') (type: map<string,string>)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 377000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 2262 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select str_to_map('a:1,b:2,c:3',',',':') from src limit 3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+{"a":"1","b":"2","c":"3"}
+{"a":"1","b":"2","c":"3"}
+{"a":"1","b":"2","c":"3"}
+PREHOOK: query: explain select str_to_map(t.ss,',',':')['a']
+from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
+limit 3
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select str_to_map(t.ss,',',':')['a']
+from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
+limit 3
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: 'a:1,b:2,c:3' (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ Transform Operator
+ command: cat
+ output info:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: str_to_map(_col0,',',':')['a'] (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 3
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select str_to_map(t.ss,',',':')['a']
+from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
+limit 3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select str_to_map(t.ss,',',':')['a']
+from (select transform('a:1,b:2,c:3') using 'cat' as (ss) from src) t
+limit 3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+1
+1
+1
+PREHOOK: query: drop table tbl_s2m
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table tbl_s2m
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tbl_s2m
+POSTHOOK: query: create table tbl_s2m as select 'ABC=CC_333=444' as t from src tablesample (3 rows)
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tbl_s2m
+POSTHOOK: Lineage: tbl_s2m.t SIMPLE []
+PREHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl_s2m
+#### A masked pattern was here ####
+POSTHOOK: query: select str_to_map(t,'_','=')['333'] from tbl_s2m
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl_s2m
+#### A masked pattern was here ####
+444
+444
+444
+PREHOOK: query: drop table tbl_s2m
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@tbl_s2m
+PREHOOK: Output: default@tbl_s2m
+POSTHOOK: query: drop table tbl_s2m
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@tbl_s2m
+POSTHOOK: Output: default@tbl_s2m
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out
deleted file mode 100644
index 279843b..0000000
--- a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.7.out
+++ /dev/null
@@ -1,999 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_4
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_4
-RUN: Stage-0:DDL
-PREHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_5
-POSTHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_5
-RUN: Stage-0:DDL
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-10 is a root stage
- Stage-2 depends on stages: Stage-10
- Stage-3 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
- Stage-6 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-6
- Stage-7 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-5
- Stats-Aggr Operator
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: key (type: string), value (type: string)
- sort order: ++
- Map-reduce partition columns: key (type: string), value (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-7
- Stats-Aggr Operator
-
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-10:MAPRED
-RUN: Stage-2:MAPRED
-RUN: Stage-3:MAPRED
-RUN: Stage-6:MAPRED
-RUN: Stage-4:MAPRED
-RUN: Stage-0:MOVE
-RUN: Stage-1:MOVE
-RUN: Stage-7:STATS
-RUN: Stage-5:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
-Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-10 is a root stage
- Stage-14 depends on stages: Stage-10 , consists of Stage-17, Stage-2
- Stage-17 has a backup stage: Stage-2
- Stage-13 depends on stages: Stage-17
- Stage-15 depends on stages: Stage-2, Stage-13
- Stage-12 depends on stages: Stage-15
- Stage-0 depends on stages: Stage-12
- Stage-7 depends on stages: Stage-0
- Stage-16 depends on stages: Stage-2, Stage-13
- Stage-4 depends on stages: Stage-16
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
- Stage-2
-
-STAGE PLANS:
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-14
- Conditional Operator
-
- Stage: Stage-17
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $INTNAME
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $INTNAME
- TableScan
- HashTable Sink Operator
- keys:
- 0
- 1
-
- Stage: Stage-13
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-15
- Map Reduce Local Work
- Alias -> Map Local Tables:
- sq_1:a
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- sq_1:a
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
-
- Stage: Stage-12
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-7
- Stats-Aggr Operator
-
- Stage: Stage-16
- Map Reduce Local Work
- Alias -> Map Local Tables:
- sq_2:s1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- sq_2:s1
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-5
- Stats-Aggr Operator
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-10:MAPRED
-RUN: Stage-14:CONDITIONAL
-RUN: Stage-17:MAPREDLOCAL
-RUN: Stage-13:MAPRED
-RUN: Stage-15:MAPREDLOCAL
-RUN: Stage-16:MAPREDLOCAL
-RUN: Stage-12:MAPRED
-RUN: Stage-4:MAPRED
-RUN: Stage-0:MOVE
-RUN: Stage-1:MOVE
-RUN: Stage-7:STATS
-RUN: Stage-5:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
[33/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
new file mode 100644
index 0000000..5f0406a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.out
@@ -0,0 +1,811 @@
+PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns. merge.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- after merge
+-- 142 000000_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+-- after merge
+-- 118 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns. merge.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- after merge
+-- 142 000000_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+-- after merge
+-- 118 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 6
+ numRows 1000
+ rawDataSize 9624
+ totalSize 10898
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+ Stage-5
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-5
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 1000
+ rawDataSize 9624
+ totalSize 10786
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(*) from list_bucketing_static_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from list_bucketing_static_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+1000
+PREHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ numFiles 4
+ numRows 1000
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 9624
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 10786
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_static_part
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 11
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 12
+PREHOOK: query: -- clean up
+drop table list_bucketing_static_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- clean up
+drop table list_bucketing_static_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out
deleted file mode 100644
index a0947b2..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.7.out
+++ /dev/null
@@ -1,506 +0,0 @@
-PREHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
-partitioned by (ds String, hr String)
-skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
-stored as DIRECTORIES
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
-partitioned by (ds String, hr String)
-skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
-stored as DIRECTORIES
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 3
- numRows 500
- rawDataSize 5312
- totalSize 5812
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-InputFormat: org.apache.hadoop.mapred.TextInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 12]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 3
- numRows 500
- rawDataSize 5312
- totalSize 5812
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-InputFormat: org.apache.hadoop.mapred.TextInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-103 val_103
-103 val_103
-103 val_103
-103 val_103
-PREHOOK: query: explain extended
-select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Partition
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '103') and (value = 'val_103')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-103 val_103 2008-04-08 11
-103 val_103 2008-04-08 11
-103 val_103 2008-04-08 12
-103 val_103 2008-04-08 12
-PREHOOK: query: -- clean up resources
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up resources
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.8.out
deleted file mode 100644
index 1c33382..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.java1.8.out
+++ /dev/null
@@ -1,617 +0,0 @@
-PREHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
-partitioned by (ds String, hr String)
-skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
-stored as DIRECTORIES
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
-partitioned by (ds String, hr String)
-skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
-stored as DIRECTORIES
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- hr
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 3
- numRows 500
- rawDataSize 5312
- totalSize 5812
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-InputFormat: org.apache.hadoop.mapred.TextInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 12]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 3
- numRows 500
- rawDataSize 5312
- totalSize 5812
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-InputFormat: org.apache.hadoop.mapred.TextInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-103 val_103
-103 val_103
-103 val_103
-103 val_103
-PREHOOK: query: explain extended
-select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- ds
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- hr
- TOK_WHERE
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- key
- "103"
- =
- TOK_TABLE_OR_COL
- value
- "val_103"
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '103') and (value = 'val_103')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: value=val_103
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
-#### A masked pattern was here ####
- Partition
- base file name: value=val_103
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Truncated Path -> Alias:
- /list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=103/value=val_103 [list_bucketing_dynamic_part]
- /list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=103/value=val_103 [list_bucketing_dynamic_part]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-103 val_103 2008-04-08 11
-103 val_103 2008-04-08 11
-103 val_103 2008-04-08 12
-103 val_103 2008-04-08 12
-PREHOOK: query: -- clean up resources
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up resources
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
[44/48] hive git commit: HIVE-13409: Fix JDK8 test failures related
to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join34.q.out b/ql/src/test/results/clientpositive/spark/join34.q.out
index 235d36a..ebd9c89 100644
--- a/ql/src/test/results/clientpositive/spark/join34.q.out
+++ b/ql/src/test/results/clientpositive/spark/join34.q.out
@@ -78,7 +78,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -98,7 +98,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -150,7 +150,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -170,7 +170,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -222,7 +222,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -242,7 +242,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join35.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join35.q.out b/ql/src/test/results/clientpositive/spark/join35.q.out
index 7b873c6..d14dadf 100644
--- a/ql/src/test/results/clientpositive/spark/join35.q.out
+++ b/ql/src/test/results/clientpositive/spark/join35.q.out
@@ -86,7 +86,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -106,7 +106,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -164,7 +164,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -184,7 +184,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -236,7 +236,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -256,7 +256,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join9.q.out b/ql/src/test/results/clientpositive/spark/join9.q.out
index 4119855..05aa50b 100644
--- a/ql/src/test/results/clientpositive/spark/join9.q.out
+++ b/ql/src/test/results/clientpositive/spark/join9.q.out
@@ -64,7 +64,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -135,7 +135,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -155,7 +155,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out b/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out
index 4d6d39d..5d7cecf 100644
--- a/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -82,7 +82,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -129,7 +129,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -149,7 +149,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -247,7 +247,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -731,7 +731,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/load_dyn_part8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/load_dyn_part8.q.out b/ql/src/test/results/clientpositive/spark/load_dyn_part8.q.out
index b528357..ee70e71 100644
--- a/ql/src/test/results/clientpositive/spark/load_dyn_part8.q.out
+++ b/ql/src/test/results/clientpositive/spark/load_dyn_part8.q.out
@@ -151,7 +151,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -197,7 +197,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -243,7 +243,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -289,7 +289,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
index 3d90dc4..6cfde3f 100644
--- a/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -83,7 +83,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -138,7 +138,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -184,7 +184,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -370,7 +370,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -416,7 +416,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -462,7 +462,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -508,7 +508,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -582,7 +582,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -602,7 +602,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -778,7 +778,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -798,7 +798,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -853,7 +853,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -899,7 +899,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1081,7 +1081,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1127,7 +1127,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1199,7 +1199,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1219,7 +1219,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out
index aea47f7..1900ed6 100644
--- a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out
@@ -50,7 +50,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -70,7 +70,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -120,7 +120,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -140,7 +140,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -237,7 +237,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -283,7 +283,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -329,7 +329,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -375,7 +375,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out b/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out
index 4aecb73..ec43c12 100644
--- a/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out
+++ b/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out
@@ -181,7 +181,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -201,7 +201,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -255,7 +255,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -300,7 +300,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -345,7 +345,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -390,7 +390,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -556,7 +556,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -576,7 +576,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -630,7 +630,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -676,7 +676,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -722,7 +722,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -768,7 +768,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -945,7 +945,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -965,7 +965,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1019,7 +1019,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1064,7 +1064,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1109,7 +1109,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1154,7 +1154,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1334,7 +1334,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1354,7 +1354,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1400,7 +1400,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1420,7 +1420,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1549,7 +1549,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1569,7 +1569,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1616,7 +1616,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1636,7 +1636,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1755,7 +1755,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1775,7 +1775,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/pcr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out
index cd16787..cbebbdd 100644
--- a/ql/src/test/results/clientpositive/spark/pcr.q.out
+++ b/ql/src/test/results/clientpositive/spark/pcr.q.out
@@ -3942,7 +3942,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4077,7 +4077,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4123,7 +4123,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4262,7 +4262,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4308,7 +4308,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out
index 6b1cadf..fbba885 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out
@@ -67,7 +67,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -87,7 +87,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -141,7 +141,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -161,7 +161,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -354,7 +354,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -374,7 +374,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -428,7 +428,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -448,7 +448,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -641,7 +641,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -661,7 +661,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -715,7 +715,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -735,7 +735,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -928,7 +928,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -948,7 +948,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1002,7 +1002,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1022,7 +1022,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
index 1149f16..9629768 100644
--- a/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -83,7 +83,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -138,7 +138,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -184,7 +184,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -230,7 +230,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -276,7 +276,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -473,7 +473,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -519,7 +519,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -591,7 +591,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -611,7 +611,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -778,7 +778,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -798,7 +798,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -853,7 +853,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -899,7 +899,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1085,7 +1085,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1131,7 +1131,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1203,7 +1203,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1223,7 +1223,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample1.q.out b/ql/src/test/results/clientpositive/spark/sample1.q.out
index eb9d5f6..4bd5c8c 100644
--- a/ql/src/test/results/clientpositive/spark/sample1.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample1.q.out
@@ -85,7 +85,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample2.q.out b/ql/src/test/results/clientpositive/spark/sample2.q.out
index b13f818..fe9e2f5 100644
--- a/ql/src/test/results/clientpositive/spark/sample2.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample2.q.out
@@ -83,7 +83,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -104,7 +104,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample4.q.out b/ql/src/test/results/clientpositive/spark/sample4.q.out
index 69066c1..987a445 100644
--- a/ql/src/test/results/clientpositive/spark/sample4.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample4.q.out
@@ -83,7 +83,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -104,7 +104,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample5.q.out b/ql/src/test/results/clientpositive/spark/sample5.q.out
index 819939c..77477ba 100644
--- a/ql/src/test/results/clientpositive/spark/sample5.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample5.q.out
@@ -84,7 +84,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -105,7 +105,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample6.q.out b/ql/src/test/results/clientpositive/spark/sample6.q.out
index bf06004..2ed7d7a 100644
--- a/ql/src/test/results/clientpositive/spark/sample6.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample6.q.out
@@ -81,7 +81,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -102,7 +102,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -472,7 +472,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -493,7 +493,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -847,7 +847,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -868,7 +868,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1475,7 +1475,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1496,7 +1496,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1946,7 +1946,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1967,7 +1967,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -2404,7 +2404,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2425,7 +2425,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2450,7 +2450,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2471,7 +2471,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2709,7 +2709,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2730,7 +2730,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample7.q.out b/ql/src/test/results/clientpositive/spark/sample7.q.out
index a821c76..784000d 100644
--- a/ql/src/test/results/clientpositive/spark/sample7.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample7.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -103,7 +103,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
[25/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/outer_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.out
new file mode 100644
index 0000000..cf20851
--- /dev/null
+++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.out
@@ -0,0 +1,683 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
+ TableScan
+ alias: b
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /src [$hdt$_0:a]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
+ /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
+ /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b]
+ /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ filter mappings:
+ 1 [0, 1]
+ filter predicates:
+ 0
+ 1 {(VALUE._col1 = '2008-04-08')}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+17 val_17 17 val_17
+17 val_17 17 val_17
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+19 val_19 19 val_19
+19 val_19 19 val_19
+PREHOOK: query: EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
+ TableScan
+ alias: b
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /src [$hdt$_0:a]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
+ /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
+ Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+17 val_17 17 val_17
+17 val_17 17 val_17
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+19 val_19 19 val_19
+19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out b/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out
deleted file mode 100644
index 825e668..0000000
--- a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.7.out
+++ /dev/null
@@ -1,70 +0,0 @@
-PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE IF EXISTS parquet_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE IF EXISTS parquet_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
-PREHOOK: type: CREATETABLE_AS_SELECT
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: database:default
-PREHOOK: Output: default@parquet_table
-POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
-POSTHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@parquet_table
-POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ]
-PREHOOK: query: SELECT * FROM parquet_table
-PREHOOK: type: QUERY
-PREHOOK: Input: default@parquet_table
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM parquet_table
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@parquet_table
-#### A masked pattern was here ####
-{"key4":null,"key3":"val3"}
-{"key4":null,"key3":"val3"}
-{"key2":"val2","key1":null}
-{"key4":null,"key3":"val3"}
-{"key4":null,"key3":"val3"}
-PREHOOK: query: DROP TABLE avro_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: DROP TABLE avro_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: DROP TABLE parquet_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@parquet_table
-PREHOOK: Output: default@parquet_table
-POSTHOOK: query: DROP TABLE parquet_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@parquet_table
-POSTHOOK: Output: default@parquet_table
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out b/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out
deleted file mode 100644
index 1462cc2..0000000
--- a/ql/src/test/results/clientpositive/parquet_map_null.q.java1.8.out
+++ /dev/null
@@ -1,70 +0,0 @@
-PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE IF EXISTS parquet_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE IF EXISTS parquet_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
-PREHOOK: type: CREATETABLE_AS_SELECT
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: database:default
-PREHOOK: Output: default@parquet_table
-POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
-POSTHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@parquet_table
-POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ]
-PREHOOK: query: SELECT * FROM parquet_table
-PREHOOK: type: QUERY
-PREHOOK: Input: default@parquet_table
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM parquet_table
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@parquet_table
-#### A masked pattern was here ####
-{"key3":"val3","key4":null}
-{"key3":"val3","key4":null}
-{"key1":null,"key2":"val2"}
-{"key3":"val3","key4":null}
-{"key3":"val3","key4":null}
-PREHOOK: query: DROP TABLE avro_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: DROP TABLE avro_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: DROP TABLE parquet_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@parquet_table
-PREHOOK: Output: default@parquet_table
-POSTHOOK: query: DROP TABLE parquet_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@parquet_table
-POSTHOOK: Output: default@parquet_table
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/parquet_map_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parquet_map_null.q.out b/ql/src/test/results/clientpositive/parquet_map_null.q.out
new file mode 100644
index 0000000..d1357c1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/parquet_map_null.q.out
@@ -0,0 +1,68 @@
+PREHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
+
+DROP TABLE IF EXISTS avro_table
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: -- This test attempts to write a parquet table from an avro table that contains map null values
+
+DROP TABLE IF EXISTS avro_table
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE IF EXISTS parquet_table
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE IF EXISTS parquet_table
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_table
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@avro_table
+PREHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@avro_table
+PREHOOK: Output: database:default
+PREHOOK: Output: default@parquet_table
+POSTHOOK: query: CREATE TABLE parquet_table STORED AS PARQUET AS SELECT * FROM avro_table
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@avro_table
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@parquet_table
+POSTHOOK: Lineage: parquet_table.avreau_col_1 SIMPLE [(avro_table)avro_table.FieldSchema(name:avreau_col_1, type:map<string,string>, comment:), ]
+PREHOOK: query: SELECT * FROM parquet_table
+PREHOOK: type: QUERY
+PREHOOK: Input: default@parquet_table
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM parquet_table
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@parquet_table
+#### A masked pattern was here ####
+{"key3":"val3","key4":null}
+{"key3":"val3","key4":null}
+{"key1":null,"key2":"val2"}
+{"key3":"val3","key4":null}
+{"key3":"val3","key4":null}
+PREHOOK: query: DROP TABLE avro_table
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@avro_table
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: DROP TABLE avro_table
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@avro_table
+POSTHOOK: Output: default@avro_table
+PREHOOK: query: DROP TABLE parquet_table
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@parquet_table
+PREHOOK: Output: default@parquet_table
+POSTHOOK: query: DROP TABLE parquet_table
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@parquet_table
+POSTHOOK: Output: default@parquet_table
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/plan_json.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out b/ql/src/test/results/clientpositive/plan_json.q.java1.7.out
deleted file mode 100644
index dda4adc..0000000
--- a/ql/src/test/results/clientpositive/plan_json.q.java1.7.out
+++ /dev/null
@@ -1,13 +0,0 @@
-PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN FORMATTED SELECT count(1) FROM src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN FORMATTED SELECT count(1) FROM src
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/plan_json.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/plan_json.q.java1.8.out b/ql/src/test/results/clientpositive/plan_json.q.java1.8.out
deleted file mode 100644
index dda4adc..0000000
--- a/ql/src/test/results/clientpositive/plan_json.q.java1.8.out
+++ /dev/null
@@ -1,13 +0,0 @@
-PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN FORMATTED SELECT count(1) FROM src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN FORMATTED SELECT count(1) FROM src
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/plan_json.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/plan_json.q.out b/ql/src/test/results/clientpositive/plan_json.q.out
new file mode 100644
index 0000000..98c6626
--- /dev/null
+++ b/ql/src/test/results/clientpositive/plan_json.q.out
@@ -0,0 +1,11 @@
+PREHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
+
+
+EXPLAIN FORMATTED SELECT count(1) FROM src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- explain plan json: the query gets the formatted json output of the query plan of the hive query
+
+
+EXPLAIN FORMATTED SELECT count(1) FROM src
+POSTHOOK: type: QUERY
+{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-0":{"DEPENDENT STAGES":"Stage-1"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Select Operator":{"Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Group By Operator":{"aggregations:":["count(1)"],"mode:":"hash","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","value expressions:":"_col0 (type: bigint)"}}}}}}}}],"Reduce Operator Tree:":{"Group By Operator":{"aggregations:":["count(VALUE._col0)"],"mode:":"mergepartial","outputColumnNames:":["_col0"],"Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: COMPLETE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out b/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out
deleted file mode 100644
index b3a58d0..0000000
--- a/ql/src/test/results/clientpositive/spark/join0.q.java1.7.out
+++ /dev/null
@@ -1,238 +0,0 @@
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out b/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out
deleted file mode 100644
index 7acd108..0000000
--- a/ql/src/test/results/clientpositive/spark/join0.q.java1.8.out
+++ /dev/null
@@ -1,238 +0,0 @@
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/join0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join0.q.out b/ql/src/test/results/clientpositive/spark/join0.q.out
index 56b154f..bc98bb4 100644
--- a/ql/src/test/results/clientpositive/spark/join0.q.out
+++ b/ql/src/test/results/clientpositive/spark/join0.q.out
@@ -1,5 +1,7 @@
Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
SELECT src1.key as k1, src1.value as v1,
src2.key as k2, src2.value as v2 FROM
(SELECT * FROM src WHERE src.key < 10) src1
@@ -7,7 +9,9 @@ SELECT src1.key as k1, src1.value as v1,
(SELECT * FROM src WHERE src.key < 10) src2
SORT BY k1, v1, k2, v2
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
SELECT src1.key as k1, src1.value as v1,
src2.key as k2, src2.value as v2 FROM
(SELECT * FROM src WHERE src.key < 10) src1
@@ -24,7 +28,7 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 4)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -64,9 +68,9 @@ STAGE PLANS:
Join Operator
condition map:
Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1}
- 1 {VALUE._col0} {VALUE._col1}
+ keys:
+ 0
+ 1
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
@@ -83,8 +87,8 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out
deleted file mode 100644
index 3040544..0000000
--- a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.7.out
+++ /dev/null
@@ -1,252 +0,0 @@
-PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5520
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [51], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51}
-Storage Desc Params:
- serialization.format 1
[04/48] hive git commit: HIVE-13513: cleardanglingscratchdir does not
work in some version of HDFS (Daniel Dai, reviewed by Thejas Nair)
Posted by sp...@apache.org.
HIVE-13513: cleardanglingscratchdir does not work in some version of HDFS (Daniel Dai, reviewed by Thejas Nair)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/13428845
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/13428845
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/13428845
Branch: refs/heads/java8
Commit: 1342884528453ea710e5a61d67762e35a2be129b
Parents: ae6ad6d
Author: Daniel Dai <da...@hortonworks.com>
Authored: Wed May 25 15:23:57 2016 -0700
Committer: Daniel Dai <da...@hortonworks.com>
Committed: Wed May 25 15:23:57 2016 -0700
----------------------------------------------------------------------
.../hadoop/hive/ql/session/ClearDanglingScratchDir.java | 6 ++++++
.../org/apache/hadoop/hive/ql/session/SessionState.java | 9 ++++++---
2 files changed, 12 insertions(+), 3 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/13428845/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java b/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
index ee012c2..725f954 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
@@ -30,6 +30,8 @@ import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.protocol.AlreadyBeingCreatedException;
+import org.apache.hadoop.hive.common.LogUtils;
+import org.apache.hadoop.hive.common.LogUtils.LogInitializationException;
import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.ipc.RemoteException;
@@ -52,6 +54,10 @@ import org.apache.hadoop.ipc.RemoteException;
public class ClearDanglingScratchDir {
public static void main(String[] args) throws Exception {
+ try {
+ LogUtils.initHiveLog4j();
+ } catch (LogInitializationException e) {
+ }
Options opts = createOptions();
CommandLine cli = new GnuParser().parse(opts, args);
http://git-wip-us.apache.org/repos/asf/hive/blob/13428845/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
index 37ef165..ce43f7d 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
@@ -109,6 +109,7 @@ public class SessionState {
private static final String HDFS_SESSION_PATH_KEY = "_hive.hdfs.session.path";
private static final String TMP_TABLE_SPACE_KEY = "_hive.tmp_table_space";
static final String LOCK_FILE_NAME = "inuse.lck";
+ static final String INFO_FILE_NAME = "inuse.info";
private final Map<String, Map<String, Table>> tempTables = new HashMap<String, Map<String, Table>>();
private final Map<String, Map<String, ColumnStatisticsObj>> tempTableColStats =
@@ -643,10 +644,12 @@ public class SessionState {
// 5. hold a lock file in HDFS session dir to indicate the it is in use
if (conf.getBoolVar(HiveConf.ConfVars.HIVE_SCRATCH_DIR_LOCK)) {
FileSystem fs = hdfsSessionPath.getFileSystem(conf);
+ FSDataOutputStream hdfsSessionPathInfoFile = fs.create(new Path(hdfsSessionPath, INFO_FILE_NAME),
+ true);
+ hdfsSessionPathInfoFile.writeUTF("process: " + ManagementFactory.getRuntimeMXBean().getName()
+ +"\n");
+ hdfsSessionPathInfoFile.close();
hdfsSessionPathLockFile = fs.create(new Path(hdfsSessionPath, LOCK_FILE_NAME), true);
- hdfsSessionPathLockFile.writeUTF("hostname: " + InetAddress.getLocalHost().getHostName() + "\n");
- hdfsSessionPathLockFile.writeUTF("process: " + ManagementFactory.getRuntimeMXBean().getName() + "\n");
- hdfsSessionPathLockFile.hsync();
}
// 6. Local session path
localSessionPath = new Path(HiveConf.getVar(conf, HiveConf.ConfVars.LOCALSCRATCHDIR), sessionId);
[34/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out
deleted file mode 100644
index c15c6a2..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.7.out
+++ /dev/null
@@ -1,813 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103, [484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 1000
- rawDataSize 9624
- totalSize 10786
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103, [484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10786
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.8.out
deleted file mode 100644
index d484626..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_4.q.java1.8.out
+++ /dev/null
@@ -1,915 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 1000
- rawDataSize 9624
- totalSize 10786
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_static_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10786
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
[28/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out
deleted file mode 100644
index 752ea4e..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.7.out
+++ /dev/null
@@ -1,813 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 1000
- rawDataSize 9624
- totalSize 10786
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10786
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.8.out
deleted file mode 100644
index 599d3b0..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.java1.8.out
+++ /dev/null
@@ -1,915 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns. merge.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103:
--- 99 000000_0
--- 99 000001_0
--- after merge
--- 142 000000_0
--- ds=2008-04-08/hr=11/key=484:
--- 87 000000_0
--- 87 000001_0
--- after merge
--- 118 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 1000
- rawDataSize 9624
- totalSize 10786
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_static_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10786
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
[05/48] hive git commit: HIVE-12279: Testcase to verify session
temporary files are removed after HIVE-11768
Posted by sp...@apache.org.
HIVE-12279: Testcase to verify session temporary files are removed after HIVE-11768
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/d2dac26d
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/d2dac26d
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/d2dac26d
Branch: refs/heads/java8
Commit: d2dac26dfa7a93fb15fae08a4eaff923495d287b
Parents: 1342884
Author: Daniel Dai <da...@hortonworks.com>
Authored: Wed May 25 15:44:32 2016 -0700
Committer: Daniel Dai <da...@hortonworks.com>
Committed: Wed May 25 15:44:32 2016 -0700
----------------------------------------------------------------------
.../service/cli/session/TestSessionCleanup.java | 77 ++++++++++++++++++++
1 file changed, 77 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/d2dac26d/service/src/test/org/apache/hive/service/cli/session/TestSessionCleanup.java
----------------------------------------------------------------------
diff --git a/service/src/test/org/apache/hive/service/cli/session/TestSessionCleanup.java b/service/src/test/org/apache/hive/service/cli/session/TestSessionCleanup.java
new file mode 100644
index 0000000..e38a52a
--- /dev/null
+++ b/service/src/test/org/apache/hive/service/cli/session/TestSessionCleanup.java
@@ -0,0 +1,77 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hive.service.cli.session;
+
+import java.io.File;
+import java.io.FilenameFilter;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.HashSet;
+import java.util.Set;
+
+import junit.framework.TestCase;
+
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.conf.HiveConf.ConfVars;
+import org.apache.hive.service.cli.SessionHandle;
+import org.apache.hive.service.cli.thrift.EmbeddedThriftBinaryCLIService;
+import org.apache.hive.service.cli.thrift.ThriftCLIServiceClient;
+import org.junit.Assert;
+import org.junit.Test;
+
+public class TestSessionCleanup extends TestCase {
+
+ @Test
+ // This is to test session temporary files are cleaned up after HIVE-11768
+ public void testTempSessionFileCleanup() throws Exception {
+ EmbeddedThriftBinaryCLIService service = new EmbeddedThriftBinaryCLIService();
+ service.init(null);
+ ThriftCLIServiceClient client = new ThriftCLIServiceClient(service);
+
+ Set<String> existingPipeoutFiles = new HashSet<String>(Arrays.asList(getPipeoutFiles()));
+ SessionHandle sessionHandle = client.openSession("user1", "foobar",
+ Collections.<String, String>emptyMap());
+ client.executeStatement(sessionHandle, "set a=b", null);
+ File operationLogRootDir = new File(
+ new HiveConf().getVar(ConfVars.HIVE_SERVER2_LOGGING_OPERATION_LOG_LOCATION));
+ Assert.assertNotEquals(operationLogRootDir.list().length, 0);
+ client.closeSession(sessionHandle);
+
+ // Check if session files are removed
+ Assert.assertEquals(operationLogRootDir.list().length, 0);
+
+ // Check if the pipeout files are removed
+ Set<String> finalPipeoutFiles = new HashSet<String>(Arrays.asList(getPipeoutFiles()));
+ finalPipeoutFiles.removeAll(existingPipeoutFiles);
+ Assert.assertTrue(finalPipeoutFiles.isEmpty());
+ }
+
+ private String[] getPipeoutFiles() {
+ File localScratchDir = new File(
+ new HiveConf().getVar(HiveConf.ConfVars.LOCALSCRATCHDIR));
+ String[] pipeoutFiles = localScratchDir.list(new FilenameFilter() {
+ @Override
+ public boolean accept(File dir, String name) {
+ if (name.endsWith("pipeout")) return true;
+ return false;
+ }
+ });
+ return pipeoutFiles;
+ }
+}
[45/48] hive git commit: HIVE-13409: Fix JDK8 test failures related
to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
index 9e9e61f..4352914 100644
--- a/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
+++ b/ql/src/test/results/clientpositive/ppr_allchildsarenull.q.out
@@ -70,7 +70,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -116,7 +116,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -259,7 +259,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -305,7 +305,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -351,7 +351,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -397,7 +397,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out
index e03c055..f3fd8f8 100644
--- a/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out
+++ b/ql/src/test/results/clientpositive/rand_partitionpruner1.q.out
@@ -55,7 +55,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -75,7 +75,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out
index de1d6f4..df42672 100644
--- a/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out
+++ b/ql/src/test/results/clientpositive/rand_partitionpruner2.q.out
@@ -87,7 +87,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -133,7 +133,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out
index eabf9d9..6377e95 100644
--- a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out
+++ b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out
@@ -21,7 +21,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -109,7 +109,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/reduce_deduplicate.q.out b/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
index 075336b..dfcbd7d 100644
--- a/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
+++ b/ql/src/test/results/clientpositive/reduce_deduplicate.q.out
@@ -49,7 +49,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -69,7 +69,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/regexp_extract.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/regexp_extract.q.out b/ql/src/test/results/clientpositive/regexp_extract.q.out
index 7026df3..fb7794c 100644
--- a/ql/src/test/results/clientpositive/regexp_extract.q.out
+++ b/ql/src/test/results/clientpositive/regexp_extract.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -88,7 +88,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -317,7 +317,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -337,7 +337,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/router_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/router_join_ppr.q.out b/ql/src/test/results/clientpositive/router_join_ppr.q.out
index 1f79be9..bf46fe9 100644
--- a/ql/src/test/results/clientpositive/router_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/router_join_ppr.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -99,7 +99,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -126,7 +126,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -172,7 +172,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -218,7 +218,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -264,7 +264,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -474,7 +474,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -494,7 +494,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -521,7 +521,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -567,7 +567,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -770,7 +770,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -790,7 +790,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -817,7 +817,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -863,7 +863,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1062,7 +1062,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1082,7 +1082,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1109,7 +1109,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1155,7 +1155,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample1.q.out b/ql/src/test/results/clientpositive/sample1.q.out
index 57e61b9..f57519b 100644
--- a/ql/src/test/results/clientpositive/sample1.q.out
+++ b/ql/src/test/results/clientpositive/sample1.q.out
@@ -87,7 +87,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample2.q.out b/ql/src/test/results/clientpositive/sample2.q.out
index 92f0d5a..096805d 100644
--- a/ql/src/test/results/clientpositive/sample2.q.out
+++ b/ql/src/test/results/clientpositive/sample2.q.out
@@ -85,7 +85,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -106,7 +106,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample4.q.out b/ql/src/test/results/clientpositive/sample4.q.out
index b4e58c5..72395c9 100644
--- a/ql/src/test/results/clientpositive/sample4.q.out
+++ b/ql/src/test/results/clientpositive/sample4.q.out
@@ -85,7 +85,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -106,7 +106,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample5.q.out b/ql/src/test/results/clientpositive/sample5.q.out
index c786f21..147a567 100644
--- a/ql/src/test/results/clientpositive/sample5.q.out
+++ b/ql/src/test/results/clientpositive/sample5.q.out
@@ -86,7 +86,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -107,7 +107,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample6.q.out b/ql/src/test/results/clientpositive/sample6.q.out
index 519647f..a34258d 100644
--- a/ql/src/test/results/clientpositive/sample6.q.out
+++ b/ql/src/test/results/clientpositive/sample6.q.out
@@ -83,7 +83,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -104,7 +104,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -652,7 +652,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -673,7 +673,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1021,7 +1021,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1042,7 +1042,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1643,7 +1643,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -1664,7 +1664,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -2108,7 +2108,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -2129,7 +2129,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -2560,7 +2560,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2581,7 +2581,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2606,7 +2606,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2627,7 +2627,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2859,7 +2859,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
@@ -2880,7 +2880,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 4
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample7.q.out b/ql/src/test/results/clientpositive/sample7.q.out
index 2352cdc..51a45dd 100644
--- a/ql/src/test/results/clientpositive/sample7.q.out
+++ b/ql/src/test/results/clientpositive/sample7.q.out
@@ -84,7 +84,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -105,7 +105,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample8.q.out b/ql/src/test/results/clientpositive/sample8.q.out
index dd55fa0..b316331 100644
--- a/ql/src/test/results/clientpositive/sample8.q.out
+++ b/ql/src/test/results/clientpositive/sample8.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -114,7 +114,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -160,7 +160,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -206,7 +206,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/sample9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample9.q.out b/ql/src/test/results/clientpositive/sample9.q.out
index 14a512a..a4c3ff6 100644
--- a/ql/src/test/results/clientpositive/sample9.q.out
+++ b/ql/src/test/results/clientpositive/sample9.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count 2
bucket_field_name key
columns key,value
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/schema_evol_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/schema_evol_stats.q.out b/ql/src/test/results/clientpositive/schema_evol_stats.q.out
index 63dab2e..63b4c19 100644
--- a/ql/src/test/results/clientpositive/schema_evol_stats.q.out
+++ b/ql/src/test/results/clientpositive/schema_evol_stats.q.out
@@ -109,7 +109,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 40
@@ -150,7 +150,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 56
@@ -309,7 +309,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 384
@@ -350,7 +350,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 732
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/serde_user_properties.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/serde_user_properties.q.out b/ql/src/test/results/clientpositive/serde_user_properties.q.out
index 1dbc274..d5b81ed 100644
--- a/ql/src/test/results/clientpositive/serde_user_properties.q.out
+++ b/ql/src/test/results/clientpositive/serde_user_properties.q.out
@@ -101,7 +101,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -121,7 +121,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -225,7 +225,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -246,7 +246,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -351,7 +351,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -372,7 +372,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/bucket2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket2.q.out b/ql/src/test/results/clientpositive/spark/bucket2.q.out
index f9d4782..dd23a25 100644
--- a/ql/src/test/results/clientpositive/spark/bucket2.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket2.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -77,7 +77,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/bucket3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket3.q.out b/ql/src/test/results/clientpositive/spark/bucket3.q.out
index 39d9c33..f4acd71 100644
--- a/ql/src/test/results/clientpositive/spark/bucket3.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket3.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -77,7 +77,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/bucket4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket4.q.out b/ql/src/test/results/clientpositive/spark/bucket4.q.out
index 68f8143..b1ef928 100644
--- a/ql/src/test/results/clientpositive/spark/bucket4.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket4.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -74,7 +74,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ctas.q.out b/ql/src/test/results/clientpositive/spark/ctas.q.out
index 5396ada..f7165fc 100644
--- a/ql/src/test/results/clientpositive/spark/ctas.q.out
+++ b/ql/src/test/results/clientpositive/spark/ctas.q.out
@@ -720,7 +720,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -740,7 +740,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/disable_merge_for_bucketing.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/disable_merge_for_bucketing.q.out b/ql/src/test/results/clientpositive/spark/disable_merge_for_bucketing.q.out
index c8503cd..8cefe46 100644
--- a/ql/src/test/results/clientpositive/spark/disable_merge_for_bucketing.q.out
+++ b/ql/src/test/results/clientpositive/spark/disable_merge_for_bucketing.q.out
@@ -53,7 +53,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -73,7 +73,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/groupby_map_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_map_ppr.q.out b/ql/src/test/results/clientpositive/spark/groupby_map_ppr.q.out
index f97f63e..beae497 100644
--- a/ql/src/test/results/clientpositive/spark/groupby_map_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/groupby_map_ppr.q.out
@@ -73,7 +73,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -119,7 +119,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/groupby_map_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_map_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/groupby_map_ppr_multi_distinct.q.out
index c833657..2ad4d68 100644
--- a/ql/src/test/results/clientpositive/spark/groupby_map_ppr_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/spark/groupby_map_ppr_multi_distinct.q.out
@@ -73,7 +73,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -119,7 +119,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/groupby_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_ppr.q.out b/ql/src/test/results/clientpositive/spark/groupby_ppr.q.out
index a2c2ced..f1e1027 100644
--- a/ql/src/test/results/clientpositive/spark/groupby_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/groupby_ppr.q.out
@@ -66,7 +66,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -112,7 +112,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
index 531854b..5251241 100644
--- a/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/spark/groupby_ppr_multi_distinct.q.out
@@ -66,7 +66,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -112,7 +112,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/input_part2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/input_part2.q.out b/ql/src/test/results/clientpositive/spark/input_part2.q.out
index 4799a7f..36bb40f 100644
--- a/ql/src/test/results/clientpositive/spark/input_part2.q.out
+++ b/ql/src/test/results/clientpositive/spark/input_part2.q.out
@@ -136,7 +136,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -182,7 +182,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join17.q.out b/ql/src/test/results/clientpositive/spark/join17.q.out
index 3acf7f9..a7103cb 100644
--- a/ql/src/test/results/clientpositive/spark/join17.q.out
+++ b/ql/src/test/results/clientpositive/spark/join17.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -82,7 +82,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -134,7 +134,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -154,7 +154,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join26.q.out b/ql/src/test/results/clientpositive/spark/join26.q.out
index 4967ab6..cacfe42 100644
--- a/ql/src/test/results/clientpositive/spark/join26.q.out
+++ b/ql/src/test/results/clientpositive/spark/join26.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -80,7 +80,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -127,7 +127,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -147,7 +147,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -245,7 +245,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join32.q.out b/ql/src/test/results/clientpositive/spark/join32.q.out
index be29cd5..7cecbc6 100644
--- a/ql/src/test/results/clientpositive/spark/join32.q.out
+++ b/ql/src/test/results/clientpositive/spark/join32.q.out
@@ -67,7 +67,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -87,7 +87,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -137,7 +137,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -157,7 +157,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -267,7 +267,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
index 8a99a56..97c520c 100644
--- a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
+++ b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
@@ -75,7 +75,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -95,7 +95,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -145,7 +145,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -165,7 +165,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -275,7 +275,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -518,7 +518,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -538,7 +538,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -604,7 +604,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -624,7 +624,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -674,7 +674,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -694,7 +694,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -801,7 +801,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -821,7 +821,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1043,7 +1043,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1112,7 +1112,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1132,7 +1132,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1243,7 +1243,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1263,7 +1263,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1487,7 +1487,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1552,7 +1552,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1572,7 +1572,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1683,7 +1683,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1703,7 +1703,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/join33.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join33.q.out b/ql/src/test/results/clientpositive/spark/join33.q.out
index be29cd5..7cecbc6 100644
--- a/ql/src/test/results/clientpositive/spark/join33.q.out
+++ b/ql/src/test/results/clientpositive/spark/join33.q.out
@@ -67,7 +67,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -87,7 +87,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -137,7 +137,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -157,7 +157,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -267,7 +267,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
[26/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
new file mode 100644
index 0000000..fc8eb1c
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
@@ -0,0 +1,216 @@
+PREHOOK: query: DROP TABLE over1k
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE over1k
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE over1korc
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE over1korc
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: -- data setup
+CREATE TABLE over1k(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@over1k
+POSTHOOK: query: -- data setup
+CREATE TABLE over1k(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@over1k
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@over1k
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@over1k
+PREHOOK: query: CREATE TABLE over1korc(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@over1korc
+POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@over1korc
+PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
+PREHOOK: type: QUERY
+PREHOOK: Input: default@over1k
+PREHOOK: Output: default@over1korc
+POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@over1k
+POSTHOOK: Output: default@over1korc
+POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
+POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
+POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
+POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
+POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
+POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
+POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
+POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
+POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
+POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
+POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
+PREHOOK: query: EXPLAIN SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1korc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: i (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(50), avg(50.0), avg(50)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
+ Reducer 3
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 10
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@over1korc
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@over1korc
+#### A masked pattern was here ####
+65536 50.0 50.0 50.0000
+65537 50.0 50.0 50.0000
+65538 50.0 50.0 50.0000
+65539 50.0 50.0 50.0000
+65540 50.0 50.0 50.0000
+65541 50.0 50.0 50.0000
+65542 50.0 50.0 50.0000
+65543 50.0 50.0 50.0000
+65544 50.0 50.0 50.0000
+65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out
deleted file mode 100644
index 1312e53..0000000
--- a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out
+++ /dev/null
@@ -1,685 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [$hdt$_0:a]
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
-PREHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [$hdt$_0:a]
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out
deleted file mode 100644
index b9c1a66..0000000
--- a/ql/src/test/results/clientpositive/outer_join_ppr.q.java1.8.out
+++ /dev/null
@@ -1,855 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- AND
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [$hdt$_0:$hdt$_1:a]
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_0:$hdt$_0:b]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_0:$hdt$_0:b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Outer Join 0 to 1
- filter mappings:
- 0 [1, 1]
- filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) and (UDFToDouble(_col0) > 15.0)) and (UDFToDouble(_col0) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
-PREHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [$hdt$_0:$hdt$_1:a]
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:$hdt$_0:b]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:$hdt$_0:b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
[31/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out
deleted file mode 100644
index 1960d41..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.8.out
+++ /dev/null
@@ -1,1119 +0,0 @@
-PREHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- TOK_FUNCTION
- if
- ==
- %
- TOK_TABLE_OR_COL
- key
- 100
- 0
- 'a1'
- 'b1'
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 2
- numRows 16
- rawDataSize 136
- totalSize 310
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 984
- rawDataSize 9488
- totalSize 10734
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- TOK_FUNCTION
- if
- ==
- %
- TOK_TABLE_OR_COL
- key
- 100
- 0
- 'a1'
- 'b1'
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 1
- numRows 16
- rawDataSize 136
- totalSize 254
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 984
- rawDataSize 9488
- totalSize 10622
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_dynamic_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr a1
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 1
- numRows 16
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 136
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 254
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr b1
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 4
- numRows 984
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9488
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10622
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-484 val_484 2008-04-08 b1
-484 val_484 2008-04-08 b1
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
[38/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/join0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join0.q.out b/ql/src/test/results/clientpositive/join0.q.out
new file mode 100644
index 0000000..59122e2
--- /dev/null
+++ b/ql/src/test/results/clientpositive/join0.q.out
@@ -0,0 +1,238 @@
+Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}},{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COM
PLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","outp
ut format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"}}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoo
p.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
+Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 9 val_9
+0 val_0 9 val_9
+0 val_0 9 val_9
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 2 val_2
+2 val_2 4 val_4
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 8 val_8
+2 val_2 9 val_9
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 2 val_2
+4 val_4 4 val_4
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 8 val_8
+4 val_4 9 val_9
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 9 val_9
+5 val_5 9 val_9
+5 val_5 9 val_9
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 2 val_2
+8 val_8 4 val_4
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 8 val_8
+8 val_8 9 val_9
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 2 val_2
+9 val_9 4 val_4
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 8 val_8
+9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.7.out
deleted file mode 100644
index 8447e86..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.7.out
+++ /dev/null
@@ -1,361 +0,0 @@
-PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5520
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [51], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484, [103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51}
-Storage Desc Params:
- serialization.format 1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.8.out
deleted file mode 100644
index d1b9598..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.java1.8.out
+++ /dev/null
@@ -1,389 +0,0 @@
-PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- src
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 0
- rawDataSize 0
- totalSize 5520
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [51], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
-Storage Desc Params:
- serialization.format 1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
new file mode 100644
index 0000000..d4681b7
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_10.q.out
@@ -0,0 +1,359 @@
+PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','51','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','51','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+ Stage-5
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-5
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 4812
+ totalSize 5520
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key]
+Skewed Values: [[484], [51], [103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
+Storage Desc Params:
+ serialization.format 1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out
deleted file mode 100644
index b58d17c..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.7.out
+++ /dev/null
@@ -1,329 +0,0 @@
-PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (value) on ('val_466','val_287','val_82')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (value) on ('val_466','val_287','val_82')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [value]
-Skewed Values: [[val_466], [val_287], [val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[val_82]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_82, [val_287]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_287, [val_466]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_466}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 4812
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 5522
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (value = 'val_466') (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), 'val_466' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-466 val_466
-466 val_466
-466 val_466
-PREHOOK: query: drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
[32/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
new file mode 100644
index 0000000..09cb847
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_5.q.out
@@ -0,0 +1,504 @@
+PREHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+stored as DIRECTORIES
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- list bucketing DML: multiple skewed columns. 2 stages
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+partitioned by (ds String, hr String)
+skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+stored as DIRECTORIES
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_dynamic_part
+PREHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.list_bucketing_dynamic_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.list_bucketing_dynamic_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds='2008-04-08', hr) select key, value, hr from srcpart where ds='2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=12).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- check DML result
+desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 3
+ numRows 500
+ rawDataSize 5312
+ totalSize 5812
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=11/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='12')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 12]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 3
+ numRows 500
+ rawDataSize 5312
+ totalSize 5812
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+InputFormat: org.apache.hadoop.mapred.TextInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=12/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds='2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds='2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from list_bucketing_dynamic_part where ds='2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select key, value from srcpart where ds='2008-04-08' and key = "103" and value ="val_103"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+103 val_103
+103 val_103
+103 val_103
+103 val_103
+PREHOOK: query: explain extended
+select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 3
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 3
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '103') and (value = 'val_103')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '103' (type: string), 'val_103' (type: string), '2008-04-08' (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select key, value, ds, hr from list_bucketing_dynamic_part where ds='2008-04-08' and key = "103" and value ="val_103"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+103 val_103 2008-04-08 11
+103 val_103 2008-04-08 11
+103 val_103 2008-04-08 12
+103 val_103 2008-04-08 12
+PREHOOK: query: -- clean up resources
+drop table list_bucketing_dynamic_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- clean up resources
+drop table list_bucketing_dynamic_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Output: default@list_bucketing_dynamic_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out
deleted file mode 100644
index c022618..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.java1.7.out
+++ /dev/null
@@ -1,1007 +0,0 @@
-PREHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 2
- numRows 16
- rawDataSize 136
- totalSize 310
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 984
- rawDataSize 9488
- totalSize 10734
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
- Stage-2 depends on stages: Stage-0
- Stage-3
- Stage-5
- Stage-6 depends on stages: Stage-5
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
- Stage: Stage-3
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-5
- Merge File Operator
- Map Operator Tree:
- RCFile Merge Operator
- merge level: block
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns hr
- partition_columns.types string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- Truncated Path -> Alias:
-#### A masked pattern was here ####
-
- Stage: Stage-6
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 1
- numRows 16
- rawDataSize 136
- totalSize 254
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 984
- rawDataSize 9488
- totalSize 10622
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_dynamic_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr a1
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 1
- numRows 16
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 136
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 254
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr b1
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 4
- numRows 984
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9488
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10622
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-484 val_484 2008-04-08 b1
-484 val_484 2008-04-08 b1
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
[29/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.8.out
deleted file mode 100644
index 9947c1a..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.8.out
+++ /dev/null
@@ -1,712 +0,0 @@
-PREHOOK: query: -- list bucketing alter table ... concatenate:
--- Use list bucketing DML to generate mutilple files in partitions by turning off merge
--- dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing alter table ... concatenate:
--- Use list bucketing DML to generate mutilple files in partitions by turning off merge
--- dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- TOK_FUNCTION
- if
- ==
- %
- TOK_TABLE_OR_COL
- key
- 100
- 0
- 'a1'
- 'b1'
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 2
- numRows 16
- rawDataSize 136
- totalSize 310
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 984
- rawDataSize 9488
- totalSize 10734
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- concatenate the partition and it will merge files
-alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
-PREHOOK: type: ALTER_PARTITION_MERGE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: query: -- concatenate the partition and it will merge files
-alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
-POSTHOOK: type: ALTER_PARTITION_MERGE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 3
- numRows 0
- rawDataSize 0
- totalSize 10586
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_dynamic_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_dynamic_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr a1
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 2
- numRows 16
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 136
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 310
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr b1
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 0
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 0
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10586
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 16 Data size: 136 Basic stats: PARTIAL Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-484 val_484 2008-04-08 b1
-484 val_484 2008-04-08 b1
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
new file mode 100644
index 0000000..ee36d3f
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.out
@@ -0,0 +1,639 @@
+PREHOOK: query: -- list bucketing alter table ... concatenate:
+-- Use list bucketing DML to generate mutilple files in partitions by turning off merge
+-- dynamic partition. multiple skewed columns. merge.
+-- The following explains merge example used in this test case
+-- DML will generated 2 partitions
+-- ds=2008-04-08/hr=a1
+-- ds=2008-04-08/hr=b1
+-- without merge, each partition has more files
+-- ds=2008-04-08/hr=a1 has 2 files
+-- ds=2008-04-08/hr=b1 has 6 files
+-- with merge each partition has more files
+-- ds=2008-04-08/hr=a1 has 1 files
+-- ds=2008-04-08/hr=b1 has 4 files
+-- The following shows file size and name in each directory
+-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 155 000000_0
+-- 155 000001_0
+-- with merge
+-- 254 000000_0
+-- hr=b1/key=103/value=val_103:
+-- without merge
+-- 99 000000_0
+-- 99 000001_0
+-- with merge
+-- 142 000001_0
+-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- with merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- hr=b1/key=484/value=val_484
+-- without merge
+-- 87 000000_0
+-- 87 000001_0
+-- with merge
+-- 118 000002_0
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- list bucketing alter table ... concatenate:
+-- Use list bucketing DML to generate mutilple files in partitions by turning off merge
+-- dynamic partition. multiple skewed columns. merge.
+-- The following explains merge example used in this test case
+-- DML will generated 2 partitions
+-- ds=2008-04-08/hr=a1
+-- ds=2008-04-08/hr=b1
+-- without merge, each partition has more files
+-- ds=2008-04-08/hr=a1 has 2 files
+-- ds=2008-04-08/hr=b1 has 6 files
+-- with merge each partition has more files
+-- ds=2008-04-08/hr=a1 has 1 files
+-- ds=2008-04-08/hr=b1 has 4 files
+-- The following shows file size and name in each directory
+-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 155 000000_0
+-- 155 000001_0
+-- with merge
+-- 254 000000_0
+-- hr=b1/key=103/value=val_103:
+-- without merge
+-- 99 000000_0
+-- 99 000001_0
+-- with merge
+-- 142 000001_0
+-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- with merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- hr=b1/key=484/value=val_484
+-- without merge
+-- 87 000000_0
+-- 87 000001_0
+-- with merge
+-- 118 000002_0
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_dynamic_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+ds=2008-04-08/hr=a1
+ds=2008-04-08/hr=b1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, a1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 2
+ numRows 16
+ rawDataSize 136
+ totalSize 310
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, b1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 6
+ numRows 984
+ rawDataSize 9488
+ totalSize 10734
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: -- concatenate the partition and it will merge files
+alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
+PREHOOK: type: ALTER_PARTITION_MERGE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+POSTHOOK: query: -- concatenate the partition and it will merge files
+alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
+POSTHOOK: type: ALTER_PARTITION_MERGE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, b1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ numFiles 3
+ numRows 984
+ rawDataSize 9488
+ totalSize 10586
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(*) from list_bucketing_dynamic_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+1000
+PREHOOK: query: explain extended
+select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr a1
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 2
+ numRows 16
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 136
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 310
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr b1
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 3
+ numRows 984
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 9488
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 10586
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+484 val_484 2008-04-08 b1
+484 val_484 2008-04-08 b1
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 12
+PREHOOK: query: -- clean up
+drop table list_bucketing_dynamic_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- clean up
+drop table list_bucketing_dynamic_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Output: default@list_bucketing_dynamic_part
[09/48] hive git commit: HIVE-13269: Simplify comparison expressions
using column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by sp...@apache.org.
HIVE-13269: Simplify comparison expressions using column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/76130a9d
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/76130a9d
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/76130a9d
Branch: refs/heads/java8
Commit: 76130a9d54d773619d3c525789d2e4ae590bfe4f
Parents: ba07055
Author: Jesus Camacho Rodriguez <jc...@apache.org>
Authored: Thu May 26 10:07:37 2016 +0100
Committer: Jesus Camacho Rodriguez <jc...@apache.org>
Committed: Thu May 26 10:07:37 2016 +0100
----------------------------------------------------------------------
.../org/apache/hadoop/hive/conf/HiveConf.java | 3 +
data/conf/perf-reg/hive-site.xml | 5 +
.../hive/ql/optimizer/calcite/HiveRexUtil.java | 24 +
.../HiveReduceExpressionsWithStatsRule.java | 330 ++++++++++
.../hadoop/hive/ql/parse/CalcitePlanner.java | 4 +
.../queries/clientpositive/remove_exprs_stats.q | 55 ++
.../clientpositive/remove_exprs_stats.q.out | 610 +++++++++++++++++++
7 files changed, 1031 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
index b1f37ff..6a404bd 100644
--- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
+++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java
@@ -1485,6 +1485,9 @@ public class HiveConf extends Configuration {
"When hive.optimize.limittranspose is true, this variable specifies the minimal reduction in the\n" +
"number of tuples of the outer input of the join or the input of the union that you should get in order to apply the rule."),
+ HIVE_OPTIMIZE_REDUCE_WITH_STATS("hive.optimize.filter.stats.reduction", false, "Whether to simplify comparison\n" +
+ "expressions in filter operators using column stats"),
+
HIVE_OPTIMIZE_SKEWJOIN_COMPILETIME("hive.optimize.skewjoin.compiletime", false,
"Whether to create a separate plan for skewed keys for the tables in the join.\n" +
"This is based on the skewed keys stored in the metadata. At compile time, the plan is broken\n" +
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/data/conf/perf-reg/hive-site.xml
----------------------------------------------------------------------
diff --git a/data/conf/perf-reg/hive-site.xml b/data/conf/perf-reg/hive-site.xml
index 9e929fc..012369f 100644
--- a/data/conf/perf-reg/hive-site.xml
+++ b/data/conf/perf-reg/hive-site.xml
@@ -277,4 +277,9 @@
<value>true</value>
</property>
+<property>
+ <name>hive.optimize.filter.stats.reduction</name>
+ <value>true</value>
+</property>
+
</configuration>
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRexUtil.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRexUtil.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRexUtil.java
index 6933fec..a5dcffb 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRexUtil.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/HiveRexUtil.java
@@ -420,6 +420,12 @@ public class HiveRexUtil {
private static RexCall invert(RexBuilder rexBuilder, RexCall call) {
switch (call.getKind()) {
+ case EQUALS:
+ return (RexCall) rexBuilder.makeCall(SqlStdOperatorTable.EQUALS,
+ Lists.reverse(call.getOperands()));
+ case NOT_EQUALS:
+ return (RexCall) rexBuilder.makeCall(SqlStdOperatorTable.NOT_EQUALS,
+ Lists.reverse(call.getOperands()));
case LESS_THAN:
return (RexCall) rexBuilder.makeCall(SqlStdOperatorTable.GREATER_THAN,
Lists.reverse(call.getOperands()));
@@ -469,6 +475,24 @@ public class HiveRexUtil {
}
}
+ public static SqlKind invert(SqlKind kind) {
+ switch (kind) {
+ case EQUALS:
+ return SqlKind.EQUALS;
+ case NOT_EQUALS:
+ return SqlKind.NOT_EQUALS;
+ case LESS_THAN:
+ return SqlKind.GREATER_THAN;
+ case GREATER_THAN:
+ return SqlKind.LESS_THAN;
+ case LESS_THAN_OR_EQUAL:
+ return SqlKind.GREATER_THAN_OR_EQUAL;
+ case GREATER_THAN_OR_EQUAL:
+ return SqlKind.LESS_THAN_OR_EQUAL;
+ }
+ return null;
+ }
+
public static class ExprSimplifier extends RexShuttle {
private final RexBuilder rexBuilder;
private final boolean unknownAsFalse;
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java
new file mode 100644
index 0000000..ec488fe
--- /dev/null
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveReduceExpressionsWithStatsRule.java
@@ -0,0 +1,330 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.hadoop.hive.ql.optimizer.calcite.rules;
+
+import java.math.BigDecimal;
+import java.util.EnumSet;
+import java.util.List;
+import java.util.Set;
+
+import org.apache.calcite.plan.RelOptRule;
+import org.apache.calcite.plan.RelOptRuleCall;
+import org.apache.calcite.rel.RelNode;
+import org.apache.calcite.rel.core.Filter;
+import org.apache.calcite.rel.metadata.RelColumnOrigin;
+import org.apache.calcite.rel.metadata.RelMetadataQuery;
+import org.apache.calcite.rex.RexBuilder;
+import org.apache.calcite.rex.RexCall;
+import org.apache.calcite.rex.RexInputRef;
+import org.apache.calcite.rex.RexLiteral;
+import org.apache.calcite.rex.RexNode;
+import org.apache.calcite.rex.RexShuttle;
+import org.apache.calcite.rex.RexUtil;
+import org.apache.calcite.sql.SqlKind;
+import org.apache.calcite.util.Pair;
+import org.apache.hadoop.hive.common.StatsSetupConst;
+import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRexUtil;
+import org.apache.hadoop.hive.ql.optimizer.calcite.RelOptHiveTable;
+import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveIn;
+import org.apache.hadoop.hive.ql.plan.ColStatistics;
+import org.apache.hadoop.hive.ql.plan.ColStatistics.Range;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.google.common.collect.Lists;
+
+/**
+ * This rule simplifies the condition in Filter operators using the
+ * column statistics (if available).
+ *
+ * For instance, given the following predicate:
+ * a > 5
+ * we can infer that the predicate will evaluate to false if the max
+ * value for column a is 4.
+ *
+ * Currently we support the simplification of =, >=, <=, >, <, and
+ * IN operations.
+ */
+public class HiveReduceExpressionsWithStatsRule extends RelOptRule {
+
+ protected static final Logger LOG = LoggerFactory.getLogger(
+ HiveReduceExpressionsWithStatsRule.class);
+
+ public static final HiveReduceExpressionsWithStatsRule INSTANCE =
+ new HiveReduceExpressionsWithStatsRule();
+
+ private static final Set<SqlKind> COMPARISON = EnumSet.of(SqlKind.EQUALS,
+ SqlKind.GREATER_THAN_OR_EQUAL,
+ SqlKind.LESS_THAN_OR_EQUAL,
+ SqlKind.GREATER_THAN,
+ SqlKind.LESS_THAN);
+
+ private HiveReduceExpressionsWithStatsRule() {
+ super(operand(Filter.class, operand(RelNode.class, any())));
+ }
+
+ @Override
+ public void onMatch(RelOptRuleCall call) {
+ final Filter filter = call.rel(0);
+
+ final RexBuilder rexBuilder = filter.getCluster().getRexBuilder();
+ final RelMetadataQuery metadataProvider = RelMetadataQuery.instance();
+
+ // 1. Recompose filter possibly by pulling out common elements from DNF
+ // expressions
+ RexNode newFilterCondition = RexUtil.pullFactors(rexBuilder, filter.getCondition());
+
+ // 2. Reduce filter with stats information
+ RexReplacer replacer = new RexReplacer(filter, rexBuilder, metadataProvider);
+ newFilterCondition = replacer.apply(newFilterCondition);
+
+ // 3. Transform if we have created a new filter operator
+ if (!filter.getCondition().toString().equals(newFilterCondition.toString())) {
+ Filter newFilter = filter.copy(filter.getTraitSet(), filter.getInput(), newFilterCondition);
+ call.transformTo(newFilter);
+ }
+
+ }
+
+ /**
+ * Replaces expressions with their reductions. Note that we only have to
+ * look for RexCall, since nothing else is reducible in the first place.
+ */
+ protected static class RexReplacer extends RexShuttle {
+ private final Filter filterOp;
+ private final RexBuilder rexBuilder;
+ private final RelMetadataQuery metadataProvider;
+
+ RexReplacer(Filter filterOp, RexBuilder rexBuilder, RelMetadataQuery metadataProvider) {
+ this.filterOp = filterOp;
+ this.rexBuilder = rexBuilder;
+ this.metadataProvider = metadataProvider;
+ }
+
+ @Override
+ public RexNode visitCall(RexCall call) {
+ if (COMPARISON.contains(call.getOperator().getKind())) {
+ RexInputRef ref = null;
+ RexLiteral literal = null;
+ SqlKind kind = null;
+ if (call.operands.get(0) instanceof RexInputRef
+ && call.operands.get(1) instanceof RexLiteral) {
+ ref = (RexInputRef) call.operands.get(0);
+ literal = (RexLiteral) call.operands.get(1);
+ kind = call.getOperator().getKind();
+ } else if (call.operands.get(1) instanceof RexInputRef
+ && call.operands.get(0) instanceof RexLiteral) {
+ ref = (RexInputRef) call.operands.get(1);
+ literal = (RexLiteral) call.operands.get(0);
+ kind = HiveRexUtil.invert(call.getOperator().getKind());
+ }
+
+ // Found an expression that we can try to reduce
+ Number max = null;
+ Number min = null;
+ if (ref != null && literal != null && kind != null) {
+ Pair<Number,Number> maxMin = extractMaxMin(ref);
+ max = maxMin.left;
+ min = maxMin.right;
+ }
+
+ if (max != null && min != null) {
+ // Stats were available, try to reduce
+ RexNode reduced = reduceCall(literal, kind, max, min);
+ if (reduced != null) {
+ return reduced;
+ }
+ }
+
+ // We cannot apply the reduction
+ return call;
+ } else if (call.getOperator().getKind() == SqlKind.IN) {
+ if (call.getOperands().get(0) instanceof RexInputRef) {
+ // Ref
+ RexInputRef ref = (RexInputRef) call.getOperands().get(0);
+ // Found an expression that we can try to reduce
+ Number max = null;
+ Number min = null;
+ if (ref != null) {
+ Pair<Number,Number> maxMin = extractMaxMin(ref);
+ max = maxMin.left;
+ min = maxMin.right;
+ }
+
+ if (max != null && min != null) {
+ // Stats were available, try to reduce
+ List<RexNode> newOperands = Lists.newArrayList();
+ newOperands.add(ref);
+ for (int i = 1; i < call.getOperands().size(); i++) {
+ RexNode operand = call.getOperands().get(i);
+ if (operand instanceof RexLiteral) {
+ RexLiteral literal = (RexLiteral) operand;
+ RexNode reduced = reduceCall(literal, SqlKind.EQUALS, max, min);
+ if (reduced != null) {
+ if (reduced.isAlwaysTrue()) {
+ return rexBuilder.makeLiteral(true);
+ }
+ } else {
+ newOperands.add(literal);
+ }
+ } else {
+ newOperands.add(operand);
+ }
+ }
+ if (newOperands.size() == 1) {
+ return rexBuilder.makeLiteral(false);
+ }
+ return rexBuilder.makeCall(HiveIn.INSTANCE, newOperands);
+ }
+ } else if (call.getOperands().get(0).getKind() == SqlKind.ROW) {
+ // Struct
+ RexCall struct = (RexCall) call.getOperands().get(0);
+ List<RexInputRef> refs = Lists.newArrayList();
+ List<Pair<Number,Number>> maxMinStats = Lists.newArrayList();
+ for (RexNode operand: struct.getOperands()) {
+ if (!(operand instanceof RexInputRef)) {
+ // Cannot simplify, we bail out
+ return call;
+ }
+ RexInputRef ref = (RexInputRef) operand;
+ refs.add(ref);
+ maxMinStats.add(extractMaxMin(ref));
+ }
+
+ // Try to reduce
+ List<RexNode> newOperands = Lists.newArrayList();
+ newOperands.add(struct);
+ for (int i = 1; i < call.getOperands().size(); i++) {
+ RexCall constStruct = (RexCall) call.getOperands().get(i);
+ boolean allTrue = true;
+ boolean addOperand = true;
+ for (int j = 0; i < constStruct.getOperands().size(); j++) {
+ RexNode operand = constStruct.getOperands().get(j);
+ if (operand instanceof RexLiteral) {
+ RexLiteral literal = (RexLiteral) operand;
+ RexNode reduced = reduceCall(literal, SqlKind.EQUALS,
+ maxMinStats.get(j).left, maxMinStats.get(j).right);
+ if (reduced != null) {
+ if (reduced.isAlwaysFalse()) {
+ allTrue = false;
+ addOperand = false;
+ break;
+ }
+ } else {
+ allTrue = false;
+ }
+ } else {
+ allTrue = false;
+ }
+ }
+ if (allTrue) {
+ return rexBuilder.makeLiteral(true);
+ }
+ if (addOperand) {
+ newOperands.add(constStruct);
+ }
+ }
+ if (newOperands.size() == 1) {
+ return rexBuilder.makeLiteral(false);
+ }
+ return rexBuilder.makeCall(HiveIn.INSTANCE, newOperands);
+ }
+
+ // We cannot apply the reduction
+ return call;
+ }
+
+ // If we did not reduce, check the children nodes
+ RexNode node = super.visitCall(call);
+ if (node != call) {
+ node = HiveRexUtil.simplify(rexBuilder, node);
+ }
+ return node;
+ }
+
+ private Pair<Number,Number> extractMaxMin(RexInputRef ref) {
+ Number max = null;
+ Number min = null;
+ RelColumnOrigin columnOrigin = this.metadataProvider.getColumnOrigin(filterOp, ref.getIndex());
+ if (columnOrigin != null) {
+ RelOptHiveTable table = (RelOptHiveTable) columnOrigin.getOriginTable();
+ if (table != null) {
+ ColStatistics colStats =
+ table.getColStat(Lists.newArrayList(columnOrigin.getOriginColumnOrdinal())).get(0);
+ if (colStats != null && StatsSetupConst.areColumnStatsUptoDate(
+ table.getHiveTableMD().getParameters(), colStats.getColumnName())) {
+ Range range = colStats.getRange();
+ if (range != null) {
+ max = range.maxValue;
+ min = range.minValue;
+ }
+ }
+ }
+ }
+ return Pair.<Number,Number>of(max, min);
+ }
+
+ @SuppressWarnings("unchecked")
+ private RexNode reduceCall(RexLiteral literal, SqlKind kind, Number max, Number min) {
+ // Stats were available, try to reduce
+ if (max != null && min != null) {
+ BigDecimal maxVal = new BigDecimal(max.floatValue());
+ BigDecimal minVal = new BigDecimal(min.floatValue());
+ RexLiteral maxLiteral = rexBuilder.makeExactLiteral(maxVal, literal.getType());
+ RexLiteral minLiteral = rexBuilder.makeExactLiteral(minVal, literal.getType());
+
+ // Equals
+ if (kind == SqlKind.EQUALS) {
+ if (minLiteral.getValue().compareTo(literal.getValue()) > 0 ||
+ maxLiteral.getValue().compareTo(literal.getValue()) < 0) {
+ return rexBuilder.makeLiteral(false);
+ }
+ }
+
+ // Greater than (or equal), and less than (or equal)
+ if (kind == SqlKind.GREATER_THAN) {
+ if (minLiteral.getValue().compareTo(literal.getValue()) > 0) {
+ return rexBuilder.makeLiteral(true);
+ } else if (maxLiteral.getValue().compareTo(literal.getValue()) <= 0) {
+ return rexBuilder.makeLiteral(false);
+ }
+ } else if (kind == SqlKind.GREATER_THAN_OR_EQUAL) {
+ if (minLiteral.getValue().compareTo(literal.getValue()) >= 0) {
+ return rexBuilder.makeLiteral(true);
+ } else if (maxLiteral.getValue().compareTo(literal.getValue()) < 0) {
+ return rexBuilder.makeLiteral(false);
+ }
+ } else if (kind == SqlKind.LESS_THAN) {
+ if (minLiteral.getValue().compareTo(literal.getValue()) >= 0) {
+ return rexBuilder.makeLiteral(false);
+ } else if (maxLiteral.getValue().compareTo(literal.getValue()) < 0) {
+ return rexBuilder.makeLiteral(true);
+ }
+ } else if (kind == SqlKind.LESS_THAN_OR_EQUAL) {
+ if (minLiteral.getValue().compareTo(literal.getValue()) > 0) {
+ return rexBuilder.makeLiteral(false);
+ } else if (maxLiteral.getValue().compareTo(literal.getValue()) <= 0) {
+ return rexBuilder.makeLiteral(true);
+ }
+ }
+ }
+ return null;
+ }
+ }
+
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
index 49e65e7..d084552 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java
@@ -161,6 +161,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveProjectFilterPullUp
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveProjectMergeRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveProjectSortTransposeRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveReduceExpressionsRule;
+import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveReduceExpressionsWithStatsRule;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveRelFieldTrimmer;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveRulesRegistry;
import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveSortJoinReduceRule;
@@ -1156,6 +1157,9 @@ public class CalcitePlanner extends SemanticAnalyzer {
rules.add(HiveFilterJoinRule.FILTER_ON_JOIN);
rules.add(new HiveFilterAggregateTransposeRule(Filter.class, HiveRelFactories.HIVE_FILTER_FACTORY, Aggregate.class));
rules.add(new FilterMergeRule(HiveRelFactories.HIVE_FILTER_FACTORY));
+ if (conf.getBoolVar(HiveConf.ConfVars.HIVE_OPTIMIZE_REDUCE_WITH_STATS)) {
+ rules.add(HiveReduceExpressionsWithStatsRule.INSTANCE);
+ }
rules.add(HiveProjectFilterPullUpConstantsRule.INSTANCE);
rules.add(HiveReduceExpressionsRule.PROJECT_INSTANCE);
rules.add(HiveReduceExpressionsRule.FILTER_INSTANCE);
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/ql/src/test/queries/clientpositive/remove_exprs_stats.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/remove_exprs_stats.q b/ql/src/test/queries/clientpositive/remove_exprs_stats.q
new file mode 100644
index 0000000..66e6615
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/remove_exprs_stats.q
@@ -0,0 +1,55 @@
+set hive.optimize.filter.stats.reduction=true;
+set hive.mapred.mode=nonstrict;
+set hive.stats.fetch.column.stats=true;
+
+create table if not exists loc_staging (
+ state string,
+ locid int,
+ zip bigint,
+ year int
+) row format delimited fields terminated by '|' stored as textfile;
+
+create table loc_orc like loc_staging;
+alter table loc_orc set fileformat orc;
+
+load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging;
+
+insert overwrite table loc_orc select * from loc_staging;
+
+analyze table loc_orc compute statistics for columns state,locid,zip,year;
+
+-- always true
+explain select * from loc_orc where locid < 30;
+-- always false
+explain select * from loc_orc where locid > 30;
+-- always true
+explain select * from loc_orc where locid <= 30;
+-- always false
+explain select * from loc_orc where locid >= 30;
+
+-- nothing to do
+explain select * from loc_orc where locid < 6;
+-- always false
+explain select * from loc_orc where locid > 6;
+-- always true
+explain select * from loc_orc where locid <= 6;
+-- nothing to do
+explain select * from loc_orc where locid >= 6;
+
+-- always false
+explain select * from loc_orc where locid < 1;
+-- nothing to do
+explain select * from loc_orc where locid > 1;
+-- nothing to do
+explain select * from loc_orc where locid <= 1;
+-- always true
+explain select * from loc_orc where locid >= 1;
+
+-- 5 should stay
+explain select * from loc_orc where locid IN (-4,5,30,40);
+-- nothing to do
+explain select * from loc_orc where locid IN (5,2,3);
+-- 1 and 6 should be left
+explain select * from loc_orc where locid IN (1,6,9);
+-- always false
+explain select * from loc_orc where locid IN (40,30);
http://git-wip-us.apache.org/repos/asf/hive/blob/76130a9d/ql/src/test/results/clientpositive/remove_exprs_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/remove_exprs_stats.q.out b/ql/src/test/results/clientpositive/remove_exprs_stats.q.out
new file mode 100644
index 0000000..e29fb4e
--- /dev/null
+++ b/ql/src/test/results/clientpositive/remove_exprs_stats.q.out
@@ -0,0 +1,610 @@
+PREHOOK: query: create table if not exists loc_staging (
+ state string,
+ locid int,
+ zip bigint,
+ year int
+) row format delimited fields terminated by '|' stored as textfile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@loc_staging
+POSTHOOK: query: create table if not exists loc_staging (
+ state string,
+ locid int,
+ zip bigint,
+ year int
+) row format delimited fields terminated by '|' stored as textfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@loc_staging
+PREHOOK: query: create table loc_orc like loc_staging
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@loc_orc
+POSTHOOK: query: create table loc_orc like loc_staging
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@loc_orc
+PREHOOK: query: alter table loc_orc set fileformat orc
+PREHOOK: type: ALTERTABLE_FILEFORMAT
+PREHOOK: Input: default@loc_orc
+PREHOOK: Output: default@loc_orc
+POSTHOOK: query: alter table loc_orc set fileformat orc
+POSTHOOK: type: ALTERTABLE_FILEFORMAT
+POSTHOOK: Input: default@loc_orc
+POSTHOOK: Output: default@loc_orc
+PREHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@loc_staging
+POSTHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@loc_staging
+PREHOOK: query: insert overwrite table loc_orc select * from loc_staging
+PREHOOK: type: QUERY
+PREHOOK: Input: default@loc_staging
+PREHOOK: Output: default@loc_orc
+POSTHOOK: query: insert overwrite table loc_orc select * from loc_staging
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@loc_staging
+POSTHOOK: Output: default@loc_orc
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+PREHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@loc_orc
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@loc_orc
+#### A masked pattern was here ####
+PREHOOK: query: -- always true
+explain select * from loc_orc where locid < 30
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always true
+explain select * from loc_orc where locid < 30
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: -- always false
+explain select * from loc_orc where locid > 30
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always false
+explain select * from loc_orc where locid > 30
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always true
+explain select * from loc_orc where locid <= 30
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always true
+explain select * from loc_orc where locid <= 30
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: -- always false
+explain select * from loc_orc where locid >= 30
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always false
+explain select * from loc_orc where locid >= 30
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- nothing to do
+explain select * from loc_orc where locid < 6
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nothing to do
+explain select * from loc_orc where locid < 6
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid < 6) (type: boolean)
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always false
+explain select * from loc_orc where locid > 6
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always false
+explain select * from loc_orc where locid > 6
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always true
+explain select * from loc_orc where locid <= 6
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always true
+explain select * from loc_orc where locid <= 6
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: -- nothing to do
+explain select * from loc_orc where locid >= 6
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nothing to do
+explain select * from loc_orc where locid >= 6
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid >= 6) (type: boolean)
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always false
+explain select * from loc_orc where locid < 1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always false
+explain select * from loc_orc where locid < 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- nothing to do
+explain select * from loc_orc where locid > 1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nothing to do
+explain select * from loc_orc where locid > 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid > 1) (type: boolean)
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- nothing to do
+explain select * from loc_orc where locid <= 1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nothing to do
+explain select * from loc_orc where locid <= 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid <= 1) (type: boolean)
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always true
+explain select * from loc_orc where locid >= 1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always true
+explain select * from loc_orc where locid >= 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ ListSink
+
+PREHOOK: query: -- 5 should stay
+explain select * from loc_orc where locid IN (-4,5,30,40)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- 5 should stay
+explain select * from loc_orc where locid IN (-4,5,30,40)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid) IN (5) (type: boolean)
+ Statistics: Num rows: 5 Data size: 498 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5 Data size: 498 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 498 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- nothing to do
+explain select * from loc_orc where locid IN (5,2,3)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nothing to do
+explain select * from loc_orc where locid IN (5,2,3)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid) IN (5, 2, 3) (type: boolean)
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- 1 and 6 should be left
+explain select * from loc_orc where locid IN (1,6,9)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- 1 and 6 should be left
+explain select * from loc_orc where locid IN (1,6,9)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (locid) IN (1, 6) (type: boolean)
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- always false
+explain select * from loc_orc where locid IN (40,30)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- always false
+explain select * from loc_orc where locid IN (40,30)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: loc_orc
+ Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: state (type: string), locid (type: int), zip (type: bigint), year (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
[40/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out
deleted file mode 100644
index 5c40dc4..0000000
--- a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out
+++ /dev/null
@@ -1,693 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
- TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [a]
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE.ds = '2008-04-08')}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns key,value,key0,value0
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
-PREHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
- TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: key, value
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /src [a]
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
- outputColumnNames: key, value, key0, value0
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns key,value,key0,value0
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
new file mode 100644
index 0000000..200b8ee
--- /dev/null
+++ b/ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.out
@@ -0,0 +1,691 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: value (type: string)
+ auto parallelism: false
+ TableScan
+ alias: b
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), ds (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string), ds (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /src [a]
+ /srcpart/ds=2008-04-08/hr=11 [b]
+ /srcpart/ds=2008-04-08/hr=12 [b]
+ /srcpart/ds=2008-04-09/hr=11 [b]
+ /srcpart/ds=2008-04-09/hr=12 [b]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ filter mappings:
+ 1 [0, 1]
+ filter predicates:
+ 0
+ 1 {(VALUE.ds = '2008-04-08')}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: key, value, key0, value0
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
+ outputColumnNames: key, value, key0, value0
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns key,value,key0,value0
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key AND b.ds = '2008-04-08')
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+#### A masked pattern was here ####
+17 val_17 17 val_17
+17 val_17 17 val_17
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+19 val_19 19 val_19
+19 val_19 19 val_19
+PREHOOK: query: EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN EXTENDED
+ FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: value (type: string)
+ auto parallelism: false
+ TableScan
+ alias: b
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /src [a]
+ /srcpart/ds=2008-04-08/hr=11 [b]
+ /srcpart/ds=2008-04-08/hr=12 [b]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: key, value, key0, value0
+ Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string)
+ outputColumnNames: key, value, key0, value0
+ Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+ Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns key,value,key0,value0
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+ src a
+ FULL OUTER JOIN
+ srcpart b
+ ON (a.key = b.key)
+ SELECT a.key, a.value, b.key, b.value
+ WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+17 val_17 17 val_17
+17 val_17 17 val_17
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+18 val_18 18 val_18
+19 val_19 19 val_19
+19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out b/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out
deleted file mode 100644
index ee1c2ae..0000000
--- a/ql/src/test/results/clientpositive/char_udf1.q.java1.7.out
+++ /dev/null
@@ -1,463 +0,0 @@
-PREHOOK: query: drop table char_udf_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table char_udf_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@char_udf_1
-PREHOOK: query: insert overwrite table char_udf_1
- select key, value, key, value from src where key = '238' limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: insert overwrite table char_udf_1
- select key, value, key, value from src where key = '238' limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@char_udf_1
-POSTHOOK: Lineage: char_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with char support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with char support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238val_238 238val_238 true
-PREHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-VAL_238 VAL_238 true
-PREHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-118 118 true
-PREHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238|val_238 238|val_238 true
-PREHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-4 4 true
-PREHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-7 7 true
-PREHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-5 5 true
-PREHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
- val_238 val_238 true
-PREHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF
--- we only allow A regexp B, not regexp (A,B).
-
-select
- c2 regexp 'val',
- c4 regexp 'val',
- (c2 regexp 'val') = (c4 regexp 'val')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF
--- we only allow A regexp B, not regexp (A,B).
-
-select
- c2 regexp 'val',
- c4 regexp 'val',
- (c2 regexp 'val') = (c4 regexp 'val')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-true true true
-PREHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238 238 true
-PREHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-replaced_238 replaced_238 true
-PREHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-832_lav 832_lav true
-PREHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as char(50)))
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as char(50)))
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
-PREHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-["val","238"] ["val","238"]
-PREHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-{"b":"2","a":"1","c":"3"} {"b":"2","a":"1","c":"3"}
-PREHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val val true
-PREHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"}
-PREHOOK: query: select
- min(c2),
- min(c4)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- min(c2),
- min(c4)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: select
- max(c2),
- max(c4)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- max(c2),
- max(c4)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: drop table char_udf_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@char_udf_1
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: drop table char_udf_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@char_udf_1
-POSTHOOK: Output: default@char_udf_1
[30/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
new file mode 100644
index 0000000..e53fee7
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_6.q.out
@@ -0,0 +1,1005 @@
+PREHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
+-- The following explains merge example used in this test case
+-- DML will generated 2 partitions
+-- ds=2008-04-08/hr=a1
+-- ds=2008-04-08/hr=b1
+-- without merge, each partition has more files
+-- ds=2008-04-08/hr=a1 has 2 files
+-- ds=2008-04-08/hr=b1 has 6 files
+-- with merge each partition has more files
+-- ds=2008-04-08/hr=a1 has 1 files
+-- ds=2008-04-08/hr=b1 has 4 files
+-- The following shows file size and name in each directory
+-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 155 000000_0
+-- 155 000001_0
+-- with merge
+-- 254 000000_0
+-- hr=b1/key=103/value=val_103:
+-- without merge
+-- 99 000000_0
+-- 99 000001_0
+-- with merge
+-- 142 000001_0
+-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- with merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- hr=b1/key=484/value=val_484
+-- without merge
+-- 87 000000_0
+-- 87 000001_0
+-- with merge
+-- 118 000002_0
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- list bucketing DML: dynamic partition. multiple skewed columns. merge.
+-- The following explains merge example used in this test case
+-- DML will generated 2 partitions
+-- ds=2008-04-08/hr=a1
+-- ds=2008-04-08/hr=b1
+-- without merge, each partition has more files
+-- ds=2008-04-08/hr=a1 has 2 files
+-- ds=2008-04-08/hr=b1 has 6 files
+-- with merge each partition has more files
+-- ds=2008-04-08/hr=a1 has 1 files
+-- ds=2008-04-08/hr=b1 has 4 files
+-- The following shows file size and name in each directory
+-- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 155 000000_0
+-- 155 000001_0
+-- with merge
+-- 254 000000_0
+-- hr=b1/key=103/value=val_103:
+-- without merge
+-- 99 000000_0
+-- 99 000001_0
+-- with merge
+-- 142 000001_0
+-- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- without merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- with merge
+-- 5181 000000_0
+-- 5181 000001_0
+-- hr=b1/key=484/value=val_484
+-- without merge
+-- 87 000000_0
+-- 87 000001_0
+-- with merge
+-- 118 000002_0
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- create a skewed table
+create table list_bucketing_dynamic_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_dynamic_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+ds=2008-04-08/hr=a1
+ds=2008-04-08/hr=b1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, a1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 2
+ numRows 16
+ rawDataSize 136
+ totalSize 310
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, b1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 6
+ numRows 984
+ rawDataSize 9488
+ totalSize 10734
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+ Stage-5
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-5
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns hr
+ partition_columns.types string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
+select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_dynamic_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+ds=2008-04-08/hr=a1
+ds=2008-04-08/hr=b1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, a1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 1
+ numRows 16
+ rawDataSize 136
+ totalSize 254
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, b1]
+Database: default
+Table: list_bucketing_dynamic_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 984
+ rawDataSize 9488
+ totalSize 10622
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484, [103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(*) from list_bucketing_dynamic_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+1000
+PREHOOK: query: explain extended
+select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr a1
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 1
+ numRows 16
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 136
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 254
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr b1
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ numFiles 4
+ numRows 984
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 9488
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 10622
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_dynamic_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_dynamic_part
+ name: default.list_bucketing_dynamic_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_dynamic_part
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
+POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
+#### A masked pattern was here ####
+484 val_484 2008-04-08 b1
+484 val_484 2008-04-08 b1
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 12
+PREHOOK: query: -- clean up
+drop table list_bucketing_dynamic_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_dynamic_part
+PREHOOK: Output: default@list_bucketing_dynamic_part
+POSTHOOK: query: -- clean up
+drop table list_bucketing_dynamic_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_dynamic_part
+POSTHOOK: Output: default@list_bucketing_dynamic_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out
deleted file mode 100644
index de1305f..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_8.q.java1.7.out
+++ /dev/null
@@ -1,641 +0,0 @@
-PREHOOK: query: -- list bucketing alter table ... concatenate:
--- Use list bucketing DML to generate mutilple files in partitions by turning off merge
--- dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- list bucketing alter table ... concatenate:
--- Use list bucketing DML to generate mutilple files in partitions by turning off merge
--- dynamic partition. multiple skewed columns. merge.
--- The following explains merge example used in this test case
--- DML will generated 2 partitions
--- ds=2008-04-08/hr=a1
--- ds=2008-04-08/hr=b1
--- without merge, each partition has more files
--- ds=2008-04-08/hr=a1 has 2 files
--- ds=2008-04-08/hr=b1 has 6 files
--- with merge each partition has more files
--- ds=2008-04-08/hr=a1 has 1 files
--- ds=2008-04-08/hr=b1 has 4 files
--- The following shows file size and name in each directory
--- hr=a1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 155 000000_0
--- 155 000001_0
--- with merge
--- 254 000000_0
--- hr=b1/key=103/value=val_103:
--- without merge
--- 99 000000_0
--- 99 000001_0
--- with merge
--- 142 000001_0
--- hr=b1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- without merge
--- 5181 000000_0
--- 5181 000001_0
--- with merge
--- 5181 000000_0
--- 5181 000001_0
--- hr=b1/key=484/value=val_484
--- without merge
--- 87 000000_0
--- 87 000001_0
--- with merge
--- 118 000002_0
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- create a skewed table
-create table list_bucketing_dynamic_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_dynamic_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0) = 0.0), 'a1', 'b1') (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08
-POSTHOOK: query: insert overwrite table list_bucketing_dynamic_part partition (ds = '2008-04-08', hr)
-select key, value, if(key % 100 == 0, 'a1', 'b1') from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=a1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_dynamic_part PARTITION(ds=2008-04-08,hr=b1).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_dynamic_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-ds=2008-04-08/hr=a1
-ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='a1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, a1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 2
- numRows 16
- rawDataSize 136
- totalSize 310
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 984
- rawDataSize 9488
- totalSize 10734
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- concatenate the partition and it will merge files
-alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
-PREHOOK: type: ALTER_PARTITION_MERGE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-POSTHOOK: query: -- concatenate the partition and it will merge files
-alter table list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1') concatenate
-POSTHOOK: type: ALTER_PARTITION_MERGE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-PREHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: query: desc formatted list_bucketing_dynamic_part partition (ds='2008-04-08', hr='b1')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, b1]
-Database: default
-Table: list_bucketing_dynamic_part
-#### A masked pattern was here ####
-Partition Parameters:
- numFiles 3
- numRows 984
- rawDataSize 9488
- totalSize 10586
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=103/value=val_103, [484, val_484]=/list_bucketing_dynamic_part/ds=2008-04-08/hr=b1/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_dynamic_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_dynamic_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr a1
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 2
- numRows 16
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 136
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 310
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr b1
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- numFiles 3
- numRows 984
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9488
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10586
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_dynamic_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_dynamic_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_dynamic_part
- name: default.list_bucketing_dynamic_part
- Processor Tree:
- TableScan
- alias: list_bucketing_dynamic_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), ds (type: string), hr (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-PREHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_dynamic_part where key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=a1
-POSTHOOK: Input: default@list_bucketing_dynamic_part@ds=2008-04-08/hr=b1
-#### A masked pattern was here ####
-484 val_484 2008-04-08 b1
-484 val_484 2008-04-08 b1
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484' order by hr
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_dynamic_part
-PREHOOK: Output: default@list_bucketing_dynamic_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_dynamic_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_dynamic_part
-POSTHOOK: Output: default@list_bucketing_dynamic_part
[15/48] hive git commit: HIVE-13587: Set Hive pom to use Hadoop 2.6.1
(Mohit Sabharwal, reviewd by Sergio Pena)
Posted by sp...@apache.org.
HIVE-13587: Set Hive pom to use Hadoop 2.6.1 (Mohit Sabharwal, reviewd by Sergio Pena)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/77f5ee78
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/77f5ee78
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/77f5ee78
Branch: refs/heads/java8
Commit: 77f5ee7802dd79cccbd6a7ca7a04d4b9e614f8ca
Parents: 793681c
Author: Sergio Pena <se...@cloudera.com>
Authored: Mon May 2 13:08:54 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Fri May 27 10:36:28 2016 -0500
----------------------------------------------------------------------
pom.xml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/77f5ee78/pom.xml
----------------------------------------------------------------------
diff --git a/pom.xml b/pom.xml
index 117aec9..3176caf 100644
--- a/pom.xml
+++ b/pom.xml
@@ -132,7 +132,7 @@
<dropwizard-metrics-hadoop-metrics2-reporter.version>0.1.0</dropwizard-metrics-hadoop-metrics2-reporter.version>
<guava.version>14.0.1</guava.version>
<groovy.version>2.4.4</groovy.version>
- <hadoop.version>2.6.0</hadoop.version>
+ <hadoop.version>2.6.1</hadoop.version>
<hadoop.bin.path>${basedir}/${hive.path.to.root}/testutils/hadoop</hadoop.bin.path>
<hbase.version>1.1.1</hbase.version>
<!-- required for logging test to avoid including hbase which pulls disruptor transitively -->
[43/48] hive git commit: HIVE-13409: Fix JDK8 test failures related
to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/sample8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/sample8.q.out b/ql/src/test/results/clientpositive/spark/sample8.q.out
index e847fa5..59807de 100644
--- a/ql/src/test/results/clientpositive/spark/sample8.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample8.q.out
@@ -57,7 +57,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -126,7 +126,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -172,7 +172,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -218,7 +218,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -264,7 +264,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/stats0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/stats0.q.out b/ql/src/test/results/clientpositive/spark/stats0.q.out
index 0b14e21..491b4d0 100644
--- a/ql/src/test/results/clientpositive/spark/stats0.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats0.q.out
@@ -74,7 +74,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -94,7 +94,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1388,7 +1388,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1408,7 +1408,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out
index 032b659..ec65619 100644
--- a/ql/src/test/results/clientpositive/spark/stats_only_null.q.out
+++ b/ql/src/test/results/clientpositive/spark/stats_only_null.q.out
@@ -230,7 +230,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 71
@@ -271,7 +271,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 49
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
index d6df85a..91e6cfb 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
@@ -73,8 +73,8 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 10 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 4), Reducer 2 (PARTITION-LEVEL SORT, 4)
- Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 4), Map 6 (PARTITION-LEVEL SORT, 4)
+ Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2)
Reducer 9 <- Map 8 (GROUP, 1)
Reducer 4 <- Reducer 3 (SORT, 1)
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/transform_ppr1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/transform_ppr1.q.out b/ql/src/test/results/clientpositive/spark/transform_ppr1.q.out
index 57cb338..0dfd7d0 100644
--- a/ql/src/test/results/clientpositive/spark/transform_ppr1.q.out
+++ b/ql/src/test/results/clientpositive/spark/transform_ppr1.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -125,7 +125,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -171,7 +171,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -217,7 +217,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/transform_ppr2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/transform_ppr2.q.out b/ql/src/test/results/clientpositive/spark/transform_ppr2.q.out
index 2dfbd1c..3959df6 100644
--- a/ql/src/test/results/clientpositive/spark/transform_ppr2.q.out
+++ b/ql/src/test/results/clientpositive/spark/transform_ppr2.q.out
@@ -81,7 +81,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -127,7 +127,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
index 0459d93..5762865 100644
--- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
+++ b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
@@ -119,7 +119,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP, 4)
+ Reducer 2 <- Map 1 (GROUP, 2)
Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/stats0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats0.q.out b/ql/src/test/results/clientpositive/stats0.q.out
index bbe38c1..97d66e7 100644
--- a/ql/src/test/results/clientpositive/stats0.q.out
+++ b/ql/src/test/results/clientpositive/stats0.q.out
@@ -71,7 +71,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -91,7 +91,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1384,7 +1384,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1404,7 +1404,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/stats_invalidation.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_invalidation.q.out b/ql/src/test/results/clientpositive/stats_invalidation.q.out
index d24fdc3..d822f4f 100644
--- a/ql/src/test/results/clientpositive/stats_invalidation.q.out
+++ b/ql/src/test/results/clientpositive/stats_invalidation.q.out
@@ -44,7 +44,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/stats_only_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_only_null.q.out b/ql/src/test/results/clientpositive/stats_only_null.q.out
index 032f6c8..b47fe64 100644
--- a/ql/src/test/results/clientpositive/stats_only_null.q.out
+++ b/ql/src/test/results/clientpositive/stats_only_null.q.out
@@ -218,7 +218,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 71
@@ -259,7 +259,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 49
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/bucket3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/bucket3.q.out b/ql/src/test/results/clientpositive/tez/bucket3.q.out
index 1532edc..250d03d 100644
--- a/ql/src/test/results/clientpositive/tez/bucket3.q.out
+++ b/ql/src/test/results/clientpositive/tez/bucket3.q.out
@@ -59,7 +59,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/bucket4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/bucket4.q.out b/ql/src/test/results/clientpositive/tez/bucket4.q.out
index 4291e44..b14c672 100644
--- a/ql/src/test/results/clientpositive/tez/bucket4.q.out
+++ b/ql/src/test/results/clientpositive/tez/bucket4.q.out
@@ -56,7 +56,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -76,7 +76,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/ctas.q.out b/ql/src/test/results/clientpositive/tez/ctas.q.out
index d92a446..9dffc0b 100644
--- a/ql/src/test/results/clientpositive/tez/ctas.q.out
+++ b/ql/src/test/results/clientpositive/tez/ctas.q.out
@@ -742,7 +742,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -762,7 +762,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/disable_merge_for_bucketing.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/disable_merge_for_bucketing.q.out b/ql/src/test/results/clientpositive/tez/disable_merge_for_bucketing.q.out
index fb71214..c1717e3 100644
--- a/ql/src/test/results/clientpositive/tez/disable_merge_for_bucketing.q.out
+++ b/ql/src/test/results/clientpositive/tez/disable_merge_for_bucketing.q.out
@@ -55,7 +55,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -75,7 +75,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out
index 316c914..2c2b2cf 100644
--- a/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out
@@ -96,7 +96,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -142,7 +142,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -188,7 +188,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -234,7 +234,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -307,7 +307,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -327,7 +327,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -378,7 +378,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -398,7 +398,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out b/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out
index 2cae5ce..b4423d4 100644
--- a/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out
+++ b/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out
@@ -183,7 +183,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -203,7 +203,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -257,7 +257,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -302,7 +302,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -347,7 +347,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -392,7 +392,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -560,7 +560,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -580,7 +580,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -634,7 +634,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -680,7 +680,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -726,7 +726,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -772,7 +772,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -952,7 +952,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -972,7 +972,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1026,7 +1026,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1071,7 +1071,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1116,7 +1116,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1161,7 +1161,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1344,7 +1344,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1364,7 +1364,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1410,7 +1410,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1430,7 +1430,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1566,7 +1566,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1586,7 +1586,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1633,7 +1633,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1653,7 +1653,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1774,7 +1774,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1794,7 +1794,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/sample1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/sample1.q.out b/ql/src/test/results/clientpositive/tez/sample1.q.out
index 2120a1ff..882621b 100644
--- a/ql/src/test/results/clientpositive/tez/sample1.q.out
+++ b/ql/src/test/results/clientpositive/tez/sample1.q.out
@@ -86,7 +86,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out b/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
index d396a61..af541aa 100644
--- a/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
+++ b/ql/src/test/results/clientpositive/tez/schema_evol_stats.q.out
@@ -109,7 +109,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 40
@@ -150,7 +150,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 56
@@ -305,7 +305,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 384
@@ -346,7 +346,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 732
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/stats_only_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/stats_only_null.q.out b/ql/src/test/results/clientpositive/tez/stats_only_null.q.out
index f4cc11e..8c17509 100644
--- a/ql/src/test/results/clientpositive/tez/stats_only_null.q.out
+++ b/ql/src/test/results/clientpositive/tez/stats_only_null.q.out
@@ -232,7 +232,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 71
@@ -273,7 +273,7 @@ Database: default
Table: stats_null_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 49
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/transform_ppr1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/transform_ppr1.q.out b/ql/src/test/results/clientpositive/tez/transform_ppr1.q.out
index 5d7374f..50deff6 100644
--- a/ql/src/test/results/clientpositive/tez/transform_ppr1.q.out
+++ b/ql/src/test/results/clientpositive/tez/transform_ppr1.q.out
@@ -80,7 +80,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -126,7 +126,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -172,7 +172,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -218,7 +218,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/tez/transform_ppr2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/transform_ppr2.q.out b/ql/src/test/results/clientpositive/tez/transform_ppr2.q.out
index 4d74124..2b1abb9 100644
--- a/ql/src/test/results/clientpositive/tez/transform_ppr2.q.out
+++ b/ql/src/test/results/clientpositive/tez/transform_ppr2.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -128,7 +128,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/transform_ppr1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/transform_ppr1.q.out b/ql/src/test/results/clientpositive/transform_ppr1.q.out
index 8c58139..f15646a 100644
--- a/ql/src/test/results/clientpositive/transform_ppr1.q.out
+++ b/ql/src/test/results/clientpositive/transform_ppr1.q.out
@@ -74,7 +74,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -120,7 +120,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -166,7 +166,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -212,7 +212,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/transform_ppr2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/transform_ppr2.q.out b/ql/src/test/results/clientpositive/transform_ppr2.q.out
index 8e36abd..db99985 100644
--- a/ql/src/test/results/clientpositive/transform_ppr2.q.out
+++ b/ql/src/test/results/clientpositive/transform_ppr2.q.out
@@ -76,7 +76,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -122,7 +122,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/udf_explode.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/udf_explode.q.out b/ql/src/test/results/clientpositive/udf_explode.q.out
index ea12e80..bd68e96 100644
--- a/ql/src/test/results/clientpositive/udf_explode.q.out
+++ b/ql/src/test/results/clientpositive/udf_explode.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -102,7 +102,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -266,7 +266,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -286,7 +286,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/udtf_explode.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/udtf_explode.q.out b/ql/src/test/results/clientpositive/udtf_explode.q.out
index e067a0a..4f8bd5e 100644
--- a/ql/src/test/results/clientpositive/udtf_explode.q.out
+++ b/ql/src/test/results/clientpositive/udtf_explode.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -99,7 +99,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -331,7 +331,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -351,7 +351,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/union_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union_ppr.q.out b/ql/src/test/results/clientpositive/union_ppr.q.out
index c5b1193..9763679 100644
--- a/ql/src/test/results/clientpositive/union_ppr.q.out
+++ b/ql/src/test/results/clientpositive/union_ppr.q.out
@@ -90,7 +90,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -136,7 +136,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
[17/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_notin_having.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.out
new file mode 100644
index 0000000..c32bf25
--- /dev/null
+++ b/ql/src/test/results/clientpositive/subquery_notin_having.q.out
@@ -0,0 +1,764 @@
+Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: -- non agg, non corr
+
+explain
+select key, count(*)
+from src
+group by key
+having key not in
+ ( select key from src s1
+ where s1.key > '12'
+ )
+PREHOOK: type: QUERY
+POSTHOOK: query: -- non agg, non corr
+
+explain
+select key, count(*)
+from src
+group by key
+having key not in
+ ( select key from src s1
+ where s1.key > '12'
+ )
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: bigint)
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key > '12') (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: false (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col0 = 0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: -- non agg, corr
+explain
+select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
+ where min(p_retailprice) = l and r - l > 600
+ )
+PREHOOK: type: QUERY
+POSTHOOK: query: -- non agg, corr
+explain
+select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
+ where min(p_retailprice) = l and r - l > 600
+ )
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-5
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-4 is a root stage
+ Stage-5 depends on stages: Stage-4
+ Stage-6 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_mfgr (type: string), p_retailprice (type: double)
+ outputColumnNames: p_mfgr, p_retailprice
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(p_retailprice)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: double)
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: double)
+ 1 _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_mfgr (type: string), p_retailprice (type: double)
+ outputColumnNames: p_mfgr, p_retailprice
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(p_retailprice), max(p_retailprice)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double), _col2 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean)
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 = 0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_mfgr (type: string), p_retailprice (type: double)
+ outputColumnNames: p_mfgr, p_retailprice
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(p_retailprice), max(p_retailprice)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double), _col2 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col2 - _col1) > 600.0) (type: boolean)
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
+ where min(p_retailprice) = l and r - l > 600
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
+ where min(p_retailprice) = l and r - l > 600
+ )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@part
+#### A masked pattern was here ####
+Manufacturer#1 1173.15
+Manufacturer#2 1690.68
+Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: -- agg, non corr
+explain
+select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from part a
+ group by p_mfgr
+ having max(p_retailprice) - min(p_retailprice) > 600
+ )
+PREHOOK: type: QUERY
+POSTHOOK: query: -- agg, non corr
+explain
+select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from part a
+ group by p_mfgr
+ having max(p_retailprice) - min(p_retailprice) > 600
+ )
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-5
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-4 is a root stage
+ Stage-5 depends on stages: Stage-4
+ Stage-6 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_mfgr (type: string), p_retailprice (type: double)
+ outputColumnNames: p_mfgr, p_retailprice
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: min(p_retailprice)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: double)
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col3 is null (type: boolean)
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_mfgr is null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_retailprice (type: double)
+ outputColumnNames: _col1
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(_col1), min(_col1)
+ keys: null (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double), _col2 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0), min(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col2 (type: double)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 - _col2) > 600.0) (type: boolean)
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 = 0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_mfgr (type: string), p_retailprice (type: double)
+ outputColumnNames: p_mfgr, p_retailprice
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(p_retailprice), min(p_retailprice)
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double), _col2 (type: double)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0), min(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 - _col2) > 600.0) (type: boolean)
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from part a
+ group by p_mfgr
+ having max(p_retailprice) - min(p_retailprice) > 600
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
+from part b
+group by b.p_mfgr
+having b.p_mfgr not in
+ (select p_mfgr
+ from part a
+ group by p_mfgr
+ having max(p_retailprice) - min(p_retailprice) > 600
+ )
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@part
+#### A masked pattern was here ####
+Manufacturer#1 1173.15
+Manufacturer#2 1690.68
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out b/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out
deleted file mode 100644
index 59d9087..0000000
--- a/ql/src/test/results/clientpositive/tez/join0.q.java1.7.out
+++ /dev/null
@@ -1,239 +0,0 @@
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
-#### A masked pattern was here ####
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reducer 2
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out b/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out
deleted file mode 100644
index 10d7802..0000000
--- a/ql/src/test/results/clientpositive/tez/join0.q.java1.8.out
+++ /dev/null
@@ -1,236 +0,0 @@
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reducer 2
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/join0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/join0.q.out b/ql/src/test/results/clientpositive/tez/join0.q.out
new file mode 100644
index 0000000..67d71d5
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez/join0.q.out
@@ -0,0 +1,237 @@
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+#### A masked pattern was here ####
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 9 val_9
+0 val_0 9 val_9
+0 val_0 9 val_9
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 2 val_2
+2 val_2 4 val_4
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 8 val_8
+2 val_2 9 val_9
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 2 val_2
+4 val_4 4 val_4
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 8 val_8
+4 val_4 9 val_9
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 9 val_9
+5 val_5 9 val_9
+5 val_5 9 val_9
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 2 val_2
+8 val_8 4 val_4
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 8 val_8
+8 val_8 9 val_9
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 2 val_2
+9 val_9 4 val_4
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 8 val_8
+9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out
deleted file mode 100644
index 420e788..0000000
--- a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.7.out
+++ /dev/null
@@ -1,218 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
-#### A masked pattern was here ####
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reducer 3
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50.0000
-65537 50.0 50.0 50.0000
-65538 50.0 50.0 50.0000
-65539 50.0 50.0 50.0000
-65540 50.0 50.0 50.0000
-65541 50.0 50.0 50.0000
-65542 50.0 50.0 50.0000
-65543 50.0 50.0 50.0000
-65544 50.0 50.0 50.0000
-65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.8.out
deleted file mode 100644
index 331edd0..0000000
--- a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.java1.8.out
+++ /dev/null
@@ -1,216 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reducer 3
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50
-65537 50.0 50.0 50
-65538 50.0 50.0 50
-65539 50.0 50.0 50
-65540 50.0 50.0 50
-65541 50.0 50.0 50
-65542 50.0 50.0 50
-65543 50.0 50.0 50
-65544 50.0 50.0 50
-65545 50.0 50.0 50
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out
new file mode 100644
index 0000000..46b13c8
--- /dev/null
+++ b/ql/src/test/results/clientpositive/tez/vector_cast_constant.q.out
@@ -0,0 +1,214 @@
+PREHOOK: query: DROP TABLE over1k
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE over1k
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE over1korc
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE over1korc
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: -- data setup
+CREATE TABLE over1k(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@over1k
+POSTHOOK: query: -- data setup
+CREATE TABLE over1k(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@over1k
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@over1k
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@over1k
+PREHOOK: query: CREATE TABLE over1korc(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@over1korc
+POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
+ si smallint,
+ i int,
+ b bigint,
+ f float,
+ d double,
+ bo boolean,
+ s string,
+ ts timestamp,
+ dec decimal(4,2),
+ bin binary)
+STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@over1korc
+PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
+PREHOOK: type: QUERY
+PREHOOK: Input: default@over1k
+PREHOOK: Output: default@over1korc
+POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@over1k
+POSTHOOK: Output: default@over1korc
+POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
+POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
+POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
+POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
+POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
+POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
+POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
+POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
+POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
+POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
+POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
+PREHOOK: query: EXPLAIN SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: over1korc
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: i (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(50), avg(50.0), avg(50)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
+ Reducer 3
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 10
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 10
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@over1korc
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT
+ i,
+ AVG(CAST(50 AS INT)) AS `avg_int_ok`,
+ AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
+ AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@over1korc
+#### A masked pattern was here ####
+65536 50.0 50.0 50.0000
+65537 50.0 50.0 50.0000
+65538 50.0 50.0 50.0000
+65539 50.0 50.0 50.0000
+65540 50.0 50.0 50.0000
+65541 50.0 50.0 50.0000
+65542 50.0 50.0 50.0000
+65543 50.0 50.0 50.0000
+65544 50.0 50.0 50.0000
+65545 50.0 50.0 50.0000
[46/48] hive git commit: HIVE-13409: Fix JDK8 test failures related
to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join33.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join33.q.out b/ql/src/test/results/clientpositive/join33.q.out
index 8653c2f..bebb007 100644
--- a/ql/src/test/results/clientpositive/join33.q.out
+++ b/ql/src/test/results/clientpositive/join33.q.out
@@ -159,7 +159,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -179,7 +179,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -203,7 +203,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -223,7 +223,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -250,7 +250,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join34.q.out b/ql/src/test/results/clientpositive/join34.q.out
index bb23644..365992b 100644
--- a/ql/src/test/results/clientpositive/join34.q.out
+++ b/ql/src/test/results/clientpositive/join34.q.out
@@ -197,7 +197,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -217,7 +217,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -241,7 +241,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -261,7 +261,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join35.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join35.q.out b/ql/src/test/results/clientpositive/join35.q.out
index b1732ec..2c2681f 100644
--- a/ql/src/test/results/clientpositive/join35.q.out
+++ b/ql/src/test/results/clientpositive/join35.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -102,7 +102,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -324,7 +324,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -344,7 +344,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -435,7 +435,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -455,7 +455,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join9.q.out b/ql/src/test/results/clientpositive/join9.q.out
index 180d46c..efddb5d 100644
--- a/ql/src/test/results/clientpositive/join9.q.out
+++ b/ql/src/test/results/clientpositive/join9.q.out
@@ -77,7 +77,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -97,7 +97,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -124,7 +124,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join_map_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join_map_ppr.q.out b/ql/src/test/results/clientpositive/join_map_ppr.q.out
index 928d4fb..e44ceac 100644
--- a/ql/src/test/results/clientpositive/join_map_ppr.q.out
+++ b/ql/src/test/results/clientpositive/join_map_ppr.q.out
@@ -148,7 +148,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -716,7 +716,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out
index 2b7ebb2..1d43bc0 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_1.q.out
@@ -88,7 +88,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -134,7 +134,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out
index 5016855..ebbbb26 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_14.q.out
@@ -85,7 +85,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -105,7 +105,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
index 548815a..385e113 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_3.q.out
@@ -82,7 +82,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -128,7 +128,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
index b8757de..224ecc2 100644
--- a/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_7.q.out
@@ -114,7 +114,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -160,7 +160,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -422,7 +422,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -468,7 +468,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/load_dyn_part8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/load_dyn_part8.q.out b/ql/src/test/results/clientpositive/load_dyn_part8.q.out
index 757e7dd..a8247f5 100644
--- a/ql/src/test/results/clientpositive/load_dyn_part8.q.out
+++ b/ql/src/test/results/clientpositive/load_dyn_part8.q.out
@@ -148,7 +148,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -194,7 +194,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -240,7 +240,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -286,7 +286,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/louter_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out
index fd127ec..c1319f8 100644
--- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -99,7 +99,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -126,7 +126,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -172,7 +172,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -371,7 +371,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -391,7 +391,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -418,7 +418,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -464,7 +464,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -510,7 +510,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -556,7 +556,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -770,7 +770,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -790,7 +790,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -817,7 +817,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -863,7 +863,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1058,7 +1058,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1078,7 +1078,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1105,7 +1105,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1151,7 +1151,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
index 85bd14b..17a1cde 100644
--- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
@@ -129,7 +129,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -149,7 +149,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -173,7 +173,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -193,7 +193,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -220,7 +220,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -266,7 +266,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -312,7 +312,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -358,7 +358,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out b/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out
index 7d8655f..a3cc93e 100644
--- a/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out
+++ b/ql/src/test/results/clientpositive/offset_limit_global_optimizer.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -190,7 +190,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -236,7 +236,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -282,7 +282,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -328,7 +328,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -463,7 +463,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -509,7 +509,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -555,7 +555,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -601,7 +601,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -746,7 +746,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -792,7 +792,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -838,7 +838,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -884,7 +884,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1609,7 +1609,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1741,7 +1741,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1787,7 +1787,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1833,7 +1833,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1879,7 +1879,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2014,7 +2014,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2060,7 +2060,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2106,7 +2106,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2152,7 +2152,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2297,7 +2297,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2343,7 +2343,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2389,7 +2389,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -2435,7 +2435,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/optimize_nullscan.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/optimize_nullscan.q.out b/ql/src/test/results/clientpositive/optimize_nullscan.q.out
index 4a693d6..b045cc5 100644
--- a/ql/src/test/results/clientpositive/optimize_nullscan.q.out
+++ b/ql/src/test/results/clientpositive/optimize_nullscan.q.out
@@ -64,7 +64,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -84,7 +84,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -252,7 +252,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -297,7 +297,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -342,7 +342,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -387,7 +387,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -518,7 +518,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -538,7 +538,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -660,7 +660,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -680,7 +680,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -861,7 +861,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -907,7 +907,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -953,7 +953,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -999,7 +999,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1140,7 +1140,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1185,7 +1185,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1230,7 +1230,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1275,7 +1275,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1404,7 +1404,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1424,7 +1424,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1558,7 +1558,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1578,7 +1578,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1720,7 +1720,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1740,7 +1740,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1834,7 +1834,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1854,7 +1854,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1967,7 +1967,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1987,7 +1987,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/partition_coltype_literals.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/partition_coltype_literals.q.out b/ql/src/test/results/clientpositive/partition_coltype_literals.q.out
index b7a09d2..06c178c 100644
--- a/ql/src/test/results/clientpositive/partition_coltype_literals.q.out
+++ b/ql/src/test/results/clientpositive/partition_coltype_literals.q.out
@@ -373,7 +373,7 @@ Database: default
Table: partcoltypenum
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
#### A masked pattern was here ####
numFiles 2
numRows 30
@@ -424,7 +424,7 @@ Database: default
Table: partcoltypenum
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
#### A masked pattern was here ####
numFiles 2
numRows 30
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/pcr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out
index 9daddfb..9fb1481 100644
--- a/ql/src/test/results/clientpositive/pcr.q.out
+++ b/ql/src/test/results/clientpositive/pcr.q.out
@@ -4635,7 +4635,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4764,7 +4764,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4810,7 +4810,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4943,7 +4943,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -4989,7 +4989,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/pcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pcs.q.out b/ql/src/test/results/clientpositive/pcs.q.out
index 8b99401..0045c1c 100644
--- a/ql/src/test/results/clientpositive/pcs.q.out
+++ b/ql/src/test/results/clientpositive/pcs.q.out
@@ -120,7 +120,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -165,7 +165,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -310,7 +310,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -355,7 +355,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -472,7 +472,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -517,7 +517,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -626,7 +626,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -671,7 +671,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -827,7 +827,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -872,7 +872,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1164,7 +1164,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1303,7 +1303,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1348,7 +1348,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1413,7 +1413,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1456,7 +1456,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1499,7 +1499,7 @@ STAGE PLANS:
partition values:
ds 2000-04-10
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1586,7 +1586,7 @@ STAGE PLANS:
partition values:
ds 2000-04-08
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1629,7 +1629,7 @@ STAGE PLANS:
partition values:
ds 2000-04-09
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
@@ -1672,7 +1672,7 @@ STAGE PLANS:
partition values:
ds 2000-04-10
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/ppd_join_filter.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_join_filter.q.out b/ql/src/test/results/clientpositive/ppd_join_filter.q.out
index d8e5009..b63161b 100644
--- a/ql/src/test/results/clientpositive/ppd_join_filter.q.out
+++ b/ql/src/test/results/clientpositive/ppd_join_filter.q.out
@@ -65,7 +65,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -85,7 +85,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -202,7 +202,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -222,7 +222,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -387,7 +387,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -407,7 +407,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -524,7 +524,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -544,7 +544,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -709,7 +709,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -729,7 +729,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -846,7 +846,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -866,7 +866,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1031,7 +1031,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1051,7 +1051,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1168,7 +1168,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1188,7 +1188,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/ppd_vc.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_vc.q.out b/ql/src/test/results/clientpositive/ppd_vc.q.out
index a82a709..21181ac 100644
--- a/ql/src/test/results/clientpositive/ppd_vc.q.out
+++ b/ql/src/test/results/clientpositive/ppd_vc.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -108,7 +108,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -154,7 +154,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -200,7 +200,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -370,7 +370,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -390,7 +390,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -417,7 +417,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -463,7 +463,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -509,7 +509,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -555,7 +555,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
[42/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
HIVE-13549: Remove jdk version specific out files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/9349b8e5
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/9349b8e5
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/9349b8e5
Branch: refs/heads/java8
Commit: 9349b8e551b5c06312900e70c43f06b10f8a370d
Parents: 77f5ee7
Author: Mohit Sabharwal <mo...@cloudera.com>
Authored: Fri May 20 11:14:13 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Fri May 27 10:36:28 2016 -0500
----------------------------------------------------------------------
.../columnstats_partlvl_invalid_values.q | 1 -
.../clientpositive/authorization_explain.q | 1 -
ql/src/test/queries/clientpositive/avro_date.q | 1 -
.../clientpositive/avro_deserialize_map_null.q | 1 -
.../clientpositive/avro_nullable_fields.q | 1 -
.../queries/clientpositive/avro_timestamp.q | 1 -
.../clientpositive/cbo_rp_outer_join_ppr.q | 1 -
ql/src/test/queries/clientpositive/char_udf1.q | 1 -
ql/src/test/queries/clientpositive/input4.q | 1 -
ql/src/test/queries/clientpositive/join0.q | 1 -
.../queries/clientpositive/list_bucket_dml_10.q | 1 -
.../queries/clientpositive/list_bucket_dml_11.q | 1 -
.../queries/clientpositive/list_bucket_dml_12.q | 1 -
.../queries/clientpositive/list_bucket_dml_13.q | 1 -
.../queries/clientpositive/list_bucket_dml_2.q | 1 -
.../queries/clientpositive/list_bucket_dml_4.q | 1 -
.../queries/clientpositive/list_bucket_dml_5.q | 1 -
.../queries/clientpositive/list_bucket_dml_6.q | 1 -
.../queries/clientpositive/list_bucket_dml_8.q | 1 -
.../queries/clientpositive/list_bucket_dml_9.q | 1 -
.../queries/clientpositive/outer_join_ppr.q | 1 -
.../queries/clientpositive/parquet_map_null.q | 1 -
ql/src/test/queries/clientpositive/plan_json.q | 1 -
.../queries/clientpositive/stats_list_bucket.q | 1 -
ql/src/test/queries/clientpositive/str_to_map.q | 1 -
.../clientpositive/subquery_multiinsert.q | 1 -
.../clientpositive/subquery_notin_having.q | 1 -
.../test/queries/clientpositive/varchar_udf1.q | 1 -
.../clientpositive/vector_cast_constant.q | 1 -
...mnstats_partlvl_invalid_values.q.java1.7.out | 73 --
...mnstats_partlvl_invalid_values.q.java1.8.out | 73 --
.../columnstats_partlvl_invalid_values.q.out | 69 ++
.../authorization_explain.q.java1.7.out | 44 -
.../authorization_explain.q.java1.8.out | 47 -
.../clientpositive/authorization_explain.q.out | 40 +
.../clientpositive/avro_date.q.java1.7.out | 130 --
.../clientpositive/avro_date.q.java1.8.out | 130 --
.../test/results/clientpositive/avro_date.q.out | 126 ++
.../avro_deserialize_map_null.q.java1.7.out | 57 -
.../avro_deserialize_map_null.q.java1.8.out | 57 -
.../avro_deserialize_map_null.q.out | 55 +
.../avro_nullable_fields.q.java1.7.out | 179 ---
.../avro_nullable_fields.q.java1.8.out | 179 ---
.../clientpositive/avro_nullable_fields.q.out | 177 +++
.../clientpositive/avro_timestamp.q.java1.7.out | 134 ---
.../clientpositive/avro_timestamp.q.java1.8.out | 134 ---
.../results/clientpositive/avro_timestamp.q.out | 132 +++
.../cbo_rp_outer_join_ppr.q.java1.7.out | 693 -----------
.../clientpositive/cbo_rp_outer_join_ppr.q.out | 691 +++++++++++
.../clientpositive/char_udf1.q.java1.7.out | 463 --------
.../clientpositive/char_udf1.q.java1.8.out | 457 -------
.../test/results/clientpositive/char_udf1.q.out | 459 +++++++
.../results/clientpositive/input4.q.java1.7.out | 559 ---------
.../results/clientpositive/input4.q.java1.8.out | 559 ---------
ql/src/test/results/clientpositive/input4.q.out | 555 +++++++++
.../results/clientpositive/join0.q.java1.7.out | 240 ----
.../results/clientpositive/join0.q.java1.8.out | 240 ----
ql/src/test/results/clientpositive/join0.q.out | 238 ++++
.../list_bucket_dml_10.q.java1.7.out | 361 ------
.../list_bucket_dml_10.q.java1.8.out | 389 ------
.../clientpositive/list_bucket_dml_10.q.out | 359 ++++++
.../list_bucket_dml_11.q.java1.7.out | 329 -----
.../list_bucket_dml_11.q.java1.8.out | 424 -------
.../clientpositive/list_bucket_dml_11.q.out | 327 +++++
.../list_bucket_dml_12.q.java1.7.out | 426 -------
.../list_bucket_dml_12.q.java1.8.out | 596 ----------
.../clientpositive/list_bucket_dml_12.q.out | 424 +++++++
.../list_bucket_dml_13.q.java1.7.out | 337 ------
.../list_bucket_dml_13.q.java1.8.out | 439 -------
.../clientpositive/list_bucket_dml_13.q.out | 335 ++++++
.../list_bucket_dml_2.q.java1.7.out | 591 ---------
.../list_bucket_dml_2.q.java1.8.out | 692 -----------
.../clientpositive/list_bucket_dml_2.q.out | 589 +++++++++
.../list_bucket_dml_4.q.java1.7.out | 813 -------------
.../list_bucket_dml_4.q.java1.8.out | 915 --------------
.../clientpositive/list_bucket_dml_4.q.out | 811 +++++++++++++
.../list_bucket_dml_5.q.java1.7.out | 506 --------
.../list_bucket_dml_5.q.java1.8.out | 617 ----------
.../clientpositive/list_bucket_dml_5.q.out | 504 ++++++++
.../list_bucket_dml_6.q.java1.7.out | 1007 ----------------
.../list_bucket_dml_6.q.java1.8.out | 1119 ------------------
.../clientpositive/list_bucket_dml_6.q.out | 1005 ++++++++++++++++
.../list_bucket_dml_8.q.java1.7.out | 641 ----------
.../list_bucket_dml_8.q.java1.8.out | 712 -----------
.../clientpositive/list_bucket_dml_8.q.out | 639 ++++++++++
.../list_bucket_dml_9.q.java1.7.out | 813 -------------
.../list_bucket_dml_9.q.java1.8.out | 915 --------------
.../clientpositive/list_bucket_dml_9.q.out | 811 +++++++++++++
.../clientpositive/llap/join0.q.java1.7.out | 242 ----
.../clientpositive/llap/join0.q.java1.8.out | 242 ----
.../results/clientpositive/llap/join0.q.out | 243 ++++
.../llap/vector_cast_constant.q.java1.7.out | 217 ----
.../llap/vector_cast_constant.q.java1.8.out | 217 ----
.../llap/vector_cast_constant.q.out | 216 ++++
.../clientpositive/outer_join_ppr.q.java1.7.out | 685 -----------
.../clientpositive/outer_join_ppr.q.java1.8.out | 855 -------------
.../results/clientpositive/outer_join_ppr.q.out | 683 +++++++++++
.../parquet_map_null.q.java1.7.out | 70 --
.../parquet_map_null.q.java1.8.out | 70 --
.../clientpositive/parquet_map_null.q.out | 68 ++
.../clientpositive/plan_json.q.java1.7.out | 13 -
.../clientpositive/plan_json.q.java1.8.out | 13 -
.../test/results/clientpositive/plan_json.q.out | 11 +
.../clientpositive/spark/join0.q.java1.7.out | 238 ----
.../clientpositive/spark/join0.q.java1.8.out | 238 ----
.../results/clientpositive/spark/join0.q.out | 20 +-
.../spark/list_bucket_dml_10.q.java1.7.out | 252 ----
.../spark/list_bucket_dml_10.q.java1.8.out | 280 -----
.../spark/list_bucket_dml_10.q.out | 250 ++++
.../spark/list_bucket_dml_2.q.java1.7.out | 591 ---------
.../spark/list_bucket_dml_2.q.java1.8.out | 663 -----------
.../spark/list_bucket_dml_2.q.out | Bin 28667 -> 27128 bytes
.../spark/outer_join_ppr.q.java1.7.out | 709 -----------
.../spark/outer_join_ppr.q.java1.8.out | 879 --------------
.../clientpositive/spark/outer_join_ppr.q.out | 490 ++------
.../spark/subquery_multiinsert.q.java1.7.out | 886 --------------
.../spark/subquery_multiinsert.q.java1.8.out | 890 --------------
.../spark/subquery_multiinsert.q.out | 56 +-
.../spark/vector_cast_constant.q.java1.7.out | 217 ----
.../spark/vector_cast_constant.q.java1.8.out | 203 ----
.../spark/vector_cast_constant.q.out | 54 +-
.../stats_list_bucket.q.java1.7.out | 191 ---
.../stats_list_bucket.q.java1.8.out | 193 ---
.../clientpositive/stats_list_bucket.q.out | 189 +++
.../clientpositive/str_to_map.q.java1.7.out | 220 ----
.../clientpositive/str_to_map.q.java1.8.out | 219 ----
.../results/clientpositive/str_to_map.q.out | 216 ++++
.../subquery_multiinsert.q.java1.7.out | 999 ----------------
.../subquery_multiinsert.q.java1.8.out | 999 ----------------
.../clientpositive/subquery_multiinsert.q.out | 997 ++++++++++++++++
.../subquery_notin_having.q.java1.7.out | 766 ------------
.../subquery_notin_having.q.java1.8.out | 762 ------------
.../clientpositive/subquery_notin_having.q.out | 764 ++++++++++++
.../clientpositive/tez/join0.q.java1.7.out | 239 ----
.../clientpositive/tez/join0.q.java1.8.out | 236 ----
.../test/results/clientpositive/tez/join0.q.out | 237 ++++
.../tez/vector_cast_constant.q.java1.7.out | 218 ----
.../tez/vector_cast_constant.q.java1.8.out | 216 ----
.../tez/vector_cast_constant.q.out | 214 ++++
.../clientpositive/varchar_udf1.q.java1.7.out | 457 -------
.../clientpositive/varchar_udf1.q.java1.8.out | 457 -------
.../results/clientpositive/varchar_udf1.q.out | 453 +++++++
.../vector_cast_constant.q.java1.7.out | 220 ----
.../vector_cast_constant.q.java1.8.out | 197 ---
.../clientpositive/vector_cast_constant.q.out | 53 +-
145 files changed, 13120 insertions(+), 32818 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientnegative/columnstats_partlvl_invalid_values.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientnegative/columnstats_partlvl_invalid_values.q b/ql/src/test/queries/clientnegative/columnstats_partlvl_invalid_values.q
index 712ece7..8521631 100644
--- a/ql/src/test/queries/clientnegative/columnstats_partlvl_invalid_values.q
+++ b/ql/src/test/queries/clientnegative/columnstats_partlvl_invalid_values.q
@@ -1,4 +1,3 @@
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE Employee_Part;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/authorization_explain.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/authorization_explain.q b/ql/src/test/queries/clientpositive/authorization_explain.q
index 6a9475c..d429704 100644
--- a/ql/src/test/queries/clientpositive/authorization_explain.q
+++ b/ql/src/test/queries/clientpositive/authorization_explain.q
@@ -2,7 +2,6 @@ set hive.security.authorization.manager=org.apache.hadoop.hive.ql.security.autho
set hive.mapred.mode=nonstrict;
set hive.security.authorization.enabled=true;
--- JAVA_VERSION_SPECIFIC_OUTPUT
explain authorization select * from src join srcpart;
explain formatted authorization select * from src join srcpart;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/avro_date.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/avro_date.q b/ql/src/test/queries/clientpositive/avro_date.q
index 15c07de..7169822 100644
--- a/ql/src/test/queries/clientpositive/avro_date.q
+++ b/ql/src/test/queries/clientpositive/avro_date.q
@@ -1,5 +1,4 @@
set hive.mapred.mode=nonstrict;
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE avro_date_staging;
DROP TABLE avro_date;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/avro_deserialize_map_null.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/avro_deserialize_map_null.q b/ql/src/test/queries/clientpositive/avro_deserialize_map_null.q
index 962e649..42258d9 100644
--- a/ql/src/test/queries/clientpositive/avro_deserialize_map_null.q
+++ b/ql/src/test/queries/clientpositive/avro_deserialize_map_null.q
@@ -4,7 +4,6 @@
-- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
-- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE IF EXISTS avro_table;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/avro_nullable_fields.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/avro_nullable_fields.q b/ql/src/test/queries/clientpositive/avro_nullable_fields.q
index 9ba7441..cb398d6 100644
--- a/ql/src/test/queries/clientpositive/avro_nullable_fields.q
+++ b/ql/src/test/queries/clientpositive/avro_nullable_fields.q
@@ -1,6 +1,5 @@
-- Verify that nullable fields properly work
--- JAVA_VERSION_SPECIFIC_OUTPUT
CREATE TABLE test_serializer(string1 STRING,
int1 INT,
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/avro_timestamp.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/avro_timestamp.q b/ql/src/test/queries/clientpositive/avro_timestamp.q
index 7bf0dc8..847f250 100644
--- a/ql/src/test/queries/clientpositive/avro_timestamp.q
+++ b/ql/src/test/queries/clientpositive/avro_timestamp.q
@@ -1,7 +1,6 @@
set hive.mapred.mode=nonstrict;
-- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
-- EXCLUDE_OS_WINDOWS
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE avro_timestamp_staging;
DROP TABLE avro_timestamp;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/cbo_rp_outer_join_ppr.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/cbo_rp_outer_join_ppr.q b/ql/src/test/queries/clientpositive/cbo_rp_outer_join_ppr.q
index c497ce9..d8f726e 100644
--- a/ql/src/test/queries/clientpositive/cbo_rp_outer_join_ppr.q
+++ b/ql/src/test/queries/clientpositive/cbo_rp_outer_join_ppr.q
@@ -4,7 +4,6 @@ set hive.cbo.returnpath.hiveop=true;
set hive.optimize.ppd=true;
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
EXPLAIN EXTENDED
FROM
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/char_udf1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/char_udf1.q b/ql/src/test/queries/clientpositive/char_udf1.q
index 09012b4..39aa0e0 100644
--- a/ql/src/test/queries/clientpositive/char_udf1.q
+++ b/ql/src/test/queries/clientpositive/char_udf1.q
@@ -4,7 +4,6 @@ create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20));
insert overwrite table char_udf_1
select key, value, key, value from src where key = '238' limit 1;
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- UDFs with char support
select
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/input4.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/input4.q b/ql/src/test/queries/clientpositive/input4.q
index 83edbe2..90fcbdd 100644
--- a/ql/src/test/queries/clientpositive/input4.q
+++ b/ql/src/test/queries/clientpositive/input4.q
@@ -1,4 +1,3 @@
--- JAVA_VERSION_SPECIFIC_OUTPUT
CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE;
EXPLAIN
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/join0.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/join0.q b/ql/src/test/queries/clientpositive/join0.q
index 66f2ef3..3252847 100644
--- a/ql/src/test/queries/clientpositive/join0.q
+++ b/ql/src/test/queries/clientpositive/join0.q
@@ -1,6 +1,5 @@
set hive.mapred.mode=nonstrict;
set hive.explain.user=false;
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- SORT_QUERY_RESULTS
EXPLAIN
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_10.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_10.q b/ql/src/test/queries/clientpositive/list_bucket_dml_10.q
index 5d3dade..f25c174 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_10.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_10.q
@@ -1,7 +1,6 @@
set mapred.input.dir.recursive=true;
-- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- list bucketing DML: static partition. multiple skewed columns.
-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_11.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_11.q b/ql/src/test/queries/clientpositive/list_bucket_dml_11.q
index 2d22d66..8ac1627 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_11.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_11.q
@@ -6,7 +6,6 @@ set hive.merge.mapredfiles=false;
-- Ensure it works if skewed column is not the first column in the table columns
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- list bucketing DML: static partition. multiple skewed columns.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_12.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_12.q b/ql/src/test/queries/clientpositive/list_bucket_dml_12.q
index ac063cc..9facfa5 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_12.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_12.q
@@ -7,7 +7,6 @@ set hive.merge.mapredfiles=false;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_13.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_13.q b/ql/src/test/queries/clientpositive/list_bucket_dml_13.q
index d68ca93..0fe7f61 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_13.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_13.q
@@ -7,7 +7,6 @@ set hive.merge.mapredfiles=false;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_2.q b/ql/src/test/queries/clientpositive/list_bucket_dml_2.q
index 263a002..c6dceab 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_2.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_2.q
@@ -10,7 +10,6 @@ set hive.stats.reliable=true;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- list bucketing DML: static partition. multiple skewed columns.
-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_4.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_4.q b/ql/src/test/queries/clientpositive/list_bucket_dml_4.q
index 86ff342..950409d 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_4.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_4.q
@@ -9,7 +9,6 @@ set hive.merge.mapredfiles=false;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- list bucketing DML: static partition. multiple skewed columns. merge.
-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_5.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_5.q b/ql/src/test/queries/clientpositive/list_bucket_dml_5.q
index ace7ba9..fce8e2e 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_5.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_5.q
@@ -10,7 +10,6 @@ set mapred.input.dir.recursive=true;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- create a skewed table
create table list_bucketing_dynamic_part (key String, value String)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_6.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_6.q b/ql/src/test/queries/clientpositive/list_bucket_dml_6.q
index 5684788..631c938 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_6.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_6.q
@@ -47,7 +47,6 @@ set hive.merge.mapredfiles=false;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- create a skewed table
create table list_bucketing_dynamic_part (key String, value String)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_8.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_8.q b/ql/src/test/queries/clientpositive/list_bucket_dml_8.q
index d904543..6d73896 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_8.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_8.q
@@ -48,7 +48,6 @@ set hive.merge.mapredfiles=false;
-- 118 000002_0
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- create a skewed table
create table list_bucketing_dynamic_part (key String, value String)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/list_bucket_dml_9.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/list_bucket_dml_9.q b/ql/src/test/queries/clientpositive/list_bucket_dml_9.q
index 620750c..d2e24af 100644
--- a/ql/src/test/queries/clientpositive/list_bucket_dml_9.q
+++ b/ql/src/test/queries/clientpositive/list_bucket_dml_9.q
@@ -9,7 +9,6 @@ set hive.merge.mapredfiles=false;
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- list bucketing DML: static partition. multiple skewed columns. merge.
-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/outer_join_ppr.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/outer_join_ppr.q b/ql/src/test/queries/clientpositive/outer_join_ppr.q
index 497a4d1..60a06ae 100644
--- a/ql/src/test/queries/clientpositive/outer_join_ppr.q
+++ b/ql/src/test/queries/clientpositive/outer_join_ppr.q
@@ -2,7 +2,6 @@ set hive.mapred.mode=nonstrict;
set hive.optimize.ppd=true;
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
EXPLAIN EXTENDED
FROM
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/parquet_map_null.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/parquet_map_null.q b/ql/src/test/queries/clientpositive/parquet_map_null.q
index 61058f3..e154159 100644
--- a/ql/src/test/queries/clientpositive/parquet_map_null.q
+++ b/ql/src/test/queries/clientpositive/parquet_map_null.q
@@ -1,5 +1,4 @@
-- This test attempts to write a parquet table from an avro table that contains map null values
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE IF EXISTS avro_table;
DROP TABLE IF EXISTS parquet_table;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/plan_json.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/plan_json.q b/ql/src/test/queries/clientpositive/plan_json.q
index aa2b134..503b55d 100644
--- a/ql/src/test/queries/clientpositive/plan_json.q
+++ b/ql/src/test/queries/clientpositive/plan_json.q
@@ -1,5 +1,4 @@
-- explain plan json: the query gets the formatted json output of the query plan of the hive query
--- JAVA_VERSION_SPECIFIC_OUTPUT
EXPLAIN FORMATTED SELECT count(1) FROM src;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/stats_list_bucket.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/stats_list_bucket.q b/ql/src/test/queries/clientpositive/stats_list_bucket.q
index 51137a8..536702c 100644
--- a/ql/src/test/queries/clientpositive/stats_list_bucket.q
+++ b/ql/src/test/queries/clientpositive/stats_list_bucket.q
@@ -1,6 +1,5 @@
-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
drop table stats_list_bucket;
drop table stats_list_bucket_1;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/str_to_map.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/str_to_map.q b/ql/src/test/queries/clientpositive/str_to_map.q
index f2993b1..3280d89 100644
--- a/ql/src/test/queries/clientpositive/str_to_map.q
+++ b/ql/src/test/queries/clientpositive/str_to_map.q
@@ -1,7 +1,6 @@
set hive.mapred.mode=nonstrict;
set hive.fetch.task.conversion=more;
--- JAVA_VERSION_SPECIFIC_OUTPUT
desc function str_to_map;
desc function extended str_to_map;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/subquery_multiinsert.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/subquery_multiinsert.q b/ql/src/test/queries/clientpositive/subquery_multiinsert.q
index bea2e13..9d70f51 100644
--- a/ql/src/test/queries/clientpositive/subquery_multiinsert.q
+++ b/ql/src/test/queries/clientpositive/subquery_multiinsert.q
@@ -2,7 +2,6 @@ set hive.mapred.mode=nonstrict;
set hive.exec.post.hooks=org.apache.hadoop.hive.ql.hooks.PostExecutePrinter,org.apache.hadoop.hive.ql.hooks.PrintCompletedTasksHook;
-- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
CREATE TABLE src_4(
key STRING,
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/subquery_notin_having.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/subquery_notin_having.q b/ql/src/test/queries/clientpositive/subquery_notin_having.q
index 8b2914d..05148df 100644
--- a/ql/src/test/queries/clientpositive/subquery_notin_having.q
+++ b/ql/src/test/queries/clientpositive/subquery_notin_having.q
@@ -1,6 +1,5 @@
set hive.mapred.mode=nonstrict;
-- non agg, non corr
--- JAVA_VERSION_SPECIFIC_OUTPUT
explain
select key, count(*)
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/varchar_udf1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/varchar_udf1.q b/ql/src/test/queries/clientpositive/varchar_udf1.q
index ff40b31..4d1f884 100644
--- a/ql/src/test/queries/clientpositive/varchar_udf1.q
+++ b/ql/src/test/queries/clientpositive/varchar_udf1.q
@@ -4,7 +4,6 @@ create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)
insert overwrite table varchar_udf_1
select key, value, key, value from src where key = '238' limit 1;
--- JAVA_VERSION_SPECIFIC_OUTPUT
-- UDFs with varchar support
select
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/queries/clientpositive/vector_cast_constant.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/vector_cast_constant.q b/ql/src/test/queries/clientpositive/vector_cast_constant.q
index c50dd8f..94bee09 100644
--- a/ql/src/test/queries/clientpositive/vector_cast_constant.q
+++ b/ql/src/test/queries/clientpositive/vector_cast_constant.q
@@ -2,7 +2,6 @@ set hive.mapred.mode=nonstrict;
set hive.explain.user=false;
SET hive.vectorized.execution.enabled=true;
--- JAVA_VERSION_SPECIFIC_OUTPUT
DROP TABLE over1k;
DROP TABLE over1korc;
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.7.out b/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.7.out
deleted file mode 100644
index 4ea70e3..0000000
--- a/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.7.out
+++ /dev/null
@@ -1,73 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE Employee_Part
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE Employee_Part
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
-row format delimited fields terminated by '|' stored as textfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@Employee_Part
-POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
-row format delimited fields terminated by '|' stored as textfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@Employee_Part
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=UK
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=4000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3500.0/country=UK
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=UK
-FAILED: SemanticException [Error 30007]: Invalid partitioning key/value specified in ANALYZE statement : {employeesalary=4000.0, country=Canada}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.8.out b/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.8.out
deleted file mode 100644
index 7cae55e..0000000
--- a/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.java1.8.out
+++ /dev/null
@@ -1,73 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE Employee_Part
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE Employee_Part
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
-row format delimited fields terminated by '|' stored as textfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@Employee_Part
-POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
-row format delimited fields terminated by '|' stored as textfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@Employee_Part
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=UK
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=4000.0/country=USA
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3500.0/country=UK
-PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@employee_part
-POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@employee_part
-POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=UK
-FAILED: SemanticException [Error 30007]: Invalid partitioning key/value specified in ANALYZE statement : {country=Canada, employeesalary=4000.0}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.out b/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.out
new file mode 100644
index 0000000..3261f78
--- /dev/null
+++ b/ql/src/test/results/clientnegative/columnstats_partlvl_invalid_values.q.out
@@ -0,0 +1,69 @@
+PREHOOK: query: DROP TABLE Employee_Part
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE Employee_Part
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
+row format delimited fields terminated by '|' stored as textfile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@Employee_Part
+POSTHOOK: query: CREATE TABLE Employee_Part(employeeID int, employeeName String) partitioned by (employeeSalary double, country string)
+row format delimited fields terminated by '|' stored as textfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@Employee_Part
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='USA')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=USA
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='2000.0', country='UK')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=2000.0/country=UK
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='USA')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=USA
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='4000.0', country='USA')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=4000.0/country=USA
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3500.0', country='UK')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=3500.0/country=UK
+PREHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@employee_part
+POSTHOOK: query: LOAD DATA LOCAL INPATH "../../data/files/employee2.dat" INTO TABLE Employee_Part partition(employeeSalary='3000.0', country='UK')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@employee_part
+POSTHOOK: Output: default@employee_part@employeesalary=3000.0/country=UK
+FAILED: SemanticException [Error 30007]: Invalid partitioning key/value specified in ANALYZE statement : {employeesalary=4000.0, country=Canada}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out b/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out
deleted file mode 100644
index fefb50c..0000000
--- a/ql/src/test/results/clientpositive/authorization_explain.q.java1.7.out
+++ /dev/null
@@ -1,44 +0,0 @@
-Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain authorization select * from src join srcpart
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain authorization select * from src join srcpart
-POSTHOOK: type: QUERY
-INPUTS:
- default@src
- default@srcpart
- default@srcpart@ds=2008-04-08/hr=11
- default@srcpart@ds=2008-04-08/hr=12
- default@srcpart@ds=2008-04-09/hr=11
- default@srcpart@ds=2008-04-09/hr=12
-OUTPUTS:
-#### A masked pattern was here ####
-CURRENT_USER:
- hive_test_user
-OPERATION:
- QUERY
-Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: explain formatted authorization select * from src join srcpart
-PREHOOK: type: QUERY
-POSTHOOK: query: explain formatted authorization select * from src join srcpart
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-PREHOOK: query: explain authorization use default
-PREHOOK: type: SWITCHDATABASE
-POSTHOOK: query: explain authorization use default
-POSTHOOK: type: SWITCHDATABASE
-INPUTS:
- database:default
-OUTPUTS:
-CURRENT_USER:
- hive_test_user
-OPERATION:
- SWITCHDATABASE
-PREHOOK: query: explain formatted authorization use default
-PREHOOK: type: SWITCHDATABASE
-POSTHOOK: query: explain formatted authorization use default
-POSTHOOK: type: SWITCHDATABASE
-{"INPUTS":["database:default"],"OUTPUTS":[],"CURRENT_USER":"hive_test_user","OPERATION":"SWITCHDATABASE"}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/authorization_explain.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/authorization_explain.q.java1.8.out b/ql/src/test/results/clientpositive/authorization_explain.q.java1.8.out
deleted file mode 100644
index b7ec209..0000000
--- a/ql/src/test/results/clientpositive/authorization_explain.q.java1.8.out
+++ /dev/null
@@ -1,47 +0,0 @@
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain authorization select * from src join srcpart
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain authorization select * from src join srcpart
-POSTHOOK: type: QUERY
-INPUTS:
- default@src
- default@srcpart
- default@srcpart@ds=2008-04-08/hr=11
- default@srcpart@ds=2008-04-08/hr=12
- default@srcpart@ds=2008-04-09/hr=11
- default@srcpart@ds=2008-04-09/hr=12
-OUTPUTS:
-#### A masked pattern was here ####
-CURRENT_USER:
- hive_test_user
-OPERATION:
- QUERY
-AUTHORIZATION_FAILURES:
- No privilege 'Select' found for inputs { database:default, table:src, columnName:key}
- No privilege 'Select' found for inputs { database:default, table:srcpart, columnName:key}
-Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: explain formatted authorization select * from src join srcpart
-PREHOOK: type: QUERY
-POSTHOOK: query: explain formatted authorization select * from src join srcpart
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-PREHOOK: query: explain authorization use default
-PREHOOK: type: SWITCHDATABASE
-POSTHOOK: query: explain authorization use default
-POSTHOOK: type: SWITCHDATABASE
-INPUTS:
- database:default
-OUTPUTS:
-CURRENT_USER:
- hive_test_user
-OPERATION:
- SWITCHDATABASE
-PREHOOK: query: explain formatted authorization use default
-PREHOOK: type: SWITCHDATABASE
-POSTHOOK: query: explain formatted authorization use default
-POSTHOOK: type: SWITCHDATABASE
-{"INPUTS":["database:default"],"OUTPUTS":[],"CURRENT_USER":"hive_test_user","OPERATION":"SWITCHDATABASE"}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/authorization_explain.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/authorization_explain.q.out b/ql/src/test/results/clientpositive/authorization_explain.q.out
new file mode 100644
index 0000000..851b845
--- /dev/null
+++ b/ql/src/test/results/clientpositive/authorization_explain.q.out
@@ -0,0 +1,40 @@
+Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain authorization select * from src join srcpart
+PREHOOK: type: QUERY
+POSTHOOK: query: explain authorization select * from src join srcpart
+POSTHOOK: type: QUERY
+INPUTS:
+ default@src
+ default@srcpart
+ default@srcpart@ds=2008-04-08/hr=11
+ default@srcpart@ds=2008-04-08/hr=12
+ default@srcpart@ds=2008-04-09/hr=11
+ default@srcpart@ds=2008-04-09/hr=12
+OUTPUTS:
+#### A masked pattern was here ####
+CURRENT_USER:
+ hive_test_user
+OPERATION:
+ QUERY
+Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain formatted authorization select * from src join srcpart
+PREHOOK: type: QUERY
+POSTHOOK: query: explain formatted authorization select * from src join srcpart
+POSTHOOK: type: QUERY
+#### A masked pattern was here ####
+PREHOOK: query: explain authorization use default
+PREHOOK: type: SWITCHDATABASE
+POSTHOOK: query: explain authorization use default
+POSTHOOK: type: SWITCHDATABASE
+INPUTS:
+ database:default
+OUTPUTS:
+CURRENT_USER:
+ hive_test_user
+OPERATION:
+ SWITCHDATABASE
+PREHOOK: query: explain formatted authorization use default
+PREHOOK: type: SWITCHDATABASE
+POSTHOOK: query: explain formatted authorization use default
+POSTHOOK: type: SWITCHDATABASE
+{"INPUTS":["database:default"],"OUTPUTS":[],"CURRENT_USER":"hive_test_user","OPERATION":"SWITCHDATABASE"}
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_date.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_date.q.java1.7.out b/ql/src/test/results/clientpositive/avro_date.q.java1.7.out
deleted file mode 100644
index 501b983..0000000
--- a/ql/src/test/results/clientpositive/avro_date.q.java1.7.out
+++ /dev/null
@@ -1,130 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_date_staging
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_date_staging
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_date
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_date
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_date_casts
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_date_casts
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_date_staging
-POSTHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_date_staging
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_date_staging
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_date_staging
-PREHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
- PARTITIONED BY (p1 int, p2 date)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_date
-POSTHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
- PARTITIONED BY (p1 int, p2 date)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_date
-PREHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date_staging
-PREHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
-POSTHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date_staging
-POSTHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).d SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:d, type:date, comment:null), ]
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).l1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:l1, type:array<date>, comment:null), ]
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).m1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:m1, type:map<string,date>, comment:null), ]
-PREHOOK: query: SELECT * FROM avro_date
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"foo":"1980-12-16","bar":"1998-05-07"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-1947-02-11 1
-2012-02-21 1
-2014-02-11 1
-8200-02-11 1
-PREHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"foo":"1980-12-16","bar":"1998-05-07"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"foo":"1980-12-16","bar":"1998-05-07"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_date.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_date.q.java1.8.out b/ql/src/test/results/clientpositive/avro_date.q.java1.8.out
deleted file mode 100644
index dea51c6..0000000
--- a/ql/src/test/results/clientpositive/avro_date.q.java1.8.out
+++ /dev/null
@@ -1,130 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_date_staging
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_date_staging
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_date
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_date
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_date_casts
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_date_casts
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_date_staging
-POSTHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_date_staging
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_date_staging
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_date_staging
-PREHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
- PARTITIONED BY (p1 int, p2 date)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_date
-POSTHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
- PARTITIONED BY (p1 int, p2 date)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_date
-PREHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date_staging
-PREHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
-POSTHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date_staging
-POSTHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).d SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:d, type:date, comment:null), ]
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).l1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:l1, type:array<date>, comment:null), ]
-POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).m1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:m1, type:map<string,date>, comment:null), ]
-PREHOOK: query: SELECT * FROM avro_date
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-1947-02-11 1
-2012-02-21 1
-2014-02-11 1
-8200-02-11 1
-PREHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
-2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
-1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
-PREHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_date
-PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_date
-POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
-#### A masked pattern was here ####
-8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_date.q.out b/ql/src/test/results/clientpositive/avro_date.q.out
new file mode 100644
index 0000000..32501cf
--- /dev/null
+++ b/ql/src/test/results/clientpositive/avro_date.q.out
@@ -0,0 +1,126 @@
+PREHOOK: query: DROP TABLE avro_date_staging
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE avro_date_staging
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE avro_date
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE avro_date
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE avro_date_casts
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE avro_date_casts
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_date_staging
+POSTHOOK: query: CREATE TABLE avro_date_staging (d date, m1 map<string, date>, l1 array<date>)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_date_staging
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@avro_date_staging
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_date.txt' OVERWRITE INTO TABLE avro_date_staging
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@avro_date_staging
+PREHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
+ PARTITIONED BY (p1 int, p2 date)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_date
+POSTHOOK: query: CREATE TABLE avro_date (d date, m1 map<string, date>, l1 array<date>)
+ PARTITIONED BY (p1 int, p2 date)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_date
+PREHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date_staging
+PREHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
+POSTHOOK: query: INSERT OVERWRITE TABLE avro_date PARTITION(p1=2, p2='2014-09-26') SELECT * FROM avro_date_staging
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date_staging
+POSTHOOK: Output: default@avro_date@p1=2/p2=2014-09-26
+POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).d SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:d, type:date, comment:null), ]
+POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).l1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:l1, type:array<date>, comment:null), ]
+POSTHOOK: Lineage: avro_date PARTITION(p1=2,p2=2014-09-26).m1 SIMPLE [(avro_date_staging)avro_date_staging.FieldSchema(name:m1, type:map<string,date>, comment:null), ]
+PREHOOK: query: SELECT * FROM avro_date
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date
+PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_date
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date
+POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
+2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
+1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
+8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
+PREHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date
+PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d, COUNT(d) FROM avro_date GROUP BY d
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date
+POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+1947-02-11 1
+2012-02-21 1
+2014-02-11 1
+8200-02-11 1
+PREHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date
+PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_date WHERE d!='1947-02-11'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date
+POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
+2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
+8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
+PREHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date
+PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_date WHERE d<'2014-12-21'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date
+POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+2012-02-21 {"bar":"1998-05-07","foo":"1980-12-16"} ["2011-09-04","2011-09-05"] 2 2014-09-26
+2014-02-11 {"baz":"1981-12-16"} ["2011-09-05"] 2 2014-09-26
+1947-02-11 {"baz":"1921-12-16"} ["2011-09-05"] 2 2014-09-26
+PREHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_date
+PREHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_date WHERE d>'8000-12-01'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_date
+POSTHOOK: Input: default@avro_date@p1=2/p2=2014-09-26
+#### A masked pattern was here ####
+8200-02-11 {"baz":"6981-12-16"} ["1039-09-05"] 2 2014-09-26
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.7.out b/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.7.out
deleted file mode 100644
index 8f8065e..0000000
--- a/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.7.out
+++ /dev/null
@@ -1,57 +0,0 @@
-PREHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
--- vs record schema have the null values in different positions
--- i.e.
--- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
--- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
--- vs record schema have the null values in different positions
--- i.e.
--- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
--- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: SELECT * FROM avro_table
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_table
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_table
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_table
-#### A masked pattern was here ####
-{"key4":null,"key3":"val3"}
-{"key4":null,"key3":"val3"}
-{"key2":"val2","key1":null}
-{"key4":null,"key3":"val3"}
-{"key4":null,"key3":"val3"}
-PREHOOK: query: DROP TABLE avro_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: DROP TABLE avro_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: default@avro_table
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.8.out b/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.8.out
deleted file mode 100644
index 127d8b3..0000000
--- a/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.java1.8.out
+++ /dev/null
@@ -1,57 +0,0 @@
-PREHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
--- vs record schema have the null values in different positions
--- i.e.
--- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
--- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
--- vs record schema have the null values in different positions
--- i.e.
--- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
--- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE IF EXISTS avro_table
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_table
-PREHOOK: query: SELECT * FROM avro_table
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_table
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_table
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_table
-#### A masked pattern was here ####
-{"key3":"val3","key4":null}
-{"key3":"val3","key4":null}
-{"key1":null,"key2":"val2"}
-{"key3":"val3","key4":null}
-{"key3":"val3","key4":null}
-PREHOOK: query: DROP TABLE avro_table
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@avro_table
-PREHOOK: Output: default@avro_table
-POSTHOOK: query: DROP TABLE avro_table
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@avro_table
-POSTHOOK: Output: default@avro_table
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.out b/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.out
new file mode 100644
index 0000000..2d983f1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/avro_deserialize_map_null.q.out
@@ -0,0 +1,55 @@
+PREHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
+-- vs record schema have the null values in different positions
+-- i.e.
+-- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
+-- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
+
+
+DROP TABLE IF EXISTS avro_table
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: -- These test attempts to deserialize an Avro file that contains map null values, and the file schema
+-- vs record schema have the null values in different positions
+-- i.e.
+-- fileSchema = [{ "type" : "map", "values" : ["string","null"]}, "null"]
+-- recordSchema = ["null", { "type" : "map", "values" : ["string","null"]}]
+
+
+DROP TABLE IF EXISTS avro_table
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: CREATE TABLE avro_table (avreau_col_1 map<string,string>) STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_table
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/map_null_val.avro' OVERWRITE INTO TABLE avro_table
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@avro_table
+PREHOOK: query: SELECT * FROM avro_table
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_table
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_table
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_table
+#### A masked pattern was here ####
+{"key3":"val3","key4":null}
+{"key3":"val3","key4":null}
+{"key1":null,"key2":"val2"}
+{"key3":"val3","key4":null}
+{"key3":"val3","key4":null}
+PREHOOK: query: DROP TABLE avro_table
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@avro_table
+PREHOOK: Output: default@avro_table
+POSTHOOK: query: DROP TABLE avro_table
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@avro_table
+POSTHOOK: Output: default@avro_table
[02/48] hive git commit: HIVE-13720. Fix failing test -
TestLlapTaskCommunicator. (Siddharth Seth, reviewed by Sergey Shelukhin)
Posted by sp...@apache.org.
HIVE-13720. Fix failing test - TestLlapTaskCommunicator. (Siddharth Seth, reviewed by Sergey Shelukhin)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b93ce782
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b93ce782
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b93ce782
Branch: refs/heads/java8
Commit: b93ce7825ef095bfcf1bd3474f110773c35ea9ab
Parents: d52131d
Author: Siddharth Seth <ss...@apache.org>
Authored: Wed May 25 14:58:34 2016 -0700
Committer: Siddharth Seth <ss...@apache.org>
Committed: Wed May 25 14:58:34 2016 -0700
----------------------------------------------------------------------
.../hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/b93ce782/llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java
----------------------------------------------------------------------
diff --git a/llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java b/llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java
index 8e2d0ac..1901328 100644
--- a/llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java
+++ b/llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskCommunicator.java
@@ -36,6 +36,7 @@ import java.util.concurrent.locks.ReentrantLock;
import com.google.common.collect.Lists;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.hive.llap.LlapNodeId;
import org.apache.hadoop.hive.llap.daemon.rpc.LlapDaemonProtocolProtos;
import org.apache.hadoop.hive.llap.tez.LlapProtocolClientProxy;
@@ -273,11 +274,15 @@ public class TestLlapTaskCommunicator {
final TezVertexID vertexId1 = TezVertexID.getInstance(dagid, 300);
final TezVertexID vertexId2 = TezVertexID.getInstance(dagid, 301);
final Configuration conf = new Configuration(false);
- final UserPayload userPayload = TezUtils.createUserPayloadFromConf(conf);
+ final UserPayload userPayload;
final LlapTaskCommunicatorForTest taskCommunicator;
public LlapTaskCommunicatorWrapperForTest(LlapProtocolClientProxy llapProxy) throws Exception {
+
+ HiveConf.setVar(conf, HiveConf.ConfVars.LLAP_DAEMON_SERVICE_HOSTS, "fake-non-zk-cluster");
+ userPayload = TezUtils.createUserPayloadFromConf(conf);
+
doReturn(appAttemptId).when(taskCommunicatorContext).getApplicationAttemptId();
doReturn(new Credentials()).when(taskCommunicatorContext).getAMCredentials();
doReturn(userPayload).when(taskCommunicatorContext).getInitialUserPayload();
[10/48] hive git commit: HIVE-13149: Remove some unnecessary HMS
connections from HS2 (Reviewed by Jimmy Xiang, Szehon Ho, Chaoyu Tang)
Posted by sp...@apache.org.
HIVE-13149: Remove some unnecessary HMS connections from HS2 (Reviewed by Jimmy Xiang, Szehon Ho, Chaoyu Tang)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/9bebaf61
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/9bebaf61
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/9bebaf61
Branch: refs/heads/java8
Commit: 9bebaf6196c1842c285bfbad50765170e064f6e4
Parents: 76130a9
Author: Aihua Xu <ai...@apache.org>
Authored: Fri Apr 22 10:58:59 2016 -0400
Committer: Aihua Xu <ai...@apache.org>
Committed: Thu May 26 09:28:25 2016 -0400
----------------------------------------------------------------------
.../hive/metastore/TestMetastoreVersion.java | 7 ++--
.../hbase/TestHBaseMetastoreMetrics.java | 4 +--
.../apache/hive/jdbc/TestJdbcWithMiniHS2.java | 37 +++++++++++++++++---
.../hadoop/hive/hbase/HBaseQTestUtil.java | 6 ++++
.../hadoop/hive/hbase/HBaseTestSetup.java | 3 --
.../org/apache/hadoop/hive/ql/QTestUtil.java | 14 +++++---
.../hive/metastore/HiveMetaStoreClient.java | 10 +++---
.../hadoop/hive/ql/session/SessionState.java | 8 -----
8 files changed, 59 insertions(+), 30 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/TestMetastoreVersion.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/TestMetastoreVersion.java b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/TestMetastoreVersion.java
index 53f0d0e..5ceb3d2 100644
--- a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/TestMetastoreVersion.java
+++ b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/TestMetastoreVersion.java
@@ -19,7 +19,6 @@ package org.apache.hadoop.hive.metastore;
import java.io.File;
import java.lang.reflect.Field;
-import java.util.Random;
import junit.framework.TestCase;
@@ -32,6 +31,7 @@ import org.apache.hive.common.util.HiveStringUtils;
import org.apache.hadoop.hive.metastore.api.MetaException;
import org.apache.hadoop.hive.metastore.ObjectStore;
import org.apache.hadoop.hive.ql.Driver;
+import org.apache.hadoop.hive.ql.metadata.Hive;
import org.apache.hadoop.hive.ql.processors.CommandProcessorResponse;
import org.apache.hadoop.hive.ql.session.SessionState;
@@ -96,8 +96,9 @@ public class TestMetastoreVersion extends TestCase {
// session creation should fail since the schema didn't get created
try {
SessionState.start(new CliSessionState(hiveConf));
- fail("Expected exception");
- } catch (RuntimeException re) {
+ Hive.get(hiveConf).getMSC();
+ fail("An exception is expected since schema is not created.");
+ } catch (Exception re) {
LOG.info("Exception in testVersionRestriction: " + re, re);
String msg = HiveStringUtils.stringifyException(re);
assertTrue("Expected 'Version information not found in metastore' in: " + msg, msg
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/hbase/TestHBaseMetastoreMetrics.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/hbase/TestHBaseMetastoreMetrics.java b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/hbase/TestHBaseMetastoreMetrics.java
index 3ed88f2..aefafe0 100644
--- a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/hbase/TestHBaseMetastoreMetrics.java
+++ b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/metastore/hbase/TestHBaseMetastoreMetrics.java
@@ -41,8 +41,6 @@ import java.io.IOException;
*/
public class TestHBaseMetastoreMetrics extends HBaseIntegrationTests {
- private CodahaleMetrics metrics;
-
@BeforeClass
public static void startup() throws Exception {
HBaseIntegrationTests.startMiniCluster();
@@ -66,7 +64,6 @@ public class TestHBaseMetastoreMetrics extends HBaseIntegrationTests {
conf.setVar(HiveConf.ConfVars.HIVE_METRICS_REPORTER, MetricsReporting.JSON_FILE.name() + "," + MetricsReporting.JMX.name());
SessionState.start(new CliSessionState(conf));
driver = new Driver(conf);
- metrics = (CodahaleMetrics) MetricsFactory.getInstance();
}
@Test
@@ -107,6 +104,7 @@ public class TestHBaseMetastoreMetrics extends HBaseIntegrationTests {
driver.run("use default");
driver.run("drop database tempdb cascade");
+ CodahaleMetrics metrics = (CodahaleMetrics) MetricsFactory.getInstance();
String json = metrics.dumpJson();
MetricsTestUtils.verifyMetricsJson(json, MetricsTestUtils.COUNTER, MetricsConstant.CREATE_TOTAL_DATABASES, 2);
MetricsTestUtils.verifyMetricsJson(json, MetricsTestUtils.COUNTER, MetricsConstant.CREATE_TOTAL_TABLES, 7);
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java b/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
index 815ccfa..4aa98ca 100644
--- a/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
+++ b/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
@@ -86,9 +86,8 @@ public class TestJdbcWithMiniHS2 {
miniHS2.start(confOverlay);
}
- @Before
- public void setUp() throws Exception {
- hs2Conn = getConnection(miniHS2.getJdbcURL(), System.getProperty("user.name"), "bar");
+ private Connection getConnection() throws Exception {
+ return getConnection(miniHS2.getJdbcURL(), System.getProperty("user.name"), "bar");
}
private Connection getConnection(String jdbcURL, String user, String pwd) throws SQLException {
@@ -99,7 +98,9 @@ public class TestJdbcWithMiniHS2 {
@After
public void tearDown() throws Exception {
- hs2Conn.close();
+ if (hs2Conn != null) {
+ hs2Conn.close();
+ }
}
@AfterClass
@@ -112,6 +113,7 @@ public class TestJdbcWithMiniHS2 {
@Test
public void testConnection() throws Exception {
String tableName = "testTab1";
+ hs2Conn = getConnection();
Statement stmt = hs2Conn.createStatement();
// create table
@@ -133,6 +135,7 @@ public class TestJdbcWithMiniHS2 {
@Test
public void testConcurrentStatements() throws Exception {
String tableName = "testConcurrentStatements";
+ hs2Conn = getConnection();
Statement stmt = hs2Conn.createStatement();
// create table
@@ -311,6 +314,7 @@ public class TestJdbcWithMiniHS2 {
stmt.execute(" drop table if exists table_in_non_default_schema");
expected = stmt.execute("DROP DATABASE "+ dbName);
stmt.close();
+ hs2Conn.close();
hs2Conn = getConnection(jdbcUri+"default",System.getProperty("user.name"),"bar");
stmt = hs2Conn .createStatement();
@@ -344,6 +348,7 @@ public class TestJdbcWithMiniHS2 {
* get/set Schema are new in JDK7 and not available in java.sql.Connection in JDK6.
* Hence the test uses HiveConnection object to call these methods so that test will run with older JDKs
*/
+ hs2Conn = getConnection();
HiveConnection hiveConn = (HiveConnection)hs2Conn;
assertEquals("default", hiveConn.getSchema());
@@ -377,6 +382,7 @@ public class TestJdbcWithMiniHS2 {
*/
private void verifyCurrentDB(String expectedDbName, Connection hs2Conn) throws Exception {
String verifyTab = "miniHS2DbVerificationTable";
+ hs2Conn = getConnection();
Statement stmt = hs2Conn.createStatement();
stmt.execute("DROP TABLE IF EXISTS " + expectedDbName + "." + verifyTab);
stmt.execute("CREATE TABLE " + expectedDbName + "." + verifyTab + "(id INT)");
@@ -582,6 +588,7 @@ public class TestJdbcWithMiniHS2 {
// Downloaded resources dir
scratchDirPath = new Path(HiveConf.getVar(conf, HiveConf.ConfVars.DOWNLOADED_RESOURCES_DIR));
verifyScratchDir(conf, fs, scratchDirPath, expectedFSPermission, userName, true);
+ hs2Conn.close();
// 2. Test with doAs=true
// Restart HiveServer2 with doAs=true
@@ -608,6 +615,7 @@ public class TestJdbcWithMiniHS2 {
// Downloaded resources dir
scratchDirPath = new Path(HiveConf.getVar(conf, HiveConf.ConfVars.DOWNLOADED_RESOURCES_DIR));
verifyScratchDir(conf, fs, scratchDirPath, expectedFSPermission, userName, true);
+ hs2Conn.close();
// Test for user "trinity"
userName = "trinity";
@@ -639,6 +647,7 @@ public class TestJdbcWithMiniHS2 {
HiveConf testConf = new HiveConf();
assertTrue(testConf.getVar(ConfVars.HIVE_SERVER2_BUILTIN_UDF_WHITELIST).isEmpty());
// verify that udf in default whitelist can be executed
+ hs2Conn = getConnection();
Statement stmt = hs2Conn.createStatement();
stmt.executeQuery("SELECT substr('foobar', 4) ");
hs2Conn.close();
@@ -680,10 +689,11 @@ public class TestJdbcWithMiniHS2 {
public void testUdfBlackList() throws Exception {
HiveConf testConf = new HiveConf();
assertTrue(testConf.getVar(ConfVars.HIVE_SERVER2_BUILTIN_UDF_BLACKLIST).isEmpty());
-
+ hs2Conn = getConnection();
Statement stmt = hs2Conn.createStatement();
// verify that udf in default whitelist can be executed
stmt.executeQuery("SELECT substr('foobar', 4) ");
+ hs2Conn.close();
miniHS2.stop();
testConf.setVar(ConfVars.HIVE_SERVER2_BUILTIN_UDF_BLACKLIST, "reflect");
@@ -705,6 +715,9 @@ public class TestJdbcWithMiniHS2 {
*/
@Test
public void testUdfBlackListOverride() throws Exception {
+ if (miniHS2.isStarted()) {
+ miniHS2.stop();
+ }
// setup whitelist
HiveConf testConf = new HiveConf();
@@ -759,6 +772,8 @@ public class TestJdbcWithMiniHS2 {
// HDFS scratch dir
scratchDirPath = new Path(HiveConf.getVar(conf, HiveConf.ConfVars.SCRATCHDIR));
verifyScratchDir(conf, fs, scratchDirPath, expectedFSPermission, userName, false);
+ hs2Conn.close();
+
// Test with multi-level scratch dir path
// Stop HiveServer2
if (miniHS2.isStarted()) {
@@ -808,6 +823,10 @@ public class TestJdbcWithMiniHS2 {
hs2Conn = getConnection(miniHS2.getJdbcURL(), userName, "password");
} catch (Exception e) {
fail("Not expecting exception: " + e);
+ } finally {
+ if (hs2Conn != null) {
+ hs2Conn.close();
+ }
}
// This should fail with given HTTP response code 413 in error message, since header is more
@@ -818,6 +837,10 @@ public class TestJdbcWithMiniHS2 {
} catch (Exception e) {
assertTrue("Header exception thrown", e != null);
assertTrue(e.getMessage().contains("HTTP Response code: 413"));
+ } finally {
+ if (hs2Conn != null) {
+ hs2Conn.close();
+ }
}
// Stop HiveServer2 to increase header size
@@ -834,6 +857,10 @@ public class TestJdbcWithMiniHS2 {
hs2Conn = getConnection(miniHS2.getJdbcURL(), userName, "password");
} catch (Exception e) {
fail("Not expecting exception: " + e);
+ } finally {
+ if (hs2Conn != null) {
+ hs2Conn.close();
+ }
}
}
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseQTestUtil.java
----------------------------------------------------------------------
diff --git a/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseQTestUtil.java b/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseQTestUtil.java
index 9d86e57..01faaba 100644
--- a/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseQTestUtil.java
+++ b/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseQTestUtil.java
@@ -72,6 +72,12 @@ public class HBaseQTestUtil extends QTestUtil {
}
@Override
+ protected void initConfFromSetup() throws Exception {
+ super.initConfFromSetup();
+ hbaseSetup.preTest(conf);
+ }
+
+ @Override
public void createSources(String tname) throws Exception {
super.createSources(tname);
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseTestSetup.java
----------------------------------------------------------------------
diff --git a/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseTestSetup.java b/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseTestSetup.java
index e6383dc..cee7158 100644
--- a/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseTestSetup.java
+++ b/itests/util/src/main/java/org/apache/hadoop/hive/hbase/HBaseTestSetup.java
@@ -22,9 +22,6 @@ import java.io.IOException;
import java.net.ServerSocket;
import java.util.Arrays;
-import junit.extensions.TestSetup;
-import junit.framework.Test;
-
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/itests/util/src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java
----------------------------------------------------------------------
diff --git a/itests/util/src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java b/itests/util/src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java
index 11e529d..0a954fc 100644
--- a/itests/util/src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java
+++ b/itests/util/src/main/java/org/apache/hadoop/hive/ql/QTestUtil.java
@@ -513,6 +513,7 @@ public class QTestUtil {
dfs.shutdown();
dfs = null;
}
+ Hive.closeCurrent();
}
public String readEntireFileIntoString(File queryFile) throws IOException {
@@ -734,8 +735,9 @@ public class QTestUtil {
return;
}
- db.getConf().set("hive.metastore.filter.hook",
+ conf.set("hive.metastore.filter.hook",
"org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl");
+ db = Hive.get(conf);
// Delete any tables other than the source tables
// and any databases other than the default database.
for (String dbName : db.getAllDatabases()) {
@@ -803,16 +805,20 @@ public class QTestUtil {
return;
}
- clearTablesCreatedDuringTests();
- clearKeysCreatedInTests();
-
// allocate and initialize a new conf since a test can
// modify conf by using 'set' commands
conf = new HiveConf(Driver.class);
initConf();
+ initConfFromSetup();
+
// renew the metastore since the cluster type is unencrypted
db = Hive.get(conf); // propagate new conf to meta store
+ clearTablesCreatedDuringTests();
+ clearKeysCreatedInTests();
+ }
+
+ protected void initConfFromSetup() throws Exception {
setup.preTest(conf);
}
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStoreClient.java
----------------------------------------------------------------------
diff --git a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStoreClient.java b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStoreClient.java
index 7d5ddee..16843af 100644
--- a/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStoreClient.java
+++ b/metastore/src/java/org/apache/hadoop/hive/metastore/HiveMetaStoreClient.java
@@ -187,7 +187,7 @@ public class HiveMetaStoreClient implements IMetaStoreClient {
private boolean isConnected = false;
private URI metastoreUris[];
private final HiveMetaHookLoader hookLoader;
- protected final HiveConf conf;
+ protected final HiveConf conf; // Keep a copy of HiveConf so if Session conf changes, we may need to get a new HMS client.
protected boolean fastpath = false;
private String tokenStrForm;
private final boolean localMetaStore;
@@ -214,8 +214,10 @@ public class HiveMetaStoreClient implements IMetaStoreClient {
this.hookLoader = hookLoader;
if (conf == null) {
conf = new HiveConf(HiveMetaStoreClient.class);
+ this.conf = conf;
+ } else {
+ this.conf = new HiveConf(conf);
}
- this.conf = conf;
filterHook = loadFilterHooks();
fileMetadataBatchSize = HiveConf.getIntVar(
conf, HiveConf.ConfVars.METASTORE_BATCH_RETRIEVE_OBJECTS_MAX);
@@ -230,10 +232,10 @@ public class HiveMetaStoreClient implements IMetaStoreClient {
// instantiate the metastore server handler directly instead of connecting
// through the network
if (conf.getBoolVar(ConfVars.METASTORE_FASTPATH)) {
- client = new HiveMetaStore.HMSHandler("hive client", conf, true);
+ client = new HiveMetaStore.HMSHandler("hive client", this.conf, true);
fastpath = true;
} else {
- client = HiveMetaStore.newRetryingHMSHandler("hive client", conf, true);
+ client = HiveMetaStore.newRetryingHMSHandler("hive client", this.conf, true);
}
isConnected = true;
snapshotActiveConf();
http://git-wip-us.apache.org/repos/asf/hive/blob/9bebaf61/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
index ce43f7d..96c826b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/session/SessionState.java
@@ -539,10 +539,6 @@ public class SessionState {
// Get the following out of the way when you start the session these take a
// while and should be done when we start up.
try {
- // Hive object instance should be created with a copy of the conf object. If the conf is
- // shared with SessionState, other parts of the code might update the config, but
- // Hive.get(HiveConf) would not recognize the case when it needs refreshing
- Hive.get(new HiveConf(startSs.sessionConf)).getMSC();
UserGroupInformation sessionUGI = Utils.getUGI();
FileSystem.get(startSs.sessionConf);
@@ -568,10 +564,6 @@ public class SessionState {
}
} catch (RuntimeException e) {
throw e;
- } catch (Hive.SchemaException e) {
- RuntimeException ex = new RuntimeException(e.getMessage());
- ex.setStackTrace(new StackTraceElement[0]);
- throw ex;
} catch (Exception e) {
// Catch-all due to some exec time dependencies on session state
// that would cause ClassNoFoundException otherwise
[13/48] hive git commit: HIVE-13561: HiveServer2 is leaking
ClassLoaders when add jar / temporary functions are used (Trystan Leftwich
reviewed by Vaibhav Gumashta)
Posted by sp...@apache.org.
HIVE-13561: HiveServer2 is leaking ClassLoaders when add jar / temporary functions are used (Trystan Leftwich reviewed by Vaibhav Gumashta)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/68a42108
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/68a42108
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/68a42108
Branch: refs/heads/java8
Commit: 68a4210808ecf965d9d8bb4c934cb548c334fe72
Parents: b420e1d
Author: Vaibhav Gumashta <vg...@hortonworks.com>
Authored: Fri May 27 00:23:25 2016 -0700
Committer: Vaibhav Gumashta <vg...@hortonworks.com>
Committed: Fri May 27 00:23:25 2016 -0700
----------------------------------------------------------------------
.../apache/hive/jdbc/TestJdbcWithMiniHS2.java | 145 +++++++++++++++++++
.../apache/hadoop/hive/ql/exec/Registry.java | 10 +-
2 files changed, 150 insertions(+), 5 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/68a42108/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java b/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
index 4aa98ca..a01daa4 100644
--- a/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
+++ b/itests/hive-unit/src/test/java/org/apache/hive/jdbc/TestJdbcWithMiniHS2.java
@@ -24,7 +24,9 @@ import static org.junit.Assert.assertNotNull;
import static org.junit.Assert.assertTrue;
import static org.junit.Assert.fail;
+import java.lang.reflect.Constructor;
import java.lang.reflect.Field;
+import java.lang.reflect.Modifier;
import java.sql.Connection;
import java.sql.DriverManager;
import java.sql.ResultSet;
@@ -46,6 +48,8 @@ import java.util.concurrent.ThreadPoolExecutor;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;
+import com.google.common.cache.Cache;
+import com.google.common.cache.CacheBuilder;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
@@ -54,6 +58,7 @@ import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.hive.conf.HiveConf.ConfVars;
import org.apache.hadoop.hive.metastore.ObjectStore;
import org.apache.hadoop.hive.ql.exec.FunctionRegistry;
+import org.apache.hive.common.util.ReflectionUtil;
import org.apache.hive.jdbc.miniHS2.MiniHS2;
import org.datanucleus.ClassLoaderResolver;
import org.datanucleus.NucleusContext;
@@ -943,4 +948,144 @@ public class TestJdbcWithMiniHS2 {
}
return -1;
}
+
+ /**
+ * Tests ADD JAR uses Hives ReflectionUtil.CONSTRUCTOR_CACHE
+ *
+ * @throws Exception
+ */
+ @Test
+ public void testAddJarConstructorUnCaching() throws Exception {
+ // This test assumes the hive-contrib JAR has been built as part of the Hive build.
+ // Also dependent on the UDFExampleAdd class within that JAR.
+ setReflectionUtilCache();
+ String udfClassName = "org.apache.hadoop.hive.contrib.udf.example.UDFExampleAdd";
+ String mvnRepo = System.getProperty("maven.local.repository");
+ String hiveVersion = System.getProperty("hive.version");
+ String jarFileName = "hive-contrib-" + hiveVersion + ".jar";
+ String[] pathParts = {
+ "org", "apache", "hive",
+ "hive-contrib", hiveVersion, jarFileName
+ };
+
+ // Create path to hive-contrib JAR on local filesystem
+ Path jarFilePath = new Path(mvnRepo);
+ for (String pathPart : pathParts) {
+ jarFilePath = new Path(jarFilePath, pathPart);
+ }
+
+ Connection conn = getConnection(miniHS2.getJdbcURL(), "foo", "bar");
+ String tableName = "testAddJar";
+ Statement stmt = conn.createStatement();
+ stmt.execute("SET hive.support.concurrency = false");
+ // Create table
+ stmt.execute("DROP TABLE IF EXISTS " + tableName);
+ stmt.execute("CREATE TABLE " + tableName + " (key INT, value STRING)");
+ // Load data
+ stmt.execute("LOAD DATA LOCAL INPATH '" + kvDataFilePath.toString() + "' INTO TABLE "
+ + tableName);
+ ResultSet res = stmt.executeQuery("SELECT * FROM " + tableName);
+ // Ensure table is populated
+ assertTrue(res.next());
+
+ long cacheBeforeAddJar, cacheAfterAddJar, cacheAfterClose;
+ // Force the cache clear so we know its empty
+ invalidateReflectionUtlCache();
+ cacheBeforeAddJar = getReflectionUtilCacheSize();
+ System.out.println("CONSTRUCTOR_CACHE size before add jar: " + cacheBeforeAddJar);
+ System.out.println("CONSTRUCTOR_CACHE as map before add jar:" + getReflectionUtilCache().asMap());
+ Assert.assertTrue("FAILED: CONSTRUCTOR_CACHE size before add jar: " + cacheBeforeAddJar,
+ cacheBeforeAddJar == 0);
+
+ // Add the jar file
+ stmt.execute("ADD JAR " + jarFilePath.toString());
+ // Create a temporary function using the jar
+ stmt.execute("CREATE TEMPORARY FUNCTION func AS '" + udfClassName + "'");
+ // Execute the UDF
+ res = stmt.executeQuery("SELECT func(value) from " + tableName);
+ assertTrue(res.next());
+
+ // Check to make sure the cache is now being used
+ cacheAfterAddJar = getReflectionUtilCacheSize();
+ System.out.println("CONSTRUCTOR_CACHE size after add jar: " + cacheAfterAddJar);
+ Assert.assertTrue("FAILED: CONSTRUCTOR_CACHE size after connection close: " + cacheAfterAddJar,
+ cacheAfterAddJar > 0);
+ conn.close();
+ TimeUnit.SECONDS.sleep(10);
+ // Have to force a cleanup of all expired entries here because its possible that the
+ // expired entries will still be counted in Cache.size().
+ // Taken from:
+ // http://docs.guava-libraries.googlecode.com/git/javadoc/com/google/common/cache/CacheBuilder.html
+ cleanUpReflectionUtlCache();
+ cacheAfterClose = getReflectionUtilCacheSize();
+ System.out.println("CONSTRUCTOR_CACHE size after connection close: " + cacheAfterClose);
+ Assert.assertTrue("FAILED: CONSTRUCTOR_CACHE size after connection close: " + cacheAfterClose,
+ cacheAfterClose == 0);
+ }
+
+ private void setReflectionUtilCache() {
+ Field constructorCacheField;
+ Cache<Class<?>, Constructor<?>> tmp;
+ try {
+ constructorCacheField = ReflectionUtil.class.getDeclaredField("CONSTRUCTOR_CACHE");
+ if (constructorCacheField != null) {
+ constructorCacheField.setAccessible(true);
+ Field modifiersField = Field.class.getDeclaredField("modifiers");
+ modifiersField.setAccessible(true);
+ modifiersField.setInt(constructorCacheField, constructorCacheField.getModifiers() & ~Modifier.FINAL);
+ tmp = CacheBuilder.newBuilder().expireAfterAccess(5, TimeUnit.SECONDS).concurrencyLevel(64).weakKeys().weakValues().build();
+ constructorCacheField.set(tmp.getClass(), tmp);
+ }
+ } catch (Exception e) {
+ System.out.println("Error when setting the CONSTRUCTOR_CACHE to expire: " + e);
+ }
+ }
+
+ private Cache getReflectionUtilCache() {
+ Field constructorCacheField;
+ try {
+ constructorCacheField = ReflectionUtil.class.getDeclaredField("CONSTRUCTOR_CACHE");
+ if (constructorCacheField != null) {
+ constructorCacheField.setAccessible(true);
+ return (Cache) constructorCacheField.get(null);
+ }
+ } catch (Exception e) {
+ System.out.println("Error when getting the CONSTRUCTOR_CACHE var: " + e);
+ }
+ return null;
+ }
+
+ private void invalidateReflectionUtlCache() {
+ try {
+ Cache constructorCache = getReflectionUtilCache();
+ if ( constructorCache != null ) {
+ constructorCache.invalidateAll();
+ }
+ } catch (Exception e) {
+ System.out.println("Error when trying to invalidate the cache: " + e);
+ }
+ }
+
+ private void cleanUpReflectionUtlCache() {
+ try {
+ Cache constructorCache = getReflectionUtilCache();
+ if ( constructorCache != null ) {
+ constructorCache.cleanUp();
+ }
+ } catch (Exception e) {
+ System.out.println("Error when trying to cleanUp the cache: " + e);
+ }
+ }
+
+ private long getReflectionUtilCacheSize() {
+ try {
+ Cache constructorCache = getReflectionUtilCache();
+ if ( constructorCache != null ) {
+ return constructorCache.size();
+ }
+ } catch (Exception e) {
+ System.out.println(e);
+ }
+ return -1;
+ }
}
http://git-wip-us.apache.org/repos/asf/hive/blob/68a42108/ql/src/java/org/apache/hadoop/hive/ql/exec/Registry.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/Registry.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/Registry.java
index 3b54b49..891514b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/Registry.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/Registry.java
@@ -47,7 +47,7 @@ import org.apache.hadoop.hive.ql.udf.generic.SimpleGenericUDAFParameterInfo;
import org.apache.hadoop.hive.ql.udf.ptf.TableFunctionResolver;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
-import org.apache.hadoop.util.ReflectionUtils;
+import org.apache.hive.common.util.ReflectionUtil;
import java.io.IOException;
import java.util.Collections;
@@ -125,7 +125,7 @@ public class Registry {
case GENERIC_UDAF_RESOLVER:
return registerGenericUDAF(
functionName, (GenericUDAFResolver)
- ReflectionUtils.newInstance(udfClass, null), resources);
+ ReflectionUtil.newInstance(udfClass, null), resources);
case TABLE_FUNCTION_RESOLVER:
// native or not would be decided by annotation. need to evaluate that first
return registerTableFunction(functionName,
@@ -154,7 +154,7 @@ public class Registry {
Class<? extends GenericUDF> genericUDFClass, FunctionResource... resources) {
validateClass(genericUDFClass, GenericUDF.class);
FunctionInfo fI = new FunctionInfo(isNative, functionName,
- ReflectionUtils.newInstance(genericUDFClass, null), resources);
+ ReflectionUtil.newInstance(genericUDFClass, null), resources);
addFunction(functionName, fI);
return fI;
}
@@ -179,7 +179,7 @@ public class Registry {
Class<? extends GenericUDTF> genericUDTFClass, FunctionResource... resources) {
validateClass(genericUDTFClass, GenericUDTF.class);
FunctionInfo fI = new FunctionInfo(isNative, functionName,
- ReflectionUtils.newInstance(genericUDTFClass, null), resources);
+ ReflectionUtil.newInstance(genericUDTFClass, null), resources);
addFunction(functionName, fI);
return fI;
}
@@ -197,7 +197,7 @@ public class Registry {
Class<? extends UDAF> udafClass, FunctionResource... resources) {
validateClass(udafClass, UDAF.class);
FunctionInfo function = new WindowFunctionInfo(isNative, functionName,
- new GenericUDAFBridge(ReflectionUtils.newInstance(udafClass, null)), resources);
+ new GenericUDAFBridge(ReflectionUtil.newInstance(udafClass, null)), resources);
addFunction(functionName, function);
addFunction(WINDOW_FUNC_PREFIX + functionName, function);
return function;
[23/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out
deleted file mode 100644
index 68943e1..0000000
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out
+++ /dev/null
@@ -1,709 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Outer Join 0 to 1
- filter mappings:
- 1 [0, 1]
- filter predicates:
- 0
- 1 {(VALUE._col1 = '2008-04-08')}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
-PREHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
deleted file mode 100644
index c3454ee..0000000
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.8.out
+++ /dev/null
@@ -1,879 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- AND
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [a]
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Outer Join 0 to 1
- filter mappings:
- 0 [1, 1]
- filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) and (UDFToDouble(_col0) > 15.0)) and (UDFToDouble(_col0) < 25.0)) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key AND b.ds = '2008-04-08')
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
-PREHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN EXTENDED
- FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [a]
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean)
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: FROM
- src a
- FULL OUTER JOIN
- srcpart b
- ON (a.key = b.key)
- SELECT a.key, a.value, b.key, b.value
- WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-17 val_17 17 val_17
-17 val_17 17 val_17
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-18 val_18 18 val_18
-19 val_19 19 val_19
-19 val_19 19 val_19
[16/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/varchar_udf1.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/varchar_udf1.q.java1.7.out b/ql/src/test/results/clientpositive/varchar_udf1.q.java1.7.out
deleted file mode 100644
index 459d93b..0000000
--- a/ql/src/test/results/clientpositive/varchar_udf1.q.java1.7.out
+++ /dev/null
@@ -1,457 +0,0 @@
-PREHOOK: query: drop table varchar_udf_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table varchar_udf_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@varchar_udf_1
-PREHOOK: query: insert overwrite table varchar_udf_1
- select key, value, key, value from src where key = '238' limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: insert overwrite table varchar_udf_1
- select key, value, key, value from src where key = '238' limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@varchar_udf_1
-POSTHOOK: Lineage: varchar_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with varchar support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with varchar support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238val_238 238val_238 true
-PREHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-VAL_238 VAL_238 true
-PREHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-118 118 true
-PREHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238|val_238 238|val_238 true
-PREHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-4 4 true
-PREHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-7 7 true
-PREHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-5 5 true
-PREHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
- val_238 val_238 true
-PREHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- c2 regexp 'val',
- c4 regexp 'val',
- (c2 regexp 'val') = (c4 regexp 'val')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- c2 regexp 'val',
- c4 regexp 'val',
- (c2 regexp 'val') = (c4 regexp 'val')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-true true true
-PREHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238 238 true
-PREHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-replaced_238 replaced_238 true
-PREHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-832_lav 832_lav true
-PREHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as varchar(50)))
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as varchar(50)))
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
-PREHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-["val","238"] ["val","238"]
-PREHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-{"b":"2","a":"1","c":"3"} {"b":"2","a":"1","c":"3"}
-PREHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val val true
-PREHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"}
-PREHOOK: query: select
- min(c2),
- min(c4)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- min(c2),
- min(c4)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: select
- max(c2),
- max(c4)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- max(c2),
- max(c4)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: drop table varchar_udf_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@varchar_udf_1
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: drop table varchar_udf_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@varchar_udf_1
-POSTHOOK: Output: default@varchar_udf_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/varchar_udf1.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/varchar_udf1.q.java1.8.out b/ql/src/test/results/clientpositive/varchar_udf1.q.java1.8.out
deleted file mode 100644
index ace8568..0000000
--- a/ql/src/test/results/clientpositive/varchar_udf1.q.java1.8.out
+++ /dev/null
@@ -1,457 +0,0 @@
-PREHOOK: query: drop table varchar_udf_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table varchar_udf_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@varchar_udf_1
-PREHOOK: query: insert overwrite table varchar_udf_1
- select key, value, key, value from src where key = '238' limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: insert overwrite table varchar_udf_1
- select key, value, key, value from src where key = '238' limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@varchar_udf_1
-POSTHOOK: Lineage: varchar_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: varchar_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with varchar support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with varchar support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238val_238 238val_238 true
-PREHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-VAL_238 VAL_238 true
-PREHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-118 118 true
-PREHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238|val_238 238|val_238 true
-PREHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-4 4 true
-PREHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-7 7 true
-PREHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-5 5 true
-PREHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
- val_238 val_238 true
-PREHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- regexp(c2, 'val'),
- regexp(c4, 'val'),
- regexp(c2, 'val') = regexp(c4, 'val')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp(c2, 'val'),
- regexp(c4, 'val'),
- regexp(c2, 'val') = regexp(c4, 'val')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-true true true
-PREHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-238 238 true
-PREHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-replaced_238 replaced_238 true
-PREHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-832_lav 832_lav true
-PREHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as varchar(50)))
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as varchar(50)))
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
-PREHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-["val","238"] ["val","238"]
-PREHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-{"a":"1","b":"2","c":"3"} {"a":"1","b":"2","c":"3"}
-PREHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val val true
-PREHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from varchar_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from varchar_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1}
-PREHOOK: query: select
- min(c2),
- min(c4)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- min(c2),
- min(c4)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: select
- max(c2),
- max(c4)
-from varchar_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- max(c2),
- max(c4)
-from varchar_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@varchar_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: drop table varchar_udf_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@varchar_udf_1
-PREHOOK: Output: default@varchar_udf_1
-POSTHOOK: query: drop table varchar_udf_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@varchar_udf_1
-POSTHOOK: Output: default@varchar_udf_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/varchar_udf1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/varchar_udf1.q.out b/ql/src/test/results/clientpositive/varchar_udf1.q.out
new file mode 100644
index 0000000..e5cfce5
--- /dev/null
+++ b/ql/src/test/results/clientpositive/varchar_udf1.q.out
@@ -0,0 +1,453 @@
+PREHOOK: query: drop table varchar_udf_1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table varchar_udf_1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@varchar_udf_1
+POSTHOOK: query: create table varchar_udf_1 (c1 string, c2 string, c3 varchar(10), c4 varchar(20))
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@varchar_udf_1
+PREHOOK: query: insert overwrite table varchar_udf_1
+ select key, value, key, value from src where key = '238' limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@varchar_udf_1
+POSTHOOK: query: insert overwrite table varchar_udf_1
+ select key, value, key, value from src where key = '238' limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@varchar_udf_1
+POSTHOOK: Lineage: varchar_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- UDFs with varchar support
+select
+ concat(c1, c2),
+ concat(c3, c4),
+ concat(c1, c2) = concat(c3, c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- UDFs with varchar support
+select
+ concat(c1, c2),
+ concat(c3, c4),
+ concat(c1, c2) = concat(c3, c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+238val_238 238val_238 true
+PREHOOK: query: select
+ upper(c2),
+ upper(c4),
+ upper(c2) = upper(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ upper(c2),
+ upper(c4),
+ upper(c2) = upper(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+VAL_238 VAL_238 true
+PREHOOK: query: select
+ lower(c2),
+ lower(c4),
+ lower(c2) = lower(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ lower(c2),
+ lower(c4),
+ lower(c2) = lower(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: -- Scalar UDFs
+select
+ ascii(c2),
+ ascii(c4),
+ ascii(c2) = ascii(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- Scalar UDFs
+select
+ ascii(c2),
+ ascii(c4),
+ ascii(c2) = ascii(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+118 118 true
+PREHOOK: query: select
+ concat_ws('|', c1, c2),
+ concat_ws('|', c3, c4),
+ concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ concat_ws('|', c1, c2),
+ concat_ws('|', c3, c4),
+ concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+238|val_238 238|val_238 true
+PREHOOK: query: select
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ instr(c2, '_'),
+ instr(c4, '_'),
+ instr(c2, '_') = instr(c4, '_')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ instr(c2, '_'),
+ instr(c4, '_'),
+ instr(c2, '_') = instr(c4, '_')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+4 4 true
+PREHOOK: query: select
+ length(c2),
+ length(c4),
+ length(c2) = length(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ length(c2),
+ length(c4),
+ length(c2) = length(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+7 7 true
+PREHOOK: query: select
+ locate('a', 'abcdabcd', 3),
+ locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
+ locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ locate('a', 'abcdabcd', 3),
+ locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3),
+ locate('a', 'abcdabcd', 3) = locate(cast('a' as varchar(1)), cast('abcdabcd' as varchar(10)), 3)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+5 5 true
+PREHOOK: query: select
+ lpad(c2, 15, ' '),
+ lpad(c4, 15, ' '),
+ lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ lpad(c2, 15, ' '),
+ lpad(c4, 15, ' '),
+ lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+ val_238 val_238 true
+PREHOOK: query: select
+ ltrim(c2),
+ ltrim(c4),
+ ltrim(c2) = ltrim(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ ltrim(c2),
+ ltrim(c4),
+ ltrim(c2) = ltrim(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ c2 regexp 'val',
+ c4 regexp 'val',
+ (c2 regexp 'val') = (c4 regexp 'val')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ c2 regexp 'val',
+ c4 regexp 'val',
+ (c2 regexp 'val') = (c4 regexp 'val')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+true true true
+PREHOOK: query: select
+ regexp_extract(c2, 'val_([0-9]+)', 1),
+ regexp_extract(c4, 'val_([0-9]+)', 1),
+ regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ regexp_extract(c2, 'val_([0-9]+)', 1),
+ regexp_extract(c4, 'val_([0-9]+)', 1),
+ regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+238 238 true
+PREHOOK: query: select
+ regexp_replace(c2, 'val', 'replaced'),
+ regexp_replace(c4, 'val', 'replaced'),
+ regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ regexp_replace(c2, 'val', 'replaced'),
+ regexp_replace(c4, 'val', 'replaced'),
+ regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+replaced_238 replaced_238 true
+PREHOOK: query: select
+ reverse(c2),
+ reverse(c4),
+ reverse(c2) = reverse(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ reverse(c2),
+ reverse(c4),
+ reverse(c2) = reverse(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+832_lav 832_lav true
+PREHOOK: query: select
+ rpad(c2, 15, ' '),
+ rpad(c4, 15, ' '),
+ rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ rpad(c2, 15, ' '),
+ rpad(c4, 15, ' '),
+ rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ rtrim(c2),
+ rtrim(c4),
+ rtrim(c2) = rtrim(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ rtrim(c2),
+ rtrim(c4),
+ rtrim(c2) = rtrim(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ sentences('See spot run. See jane run.'),
+ sentences(cast('See spot run. See jane run.' as varchar(50)))
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ sentences('See spot run. See jane run.'),
+ sentences(cast('See spot run. See jane run.' as varchar(50)))
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
+PREHOOK: query: select
+ split(c2, '_'),
+ split(c4, '_')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ split(c2, '_'),
+ split(c4, '_')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+["val","238"] ["val","238"]
+PREHOOK: query: select
+ str_to_map('a:1,b:2,c:3',',',':'),
+ str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ str_to_map('a:1,b:2,c:3',',',':'),
+ str_to_map(cast('a:1,b:2,c:3' as varchar(20)),',',':')
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+{"a":"1","b":"2","c":"3"} {"a":"1","b":"2","c":"3"}
+PREHOOK: query: select
+ substr(c2, 1, 3),
+ substr(c4, 1, 3),
+ substr(c2, 1, 3) = substr(c4, 1, 3)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ substr(c2, 1, 3),
+ substr(c4, 1, 3),
+ substr(c2, 1, 3) = substr(c4, 1, 3)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val val true
+PREHOOK: query: select
+ trim(c2),
+ trim(c4),
+ trim(c2) = trim(c4)
+from varchar_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ trim(c2),
+ trim(c4),
+ trim(c2) = trim(c4)
+from varchar_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: -- Aggregate Functions
+select
+ compute_stats(c2, 16),
+ compute_stats(c4, 16)
+from varchar_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- Aggregate Functions
+select
+ compute_stats(c2, 16),
+ compute_stats(c4, 16)
+from varchar_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"}
+PREHOOK: query: select
+ min(c2),
+ min(c4)
+from varchar_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ min(c2),
+ min(c4)
+from varchar_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238
+PREHOOK: query: select
+ max(c2),
+ max(c4)
+from varchar_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ max(c2),
+ max(c4)
+from varchar_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_1
+#### A masked pattern was here ####
+val_238 val_238
+PREHOOK: query: drop table varchar_udf_1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@varchar_udf_1
+PREHOOK: Output: default@varchar_udf_1
+POSTHOOK: query: drop table varchar_udf_1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@varchar_udf_1
+POSTHOOK: Output: default@varchar_udf_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out
deleted file mode 100644
index 867dd4c..0000000
--- a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.7.out
+++ /dev/null
@@ -1,220 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50.0000
-65537 50.0 50.0 50.0000
-65538 50.0 50.0 50.0000
-65539 50.0 50.0 50.0000
-65540 50.0 50.0 50.0000
-65541 50.0 50.0 50.0000
-65542 50.0 50.0 50.0000
-65543 50.0 50.0 50.0000
-65544 50.0 50.0 50.0000
-65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.8.out
deleted file mode 100644
index 789e6c2..0000000
--- a/ql/src/test/results/clientpositive/vector_cast_constant.q.java1.8.out
+++ /dev/null
@@ -1,197 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50
-65537 50.0 50.0 50
-65538 50.0 50.0 50
-65539 50.0 50.0 50
-65540 50.0 50.0 50
-65541 50.0 50.0 50
-65542 50.0 50.0 50
-65543 50.0 50.0 50
-65544 50.0 50.0 50
-65545 50.0 50.0 50
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/vector_cast_constant.q.out
index 39ed1c8..6033aad 100644
--- a/ql/src/test/results/clientpositive/vector_cast_constant.q.out
+++ b/ql/src/test/results/clientpositive/vector_cast_constant.q.out
@@ -102,18 +102,19 @@ PREHOOK: query: EXPLAIN SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN SELECT
i,
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -146,6 +147,28 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
@@ -168,7 +191,7 @@ PREHOOK: query: SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
PREHOOK: type: QUERY
PREHOOK: Input: default@over1korc
#### A masked pattern was here ####
@@ -177,17 +200,17 @@ POSTHOOK: query: SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@over1korc
#### A masked pattern was here ####
-65536 50.0 50.0 50
-65537 50.0 50.0 50
-65538 50.0 50.0 50
-65539 50.0 50.0 50
-65540 50.0 50.0 50
-65541 50.0 50.0 50
-65542 50.0 50.0 50
-65543 50.0 50.0 50
-65544 50.0 50.0 50
-65545 50.0 50.0 50
+65536 50.0 50.0 50.0000
+65537 50.0 50.0 50.0000
+65538 50.0 50.0 50.0000
+65539 50.0 50.0 50.0000
+65540 50.0 50.0 50.0000
+65541 50.0 50.0 50.0000
+65542 50.0 50.0 50.0000
+65543 50.0 50.0 50.0000
+65544 50.0 50.0 50.0000
+65545 50.0 50.0 50.0000
[27/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
new file mode 100644
index 0000000..81f3af3
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_9.q.out
@@ -0,0 +1,811 @@
+PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns. merge.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103:
+-- 99 000000_0
+-- 99 000001_0
+-- after merge
+-- 142 000000_0
+-- ds=2008-04-08/hr=11/key=484:
+-- 87 000000_0
+-- 87 000001_0
+-- after merge
+-- 118 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns. merge.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103:
+-- 99 000000_0
+-- 99 000001_0
+-- after merge
+-- 142 000000_0
+-- ds=2008-04-08/hr=11/key=484:
+-- 87 000000_0
+-- 87 000001_0
+-- after merge
+-- 118 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 6
+ numRows 1000
+ rawDataSize 9624
+ totalSize 10898
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key]
+Skewed Values: [[484], [103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML with merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+ Stage-5
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-5
+ Merge File Operator
+ Map Operator Tree:
+ RCFile Merge Operator
+ merge level: block
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 1000
+ rawDataSize 9624
+ totalSize 10786
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key]
+Skewed Values: [[484], [103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(*) from list_bucketing_static_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from list_bucketing_static_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+1000
+PREHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ numFiles 4
+ numRows 1000
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 9624
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 10786
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_static_part
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 11
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 12
+PREHOOK: query: -- clean up
+drop table list_bucketing_static_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- clean up
+drop table list_bucketing_static_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out b/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out
deleted file mode 100644
index 5651839..0000000
--- a/ql/src/test/results/clientpositive/llap/join0.q.java1.7.out
+++ /dev/null
@@ -1,242 +0,0 @@
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: llap
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: llap
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Execution mode: uber
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out b/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out
deleted file mode 100644
index 5651839..0000000
--- a/ql/src/test/results/clientpositive/llap/join0.q.java1.8.out
+++ /dev/null
@@ -1,242 +0,0 @@
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: llap
- Map 4
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Execution mode: llap
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Execution mode: uber
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-#### A masked pattern was here ####
-Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/join0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/join0.q.out b/ql/src/test/results/clientpositive/llap/join0.q.out
new file mode 100644
index 0000000..f177afc
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/join0.q.out
@@ -0,0 +1,243 @@
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+EXPLAIN
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 10) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FORMATTED
+SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+#### A masked pattern was here ####
+Warning: Shuffle Join MERGEJOIN[15][tables = [src1, src2]] in Stage 'Reducer 2' is a cross product
+PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
+ src2.key as k2, src2.value as v2 FROM
+ (SELECT * FROM src WHERE src.key < 10) src1
+ JOIN
+ (SELECT * FROM src WHERE src.key < 10) src2
+ SORT BY k1, v1, k2, v2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 2 val_2
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 4 val_4
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 5 val_5
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 8 val_8
+0 val_0 9 val_9
+0 val_0 9 val_9
+0 val_0 9 val_9
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 0 val_0
+2 val_2 2 val_2
+2 val_2 4 val_4
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 5 val_5
+2 val_2 8 val_8
+2 val_2 9 val_9
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 0 val_0
+4 val_4 2 val_2
+4 val_4 4 val_4
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 5 val_5
+4 val_4 8 val_8
+4 val_4 9 val_9
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 0 val_0
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 2 val_2
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 4 val_4
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 8 val_8
+5 val_5 9 val_9
+5 val_5 9 val_9
+5 val_5 9 val_9
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 0 val_0
+8 val_8 2 val_2
+8 val_8 4 val_4
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 5 val_5
+8 val_8 8 val_8
+8 val_8 9 val_9
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 0 val_0
+9 val_9 2 val_2
+9 val_9 4 val_4
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 5 val_5
+9 val_9 8 val_8
+9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out
deleted file mode 100644
index 22b5d93..0000000
--- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.7.out
+++ /dev/null
@@ -1,217 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized, llap
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reducer 3
- Execution mode: vectorized, uber
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50
-65537 50.0 50.0 50
-65538 50.0 50.0 50
-65539 50.0 50.0 50
-65540 50.0 50.0 50
-65541 50.0 50.0 50
-65542 50.0 50.0 50
-65543 50.0 50.0 50
-65544 50.0 50.0 50
-65545 50.0 50.0 50
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out
deleted file mode 100644
index 22b5d93..0000000
--- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.java1.8.out
+++ /dev/null
@@ -1,217 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
- Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized, llap
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reducer 3
- Execution mode: vectorized, uber
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50
-65537 50.0 50.0 50
-65538 50.0 50.0 50
-65539 50.0 50.0 50
-65540 50.0 50.0 50
-65541 50.0 50.0 50
-65542 50.0 50.0 50
-65543 50.0 50.0 50
-65544 50.0 50.0 50
-65545 50.0 50.0 50
[12/48] hive git commit: HIVE-13868: Include derby.log file in the
Hive ptest logs (Sergio Pena)
Posted by sp...@apache.org.
HIVE-13868: Include derby.log file in the Hive ptest logs (Sergio Pena)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/b420e1da
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/b420e1da
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/b420e1da
Branch: refs/heads/java8
Commit: b420e1da98505f1b446b7c65e2a6cf1f0c4d5e00
Parents: 7172586
Author: Sergio Pena <se...@cloudera.com>
Authored: Thu May 26 17:47:04 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Thu May 26 17:47:04 2016 -0500
----------------------------------------------------------------------
testutils/ptest2/src/main/resources/batch-exec.vm | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/b420e1da/testutils/ptest2/src/main/resources/batch-exec.vm
----------------------------------------------------------------------
diff --git a/testutils/ptest2/src/main/resources/batch-exec.vm b/testutils/ptest2/src/main/resources/batch-exec.vm
index 99ddf80..652084d 100644
--- a/testutils/ptest2/src/main/resources/batch-exec.vm
+++ b/testutils/ptest2/src/main/resources/batch-exec.vm
@@ -86,7 +86,7 @@ fi
echo $pid >> batch.pid
wait $pid
ret=$?
-find ./ -type f -name hive.log -o -name spark.log | \
+find ./ -type f -name hive.log -o -name spark.log -o -name derby.log | \
xargs -I {} sh -c 'f=$(basename {}); test -f ${logDir}/$f && f=$f-$(uuidgen); mv {} ${logDir}/$f'
find ./ -type f -name 'TEST-*.xml' | \
xargs -I {} sh -c 'f=TEST-${batchName}-$(basename {}); test -f ${logDir}/$f && f=$f-$(uuidgen); mv {} ${logDir}/$f'
[03/48] hive git commit: HIVE-13551: Make cleardanglingscratchdir
work on Windows (Daniel Dai, reviewed by Thejas Nair)
Posted by sp...@apache.org.
HIVE-13551: Make cleardanglingscratchdir work on Windows (Daniel Dai, reviewed by Thejas Nair)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/ae6ad6d1
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/ae6ad6d1
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/ae6ad6d1
Branch: refs/heads/java8
Commit: ae6ad6d1b7423d47080b7777cc43298af70c25ef
Parents: b93ce78
Author: Daniel Dai <da...@hortonworks.com>
Authored: Wed May 25 15:00:05 2016 -0700
Committer: Daniel Dai <da...@hortonworks.com>
Committed: Wed May 25 15:01:23 2016 -0700
----------------------------------------------------------------------
bin/ext/cleardanglingscratchdir.cmd | 1 -
bin/hive.cmd | 3 ++
.../ql/session/TestClearDanglingScratchDir.java | 5 +++
.../ql/session/ClearDanglingScratchDir.java | 46 +++++++++++++++-----
4 files changed, 44 insertions(+), 11 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/ae6ad6d1/bin/ext/cleardanglingscratchdir.cmd
----------------------------------------------------------------------
diff --git a/bin/ext/cleardanglingscratchdir.cmd b/bin/ext/cleardanglingscratchdir.cmd
index 31104af..1bb0453 100644
--- a/bin/ext/cleardanglingscratchdir.cmd
+++ b/bin/ext/cleardanglingscratchdir.cmd
@@ -16,7 +16,6 @@
set CLASS=org.apache.hadoop.hive.ql.session.ClearDanglingScratchDir
set HIVE_OPTS=
-set HADOOP_CLASSPATH=
pushd %HIVE_LIB%
for /f %%a IN ('dir /b hive-exec-*.jar') do (
http://git-wip-us.apache.org/repos/asf/hive/blob/ae6ad6d1/bin/hive.cmd
----------------------------------------------------------------------
diff --git a/bin/hive.cmd b/bin/hive.cmd
index 9080796..79d6d1b 100644
--- a/bin/hive.cmd
+++ b/bin/hive.cmd
@@ -361,6 +361,9 @@ goto :EOF
set /a SERVICE_COUNT = %SERVICE_COUNT% + 1
set VAR%SERVICE_COUNT%=schematool
+
+ set /a SERVICE_COUNT = %SERVICE_COUNT% + 1
+ set VAR%SERVICE_COUNT%=cleardanglingscratchdir
goto :EOF
:AddToAuxParam
http://git-wip-us.apache.org/repos/asf/hive/blob/ae6ad6d1/itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/session/TestClearDanglingScratchDir.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/session/TestClearDanglingScratchDir.java b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/session/TestClearDanglingScratchDir.java
index 3cb80a7..185dbd5 100644
--- a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/session/TestClearDanglingScratchDir.java
+++ b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/session/TestClearDanglingScratchDir.java
@@ -28,6 +28,8 @@ import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.permission.FsPermission;
import org.apache.hadoop.hdfs.MiniDFSCluster;
import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.ql.WindowsPathUtil;
+import org.apache.hadoop.util.Shell;
import org.junit.AfterClass;
import org.junit.Assert;
import org.junit.BeforeClass;
@@ -47,6 +49,9 @@ public class TestClearDanglingScratchDir {
static public void oneTimeSetup() throws Exception {
m_dfs = new MiniDFSCluster.Builder(new Configuration()).numDataNodes(1).format(true).build();
conf = new HiveConf();
+ if (Shell.WINDOWS) {
+ WindowsPathUtil.convertPathsFromWindowsToHdfs(conf);
+ }
conf.set(HiveConf.ConfVars.HIVE_SCRATCH_DIR_LOCK.toString(), "true");
conf.set(HiveConf.ConfVars.METASTORE_AUTO_CREATE_ALL.toString(), "true");
LoggerFactory.getLogger("SessionState");
http://git-wip-us.apache.org/repos/asf/hive/blob/ae6ad6d1/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java b/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
index 8543768..ee012c2 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/session/ClearDanglingScratchDir.java
@@ -25,6 +25,7 @@ import org.apache.commons.cli.GnuParser;
import org.apache.commons.cli.HelpFormatter;
import org.apache.commons.cli.OptionBuilder;
import org.apache.commons.cli.Options;
+import org.apache.hadoop.fs.FileAlreadyExistsException;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
@@ -66,6 +67,7 @@ public class ClearDanglingScratchDir {
if (cli.hasOption("r")) {
dryRun = true;
+ SessionState.getConsole().printInfo("dry-run mode on");
}
if (cli.hasOption("v")) {
@@ -99,24 +101,48 @@ public class ClearDanglingScratchDir {
}
continue;
}
+ boolean removable = false;
+ boolean inuse = false;
try {
IOUtils.closeStream(fs.append(lockFilePath));
- scratchDirToRemove.add(scratchDir.getPath());
- } catch (RemoteException e) {
+ removable = true;
+ } catch (RemoteException eAppend) {
// RemoteException with AlreadyBeingCreatedException will be thrown
// if the file is currently held by a writer
- if(AlreadyBeingCreatedException.class.getName().equals(e.getClassName())){
- // Cannot open the lock file for writing, must be held by a live process
- String message = scratchDir.getPath() + " is being used by live process";
- if (verbose) {
- SessionState.getConsole().printInfo(message);
- } else {
- SessionState.getConsole().logInfo(message);
+ if(AlreadyBeingCreatedException.class.getName().equals(eAppend.getClassName())){
+ inuse = true;
+ } else if (UnsupportedOperationException.class.getName().equals(eAppend.getClassName())) {
+ // Append is not supported in the cluster, try to use create
+ try {
+ IOUtils.closeStream(fs.create(lockFilePath, false));
+ } catch (RemoteException eCreate) {
+ if (AlreadyBeingCreatedException.class.getName().equals(eCreate.getClassName())){
+ // If the file is held by a writer, will throw AlreadyBeingCreatedException
+ inuse = true;
+ } else {
+ SessionState.getConsole().printInfo("Unexpected error:" + eCreate.getMessage());
+ }
+ } catch (FileAlreadyExistsException eCreateNormal) {
+ // Otherwise, throw FileAlreadyExistsException, which means the file owner is
+ // dead
+ removable = true;
}
} else {
- throw e;
+ SessionState.getConsole().printInfo("Unexpected error:" + eAppend.getMessage());
}
}
+ if (inuse) {
+ // Cannot open the lock file for writing, must be held by a live process
+ String message = scratchDir.getPath() + " is being used by live process";
+ if (verbose) {
+ SessionState.getConsole().printInfo(message);
+ } else {
+ SessionState.getConsole().logInfo(message);
+ }
+ }
+ if (removable) {
+ scratchDirToRemove.add(scratchDir.getPath());
+ }
}
}
[14/48] hive git commit: HIVE-12721: Add UUID built in function
(Jeremy Beard, reviewed by Sergio Pena and Sean Busbey)
Posted by sp...@apache.org.
HIVE-12721: Add UUID built in function (Jeremy Beard, reviewed by Sergio Pena and Sean Busbey)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/793681c7
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/793681c7
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/793681c7
Branch: refs/heads/java8
Commit: 793681c76e6892bfddc5a4609c124648b9284279
Parents: 68a4210
Author: Jeremy Beard <je...@cloudera.com>
Authored: Fri May 27 10:31:46 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Fri May 27 10:32:16 2016 -0500
----------------------------------------------------------------------
.../hadoop/hive/ql/exec/FunctionRegistry.java | 2 +
.../org/apache/hadoop/hive/ql/udf/UDFUUID.java | 50 ++++++++++++++++++++
.../apache/hadoop/hive/ql/udf/TestUDFUUID.java | 38 +++++++++++++++
.../results/clientpositive/show_functions.q.out | 1 +
4 files changed, 91 insertions(+)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/793681c7/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
index 2f4a94c..fa90242 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/FunctionRegistry.java
@@ -103,6 +103,7 @@ import org.apache.hadoop.hive.ql.udf.UDFToLong;
import org.apache.hadoop.hive.ql.udf.UDFToShort;
import org.apache.hadoop.hive.ql.udf.UDFToString;
import org.apache.hadoop.hive.ql.udf.UDFType;
+import org.apache.hadoop.hive.ql.udf.UDFUUID;
import org.apache.hadoop.hive.ql.udf.UDFUnbase64;
import org.apache.hadoop.hive.ql.udf.UDFUnhex;
import org.apache.hadoop.hive.ql.udf.UDFWeekOfYear;
@@ -238,6 +239,7 @@ public final class FunctionRegistry {
system.registerUDF("sha", UDFSha1.class, false);
system.registerGenericUDF("aes_encrypt", GenericUDFAesEncrypt.class);
system.registerGenericUDF("aes_decrypt", GenericUDFAesDecrypt.class);
+ system.registerUDF("uuid", UDFUUID.class, false);
system.registerGenericUDF("encode", GenericUDFEncode.class);
system.registerGenericUDF("decode", GenericUDFDecode.class);
http://git-wip-us.apache.org/repos/asf/hive/blob/793681c7/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFUUID.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFUUID.java b/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFUUID.java
new file mode 100644
index 0000000..1340ded
--- /dev/null
+++ b/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFUUID.java
@@ -0,0 +1,50 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.hive.ql.udf;
+
+import java.util.UUID;
+
+import org.apache.hadoop.hive.ql.exec.Description;
+import org.apache.hadoop.hive.ql.exec.UDF;
+import org.apache.hadoop.io.Text;
+
+/**
+ * UDFUUID.
+ *
+ */
+@Description(name = "uuid",
+value = "_FUNC_() - Returns a universally unique identifier (UUID) string.",
+extended = "The value is returned as a canonical UUID 36-character string.\n"
++ "Example:\n"
++ " > SELECT _FUNC_();\n"
++ " '0baf1f52-53df-487f-8292-99a03716b688'\n"
++ " > SELECT _FUNC_();\n"
++ " '36718a53-84f5-45d6-8796-4f79983ad49d'")
+public class UDFUUID extends UDF {
+ private final Text result = new Text();
+ /**
+ * Returns a universally unique identifier (UUID) string (36 characters).
+ *
+ * @return Text
+ */
+ public Text evaluate() {
+ result.set(UUID.randomUUID().toString());
+ return result;
+ }
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/793681c7/ql/src/test/org/apache/hadoop/hive/ql/udf/TestUDFUUID.java
----------------------------------------------------------------------
diff --git a/ql/src/test/org/apache/hadoop/hive/ql/udf/TestUDFUUID.java b/ql/src/test/org/apache/hadoop/hive/ql/udf/TestUDFUUID.java
new file mode 100644
index 0000000..5f04547
--- /dev/null
+++ b/ql/src/test/org/apache/hadoop/hive/ql/udf/TestUDFUUID.java
@@ -0,0 +1,38 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.hive.ql.udf;
+
+import junit.framework.TestCase;
+
+import org.junit.Test;
+
+public class TestUDFUUID extends TestCase {
+ @Test
+ public void testUUID() throws Exception {
+ UDFUUID udf = new UDFUUID();
+
+ String id1 = udf.evaluate().toString();
+ String id2 = udf.evaluate().toString();
+
+ assertFalse(id1.equals(id2));
+
+ assertEquals(id1.length(), 36);
+ assertEquals(id2.length(), 36);
+ }
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/793681c7/ql/src/test/results/clientpositive/show_functions.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/show_functions.q.out b/ql/src/test/results/clientpositive/show_functions.q.out
index a811747..6e3f9c8 100644
--- a/ql/src/test/results/clientpositive/show_functions.q.out
+++ b/ql/src/test/results/clientpositive/show_functions.q.out
@@ -221,6 +221,7 @@ unbase64
unhex
unix_timestamp
upper
+uuid
var_pop
var_samp
variance
[07/48] hive git commit: HIVE-13821: OrcSplit groups all delta files
together into a single split (Prasanth Jayachandran reviewed by Eugene
Koifman)
Posted by sp...@apache.org.
HIVE-13821: OrcSplit groups all delta files together into a single split (Prasanth Jayachandran reviewed by Eugene Koifman)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/76961d1f
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/76961d1f
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/76961d1f
Branch: refs/heads/java8
Commit: 76961d1f67a5d5e3614d3d81c417684fab92c6c2
Parents: 51609a0
Author: Prasanth Jayachandran <pr...@apache.org>
Authored: Wed May 25 18:22:34 2016 -0700
Committer: Prasanth Jayachandran <pr...@apache.org>
Committed: Wed May 25 18:22:34 2016 -0700
----------------------------------------------------------------------
.../ql/exec/tez/ColumnarSplitSizeEstimator.java | 6 +++--
.../hive/ql/io/orc/TestInputOutputFormat.java | 23 ++++++++++++++++++++
2 files changed, 27 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/76961d1f/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ColumnarSplitSizeEstimator.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ColumnarSplitSizeEstimator.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ColumnarSplitSizeEstimator.java
index dfc778a..ecd4ddc 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ColumnarSplitSizeEstimator.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/tez/ColumnarSplitSizeEstimator.java
@@ -42,7 +42,6 @@ public class ColumnarSplitSizeEstimator implements SplitSizeEstimator {
if (isDebugEnabled) {
LOG.debug("Estimated column projection size: " + colProjSize);
}
- return colProjSize;
} else if (inputSplit instanceof HiveInputFormat.HiveInputSplit) {
InputSplit innerSplit = ((HiveInputFormat.HiveInputSplit) inputSplit).getInputSplit();
@@ -51,9 +50,12 @@ public class ColumnarSplitSizeEstimator implements SplitSizeEstimator {
if (isDebugEnabled) {
LOG.debug("Estimated column projection size: " + colProjSize);
}
- return colProjSize;
}
}
+ if (colProjSize <= 0) {
+ /* columnar splits of unknown size - estimate worst-case */
+ return Integer.MAX_VALUE;
+ }
return colProjSize;
}
}
http://git-wip-us.apache.org/repos/asf/hive/blob/76961d1f/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestInputOutputFormat.java
----------------------------------------------------------------------
diff --git a/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestInputOutputFormat.java b/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestInputOutputFormat.java
index 4eb0249..c1ef0e7 100644
--- a/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestInputOutputFormat.java
+++ b/ql/src/test/org/apache/hadoop/hive/ql/io/orc/TestInputOutputFormat.java
@@ -56,6 +56,7 @@ import org.apache.hadoop.hive.metastore.api.hive_metastoreConstants;
import org.apache.hadoop.hive.ql.exec.SerializationUtilities;
import org.apache.hadoop.hive.ql.exec.Utilities;
import org.apache.hadoop.hive.ql.exec.mr.ExecMapper;
+import org.apache.hadoop.hive.ql.exec.tez.ColumnarSplitSizeEstimator;
import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.DecimalColumnVector;
import org.apache.hadoop.hive.ql.exec.vector.DoubleColumnVector;
@@ -556,6 +557,28 @@ public class TestInputOutputFormat {
}
@Test
+ public void testACIDSplitStrategy() throws Exception {
+ conf.set("bucket_count", "2");
+ OrcInputFormat.Context context = new OrcInputFormat.Context(conf);
+ MockFileSystem fs = new MockFileSystem(conf,
+ new MockFile("mock:/a/delta_000_001/part-00", 1000, new byte[1], new MockBlock("host1")),
+ new MockFile("mock:/a/delta_000_001/part-01", 1000, new byte[1], new MockBlock("host1")),
+ new MockFile("mock:/a/delta_001_002/part-02", 1000, new byte[1], new MockBlock("host1")),
+ new MockFile("mock:/a/delta_001_002/part-03", 1000, new byte[1], new MockBlock("host1")));
+ OrcInputFormat.FileGenerator gen =
+ new OrcInputFormat.FileGenerator(context, fs,
+ new MockPath(fs, "mock:/a"), false, null);
+ OrcInputFormat.SplitStrategy splitStrategy = createSplitStrategy(context, gen);
+ assertEquals(true, splitStrategy instanceof OrcInputFormat.ACIDSplitStrategy);
+ List<OrcSplit> splits = splitStrategy.getSplits();
+ ColumnarSplitSizeEstimator splitSizeEstimator = new ColumnarSplitSizeEstimator();
+ for (OrcSplit split: splits) {
+ assertEquals(Integer.MAX_VALUE, splitSizeEstimator.getEstimatedSize(split));
+ }
+ assertEquals(2, splits.size());
+ }
+
+ @Test
public void testBIStrategySplitBlockBoundary() throws Exception {
conf.set(HiveConf.ConfVars.HIVE_ORC_SPLIT_STRATEGY.varname, "BI");
OrcInputFormat.Context context = new OrcInputFormat.Context(conf);
[48/48] hive git commit: HIVE-13860: Fix more json related JDK8 test
failures (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
HIVE-13860: Fix more json related JDK8 test failures (Mohit Sabharwal, reviewed by Sergio Pena)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/eaa8ff21
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/eaa8ff21
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/eaa8ff21
Branch: refs/heads/java8
Commit: eaa8ff214d3acdf6245a5e0f490a55cdc0097a83
Parents: 4ca8a63
Author: Mohit Sabharwal <mo...@cloudera.com>
Authored: Fri May 27 10:35:16 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Fri May 27 10:36:29 2016 -0500
----------------------------------------------------------------------
.../clientpositive/autoColumnStats_1.q.out | 28 +++---
.../clientpositive/autoColumnStats_2.q.out | 24 ++---
.../clientpositive/autoColumnStats_3.q.out | 10 +-
.../clientpositive/autoColumnStats_4.q.out | 2 +-
.../clientpositive/autoColumnStats_5.q.out | 8 +-
.../clientpositive/autoColumnStats_8.q.out | 8 +-
.../clientpositive/autoColumnStats_9.q.out | 2 +-
.../clientpositive/binary_output_format.q.out | 4 +-
.../results/clientpositive/json_serde1.q.out | 4 +-
.../results/clientpositive/orc_create.q.out | 12 +--
.../clientpositive/orc_int_type_promotion.q.out | 6 +-
.../results/clientpositive/perf/query85.q.out | 2 +-
.../results/clientpositive/perf/query89.q.out | 2 +-
.../results/clientpositive/perf/query91.q.out | 2 +-
.../results/clientpositive/spark/bucket5.q.out | 8 +-
.../results/clientpositive/spark/join0.q.out | 2 +-
.../clientpositive/spark/outer_join_ppr.q.out | 4 +-
.../spark/reduce_deduplicate.q.out | 4 +-
.../clientpositive/spark/union_ppr.q.out | 8 +-
.../clientpositive/stats_list_bucket.q.out | 2 +-
.../results/clientpositive/tez/bucket2.q.out | 4 +-
.../clientpositive/udaf_collect_set_2.q.out | 96 ++++++++++----------
.../results/clientpositive/udf_sort_array.q.out | 2 +-
.../clientpositive/vector_complex_all.q.out | 6 +-
.../results/clientpositive/vector_udf1.q.out | 2 +-
25 files changed, 126 insertions(+), 126 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_1.q.out b/ql/src/test/results/clientpositive/autoColumnStats_1.q.out
index e290e52..4cf6df1 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_1.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_1.q.out
@@ -60,7 +60,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -137,7 +137,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -172,7 +172,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -257,7 +257,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -292,7 +292,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -351,7 +351,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 508
rawDataSize 5400
@@ -564,7 +564,7 @@ Database: default
Table: alter5
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"col1\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 1406
@@ -648,7 +648,7 @@ Database: default
Table: src_stat_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 5
rawDataSize 38
@@ -699,7 +699,7 @@ Database: default
Table: src_stat_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 25
rawDataSize 191
@@ -838,7 +838,7 @@ Database: default
Table: tab_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 4
numRows 500
rawDataSize 5312
@@ -899,7 +899,7 @@ Database: default
Table: tab
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 242
rawDataSize 2566
@@ -1023,7 +1023,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 2
rawDataSize 6
@@ -1086,7 +1086,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1000
rawDataSize 10624
@@ -1167,7 +1167,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1000
rawDataSize 10624
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out
index a76bf5f..791e6ae 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out
@@ -60,7 +60,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -173,7 +173,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -208,7 +208,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 1000
rawDataSize 10624
@@ -341,7 +341,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 508
rawDataSize 5400
@@ -561,7 +561,7 @@ Database: default
Table: alter5
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"col1\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"col1\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 1406
@@ -769,7 +769,7 @@ Database: default
Table: src_stat_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 5
rawDataSize 38
@@ -820,7 +820,7 @@ Database: default
Table: src_stat_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 25
rawDataSize 191
@@ -959,7 +959,7 @@ Database: default
Table: tab_part
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 4
numRows 500
rawDataSize 5312
@@ -1020,7 +1020,7 @@ Database: default
Table: tab
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 242
rawDataSize 2566
@@ -1144,7 +1144,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 2
rawDataSize 6
@@ -1207,7 +1207,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1000
rawDataSize 10624
@@ -1288,7 +1288,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1000
rawDataSize 10624
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_3.q.out b/ql/src/test/results/clientpositive/autoColumnStats_3.q.out
index ee41910..dca158b 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_3.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_3.q.out
@@ -36,7 +36,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
numFiles 0
numRows 0
rawDataSize 0
@@ -81,7 +81,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -251,7 +251,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"value\":\"true\"}}
numFiles 1
numRows 2
rawDataSize 6
@@ -361,7 +361,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 12
@@ -401,7 +401,7 @@ Database: default
Table: nzhang_part14
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 16
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
index 676a27a..50d988d 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
@@ -196,7 +196,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}}
numFiles 2
numRows 10
rawDataSize 0
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
index 04ed3ce..c2153fb 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_5.q.out
@@ -185,7 +185,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 40
@@ -245,7 +245,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 40
@@ -431,7 +431,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 56
@@ -625,7 +625,7 @@ Database: default
Table: partitioned1
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\",\"d\":\"true\"}}
numFiles 2
numRows 6
rawDataSize 78
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out
index 5b74d2d..5d9e5ab 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_8.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_8.q.out
@@ -197,7 +197,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -243,7 +243,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -289,7 +289,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -335,7 +335,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/autoColumnStats_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out
index 4a7b2b7..da8b19c 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out
@@ -231,7 +231,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 137
numRows 855
rawDataSize 9143
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/binary_output_format.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/binary_output_format.q.out b/ql/src/test/results/clientpositive/binary_output_format.q.out
index 51328e2..f3c624c 100644
--- a/ql/src/test/results/clientpositive/binary_output_format.q.out
+++ b/ql/src/test/results/clientpositive/binary_output_format.q.out
@@ -129,7 +129,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -149,7 +149,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/json_serde1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/json_serde1.q.out b/ql/src/test/results/clientpositive/json_serde1.q.out
index 6235aff..e14d674 100644
--- a/ql/src/test/results/clientpositive/json_serde1.q.out
+++ b/ql/src/test/results/clientpositive/json_serde1.q.out
@@ -93,8 +93,8 @@ POSTHOOK: query: select * from json_serde1_2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@json_serde1_2
#### A masked pattern was here ####
-[3,2,1] {1:"2001-01-01",2:null} {"c1":123456,"c2":"hello","c3":["aa","bb","cc"],"c4":{"xyz":456,"abc":123},"c5":{"c5_1":"bye","c5_2":88}}
-[3,2,1] {1:"2001-01-01",2:null} {"c1":123456,"c2":"hello","c3":["aa","bb","cc"],"c4":{"xyz":456,"abc":123},"c5":{"c5_1":"bye","c5_2":88}}
+[3,2,1] {1:"2001-01-01",2:null} {"c1":123456,"c2":"hello","c3":["aa","bb","cc"],"c4":{"abc":123,"xyz":456},"c5":{"c5_1":"bye","c5_2":88}}
+[3,2,1] {1:"2001-01-01",2:null} {"c1":123456,"c2":"hello","c3":["aa","bb","cc"],"c4":{"abc":123,"xyz":456},"c5":{"c5_1":"bye","c5_2":88}}
PREHOOK: query: drop table json_serde1_1
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@json_serde1_1
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/orc_create.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_create.q.out b/ql/src/test/results/clientpositive/orc_create.q.out
index 34ab00d..40d127c 100644
--- a/ql/src/test/results/clientpositive/orc_create.q.out
+++ b/ql/src/test/results/clientpositive/orc_create.q.out
@@ -380,9 +380,9 @@ POSTHOOK: query: SELECT * from orc_create_complex
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_create_complex
#### A masked pattern was here ####
-line1 {"key13":"value13","key12":"value12","key11":"value11"} ["a","b","c"] {"A":"one","B":"two"}
-line2 {"key21":"value21","key23":"value23","key22":"value22"} ["d","e","f"] {"A":"three","B":"four"}
-line3 {"key33":"value33","key31":"value31","key32":"value32"} ["g","h","i"] {"A":"five","B":"six"}
+line1 {"key13":"value13","key11":"value11","key12":"value12"} ["a","b","c"] {"A":"one","B":"two"}
+line2 {"key21":"value21","key22":"value22","key23":"value23"} ["d","e","f"] {"A":"three","B":"four"}
+line3 {"key31":"value31","key32":"value32","key33":"value33"} ["g","h","i"] {"A":"five","B":"six"}
PREHOOK: query: SELECT str from orc_create_complex
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_create_complex
@@ -402,9 +402,9 @@ POSTHOOK: query: SELECT mp from orc_create_complex
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_create_complex
#### A masked pattern was here ####
-{"key13":"value13","key12":"value12","key11":"value11"}
-{"key21":"value21","key23":"value23","key22":"value22"}
-{"key33":"value33","key31":"value31","key32":"value32"}
+{"key13":"value13","key11":"value11","key12":"value12"}
+{"key21":"value21","key22":"value22","key23":"value23"}
+{"key31":"value31","key32":"value32","key33":"value33"}
PREHOOK: query: SELECT lst from orc_create_complex
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_create_complex
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
index 3b2e962..d3837a3 100644
--- a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
+++ b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
@@ -127,7 +127,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypes_orc
#### A masked pattern was here ####
true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k2":"v2","k1":"v1"} [100,200] {"c1":null,"c2":" \"foo\"}"}
-false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k4":"v4","k3":"v3"} [200,300] {"c1":null,"c2":" \"bar\"}"}
+false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"}
PREHOOK: query: alter table alltypes_orc change si si int
PREHOOK: type: ALTERTABLE_RENAMECOL
PREHOOK: Input: default@alltypes_orc
@@ -145,7 +145,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypes_orc
#### A masked pattern was here ####
true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k2":"v2","k1":"v1"} [100,200] {"c1":null,"c2":" \"foo\"}"}
-false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k4":"v4","k3":"v3"} [200,300] {"c1":null,"c2":" \"bar\"}"}
+false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"}
PREHOOK: query: alter table alltypes_orc change si si bigint
PREHOOK: type: ALTERTABLE_RENAMECOL
PREHOOK: Input: default@alltypes_orc
@@ -171,7 +171,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypes_orc
#### A masked pattern was here ####
true 10 100 1000 10000 4.0 20.0 4.222 1969-12-31 15:59:58.174 1970-01-01 string hello hello {"k2":"v2","k1":"v1"} [100,200] {"c1":null,"c2":" \"foo\"}"}
-false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k4":"v4","k3":"v3"} [200,300] {"c1":null,"c2":" \"bar\"}"}
+false 20 200 2000 20000 8.0 40.0 2.222 1970-12-31 15:59:58.174 1971-01-01 abcd world world {"k3":"v3","k4":"v4"} [200,300] {"c1":null,"c2":" \"bar\"}"}
PREHOOK: query: explain select ti, si, i, bi from alltypes_orc
PREHOOK: type: QUERY
POSTHOOK: query: explain select ti, si, i, bi from alltypes_orc
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/perf/query85.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query85.q.out b/ql/src/test/results/clientpositive/perf/query85.q.out
index 0ae13e3..ca23bbb 100644
--- a/ql/src/test/results/clientpositive/perf/query85.q.out
+++ b/ql/src/test/results/clientpositive/perf/query85.q.out
@@ -114,7 +114,7 @@ Stage-0
Select Operator [SEL_17] (rows=1583 width=204)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_100] (rows=1583 width=204)
- predicate:(((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_education_status is not null and cd_marital_status is not null)
+ predicate:(((cd_education_status = '4 yr Degree') or (cd_education_status = 'Primary') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'D') or (cd_marital_status = 'U')) and cd_demo_sk is not null and cd_marital_status is not null and cd_education_status is not null)
TableScan [TS_15] (rows=1583 width=204)
default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
<-Reducer 11 [SIMPLE_EDGE]
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/perf/query89.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query89.q.out b/ql/src/test/results/clientpositive/perf/query89.q.out
index 8e6cc49..c80f06c 100644
--- a/ql/src/test/results/clientpositive/perf/query89.q.out
+++ b/ql/src/test/results/clientpositive/perf/query89.q.out
@@ -143,7 +143,7 @@ Stage-0
Select Operator [SEL_5] (rows=231000 width=1436)
Output:["_col0","_col1","_col2","_col3"]
Filter Operator [FIL_48] (rows=231000 width=1436)
- predicate:(((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and ((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and (((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null)
+ predicate:(((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and ((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and (((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and i_item_sk is not null)
TableScan [TS_3] (rows=462000 width=1436)
default@item,item,Tbl:COMPLETE,Col:NONE,Output:["i_item_sk","i_brand","i_class","i_category"]
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/perf/query91.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/query91.q.out b/ql/src/test/results/clientpositive/perf/query91.q.out
index fa9165f..81f37c5 100644
--- a/ql/src/test/results/clientpositive/perf/query91.q.out
+++ b/ql/src/test/results/clientpositive/perf/query91.q.out
@@ -43,7 +43,7 @@ Stage-0
Select Operator [SEL_27] (rows=790 width=204)
Output:["_col0","_col1","_col2"]
Filter Operator [FIL_79] (rows=790 width=204)
- predicate:(((cd_marital_status = 'M') or (cd_marital_status = 'W')) and ((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and (((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and cd_demo_sk is not null)
+ predicate:(((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'W')) and (((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and cd_demo_sk is not null)
TableScan [TS_25] (rows=1583 width=204)
default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_marital_status","cd_education_status"]
<-Reducer 4 [SIMPLE_EDGE]
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/spark/bucket5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket5.q.out b/ql/src/test/results/clientpositive/spark/bucket5.q.out
index a78fae0..b5d8890 100644
--- a/ql/src/test/results/clientpositive/spark/bucket5.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket5.q.out
@@ -73,7 +73,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -93,7 +93,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -141,7 +141,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -161,7 +161,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/spark/join0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join0.q.out b/ql/src/test/results/clientpositive/spark/join0.q.out
index bc98bb4..3398ae7 100644
--- a/ql/src/test/results/clientpositive/spark/join0.q.out
+++ b/ql/src/test/results/clientpositive/spark/join0.q.out
@@ -28,7 +28,7 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 4)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
index dfa6ea5..360abc9 100644
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
@@ -28,7 +28,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 3 (PARTITION-LEVEL SORT, 4)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -427,7 +427,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 3 (PARTITION-LEVEL SORT, 4)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/spark/reduce_deduplicate.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/reduce_deduplicate.q.out b/ql/src/test/results/clientpositive/spark/reduce_deduplicate.q.out
index b20e8fe..1fc9d28 100644
--- a/ql/src/test/results/clientpositive/spark/reduce_deduplicate.q.out
+++ b/ql/src/test/results/clientpositive/spark/reduce_deduplicate.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -74,7 +74,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/spark/union_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/union_ppr.q.out b/ql/src/test/results/clientpositive/spark/union_ppr.q.out
index 8f7b1f2..01747c6 100644
--- a/ql/src/test/results/clientpositive/spark/union_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/union_ppr.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -114,7 +114,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -191,7 +191,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -237,7 +237,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/stats_list_bucket.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_list_bucket.q.out b/ql/src/test/results/clientpositive/stats_list_bucket.q.out
index c34c414..c66da97 100644
--- a/ql/src/test/results/clientpositive/stats_list_bucket.q.out
+++ b/ql/src/test/results/clientpositive/stats_list_bucket.q.out
@@ -168,7 +168,7 @@ Stored As SubDirectories: Yes
Skewed Columns: [c1, c2]
Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287, [82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82}
+Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287}
Storage Desc Params:
serialization.format 1
PREHOOK: query: drop table stats_list_bucket
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/tez/bucket2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/bucket2.q.out b/ql/src/test/results/clientpositive/tez/bucket2.q.out
index 800edf3..e78a1a7 100644
--- a/ql/src/test/results/clientpositive/tez/bucket2.q.out
+++ b/ql/src/test/results/clientpositive/tez/bucket2.q.out
@@ -59,7 +59,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -79,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/udaf_collect_set_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/udaf_collect_set_2.q.out b/ql/src/test/results/clientpositive/udaf_collect_set_2.q.out
index 536234f..7425988 100644
--- a/ql/src/test/results/clientpositive/udaf_collect_set_2.q.out
+++ b/ql/src/test/results/clientpositive/udaf_collect_set_2.q.out
@@ -232,9 +232,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"name":"Chris","date":"2013-06-21","sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"name":"Chris","date":"2014-10-11","sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"name":"John","date":"2013-08-10","sub":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"name":"John","date":"2014-06-25","sub":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"name":"John","date":"2015-01-15","sub":{"\"milk\"":27.45}}]
-3 [{"name":"Martin","date":"2014-05-11","sub":{"\"orange\"":41.35,"\"apple\"":30.5}},{"name":"Martin","date":"2014-12-12","sub":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"name":"Chris","date":"2013-06-21","sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"name":"Chris","date":"2014-10-11","sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"name":"John","date":"2013-08-10","sub":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"name":"John","date":"2014-06-25","sub":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"name":"John","date":"2015-01-15","sub":{"\"milk\"":27.45}}]
+3 [{"name":"Martin","date":"2014-05-11","sub":{"\"apple\"":30.5,"\"orange\"":41.35}},{"name":"Martin","date":"2014-12-12","sub":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(named_struct("name", c.name, "date", o.date, "sub", o.sub)))
FROM customers c
INNER JOIN nested_orders o
@@ -251,9 +251,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"name":"Chris","date":"2013-06-21","sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"name":"Chris","date":"2013-06-21","sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"name":"Chris","date":"2014-10-11","sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"name":"John","date":"2013-08-10","sub":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"name":"John","date":"2014-06-25","sub":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"name":"John","date":"2015-01-15","sub":{"\"milk\"":27.45}}]
-3 [{"name":"Martin","date":"2014-05-11","sub":{"\"orange\"":41.35,"\"apple\"":30.5}},{"name":"Martin","date":"2014-12-12","sub":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"name":"Chris","date":"2013-06-21","sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"name":"Chris","date":"2013-06-21","sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"name":"Chris","date":"2014-10-11","sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"name":"John","date":"2013-08-10","sub":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"name":"John","date":"2014-06-25","sub":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"name":"John","date":"2015-01-15","sub":{"\"milk\"":27.45}}]
+3 [{"name":"Martin","date":"2014-05-11","sub":{"\"apple\"":30.5,"\"orange\"":41.35}},{"name":"Martin","date":"2014-12-12","sub":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: SELECT c.id, sort_array(collect_set(struct(c.name, o.date, o.sub)))
FROM customers c
INNER JOIN nested_orders o
@@ -270,9 +270,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"col1":"Chris","col2":"2013-06-21","col3":{"\"bread\"":15.2,"\"juice\"":21.45}},{"col1":"Chris","col2":"2014-10-11","col3":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"col1":"John","col2":"2013-08-10","col3":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"col1":"John","col2":"2014-06-25","col3":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"col1":"John","col2":"2015-01-15","col3":{"\"milk\"":27.45}}]
-3 [{"col1":"Martin","col2":"2014-05-11","col3":{"\"orange\"":41.35,"\"apple\"":30.5}},{"col1":"Martin","col2":"2014-12-12","col3":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"col1":"Chris","col2":"2013-06-21","col3":{"\"juice\"":21.45,"\"bread\"":15.2}},{"col1":"Chris","col2":"2014-10-11","col3":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"col1":"John","col2":"2013-08-10","col3":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"col1":"John","col2":"2014-06-25","col3":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"col1":"John","col2":"2015-01-15","col3":{"\"milk\"":27.45}}]
+3 [{"col1":"Martin","col2":"2014-05-11","col3":{"\"apple\"":30.5,"\"orange\"":41.35}},{"col1":"Martin","col2":"2014-12-12","col3":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(struct(c.name, o.date, o.sub)))
FROM customers c
INNER JOIN nested_orders o
@@ -289,9 +289,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"col1":"Chris","col2":"2013-06-21","col3":{"\"bread\"":15.2,"\"juice\"":21.45}},{"col1":"Chris","col2":"2013-06-21","col3":{"\"bread\"":15.2,"\"juice\"":21.45}},{"col1":"Chris","col2":"2014-10-11","col3":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"col1":"John","col2":"2013-08-10","col3":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"col1":"John","col2":"2014-06-25","col3":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"col1":"John","col2":"2015-01-15","col3":{"\"milk\"":27.45}}]
-3 [{"col1":"Martin","col2":"2014-05-11","col3":{"\"orange\"":41.35,"\"apple\"":30.5}},{"col1":"Martin","col2":"2014-12-12","col3":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"col1":"Chris","col2":"2013-06-21","col3":{"\"juice\"":21.45,"\"bread\"":15.2}},{"col1":"Chris","col2":"2013-06-21","col3":{"\"juice\"":21.45,"\"bread\"":15.2}},{"col1":"Chris","col2":"2014-10-11","col3":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"col1":"John","col2":"2013-08-10","col3":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"col1":"John","col2":"2014-06-25","col3":{"\"chocolate\"":3.65,"\"water\"":420.36}},{"col1":"John","col2":"2015-01-15","col3":{"\"milk\"":27.45}}]
+3 [{"col1":"Martin","col2":"2014-05-11","col3":{"\"apple\"":30.5,"\"orange\"":41.35}},{"col1":"Martin","col2":"2014-12-12","col3":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: -- 1.3 when field is list
SELECT c.id, sort_array(collect_set(named_struct("name", c.name, "date", o.date, "sub", map_values(o.sub))))
@@ -312,9 +312,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"name":"Chris","date":"2013-06-21","sub":[15.2,21.45]},{"name":"Chris","date":"2014-10-11","sub":[1200.5,29.36]}]
-2 [{"name":"John","date":"2013-08-10","sub":[210.57,126.57]},{"name":"John","date":"2014-06-25","sub":[3.65,420.36]},{"name":"John","date":"2015-01-15","sub":[27.45]}]
-3 [{"name":"Martin","date":"2014-05-11","sub":[41.35,30.5]},{"name":"Martin","date":"2014-12-12","sub":[210.03,500.0,100.56]}]
+1 [{"name":"Chris","date":"2013-06-21","sub":[21.45,15.2]},{"name":"Chris","date":"2014-10-11","sub":[1200.5,29.36]}]
+2 [{"name":"John","date":"2013-08-10","sub":[126.57,210.57]},{"name":"John","date":"2014-06-25","sub":[3.65,420.36]},{"name":"John","date":"2015-01-15","sub":[27.45]}]
+3 [{"name":"Martin","date":"2014-05-11","sub":[30.5,41.35]},{"name":"Martin","date":"2014-12-12","sub":[210.03,100.56,500.0]}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(named_struct("name", c.name, "date", o.date, "sub", map_values(o.sub))))
FROM customers c
INNER JOIN nested_orders o
@@ -331,9 +331,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"name":"Chris","date":"2013-06-21","sub":[15.2,21.45]},{"name":"Chris","date":"2013-06-21","sub":[15.2,21.45]},{"name":"Chris","date":"2014-10-11","sub":[1200.5,29.36]}]
-2 [{"name":"John","date":"2013-08-10","sub":[210.57,126.57]},{"name":"John","date":"2014-06-25","sub":[3.65,420.36]},{"name":"John","date":"2015-01-15","sub":[27.45]}]
-3 [{"name":"Martin","date":"2014-05-11","sub":[41.35,30.5]},{"name":"Martin","date":"2014-12-12","sub":[210.03,500.0,100.56]}]
+1 [{"name":"Chris","date":"2013-06-21","sub":[21.45,15.2]},{"name":"Chris","date":"2013-06-21","sub":[21.45,15.2]},{"name":"Chris","date":"2014-10-11","sub":[1200.5,29.36]}]
+2 [{"name":"John","date":"2013-08-10","sub":[126.57,210.57]},{"name":"John","date":"2014-06-25","sub":[3.65,420.36]},{"name":"John","date":"2015-01-15","sub":[27.45]}]
+3 [{"name":"Martin","date":"2014-05-11","sub":[30.5,41.35]},{"name":"Martin","date":"2014-12-12","sub":[210.03,100.56,500.0]}]
PREHOOK: query: SELECT c.id, sort_array(collect_set(struct(c.name, o.date, map_values(o.sub))))
FROM customers c
INNER JOIN nested_orders o
@@ -350,9 +350,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"col1":"Chris","col2":"2013-06-21","col3":[15.2,21.45]},{"col1":"Chris","col2":"2014-10-11","col3":[1200.5,29.36]}]
-2 [{"col1":"John","col2":"2013-08-10","col3":[210.57,126.57]},{"col1":"John","col2":"2014-06-25","col3":[3.65,420.36]},{"col1":"John","col2":"2015-01-15","col3":[27.45]}]
-3 [{"col1":"Martin","col2":"2014-05-11","col3":[41.35,30.5]},{"col1":"Martin","col2":"2014-12-12","col3":[210.03,500.0,100.56]}]
+1 [{"col1":"Chris","col2":"2013-06-21","col3":[21.45,15.2]},{"col1":"Chris","col2":"2014-10-11","col3":[1200.5,29.36]}]
+2 [{"col1":"John","col2":"2013-08-10","col3":[126.57,210.57]},{"col1":"John","col2":"2014-06-25","col3":[3.65,420.36]},{"col1":"John","col2":"2015-01-15","col3":[27.45]}]
+3 [{"col1":"Martin","col2":"2014-05-11","col3":[30.5,41.35]},{"col1":"Martin","col2":"2014-12-12","col3":[210.03,100.56,500.0]}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(struct(c.name, o.date, map_values(o.sub))))
FROM customers c
INNER JOIN nested_orders o
@@ -369,9 +369,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"col1":"Chris","col2":"2013-06-21","col3":[15.2,21.45]},{"col1":"Chris","col2":"2013-06-21","col3":[15.2,21.45]},{"col1":"Chris","col2":"2014-10-11","col3":[1200.5,29.36]}]
-2 [{"col1":"John","col2":"2013-08-10","col3":[210.57,126.57]},{"col1":"John","col2":"2014-06-25","col3":[3.65,420.36]},{"col1":"John","col2":"2015-01-15","col3":[27.45]}]
-3 [{"col1":"Martin","col2":"2014-05-11","col3":[41.35,30.5]},{"col1":"Martin","col2":"2014-12-12","col3":[210.03,500.0,100.56]}]
+1 [{"col1":"Chris","col2":"2013-06-21","col3":[21.45,15.2]},{"col1":"Chris","col2":"2013-06-21","col3":[21.45,15.2]},{"col1":"Chris","col2":"2014-10-11","col3":[1200.5,29.36]}]
+2 [{"col1":"John","col2":"2013-08-10","col3":[126.57,210.57]},{"col1":"John","col2":"2014-06-25","col3":[3.65,420.36]},{"col1":"John","col2":"2015-01-15","col3":[27.45]}]
+3 [{"col1":"Martin","col2":"2014-05-11","col3":[30.5,41.35]},{"col1":"Martin","col2":"2014-12-12","col3":[210.03,100.56,500.0]}]
PREHOOK: query: -- 2. test array
-- 2.1 when field is primitive
@@ -480,9 +480,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [[{"\"bread\"":15.2,"\"juice\"":21.45}],[{"\"grape\"":1200.5,"\"rice\"":29.36}]]
-2 [[{"\"milk\"":27.45}],[{"\"beef\"":210.57,"\"yogurt\"":126.57}],[{"\"chocolate\"":3.65,"\"water\"":420.36}]]
-3 [[{"\"orange\"":41.35,"\"apple\"":30.5}],[{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}]]
+1 [[{"\"juice\"":21.45,"\"bread\"":15.2}],[{"\"grape\"":1200.5,"\"rice\"":29.36}]]
+2 [[{"\"milk\"":27.45}],[{"\"yogurt\"":126.57,"\"beef\"":210.57}],[{"\"chocolate\"":3.65,"\"water\"":420.36}]]
+3 [[{"\"apple\"":30.5,"\"orange\"":41.35}],[{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}]]
PREHOOK: query: SELECT c.id, sort_array(collect_list(array(o.sub)))
FROM customers c
INNER JOIN nested_orders o
@@ -499,9 +499,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [[{"\"bread\"":15.2,"\"juice\"":21.45}],[{"\"bread\"":15.2,"\"juice\"":21.45}],[{"\"grape\"":1200.5,"\"rice\"":29.36}]]
-2 [[{"\"milk\"":27.45}],[{"\"beef\"":210.57,"\"yogurt\"":126.57}],[{"\"chocolate\"":3.65,"\"water\"":420.36}]]
-3 [[{"\"orange\"":41.35,"\"apple\"":30.5}],[{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}]]
+1 [[{"\"juice\"":21.45,"\"bread\"":15.2}],[{"\"juice\"":21.45,"\"bread\"":15.2}],[{"\"grape\"":1200.5,"\"rice\"":29.36}]]
+2 [[{"\"milk\"":27.45}],[{"\"yogurt\"":126.57,"\"beef\"":210.57}],[{"\"chocolate\"":3.65,"\"water\"":420.36}]]
+3 [[{"\"apple\"":30.5,"\"orange\"":41.35}],[{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}]]
PREHOOK: query: -- 2.3 when field is list
SELECT c.id, sort_array(collect_set(array(map_values(o.sub))))
@@ -522,9 +522,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [[[15.2,21.45]],[[1200.5,29.36]]]
-2 [[[3.65,420.36]],[[27.45]],[[210.57,126.57]]]
-3 [[[41.35,30.5]],[[210.03,500.0,100.56]]]
+1 [[[21.45,15.2]],[[1200.5,29.36]]]
+2 [[[3.65,420.36]],[[27.45]],[[126.57,210.57]]]
+3 [[[30.5,41.35]],[[210.03,100.56,500.0]]]
PREHOOK: query: SELECT c.id, sort_array(collect_list(array(map_values(o.sub))))
FROM customers c
INNER JOIN nested_orders o
@@ -541,9 +541,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [[[15.2,21.45]],[[15.2,21.45]],[[1200.5,29.36]]]
-2 [[[3.65,420.36]],[[27.45]],[[210.57,126.57]]]
-3 [[[41.35,30.5]],[[210.03,500.0,100.56]]]
+1 [[[21.45,15.2]],[[21.45,15.2]],[[1200.5,29.36]]]
+2 [[[3.65,420.36]],[[27.45]],[[126.57,210.57]]]
+3 [[[30.5,41.35]],[[210.03,100.56,500.0]]]
PREHOOK: query: -- 3. test map
-- 3.1 when field is primitive
@@ -652,9 +652,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"sub":{"\"milk\"":27.45}},{"sub":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"sub":{"\"chocolate\"":3.65,"\"water\"":420.36}}]
-3 [{"sub":{"\"orange\"":41.35,"\"apple\"":30.5}},{"sub":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"sub":{"\"milk\"":27.45}},{"sub":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"sub":{"\"chocolate\"":3.65,"\"water\"":420.36}}]
+3 [{"sub":{"\"apple\"":30.5,"\"orange\"":41.35}},{"sub":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(map("sub", o.sub)))
FROM customers c
INNER JOIN nested_orders o
@@ -671,9 +671,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"sub":{"\"bread\"":15.2,"\"juice\"":21.45}},{"sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
-2 [{"sub":{"\"milk\"":27.45}},{"sub":{"\"beef\"":210.57,"\"yogurt\"":126.57}},{"sub":{"\"chocolate\"":3.65,"\"water\"":420.36}}]
-3 [{"sub":{"\"orange\"":41.35,"\"apple\"":30.5}},{"sub":{"\"icecream\"":210.03,"\"coffee":500.0,"\"banana\"":100.56}}]
+1 [{"sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"sub":{"\"juice\"":21.45,"\"bread\"":15.2}},{"sub":{"\"grape\"":1200.5,"\"rice\"":29.36}}]
+2 [{"sub":{"\"milk\"":27.45}},{"sub":{"\"yogurt\"":126.57,"\"beef\"":210.57}},{"sub":{"\"chocolate\"":3.65,"\"water\"":420.36}}]
+3 [{"sub":{"\"apple\"":30.5,"\"orange\"":41.35}},{"sub":{"\"icecream\"":210.03,"\"banana\"":100.56,"\"coffee":500.0}}]
PREHOOK: query: -- 3.3 when field is list
SELECT c.id, sort_array(collect_set(map("sub", map_values(o.sub))))
@@ -694,9 +694,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"sub":[15.2,21.45]},{"sub":[1200.5,29.36]}]
-2 [{"sub":[3.65,420.36]},{"sub":[27.45]},{"sub":[210.57,126.57]}]
-3 [{"sub":[41.35,30.5]},{"sub":[210.03,500.0,100.56]}]
+1 [{"sub":[21.45,15.2]},{"sub":[1200.5,29.36]}]
+2 [{"sub":[3.65,420.36]},{"sub":[27.45]},{"sub":[126.57,210.57]}]
+3 [{"sub":[30.5,41.35]},{"sub":[210.03,100.56,500.0]}]
PREHOOK: query: SELECT c.id, sort_array(collect_list(map("sub", map_values(o.sub))))
FROM customers c
INNER JOIN nested_orders o
@@ -713,9 +713,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@customers
POSTHOOK: Input: default@nested_orders
#### A masked pattern was here ####
-1 [{"sub":[15.2,21.45]},{"sub":[15.2,21.45]},{"sub":[1200.5,29.36]}]
-2 [{"sub":[3.65,420.36]},{"sub":[27.45]},{"sub":[210.57,126.57]}]
-3 [{"sub":[41.35,30.5]},{"sub":[210.03,500.0,100.56]}]
+1 [{"sub":[21.45,15.2]},{"sub":[21.45,15.2]},{"sub":[1200.5,29.36]}]
+2 [{"sub":[3.65,420.36]},{"sub":[27.45]},{"sub":[126.57,210.57]}]
+3 [{"sub":[30.5,41.35]},{"sub":[210.03,100.56,500.0]}]
PREHOOK: query: -- clean up
DROP TABLE customer
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/udf_sort_array.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/udf_sort_array.q.out b/ql/src/test/results/clientpositive/udf_sort_array.q.out
index 523b297..a29763a 100644
--- a/ql/src/test/results/clientpositive/udf_sort_array.q.out
+++ b/ql/src/test/results/clientpositive/udf_sort_array.q.out
@@ -119,7 +119,7 @@ SELECT sort_array(array(map("b", 2, "a", 9, "c", 7), map("c", 3, "b", 5, "a", 1)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
#### A masked pattern was here ####
-[{"b":5,"a":1,"c":3},{"b":8,"a":1,"c":6},{"b":2,"a":9,"c":7}]
+[{"a":1,"b":5,"c":3},{"a":1,"b":8,"c":6},{"a":9,"b":2,"c":7}]
PREHOOK: query: -- Test it against data in a table.
CREATE TABLE dest1 (
tinyints ARRAY<TINYINT>,
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/vector_complex_all.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_complex_all.q.out b/ql/src/test/results/clientpositive/vector_complex_all.q.out
index 2ae7c1b..a54a371 100644
--- a/ql/src/test/results/clientpositive/vector_complex_all.q.out
+++ b/ql/src/test/results/clientpositive/vector_complex_all.q.out
@@ -108,9 +108,9 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_create_complex
#### A masked pattern was here ####
orc_create_complex.str orc_create_complex.mp orc_create_complex.lst orc_create_complex.strct
-line1 {"key13":"value13","key12":"value12","key11":"value11"} ["a","b","c"] {"a":"one","b":"two"}
-line2 {"key21":"value21","key23":"value23","key22":"value22"} ["d","e","f"] {"a":"three","b":"four"}
-line3 {"key33":"value33","key31":"value31","key32":"value32"} ["g","h","i"] {"a":"five","b":"six"}
+line1 {"key13":"value13","key11":"value11","key12":"value12"} ["a","b","c"] {"a":"one","b":"two"}
+line2 {"key21":"value21","key22":"value22","key23":"value23"} ["d","e","f"] {"a":"three","b":"four"}
+line3 {"key31":"value31","key32":"value32","key33":"value33"} ["g","h","i"] {"a":"five","b":"six"}
PREHOOK: query: -- However, since this query is not referencing the complex fields, it should vectorize.
EXPLAIN
SELECT COUNT(*) FROM orc_create_complex
http://git-wip-us.apache.org/repos/asf/hive/blob/eaa8ff21/ql/src/test/results/clientpositive/vector_udf1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_udf1.q.out b/ql/src/test/results/clientpositive/vector_udf1.q.out
index 232d78e..92fa06f 100644
--- a/ql/src/test/results/clientpositive/vector_udf1.q.out
+++ b/ql/src/test/results/clientpositive/vector_udf1.q.out
@@ -1285,7 +1285,7 @@ from varchar_udf_1 limit 1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@varchar_udf_1
#### A masked pattern was here ####
-{"b":"2","a":"1","c":"3"} {"b":"2","a":"1","c":"3"}
+{"a":"1","b":"2","c":"3"} {"a":"1","b":"2","c":"3"}
PREHOOK: query: explain
select
substr(c2, 1, 3),
[08/48] hive git commit: HIVE-13729: FileSystem leaks in
FileUtils.checkFileAccessWithImpersonation
Posted by sp...@apache.org.
HIVE-13729: FileSystem leaks in FileUtils.checkFileAccessWithImpersonation
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/ba070558
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/ba070558
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/ba070558
Branch: refs/heads/java8
Commit: ba070558a14162efbc81d5f8fe374ee75d43133b
Parents: 76961d1
Author: Daniel Dai <da...@hortonworks.com>
Authored: Wed May 25 21:44:54 2016 -0700
Committer: Daniel Dai <da...@hortonworks.com>
Committed: Wed May 25 21:44:54 2016 -0700
----------------------------------------------------------------------
.../apache/hadoop/hive/common/FileUtils.java | 20 ++++++++++++--------
1 file changed, 12 insertions(+), 8 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/ba070558/common/src/java/org/apache/hadoop/hive/common/FileUtils.java
----------------------------------------------------------------------
diff --git a/common/src/java/org/apache/hadoop/hive/common/FileUtils.java b/common/src/java/org/apache/hadoop/hive/common/FileUtils.java
index 5cf4d39..d755798 100644
--- a/common/src/java/org/apache/hadoop/hive/common/FileUtils.java
+++ b/common/src/java/org/apache/hadoop/hive/common/FileUtils.java
@@ -387,14 +387,18 @@ public final class FileUtils {
// Otherwise, try user impersonation. Current user must be configured to do user impersonation.
UserGroupInformation proxyUser = UserGroupInformation.createProxyUser(
user, UserGroupInformation.getLoginUser());
- proxyUser.doAs(new PrivilegedExceptionAction<Object>() {
- @Override
- public Object run() throws Exception {
- FileSystem fsAsUser = FileSystem.get(fs.getUri(), fs.getConf());
- ShimLoader.getHadoopShims().checkFileAccess(fsAsUser, stat, action);
- return null;
- }
- });
+ try {
+ proxyUser.doAs(new PrivilegedExceptionAction<Object>() {
+ @Override
+ public Object run() throws Exception {
+ FileSystem fsAsUser = FileSystem.get(fs.getUri(), fs.getConf());
+ ShimLoader.getHadoopShims().checkFileAccess(fsAsUser, stat, action);
+ return null;
+ }
+ });
+ } finally {
+ FileSystem.closeAllForUGI(proxyUser);
+ }
}
/**
[37/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.8.out
deleted file mode 100644
index 00a6235..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.java1.8.out
+++ /dev/null
@@ -1,424 +0,0 @@
-PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (value) on ('val_466','val_287','val_82')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (value) on ('val_466','val_287','val_82')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- src
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [value]
-Skewed Values: [[val_466], [val_287], [val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[val_287]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_287, [val_82]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_82, [val_466]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_466}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_static_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- value
- "val_466"
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (value = 'val_466') (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), 'val_466' (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: value=val_466
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 4812
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 5522
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Truncated Path -> Alias:
- /list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_466 [$hdt$_0:list_bucketing_static_part]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-466 val_466
-466 val_466
-466 val_466
-PREHOOK: query: drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out
new file mode 100644
index 0000000..ecf54a8
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_11.q.out
@@ -0,0 +1,327 @@
+PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- list bucketing DML: static partition. multiple skewed columns.
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (value) on ('val_466','val_287','val_82')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+
+-- list bucketing DML: static partition. multiple skewed columns.
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (value) on ('val_466','val_287','val_82')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 4812
+ totalSize 5522
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [value]
+Skewed Values: [[val_466], [val_287], [val_82]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[val_287]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_287, [val_82]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_82, [val_466]=/list_bucketing_static_part/ds=2008-04-08/hr=11/value=val_466}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain extended
+select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ numFiles 4
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 4812
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 5522
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_static_part
+ Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (value = 'val_466') (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), 'val_466' (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select key, value from list_bucketing_static_part where ds='2008-04-08' and hr='11' and value = "val_466"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+466 val_466
+466 val_466
+466 val_466
+PREHOOK: query: drop table list_bucketing_static_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: drop table list_bucketing_static_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out
deleted file mode 100644
index 0be7f4e..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.7.out
+++ /dev/null
@@ -1,426 +0,0 @@
-PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_mul_col
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col1 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col3 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col5 EXPRESSION []
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_mul_col
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-# col_name data_type comment
-
-col1 string
-col2 string
-col3 string
-col4 string
-col5 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_mul_col
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 6312
- totalSize 7094
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [col2, col4]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=82/col4=val_82, [466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=287/col4=val_287}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Processor Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1 466 1 val_466 1 2008-04-08 11
-1 466 1 val_466 1 2008-04-08 11
-1 466 1 val_466 1 2008-04-08 11
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Processor Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '382') and (col4 = 'val_382')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '382' (type: string), col3 (type: string), 'val_382' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1 382 1 val_382 1 2008-04-08 11
-1 382 1 val_382 1 2008-04-08 11
-PREHOOK: query: drop table list_bucketing_mul_col
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: drop table list_bucketing_mul_col
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Output: default@list_bucketing_mul_col
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.8.out
deleted file mode 100644
index 6d2298b..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.java1.8.out
+++ /dev/null
@@ -1,596 +0,0 @@
-PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_mul_col
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- src
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_mul_col
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- 1
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- 1
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- 1
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: UDFToString(1) (type: string), key (type: string), UDFToString(1) (type: string), value (type: string), UDFToString(1) (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [$hdt$_0:src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col1 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col3 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col5 EXPRESSION []
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_mul_col
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-# col_name data_type comment
-
-col1 string
-col2 string
-col3 string
-col4 string
-col5 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_mul_col
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 6312
- totalSize 7094
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [col2, col4]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=287/col4=val_287, [82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=82/col4=val_82}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_mul_col
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- col2
- "466"
- =
- TOK_TABLE_OR_COL
- col4
- "val_466"
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5,_col6
- columns.types string:string:string:string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: col4=val_466
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Truncated Path -> Alias:
- /list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=466/col4=val_466 [list_bucketing_mul_col]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1 466 1 val_466 1 2008-04-08 11
-1 466 1 val_466 1 2008-04-08 11
-1 466 1 val_466 1 2008-04-08 11
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_mul_col
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- col2
- "382"
- =
- TOK_TABLE_OR_COL
- col4
- "val_382"
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '382') and (col4 = 'val_382')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '382' (type: string), col3 (type: string), 'val_382' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5,_col6
- columns.types string:string:string:string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Truncated Path -> Alias:
- /list_bucketing_mul_col/ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [list_bucketing_mul_col]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1 382 1 val_382 1 2008-04-08 11
-1 382 1 val_382 1 2008-04-08 11
-PREHOOK: query: drop table list_bucketing_mul_col
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: drop table list_bucketing_mul_col
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Output: default@list_bucketing_mul_col
[36/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out
new file mode 100644
index 0000000..0e11f3f
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_12.q.out
@@ -0,0 +1,424 @@
+PREHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
+create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
+ partitioned by (ds String, hr String)
+ skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_mul_col
+POSTHOOK: query: -- Ensure it works if skewed column is not the first column in the table columns
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
+create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
+ partitioned by (ds String, hr String)
+ skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_mul_col
+PREHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
+select 1, key, 1, value, 1 from src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
+select 1, key, 1, value, 1 from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
+select 1, key, 1, value, 1 from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '11')
+select 1, key, 1, value, 1 from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col1 EXPRESSION []
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col3 EXPRESSION []
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=11).col5 EXPRESSION []
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_mul_col
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_mul_col
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_mul_col
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_mul_col
+# col_name data_type comment
+
+col1 string
+col2 string
+col3 string
+col4 string
+col5 string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_mul_col
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 6312
+ totalSize 7094
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [col2, col4]
+Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=287/col4=val_287, [82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=11/col2=82/col4=val_82}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ numFiles 4
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 6312
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 7094
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+ name: default.list_bucketing_mul_col
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_mul_col
+ Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_mul_col
+PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "466" and col4 = "val_466"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+1 466 1 val_466 1 2008-04-08 11
+1 466 1 val_466 1 2008-04-08 11
+1 466 1 val_466 1 2008-04-08 11
+PREHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ numFiles 4
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 6312
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 7094
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+ name: default.list_bucketing_mul_col
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_mul_col
+ Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((col2 = '382') and (col4 = 'val_382')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: col1 (type: string), '382' (type: string), col3 (type: string), 'val_382' (type: string), col5 (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_mul_col
+PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='11' and col2 = "382" and col4 = "val_382"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+1 382 1 val_382 1 2008-04-08 11
+1 382 1 val_382 1 2008-04-08 11
+PREHOOK: query: drop table list_bucketing_mul_col
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_mul_col
+PREHOOK: Output: default@list_bucketing_mul_col
+POSTHOOK: query: drop table list_bucketing_mul_col
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: Output: default@list_bucketing_mul_col
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out
deleted file mode 100644
index bfce335..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.7.out
+++ /dev/null
@@ -1,337 +0,0 @@
-PREHOOK: query: -- Ensure skewed value map has escaped directory name
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: -- Ensure skewed value map has escaped directory name
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_mul_col
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 2013-01-23+18:00:99
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col1 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col3 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col5 EXPRESSION []
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_mul_col
-ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-# col_name data_type comment
-
-col1 string
-col2 string
-col3 string
-col4 string
-col5 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 2013-01-23+18:00:99]
-Database: default
-Table: list_bucketing_mul_col
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 6312
- totalSize 7094
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [col2, col4]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=82/col4=val_82, [466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=287/col4=val_287}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 2013-01-23+18:00:99
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Processor Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-#### A masked pattern was here ####
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-PREHOOK: query: drop table list_bucketing_mul_col
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: drop table list_bucketing_mul_col
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Output: default@list_bucketing_mul_col
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.8.out
deleted file mode 100644
index f7a1039..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.java1.8.out
+++ /dev/null
@@ -1,439 +0,0 @@
-PREHOOK: query: -- Ensure skewed value map has escaped directory name
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: -- Ensure skewed value map has escaped directory name
-
--- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
-create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
- partitioned by (ds String, hr String)
- skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_mul_col
-PREHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML
-explain extended
-insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- src
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_mul_col
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '2013-01-23+18:00:99'
- TOK_SELECT
- TOK_SELEXPR
- 1
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- 1
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_SELEXPR
- 1
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: UDFToString(1) (type: string), key (type: string), UDFToString(1) (type: string), value (type: string), UDFToString(1) (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [$hdt$_0:src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 2013-01-23+18:00:99
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
-select 1, key, 1, value, 1 from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col1 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col3 EXPRESSION []
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col5 EXPRESSION []
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_mul_col
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_mul_col
-ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-# col_name data_type comment
-
-col1 string
-col2 string
-col3 string
-col4 string
-col5 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 2013-01-23+18:00:99]
-Database: default
-Table: list_bucketing_mul_col
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 6312
- totalSize 7094
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [col2, col4]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=287/col4=val_287, [82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=82/col4=val_82}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_mul_col
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '2013-01-23+18:00:99'
- =
- TOK_TABLE_OR_COL
- col2
- "466"
- =
- TOK_TABLE_OR_COL
- col4
- "val_466"
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_mul_col
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5,_col6
- columns.types string:string:string:string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: col4=val_466
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 2013-01-23+18:00:99
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- numFiles 4
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 6312
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 7094
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns col1,col2,col3,col4,col5
- columns.comments
- columns.types string:string:string:string:string
-#### A masked pattern was here ####
- name default.list_bucketing_mul_col
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_mul_col
- name: default.list_bucketing_mul_col
- Truncated Path -> Alias:
- /list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=466/col4=val_466 [list_bucketing_mul_col]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_mul_col
-where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
-#### A masked pattern was here ####
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
-PREHOOK: query: drop table list_bucketing_mul_col
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_mul_col
-PREHOOK: Output: default@list_bucketing_mul_col
-POSTHOOK: query: drop table list_bucketing_mul_col
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_mul_col
-POSTHOOK: Output: default@list_bucketing_mul_col
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
new file mode 100644
index 0000000..93ebef0
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_13.q.out
@@ -0,0 +1,335 @@
+PREHOOK: query: -- Ensure skewed value map has escaped directory name
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
+create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
+ partitioned by (ds String, hr String)
+ skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_mul_col
+POSTHOOK: query: -- Ensure skewed value map has escaped directory name
+
+-- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- test where the skewed values are more than 1 say columns no. 2 and 4 in a table with 5 columns
+create table list_bucketing_mul_col (col1 String, col2 String, col3 String, col4 String, col5 string)
+ partitioned by (ds String, hr String)
+ skewed by (col2, col4) on (('466','val_466'),('287','val_287'),('82','val_82'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_mul_col
+PREHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
+select 1, key, 1, value, 1 from src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML
+explain extended
+insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
+select 1, key, 1, value, 1 from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: '1' (type: string), key (type: string), '1' (type: string), value (type: string), '1' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 2013-01-23+18:00:99
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
+select 1, key, 1, value, 1 from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
+POSTHOOK: query: insert overwrite table list_bucketing_mul_col partition (ds = '2008-04-08', hr = '2013-01-23+18:00:99')
+select 1, key, 1, value, 1 from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col1 EXPRESSION []
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col2 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col3 EXPRESSION []
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col4 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_mul_col PARTITION(ds=2008-04-08,hr=2013-01-23+18:00:99).col5 EXPRESSION []
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_mul_col
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_mul_col
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_mul_col
+ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
+PREHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: query: desc formatted list_bucketing_mul_col partition (ds='2008-04-08', hr='2013-01-23+18:00:99')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_mul_col
+# col_name data_type comment
+
+col1 string
+col2 string
+col3 string
+col4 string
+col5 string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 2013-01-23+18:00:99]
+Database: default
+Table: list_bucketing_mul_col
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 6312
+ totalSize 7094
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [col2, col4]
+Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[466, val_466]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=466/col4=val_466, [287, val_287]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=287/col4=val_287, [82, val_82]=/list_bucketing_mul_col/ds=2008-04-08/hr=2013-01-23+18%3A00%3A99/col2=82/col4=val_82}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 2013-01-23+18:00:99
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ numFiles 4
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 6312
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 7094
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns col1,col2,col3,col4,col5
+ columns.comments
+ columns.types string:string:string:string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_mul_col
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_mul_col { string col1, string col2, string col3, string col4, string col5}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_mul_col
+ name: default.list_bucketing_mul_col
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_mul_col
+ Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((col2 = '466') and (col4 = 'val_466')) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: col1 (type: string), '466' (type: string), col3 (type: string), 'val_466' (type: string), col5 (type: string), '2008-04-08' (type: string), '2013-01-23+18:00:99' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 125 Data size: 1578 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_mul_col
+PREHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_mul_col
+where ds='2008-04-08' and hr='2013-01-23+18:00:99' and col2 = "466" and col4 = "val_466"
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: Input: default@list_bucketing_mul_col@ds=2008-04-08/hr=2013-01-23+18%3A00%3A99
+#### A masked pattern was here ####
+1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
+1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
+1 466 1 val_466 1 2008-04-08 2013-01-23+18:00:99
+PREHOOK: query: drop table list_bucketing_mul_col
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_mul_col
+PREHOOK: Output: default@list_bucketing_mul_col
+POSTHOOK: query: drop table list_bucketing_mul_col
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_mul_col
+POSTHOOK: Output: default@list_bucketing_mul_col
[18/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
deleted file mode 100644
index 793b8be..0000000
--- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out
+++ /dev/null
@@ -1,766 +0,0 @@
-Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: -- non agg, non corr
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain
-select key, count(*)
-from src
-group by key
-having key not in
- ( select key from src s1
- where s1.key > '12'
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- non agg, non corr
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain
-select key, count(*)
-from src
-group by key
-having key not in
- ( select key from src s1
- where s1.key > '12'
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4
- Stage-3 depends on stages: Stage-2
- Stage-4 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: key
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- keys: key (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '12') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: -- non agg, corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- non agg, corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-5
- Stage-3 depends on stages: Stage-2, Stage-6
- Stage-4 is a root stage
- Stage-5 depends on stages: Stage-4
- Stage-6 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: p_mfgr, p_retailprice
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(p_retailprice)
- keys: p_mfgr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: double)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string), _col1 (type: double)
- 1 _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: p_mfgr, p_retailprice
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(p_retailprice), max(p_retailprice)
- keys: p_mfgr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: p_mfgr, p_retailprice
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(p_retailprice), max(p_retailprice)
- keys: p_mfgr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 - _col1) > 600.0) (type: boolean)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
-POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@part
-#### A masked pattern was here ####
-Manufacturer#1 1173.15
-Manufacturer#2 1690.68
-Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: -- agg, non corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- agg, non corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-5
- Stage-3 depends on stages: Stage-2, Stage-6
- Stage-4 is a root stage
- Stage-5 depends on stages: Stage-4
- Stage-6 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: p_mfgr, p_retailprice
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(p_retailprice)
- keys: p_mfgr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: double)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: p_mfgr is null (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_retailprice (type: double)
- outputColumnNames: _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: max(_col1), min(_col1)
- keys: null (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0), min(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: double), _col2 (type: double)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 - _col2) > 600.0) (type: boolean)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: p_mfgr, p_retailprice
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: max(p_retailprice), min(p_retailprice)
- keys: p_mfgr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0), min(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 - _col2) > 600.0) (type: boolean)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
-POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@part
-#### A masked pattern was here ####
-Manufacturer#1 1173.15
-Manufacturer#2 1690.68
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out
deleted file mode 100644
index 4e227cd..0000000
--- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out
+++ /dev/null
@@ -1,762 +0,0 @@
-Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: -- non agg, non corr
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain
-select key, count(*)
-from src
-group by key
-having key not in
- ( select key from src s1
- where s1.key > '12'
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- non agg, non corr
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-explain
-select key, count(*)
-from src
-group by key
-having key not in
- ( select key from src s1
- where s1.key > '12'
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4
- Stage-3 depends on stages: Stage-2
- Stage-4 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '12') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '12') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: -- non agg, corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- non agg, corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-5
- Stage-3 depends on stages: Stage-2, Stage-6
- Stage-4 is a root stage
- Stage-5 depends on stages: Stage-4
- Stage-6 is a root stage
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: double)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: double)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string), _col1 (type: double)
- 1 _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(_col1), max(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(_col1), max(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 - _col1) > 600.0) (type: boolean)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
-POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a
- where min(p_retailprice) = l and r - l > 600
- )
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@part
-#### A masked pattern was here ####
-Manufacturer#1 1173.15
-Manufacturer#2 1690.68
-Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
-PREHOOK: query: -- agg, non corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-PREHOOK: type: QUERY
-POSTHOOK: query: -- agg, non corr
-explain
-select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-4
- Stage-3 depends on stages: Stage-2, Stage-6
- Stage-4 is a root stage
- Stage-5 is a root stage
- Stage-6 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-3
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: min(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col2 is null (type: boolean)
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: double)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_mfgr (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: max(_col1), min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0), min(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 - _col2) > 600.0) (type: boolean)
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: p_mfgr is null (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: null (type: string), p_retailprice (type: double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: max(_col1), min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double), _col2 (type: double)
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0), min(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: double), _col2 (type: double)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 - _col2) > 600.0) (type: boolean)
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product
-PREHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
-POSTHOOK: query: select b.p_mfgr, min(p_retailprice)
-from part b
-group by b.p_mfgr
-having b.p_mfgr not in
- (select p_mfgr
- from part a
- group by p_mfgr
- having max(p_retailprice) - min(p_retailprice) > 600
- )
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@part
-#### A masked pattern was here ####
-Manufacturer#2 1690.68
-Manufacturer#1 1173.15
[24/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.8.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.8.out
deleted file mode 100644
index 12f41eb..0000000
--- a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.java1.8.out
+++ /dev/null
@@ -1,280 +0,0 @@
-PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key) on ('484','51','103')
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- src
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: src
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
- Truncated Path -> Alias:
- /src [src]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5520
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key]
-Skewed Values: [[484], [51], [103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
-Storage Desc Params:
- serialization.format 1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.out
new file mode 100644
index 0000000..9eca85a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/spark/list_bucket_dml_10.q.out
@@ -0,0 +1,250 @@
+PREHOOK: query: -- run this test case in minimr to ensure it works in cluster
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','51','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- run this test case in minimr to ensure it works in cluster
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key) on ('484','51','103')
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: src
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [src]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 4
+ numRows 500
+ rawDataSize 4812
+ totalSize 5520
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key]
+Skewed Values: [[484], [51], [103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103, [51]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=51, [484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484}
+Storage Desc Params:
+ serialization.format 1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.7.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.7.out
deleted file mode 100644
index d8da70c..0000000
--- a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.7.out
+++ /dev/null
@@ -1,591 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103, [484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 6
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10898
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 12
-51 val_51 2008-04-08 12
-PREHOOK: query: select * from list_bucketing_static_part where key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-PREHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-PREHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-90
-PREHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-90
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.8.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.8.out
deleted file mode 100644
index 23dc6a3..0000000
--- a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.java1.8.out
+++ /dev/null
@@ -1,663 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_static_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 6
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10898
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 12
-51 val_51 2008-04-08 12
-PREHOOK: query: select * from list_bucketing_static_part where key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-PREHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-PREHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-90
-PREHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-90
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.out b/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.out
index 3ee9b5a..c83c02e 100644
Binary files a/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.out and b/ql/src/test/results/clientpositive/spark/list_bucket_dml_2.q.out differ
[06/48] hive git commit: HIVE-13267: Vectorization: Add
SelectLikeStringColScalar for non-filter operations (Gopal V,
reviewed by Matt McCline)
Posted by sp...@apache.org.
HIVE-13267: Vectorization: Add SelectLikeStringColScalar for non-filter operations (Gopal V, reviewed by Matt McCline)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/51609a0f
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/51609a0f
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/51609a0f
Branch: refs/heads/java8
Commit: 51609a0f242ca96de2d6c92b57d4343f89e0d9cc
Parents: d2dac26
Author: Gopal V <go...@apache.org>
Authored: Wed May 25 16:50:33 2016 -0700
Committer: Gopal V <go...@apache.org>
Committed: Wed May 25 16:50:33 2016 -0700
----------------------------------------------------------------------
...AbstractFilterStringColLikeStringScalar.java | 2 +-
.../SelectStringColLikeStringScalar.java | 179 +++++++++++++++++++
.../org/apache/hadoop/hive/ql/udf/UDFLike.java | 3 +-
.../test/queries/clientpositive/vector_udf2.q | 29 +++
.../results/clientpositive/vector_udf2.q.out | 110 ++++++++++++
5 files changed, 321 insertions(+), 2 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/51609a0f/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/AbstractFilterStringColLikeStringScalar.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/AbstractFilterStringColLikeStringScalar.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/AbstractFilterStringColLikeStringScalar.java
index b70beef..c50af8d 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/AbstractFilterStringColLikeStringScalar.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/AbstractFilterStringColLikeStringScalar.java
@@ -63,7 +63,7 @@ public abstract class AbstractFilterStringColLikeStringScalar extends VectorExpr
* @param pattern
* @return
*/
- private Checker createChecker(String pattern) {
+ Checker createChecker(String pattern) {
for (CheckerFactory checkerFactory : getCheckerFactories()) {
Checker checker = checkerFactory.tryCreate(pattern);
if (checker != null) {
http://git-wip-us.apache.org/repos/asf/hive/blob/51609a0f/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/SelectStringColLikeStringScalar.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/SelectStringColLikeStringScalar.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/SelectStringColLikeStringScalar.java
new file mode 100644
index 0000000..b914196
--- /dev/null
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/SelectStringColLikeStringScalar.java
@@ -0,0 +1,179 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hadoop.hive.ql.exec.vector.expressions;
+
+import java.nio.charset.StandardCharsets;
+
+import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor.Descriptor;
+import org.apache.hadoop.hive.ql.exec.vector.expressions.AbstractFilterStringColLikeStringScalar.Checker;
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.LongColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorExpressionDescriptor;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+
+public class SelectStringColLikeStringScalar extends VectorExpression {
+
+ private static final long serialVersionUID = 1L;
+
+ private int colNum;
+ private int outputColumn;
+ private byte[] pattern;
+ transient Checker checker = null;
+
+ public SelectStringColLikeStringScalar() {
+ super();
+ }
+
+ public SelectStringColLikeStringScalar(int colNum, byte[] pattern, int outputColumn) {
+ super();
+ this.colNum = colNum;
+ this.pattern = pattern;
+ this.outputColumn = outputColumn;
+ }
+
+ @Override
+ public void evaluate(VectorizedRowBatch batch) {
+ if (checker == null) {
+ checker = borrowChecker();
+ }
+
+ if (childExpressions != null) {
+ super.evaluateChildren(batch);
+ }
+
+ BytesColumnVector inputColVector = (BytesColumnVector) batch.cols[colNum];
+ int[] sel = batch.selected;
+ boolean[] nullPos = inputColVector.isNull;
+ int n = batch.size;
+ byte[][] vector = inputColVector.vector;
+ int[] length = inputColVector.length;
+ int[] start = inputColVector.start;
+
+ LongColumnVector outV = (LongColumnVector) batch.cols[outputColumn];
+ long[] outputVector = outV.vector;
+
+ // return immediately if batch is empty
+ if (n == 0) {
+ return;
+ }
+
+ outV.noNulls = inputColVector.noNulls;
+ outV.isRepeating = inputColVector.isRepeating;
+
+ if (inputColVector.noNulls) {
+ if (inputColVector.isRepeating) {
+ outputVector[0] = (checker.check(vector[0], start[0], length[0]) ? 1 : 0);
+ outV.isNull[0] = false;
+ } else if (batch.selectedInUse) {
+ for (int j = 0; j != n; j++) {
+ int i = sel[j];
+ outputVector[i] = (checker.check(vector[i], start[i], length[i]) ? 1 : 0);
+ outV.isNull[i] = false;
+ }
+ } else {
+ for (int i = 0; i != n; i++) {
+ outputVector[i] = (checker.check(vector[i], start[i], length[i]) ? 1 : 0);
+ outV.isNull[i] = false;
+ }
+ }
+ } else {
+ if (inputColVector.isRepeating) {
+ //All must be selected otherwise size would be zero. Repeating property will not change.
+ if (!nullPos[0]) {
+ outputVector[0] = (checker.check(vector[0], start[0], length[0]) ? 1 : 0);
+ outV.isNull[0] = false;
+ } else {
+ outputVector[0] = LongColumnVector.NULL_VALUE;
+ outV.isNull[0] = true;
+ }
+ } else if (batch.selectedInUse) {
+ for (int j = 0; j != n; j++) {
+ int i = sel[j];
+ if (!nullPos[i]) {
+ outputVector[i] = (checker.check(vector[i], start[i], length[i]) ? 1 : 0);
+ outV.isNull[i] = false;
+ } else {
+ outputVector[0] = LongColumnVector.NULL_VALUE;
+ outV.isNull[i] = true;
+ }
+ }
+ } else {
+ for (int i = 0; i != n; i++) {
+ if (!nullPos[i]) {
+ outputVector[i] = (checker.check(vector[i], start[i], length[i]) ? 1 : 0);
+ outV.isNull[i] = false;
+ } else {
+ outputVector[0] = LongColumnVector.NULL_VALUE;
+ outV.isNull[i] = true;
+ }
+ }
+ }
+ }
+ }
+
+ private Checker borrowChecker() {
+ FilterStringColLikeStringScalar fil = new FilterStringColLikeStringScalar();
+ return fil.createChecker(new String(pattern, StandardCharsets.UTF_8));
+ }
+
+ public int getColNum() {
+ return colNum;
+ }
+
+ public void setColNum(int colNum) {
+ this.colNum = colNum;
+ }
+
+ public byte[] getPattern() {
+ return pattern;
+ }
+
+ public void setPattern(byte[] pattern) {
+ this.pattern = pattern;
+ }
+
+ public void setOutputColumn(int outputColumn) {
+ this.outputColumn = outputColumn;
+ }
+
+ @Override
+ public int getOutputColumn() {
+ return outputColumn;
+ }
+
+ @Override
+ public String getOutputType() {
+ return "String_Family";
+ }
+
+ @Override
+ public Descriptor getDescriptor() {
+ return (new VectorExpressionDescriptor.Builder())
+ .setMode(
+ VectorExpressionDescriptor.Mode.PROJECTION)
+ .setNumArguments(2)
+ .setArgumentTypes(
+ VectorExpressionDescriptor.ArgumentType.STRING_FAMILY,
+ VectorExpressionDescriptor.ArgumentType.STRING)
+ .setInputExpressionTypes(
+ VectorExpressionDescriptor.InputExpressionType.COLUMN,
+ VectorExpressionDescriptor.InputExpressionType.SCALAR).build();
+ }
+
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/51609a0f/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFLike.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFLike.java b/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFLike.java
index 85d0363..7bcd36e 100755
--- a/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFLike.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/udf/UDFLike.java
@@ -25,6 +25,7 @@ import org.apache.hadoop.hive.ql.exec.Description;
import org.apache.hadoop.hive.ql.exec.UDF;
import org.apache.hadoop.hive.ql.exec.vector.VectorizedExpressions;
import org.apache.hadoop.hive.ql.exec.vector.expressions.FilterStringColLikeStringScalar;
+import org.apache.hadoop.hive.ql.exec.vector.expressions.SelectStringColLikeStringScalar;
import org.apache.hadoop.io.BooleanWritable;
import org.apache.hadoop.io.Text;
@@ -37,7 +38,7 @@ import org.apache.hadoop.io.Text;
extended = "Example:\n"
+ " > SELECT a.* FROM srcpart a WHERE a.hr _FUNC_ '%2' LIMIT 1;\n"
+ " 27 val_27 2008-04-08 12")
-@VectorizedExpressions({FilterStringColLikeStringScalar.class})
+@VectorizedExpressions({FilterStringColLikeStringScalar.class, SelectStringColLikeStringScalar.class})
public class UDFLike extends UDF {
private final Text lastLikePattern = new Text();
private Pattern p = null;
http://git-wip-us.apache.org/repos/asf/hive/blob/51609a0f/ql/src/test/queries/clientpositive/vector_udf2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/vector_udf2.q b/ql/src/test/queries/clientpositive/vector_udf2.q
new file mode 100644
index 0000000..e349d14
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/vector_udf2.q
@@ -0,0 +1,29 @@
+SET hive.vectorized.execution.enabled=true;
+set hive.fetch.task.conversion=none;
+
+drop table varchar_udf_2;
+
+create table varchar_udf_2 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC;
+insert overwrite table varchar_udf_2
+ select key, value, key, value from src where key = '238' limit 1;
+
+explain
+select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1;
+
+select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1;
+
+drop table varchar_udf_2;
http://git-wip-us.apache.org/repos/asf/hive/blob/51609a0f/ql/src/test/results/clientpositive/vector_udf2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_udf2.q.out b/ql/src/test/results/clientpositive/vector_udf2.q.out
new file mode 100644
index 0000000..42e7041
--- /dev/null
+++ b/ql/src/test/results/clientpositive/vector_udf2.q.out
@@ -0,0 +1,110 @@
+PREHOOK: query: drop table varchar_udf_2
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table varchar_udf_2
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table varchar_udf_2 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@varchar_udf_2
+POSTHOOK: query: create table varchar_udf_2 (c1 string, c2 string, c3 varchar(10), c4 varchar(20)) STORED AS ORC
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@varchar_udf_2
+PREHOOK: query: insert overwrite table varchar_udf_2
+ select key, value, key, value from src where key = '238' limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@varchar_udf_2
+POSTHOOK: query: insert overwrite table varchar_udf_2
+ select key, value, key, value from src where key = '238' limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@varchar_udf_2
+POSTHOOK: Lineage: varchar_udf_2.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_2.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_2.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: varchar_udf_2.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: explain
+select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: varchar_udf_2
+ Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (c1 like '%38%') (type: boolean), (c2 like 'val_%') (type: boolean), (c3 like '%38') (type: boolean), (c1 like '%3x8%') (type: boolean), (c2 like 'xval_%') (type: boolean), (c3 like '%x38') (type: boolean)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@varchar_udf_2
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ c1 LIKE '%38%',
+ c2 LIKE 'val_%',
+ c3 LIKE '%38',
+ c1 LIKE '%3x8%',
+ c2 LIKE 'xval_%',
+ c3 LIKE '%x38'
+from varchar_udf_2 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@varchar_udf_2
+#### A masked pattern was here ####
+true true true false false false
+PREHOOK: query: drop table varchar_udf_2
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@varchar_udf_2
+PREHOOK: Output: default@varchar_udf_2
+POSTHOOK: query: drop table varchar_udf_2
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@varchar_udf_2
+POSTHOOK: Output: default@varchar_udf_2
[35/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out
deleted file mode 100644
index dcfbec0..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.7.out
+++ /dev/null
@@ -1,591 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [srcpart]
- /srcpart/ds=2008-04-08/hr=12 [srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103, [484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
-
-STAGE PLANS:
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 6
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10898
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Processor Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 12
-51 val_51 2008-04-08 12
-PREHOOK: query: select * from list_bucketing_static_part where key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-PREHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-PREHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-90
-PREHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-90
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.8.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.8.out
deleted file mode 100644
index aeeba03..0000000
--- a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.java1.8.out
+++ /dev/null
@@ -1,692 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- list bucketing DML: static partition. multiple skewed columns.
--- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
--- 5263 000000_0
--- 5263 000001_0
--- ds=2008-04-08/hr=11/key=103/value=val_103:
--- 99 000000_0
--- 99 000001_0
--- ds=2008-04-08/hr=11/key=484/value=val_484:
--- 87 000000_0
--- 87 000001_0
-
--- create a skewed table
-create table list_bucketing_static_part (key String, value String)
- partitioned by (ds String, hr String)
- skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
- stored as DIRECTORIES
- STORED AS RCFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@list_bucketing_static_part
-PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
-explain extended
-insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- srcpart
- TOK_INSERT
- TOK_DESTINATION
- TOK_TAB
- TOK_TABNAME
- list_bucketing_static_part
- TOK_PARTSPEC
- TOK_PARTVAL
- ds
- '2008-04-08'
- TOK_PARTVAL
- hr
- '11'
- TOK_SELECT
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- key
- TOK_SELEXPR
- TOK_TABLE_OR_COL
- value
- TOK_WHERE
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: srcpart
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-04-08/hr=11/
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:srcpart]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_0:srcpart]
-
- Stage: Stage-0
- Move Operator
- tables:
- partition:
- ds 2008-04-08
- hr 11
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
-
- Stage: Stage-2
- Stats-Aggr Operator
-#### A masked pattern was here ####
-
-PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
-select key, value from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-PREHOOK: type: SHOWPARTITIONS
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: -- check DML result
-show partitions list_bucketing_static_part
-POSTHOOK: type: SHOWPARTITIONS
-POSTHOOK: Input: default@list_bucketing_static_part
-ds=2008-04-08/hr=11
-PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-# col_name data_type comment
-
-key string
-value string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: list_bucketing_static_part
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 6
- numRows 1000
- rawDataSize 9624
- totalSize 10898
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [key, value]
-Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-1000
-PREHOOK: query: select count(*) from list_bucketing_static_part
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) from list_bucketing_static_part
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-1000
-PREHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-POSTHOOK: query: explain extended
-select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_TABREF
- TOK_TABNAME
- list_bucketing_static_part
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- TOK_ALLCOLREF
- TOK_WHERE
- and
- and
- and
- =
- TOK_TABLE_OR_COL
- ds
- '2008-04-08'
- =
- TOK_TABLE_OR_COL
- hr
- '11'
- =
- TOK_TABLE_OR_COL
- key
- '484'
- =
- TOK_TABLE_OR_COL
- value
- 'val_484'
-
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: list_bucketing_static_part
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: value=val_484
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- numFiles 6
- numRows 1000
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 9624
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- totalSize 10898
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.list_bucketing_static_part
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct list_bucketing_static_part { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.list_bucketing_static_part
- name: default.list_bucketing_static_part
- Truncated Path -> Alias:
- /list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484 [list_bucketing_static_part]
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-484 val_484 2008-04-08 11
-484 val_484 2008-04-08 12
-PREHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
--- but query should succeed for 51 or 51 and val_14
-select * from srcpart where ds = '2008-04-08' and key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 12
-51 val_51 2008-04-08 12
-PREHOOK: query: select * from list_bucketing_static_part where key = '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-51 val_51 2008-04-08 11
-PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-PREHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-PREHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
-select count(1) from srcpart where ds = '2008-04-08' and key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-910
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-914
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-86
-PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@srcpart
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@srcpart
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-#### A masked pattern was here ####
-90
-PREHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-POSTHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
-#### A masked pattern was here ####
-90
-PREHOOK: query: -- clean up
-drop table list_bucketing_static_part
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@list_bucketing_static_part
-PREHOOK: Output: default@list_bucketing_static_part
-POSTHOOK: query: -- clean up
-drop table list_bucketing_static_part
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@list_bucketing_static_part
-POSTHOOK: Output: default@list_bucketing_static_part
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
new file mode 100644
index 0000000..a29c224
--- /dev/null
+++ b/ql/src/test/results/clientpositive/list_bucket_dml_2.q.out
@@ -0,0 +1,589 @@
+PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
+-- SORT_QUERY_RESULTS
+
+-- list bucketing DML: static partition. multiple skewed columns.
+-- ds=2008-04-08/hr=11/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME:
+-- 5263 000000_0
+-- 5263 000001_0
+-- ds=2008-04-08/hr=11/key=103/value=val_103:
+-- 99 000000_0
+-- 99 000001_0
+-- ds=2008-04-08/hr=11/key=484/value=val_484:
+-- 87 000000_0
+-- 87 000001_0
+
+-- create a skewed table
+create table list_bucketing_static_part (key String, value String)
+ partitioned by (ds String, hr String)
+ skewed by (key, value) on (('484','val_484'),('51','val_14'),('103','val_103'))
+ stored as DIRECTORIES
+ STORED AS RCFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@list_bucketing_static_part
+PREHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- list bucketing DML without merge. use bucketize to generate a few small files.
+explain extended
+insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-04-08/hr=11/
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=11
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+#### A masked pattern was here ####
+ Partition
+ base file name: hr=12
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ numFiles 1
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.srcpart
+ name: default.srcpart
+ Truncated Path -> Alias:
+ /srcpart/ds=2008-04-08/hr=11 [srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [srcpart]
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ partition:
+ ds 2008-04-08
+ hr 11
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+#### A masked pattern was here ####
+
+PREHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: query: insert overwrite table list_bucketing_static_part partition (ds = '2008-04-08', hr = '11')
+select key, value from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: list_bucketing_static_part PARTITION(ds=2008-04-08,hr=11).value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+PREHOOK: type: SHOWPARTITIONS
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: -- check DML result
+show partitions list_bucketing_static_part
+POSTHOOK: type: SHOWPARTITIONS
+POSTHOOK: Input: default@list_bucketing_static_part
+ds=2008-04-08/hr=11
+PREHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: query: desc formatted list_bucketing_static_part partition (ds='2008-04-08', hr='11')
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+# col_name data_type comment
+
+key string
+value string
+
+# Partition Information
+# col_name data_type comment
+
+ds string
+hr string
+
+# Detailed Partition Information
+Partition Value: [2008-04-08, 11]
+Database: default
+Table: list_bucketing_static_part
+#### A masked pattern was here ####
+Partition Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ numFiles 6
+ numRows 1000
+ rawDataSize 9624
+ totalSize 10898
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+Stored As SubDirectories: Yes
+Skewed Columns: [key, value]
+Skewed Values: [[484, val_484], [51, val_14], [103, val_103]]
+#### A masked pattern was here ####
+Skewed Value to Truncated Path: {[484, val_484]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=484/value=val_484, [103, val_103]=/list_bucketing_static_part/ds=2008-04-08/hr=11/key=103/value=val_103}
+Storage Desc Params:
+ serialization.format 1
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+1000
+PREHOOK: query: select count(*) from list_bucketing_static_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from list_bucketing_static_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+1000
+PREHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
+ properties:
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ numFiles 6
+ numRows 1000
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 9624
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ totalSize 10898
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.list_bucketing_static_part
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct list_bucketing_static_part { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.list_bucketing_static_part
+ name: default.list_bucketing_static_part
+ Processor Tree:
+ TableScan
+ alias: list_bucketing_static_part
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((key = '484') and (value = 'val_484')) (type: boolean)
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '484' (type: string), 'val_484' (type: string), '2008-04-08' (type: string), '11' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+ ListSink
+
+PREHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_static_part where ds = '2008-04-08' and hr = '11' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 11
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '484' and value = 'val_484'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+484 val_484 2008-04-08 11
+484 val_484 2008-04-08 12
+PREHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
+-- but query should succeed for 51 or 51 and val_14
+select * from srcpart where ds = '2008-04-08' and key = '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: -- 51 and val_51 in the table so skewed data for 51 and val_14 should be none
+-- but query should succeed for 51 or 51 and val_14
+select * from srcpart where ds = '2008-04-08' and key = '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+51 val_51 2008-04-08 11
+51 val_51 2008-04-08 11
+51 val_51 2008-04-08 12
+51 val_51 2008-04-08 12
+PREHOOK: query: select * from list_bucketing_static_part where key = '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_static_part where key = '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+51 val_51 2008-04-08 11
+51 val_51 2008-04-08 11
+51 val_51 2008-04-08 11
+51 val_51 2008-04-08 11
+PREHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select * from srcpart where ds = '2008-04-08' and key = '51' and value = 'val_14'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+PREHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select * from list_bucketing_static_part where key = '51' and value = 'val_14'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+PREHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
+select count(1) from srcpart where ds = '2008-04-08' and key < '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: -- queries with < <= > >= should work for skewed test although we don't benefit from pruning
+select count(1) from srcpart where ds = '2008-04-08' and key < '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+910
+PREHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from list_bucketing_static_part where key < '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+910
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key <= '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+914
+PREHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from list_bucketing_static_part where key <= '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+914
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key > '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+86
+PREHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from list_bucketing_static_part where key > '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+86
+PREHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from srcpart where ds = '2008-04-08' and key >= '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+90
+PREHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: select count(1) from list_bucketing_static_part where key >= '51'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Input: default@list_bucketing_static_part@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+90
+PREHOOK: query: -- clean up
+drop table list_bucketing_static_part
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@list_bucketing_static_part
+PREHOOK: Output: default@list_bucketing_static_part
+POSTHOOK: query: -- clean up
+drop table list_bucketing_static_part
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@list_bucketing_static_part
+POSTHOOK: Output: default@list_bucketing_static_part
[22/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
index 217fe76..dfa6ea5 100644
--- a/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/outer_join_ppr.q.out
@@ -20,90 +20,6 @@ EXPLAIN EXTENDED
SELECT a.key, a.value, b.key, b.value
WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- AND
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
-
-
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
@@ -112,7 +28,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 3 (PARTITION-LEVEL SORT, 4)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -121,14 +37,19 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -138,7 +59,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -158,7 +79,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -184,14 +105,19 @@ STAGE PLANS:
alias: b
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -204,7 +130,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -250,7 +176,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -296,7 +222,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -342,7 +268,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -396,39 +322,36 @@ STAGE PLANS:
0
1 {(VALUE._col1 = '2008-04-08')}
keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col1, _col5, _col6
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: ((((_col5 > 15) and (_col5 < 25)) and (_col0 > 10)) and (_col0 < 20)) (type: boolean)
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean)
Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -496,90 +419,6 @@ POSTHOOK: query: EXPLAIN EXTENDED
SELECT a.key, a.value, b.key, b.value
WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25 AND b.ds = '2008-04-08'
POSTHOOK: type: QUERY
-ABSTRACT SYNTAX TREE:
-
-TOK_QUERY
- TOK_FROM
- TOK_FULLOUTERJOIN
- TOK_TABREF
- TOK_TABNAME
- src
- a
- TOK_TABREF
- TOK_TABNAME
- srcpart
- b
- =
- .
- TOK_TABLE_OR_COL
- a
- key
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_INSERT
- TOK_DESTINATION
- TOK_DIR
- TOK_TMP_FILE
- TOK_SELECT
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- a
- value
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- key
- TOK_SELEXPR
- .
- TOK_TABLE_OR_COL
- b
- value
- TOK_WHERE
- AND
- AND
- AND
- AND
- >
- .
- TOK_TABLE_OR_COL
- a
- key
- 10
- <
- .
- TOK_TABLE_OR_COL
- a
- key
- 20
- >
- .
- TOK_TABLE_OR_COL
- b
- key
- 15
- <
- .
- TOK_TABLE_OR_COL
- b
- key
- 25
- =
- .
- TOK_TABLE_OR_COL
- b
- ds
- '2008-04-08'
-
-
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
@@ -588,7 +427,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 4), Map 3 (PARTITION-LEVEL SORT, 4)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -597,14 +436,23 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -614,7 +462,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -634,7 +482,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -658,16 +506,25 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -680,7 +537,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -726,99 +583,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=11
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 11
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- numFiles 1
- numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
- rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
-#### A masked pattern was here ####
- Partition
- base file name: hr=12
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- hr 12
- properties:
- COLUMN_STATS_ACCURATE true
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -858,48 +623,43 @@ STAGE PLANS:
Truncated Path -> Alias:
/srcpart/ds=2008-04-08/hr=11 [b]
/srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
Reducer 2
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Outer Join 0 to 1
+ Right Outer Join0 to 1
keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col1, _col5, _col6, _col7
- Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: (((((_col5 > 15) and (_col5 < 25)) and (_col7 = '2008-04-08')) and (_col0 > 10)) and (_col0 < 20)) (type: boolean)
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -919,8 +679,6 @@ PREHOOK: Input: default@src
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: FROM
src a
@@ -934,8 +692,6 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
-POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
17 val_17 17 val_17
17 val_17 17 val_17
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.7.out b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.7.out
deleted file mode 100644
index b43ea5c..0000000
--- a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.7.out
+++ /dev/null
@@ -1,886 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_4
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_4
-RUN: Stage-0:DDL
-PREHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_5
-POSTHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_5
-RUN: Stage-0:DDL
-Warning: Shuffle Join JOIN[31][tables = [sq_2_notin_nullcheck]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-2
- Spark
- Edges:
- Reducer 2 <- Map 10 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
- Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2)
- Reducer 9 <- Map 8 (GROUP, 1)
- Reducer 4 <- Reducer 3 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 10
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Map 11
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string), value (type: string)
- sort order: ++
- Map-reduce partition columns: key (type: string), value (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map 6
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Map 7
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Map 8
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 4
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
- Reducer 5
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Reducer 9
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-4
- Stats-Aggr Operator
-
-Warning: Shuffle Join JOIN[31][tables = [sq_2_notin_nullcheck]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-2:MAPRED
-RUN: Stage-1:MOVE
-RUN: Stage-0:MOVE
-RUN: Stage-3:STATS
-RUN: Stage-4:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
-Warning: Map Join MAPJOIN[46][bigTable=b] in task 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-2 depends on stages: Stage-5
- Stage-1 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-5
- Spark
- Edges:
- Reducer 6 <- Map 5 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 4
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 5
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 6
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0
- 1
-
- Stage: Stage-2
- Spark
- Edges:
- Reducer 2 <- Map 1 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Reducer 6
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- input vertices:
- 1 Map 4
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Local Work:
- Map Reduce Local Work
- Reducer 2
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-4
- Stats-Aggr Operator
-
-Warning: Map Join MAPJOIN[46][bigTable=b] in task 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-5:MAPRED
-RUN: Stage-2:MAPRED
-RUN: Stage-1:MOVE
-RUN: Stage-0:MOVE
-RUN: Stage-3:STATS
-RUN: Stage-4:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
[19/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.8.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.8.out
deleted file mode 100644
index 899723f..0000000
--- a/ql/src/test/results/clientpositive/subquery_multiinsert.q.java1.8.out
+++ /dev/null
@@ -1,999 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_4
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_4
-RUN: Stage-0:DDL
-PREHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_5
-POSTHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_5
-RUN: Stage-0:DDL
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-10 is a root stage
- Stage-2 depends on stages: Stage-10
- Stage-3 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
- Stage-6 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-6
- Stage-7 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-5
- Stats-Aggr Operator
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: key (type: string), value (type: string)
- sort order: ++
- Map-reduce partition columns: key (type: string), value (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-7
- Stats-Aggr Operator
-
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-10:MAPRED
-RUN: Stage-2:MAPRED
-RUN: Stage-3:MAPRED
-RUN: Stage-6:MAPRED
-RUN: Stage-4:MAPRED
-RUN: Stage-0:MOVE
-RUN: Stage-1:MOVE
-RUN: Stage-7:STATS
-RUN: Stage-5:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
-Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-10 is a root stage
- Stage-14 depends on stages: Stage-10 , consists of Stage-17, Stage-2
- Stage-17 has a backup stage: Stage-2
- Stage-13 depends on stages: Stage-17
- Stage-15 depends on stages: Stage-2, Stage-13
- Stage-4 depends on stages: Stage-15
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
- Stage-16 depends on stages: Stage-2, Stage-13
- Stage-12 depends on stages: Stage-16
- Stage-0 depends on stages: Stage-12
- Stage-7 depends on stages: Stage-0
- Stage-2
-
-STAGE PLANS:
- Stage: Stage-10
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: 0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-14
- Conditional Operator
-
- Stage: Stage-17
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $INTNAME
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $INTNAME
- TableScan
- HashTable Sink Operator
- keys:
- 0
- 1
-
- Stage: Stage-13
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-15
- Map Reduce Local Work
- Alias -> Map Local Tables:
- sq_2:s1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- sq_2:s1
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-5
- Stats-Aggr Operator
-
- Stage: Stage-16
- Map Reduce Local Work
- Alias -> Map Local Tables:
- sq_1:a
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- sq_1:a
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
-
- Stage: Stage-12
- Map Reduce
- Map Operator Tree:
- TableScan
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-7
- Stats-Aggr Operator
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-10:MAPRED
-RUN: Stage-14:CONDITIONAL
-RUN: Stage-17:MAPREDLOCAL
-RUN: Stage-13:MAPRED
-RUN: Stage-15:MAPREDLOCAL
-RUN: Stage-16:MAPREDLOCAL
-RUN: Stage-4:MAPRED
-RUN: Stage-12:MAPRED
-RUN: Stage-1:MOVE
-RUN: Stage-0:MOVE
-RUN: Stage-5:STATS
-RUN: Stage-7:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/subquery_multiinsert.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_multiinsert.q.out b/ql/src/test/results/clientpositive/subquery_multiinsert.q.out
new file mode 100644
index 0000000..ff3abc4
--- /dev/null
+++ b/ql/src/test/results/clientpositive/subquery_multiinsert.q.out
@@ -0,0 +1,997 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE src_4(
+ key STRING,
+ value STRING
+)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@src_4
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE src_4(
+ key STRING,
+ value STRING
+)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@src_4
+RUN: Stage-0:DDL
+PREHOOK: query: CREATE TABLE src_5(
+ key STRING,
+ value STRING
+)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@src_5
+POSTHOOK: query: CREATE TABLE src_5(
+ key STRING,
+ value STRING
+)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@src_5
+RUN: Stage-0:DDL
+Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: explain
+from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-10 is a root stage
+ Stage-2 depends on stages: Stage-10
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-1
+ Stage-6 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-6
+ Stage-7 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-10
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key > '2') and key is null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 = 0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: 0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string), value (type: string)
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key > '2') (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col5 is null (type: boolean)
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_5
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_5
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key > '9') and value is not null) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 key (type: string), value (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_4
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_4
+
+ Stage: Stage-7
+ Stats-Aggr Operator
+
+Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@src_4
+PREHOOK: Output: default@src_5
+POSTHOOK: query: from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@src_4
+POSTHOOK: Output: default@src_5
+POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-10:MAPRED
+RUN: Stage-2:MAPRED
+RUN: Stage-3:MAPRED
+RUN: Stage-6:MAPRED
+RUN: Stage-4:MAPRED
+RUN: Stage-0:MOVE
+RUN: Stage-1:MOVE
+RUN: Stage-7:STATS
+RUN: Stage-5:STATS
+PREHOOK: query: select * from src_4
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_4
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src_4
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_4
+#### A masked pattern was here ####
+90 val_90
+90 val_90
+90 val_90
+92 val_92
+95 val_95
+95 val_95
+96 val_96
+97 val_97
+97 val_97
+98 val_98
+98 val_98
+PREHOOK: query: select * from src_5
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_5
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src_5
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_5
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+10 val_10
+100 val_100
+100 val_100
+103 val_103
+103 val_103
+104 val_104
+104 val_104
+105 val_105
+11 val_11
+111 val_111
+113 val_113
+113 val_113
+114 val_114
+116 val_116
+118 val_118
+118 val_118
+119 val_119
+119 val_119
+119 val_119
+12 val_12
+12 val_12
+120 val_120
+120 val_120
+125 val_125
+125 val_125
+126 val_126
+128 val_128
+128 val_128
+128 val_128
+129 val_129
+129 val_129
+131 val_131
+133 val_133
+134 val_134
+134 val_134
+136 val_136
+137 val_137
+137 val_137
+138 val_138
+138 val_138
+138 val_138
+138 val_138
+143 val_143
+145 val_145
+146 val_146
+146 val_146
+149 val_149
+149 val_149
+15 val_15
+15 val_15
+150 val_150
+152 val_152
+152 val_152
+153 val_153
+155 val_155
+156 val_156
+157 val_157
+158 val_158
+160 val_160
+162 val_162
+163 val_163
+164 val_164
+164 val_164
+165 val_165
+165 val_165
+166 val_166
+167 val_167
+167 val_167
+167 val_167
+168 val_168
+169 val_169
+169 val_169
+169 val_169
+169 val_169
+17 val_17
+170 val_170
+172 val_172
+172 val_172
+174 val_174
+174 val_174
+175 val_175
+175 val_175
+176 val_176
+176 val_176
+177 val_177
+178 val_178
+179 val_179
+179 val_179
+18 val_18
+18 val_18
+180 val_180
+181 val_181
+183 val_183
+186 val_186
+187 val_187
+187 val_187
+187 val_187
+189 val_189
+19 val_19
+190 val_190
+191 val_191
+191 val_191
+192 val_192
+193 val_193
+193 val_193
+193 val_193
+194 val_194
+195 val_195
+195 val_195
+196 val_196
+197 val_197
+197 val_197
+199 val_199
+199 val_199
+199 val_199
+2 val_2
+Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: explain
+from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-10 is a root stage
+ Stage-14 depends on stages: Stage-10 , consists of Stage-17, Stage-2
+ Stage-17 has a backup stage: Stage-2
+ Stage-13 depends on stages: Stage-17
+ Stage-15 depends on stages: Stage-2, Stage-13
+ Stage-4 depends on stages: Stage-15
+ Stage-1 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-1
+ Stage-16 depends on stages: Stage-2, Stage-13
+ Stage-12 depends on stages: Stage-16
+ Stage-0 depends on stages: Stage-12
+ Stage-7 depends on stages: Stage-0
+ Stage-2
+
+STAGE PLANS:
+ Stage: Stage-10
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key > '2') and key is null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 = 0) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: 0 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-14
+ Conditional Operator
+
+ Stage: Stage-17
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-13
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-15
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ sq_2:s1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ sq_2:s1
+ TableScan
+ alias: s1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key > '2') (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col5 is null (type: boolean)
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_5
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_5
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-16
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ sq_1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ sq_1:a
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key > '9') and value is not null) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 key (type: string), value (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+
+ Stage: Stage-12
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0 key (type: string), value (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_4
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_4
+
+ Stage: Stage-7
+ Stats-Aggr Operator
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string), value (type: string)
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+Warning: Map Join MAPJOIN[55][bigTable=b] in task 'Stage-13:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[31][tables = [b, sq_2_notin_nullcheck]] in Stage 'Stage-2:MAPRED' is a cross product
+PREHOOK: query: from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@src_4
+PREHOOK: Output: default@src_5
+POSTHOOK: query: from src b
+INSERT OVERWRITE TABLE src_4
+ select *
+ where b.key in
+ (select a.key
+ from src a
+ where b.value = a.value and a.key > '9'
+ )
+INSERT OVERWRITE TABLE src_5
+ select *
+ where b.key not in ( select key from src s1 where s1.key > '2')
+ order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@src_4
+POSTHOOK: Output: default@src_5
+POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-10:MAPRED
+RUN: Stage-14:CONDITIONAL
+RUN: Stage-17:MAPREDLOCAL
+RUN: Stage-13:MAPRED
+RUN: Stage-15:MAPREDLOCAL
+RUN: Stage-16:MAPREDLOCAL
+RUN: Stage-4:MAPRED
+RUN: Stage-12:MAPRED
+RUN: Stage-1:MOVE
+RUN: Stage-0:MOVE
+RUN: Stage-5:STATS
+RUN: Stage-7:STATS
+PREHOOK: query: select * from src_4
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_4
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src_4
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_4
+#### A masked pattern was here ####
+90 val_90
+90 val_90
+90 val_90
+92 val_92
+95 val_95
+95 val_95
+96 val_96
+97 val_97
+97 val_97
+98 val_98
+98 val_98
+PREHOOK: query: select * from src_5
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src_5
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src_5
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src_5
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+10 val_10
+100 val_100
+100 val_100
+103 val_103
+103 val_103
+104 val_104
+104 val_104
+105 val_105
+11 val_11
+111 val_111
+113 val_113
+113 val_113
+114 val_114
+116 val_116
+118 val_118
+118 val_118
+119 val_119
+119 val_119
+119 val_119
+12 val_12
+12 val_12
+120 val_120
+120 val_120
+125 val_125
+125 val_125
+126 val_126
+128 val_128
+128 val_128
+128 val_128
+129 val_129
+129 val_129
+131 val_131
+133 val_133
+134 val_134
+134 val_134
+136 val_136
+137 val_137
+137 val_137
+138 val_138
+138 val_138
+138 val_138
+138 val_138
+143 val_143
+145 val_145
+146 val_146
+146 val_146
+149 val_149
+149 val_149
+15 val_15
+15 val_15
+150 val_150
+152 val_152
+152 val_152
+153 val_153
+155 val_155
+156 val_156
+157 val_157
+158 val_158
+160 val_160
+162 val_162
+163 val_163
+164 val_164
+164 val_164
+165 val_165
+165 val_165
+166 val_166
+167 val_167
+167 val_167
+167 val_167
+168 val_168
+169 val_169
+169 val_169
+169 val_169
+169 val_169
+17 val_17
+170 val_170
+172 val_172
+172 val_172
+174 val_174
+174 val_174
+175 val_175
+175 val_175
+176 val_176
+176 val_176
+177 val_177
+178 val_178
+179 val_179
+179 val_179
+18 val_18
+18 val_18
+180 val_180
+181 val_181
+183 val_183
+186 val_186
+187 val_187
+187 val_187
+187 val_187
+189 val_189
+19 val_19
+190 val_190
+191 val_191
+191 val_191
+192 val_192
+193 val_193
+193 val_193
+193 val_193
+194 val_194
+195 val_195
+195 val_195
+196 val_196
+197 val_197
+197 val_197
+199 val_199
+199 val_199
+199 val_199
+2 val_2
[39/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/char_udf1.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/char_udf1.q.java1.8.out b/ql/src/test/results/clientpositive/char_udf1.q.java1.8.out
deleted file mode 100644
index 5691a06..0000000
--- a/ql/src/test/results/clientpositive/char_udf1.q.java1.8.out
+++ /dev/null
@@ -1,457 +0,0 @@
-PREHOOK: query: drop table char_udf_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table char_udf_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@char_udf_1
-PREHOOK: query: insert overwrite table char_udf_1
- select key, value, key, value from src where key = '238' limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: insert overwrite table char_udf_1
- select key, value, key, value from src where key = '238' limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@char_udf_1
-POSTHOOK: Lineage: char_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: char_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with char support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
--- UDFs with char support
-select
- concat(c1, c2),
- concat(c3, c4),
- concat(c1, c2) = concat(c3, c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238val_238 238val_238 true
-PREHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- upper(c2),
- upper(c4),
- upper(c2) = upper(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-VAL_238 VAL_238 true
-PREHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lower(c2),
- lower(c4),
- lower(c2) = lower(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Scalar UDFs
-select
- ascii(c2),
- ascii(c4),
- ascii(c2) = ascii(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-118 118 true
-PREHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- concat_ws('|', c1, c2),
- concat_ws('|', c3, c4),
- concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238|val_238 238|val_238 true
-PREHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
- decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- instr(c2, '_'),
- instr(c4, '_'),
- instr(c2, '_') = instr(c4, '_')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-4 4 true
-PREHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- length(c2),
- length(c4),
- length(c2) = length(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-7 7 true
-PREHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- locate('a', 'abcdabcd', 3),
- locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
- locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-5 5 true
-PREHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- lpad(c2, 15, ' '),
- lpad(c4, 15, ' '),
- lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
- val_238 val_238 true
-PREHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- ltrim(c2),
- ltrim(c4),
- ltrim(c2) = ltrim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- regexp(c2, 'val'),
- regexp(c4, 'val'),
- regexp(c2, 'val') = regexp(c4, 'val')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp(c2, 'val'),
- regexp(c4, 'val'),
- regexp(c2, 'val') = regexp(c4, 'val')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-true true true
-PREHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_extract(c2, 'val_([0-9]+)', 1),
- regexp_extract(c4, 'val_([0-9]+)', 1),
- regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-238 238 true
-PREHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- regexp_replace(c2, 'val', 'replaced'),
- regexp_replace(c4, 'val', 'replaced'),
- regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-replaced_238 replaced_238 true
-PREHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- reverse(c2),
- reverse(c4),
- reverse(c2) = reverse(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-832_lav 832_lav true
-PREHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rpad(c2, 15, ' '),
- rpad(c4, 15, ' '),
- rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- rtrim(c2),
- rtrim(c4),
- rtrim(c2) = rtrim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as char(50)))
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- sentences('See spot run. See jane run.'),
- sentences(cast('See spot run. See jane run.' as char(50)))
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
-PREHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- split(c2, '_'),
- split(c4, '_')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-["val","238"] ["val","238"]
-PREHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- str_to_map('a:1,b:2,c:3',',',':'),
- str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-{"a":"1","b":"2","c":"3"} {"a":"1","b":"2","c":"3"}
-PREHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- substr(c2, 1, 3),
- substr(c4, 1, 3),
- substr(c2, 1, 3) = substr(c4, 1, 3)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val val true
-PREHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from char_udf_1 limit 1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- trim(c2),
- trim(c4),
- trim(c2) = trim(c4)
-from char_udf_1 limit 1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238 true
-PREHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: -- Aggregate Functions
-select
- compute_stats(c2, 16),
- compute_stats(c4, 16)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1}
-PREHOOK: query: select
- min(c2),
- min(c4)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- min(c2),
- min(c4)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: select
- max(c2),
- max(c4)
-from char_udf_1
-PREHOOK: type: QUERY
-PREHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-POSTHOOK: query: select
- max(c2),
- max(c4)
-from char_udf_1
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@char_udf_1
-#### A masked pattern was here ####
-val_238 val_238
-PREHOOK: query: drop table char_udf_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@char_udf_1
-PREHOOK: Output: default@char_udf_1
-POSTHOOK: query: drop table char_udf_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@char_udf_1
-POSTHOOK: Output: default@char_udf_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/char_udf1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/char_udf1.q.out b/ql/src/test/results/clientpositive/char_udf1.q.out
new file mode 100644
index 0000000..d84237a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/char_udf1.q.out
@@ -0,0 +1,459 @@
+PREHOOK: query: drop table char_udf_1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table char_udf_1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@char_udf_1
+POSTHOOK: query: create table char_udf_1 (c1 string, c2 string, c3 char(10), c4 char(20))
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@char_udf_1
+PREHOOK: query: insert overwrite table char_udf_1
+ select key, value, key, value from src where key = '238' limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@char_udf_1
+POSTHOOK: query: insert overwrite table char_udf_1
+ select key, value, key, value from src where key = '238' limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@char_udf_1
+POSTHOOK: Lineage: char_udf_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: char_udf_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: char_udf_1.c3 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: char_udf_1.c4 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- UDFs with char support
+select
+ concat(c1, c2),
+ concat(c3, c4),
+ concat(c1, c2) = concat(c3, c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- UDFs with char support
+select
+ concat(c1, c2),
+ concat(c3, c4),
+ concat(c1, c2) = concat(c3, c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+238val_238 238val_238 true
+PREHOOK: query: select
+ upper(c2),
+ upper(c4),
+ upper(c2) = upper(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ upper(c2),
+ upper(c4),
+ upper(c2) = upper(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+VAL_238 VAL_238 true
+PREHOOK: query: select
+ lower(c2),
+ lower(c4),
+ lower(c2) = lower(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ lower(c2),
+ lower(c4),
+ lower(c2) = lower(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: -- Scalar UDFs
+select
+ ascii(c2),
+ ascii(c4),
+ ascii(c2) = ascii(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- Scalar UDFs
+select
+ ascii(c2),
+ ascii(c4),
+ ascii(c2) = ascii(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+118 118 true
+PREHOOK: query: select
+ concat_ws('|', c1, c2),
+ concat_ws('|', c3, c4),
+ concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ concat_ws('|', c1, c2),
+ concat_ws('|', c3, c4),
+ concat_ws('|', c1, c2) = concat_ws('|', c3, c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+238|val_238 238|val_238 true
+PREHOOK: query: select
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c4, 'US-ASCII'), 'US-ASCII'),
+ decode(encode(c2, 'US-ASCII'), 'US-ASCII') = decode(encode(c4, 'US-ASCII'), 'US-ASCII')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ instr(c2, '_'),
+ instr(c4, '_'),
+ instr(c2, '_') = instr(c4, '_')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ instr(c2, '_'),
+ instr(c4, '_'),
+ instr(c2, '_') = instr(c4, '_')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+4 4 true
+PREHOOK: query: select
+ length(c2),
+ length(c4),
+ length(c2) = length(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ length(c2),
+ length(c4),
+ length(c2) = length(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+7 7 true
+PREHOOK: query: select
+ locate('a', 'abcdabcd', 3),
+ locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
+ locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ locate('a', 'abcdabcd', 3),
+ locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3),
+ locate('a', 'abcdabcd', 3) = locate(cast('a' as char(1)), cast('abcdabcd' as char(10)), 3)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+5 5 true
+PREHOOK: query: select
+ lpad(c2, 15, ' '),
+ lpad(c4, 15, ' '),
+ lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ lpad(c2, 15, ' '),
+ lpad(c4, 15, ' '),
+ lpad(c2, 15, ' ') = lpad(c4, 15, ' ')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+ val_238 val_238 true
+PREHOOK: query: select
+ ltrim(c2),
+ ltrim(c4),
+ ltrim(c2) = ltrim(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ ltrim(c2),
+ ltrim(c4),
+ ltrim(c2) = ltrim(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF
+-- we only allow A regexp B, not regexp (A,B).
+
+select
+ c2 regexp 'val',
+ c4 regexp 'val',
+ (c2 regexp 'val') = (c4 regexp 'val')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- In hive wiki page https://cwiki.apache.org/confluence/display/Hive/LanguageManual+UDF
+-- we only allow A regexp B, not regexp (A,B).
+
+select
+ c2 regexp 'val',
+ c4 regexp 'val',
+ (c2 regexp 'val') = (c4 regexp 'val')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+true true true
+PREHOOK: query: select
+ regexp_extract(c2, 'val_([0-9]+)', 1),
+ regexp_extract(c4, 'val_([0-9]+)', 1),
+ regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ regexp_extract(c2, 'val_([0-9]+)', 1),
+ regexp_extract(c4, 'val_([0-9]+)', 1),
+ regexp_extract(c2, 'val_([0-9]+)', 1) = regexp_extract(c4, 'val_([0-9]+)', 1)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+238 238 true
+PREHOOK: query: select
+ regexp_replace(c2, 'val', 'replaced'),
+ regexp_replace(c4, 'val', 'replaced'),
+ regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ regexp_replace(c2, 'val', 'replaced'),
+ regexp_replace(c4, 'val', 'replaced'),
+ regexp_replace(c2, 'val', 'replaced') = regexp_replace(c4, 'val', 'replaced')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+replaced_238 replaced_238 true
+PREHOOK: query: select
+ reverse(c2),
+ reverse(c4),
+ reverse(c2) = reverse(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ reverse(c2),
+ reverse(c4),
+ reverse(c2) = reverse(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+832_lav 832_lav true
+PREHOOK: query: select
+ rpad(c2, 15, ' '),
+ rpad(c4, 15, ' '),
+ rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ rpad(c2, 15, ' '),
+ rpad(c4, 15, ' '),
+ rpad(c2, 15, ' ') = rpad(c4, 15, ' ')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ rtrim(c2),
+ rtrim(c4),
+ rtrim(c2) = rtrim(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ rtrim(c2),
+ rtrim(c4),
+ rtrim(c2) = rtrim(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: select
+ sentences('See spot run. See jane run.'),
+ sentences(cast('See spot run. See jane run.' as char(50)))
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ sentences('See spot run. See jane run.'),
+ sentences(cast('See spot run. See jane run.' as char(50)))
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+[["See","spot","run"],["See","jane","run"]] [["See","spot","run"],["See","jane","run"]]
+PREHOOK: query: select
+ split(c2, '_'),
+ split(c4, '_')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ split(c2, '_'),
+ split(c4, '_')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+["val","238"] ["val","238"]
+PREHOOK: query: select
+ str_to_map('a:1,b:2,c:3',',',':'),
+ str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ str_to_map('a:1,b:2,c:3',',',':'),
+ str_to_map(cast('a:1,b:2,c:3' as char(20)),',',':')
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+{"a":"1","b":"2","c":"3"} {"a":"1","b":"2","c":"3"}
+PREHOOK: query: select
+ substr(c2, 1, 3),
+ substr(c4, 1, 3),
+ substr(c2, 1, 3) = substr(c4, 1, 3)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ substr(c2, 1, 3),
+ substr(c4, 1, 3),
+ substr(c2, 1, 3) = substr(c4, 1, 3)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val val true
+PREHOOK: query: select
+ trim(c2),
+ trim(c4),
+ trim(c2) = trim(c4)
+from char_udf_1 limit 1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ trim(c2),
+ trim(c4),
+ trim(c2) = trim(c4)
+from char_udf_1 limit 1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238 true
+PREHOOK: query: -- Aggregate Functions
+select
+ compute_stats(c2, 16),
+ compute_stats(c4, 16)
+from char_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: -- Aggregate Functions
+select
+ compute_stats(c2, 16),
+ compute_stats(c4, 16)
+from char_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+{"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"} {"columntype":"String","maxlength":7,"avglength":7.0,"countnulls":0,"numdistinctvalues":1,"ndvbitvector":"{0}{3}{2}{3}{1}{0}{2}{0}{1}{0}{0}{1}{3}{2}{0}{3}"}
+PREHOOK: query: select
+ min(c2),
+ min(c4)
+from char_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ min(c2),
+ min(c4)
+from char_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238
+PREHOOK: query: select
+ max(c2),
+ max(c4)
+from char_udf_1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+POSTHOOK: query: select
+ max(c2),
+ max(c4)
+from char_udf_1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@char_udf_1
+#### A masked pattern was here ####
+val_238 val_238
+PREHOOK: query: drop table char_udf_1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@char_udf_1
+PREHOOK: Output: default@char_udf_1
+POSTHOOK: query: drop table char_udf_1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@char_udf_1
+POSTHOOK: Output: default@char_udf_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/input4.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input4.q.java1.7.out b/ql/src/test/results/clientpositive/input4.q.java1.7.out
deleted file mode 100644
index eaeedcb..0000000
--- a/ql/src/test/results/clientpositive/input4.q.java1.7.out
+++ /dev/null
@@ -1,559 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@INPUT4
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@INPUT4
-PREHOOK: query: EXPLAIN
-LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-PREHOOK: type: LOAD
-POSTHOOK: query: EXPLAIN
-LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-POSTHOOK: type: LOAD
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
- Stage-1 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.input4
-
- Stage: Stage-1
- Stats-Aggr Operator
-
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@input4
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@input4
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"ListSink":{}}}}}}}}}}
-PREHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-PREHOOK: type: QUERY
-PREHOOK: Input: default@input4
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@input4
-#### A masked pattern was here ####
-val_238 238
-val_86 86
-val_311 311
-val_27 27
-val_165 165
-val_409 409
-val_255 255
-val_278 278
-val_98 98
-val_484 484
-val_265 265
-val_193 193
-val_401 401
-val_150 150
-val_273 273
-val_224 224
-val_369 369
-val_66 66
-val_128 128
-val_213 213
-val_146 146
-val_406 406
-val_429 429
-val_374 374
-val_152 152
-val_469 469
-val_145 145
-val_495 495
-val_37 37
-val_327 327
-val_281 281
-val_277 277
-val_209 209
-val_15 15
-val_82 82
-val_403 403
-val_166 166
-val_417 417
-val_430 430
-val_252 252
-val_292 292
-val_219 219
-val_287 287
-val_153 153
-val_193 193
-val_338 338
-val_446 446
-val_459 459
-val_394 394
-val_237 237
-val_482 482
-val_174 174
-val_413 413
-val_494 494
-val_207 207
-val_199 199
-val_466 466
-val_208 208
-val_174 174
-val_399 399
-val_396 396
-val_247 247
-val_417 417
-val_489 489
-val_162 162
-val_377 377
-val_397 397
-val_309 309
-val_365 365
-val_266 266
-val_439 439
-val_342 342
-val_367 367
-val_325 325
-val_167 167
-val_195 195
-val_475 475
-val_17 17
-val_113 113
-val_155 155
-val_203 203
-val_339 339
-val_0 0
-val_455 455
-val_128 128
-val_311 311
-val_316 316
-val_57 57
-val_302 302
-val_205 205
-val_149 149
-val_438 438
-val_345 345
-val_129 129
-val_170 170
-val_20 20
-val_489 489
-val_157 157
-val_378 378
-val_221 221
-val_92 92
-val_111 111
-val_47 47
-val_72 72
-val_4 4
-val_280 280
-val_35 35
-val_427 427
-val_277 277
-val_208 208
-val_356 356
-val_399 399
-val_169 169
-val_382 382
-val_498 498
-val_125 125
-val_386 386
-val_437 437
-val_469 469
-val_192 192
-val_286 286
-val_187 187
-val_176 176
-val_54 54
-val_459 459
-val_51 51
-val_138 138
-val_103 103
-val_239 239
-val_213 213
-val_216 216
-val_430 430
-val_278 278
-val_176 176
-val_289 289
-val_221 221
-val_65 65
-val_318 318
-val_332 332
-val_311 311
-val_275 275
-val_137 137
-val_241 241
-val_83 83
-val_333 333
-val_180 180
-val_284 284
-val_12 12
-val_230 230
-val_181 181
-val_67 67
-val_260 260
-val_404 404
-val_384 384
-val_489 489
-val_353 353
-val_373 373
-val_272 272
-val_138 138
-val_217 217
-val_84 84
-val_348 348
-val_466 466
-val_58 58
-val_8 8
-val_411 411
-val_230 230
-val_208 208
-val_348 348
-val_24 24
-val_463 463
-val_431 431
-val_179 179
-val_172 172
-val_42 42
-val_129 129
-val_158 158
-val_119 119
-val_496 496
-val_0 0
-val_322 322
-val_197 197
-val_468 468
-val_393 393
-val_454 454
-val_100 100
-val_298 298
-val_199 199
-val_191 191
-val_418 418
-val_96 96
-val_26 26
-val_165 165
-val_327 327
-val_230 230
-val_205 205
-val_120 120
-val_131 131
-val_51 51
-val_404 404
-val_43 43
-val_436 436
-val_156 156
-val_469 469
-val_468 468
-val_308 308
-val_95 95
-val_196 196
-val_288 288
-val_481 481
-val_457 457
-val_98 98
-val_282 282
-val_197 197
-val_187 187
-val_318 318
-val_318 318
-val_409 409
-val_470 470
-val_137 137
-val_369 369
-val_316 316
-val_169 169
-val_413 413
-val_85 85
-val_77 77
-val_0 0
-val_490 490
-val_87 87
-val_364 364
-val_179 179
-val_118 118
-val_134 134
-val_395 395
-val_282 282
-val_138 138
-val_238 238
-val_419 419
-val_15 15
-val_118 118
-val_72 72
-val_90 90
-val_307 307
-val_19 19
-val_435 435
-val_10 10
-val_277 277
-val_273 273
-val_306 306
-val_224 224
-val_309 309
-val_389 389
-val_327 327
-val_242 242
-val_369 369
-val_392 392
-val_272 272
-val_331 331
-val_401 401
-val_242 242
-val_452 452
-val_177 177
-val_226 226
-val_5 5
-val_497 497
-val_402 402
-val_396 396
-val_317 317
-val_395 395
-val_58 58
-val_35 35
-val_336 336
-val_95 95
-val_11 11
-val_168 168
-val_34 34
-val_229 229
-val_233 233
-val_143 143
-val_472 472
-val_322 322
-val_498 498
-val_160 160
-val_195 195
-val_42 42
-val_321 321
-val_430 430
-val_119 119
-val_489 489
-val_458 458
-val_78 78
-val_76 76
-val_41 41
-val_223 223
-val_492 492
-val_149 149
-val_449 449
-val_218 218
-val_228 228
-val_138 138
-val_453 453
-val_30 30
-val_209 209
-val_64 64
-val_468 468
-val_76 76
-val_74 74
-val_342 342
-val_69 69
-val_230 230
-val_33 33
-val_368 368
-val_103 103
-val_296 296
-val_113 113
-val_216 216
-val_367 367
-val_344 344
-val_167 167
-val_274 274
-val_219 219
-val_239 239
-val_485 485
-val_116 116
-val_223 223
-val_256 256
-val_263 263
-val_70 70
-val_487 487
-val_480 480
-val_401 401
-val_288 288
-val_191 191
-val_5 5
-val_244 244
-val_438 438
-val_128 128
-val_467 467
-val_432 432
-val_202 202
-val_316 316
-val_229 229
-val_469 469
-val_463 463
-val_280 280
-val_2 2
-val_35 35
-val_283 283
-val_331 331
-val_235 235
-val_80 80
-val_44 44
-val_193 193
-val_321 321
-val_335 335
-val_104 104
-val_466 466
-val_366 366
-val_175 175
-val_403 403
-val_483 483
-val_53 53
-val_105 105
-val_257 257
-val_406 406
-val_409 409
-val_190 190
-val_406 406
-val_401 401
-val_114 114
-val_258 258
-val_90 90
-val_203 203
-val_262 262
-val_348 348
-val_424 424
-val_12 12
-val_396 396
-val_201 201
-val_217 217
-val_164 164
-val_431 431
-val_454 454
-val_478 478
-val_298 298
-val_125 125
-val_431 431
-val_164 164
-val_424 424
-val_187 187
-val_382 382
-val_5 5
-val_70 70
-val_397 397
-val_480 480
-val_291 291
-val_24 24
-val_351 351
-val_255 255
-val_104 104
-val_70 70
-val_163 163
-val_438 438
-val_119 119
-val_414 414
-val_200 200
-val_491 491
-val_237 237
-val_439 439
-val_360 360
-val_248 248
-val_479 479
-val_305 305
-val_417 417
-val_199 199
-val_444 444
-val_120 120
-val_429 429
-val_169 169
-val_443 443
-val_323 323
-val_325 325
-val_277 277
-val_230 230
-val_478 478
-val_178 178
-val_468 468
-val_310 310
-val_317 317
-val_333 333
-val_493 493
-val_460 460
-val_207 207
-val_249 249
-val_265 265
-val_480 480
-val_83 83
-val_136 136
-val_353 353
-val_172 172
-val_214 214
-val_462 462
-val_233 233
-val_406 406
-val_133 133
-val_175 175
-val_189 189
-val_454 454
-val_375 375
-val_401 401
-val_421 421
-val_407 407
-val_384 384
-val_256 256
-val_26 26
-val_134 134
-val_67 67
-val_384 384
-val_379 379
-val_18 18
-val_462 462
-val_492 492
-val_100 100
-val_298 298
-val_9 9
-val_341 341
-val_498 498
-val_146 146
-val_458 458
-val_362 362
-val_186 186
-val_285 285
-val_348 348
-val_167 167
-val_18 18
-val_273 273
-val_183 183
-val_281 281
-val_344 344
-val_97 97
-val_469 469
-val_315 315
-val_84 84
-val_28 28
-val_37 37
-val_448 448
-val_152 152
-val_348 348
-val_307 307
-val_194 194
-val_414 414
-val_477 477
-val_222 222
-val_126 126
-val_90 90
-val_169 169
-val_403 403
-val_400 400
-val_200 200
-val_97 97
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/input4.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input4.q.java1.8.out b/ql/src/test/results/clientpositive/input4.q.java1.8.out
deleted file mode 100644
index eaeedcb..0000000
--- a/ql/src/test/results/clientpositive/input4.q.java1.8.out
+++ /dev/null
@@ -1,559 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@INPUT4
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@INPUT4
-PREHOOK: query: EXPLAIN
-LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-PREHOOK: type: LOAD
-POSTHOOK: query: EXPLAIN
-LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-POSTHOOK: type: LOAD
-STAGE DEPENDENCIES:
- Stage-0 is a root stage
- Stage-1 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-0
- Move Operator
- tables:
- replace: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.input4
-
- Stage: Stage-1
- Stats-Aggr Operator
-
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@input4
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@input4
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"ListSink":{}}}}}}}}}}
-PREHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-PREHOOK: type: QUERY
-PREHOOK: Input: default@input4
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@input4
-#### A masked pattern was here ####
-val_238 238
-val_86 86
-val_311 311
-val_27 27
-val_165 165
-val_409 409
-val_255 255
-val_278 278
-val_98 98
-val_484 484
-val_265 265
-val_193 193
-val_401 401
-val_150 150
-val_273 273
-val_224 224
-val_369 369
-val_66 66
-val_128 128
-val_213 213
-val_146 146
-val_406 406
-val_429 429
-val_374 374
-val_152 152
-val_469 469
-val_145 145
-val_495 495
-val_37 37
-val_327 327
-val_281 281
-val_277 277
-val_209 209
-val_15 15
-val_82 82
-val_403 403
-val_166 166
-val_417 417
-val_430 430
-val_252 252
-val_292 292
-val_219 219
-val_287 287
-val_153 153
-val_193 193
-val_338 338
-val_446 446
-val_459 459
-val_394 394
-val_237 237
-val_482 482
-val_174 174
-val_413 413
-val_494 494
-val_207 207
-val_199 199
-val_466 466
-val_208 208
-val_174 174
-val_399 399
-val_396 396
-val_247 247
-val_417 417
-val_489 489
-val_162 162
-val_377 377
-val_397 397
-val_309 309
-val_365 365
-val_266 266
-val_439 439
-val_342 342
-val_367 367
-val_325 325
-val_167 167
-val_195 195
-val_475 475
-val_17 17
-val_113 113
-val_155 155
-val_203 203
-val_339 339
-val_0 0
-val_455 455
-val_128 128
-val_311 311
-val_316 316
-val_57 57
-val_302 302
-val_205 205
-val_149 149
-val_438 438
-val_345 345
-val_129 129
-val_170 170
-val_20 20
-val_489 489
-val_157 157
-val_378 378
-val_221 221
-val_92 92
-val_111 111
-val_47 47
-val_72 72
-val_4 4
-val_280 280
-val_35 35
-val_427 427
-val_277 277
-val_208 208
-val_356 356
-val_399 399
-val_169 169
-val_382 382
-val_498 498
-val_125 125
-val_386 386
-val_437 437
-val_469 469
-val_192 192
-val_286 286
-val_187 187
-val_176 176
-val_54 54
-val_459 459
-val_51 51
-val_138 138
-val_103 103
-val_239 239
-val_213 213
-val_216 216
-val_430 430
-val_278 278
-val_176 176
-val_289 289
-val_221 221
-val_65 65
-val_318 318
-val_332 332
-val_311 311
-val_275 275
-val_137 137
-val_241 241
-val_83 83
-val_333 333
-val_180 180
-val_284 284
-val_12 12
-val_230 230
-val_181 181
-val_67 67
-val_260 260
-val_404 404
-val_384 384
-val_489 489
-val_353 353
-val_373 373
-val_272 272
-val_138 138
-val_217 217
-val_84 84
-val_348 348
-val_466 466
-val_58 58
-val_8 8
-val_411 411
-val_230 230
-val_208 208
-val_348 348
-val_24 24
-val_463 463
-val_431 431
-val_179 179
-val_172 172
-val_42 42
-val_129 129
-val_158 158
-val_119 119
-val_496 496
-val_0 0
-val_322 322
-val_197 197
-val_468 468
-val_393 393
-val_454 454
-val_100 100
-val_298 298
-val_199 199
-val_191 191
-val_418 418
-val_96 96
-val_26 26
-val_165 165
-val_327 327
-val_230 230
-val_205 205
-val_120 120
-val_131 131
-val_51 51
-val_404 404
-val_43 43
-val_436 436
-val_156 156
-val_469 469
-val_468 468
-val_308 308
-val_95 95
-val_196 196
-val_288 288
-val_481 481
-val_457 457
-val_98 98
-val_282 282
-val_197 197
-val_187 187
-val_318 318
-val_318 318
-val_409 409
-val_470 470
-val_137 137
-val_369 369
-val_316 316
-val_169 169
-val_413 413
-val_85 85
-val_77 77
-val_0 0
-val_490 490
-val_87 87
-val_364 364
-val_179 179
-val_118 118
-val_134 134
-val_395 395
-val_282 282
-val_138 138
-val_238 238
-val_419 419
-val_15 15
-val_118 118
-val_72 72
-val_90 90
-val_307 307
-val_19 19
-val_435 435
-val_10 10
-val_277 277
-val_273 273
-val_306 306
-val_224 224
-val_309 309
-val_389 389
-val_327 327
-val_242 242
-val_369 369
-val_392 392
-val_272 272
-val_331 331
-val_401 401
-val_242 242
-val_452 452
-val_177 177
-val_226 226
-val_5 5
-val_497 497
-val_402 402
-val_396 396
-val_317 317
-val_395 395
-val_58 58
-val_35 35
-val_336 336
-val_95 95
-val_11 11
-val_168 168
-val_34 34
-val_229 229
-val_233 233
-val_143 143
-val_472 472
-val_322 322
-val_498 498
-val_160 160
-val_195 195
-val_42 42
-val_321 321
-val_430 430
-val_119 119
-val_489 489
-val_458 458
-val_78 78
-val_76 76
-val_41 41
-val_223 223
-val_492 492
-val_149 149
-val_449 449
-val_218 218
-val_228 228
-val_138 138
-val_453 453
-val_30 30
-val_209 209
-val_64 64
-val_468 468
-val_76 76
-val_74 74
-val_342 342
-val_69 69
-val_230 230
-val_33 33
-val_368 368
-val_103 103
-val_296 296
-val_113 113
-val_216 216
-val_367 367
-val_344 344
-val_167 167
-val_274 274
-val_219 219
-val_239 239
-val_485 485
-val_116 116
-val_223 223
-val_256 256
-val_263 263
-val_70 70
-val_487 487
-val_480 480
-val_401 401
-val_288 288
-val_191 191
-val_5 5
-val_244 244
-val_438 438
-val_128 128
-val_467 467
-val_432 432
-val_202 202
-val_316 316
-val_229 229
-val_469 469
-val_463 463
-val_280 280
-val_2 2
-val_35 35
-val_283 283
-val_331 331
-val_235 235
-val_80 80
-val_44 44
-val_193 193
-val_321 321
-val_335 335
-val_104 104
-val_466 466
-val_366 366
-val_175 175
-val_403 403
-val_483 483
-val_53 53
-val_105 105
-val_257 257
-val_406 406
-val_409 409
-val_190 190
-val_406 406
-val_401 401
-val_114 114
-val_258 258
-val_90 90
-val_203 203
-val_262 262
-val_348 348
-val_424 424
-val_12 12
-val_396 396
-val_201 201
-val_217 217
-val_164 164
-val_431 431
-val_454 454
-val_478 478
-val_298 298
-val_125 125
-val_431 431
-val_164 164
-val_424 424
-val_187 187
-val_382 382
-val_5 5
-val_70 70
-val_397 397
-val_480 480
-val_291 291
-val_24 24
-val_351 351
-val_255 255
-val_104 104
-val_70 70
-val_163 163
-val_438 438
-val_119 119
-val_414 414
-val_200 200
-val_491 491
-val_237 237
-val_439 439
-val_360 360
-val_248 248
-val_479 479
-val_305 305
-val_417 417
-val_199 199
-val_444 444
-val_120 120
-val_429 429
-val_169 169
-val_443 443
-val_323 323
-val_325 325
-val_277 277
-val_230 230
-val_478 478
-val_178 178
-val_468 468
-val_310 310
-val_317 317
-val_333 333
-val_493 493
-val_460 460
-val_207 207
-val_249 249
-val_265 265
-val_480 480
-val_83 83
-val_136 136
-val_353 353
-val_172 172
-val_214 214
-val_462 462
-val_233 233
-val_406 406
-val_133 133
-val_175 175
-val_189 189
-val_454 454
-val_375 375
-val_401 401
-val_421 421
-val_407 407
-val_384 384
-val_256 256
-val_26 26
-val_134 134
-val_67 67
-val_384 384
-val_379 379
-val_18 18
-val_462 462
-val_492 492
-val_100 100
-val_298 298
-val_9 9
-val_341 341
-val_498 498
-val_146 146
-val_458 458
-val_362 362
-val_186 186
-val_285 285
-val_348 348
-val_167 167
-val_18 18
-val_273 273
-val_183 183
-val_281 281
-val_344 344
-val_97 97
-val_469 469
-val_315 315
-val_84 84
-val_28 28
-val_37 37
-val_448 448
-val_152 152
-val_348 348
-val_307 307
-val_194 194
-val_414 414
-val_477 477
-val_222 222
-val_126 126
-val_90 90
-val_169 169
-val_403 403
-val_400 400
-val_200 200
-val_97 97
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/input4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input4.q.out b/ql/src/test/results/clientpositive/input4.q.out
new file mode 100644
index 0000000..83912f6
--- /dev/null
+++ b/ql/src/test/results/clientpositive/input4.q.out
@@ -0,0 +1,555 @@
+PREHOOK: query: CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@INPUT4
+POSTHOOK: query: CREATE TABLE INPUT4(KEY STRING, VALUE STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@INPUT4
+PREHOOK: query: EXPLAIN
+LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
+PREHOOK: type: LOAD
+POSTHOOK: query: EXPLAIN
+LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
+POSTHOOK: type: LOAD
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+ Stage-1 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.input4
+
+ Stage: Stage-1
+ Stats-Aggr Operator
+
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@input4
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/kv1.txt' INTO TABLE INPUT4
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@input4
+PREHOOK: query: EXPLAIN FORMATTED
+SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN FORMATTED
+SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
+POSTHOOK: type: QUERY
+{"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"TableScan":{"alias:":"input4alias","Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"value (type: string), key (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE","children":{"ListSink":{}}}}}}}}}}
+PREHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
+PREHOOK: type: QUERY
+PREHOOK: Input: default@input4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT Input4Alias.VALUE, Input4Alias.KEY FROM INPUT4 AS Input4Alias
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@input4
+#### A masked pattern was here ####
+val_238 238
+val_86 86
+val_311 311
+val_27 27
+val_165 165
+val_409 409
+val_255 255
+val_278 278
+val_98 98
+val_484 484
+val_265 265
+val_193 193
+val_401 401
+val_150 150
+val_273 273
+val_224 224
+val_369 369
+val_66 66
+val_128 128
+val_213 213
+val_146 146
+val_406 406
+val_429 429
+val_374 374
+val_152 152
+val_469 469
+val_145 145
+val_495 495
+val_37 37
+val_327 327
+val_281 281
+val_277 277
+val_209 209
+val_15 15
+val_82 82
+val_403 403
+val_166 166
+val_417 417
+val_430 430
+val_252 252
+val_292 292
+val_219 219
+val_287 287
+val_153 153
+val_193 193
+val_338 338
+val_446 446
+val_459 459
+val_394 394
+val_237 237
+val_482 482
+val_174 174
+val_413 413
+val_494 494
+val_207 207
+val_199 199
+val_466 466
+val_208 208
+val_174 174
+val_399 399
+val_396 396
+val_247 247
+val_417 417
+val_489 489
+val_162 162
+val_377 377
+val_397 397
+val_309 309
+val_365 365
+val_266 266
+val_439 439
+val_342 342
+val_367 367
+val_325 325
+val_167 167
+val_195 195
+val_475 475
+val_17 17
+val_113 113
+val_155 155
+val_203 203
+val_339 339
+val_0 0
+val_455 455
+val_128 128
+val_311 311
+val_316 316
+val_57 57
+val_302 302
+val_205 205
+val_149 149
+val_438 438
+val_345 345
+val_129 129
+val_170 170
+val_20 20
+val_489 489
+val_157 157
+val_378 378
+val_221 221
+val_92 92
+val_111 111
+val_47 47
+val_72 72
+val_4 4
+val_280 280
+val_35 35
+val_427 427
+val_277 277
+val_208 208
+val_356 356
+val_399 399
+val_169 169
+val_382 382
+val_498 498
+val_125 125
+val_386 386
+val_437 437
+val_469 469
+val_192 192
+val_286 286
+val_187 187
+val_176 176
+val_54 54
+val_459 459
+val_51 51
+val_138 138
+val_103 103
+val_239 239
+val_213 213
+val_216 216
+val_430 430
+val_278 278
+val_176 176
+val_289 289
+val_221 221
+val_65 65
+val_318 318
+val_332 332
+val_311 311
+val_275 275
+val_137 137
+val_241 241
+val_83 83
+val_333 333
+val_180 180
+val_284 284
+val_12 12
+val_230 230
+val_181 181
+val_67 67
+val_260 260
+val_404 404
+val_384 384
+val_489 489
+val_353 353
+val_373 373
+val_272 272
+val_138 138
+val_217 217
+val_84 84
+val_348 348
+val_466 466
+val_58 58
+val_8 8
+val_411 411
+val_230 230
+val_208 208
+val_348 348
+val_24 24
+val_463 463
+val_431 431
+val_179 179
+val_172 172
+val_42 42
+val_129 129
+val_158 158
+val_119 119
+val_496 496
+val_0 0
+val_322 322
+val_197 197
+val_468 468
+val_393 393
+val_454 454
+val_100 100
+val_298 298
+val_199 199
+val_191 191
+val_418 418
+val_96 96
+val_26 26
+val_165 165
+val_327 327
+val_230 230
+val_205 205
+val_120 120
+val_131 131
+val_51 51
+val_404 404
+val_43 43
+val_436 436
+val_156 156
+val_469 469
+val_468 468
+val_308 308
+val_95 95
+val_196 196
+val_288 288
+val_481 481
+val_457 457
+val_98 98
+val_282 282
+val_197 197
+val_187 187
+val_318 318
+val_318 318
+val_409 409
+val_470 470
+val_137 137
+val_369 369
+val_316 316
+val_169 169
+val_413 413
+val_85 85
+val_77 77
+val_0 0
+val_490 490
+val_87 87
+val_364 364
+val_179 179
+val_118 118
+val_134 134
+val_395 395
+val_282 282
+val_138 138
+val_238 238
+val_419 419
+val_15 15
+val_118 118
+val_72 72
+val_90 90
+val_307 307
+val_19 19
+val_435 435
+val_10 10
+val_277 277
+val_273 273
+val_306 306
+val_224 224
+val_309 309
+val_389 389
+val_327 327
+val_242 242
+val_369 369
+val_392 392
+val_272 272
+val_331 331
+val_401 401
+val_242 242
+val_452 452
+val_177 177
+val_226 226
+val_5 5
+val_497 497
+val_402 402
+val_396 396
+val_317 317
+val_395 395
+val_58 58
+val_35 35
+val_336 336
+val_95 95
+val_11 11
+val_168 168
+val_34 34
+val_229 229
+val_233 233
+val_143 143
+val_472 472
+val_322 322
+val_498 498
+val_160 160
+val_195 195
+val_42 42
+val_321 321
+val_430 430
+val_119 119
+val_489 489
+val_458 458
+val_78 78
+val_76 76
+val_41 41
+val_223 223
+val_492 492
+val_149 149
+val_449 449
+val_218 218
+val_228 228
+val_138 138
+val_453 453
+val_30 30
+val_209 209
+val_64 64
+val_468 468
+val_76 76
+val_74 74
+val_342 342
+val_69 69
+val_230 230
+val_33 33
+val_368 368
+val_103 103
+val_296 296
+val_113 113
+val_216 216
+val_367 367
+val_344 344
+val_167 167
+val_274 274
+val_219 219
+val_239 239
+val_485 485
+val_116 116
+val_223 223
+val_256 256
+val_263 263
+val_70 70
+val_487 487
+val_480 480
+val_401 401
+val_288 288
+val_191 191
+val_5 5
+val_244 244
+val_438 438
+val_128 128
+val_467 467
+val_432 432
+val_202 202
+val_316 316
+val_229 229
+val_469 469
+val_463 463
+val_280 280
+val_2 2
+val_35 35
+val_283 283
+val_331 331
+val_235 235
+val_80 80
+val_44 44
+val_193 193
+val_321 321
+val_335 335
+val_104 104
+val_466 466
+val_366 366
+val_175 175
+val_403 403
+val_483 483
+val_53 53
+val_105 105
+val_257 257
+val_406 406
+val_409 409
+val_190 190
+val_406 406
+val_401 401
+val_114 114
+val_258 258
+val_90 90
+val_203 203
+val_262 262
+val_348 348
+val_424 424
+val_12 12
+val_396 396
+val_201 201
+val_217 217
+val_164 164
+val_431 431
+val_454 454
+val_478 478
+val_298 298
+val_125 125
+val_431 431
+val_164 164
+val_424 424
+val_187 187
+val_382 382
+val_5 5
+val_70 70
+val_397 397
+val_480 480
+val_291 291
+val_24 24
+val_351 351
+val_255 255
+val_104 104
+val_70 70
+val_163 163
+val_438 438
+val_119 119
+val_414 414
+val_200 200
+val_491 491
+val_237 237
+val_439 439
+val_360 360
+val_248 248
+val_479 479
+val_305 305
+val_417 417
+val_199 199
+val_444 444
+val_120 120
+val_429 429
+val_169 169
+val_443 443
+val_323 323
+val_325 325
+val_277 277
+val_230 230
+val_478 478
+val_178 178
+val_468 468
+val_310 310
+val_317 317
+val_333 333
+val_493 493
+val_460 460
+val_207 207
+val_249 249
+val_265 265
+val_480 480
+val_83 83
+val_136 136
+val_353 353
+val_172 172
+val_214 214
+val_462 462
+val_233 233
+val_406 406
+val_133 133
+val_175 175
+val_189 189
+val_454 454
+val_375 375
+val_401 401
+val_421 421
+val_407 407
+val_384 384
+val_256 256
+val_26 26
+val_134 134
+val_67 67
+val_384 384
+val_379 379
+val_18 18
+val_462 462
+val_492 492
+val_100 100
+val_298 298
+val_9 9
+val_341 341
+val_498 498
+val_146 146
+val_458 458
+val_362 362
+val_186 186
+val_285 285
+val_348 348
+val_167 167
+val_18 18
+val_273 273
+val_183 183
+val_281 281
+val_344 344
+val_97 97
+val_469 469
+val_315 315
+val_84 84
+val_28 28
+val_37 37
+val_448 448
+val_152 152
+val_348 348
+val_307 307
+val_194 194
+val_414 414
+val_477 477
+val_222 222
+val_126 126
+val_90 90
+val_169 169
+val_403 403
+val_400 400
+val_200 200
+val_97 97
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/join0.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join0.q.java1.7.out b/ql/src/test/results/clientpositive/join0.q.java1.7.out
deleted file mode 100644
index 343f8a4..0000000
--- a/ql/src/test/results/clientpositive/join0.q.java1.7.out
+++ /dev/null
@@ -1,240 +0,0 @@
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}},{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COM
PLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","outp
ut format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"}}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoo
p.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/join0.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join0.q.java1.8.out b/ql/src/test/results/clientpositive/join0.q.java1.8.out
deleted file mode 100644
index 343f8a4..0000000
--- a/ql/src/test/results/clientpositive/join0.q.java1.8.out
+++ /dev/null
@@ -1,240 +0,0 @@
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
--- SORT_QUERY_RESULTS
-
-EXPLAIN
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 10) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string)
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: ++++
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN FORMATTED
-SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-{"STAGE DEPENDENCIES":{"Stage-1":{"ROOT STAGE":"TRUE"},"Stage-2":{"DEPENDENT STAGES":"Stage-1"},"Stage-0":{"DEPENDENT STAGES":"Stage-2"}},"STAGE PLANS":{"Stage-1":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}},{"TableScan":{"alias:":"src","Statistics:":"Num rows: 500 Data size: 5312 Basic stats: COM
PLETE Column stats: NONE","children":{"Filter Operator":{"predicate:":"(key < 10) (type: boolean)","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Select Operator":{"expressions:":"key (type: string), value (type: string)","outputColumnNames:":["_col0","_col1"],"Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","children":{"Reduce Output Operator":{"sort order:":"","Statistics:":"Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE","value expressions:":"_col0 (type: string), _col1 (type: string)"}}}}}}}}],"Reduce Operator Tree:":{"Join Operator":{"condition map:":[{"":"Inner Join 0 to 1"}],"keys:":{},"outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","table:":{"input format:":"org.apache.hadoop.mapred.SequenceFileInputFormat","outp
ut format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe"}}}}}}},"Stage-2":{"Map Reduce":{"Map Operator Tree:":[{"TableScan":{"children":{"Reduce Output Operator":{"key expressions:":"_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)","sort order:":"++++","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE"}}}}],"Reduce Operator Tree:":{"Select Operator":{"expressions:":"KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)","outputColumnNames:":["_col0","_col1","_col2","_col3"],"Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","children":{"File Output Operator":{"compressed:":"false","Statistics:":"Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE","table:":{"input format:":"org.apache.hadoo
p.mapred.SequenceFileInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"}}}}}}},"Stage-0":{"Fetch Operator":{"limit:":"-1","Processor Tree:":{"ListSink":{}}}}}}
-Warning: Shuffle Join JOIN[8][tables = [src1, src2]] in Stage 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT src1.key as k1, src1.value as v1,
- src2.key as k2, src2.value as v2 FROM
- (SELECT * FROM src WHERE src.key < 10) src1
- JOIN
- (SELECT * FROM src WHERE src.key < 10) src2
- SORT BY k1, v1, k2, v2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-#### A masked pattern was here ####
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 0 val_0
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 2 val_2
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 4 val_4
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 5 val_5
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 8 val_8
-0 val_0 9 val_9
-0 val_0 9 val_9
-0 val_0 9 val_9
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 0 val_0
-2 val_2 2 val_2
-2 val_2 4 val_4
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 5 val_5
-2 val_2 8 val_8
-2 val_2 9 val_9
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 0 val_0
-4 val_4 2 val_2
-4 val_4 4 val_4
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 5 val_5
-4 val_4 8 val_8
-4 val_4 9 val_9
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 0 val_0
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 2 val_2
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 4 val_4
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 5 val_5
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 8 val_8
-5 val_5 9 val_9
-5 val_5 9 val_9
-5 val_5 9 val_9
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 0 val_0
-8 val_8 2 val_2
-8 val_8 4 val_4
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 5 val_5
-8 val_8 8 val_8
-8 val_8 9 val_9
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 0 val_0
-9 val_9 2 val_2
-9 val_9 4 val_4
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 5 val_5
-9 val_9 8 val_8
-9 val_9 9 val_9
[11/48] hive git commit: HIVE-13826: Make VectorUDFAdaptor work for
GenericUDFBetween when used as FILTER (Matt McCline,
reviewed by Ashutosh Chauhan)
Posted by sp...@apache.org.
HIVE-13826: Make VectorUDFAdaptor work for GenericUDFBetween when used as FILTER (Matt McCline, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/71725869
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/71725869
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/71725869
Branch: refs/heads/java8
Commit: 7172586966739de0ba1659bf9abcea40d109b341
Parents: 9bebaf6
Author: Matt McCline <mm...@hortonworks.com>
Authored: Thu May 26 08:25:29 2016 -0700
Committer: Matt McCline <mm...@hortonworks.com>
Committed: Thu May 26 08:25:29 2016 -0700
----------------------------------------------------------------------
.../ql/exec/vector/VectorizationContext.java | 22 +++-
.../clientpositive/vector_between_columns.q | 8 +-
.../tez/vector_between_columns.q.out | 116 +++++++++++++++++-
.../clientpositive/vector_between_columns.q.out | 117 ++++++++++++++++++-
4 files changed, 250 insertions(+), 13 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/71725869/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java
index 886e222..a76e31d 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/VectorizationContext.java
@@ -1965,8 +1965,17 @@ public class VectorizationContext {
private VectorExpression getCustomUDFExpression(ExprNodeGenericFuncDesc expr, Mode mode)
throws HiveException {
- if (mode != Mode.PROJECTION) {
- return null;
+ boolean isFilter = false; // Assume.
+ if (mode == Mode.FILTER) {
+
+ // Is output type a BOOLEAN?
+ TypeInfo resultTypeInfo = expr.getTypeInfo();
+ if (resultTypeInfo.getCategory() == Category.PRIMITIVE &&
+ ((PrimitiveTypeInfo) resultTypeInfo).getPrimitiveCategory() == PrimitiveCategory.BOOLEAN) {
+ isFilter = true;
+ } else {
+ return null;
+ }
}
//GenericUDFBridge udfBridge = (GenericUDFBridge) expr.getGenericUDF();
@@ -2032,7 +2041,14 @@ public class VectorizationContext {
for (Integer i : exprResultColumnNums) {
ocm.freeOutputColumn(i);
}
- return ve;
+
+ if (isFilter) {
+ SelectColumnIsTrue filterVectorExpr = new SelectColumnIsTrue(outputCol);
+ filterVectorExpr.setChildExpressions(new VectorExpression[] {ve});
+ return filterVectorExpr;
+ } else {
+ return ve;
+ }
}
public static boolean isStringFamily(String resultType) {
http://git-wip-us.apache.org/repos/asf/hive/blob/71725869/ql/src/test/queries/clientpositive/vector_between_columns.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/vector_between_columns.q b/ql/src/test/queries/clientpositive/vector_between_columns.q
index ba38445..41f9243 100644
--- a/ql/src/test/queries/clientpositive/vector_between_columns.q
+++ b/ql/src/test/queries/clientpositive/vector_between_columns.q
@@ -7,8 +7,7 @@ set hive.mapred.mode=nonstrict;
-- SORT_QUERY_RESULTS
--
--- The following WILL NOT BE ABLE TO USE the VectorUDFAdaptor to GenericUDFBetween
--- because the mode = FILTER is not supported yet.
+-- Verify the VectorUDFAdaptor to GenericUDFBetween works for PROJECTION and FILTER.
--
create table if not exists TSINT_txt ( RNUM int , CSINT smallint )
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n';
@@ -25,6 +24,11 @@ create table TSINT stored as orc AS SELECT * FROM TSINT_txt;
create table TINT stored as orc AS SELECT * FROM TINT_txt;
+explain
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint;
+
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint;
+
explain
select tint.rnum, tsint.rnum, tint.cint, tsint.csint from tint , tsint where tint.cint between tsint.csint and tsint.csint;
http://git-wip-us.apache.org/repos/asf/hive/blob/71725869/ql/src/test/results/clientpositive/tez/vector_between_columns.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vector_between_columns.q.out b/ql/src/test/results/clientpositive/tez/vector_between_columns.q.out
index 8a9978b..939aab5 100644
--- a/ql/src/test/results/clientpositive/tez/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/tez/vector_between_columns.q.out
@@ -1,7 +1,6 @@
PREHOOK: query: -- SORT_QUERY_RESULTS
--
--- The following WILL NOT BE ABLE TO USE the VectorUDFAdaptor to GenericUDFBetween
--- because the mode = FILTER is not supported yet.
+-- Verify the VectorUDFAdaptor to GenericUDFBetween works for PROJECTION and FILTER.
--
create table if not exists TSINT_txt ( RNUM int , CSINT smallint )
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n'
@@ -10,8 +9,7 @@ PREHOOK: Output: database:default
PREHOOK: Output: default@TSINT_txt
POSTHOOK: query: -- SORT_QUERY_RESULTS
--
--- The following WILL NOT BE ABLE TO USE the VectorUDFAdaptor to GenericUDFBetween
--- because the mode = FILTER is not supported yet.
+-- Verify the VectorUDFAdaptor to GenericUDFBetween works for PROJECTION and FILTER.
--
create table if not exists TSINT_txt ( RNUM int , CSINT smallint )
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n'
@@ -70,6 +68,115 @@ POSTHOOK: Output: default@TINT
POSTHOOK: Lineage: tint.cint SIMPLE [(tint_txt)tint_txt.FieldSchema(name:cint, type:int, comment:null), ]
POSTHOOK: Lineage: tint.rnum SIMPLE [(tint_txt)tint_txt.FieldSchema(name:rnum, type:int, comment:null), ]
tint_txt.rnum tint_txt.cint
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product
+PREHOOK: query: explain
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+POSTHOOK: type: QUERY
+Explain
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: tint
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: rnum (type: int), cint (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col3 AND _col3) THEN ('Ok') ELSE ('NoOk') END (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: tsint
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: rnum (type: int), csint (type: smallint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: smallint)
+ Execution mode: vectorized
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product
+PREHOOK: query: select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tint
+PREHOOK: Input: default@tsint
+#### A masked pattern was here ####
+POSTHOOK: query: select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tint
+POSTHOOK: Input: default@tsint
+#### A masked pattern was here ####
+tint.rnum tsint.rnum tint.cint tsint.csint between_col
+0 0 NULL NULL NoOk
+0 1 NULL -1 NoOk
+0 2 NULL 0 NoOk
+0 3 NULL 1 NoOk
+0 4 NULL 10 NoOk
+1 0 -1 NULL NoOk
+1 1 -1 -1 Ok
+1 2 -1 0 NoOk
+1 3 -1 1 NoOk
+1 4 -1 10 NoOk
+2 0 0 NULL NoOk
+2 1 0 -1 NoOk
+2 2 0 0 Ok
+2 3 0 1 NoOk
+2 4 0 10 NoOk
+3 0 1 NULL NoOk
+3 1 1 -1 NoOk
+3 2 1 0 NoOk
+3 3 1 1 Ok
+3 4 1 10 NoOk
+4 0 10 NULL NoOk
+4 1 10 -1 NoOk
+4 2 10 0 NoOk
+4 3 10 1 NoOk
+4 4 10 10 Ok
Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Map 1' is a cross product
PREHOOK: query: explain
select tint.rnum, tsint.rnum, tint.cint, tsint.csint from tint , tsint where tint.cint between tsint.csint and tsint.csint
@@ -123,6 +230,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
Map 2
Map Operator Tree:
TableScan
http://git-wip-us.apache.org/repos/asf/hive/blob/71725869/ql/src/test/results/clientpositive/vector_between_columns.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_between_columns.q.out b/ql/src/test/results/clientpositive/vector_between_columns.q.out
index 5143074..a1bd6c6 100644
--- a/ql/src/test/results/clientpositive/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/vector_between_columns.q.out
@@ -1,7 +1,6 @@
PREHOOK: query: -- SORT_QUERY_RESULTS
--
--- The following WILL NOT BE ABLE TO USE the VectorUDFAdaptor to GenericUDFBetween
--- because the mode = FILTER is not supported yet.
+-- Verify the VectorUDFAdaptor to GenericUDFBetween works for PROJECTION and FILTER.
--
create table if not exists TSINT_txt ( RNUM int , CSINT smallint )
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n'
@@ -10,8 +9,7 @@ PREHOOK: Output: database:default
PREHOOK: Output: default@TSINT_txt
POSTHOOK: query: -- SORT_QUERY_RESULTS
--
--- The following WILL NOT BE ABLE TO USE the VectorUDFAdaptor to GenericUDFBetween
--- because the mode = FILTER is not supported yet.
+-- Verify the VectorUDFAdaptor to GenericUDFBetween works for PROJECTION and FILTER.
--
create table if not exists TSINT_txt ( RNUM int , CSINT smallint )
ROW FORMAT DELIMITED FIELDS TERMINATED BY '|' LINES TERMINATED BY '\n'
@@ -70,6 +68,116 @@ POSTHOOK: Output: default@TINT
POSTHOOK: Lineage: tint.cint SIMPLE [(tint_txt)tint_txt.FieldSchema(name:cint, type:int, comment:null), ]
POSTHOOK: Lineage: tint.rnum SIMPLE [(tint_txt)tint_txt.FieldSchema(name:rnum, type:int, comment:null), ]
tint_txt.rnum tint_txt.cint
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product
+PREHOOK: query: explain
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+POSTHOOK: type: QUERY
+Explain
+STAGE DEPENDENCIES:
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-4
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0:tint
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_0:tint
+ TableScan
+ alias: tint
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: rnum (type: int), cint (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: tsint
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: rnum (type: int), csint (type: smallint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col3 AND _col3) THEN ('Ok') ELSE ('NoOk') END (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 39 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product
+PREHOOK: query: select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tint
+PREHOOK: Input: default@tsint
+#### A masked pattern was here ####
+POSTHOOK: query: select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col from tint , tsint
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tint
+POSTHOOK: Input: default@tsint
+#### A masked pattern was here ####
+tint.rnum tsint.rnum tint.cint tsint.csint between_col
+0 0 NULL NULL NoOk
+0 1 NULL -1 NoOk
+0 2 NULL 0 NoOk
+0 3 NULL 1 NoOk
+0 4 NULL 10 NoOk
+1 0 -1 NULL NoOk
+1 1 -1 -1 Ok
+1 2 -1 0 NoOk
+1 3 -1 1 NoOk
+1 4 -1 10 NoOk
+2 0 0 NULL NoOk
+2 1 0 -1 NoOk
+2 2 0 0 Ok
+2 3 0 1 NoOk
+2 4 0 10 NoOk
+3 0 1 NULL NoOk
+3 1 1 -1 NoOk
+3 2 1 0 NoOk
+3 3 1 1 Ok
+3 4 1 10 NoOk
+4 0 10 NULL NoOk
+4 1 10 -1 NoOk
+4 2 10 0 NoOk
+4 3 10 1 NoOk
+4 4 10 10 Ok
Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-3:MAPRED' is a cross product
PREHOOK: query: explain
select tint.rnum, tsint.rnum, tint.cint, tsint.csint from tint , tsint where tint.cint between tsint.csint and tsint.csint
@@ -136,6 +244,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized
Local Work:
Map Reduce Local Work
[47/48] hive git commit: HIVE-13409: Fix JDK8 test failures related
to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
HIVE-13409: Fix JDK8 test failures related to COLUMN_STATS_ACCURATE (Mohit Sabharwal, reviewed by Sergio Pena)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/4ca8a63b
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/4ca8a63b
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/4ca8a63b
Branch: refs/heads/java8
Commit: 4ca8a63b2eb3707bbc8529d8039be2ff358ca764
Parents: 9349b8e
Author: Mohit Sabharwal <mo...@cloudera.com>
Authored: Tue May 24 09:30:32 2016 -0500
Committer: Sergio Pena <se...@cloudera.com>
Committed: Fri May 27 10:36:29 2016 -0500
----------------------------------------------------------------------
.../test/results/clientpositive/bucket1.q.out | 4 +-
.../test/results/clientpositive/bucket2.q.out | 4 +-
.../test/results/clientpositive/bucket3.q.out | 4 +-
.../test/results/clientpositive/bucket4.q.out | 4 +-
.../test/results/clientpositive/bucket5.q.out | 4 +-
.../results/clientpositive/bucket_many.q.out | 4 +-
.../columnStatsUpdateForStatsOptimizer_1.q.out | 8 +--
.../columnStatsUpdateForStatsOptimizer_2.q.out | 2 +-
.../constantPropagateForSubQuery.q.out | 8 +--
ql/src/test/results/clientpositive/ctas.q.out | 4 +-
.../results/clientpositive/describe_table.q.out | 4 +-
.../disable_merge_for_bucketing.q.out | 4 +-
.../extrapolate_part_stats_full.q.out | 24 ++++-----
.../extrapolate_part_stats_partial.q.out | 32 +++++------
.../extrapolate_part_stats_partial_ndv.q.out | 16 +++---
.../clientpositive/fouter_join_ppr.q.out | 40 +++++++-------
.../clientpositive/groupby_map_ppr.q.out | 4 +-
.../groupby_map_ppr_multi_distinct.q.out | 4 +-
.../results/clientpositive/groupby_ppr.q.out | 4 +-
.../groupby_ppr_multi_distinct.q.out | 4 +-
.../test/results/clientpositive/input23.q.out | 2 +-
.../test/results/clientpositive/input42.q.out | 12 ++---
.../results/clientpositive/input_part1.q.out | 2 +-
.../results/clientpositive/input_part2.q.out | 4 +-
.../results/clientpositive/input_part7.q.out | 4 +-
.../results/clientpositive/input_part9.q.out | 4 +-
ql/src/test/results/clientpositive/join17.q.out | 4 +-
ql/src/test/results/clientpositive/join26.q.out | 2 +-
ql/src/test/results/clientpositive/join32.q.out | 10 ++--
.../clientpositive/join32_lessSize.q.out | 46 ++++++++--------
ql/src/test/results/clientpositive/join33.q.out | 10 ++--
ql/src/test/results/clientpositive/join34.q.out | 8 +--
ql/src/test/results/clientpositive/join35.q.out | 12 ++---
ql/src/test/results/clientpositive/join9.q.out | 6 +--
.../results/clientpositive/join_map_ppr.q.out | 4 +-
.../clientpositive/list_bucket_dml_1.q.out | 4 +-
.../clientpositive/list_bucket_dml_14.q.out | 4 +-
.../clientpositive/list_bucket_dml_3.q.out | 4 +-
.../clientpositive/list_bucket_dml_7.q.out | 8 +--
.../results/clientpositive/load_dyn_part8.q.out | 8 +--
.../clientpositive/louter_join_ppr.q.out | 36 ++++++-------
.../clientpositive/mapjoin_mapjoin.q.out | 16 +++---
.../offset_limit_global_optimizer.q.out | 52 +++++++++---------
.../clientpositive/optimize_nullscan.q.out | 56 ++++++++++----------
.../partition_coltype_literals.q.out | 4 +-
ql/src/test/results/clientpositive/pcr.q.out | 10 ++--
ql/src/test/results/clientpositive/pcs.q.out | 38 ++++++-------
.../clientpositive/ppd_join_filter.q.out | 32 +++++------
ql/src/test/results/clientpositive/ppd_vc.q.out | 20 +++----
.../clientpositive/ppr_allchildsarenull.q.out | 12 ++---
.../clientpositive/rand_partitionpruner1.q.out | 4 +-
.../clientpositive/rand_partitionpruner2.q.out | 4 +-
.../clientpositive/rand_partitionpruner3.q.out | 4 +-
.../clientpositive/reduce_deduplicate.q.out | 4 +-
.../results/clientpositive/regexp_extract.q.out | 8 +--
.../clientpositive/router_join_ppr.q.out | 36 ++++++-------
.../test/results/clientpositive/sample1.q.out | 2 +-
.../test/results/clientpositive/sample2.q.out | 4 +-
.../test/results/clientpositive/sample4.q.out | 4 +-
.../test/results/clientpositive/sample5.q.out | 4 +-
.../test/results/clientpositive/sample6.q.out | 32 +++++------
.../test/results/clientpositive/sample7.q.out | 4 +-
.../test/results/clientpositive/sample8.q.out | 8 +--
.../test/results/clientpositive/sample9.q.out | 4 +-
.../clientpositive/schema_evol_stats.q.out | 8 +--
.../clientpositive/serde_user_properties.q.out | 12 ++---
.../results/clientpositive/spark/bucket2.q.out | 4 +-
.../results/clientpositive/spark/bucket3.q.out | 4 +-
.../results/clientpositive/spark/bucket4.q.out | 4 +-
.../results/clientpositive/spark/ctas.q.out | 4 +-
.../spark/disable_merge_for_bucketing.q.out | 4 +-
.../clientpositive/spark/groupby_map_ppr.q.out | 4 +-
.../spark/groupby_map_ppr_multi_distinct.q.out | 4 +-
.../clientpositive/spark/groupby_ppr.q.out | 4 +-
.../spark/groupby_ppr_multi_distinct.q.out | 4 +-
.../clientpositive/spark/input_part2.q.out | 4 +-
.../results/clientpositive/spark/join17.q.out | 8 +--
.../results/clientpositive/spark/join26.q.out | 10 ++--
.../results/clientpositive/spark/join32.q.out | 10 ++--
.../clientpositive/spark/join32_lessSize.q.out | 46 ++++++++--------
.../results/clientpositive/spark/join33.q.out | 10 ++--
.../results/clientpositive/spark/join34.q.out | 12 ++---
.../results/clientpositive/spark/join35.q.out | 12 ++---
.../results/clientpositive/spark/join9.q.out | 6 +--
.../clientpositive/spark/join_map_ppr.q.out | 12 ++---
.../clientpositive/spark/load_dyn_part8.q.out | 8 +--
.../clientpositive/spark/louter_join_ppr.q.out | 36 ++++++-------
.../clientpositive/spark/mapjoin_mapjoin.q.out | 16 +++---
.../spark/optimize_nullscan.q.out | 56 ++++++++++----------
.../test/results/clientpositive/spark/pcr.q.out | 10 ++--
.../clientpositive/spark/ppd_join_filter.q.out | 32 +++++------
.../clientpositive/spark/router_join_ppr.q.out | 36 ++++++-------
.../results/clientpositive/spark/sample1.q.out | 2 +-
.../results/clientpositive/spark/sample2.q.out | 4 +-
.../results/clientpositive/spark/sample4.q.out | 4 +-
.../results/clientpositive/spark/sample5.q.out | 4 +-
.../results/clientpositive/spark/sample6.q.out | 32 +++++------
.../results/clientpositive/spark/sample7.q.out | 4 +-
.../results/clientpositive/spark/sample8.q.out | 10 ++--
.../results/clientpositive/spark/stats0.q.out | 8 +--
.../clientpositive/spark/stats_only_null.q.out | 4 +-
.../spark/subquery_multiinsert.q.out | 4 +-
.../clientpositive/spark/transform_ppr1.q.out | 8 +--
.../clientpositive/spark/transform_ppr2.q.out | 4 +-
.../spark/vector_cast_constant.q.out | 2 +-
ql/src/test/results/clientpositive/stats0.q.out | 8 +--
.../clientpositive/stats_invalidation.q.out | 2 +-
.../clientpositive/stats_only_null.q.out | 4 +-
.../results/clientpositive/tez/bucket3.q.out | 4 +-
.../results/clientpositive/tez/bucket4.q.out | 4 +-
.../test/results/clientpositive/tez/ctas.q.out | 4 +-
.../tez/disable_merge_for_bucketing.q.out | 4 +-
.../clientpositive/tez/mapjoin_mapjoin.q.out | 16 +++---
.../clientpositive/tez/optimize_nullscan.q.out | 56 ++++++++++----------
.../results/clientpositive/tez/sample1.q.out | 2 +-
.../clientpositive/tez/schema_evol_stats.q.out | 8 +--
.../clientpositive/tez/stats_only_null.q.out | 4 +-
.../clientpositive/tez/transform_ppr1.q.out | 8 +--
.../clientpositive/tez/transform_ppr2.q.out | 4 +-
.../results/clientpositive/transform_ppr1.q.out | 8 +--
.../results/clientpositive/transform_ppr2.q.out | 4 +-
.../results/clientpositive/udf_explode.q.out | 8 +--
.../results/clientpositive/udtf_explode.q.out | 8 +--
.../test/results/clientpositive/union_ppr.q.out | 4 +-
124 files changed, 684 insertions(+), 684 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket1.q.out b/ql/src/test/results/clientpositive/bucket1.q.out
index 78fb530..92ecd67 100644
--- a/ql/src/test/results/clientpositive/bucket1.q.out
+++ b/ql/src/test/results/clientpositive/bucket1.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -72,7 +72,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket2.q.out b/ql/src/test/results/clientpositive/bucket2.q.out
index 297984e..b849ed3 100644
--- a/ql/src/test/results/clientpositive/bucket2.q.out
+++ b/ql/src/test/results/clientpositive/bucket2.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -72,7 +72,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket3.q.out b/ql/src/test/results/clientpositive/bucket3.q.out
index 29afaea..fa8b0f9 100644
--- a/ql/src/test/results/clientpositive/bucket3.q.out
+++ b/ql/src/test/results/clientpositive/bucket3.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -72,7 +72,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket4.q.out b/ql/src/test/results/clientpositive/bucket4.q.out
index 803a2bb..ec28d09 100644
--- a/ql/src/test/results/clientpositive/bucket4.q.out
+++ b/ql/src/test/results/clientpositive/bucket4.q.out
@@ -49,7 +49,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -69,7 +69,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket5.q.out b/ql/src/test/results/clientpositive/bucket5.q.out
index 2e37eef..bd1013a 100644
--- a/ql/src/test/results/clientpositive/bucket5.q.out
+++ b/ql/src/test/results/clientpositive/bucket5.q.out
@@ -94,7 +94,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -114,7 +114,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/bucket_many.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket_many.q.out b/ql/src/test/results/clientpositive/bucket_many.q.out
index 9bd90b1..87954e0 100644
--- a/ql/src/test/results/clientpositive/bucket_many.q.out
+++ b/ql/src/test/results/clientpositive/bucket_many.q.out
@@ -48,7 +48,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -68,7 +68,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_1.q.out b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_1.q.out
index d812193..00f3776 100644
--- a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_1.q.out
+++ b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_1.q.out
@@ -204,7 +204,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"year\":\"true\",\"month\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"year\":\"true\",\"month\":\"true\"}}
numFiles 1
numRows 3
rawDataSize 21
@@ -429,7 +429,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"year\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"year\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 28
@@ -552,7 +552,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"month\":\"true\",\"year\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"month\":\"true\",\"year\":\"true\"}}
numFiles 2
numRows 4
rawDataSize 28
@@ -737,7 +737,7 @@ Database: default
Table: calendarp
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"year\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"year\":\"true\"}}
numFiles 1
numRows 3
rawDataSize 12
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out
index 179bc66..48e7a40 100644
--- a/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out
+++ b/ql/src/test/results/clientpositive/columnStatsUpdateForStatsOptimizer_2.q.out
@@ -81,7 +81,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"year\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"year\":\"true\"}}
numFiles 2
numRows 3
rawDataSize 24
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out
index 2aa8d77..f90cdb6 100644
--- a/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out
+++ b/ql/src/test/results/clientpositive/constantPropagateForSubQuery.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -80,7 +80,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -104,7 +104,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -124,7 +124,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ctas.q.out b/ql/src/test/results/clientpositive/ctas.q.out
index 8d6c117..afd6d7c 100644
--- a/ql/src/test/results/clientpositive/ctas.q.out
+++ b/ql/src/test/results/clientpositive/ctas.q.out
@@ -731,7 +731,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -751,7 +751,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/describe_table.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/describe_table.q.out b/ql/src/test/results/clientpositive/describe_table.q.out
index 19664b0..ad3bfc1 100644
--- a/ql/src/test/results/clientpositive/describe_table.q.out
+++ b/ql/src/test/results/clientpositive/describe_table.q.out
@@ -230,7 +230,7 @@ Database: default
Table: srcpart
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -315,7 +315,7 @@ Database: default
Table: srcpart
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"},\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out b/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
index c9aed0d..ba7c640 100644
--- a/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
+++ b/ql/src/test/results/clientpositive/disable_merge_for_bucketing.q.out
@@ -48,7 +48,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -68,7 +68,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out
index fa2c77e..8f40040 100644
--- a/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out
+++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_full.q.out
@@ -104,7 +104,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -147,7 +147,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -217,7 +217,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -260,7 +260,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -400,7 +400,7 @@ STAGE PLANS:
year 2000
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -444,7 +444,7 @@ STAGE PLANS:
year 2001
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -488,7 +488,7 @@ STAGE PLANS:
year 2000
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -532,7 +532,7 @@ STAGE PLANS:
year 2001
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -599,7 +599,7 @@ STAGE PLANS:
year 2000
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -643,7 +643,7 @@ STAGE PLANS:
year 2001
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -687,7 +687,7 @@ STAGE PLANS:
year 2000
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -731,7 +731,7 @@ STAGE PLANS:
year 2001
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out
index 68652e9..0acfe90 100644
--- a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out
+++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial.q.out
@@ -164,7 +164,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -207,7 +207,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -363,7 +363,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -406,7 +406,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -535,7 +535,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -578,7 +578,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -621,7 +621,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -664,7 +664,7 @@ STAGE PLANS:
partition values:
year 2003
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -730,7 +730,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -773,7 +773,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -816,7 +816,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -859,7 +859,7 @@ STAGE PLANS:
partition values:
year 2003
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true"}}
bucket_count -1
columns state,locid,zip
columns.comments
@@ -1176,7 +1176,7 @@ STAGE PLANS:
year 2001
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -1396,7 +1396,7 @@ STAGE PLANS:
year 2002
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -1683,7 +1683,7 @@ STAGE PLANS:
year 2001
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
@@ -1903,7 +1903,7 @@ STAGE PLANS:
year 2002
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true"}}
bucket_count -1
columns state,locid
columns.comments
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out
index e82136f..70e4db3 100644
--- a/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out
+++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_partial_ndv.q.out
@@ -232,7 +232,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -275,7 +275,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -476,7 +476,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -519,7 +519,7 @@ STAGE PLANS:
partition values:
year 2001
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -562,7 +562,7 @@ STAGE PLANS:
partition values:
year 2002
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -605,7 +605,7 @@ STAGE PLANS:
partition values:
year 2003
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true","zip":"true"}}
bucket_count -1
columns state,locid,cnt,zip
columns.comments
@@ -993,7 +993,7 @@ STAGE PLANS:
year 2001
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true"}}
bucket_count -1
columns state,locid,cnt
columns.comments
@@ -1213,7 +1213,7 @@ STAGE PLANS:
year 2002
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"state":"true","locid":"true","cnt":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"state":"true","locid":"true","cnt":"true"}}
bucket_count -1
columns state,locid,cnt
columns.comments
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
index 45dbc36..048ab96 100644
--- a/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/fouter_join_ppr.q.out
@@ -71,7 +71,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -91,7 +91,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -118,7 +118,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -164,7 +164,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -210,7 +210,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -256,7 +256,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -458,7 +458,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -478,7 +478,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -505,7 +505,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -551,7 +551,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -597,7 +597,7 @@ STAGE PLANS:
ds 2008-04-09
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -643,7 +643,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -857,7 +857,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -877,7 +877,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -904,7 +904,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -950,7 +950,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1149,7 +1149,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1169,7 +1169,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1196,7 +1196,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1242,7 +1242,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out
index 84999f2..24bf7a6 100644
--- a/ql/src/test/results/clientpositive/groupby_map_ppr.q.out
+++ b/ql/src/test/results/clientpositive/groupby_map_ppr.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -114,7 +114,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out
index 5cf8bb1..c3cb7fb 100644
--- a/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby_map_ppr_multi_distinct.q.out
@@ -68,7 +68,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -114,7 +114,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/groupby_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_ppr.q.out b/ql/src/test/results/clientpositive/groupby_ppr.q.out
index a15b557..a4e9ff3 100644
--- a/ql/src/test/results/clientpositive/groupby_ppr.q.out
+++ b/ql/src/test/results/clientpositive/groupby_ppr.q.out
@@ -61,7 +61,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -107,7 +107,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
index 117b2cd..33d1ed0 100644
--- a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
@@ -61,7 +61,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -107,7 +107,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input23.q.out b/ql/src/test/results/clientpositive/input23.q.out
index e03c9e7..25225d7 100644
--- a/ql/src/test/results/clientpositive/input23.q.out
+++ b/ql/src/test/results/clientpositive/input23.q.out
@@ -59,7 +59,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input42.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input42.q.out b/ql/src/test/results/clientpositive/input42.q.out
index 866468d..8e91af0 100644
--- a/ql/src/test/results/clientpositive/input42.q.out
+++ b/ql/src/test/results/clientpositive/input42.q.out
@@ -23,7 +23,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -67,7 +67,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1148,7 +1148,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1192,7 +1192,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1655,7 +1655,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1699,7 +1699,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input_part1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input_part1.q.out b/ql/src/test/results/clientpositive/input_part1.q.out
index d3efb0d..16c450b 100644
--- a/ql/src/test/results/clientpositive/input_part1.q.out
+++ b/ql/src/test/results/clientpositive/input_part1.q.out
@@ -83,7 +83,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input_part2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input_part2.q.out b/ql/src/test/results/clientpositive/input_part2.q.out
index 74db456..0c069a5 100644
--- a/ql/src/test/results/clientpositive/input_part2.q.out
+++ b/ql/src/test/results/clientpositive/input_part2.q.out
@@ -143,7 +143,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -189,7 +189,7 @@ STAGE PLANS:
ds 2008-04-09
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input_part7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input_part7.q.out b/ql/src/test/results/clientpositive/input_part7.q.out
index 1429080..459e384 100644
--- a/ql/src/test/results/clientpositive/input_part7.q.out
+++ b/ql/src/test/results/clientpositive/input_part7.q.out
@@ -84,7 +84,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -130,7 +130,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/input_part9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input_part9.q.out b/ql/src/test/results/clientpositive/input_part9.q.out
index 920096e..f73d0e1 100644
--- a/ql/src/test/results/clientpositive/input_part9.q.out
+++ b/ql/src/test/results/clientpositive/input_part9.q.out
@@ -23,7 +23,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -67,7 +67,7 @@ STAGE PLANS:
ds 2008-04-08
hr 12
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join17.q.out b/ql/src/test/results/clientpositive/join17.q.out
index 2c03584..a827c67 100644
--- a/ql/src/test/results/clientpositive/join17.q.out
+++ b/ql/src/test/results/clientpositive/join17.q.out
@@ -78,7 +78,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -98,7 +98,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join26.q.out b/ql/src/test/results/clientpositive/join26.q.out
index 86e51fb..781c0e5 100644
--- a/ql/src/test/results/clientpositive/join26.q.out
+++ b/ql/src/test/results/clientpositive/join26.q.out
@@ -146,7 +146,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join32.q.out b/ql/src/test/results/clientpositive/join32.q.out
index 8653c2f..bebb007 100644
--- a/ql/src/test/results/clientpositive/join32.q.out
+++ b/ql/src/test/results/clientpositive/join32.q.out
@@ -159,7 +159,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -179,7 +179,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -203,7 +203,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -223,7 +223,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -250,7 +250,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
http://git-wip-us.apache.org/repos/asf/hive/blob/4ca8a63b/ql/src/test/results/clientpositive/join32_lessSize.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join32_lessSize.q.out b/ql/src/test/results/clientpositive/join32_lessSize.q.out
index fd7bba7..357a84f 100644
--- a/ql/src/test/results/clientpositive/join32_lessSize.q.out
+++ b/ql/src/test/results/clientpositive/join32_lessSize.q.out
@@ -121,7 +121,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -141,7 +141,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -168,7 +168,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -314,7 +314,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -334,7 +334,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -605,7 +605,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -625,7 +625,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -734,7 +734,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -754,7 +754,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -881,7 +881,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -901,7 +901,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1170,7 +1170,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1190,7 +1190,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1214,7 +1214,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1234,7 +1234,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1270,7 +1270,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1410,7 +1410,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1696,7 +1696,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1716,7 +1716,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1740,7 +1740,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1760,7 +1760,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1796,7 +1796,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
@@ -1936,7 +1936,7 @@ STAGE PLANS:
ds 2008-04-08
hr 11
properties:
- COLUMN_STATS_ACCURATE {"COLUMN_STATS":{"key":"true","value":"true"},"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
columns key,value
columns.comments 'default','default'
[41/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.7.out b/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.7.out
deleted file mode 100644
index 52b09d4..0000000
--- a/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.7.out
+++ /dev/null
@@ -1,179 +0,0 @@
-PREHOOK: query: -- Verify that nullable fields properly work
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE test_serializer(string1 STRING,
- int1 INT,
- tinyint1 TINYINT,
- smallint1 SMALLINT,
- bigint1 BIGINT,
- boolean1 BOOLEAN,
- float1 FLOAT,
- double1 DOUBLE,
- list1 ARRAY<STRING>,
- map1 MAP<STRING,INT>,
- struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
- enum1 STRING,
- nullableint INT,
- bytes1 BINARY,
- fixed1 BINARY)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@test_serializer
-POSTHOOK: query: -- Verify that nullable fields properly work
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE test_serializer(string1 STRING,
- int1 INT,
- tinyint1 TINYINT,
- smallint1 SMALLINT,
- bigint1 BIGINT,
- boolean1 BOOLEAN,
- float1 FLOAT,
- double1 DOUBLE,
- list1 ARRAY<STRING>,
- map1 MAP<STRING,INT>,
- struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
- enum1 STRING,
- nullableint INT,
- bytes1 BINARY,
- fixed1 BINARY)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@test_serializer
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@test_serializer
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@test_serializer
-PREHOOK: query: CREATE TABLE as_avro
- ROW FORMAT
- SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
- STORED AS
- INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
- OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
- TBLPROPERTIES (
- 'avro.schema.literal'='{
- "namespace": "com.howdy",
- "name": "some_schema",
- "type": "record",
- "fields": [
- { "name": "string1", "type": ["null", "string"] },
- { "name": "int1", "type": ["null", "int"] },
- { "name": "tinyint1", "type": ["null", "int"] },
- { "name": "smallint1", "type": ["null", "int"] },
- { "name": "bigint1", "type": ["null", "long"] },
- { "name": "boolean1", "type": ["null", "boolean"] },
- { "name": "float1", "type": ["null", "float"] },
- { "name": "double1", "type": ["null", "double"] },
- { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
- { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
- { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
- { "name": "sInt", "type": "int" },
- { "name": "sBoolean", "type": "boolean" },
- { "name": "sString", "type": "string" }
- ]}] },
- { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
- { "name": "nullableint", "type": ["null", "int"] },
- { "name": "bytes1", "type": ["null", "bytes"] },
- { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
- ]
- }'
- )
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@as_avro
-POSTHOOK: query: CREATE TABLE as_avro
- ROW FORMAT
- SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
- STORED AS
- INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
- OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
- TBLPROPERTIES (
- 'avro.schema.literal'='{
- "namespace": "com.howdy",
- "name": "some_schema",
- "type": "record",
- "fields": [
- { "name": "string1", "type": ["null", "string"] },
- { "name": "int1", "type": ["null", "int"] },
- { "name": "tinyint1", "type": ["null", "int"] },
- { "name": "smallint1", "type": ["null", "int"] },
- { "name": "bigint1", "type": ["null", "long"] },
- { "name": "boolean1", "type": ["null", "boolean"] },
- { "name": "float1", "type": ["null", "float"] },
- { "name": "double1", "type": ["null", "double"] },
- { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
- { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
- { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
- { "name": "sInt", "type": "int" },
- { "name": "sBoolean", "type": "boolean" },
- { "name": "sString", "type": "string" }
- ]}] },
- { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
- { "name": "nullableint", "type": ["null", "int"] },
- { "name": "bytes1", "type": ["null", "bytes"] },
- { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
- ]
- }'
- )
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@as_avro
-PREHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
-PREHOOK: type: QUERY
-PREHOOK: Input: default@test_serializer
-PREHOOK: Output: default@as_avro
-POSTHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@test_serializer
-POSTHOOK: Output: default@as_avro
-POSTHOOK: Lineage: as_avro.bigint1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bigint1, type:bigint, comment:null), ]
-POSTHOOK: Lineage: as_avro.boolean1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:boolean1, type:boolean, comment:null), ]
-POSTHOOK: Lineage: as_avro.bytes1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bytes1, type:binary, comment:null), ]
-POSTHOOK: Lineage: as_avro.double1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:double1, type:double, comment:null), ]
-POSTHOOK: Lineage: as_avro.enum1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:enum1, type:string, comment:null), ]
-POSTHOOK: Lineage: as_avro.fixed1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:fixed1, type:binary, comment:null), ]
-POSTHOOK: Lineage: as_avro.float1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:float1, type:float, comment:null), ]
-POSTHOOK: Lineage: as_avro.int1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:int1, type:int, comment:null), ]
-POSTHOOK: Lineage: as_avro.list1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:list1, type:array<string>, comment:null), ]
-POSTHOOK: Lineage: as_avro.map1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:map1, type:map<string,int>, comment:null), ]
-POSTHOOK: Lineage: as_avro.nullableint SIMPLE [(test_serializer)test_serializer.FieldSchema(name:nullableint, type:int, comment:null), ]
-POSTHOOK: Lineage: as_avro.smallint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:smallint1, type:smallint, comment:null), ]
-POSTHOOK: Lineage: as_avro.string1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:string1, type:string, comment:null), ]
-POSTHOOK: Lineage: as_avro.struct1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:struct1, type:struct<sint:int,sboolean:boolean,sstring:string>, comment:null), ]
-POSTHOOK: Lineage: as_avro.tinyint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:tinyint1, type:tinyint, comment:null), ]
-PREHOOK: query: SELECT * FROM as_avro
-PREHOOK: type: QUERY
-PREHOOK: Input: default@as_avro
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM as_avro
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@as_avro
-#### A masked pattern was here ####
-why hello there 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-another record 98 4 101 9999999 false 99.89 9.0E-8 ["beta"] {"Earth":101} {"sint":1134,"sboolean":false,"sstring":"wazzup"} RED NULL ef
-third record 45 5 102 999999999 true 89.99 9.0E-14 ["alpha","gamma"] {"Earth":237,"Bob":723} {"sint":102,"sboolean":false,"sstring":"BNL"} GREEN NULL hi
-NULL 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string NULL 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 NULL 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 NULL 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 NULL true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 NULL 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true NULL 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 NULL ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 NULL {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] NULL {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} NULL BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} NULL 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE NULL bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Bob":31,"Control":86} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.8.out b/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.8.out
deleted file mode 100644
index 3690f7b..0000000
--- a/ql/src/test/results/clientpositive/avro_nullable_fields.q.java1.8.out
+++ /dev/null
@@ -1,179 +0,0 @@
-PREHOOK: query: -- Verify that nullable fields properly work
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE test_serializer(string1 STRING,
- int1 INT,
- tinyint1 TINYINT,
- smallint1 SMALLINT,
- bigint1 BIGINT,
- boolean1 BOOLEAN,
- float1 FLOAT,
- double1 DOUBLE,
- list1 ARRAY<STRING>,
- map1 MAP<STRING,INT>,
- struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
- enum1 STRING,
- nullableint INT,
- bytes1 BINARY,
- fixed1 BINARY)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@test_serializer
-POSTHOOK: query: -- Verify that nullable fields properly work
-
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE test_serializer(string1 STRING,
- int1 INT,
- tinyint1 TINYINT,
- smallint1 SMALLINT,
- bigint1 BIGINT,
- boolean1 BOOLEAN,
- float1 FLOAT,
- double1 DOUBLE,
- list1 ARRAY<STRING>,
- map1 MAP<STRING,INT>,
- struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
- enum1 STRING,
- nullableint INT,
- bytes1 BINARY,
- fixed1 BINARY)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@test_serializer
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@test_serializer
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@test_serializer
-PREHOOK: query: CREATE TABLE as_avro
- ROW FORMAT
- SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
- STORED AS
- INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
- OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
- TBLPROPERTIES (
- 'avro.schema.literal'='{
- "namespace": "com.howdy",
- "name": "some_schema",
- "type": "record",
- "fields": [
- { "name": "string1", "type": ["null", "string"] },
- { "name": "int1", "type": ["null", "int"] },
- { "name": "tinyint1", "type": ["null", "int"] },
- { "name": "smallint1", "type": ["null", "int"] },
- { "name": "bigint1", "type": ["null", "long"] },
- { "name": "boolean1", "type": ["null", "boolean"] },
- { "name": "float1", "type": ["null", "float"] },
- { "name": "double1", "type": ["null", "double"] },
- { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
- { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
- { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
- { "name": "sInt", "type": "int" },
- { "name": "sBoolean", "type": "boolean" },
- { "name": "sString", "type": "string" }
- ]}] },
- { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
- { "name": "nullableint", "type": ["null", "int"] },
- { "name": "bytes1", "type": ["null", "bytes"] },
- { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
- ]
- }'
- )
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@as_avro
-POSTHOOK: query: CREATE TABLE as_avro
- ROW FORMAT
- SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
- STORED AS
- INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
- OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
- TBLPROPERTIES (
- 'avro.schema.literal'='{
- "namespace": "com.howdy",
- "name": "some_schema",
- "type": "record",
- "fields": [
- { "name": "string1", "type": ["null", "string"] },
- { "name": "int1", "type": ["null", "int"] },
- { "name": "tinyint1", "type": ["null", "int"] },
- { "name": "smallint1", "type": ["null", "int"] },
- { "name": "bigint1", "type": ["null", "long"] },
- { "name": "boolean1", "type": ["null", "boolean"] },
- { "name": "float1", "type": ["null", "float"] },
- { "name": "double1", "type": ["null", "double"] },
- { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
- { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
- { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
- { "name": "sInt", "type": "int" },
- { "name": "sBoolean", "type": "boolean" },
- { "name": "sString", "type": "string" }
- ]}] },
- { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
- { "name": "nullableint", "type": ["null", "int"] },
- { "name": "bytes1", "type": ["null", "bytes"] },
- { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
- ]
- }'
- )
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@as_avro
-PREHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
-PREHOOK: type: QUERY
-PREHOOK: Input: default@test_serializer
-PREHOOK: Output: default@as_avro
-POSTHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@test_serializer
-POSTHOOK: Output: default@as_avro
-POSTHOOK: Lineage: as_avro.bigint1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bigint1, type:bigint, comment:null), ]
-POSTHOOK: Lineage: as_avro.boolean1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:boolean1, type:boolean, comment:null), ]
-POSTHOOK: Lineage: as_avro.bytes1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bytes1, type:binary, comment:null), ]
-POSTHOOK: Lineage: as_avro.double1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:double1, type:double, comment:null), ]
-POSTHOOK: Lineage: as_avro.enum1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:enum1, type:string, comment:null), ]
-POSTHOOK: Lineage: as_avro.fixed1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:fixed1, type:binary, comment:null), ]
-POSTHOOK: Lineage: as_avro.float1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:float1, type:float, comment:null), ]
-POSTHOOK: Lineage: as_avro.int1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:int1, type:int, comment:null), ]
-POSTHOOK: Lineage: as_avro.list1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:list1, type:array<string>, comment:null), ]
-POSTHOOK: Lineage: as_avro.map1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:map1, type:map<string,int>, comment:null), ]
-POSTHOOK: Lineage: as_avro.nullableint SIMPLE [(test_serializer)test_serializer.FieldSchema(name:nullableint, type:int, comment:null), ]
-POSTHOOK: Lineage: as_avro.smallint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:smallint1, type:smallint, comment:null), ]
-POSTHOOK: Lineage: as_avro.string1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:string1, type:string, comment:null), ]
-POSTHOOK: Lineage: as_avro.struct1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:struct1, type:struct<sint:int,sboolean:boolean,sstring:string>, comment:null), ]
-POSTHOOK: Lineage: as_avro.tinyint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:tinyint1, type:tinyint, comment:null), ]
-PREHOOK: query: SELECT * FROM as_avro
-PREHOOK: type: QUERY
-PREHOOK: Input: default@as_avro
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM as_avro
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@as_avro
-#### A masked pattern was here ####
-why hello there 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-another record 98 4 101 9999999 false 99.89 9.0E-8 ["beta"] {"Earth":101} {"sint":1134,"sboolean":false,"sstring":"wazzup"} RED NULL ef
-third record 45 5 102 999999999 true 89.99 9.0E-14 ["alpha","gamma"] {"Earth":237,"Bob":723} {"sint":102,"sboolean":false,"sstring":"BNL"} GREEN NULL hi
-NULL 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string NULL 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 NULL 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 NULL 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 NULL true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 NULL 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true NULL 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 NULL ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 NULL {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] NULL {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} NULL BLUE 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} NULL 72 bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE NULL bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL bc
-string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_nullable_fields.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_nullable_fields.q.out b/ql/src/test/results/clientpositive/avro_nullable_fields.q.out
new file mode 100644
index 0000000..2272b34
--- /dev/null
+++ b/ql/src/test/results/clientpositive/avro_nullable_fields.q.out
@@ -0,0 +1,177 @@
+PREHOOK: query: -- Verify that nullable fields properly work
+
+
+CREATE TABLE test_serializer(string1 STRING,
+ int1 INT,
+ tinyint1 TINYINT,
+ smallint1 SMALLINT,
+ bigint1 BIGINT,
+ boolean1 BOOLEAN,
+ float1 FLOAT,
+ double1 DOUBLE,
+ list1 ARRAY<STRING>,
+ map1 MAP<STRING,INT>,
+ struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
+ enum1 STRING,
+ nullableint INT,
+ bytes1 BINARY,
+ fixed1 BINARY)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
+ STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_serializer
+POSTHOOK: query: -- Verify that nullable fields properly work
+
+
+CREATE TABLE test_serializer(string1 STRING,
+ int1 INT,
+ tinyint1 TINYINT,
+ smallint1 SMALLINT,
+ bigint1 BIGINT,
+ boolean1 BOOLEAN,
+ float1 FLOAT,
+ double1 DOUBLE,
+ list1 ARRAY<STRING>,
+ map1 MAP<STRING,INT>,
+ struct1 STRUCT<sint:INT,sboolean:BOOLEAN,sstring:STRING>,
+ enum1 STRING,
+ nullableint INT,
+ bytes1 BINARY,
+ fixed1 BINARY)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' COLLECTION ITEMS TERMINATED BY ':' MAP KEYS TERMINATED BY '#' LINES TERMINATED BY '\n'
+ STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_serializer
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@test_serializer
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/csv.txt' INTO TABLE test_serializer
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@test_serializer
+PREHOOK: query: CREATE TABLE as_avro
+ ROW FORMAT
+ SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+ STORED AS
+ INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+ OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+ TBLPROPERTIES (
+ 'avro.schema.literal'='{
+ "namespace": "com.howdy",
+ "name": "some_schema",
+ "type": "record",
+ "fields": [
+ { "name": "string1", "type": ["null", "string"] },
+ { "name": "int1", "type": ["null", "int"] },
+ { "name": "tinyint1", "type": ["null", "int"] },
+ { "name": "smallint1", "type": ["null", "int"] },
+ { "name": "bigint1", "type": ["null", "long"] },
+ { "name": "boolean1", "type": ["null", "boolean"] },
+ { "name": "float1", "type": ["null", "float"] },
+ { "name": "double1", "type": ["null", "double"] },
+ { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
+ { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
+ { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
+ { "name": "sInt", "type": "int" },
+ { "name": "sBoolean", "type": "boolean" },
+ { "name": "sString", "type": "string" }
+ ]}] },
+ { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
+ { "name": "nullableint", "type": ["null", "int"] },
+ { "name": "bytes1", "type": ["null", "bytes"] },
+ { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
+ ]
+ }'
+ )
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@as_avro
+POSTHOOK: query: CREATE TABLE as_avro
+ ROW FORMAT
+ SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
+ STORED AS
+ INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
+ OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
+ TBLPROPERTIES (
+ 'avro.schema.literal'='{
+ "namespace": "com.howdy",
+ "name": "some_schema",
+ "type": "record",
+ "fields": [
+ { "name": "string1", "type": ["null", "string"] },
+ { "name": "int1", "type": ["null", "int"] },
+ { "name": "tinyint1", "type": ["null", "int"] },
+ { "name": "smallint1", "type": ["null", "int"] },
+ { "name": "bigint1", "type": ["null", "long"] },
+ { "name": "boolean1", "type": ["null", "boolean"] },
+ { "name": "float1", "type": ["null", "float"] },
+ { "name": "double1", "type": ["null", "double"] },
+ { "name": "list1", "type": ["null", {"type": "array", "items": "string"}] },
+ { "name": "map1", "type": ["null", {"type": "map", "values": "int"}] },
+ { "name": "struct1", "type": ["null", {"type": "record", "name": "struct1_name", "fields": [
+ { "name": "sInt", "type": "int" },
+ { "name": "sBoolean", "type": "boolean" },
+ { "name": "sString", "type": "string" }
+ ]}] },
+ { "name": "enum1", "type": ["null", {"type": "enum", "name": "enum1_values", "symbols": ["BLUE", "RED", "GREEN"]}] },
+ { "name": "nullableint", "type": ["null", "int"] },
+ { "name": "bytes1", "type": ["null", "bytes"] },
+ { "name": "fixed1", "type": ["null", {"type": "fixed", "name": "threebytes", "size": 3}] }
+ ]
+ }'
+ )
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@as_avro
+PREHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_serializer
+PREHOOK: Output: default@as_avro
+POSTHOOK: query: INSERT OVERWRITE TABLE as_avro SELECT * FROM test_serializer
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_serializer
+POSTHOOK: Output: default@as_avro
+POSTHOOK: Lineage: as_avro.bigint1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bigint1, type:bigint, comment:null), ]
+POSTHOOK: Lineage: as_avro.boolean1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:boolean1, type:boolean, comment:null), ]
+POSTHOOK: Lineage: as_avro.bytes1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:bytes1, type:binary, comment:null), ]
+POSTHOOK: Lineage: as_avro.double1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:double1, type:double, comment:null), ]
+POSTHOOK: Lineage: as_avro.enum1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:enum1, type:string, comment:null), ]
+POSTHOOK: Lineage: as_avro.fixed1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:fixed1, type:binary, comment:null), ]
+POSTHOOK: Lineage: as_avro.float1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:float1, type:float, comment:null), ]
+POSTHOOK: Lineage: as_avro.int1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:int1, type:int, comment:null), ]
+POSTHOOK: Lineage: as_avro.list1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:list1, type:array<string>, comment:null), ]
+POSTHOOK: Lineage: as_avro.map1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:map1, type:map<string,int>, comment:null), ]
+POSTHOOK: Lineage: as_avro.nullableint SIMPLE [(test_serializer)test_serializer.FieldSchema(name:nullableint, type:int, comment:null), ]
+POSTHOOK: Lineage: as_avro.smallint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:smallint1, type:smallint, comment:null), ]
+POSTHOOK: Lineage: as_avro.string1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:string1, type:string, comment:null), ]
+POSTHOOK: Lineage: as_avro.struct1 SIMPLE [(test_serializer)test_serializer.FieldSchema(name:struct1, type:struct<sint:int,sboolean:boolean,sstring:string>, comment:null), ]
+POSTHOOK: Lineage: as_avro.tinyint1 EXPRESSION [(test_serializer)test_serializer.FieldSchema(name:tinyint1, type:tinyint, comment:null), ]
+PREHOOK: query: SELECT * FROM as_avro
+PREHOOK: type: QUERY
+PREHOOK: Input: default@as_avro
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM as_avro
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@as_avro
+#### A masked pattern was here ####
+why hello there 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+another record 98 4 101 9999999 false 99.89 9.0E-8 ["beta"] {"Earth":101} {"sint":1134,"sboolean":false,"sstring":"wazzup"} RED NULL ef
+third record 45 5 102 999999999 true 89.99 9.0E-14 ["alpha","gamma"] {"Earth":237,"Bob":723} {"sint":102,"sboolean":false,"sstring":"BNL"} GREEN NULL hi
+NULL 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string NULL 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 NULL 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 NULL 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 NULL true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 NULL 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 true NULL 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 true 42.43 NULL ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 true 42.43 85.23423424 NULL {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] NULL {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} NULL BLUE 72 bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} NULL 72 bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE NULL bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL bc
+string 42 3 100 1412341 true 42.43 85.23423424 ["alpha","beta","gamma"] {"Earth":42,"Control":86,"Bob":31} {"sint":17,"sboolean":true,"sstring":"Abe Linkedin"} BLUE 72 NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_timestamp.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_timestamp.q.java1.7.out b/ql/src/test/results/clientpositive/avro_timestamp.q.java1.7.out
deleted file mode 100644
index d2d3b7c..0000000
--- a/ql/src/test/results/clientpositive/avro_timestamp.q.java1.7.out
+++ /dev/null
@@ -1,134 +0,0 @@
-PREHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
--- EXCLUDE_OS_WINDOWS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_timestamp_staging
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
--- EXCLUDE_OS_WINDOWS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_timestamp_staging
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_timestamp
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_timestamp
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_timestamp_casts
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_timestamp_casts
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_timestamp_staging
-POSTHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_timestamp_staging
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_timestamp_staging
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_timestamp_staging
-PREHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- PARTITIONED BY (p1 int, p2 timestamp)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_timestamp
-POSTHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- PARTITIONED BY (p1 int, p2 timestamp)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_timestamp
-PREHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp_staging
-PREHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-POSTHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp_staging
-POSTHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).d SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:d, type:timestamp, comment:null), ]
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).l1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:l1, type:array<timestamp>, comment:null), ]
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).m1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:m1, type:map<string,timestamp>, comment:null), ]
-PREHOOK: query: SELECT * FROM avro_timestamp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"foo":"1980-12-16 07:08:09.123","bar":"1998-05-07 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-1947-02-11 07:08:09.123 1
-2012-02-21 07:08:09.123 1
-2014-02-11 07:08:09.123 1
-8200-02-11 07:08:09.123 1
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"foo":"1980-12-16 07:08:09.123","bar":"1998-05-07 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"foo":"1980-12-16 07:08:09.123","bar":"1998-05-07 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_timestamp.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_timestamp.q.java1.8.out b/ql/src/test/results/clientpositive/avro_timestamp.q.java1.8.out
deleted file mode 100644
index 4c38347..0000000
--- a/ql/src/test/results/clientpositive/avro_timestamp.q.java1.8.out
+++ /dev/null
@@ -1,134 +0,0 @@
-PREHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
--- EXCLUDE_OS_WINDOWS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_timestamp_staging
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
--- EXCLUDE_OS_WINDOWS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE avro_timestamp_staging
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_timestamp
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_timestamp
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE avro_timestamp_casts
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE avro_timestamp_casts
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_timestamp_staging
-POSTHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_timestamp_staging
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@avro_timestamp_staging
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@avro_timestamp_staging
-PREHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- PARTITIONED BY (p1 int, p2 timestamp)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@avro_timestamp
-POSTHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
- PARTITIONED BY (p1 int, p2 timestamp)
- ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
- COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
- STORED AS AVRO
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@avro_timestamp
-PREHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp_staging
-PREHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-POSTHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp_staging
-POSTHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).d SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:d, type:timestamp, comment:null), ]
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).l1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:l1, type:array<timestamp>, comment:null), ]
-POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).m1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:m1, type:map<string,timestamp>, comment:null), ]
-PREHOOK: query: SELECT * FROM avro_timestamp
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-1947-02-11 07:08:09.123 1
-2012-02-21 07:08:09.123 1
-2014-02-11 07:08:09.123 1
-8200-02-11 07:08:09.123 1
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
-PREHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
-PREHOOK: type: QUERY
-PREHOOK: Input: default@avro_timestamp
-PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@avro_timestamp
-POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
-#### A masked pattern was here ####
-8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/avro_timestamp.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_timestamp.q.out b/ql/src/test/results/clientpositive/avro_timestamp.q.out
new file mode 100644
index 0000000..868807a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/avro_timestamp.q.out
@@ -0,0 +1,132 @@
+PREHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
+-- EXCLUDE_OS_WINDOWS
+
+DROP TABLE avro_timestamp_staging
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: -- Exclude test on Windows due to space character being escaped in Hive paths on Windows.
+-- EXCLUDE_OS_WINDOWS
+
+DROP TABLE avro_timestamp_staging
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE avro_timestamp
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE avro_timestamp
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: DROP TABLE avro_timestamp_casts
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: DROP TABLE avro_timestamp_casts
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_timestamp_staging
+POSTHOOK: query: CREATE TABLE avro_timestamp_staging (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_timestamp_staging
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@avro_timestamp_staging
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/avro_timestamp.txt' OVERWRITE INTO TABLE avro_timestamp_staging
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@avro_timestamp_staging
+PREHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
+ PARTITIONED BY (p1 int, p2 timestamp)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS AVRO
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@avro_timestamp
+POSTHOOK: query: CREATE TABLE avro_timestamp (d timestamp, m1 map<string, timestamp>, l1 array<timestamp>)
+ PARTITIONED BY (p1 int, p2 timestamp)
+ ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
+ COLLECTION ITEMS TERMINATED BY ',' MAP KEYS TERMINATED BY ':'
+ STORED AS AVRO
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@avro_timestamp
+PREHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp_staging
+PREHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+POSTHOOK: query: INSERT OVERWRITE TABLE avro_timestamp PARTITION(p1=2, p2='2014-09-26 07:08:09.123') SELECT * FROM avro_timestamp_staging
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp_staging
+POSTHOOK: Output: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).d SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:d, type:timestamp, comment:null), ]
+POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).l1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:l1, type:array<timestamp>, comment:null), ]
+POSTHOOK: Lineage: avro_timestamp PARTITION(p1=2,p2=2014-09-26 07:08:09.123).m1 SIMPLE [(avro_timestamp_staging)avro_timestamp_staging.FieldSchema(name:m1, type:map<string,timestamp>, comment:null), ]
+PREHOOK: query: SELECT * FROM avro_timestamp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp
+PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_timestamp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp
+POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+PREHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp
+PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT d, COUNT(d) FROM avro_timestamp GROUP BY d
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp
+POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+1947-02-11 07:08:09.123 1
+2012-02-21 07:08:09.123 1
+2014-02-11 07:08:09.123 1
+8200-02-11 07:08:09.123 1
+PREHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp
+PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d!='1947-02-11 07:08:09.123'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp
+POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+PREHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp
+PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d<'2014-12-21 07:08:09.123'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp
+POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+2012-02-21 07:08:09.123 {"bar":"1998-05-07 07:08:09.123","foo":"1980-12-16 07:08:09.123"} ["2011-09-04 07:08:09.123","2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+2014-02-11 07:08:09.123 {"baz":"1981-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+1947-02-11 07:08:09.123 {"baz":"1921-12-16 07:08:09.123"} ["2011-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
+PREHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@avro_timestamp
+PREHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM avro_timestamp WHERE d>'8000-12-01 07:08:09.123'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@avro_timestamp
+POSTHOOK: Input: default@avro_timestamp@p1=2/p2=2014-09-26 07%3A08%3A09.123
+#### A masked pattern was here ####
+8200-02-11 07:08:09.123 {"baz":"6981-12-16 07:08:09.123"} ["1039-09-05 07:08:09.123"] 2 2014-09-26 07:08:09.123
[21/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
Posted by sp...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.8.out b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.8.out
deleted file mode 100644
index 1bfdba2..0000000
--- a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.java1.8.out
+++ /dev/null
@@ -1,890 +0,0 @@
-PREHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_4
-POSTHOOK: query: -- SORT_QUERY_RESULTS
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-CREATE TABLE src_4(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_4
-RUN: Stage-0:DDL
-PREHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@src_5
-POSTHOOK: query: CREATE TABLE src_5(
- key STRING,
- value STRING
-)
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@src_5
-RUN: Stage-0:DDL
-Warning: Shuffle Join JOIN[31][tables = [sq_2_notin_nullcheck]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-2
- Spark
- Edges:
- Reducer 2 <- Map 10 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
- Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2)
- Reducer 9 <- Map 8 (GROUP, 1)
- Reducer 4 <- Reducer 3 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 10
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Map 11
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string), value (type: string)
- sort order: ++
- Map-reduce partition columns: key (type: string), value (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map 6
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Map 7
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Map 8
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Reducer 4
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
- Reducer 5
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Reducer 9
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 0 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-4
- Stats-Aggr Operator
-
-Warning: Shuffle Join JOIN[31][tables = [sq_2_notin_nullcheck]] in Work 'Reducer 2' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-2:MAPRED
-RUN: Stage-1:MOVE
-RUN: Stage-0:MOVE
-RUN: Stage-3:STATS
-RUN: Stage-4:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
-Warning: Map Join MAPJOIN[46][bigTable=b] in task 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-POSTHOOK: query: explain
-from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-2 depends on stages: Stage-5
- Stage-1 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
-
-STAGE PLANS:
- Stage: Stage-5
- Spark
- Edges:
- Reducer 6 <- Map 5 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 4
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > '2') (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 5
- Map Operator Tree:
- TableScan
- alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key > '2') and key is null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 6
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 0 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: bigint)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0
- 1
-
- Stage: Stage-2
- Spark
- Edges:
- Reducer 2 <- Map 1 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Reducer 6
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- input vertices:
- 1 Map 4
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Local Work:
- Map Reduce Local Work
- Reducer 2
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
-
- Stage: Stage-4
- Stats-Aggr Operator
-
-Warning: Map Join MAPJOIN[46][bigTable=b] in task 'Stage-2:MAPRED' is a cross product
-PREHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@src_4
-PREHOOK: Output: default@src_5
-POSTHOOK: query: from src b
-INSERT OVERWRITE TABLE src_4
- select *
- where b.key in
- (select a.key
- from src a
- where b.value = a.value and a.key > '9'
- )
-INSERT OVERWRITE TABLE src_5
- select *
- where b.key not in ( select key from src s1 where s1.key > '2')
- order by key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@src_4
-POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-5:MAPRED
-RUN: Stage-2:MAPRED
-RUN: Stage-1:MOVE
-RUN: Stage-0:MOVE
-RUN: Stage-3:STATS
-RUN: Stage-4:STATS
-PREHOOK: query: select * from src_4
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_4
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_4
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_4
-#### A masked pattern was here ####
-90 val_90
-90 val_90
-90 val_90
-92 val_92
-95 val_95
-95 val_95
-96 val_96
-97 val_97
-97 val_97
-98 val_98
-98 val_98
-PREHOOK: query: select * from src_5
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src_5
-#### A masked pattern was here ####
-POSTHOOK: query: select * from src_5
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src_5
-#### A masked pattern was here ####
-0 val_0
-0 val_0
-0 val_0
-10 val_10
-100 val_100
-100 val_100
-103 val_103
-103 val_103
-104 val_104
-104 val_104
-105 val_105
-11 val_11
-111 val_111
-113 val_113
-113 val_113
-114 val_114
-116 val_116
-118 val_118
-118 val_118
-119 val_119
-119 val_119
-119 val_119
-12 val_12
-12 val_12
-120 val_120
-120 val_120
-125 val_125
-125 val_125
-126 val_126
-128 val_128
-128 val_128
-128 val_128
-129 val_129
-129 val_129
-131 val_131
-133 val_133
-134 val_134
-134 val_134
-136 val_136
-137 val_137
-137 val_137
-138 val_138
-138 val_138
-138 val_138
-138 val_138
-143 val_143
-145 val_145
-146 val_146
-146 val_146
-149 val_149
-149 val_149
-15 val_15
-15 val_15
-150 val_150
-152 val_152
-152 val_152
-153 val_153
-155 val_155
-156 val_156
-157 val_157
-158 val_158
-160 val_160
-162 val_162
-163 val_163
-164 val_164
-164 val_164
-165 val_165
-165 val_165
-166 val_166
-167 val_167
-167 val_167
-167 val_167
-168 val_168
-169 val_169
-169 val_169
-169 val_169
-169 val_169
-17 val_17
-170 val_170
-172 val_172
-172 val_172
-174 val_174
-174 val_174
-175 val_175
-175 val_175
-176 val_176
-176 val_176
-177 val_177
-178 val_178
-179 val_179
-179 val_179
-18 val_18
-18 val_18
-180 val_180
-181 val_181
-183 val_183
-186 val_186
-187 val_187
-187 val_187
-187 val_187
-189 val_189
-19 val_19
-190 val_190
-191 val_191
-191 val_191
-192 val_192
-193 val_193
-193 val_193
-193 val_193
-194 val_194
-195 val_195
-195 val_195
-196 val_196
-197 val_197
-197 val_197
-199 val_199
-199 val_199
-199 val_199
-2 val_2
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
index 04dd9b4..d6df85a 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
@@ -73,8 +73,8 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 10 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
- Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 4), Reducer 2 (PARTITION-LEVEL SORT, 4)
+ Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 4), Map 6 (PARTITION-LEVEL SORT, 4)
Reducer 9 <- Map 8 (GROUP, 1)
Reducer 4 <- Reducer 3 (SORT, 1)
#### A masked pattern was here ####
@@ -105,21 +105,21 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Map 7
Map Operator Tree:
TableScan
@@ -235,19 +235,17 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: 0 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: _col0 (type: bigint)
+ keys: 0 (type: bigint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-1
Move Operator
@@ -308,10 +306,10 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@src_4
POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
RUN: Stage-2:MAPRED
RUN: Stage-1:MOVE
RUN: Stage-0:MOVE
@@ -514,16 +512,16 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key > '9') and value is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 key (type: string), value (type: string)
@@ -578,16 +576,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: 0 (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: _col0 (type: bigint)
+ keys: 0 (type: bigint)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0
@@ -730,10 +726,10 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@src_4
POSTHOOK: Output: default@src_5
-POSTHOOK: Lineage: src_4.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_4.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: src_5.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_4.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.key SIMPLE [(src)b.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src_5.value SIMPLE [(src)b.FieldSchema(name:value, type:string, comment:default), ]
RUN: Stage-5:MAPRED
RUN: Stage-2:MAPRED
RUN: Stage-1:MOVE
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out
deleted file mode 100644
index 86b7544..0000000
--- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.7.out
+++ /dev/null
@@ -1,217 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 2)
- Reducer 3 <- Reducer 2 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
- Reducer 3
- Execution mode: vectorized
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i ORDER BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65536 50.0 50.0 50.0000
-65537 50.0 50.0 50.0000
-65538 50.0 50.0 50.0000
-65539 50.0 50.0 50.0000
-65540 50.0 50.0 50.0000
-65541 50.0 50.0 50.0000
-65542 50.0 50.0 50.0000
-65543 50.0 50.0 50.0000
-65544 50.0 50.0 50.0000
-65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out
deleted file mode 100644
index 69f4754..0000000
--- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.java1.8.out
+++ /dev/null
@@ -1,203 +0,0 @@
-PREHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- JAVA_VERSION_SPECIFIC_OUTPUT
-
-DROP TABLE over1k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: DROP TABLE over1korc
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: DROP TABLE over1korc
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1k
-POSTHOOK: query: -- data setup
-CREATE TABLE over1k(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-ROW FORMAT DELIMITED FIELDS TERMINATED BY '|'
-STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1k
-PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over1k
-POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/over1k' OVERWRITE INTO TABLE over1k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over1k
-PREHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: CREATE TABLE over1korc(t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- dec decimal(4,2),
- bin binary)
-STORED AS ORC
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over1korc
-PREHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1k
-PREHOOK: Output: default@over1korc
-POSTHOOK: query: INSERT INTO TABLE over1korc SELECT * FROM over1k
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1k
-POSTHOOK: Output: default@over1korc
-POSTHOOK: Lineage: over1korc.b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ]
-POSTHOOK: Lineage: over1korc.bin SIMPLE [(over1k)over1k.FieldSchema(name:bin, type:binary, comment:null), ]
-POSTHOOK: Lineage: over1korc.bo SIMPLE [(over1k)over1k.FieldSchema(name:bo, type:boolean, comment:null), ]
-POSTHOOK: Lineage: over1korc.d SIMPLE [(over1k)over1k.FieldSchema(name:d, type:double, comment:null), ]
-POSTHOOK: Lineage: over1korc.dec SIMPLE [(over1k)over1k.FieldSchema(name:dec, type:decimal(4,2), comment:null), ]
-POSTHOOK: Lineage: over1korc.f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ]
-POSTHOOK: Lineage: over1korc.i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ]
-POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:string, comment:null), ]
-POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
-POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
-POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
-PREHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: i (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: avg(50), avg(50.0), avg(50)
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:double,input:double>), _col3 (type: struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>)
- Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
- Group By Operator
- aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
- keys: KEY._col0 (type: int)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-POSTHOOK: query: SELECT
- i,
- AVG(CAST(50 AS INT)) AS `avg_int_ok`,
- AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
- AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over1korc
-#### A masked pattern was here ####
-65636 50.0 50.0 50
-65550 50.0 50.0 50
-65592 50.0 50.0 50
-65744 50.0 50.0 50
-65722 50.0 50.0 50
-65668 50.0 50.0 50
-65598 50.0 50.0 50
-65596 50.0 50.0 50
-65568 50.0 50.0 50
-65738 50.0 50.0 50
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
index 63cdc24..0459d93 100644
--- a/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
+++ b/ql/src/test/results/clientpositive/spark/vector_cast_constant.q.out
@@ -102,14 +102,14 @@ PREHOOK: query: EXPLAIN SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN SELECT
i,
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
@@ -119,7 +119,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP, 2)
+ Reducer 2 <- Map 1 (GROUP, 4)
+ Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -129,11 +130,11 @@ STAGE PLANS:
Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i (type: int)
- outputColumnNames: i
+ outputColumnNames: _col0
Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: avg(50), avg(UDFToDouble(50)), avg(CAST( 50 AS decimal(10,0)))
- keys: i (type: int)
+ aggregations: avg(50), avg(50.0), avg(50)
+ keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
@@ -152,6 +153,19 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(14,4))
+ Reducer 3
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: decimal(14,4))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
@@ -159,8 +173,8 @@ STAGE PLANS:
compressed: false
Statistics: Num rows: 10 Data size: 2960 Basic stats: COMPLETE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
@@ -174,7 +188,7 @@ PREHOOK: query: SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
PREHOOK: type: QUERY
PREHOOK: Input: default@over1korc
#### A masked pattern was here ####
@@ -183,17 +197,17 @@ POSTHOOK: query: SELECT
AVG(CAST(50 AS INT)) AS `avg_int_ok`,
AVG(CAST(50 AS DOUBLE)) AS `avg_double_ok`,
AVG(CAST(50 AS DECIMAL)) AS `avg_decimal_ok`
- FROM over1korc GROUP BY i LIMIT 10
+ FROM over1korc GROUP BY i ORDER BY i LIMIT 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@over1korc
#### A masked pattern was here ####
-65598 50.0 50.0 50
-65694 50.0 50.0 50
-65678 50.0 50.0 50
-65684 50.0 50.0 50
-65596 50.0 50.0 50
-65692 50.0 50.0 50
-65630 50.0 50.0 50
-65674 50.0 50.0 50
-65628 50.0 50.0 50
-65776 50.0 50.0 50
+65536 50.0 50.0 50.0000
+65537 50.0 50.0 50.0000
+65538 50.0 50.0 50.0000
+65539 50.0 50.0 50.0000
+65540 50.0 50.0 50.0000
+65541 50.0 50.0 50.0000
+65542 50.0 50.0 50.0000
+65543 50.0 50.0 50.0000
+65544 50.0 50.0 50.0000
+65545 50.0 50.0 50.0000
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.7.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.7.out b/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.7.out
deleted file mode 100644
index a4908bc..0000000
--- a/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.7.out
+++ /dev/null
@@ -1,191 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-drop table stats_list_bucket
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-drop table stats_list_bucket
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: drop table stats_list_bucket_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table stats_list_bucket_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table stats_list_bucket (
- c1 string,
- c2 string
-) partitioned by (ds string, hr string)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@stats_list_bucket
-POSTHOOK: query: create table stats_list_bucket (
- c1 string,
- c2 string
-) partitioned by (ds string, hr string)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@stats_list_bucket
-PREHOOK: query: -- Try partitioned table with list bucketing.
--- The stats should show 500 rows loaded, as many rows as the src table has.
-
-insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
- select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
-POSTHOOK: query: -- Try partitioned table with list bucketing.
--- The stats should show 500 rows loaded, as many rows as the src table has.
-
-insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
- select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@stats_list_bucket
-POSTHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@stats_list_bucket
-# col_name data_type comment
-
-c1 string
-c2 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: stats_list_bucket
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [c1, c2]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[82, val_82]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=82/c2=val_82, [466, val_466]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=287/c2=val_287}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- Also try non-partitioned table with list bucketing.
--- Stats should show the same number of rows.
-
-create table stats_list_bucket_1 (
- c1 string,
- c2 string
-)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: -- Also try non-partitioned table with list bucketing.
--- Stats should show the same number of rows.
-
-create table stats_list_bucket_1 (
- c1 string,
- c2 string
-)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@stats_list_bucket_1
-PREHOOK: query: insert overwrite table stats_list_bucket_1
- select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: insert overwrite table stats_list_bucket_1
- select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: Lineage: stats_list_bucket_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: stats_list_bucket_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: desc formatted stats_list_bucket_1
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@stats_list_bucket_1
-POSTHOOK: query: desc formatted stats_list_bucket_1
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@stats_list_bucket_1
-# col_name data_type comment
-
-c1 string
-c2 string
-
-# Detailed Table Information
-Database: default
-#### A masked pattern was here ####
-Retention: 0
-#### A masked pattern was here ####
-Table Type: MANAGED_TABLE
-Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [c1, c2]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82, [466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: drop table stats_list_bucket
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@stats_list_bucket
-PREHOOK: Output: default@stats_list_bucket
-POSTHOOK: query: drop table stats_list_bucket
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@stats_list_bucket
-POSTHOOK: Output: default@stats_list_bucket
-PREHOOK: query: drop table stats_list_bucket_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@stats_list_bucket_1
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: drop table stats_list_bucket_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@stats_list_bucket_1
-POSTHOOK: Output: default@stats_list_bucket_1
http://git-wip-us.apache.org/repos/asf/hive/blob/9349b8e5/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.8.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.8.out b/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.8.out
deleted file mode 100644
index 8688cee..0000000
--- a/ql/src/test/results/clientpositive/stats_list_bucket.q.java1.8.out
+++ /dev/null
@@ -1,193 +0,0 @@
-PREHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-drop table stats_list_bucket
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23)
--- JAVA_VERSION_SPECIFIC_OUTPUT
-
-drop table stats_list_bucket
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: drop table stats_list_bucket_1
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table stats_list_bucket_1
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table stats_list_bucket (
- c1 string,
- c2 string
-) partitioned by (ds string, hr string)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@stats_list_bucket
-POSTHOOK: query: create table stats_list_bucket (
- c1 string,
- c2 string
-) partitioned by (ds string, hr string)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@stats_list_bucket
-PREHOOK: query: -- Make sure we use hashed IDs during stats publishing.
--- Try partitioned table with list bucketing.
--- The stats should show 500 rows loaded, as many rows as the src table has.
-
-insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
- select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
-POSTHOOK: query: -- Make sure we use hashed IDs during stats publishing.
--- Try partitioned table with list bucketing.
--- The stats should show 500 rows loaded, as many rows as the src table has.
-
-insert overwrite table stats_list_bucket partition (ds = '2008-04-08', hr = '11')
- select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@stats_list_bucket@ds=2008-04-08/hr=11
-POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: stats_list_bucket PARTITION(ds=2008-04-08,hr=11).c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@stats_list_bucket
-POSTHOOK: query: desc formatted stats_list_bucket partition (ds = '2008-04-08', hr = '11')
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@stats_list_bucket
-# col_name data_type comment
-
-c1 string
-c2 string
-
-# Partition Information
-# col_name data_type comment
-
-ds string
-hr string
-
-# Detailed Partition Information
-Partition Value: [2008-04-08, 11]
-Database: default
-Table: stats_list_bucket
-#### A masked pattern was here ####
-Partition Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [c1, c2]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=466/c2=val_466, [287, val_287]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=287/c2=val_287, [82, val_82]=/stats_list_bucket/ds=2008-04-08/hr=11/c1=82/c2=val_82}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: -- Also try non-partitioned table with list bucketing.
--- Stats should show the same number of rows.
-
-create table stats_list_bucket_1 (
- c1 string,
- c2 string
-)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: -- Also try non-partitioned table with list bucketing.
--- Stats should show the same number of rows.
-
-create table stats_list_bucket_1 (
- c1 string,
- c2 string
-)
-skewed by (c1, c2) on (('466','val_466'),('287','val_287'),('82','val_82'))
-stored as directories
-stored as rcfile
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@stats_list_bucket_1
-PREHOOK: query: insert overwrite table stats_list_bucket_1
- select key, value from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: insert overwrite table stats_list_bucket_1
- select key, value from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: Lineage: stats_list_bucket_1.c1 SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: stats_list_bucket_1.c2 SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: desc formatted stats_list_bucket_1
-PREHOOK: type: DESCTABLE
-PREHOOK: Input: default@stats_list_bucket_1
-POSTHOOK: query: desc formatted stats_list_bucket_1
-POSTHOOK: type: DESCTABLE
-POSTHOOK: Input: default@stats_list_bucket_1
-# col_name data_type comment
-
-c1 string
-c2 string
-
-# Detailed Table Information
-Database: default
-#### A masked pattern was here ####
-Retention: 0
-#### A masked pattern was here ####
-Table Type: MANAGED_TABLE
-Table Parameters:
- COLUMN_STATS_ACCURATE true
- numFiles 4
- numRows 500
- rawDataSize 4812
- totalSize 5522
-#### A masked pattern was here ####
-
-# Storage Information
-SerDe Library: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
-InputFormat: org.apache.hadoop.hive.ql.io.RCFileInputFormat
-OutputFormat: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
-Compressed: No
-Num Buckets: -1
-Bucket Columns: []
-Sort Columns: []
-Stored As SubDirectories: Yes
-Skewed Columns: [c1, c2]
-Skewed Values: [[466, val_466], [287, val_287], [82, val_82]]
-#### A masked pattern was here ####
-Skewed Value to Truncated Path: {[466, val_466]=/stats_list_bucket_1/c1=466/c2=val_466, [82, val_82]=/stats_list_bucket_1/c1=82/c2=val_82, [287, val_287]=/stats_list_bucket_1/c1=287/c2=val_287}
-Storage Desc Params:
- serialization.format 1
-PREHOOK: query: drop table stats_list_bucket
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@stats_list_bucket
-PREHOOK: Output: default@stats_list_bucket
-POSTHOOK: query: drop table stats_list_bucket
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@stats_list_bucket
-POSTHOOK: Output: default@stats_list_bucket
-PREHOOK: query: drop table stats_list_bucket_1
-PREHOOK: type: DROPTABLE
-PREHOOK: Input: default@stats_list_bucket_1
-PREHOOK: Output: default@stats_list_bucket_1
-POSTHOOK: query: drop table stats_list_bucket_1
-POSTHOOK: type: DROPTABLE
-POSTHOOK: Input: default@stats_list_bucket_1
-POSTHOOK: Output: default@stats_list_bucket_1