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 15:37:44 UTC
[23/48] hive git commit: HIVE-13549: Remove jdk version specific out
files from Hive2 (Mohit Sabharwal, reviewed by Sergio Pena)
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