You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2018/06/27 02:05:35 UTC
[02/13] hive git commit: HIVE-19481 : Tablesample uses incorrect
logic to pick files corresponding to buckets. (Deepak Jaiswal,
reviewed by Sergey Shelukhin)
http://git-wip-us.apache.org/repos/asf/hive/blob/eaf416ea/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 36532d7..153f0fd 100644
--- a/ql/src/test/results/clientpositive/spark/sample6.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample6.q.out
@@ -78,7 +78,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000000_0
+ base file name: srcbucket
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -127,7 +127,7 @@ STAGE PLANS:
name: default.srcbucket
name: default.srcbucket
Truncated Path -> Alias:
- /srcbucket/000000_0 [s]
+ /srcbucket [s]
Stage: Stage-0
Move Operator
@@ -499,7 +499,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000001_0
+ base file name: srcbucket
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -548,7 +548,7 @@ STAGE PLANS:
name: default.srcbucket
name: default.srcbucket
Truncated Path -> Alias:
- /srcbucket/000001_0 [s]
+ /srcbucket [s]
Reducer 2
Execution mode: vectorized
Needs Tagging: false
@@ -913,7 +913,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000000_0
+ base file name: srcbucket
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -962,7 +962,7 @@ STAGE PLANS:
name: default.srcbucket
name: default.srcbucket
Truncated Path -> Alias:
- /srcbucket/000000_0 [s]
+ /srcbucket [s]
Reducer 2
Execution mode: vectorized
Needs Tagging: false
@@ -2528,57 +2528,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000000_0
- 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 4
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types int:string
-#### A masked pattern was here ####
- name default.srcbucket2
- numFiles 4
- numRows 500
- rawDataSize 5312
- serialization.ddl struct srcbucket2 { i32 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 4
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types int:string
-#### A masked pattern was here ####
- name default.srcbucket2
- numFiles 4
- numRows 500
- rawDataSize 5312
- serialization.ddl struct srcbucket2 { i32 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.srcbucket2
- name: default.srcbucket2
-#### A masked pattern was here ####
- Partition
- base file name: 000002_0
+ base file name: srcbucket2
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -2627,8 +2577,7 @@ STAGE PLANS:
name: default.srcbucket2
name: default.srcbucket2
Truncated Path -> Alias:
- /srcbucket2/000000_0 [s]
- /srcbucket2/000002_0 [s]
+ /srcbucket2 [s]
Reducer 2
Execution mode: vectorized
Needs Tagging: false
@@ -2964,7 +2913,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000001_0
+ base file name: srcbucket2
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -3013,7 +2962,7 @@ STAGE PLANS:
name: default.srcbucket2
name: default.srcbucket2
Truncated Path -> Alias:
- /srcbucket2/000001_0 [s]
+ /srcbucket2 [s]
Reducer 2
Execution mode: vectorized
Needs Tagging: false
@@ -3235,6 +3184,61 @@ STAGE PLANS:
tag: -1
auto parallelism: false
Execution mode: vectorized
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: empty_bucket
+ 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 2
+ bucket_field_name key
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.empty_bucket
+ numFiles 0
+ numRows 0
+ rawDataSize 0
+ serialization.ddl struct empty_bucket { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 0
+#### 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 2
+ bucket_field_name key
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.empty_bucket
+ numFiles 0
+ numRows 0
+ rawDataSize 0
+ serialization.ddl struct empty_bucket { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 0
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.empty_bucket
+ name: default.empty_bucket
+ Truncated Path -> Alias:
+ /empty_bucket [s]
Reducer 2
Execution mode: vectorized
Needs Tagging: false
http://git-wip-us.apache.org/repos/asf/hive/blob/eaf416ea/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 d0b52bc..d028e68 100644
--- a/ql/src/test/results/clientpositive/spark/sample7.q.out
+++ b/ql/src/test/results/clientpositive/spark/sample7.q.out
@@ -80,7 +80,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: 000000_0
+ base file name: srcbucket
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -129,7 +129,7 @@ STAGE PLANS:
name: default.srcbucket
name: default.srcbucket
Truncated Path -> Alias:
- /srcbucket/000000_0 [s]
+ /srcbucket [s]
Stage: Stage-0
Move Operator