You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2017/12/12 00:00:35 UTC
[37/51] [partial] hive git commit: HIVE-13567 : Enable auto-gather
column stats by default (Zoltan Haindrich,
Pengcheng Xiong via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out
index 1723e75..ffe6515 100644
--- a/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out
+++ b/ql/src/test/results/clientpositive/groupby_sort_test_1.q.out
@@ -81,6 +81,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.outputtbl1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int)
+ outputColumnNames: key, cnt
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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-7
Conditional Operator
@@ -104,6 +130,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, cnt
+ Column Types: int, int
+ Table: default.outputtbl1
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out b/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out
index 1fa9e94..a515847 100644
--- a/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out
+++ b/ql/src/test/results/clientpositive/implicit_cast_during_insert.q.out
@@ -56,6 +56,27 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.implicit_cast_during_insert
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: c1, c2, p1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll')
+ keys: p1 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 125 Data size: 1328 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
Move Operator
@@ -72,6 +93,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: c1, c2
+ Column Types: int, string
+ Table: default.implicit_cast_during_insert
PREHOOK: query: insert overwrite table implicit_cast_during_insert partition (p1)
select key, value, key key1 from (select * from src where key in (0,1)) q
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/index_auto_update.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/index_auto_update.q.out b/ql/src/test/results/clientpositive/index_auto_update.q.out
index bc444cc..e48b657 100644
--- a/ql/src/test/results/clientpositive/index_auto_update.q.out
+++ b/ql/src/test/results/clientpositive/index_auto_update.q.out
@@ -45,10 +45,10 @@ STAGE DEPENDENCIES:
Stage-0 depends on stages: Stage-9, Stage-8, Stage-11
Stage-2 depends on stages: Stage-0
Stage-1 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-1, Stage-4, Stage-5
Stage-4 depends on stages: Stage-2
+ Stage-7 depends on stages: Stage-0, Stage-4, Stage-5
Stage-5 depends on stages: Stage-2
- Stage-7 depends on stages: Stage-0
Stage-8
Stage-10
Stage-11 depends on stages: Stage-10
@@ -72,6 +72,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.temp
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, val
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(val, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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-12
Conditional Operator
@@ -140,11 +166,15 @@ STAGE PLANS:
Stage: Stage-4
- Stage: Stage-5
-
Stage: Stage-7
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, val
+ Column Types: string, string
+ Table: default.temp
+
+ Stage: Stage-5
Stage: Stage-8
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort.q.out
index 8ed1054..fee672b 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort.q.out
@@ -38,7 +38,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -87,7 +87,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -136,7 +136,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -185,7 +185,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -234,7 +234,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 4970
@@ -283,7 +283,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 2654
rawDataSize 28466
@@ -332,7 +332,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 2654
rawDataSize 28466
@@ -381,7 +381,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -430,7 +430,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -479,7 +479,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -528,7 +528,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -577,7 +577,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -626,7 +626,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -675,7 +675,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -724,7 +724,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -773,7 +773,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -822,7 +822,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 18
@@ -871,7 +871,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 6
rawDataSize 18
@@ -920,7 +920,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 618
rawDataSize 2964
@@ -969,7 +969,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 5
rawDataSize 19
@@ -1018,7 +1018,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -1067,7 +1067,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -1116,7 +1116,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -1165,7 +1165,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -1214,7 +1214,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 3582
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
index cba50a7..32e4513 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_dyn_part.q.out
@@ -56,7 +56,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 4812
@@ -94,7 +94,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 4812
@@ -155,7 +155,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1173
@@ -193,7 +193,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1173
@@ -256,7 +256,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 155
rawDataSize 586
@@ -294,7 +294,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 154
rawDataSize 591
@@ -415,10 +415,11 @@ STAGE DEPENDENCIES:
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-2 depends on stages: Stage-0, Stage-8
Stage-3
Stage-5
Stage-6 depends on stages: Stage-5
+ Stage-8 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -462,6 +463,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.test_table
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string)
+ outputColumnNames: key, value, ds, hr
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string), hr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 58 Data size: 5812 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-7
Conditional Operator
@@ -488,6 +505,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.test_table
Stage: Stage-3
Merge File Operator
@@ -509,6 +530,35 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ 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: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 29 Data size: 2906 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
+
PREHOOK: query: INSERT OVERWRITE TABLE test_table PARTITION (ds = '2008-04-08', hr)
SELECT key, value, IF (key % 100 == 0, '11', '12') FROM
(SELECT key, COUNT(*) AS value FROM srcpart
@@ -555,7 +605,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 4
rawDataSize 14
@@ -593,7 +643,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 305
rawDataSize 1163
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out
index 8ae7320..5f1d264 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out
@@ -23,7 +23,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -68,6 +69,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string)
+ outputColumnNames: key, value, agg, part
+ Statistics: Num rows: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll')
+ keys: part (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 750 Data size: 7968 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
Move Operator
@@ -84,6 +101,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, agg
+ Column Types: string, string, string
+ Table: default.test_table_out
+
+ 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: 750 Data size: 7968 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 375 Data size: 3984 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
PREHOOK: query: SELECT key, value, count(1) FROM src GROUP BY ROLLUP (key, value)
PREHOOK: type: QUERY
@@ -746,7 +796,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 619
rawDataSize 6309
@@ -1426,7 +1476,7 @@ Database: default
Table: test_table_out_2
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"grouping_key\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 619
rawDataSize 7547
@@ -1452,7 +1502,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1497,6 +1548,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string)
+ outputColumnNames: key, value, agg, part
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll')
+ keys: part (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1000 Data size: 10624 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
Move Operator
@@ -1513,6 +1580,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, agg
+ Column Types: string, string, string
+ Table: default.test_table_out
+
+ 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 500 Data size: 5312 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
PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1')
SELECT key, value, count(1) FROM src GROUP BY key, value WITH CUBE
@@ -1548,7 +1648,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 928
rawDataSize 9954
@@ -1601,7 +1701,7 @@ Database: default
Table: test_table_out_2
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"grouping_key\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 928
rawDataSize 11810
@@ -1627,7 +1727,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1672,6 +1773,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), '1' (type: string)
+ outputColumnNames: key, value, agg, part
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(agg, 'hll')
+ keys: part (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 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
Move Operator
@@ -1688,6 +1805,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, agg
+ Column Types: string, string, string
+ Table: default.test_table_out
+
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (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
+ Statistics: Num rows: 250 Data size: 2656 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
PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1')
SELECT key, value, count(1) FROM src GROUP BY key, value GROUPING SETS (key, value)
@@ -1723,7 +1873,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 618
rawDataSize 6054
@@ -1776,7 +1926,7 @@ Database: default
Table: test_table_out_2
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"agg\":\"true\",\"grouping_key\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 618
rawDataSize 7290
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out
index 98c062b..c701de9 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_list_bucket.q.out
@@ -44,7 +44,7 @@ Database: default
Table: list_bucketing_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 309
rawDataSize 1482
@@ -112,7 +112,7 @@ Database: default
Table: list_bucketing_table2
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
index f2218e3..0711eb5 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out
@@ -91,6 +91,40 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, part
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: part (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 125 Data size: 1328 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-7
Conditional Operator
@@ -116,6 +150,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.test_table_out
Stage: Stage-3
Map Reduce
@@ -179,7 +217,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 1482
@@ -216,7 +254,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -280,6 +319,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, part
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: part (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ 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-0
Move Operator
@@ -296,6 +351,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.test_table_out
+
+ 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: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 137 Data size: 1455 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
PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1')
SELECT a.key, a.value FROM (
@@ -341,7 +429,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 0
rawDataSize 0
@@ -401,6 +489,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: '1' (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions: '1' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1' (type: string)
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: '1' (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '1' (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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.lazy.LazySimpleSerDe
Stage: Stage-8
Conditional Operator
@@ -426,6 +542,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.test_table_out
Stage: Stage-4
Map Reduce
@@ -491,7 +611,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -519,7 +639,8 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -564,6 +685,20 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table_out
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: '1' (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ 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
Move Operator
@@ -580,6 +715,35 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.test_table_out
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: '1' (type: string)
+ sort order: +
+ Map-reduce partition columns: '1' (type: string)
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: '1' (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '1' (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE test_table_out PARTITION (part = '1')
SELECT /*+ MAPJOIN(a) */ b.value, count(*) FROM test_table1 a JOIN test_table2 b ON a.key = b.key
@@ -617,7 +781,7 @@ Database: default
Table: test_table_out
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 2728
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_merge.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_merge.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_merge.q.out
index 44a9435..694d15c 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_merge.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_merge.q.out
@@ -38,7 +38,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 1028
rawDataSize 10968
@@ -87,7 +87,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 1028
rawDataSize 10968
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_multi_insert.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_multi_insert.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_multi_insert.q.out
index d915c30..a10c06e 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_multi_insert.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_multi_insert.q.out
@@ -81,7 +81,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"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 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 2718
@@ -265,7 +265,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -357,7 +357,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 309
rawDataSize 2690
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
index 5c7659b..cf332e2 100644
--- a/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
+++ b/ql/src/test/results/clientpositive/infer_bucket_sort_num_buckets.q.out
@@ -25,7 +25,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -56,6 +57,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.test_table
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), UDFToString(_col2) (type: string)
+ outputColumnNames: key, value, hr
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: '2008-04-08' (type: string), hr (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 58 Data size: 11624 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
Move Operator
@@ -73,6 +90,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.test_table
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: '2008-04-08' (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: '2008-04-08' (type: string), _col1 (type: string)
+ Statistics: Num rows: 58 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ keys: '2008-04-08' (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-04-08' (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 29 Data size: 5812 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
PREHOOK: query: INSERT OVERWRITE TABLE test_table PARTITION (ds = '2008-04-08', hr)
SELECT key2, value, cast(hr as int) FROM
@@ -122,7 +172,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 2
numRows 670
rawDataSize 5888
@@ -160,7 +210,7 @@ Database: default
Table: test_table
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 1
numRows 330
rawDataSize 2924
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/innerjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/innerjoin.q.out b/ql/src/test/results/clientpositive/innerjoin.q.out
index 741c9fb..138eb93 100644
--- a/ql/src/test/results/clientpositive/innerjoin.q.out
+++ b/ql/src/test/results/clientpositive/innerjoin.q.out
@@ -17,7 +17,8 @@ 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-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -75,6 +76,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 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
Move Operator
@@ -89,6 +105,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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
PREHOOK: query: FROM src src1 INNER JOIN src src2 ON (src1.key = src2.key)
INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/input11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input11.q.out b/ql/src/test/results/clientpositive/input11.q.out
index 356cef1..bb59b4f 100644
--- a/ql/src/test/results/clientpositive/input11.q.out
+++ b/ql/src/test/results/clientpositive/input11.q.out
@@ -46,6 +46,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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-7
Conditional Operator
@@ -69,6 +95,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/input12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input12.q.out b/ql/src/test/results/clientpositive/input12.q.out
index 8bb52c0..8096c71 100644
--- a/ql/src/test/results/clientpositive/input12.q.out
+++ b/ql/src/test/results/clientpositive/input12.q.out
@@ -39,24 +39,16 @@ STAGE DEPENDENCIES:
Stage-9 depends on stages: Stage-3 , consists of Stage-6, Stage-5, Stage-7
Stage-6
Stage-0 depends on stages: Stage-6, Stage-5, Stage-8
- Stage-4 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-11, Stage-13
Stage-5
Stage-7
Stage-8 depends on stages: Stage-7
- Stage-15 depends on stages: Stage-3 , consists of Stage-12, Stage-11, Stage-13
- Stage-12
- Stage-1 depends on stages: Stage-12, Stage-11, Stage-14
- Stage-10 depends on stages: Stage-1
- Stage-11
- Stage-13
- Stage-14 depends on stages: Stage-13
- Stage-21 depends on stages: Stage-3 , consists of Stage-18, Stage-17, Stage-19
- Stage-18
- Stage-2 depends on stages: Stage-18, Stage-17, Stage-20
- Stage-16 depends on stages: Stage-2
- Stage-17
- Stage-19
- Stage-20 depends on stages: Stage-19
+ Stage-1 depends on stages: Stage-3
+ Stage-10 depends on stages: Stage-1, Stage-11, Stage-13
+ Stage-11 depends on stages: Stage-3
+ Stage-12 depends on stages: Stage-2, Stage-11, Stage-13
+ Stage-2 depends on stages: Stage-3
+ Stage-13 depends on stages: Stage-3
STAGE PLANS:
Stage: Stage-3
@@ -80,6 +72,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Filter Operator
predicate: ((key < 200) and (key >= 100)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
@@ -95,6 +100,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 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
Filter Operator
predicate: (key >= 200) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
@@ -110,6 +130,35 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest3
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: key
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll')
+ keys: '2008-04-08' (type: string), '12' (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 166 Data size: 1763 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
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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-9
Conditional Operator
@@ -133,6 +182,10 @@ STAGE PLANS:
Stage: Stage-4
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1
Stage: Stage-5
Map Reduce
@@ -164,15 +217,6 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-15
- Conditional Operator
-
- Stage: Stage-12
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
Stage: Stage-1
Move Operator
tables:
@@ -186,45 +230,40 @@ STAGE PLANS:
Stage: Stage-10
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest2
Stage: Stage-11
Map Reduce
Map Operator Tree:
TableScan
- File Output Operator
- compressed: 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.dest2
-
- Stage: Stage-13
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: 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.dest2
-
- Stage: Stage-14
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
-
- Stage: Stage-21
- Conditional Operator
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 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-18
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
+ Stage: Stage-12
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key
+ Column Types: int
+ Table: default.dest3
Stage: Stage-2
Move Operator
@@ -239,39 +278,34 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest3
- Stage: Stage-16
- Stats Work
- Basic Stats Work:
-
- Stage: Stage-17
- Map Reduce
- Map Operator Tree:
- TableScan
- File Output Operator
- compressed: 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.dest3
-
- Stage: Stage-19
+ Stage: Stage-13
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: '2008-04-08' (type: string), '12' (type: string)
+ sort order: ++
+ Map-reduce partition columns: '2008-04-08' (type: string), '12' (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ keys: '2008-04-08' (type: string), '12' (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-04-08' (type: string), '12' (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 83 Data size: 881 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
- name: default.dest3
-
- Stage: Stage-20
- Move Operator
- files:
- hdfs directory: true
-#### A masked pattern was here ####
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest1 SELECT src.* WHERE src.key < 100