You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by kg...@apache.org on 2019/01/23 16:38:43 UTC
[11/51] [partial] hive git commit: HIVE-17084: Turn on
hive.stats.fetch.column.stats configuration flag (Zoltan Haindrich reviewed
by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_position.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_position.q.out b/ql/src/test/results/clientpositive/groupby_position.q.out
index e9d9fdb..296279a 100644
--- a/ql/src/test/results/clientpositive/groupby_position.q.out
+++ b/ql/src/test/results/clientpositive/groupby_position.q.out
@@ -46,30 +46,30 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 20) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT substr(value, 5))
keys: key (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 20) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT substr(value, 5))
keys: key (type: string), value (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -82,14 +82,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -98,12 +98,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -135,7 +135,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -143,10 +143,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -168,7 +168,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -176,14 +176,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -192,12 +192,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -221,7 +221,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
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>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -229,10 +229,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -331,30 +331,30 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 20) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT substr(value, 5))
keys: key (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 20) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT substr(value, 5))
keys: value (type: string), key (type: string), substr(value, 5) (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -367,14 +367,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col0) (type: int), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -383,12 +383,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15604 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -420,7 +420,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 872 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
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>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -428,10 +428,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 888 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -453,7 +453,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 30710 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -461,14 +461,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(_col1) (type: int), _col0 (type: string), CAST( _col2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -477,12 +477,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
outputColumnNames: key, val1, val2
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(val1, 'hll'), compute_stats(val2, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -506,7 +506,7 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
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>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
@@ -514,10 +514,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -610,21 +610,21 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (UDFToDouble(key) <= 20.0D) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) <= 20.0D) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -633,7 +633,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -648,16 +648,16 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col1 (type: bigint), _col0 (type: string)
sort order: -+
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 7885 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -745,27 +745,27 @@ STAGE PLANS:
TableScan
alias: src1
filterExpr: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -781,14 +781,14 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
@@ -798,7 +798,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -813,16 +813,16 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
sort order: --++
- Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 29 Data size: 314 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 9612 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -834,27 +834,27 @@ STAGE PLANS:
TableScan
alias: src2
filterExpr: ((UDFToDouble(key) > 15.0D) and (UDFToDouble(key) < 20.0D)) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 20.0D) and (UDFToDouble(key) > 15.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string), value (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 4806 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -925,24 +925,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1483,28 +1483,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
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
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
table:
@@ -1519,16 +1519,16 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_ppd.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_ppd.q.out b/ql/src/test/results/clientpositive/groupby_ppd.q.out
index 7103623..f9a1ec6 100644
--- a/ql/src/test/results/clientpositive/groupby_ppd.q.out
+++ b/ql/src/test/results/clientpositive/groupby_ppd.q.out
@@ -25,62 +25,62 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: (bar = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (bar = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: foo (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Union
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: d
filterExpr: (bar = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (bar = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: foo (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Union
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), 1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_ppr.q.out b/ql/src/test/results/clientpositive/groupby_ppr.q.out
index cfd03a4..e9c20af 100644
--- a/ql/src/test/results/clientpositive/groupby_ppr.q.out
+++ b/ql/src/test/results/clientpositive/groupby_ppr.q.out
@@ -41,18 +41,18 @@ STAGE PLANS:
TableScan
alias: src
filterExpr: (ds = '2008-04-08') (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: false
Execution mode: vectorized
@@ -167,17 +167,17 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -208,7 +208,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
outputColumnNames: key, c1, c2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
@@ -275,7 +275,7 @@ STAGE PLANS:
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: key (type: string), c1 (type: int), c2 (type: string)
auto parallelism: false
@@ -313,13 +313,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
index 028f7b5..2885282 100644
--- a/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
+++ b/ql/src/test/results/clientpositive/groupby_ppr_multi_distinct.q.out
@@ -41,18 +41,18 @@ STAGE PLANS:
TableScan
alias: src
filterExpr: (ds = '2008-04-08') (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
null sort order: aaa
sort order: +++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: false
Execution mode: vectorized
@@ -167,17 +167,17 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 68256 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -208,7 +208,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int)
outputColumnNames: key, c1, c2, c3, c4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
@@ -275,7 +275,7 @@ STAGE PLANS:
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 120080 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int)
auto parallelism: false
@@ -313,13 +313,13 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -415,18 +415,18 @@ STAGE PLANS:
TableScan
alias: src
filterExpr: (ds = '2008-04-08') (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Select Operator
expressions: substr(key, 1, 1) (type: string), substr(value, 5) (type: string), value (type: string)
outputColumnNames: $f0, $f1, $f2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 459000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: $f0 (type: string), $f1 (type: string), $f2 (type: string)
null sort order: aaa
sort order: +++
Map-reduce partition columns: $f0 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 459000 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: false
Execution mode: vectorized
@@ -541,17 +541,17 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: $f0, $f1, $f2, $f3, $f4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: $f0 (type: string), UDFToInteger($f1) (type: int), concat($f0, $f2) (type: string), UDFToInteger($f3) (type: int), UDFToInteger($f4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -582,7 +582,7 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int)
outputColumnNames: key, c1, c2, c3, c4
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
@@ -649,7 +649,7 @@ STAGE PLANS:
Reduce Output Operator
null sort order:
sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 196 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: key (type: string), c1 (type: int), c2 (type: string), c3 (type: int), c4 (type: int)
auto parallelism: false
@@ -687,17 +687,17 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll'), compute_stats(VALUE._col4, 'hll'), compute_stats(VALUE._col5, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _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>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 2232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2200 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_rollup1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_rollup1.q.out b/ql/src/test/results/clientpositive/groupby_rollup1.q.out
index 54e312e..0685ae9 100644
--- a/ql/src/test/results/clientpositive/groupby_rollup1.q.out
+++ b/ql/src/test/results/clientpositive/groupby_rollup1.q.out
@@ -34,22 +34,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n91
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: key (type: string), val (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -57,15 +57,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -117,37 +117,37 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n91
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(DISTINCT val)
keys: key (type: string), 0L (type: bigint), val (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col2 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -194,22 +194,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n91
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
keys: key (type: string), val (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -217,7 +217,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -233,7 +233,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -241,15 +241,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -302,29 +302,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n91
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(DISTINCT val)
keys: key (type: string), 0L (type: bigint), val (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -340,7 +340,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: bigint)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -348,15 +348,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: final
outputColumnNames: _col0, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col2 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -432,33 +432,33 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n91
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
keys: key (type: string), val (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: key, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(1)
keys: key (type: string), val (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -471,7 +471,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -487,7 +487,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -495,15 +495,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -512,12 +512,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
outputColumnNames: key1, key2, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -549,17 +549,17 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1680 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>), _col2 (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), compute_stats(VALUE._col2)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -581,7 +581,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: rand() (type: double)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -589,7 +589,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -605,7 +605,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 3 Data size: 900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reduce Operator Tree:
Group By Operator
@@ -613,15 +613,15 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -630,12 +630,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
outputColumnNames: key1, key2, val
- Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: compute_stats(key1, 'hll'), compute_stats(key2, 'hll'), compute_stats(val, 'hll')
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1680 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -659,17 +659,17 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1680 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>), _col2 (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), compute_stats(VALUE._col2)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 1696 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/268a6e5a/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out b/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out
index 3c27a81..5eac74e 100644
--- a/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out
+++ b/ql/src/test/results/clientpositive/groupby_rollup_empty.q.out
@@ -164,25 +164,25 @@ STAGE PLANS:
TableScan
alias: tx2_n1
filterExpr: (a < 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (a < 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: int), b (type: int), c (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
- Statistics: Num rows: 3 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
@@ -191,14 +191,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col3 (type: bigint), grouping(_col2, 0) (type: bigint), 'NULL,1' (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat