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 2015/07/07 18:21:41 UTC
[4/9] hive git commit: HIVE-11171 : Join reordering algorithm might
introduce projects between joins (Jesus Camacho Rodriguez via Ashutosh
Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/spark/ppd_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join.q.out b/ql/src/test/results/clientpositive/spark/ppd_join.q.out
index b97431c..42a83f3 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join.q.out
@@ -37,33 +37,6 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 <> '4') (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -88,6 +61,33 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 > '1') and ((_col0 > '20') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -98,24 +98,20 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2
+ Filter Operator
+ predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean)
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean)
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -596,35 +592,35 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
+ Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 21 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
Map 3
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((((((key > '1') and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key < '400')) and (key > '2')) and (key <> '4')) and key is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((key > '2') and (key <> '4')) and (key > '1')) and (key > '20')) and (key < '400')) and key is not null) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 31 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: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -636,10 +632,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '50') or (_col2 < '50')) (type: boolean)
+ predicate: ((_col1 > '50') or (_col0 < '50')) (type: boolean)
Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string)
+ expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
index cf81423..a98ab13 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join2.q.out
@@ -71,26 +71,26 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean)
+ Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0 <> '14') (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 <> '311') and (((_col1 <> 'val_50') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
+ Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 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: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
@@ -98,26 +98,26 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean)
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '311') and (((_col1 <> 'val_50') or (_col0 > '1')) and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col0 <> '14') (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '305') and (_col0 <> '14')) (type: boolean)
- Statistics: Num rows: 24 Data size: 254 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 <> '302') and ((_col0 <> '311') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 148 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: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
@@ -150,26 +150,22 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ Filter Operator
+ predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col1 is not null (type: boolean)
+ Filter Operator
+ predicate: _col1 is not null (type: boolean)
+ Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 8 Data size: 86 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
+ value expressions: _col0 (type: string), _col3 (type: string)
Stage: Stage-0
Fetch Operator
@@ -1780,17 +1776,17 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean)
+ Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 594 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
@@ -1798,17 +1794,17 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean)
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((key <> '305') and (key <> '14')) and (key <> '302')) and (key <> '311')) and (key < '400')) and key is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 881 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: 56 Data size: 594 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
@@ -1842,10 +1838,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '10') or (_col2 <> '10')) (type: boolean)
+ predicate: ((_col2 <> '10') or (_col0 <> '10')) (type: boolean)
Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col3 (type: string), _col1 (type: string)
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
index d2343c4..9b5e0af 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_join3.q.out
@@ -70,33 +70,6 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 <> '4') (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 20 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: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 5
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -121,6 +94,33 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 <> '4') (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 <> '11') and ((_col0 > '0') and (_col0 < '400'))) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 20 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: 2 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -152,29 +152,25 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2
+ Filter Operator
+ predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col2
+ Filter Operator
+ predicate: ((_col0 <> '13') and (_col0 <> '1')) (type: boolean)
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 <> '13') and (_col0 <> '1')) (type: boolean)
- Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 22 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: 2 Data size: 22 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: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: string)
+ value expressions: _col2 (type: string)
Stage: Stage-0
Fetch Operator
@@ -1842,35 +1838,35 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
+ Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 37 Data size: 393 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
Map 5
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
- Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((((((((key <> '12') and (key <> '4')) and (key <> '11')) and (key > '0')) and (key < '400')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 297 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: 37 Data size: 393 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -1903,10 +1899,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 40 Data size: 432 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '10') or (_col2 <> '10')) (type: boolean)
+ predicate: ((_col1 > '10') or (_col0 <> '10')) (type: boolean)
Statistics: Num rows: 40 Data size: 432 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string)
+ expressions: _col0 (type: string), _col2 (type: string)
outputColumnNames: _col0, _col2
Statistics: Num rows: 40 Data size: 432 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out b/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out
index 2abca78..db5914c 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out
@@ -34,8 +34,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -44,14 +44,14 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean)
+ predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '10') and ((_col0 < '20') and ((_col0 > '15') and (_col0 < '25')))) (type: boolean)
+ predicate: ((_col0 > '15') and (_col0 < '25')) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
@@ -61,20 +61,21 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Map 3
+ value expressions: _col1 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
+ predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '15') and (_col0 < '25')) (type: boolean)
+ predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
@@ -91,14 +92,14 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
+ predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean)
+ predicate: ((_col0 > '10') and ((_col0 < '20') and ((_col0 > '15') and (_col0 < '25')))) (type: boolean)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: _col0 is not null (type: boolean)
@@ -108,7 +109,6 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -117,27 +117,6 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -152,6 +131,23 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -447,8 +443,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -457,24 +453,25 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean)
+ predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Map 3
+ value expressions: _col1 (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
+ predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -492,18 +489,17 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((((((key > '15') and (key < '25')) and (key > '10')) and (key < '20')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean)
+ predicate: ((((((sqrt(key) <> 13.0) and (key > '10')) and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 31 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: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -512,20 +508,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Reducer 3
Reduce Operator Tree:
Join Operator
condition map:
@@ -533,14 +524,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 34 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: 3 Data size: 34 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 3 Data size: 37 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 37 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
index 12f1abb..268d482 100644
--- a/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
+++ b/ql/src/test/results/clientpositive/spark/router_join_ppr.q.out
@@ -118,36 +118,33 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: b
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string), ds (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col1 (type: string), _col2 (type: string)
+ value expressions: _col1 (type: string)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -155,13 +152,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -171,29 +166,59 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [a]
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 222 Data size: 2358 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: 222 Data size: 2358 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=12
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
- hr 12
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -234,12 +259,12 @@ STAGE PLANS:
name: default.srcpart
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: hr=12
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-09
- hr 11
+ ds 2008-04-08
+ hr 12
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -280,12 +305,12 @@ STAGE PLANS:
name: default.srcpart
#### A masked pattern was here ####
Partition
- base file name: hr=12
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-09
- hr 12
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -324,41 +349,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- /srcpart/ds=2008-04-09/hr=11 [b]
- /srcpart/ds=2008-04-09/hr=12 [b]
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=12
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ hr 12
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -366,11 +364,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -380,71 +380,67 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [a]
+ /srcpart/ds=2008-04-08/hr=11 [b]
+ /srcpart/ds=2008-04-08/hr=12 [b]
+ /srcpart/ds=2008-04-09/hr=11 [b]
+ /srcpart/ds=2008-04-09/hr=12 [b]
Reducer 2
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Right Outer Join0 to 1
filter mappings:
- 0 [1, 1]
+ 1 [0, 1]
filter predicates:
- 0 {(VALUE._col1 = '2008-04-08')}
- 1
+ 0
+ 1 {(VALUE._col1 = '2008-04-08')}
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 244 Data size: 2593 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean)
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -999,22 +995,22 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: b
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
tag: 0
value expressions: _col1 (type: string)
auto parallelism: false
@@ -1023,12 +1019,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -1036,13 +1029,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -1052,29 +1043,59 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
+ Truncated Path -> Alias:
+ /src [a]
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 111 Data size: 1179 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=12
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
- hr 12
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -1113,39 +1134,14 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart
name: default.srcpart
- Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [b]
- /srcpart/ds=2008-04-08/hr=12 [b]
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) (type: boolean)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=12
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 12
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -1153,11 +1149,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -1167,66 +1165,60 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [a]
+ /srcpart/ds=2008-04-08/hr=11 [b]
+ /srcpart/ds=2008-04-08/hr=12 [b]
Reducer 2
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Right Outer Join0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: ((UDFToDouble(_col3) > 10.0) and (UDFToDouble(_col3) < 20.0)) (type: boolean)
+ predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) (type: boolean)
Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types string:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types string:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator