You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/27 20:57:03 UTC
svn commit: r1634671 [24/46] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_distinct.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,528 @@
+PREHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: partials
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+val_0
+val_10
+val_100
+val_103
+val_104
+val_105
+val_11
+val_111
+val_113
+val_114
+PREHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+val_0
+val_10
+val_100
+val_103
+val_104
+val_105
+val_11
+val_111
+val_113
+val_114
+PREHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: partial1
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+val_0
+val_10
+val_100
+val_103
+val_104
+val_105
+val_11
+val_111
+val_113
+val_114
+PREHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+POSTHOOK: query: FROM srcpart c
+JOIN srcpart d
+ON ( c.key=d.key AND c.ds='2008-04-08' AND d.ds='2008-04-08')
+SELECT /*+ MAPJOIN(d) */ DISTINCT c.value as value order by value limit 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+#### A masked pattern was here ####
+val_0
+val_10
+val_100
+val_103
+val_104
+val_105
+val_11
+val_111
+val_113
+val_114
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_filter_on_outerjoin.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_filter_on_outerjoin.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_filter_on_outerjoin.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_filter_on_outerjoin.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,340 @@
+PREHOOK: query: --HIVE-2101 mapjoin sometimes gives wrong results if there is a filter in the on condition
+
+SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: --HIVE-2101 mapjoin sometimes gives wrong results if there is a filter in the on condition
+
+SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 146 val_146 146 val_146
+NULL NULL 146 val_146 146 val_146
+NULL NULL 150 val_150 150 val_150
+NULL NULL 213 val_213 213 val_213
+NULL NULL 213 val_213 213 val_213
+NULL NULL 224 224 val_224
+NULL NULL 224 224 val_224
+NULL NULL 238 val_238 238 val_238
+NULL NULL 238 val_238 238 val_238
+NULL NULL 255 val_255 255 val_255
+NULL NULL 255 val_255 255 val_255
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 278 val_278 278 val_278
+NULL NULL 278 val_278 278 val_278
+NULL NULL 66 val_66 66 val_66
+NULL NULL 98 val_98 98 val_98
+NULL NULL 98 val_98 98 val_98
+PREHOOK: query: explain
+SELECT /*+ mapjoin(src1, src2) */ * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT /*+ mapjoin(src1, src2) */ * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 300) (type: boolean)
+ Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 300) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 300) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ filter predicates:
+ 0
+ 1 {(KEY.reducesinkkey0 > 10)}
+ 2
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string)
+ sort order: +++
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 365 Data size: 3878 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT /*+ mapjoin(src1, src2) */ * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT /*+ mapjoin(src1, src2) */ * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 146 val_146 146 val_146
+NULL NULL 146 val_146 146 val_146
+NULL NULL 150 val_150 150 val_150
+NULL NULL 213 val_213 213 val_213
+NULL NULL 213 val_213 213 val_213
+NULL NULL 224 224 val_224
+NULL NULL 224 224 val_224
+NULL NULL 238 val_238 238 val_238
+NULL NULL 238 val_238 238 val_238
+NULL NULL 255 val_255 255 val_255
+NULL NULL 255 val_255 255 val_255
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 278 val_278 278 val_278
+NULL NULL 278 val_278 278 val_278
+NULL NULL 66 val_66 66 val_66
+NULL NULL 98 val_98 98 val_98
+NULL NULL 98 val_98 98 val_98
+PREHOOK: query: explain
+SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 300) (type: boolean)
+ Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key < 300) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 300) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ filter predicates:
+ 0
+ 1 {(KEY.reducesinkkey0 > 10)}
+ 2
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string)
+ sort order: +++
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col3 (type: string), _col5 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 365 Data size: 3878 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM src1
+ RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10)
+ JOIN src src3 ON (src2.key = src3.key AND src3.key < 300)
+ SORT BY src1.key, src2.key, src3.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 128 128 val_128
+NULL NULL 146 val_146 146 val_146
+NULL NULL 146 val_146 146 val_146
+NULL NULL 150 val_150 150 val_150
+NULL NULL 213 val_213 213 val_213
+NULL NULL 213 val_213 213 val_213
+NULL NULL 224 224 val_224
+NULL NULL 224 224 val_224
+NULL NULL 238 val_238 238 val_238
+NULL NULL 238 val_238 238 val_238
+NULL NULL 255 val_255 255 val_255
+NULL NULL 255 val_255 255 val_255
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 273 val_273 273 val_273
+NULL NULL 278 val_278 278 val_278
+NULL NULL 278 val_278 278 val_278
+NULL NULL 66 val_66 66 val_66
+NULL NULL 98 val_98 98 val_98
+NULL NULL 98 val_98 98 val_98
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_hook.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_hook.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_hook.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_hook.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,59 @@
+PREHOOK: query: drop table dest1
+PREHOOK: type: DROPTABLE
+RUN: Stage-0:DDL
+PREHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+RUN: Stage-0:DDL
+PREHOOK: query: INSERT OVERWRITE TABLE dest1
+SELECT /*+ MAPJOIN(x) */ x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@dest1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[MapJoinCounter PostHook] COMMON_JOIN: 0 HINTED_MAPJOIN: 0 HINTED_MAPJOIN_LOCAL: 0 CONVERTED_MAPJOIN: 0 CONVERTED_MAPJOIN_LOCAL: 0 BACKUP_COMMON_JOIN: 0
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key = src3.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.key, src3.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[MapJoinCounter PostHook] COMMON_JOIN: 0 HINTED_MAPJOIN: 0 HINTED_MAPJOIN_LOCAL: 0 CONVERTED_MAPJOIN: 0 CONVERTED_MAPJOIN_LOCAL: 0 BACKUP_COMMON_JOIN: 0
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: FROM srcpart src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.key, src2.value
+where (src1.ds = '2008-04-08' or src1.ds = '2008-04-09' )and (src1.hr = '12' or src1.hr = '11')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+PREHOOK: Output: default@dest1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[MapJoinCounter PostHook] COMMON_JOIN: 0 HINTED_MAPJOIN: 0 HINTED_MAPJOIN_LOCAL: 0 CONVERTED_MAPJOIN: 0 CONVERTED_MAPJOIN_LOCAL: 0 BACKUP_COMMON_JOIN: 0
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.key, src3.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest1
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[MapJoinCounter PostHook] COMMON_JOIN: 0 HINTED_MAPJOIN: 0 HINTED_MAPJOIN_LOCAL: 0 CONVERTED_MAPJOIN: 0 CONVERTED_MAPJOIN_LOCAL: 0 BACKUP_COMMON_JOIN: 0
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out?rev=1634671&view=auto
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out (added) and hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out Mon Oct 27 19:56:58 2014 differ
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,138 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+create table src0 like src
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@src0
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+create table src0 like src
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@src0
+PREHOOK: query: insert into table src0 select * from src where src.key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@src0
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert into table src0 select * from src where src.key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@src0
+POSTHOOK: Lineage: src0.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: src0.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: explain
+select src1.key as k1, src1.value as v1, src2.key, src2.value
+from src0 src1 inner join src0 src2 on src1.key = src2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select src1.key as k1, src1.value as v1, src2.key, src2.value
+from src0 src1 inner join src0 src2 on src1.key = src2.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 0 Data size: 80 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 0 Data size: 80 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select src1.key as k1, src1.value as v1, src2.key, src2.value
+from src0 src1 inner join src0 src2 on src1.key = src2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src0
+#### A masked pattern was here ####
+POSTHOOK: query: select src1.key as k1, src1.value as v1, src2.key, src2.value
+from src0 src1 inner join src0 src2 on src1.key = src2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src0
+#### A masked pattern was here ####
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+0 val_0 0 val_0
+2 val_2 2 val_2
+4 val_4 4 val_4
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+5 val_5 5 val_5
+8 val_8 8 val_8
+9 val_9 9 val_9
+PREHOOK: query: drop table src0
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@src0
+PREHOOK: Output: default@src0
+POSTHOOK: query: drop table src0
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@src0
+POSTHOOK: Output: default@src0
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,490 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+-- Since the inputs are small, it should be automatically converted to mapjoin
+
+EXPLAIN
+SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+-- Since the inputs are small, it should be automatically converted to mapjoin
+
+EXPLAIN
+SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: z
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col5
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+146 val_146
+146 val_146
+146 val_146
+146 val_146
+150 val_150
+213 val_213
+213 val_213
+213 val_213
+213 val_213
+224 val_224
+224 val_224
+224 val_224
+224 val_224
+238 val_238
+238 val_238
+238 val_238
+238 val_238
+255 val_255
+255 val_255
+255 val_255
+255 val_255
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+278 val_278
+278 val_278
+278 val_278
+278 val_278
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+66 val_66
+98 val_98
+98 val_98
+98 val_98
+98 val_98
+PREHOOK: query: EXPLAIN
+SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: z
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col5
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Input: default@srcpart
+PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT subq.key1, z.value
+FROM
+(SELECT x.key as key1, x.value as value1, y.key as key2, y.value as value2
+ FROM src1 x JOIN src y ON (x.key = y.key)) subq
+ JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+#### A masked pattern was here ####
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+128 val_128
+146 val_146
+146 val_146
+146 val_146
+146 val_146
+150 val_150
+213 val_213
+213 val_213
+213 val_213
+213 val_213
+224 val_224
+224 val_224
+224 val_224
+224 val_224
+238 val_238
+238 val_238
+238 val_238
+238 val_238
+255 val_255
+255 val_255
+255 val_255
+255 val_255
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+278 val_278
+278 val_278
+278 val_278
+278 val_278
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+401 val_401
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+406 val_406
+66 val_66
+98 val_98
+98 val_98
+98 val_98
+98 val_98
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,232 @@
+PREHOOK: query: drop table x
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table x
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table y
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table y
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table z
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table z
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: CREATE TABLE x (name STRING, id INT)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@x
+POSTHOOK: query: CREATE TABLE x (name STRING, id INT)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@x
+PREHOOK: query: CREATE TABLE y (id INT, name STRING)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@y
+POSTHOOK: query: CREATE TABLE y (id INT, name STRING)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@y
+PREHOOK: query: CREATE TABLE z (id INT, name STRING)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@z
+POSTHOOK: query: CREATE TABLE z (id INT, name STRING)
+ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@z
+PREHOOK: query: load data local inpath '../../data/files/x.txt' INTO TABLE x
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@x
+POSTHOOK: query: load data local inpath '../../data/files/x.txt' INTO TABLE x
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@x
+PREHOOK: query: load data local inpath '../../data/files/y.txt' INTO TABLE y
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@y
+POSTHOOK: query: load data local inpath '../../data/files/y.txt' INTO TABLE y
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@y
+PREHOOK: query: load data local inpath '../../data/files/z.txt' INTO TABLE z
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@z
+POSTHOOK: query: load data local inpath '../../data/files/z.txt' INTO TABLE z
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@z
+PREHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin
+
+EXPLAIN
+SELECT subq.key1, subq.value1, subq.key2, subq.value2, z.id, z.name
+FROM
+(SELECT x.id as key1, x.name as value1, y.id as key2, y.name as value2
+ FROM y JOIN x ON (x.id = y.id)) subq
+ JOIN z ON (subq.key1 = z.id)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin
+
+EXPLAIN
+SELECT subq.key1, subq.value1, subq.key2, subq.value2, z.id, z.name
+FROM
+(SELECT x.id as key1, x.name as value1, y.id as key2, y.name as value2
+ FROM y JOIN x ON (x.id = y.id)) subq
+ JOIN z ON (subq.key1 = z.id)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 0 Data size: 13 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: id (type: int)
+ sort order: +
+ Map-reduce partition columns: id (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: name (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 0 Data size: 6 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: id (type: int)
+ sort order: +
+ Map-reduce partition columns: id (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: name (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: z
+ Statistics: Num rows: 0 Data size: 6 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: id is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: id (type: int)
+ sort order: +
+ Map-reduce partition columns: id (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: name (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0} {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int), _col5 (type: string), _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT subq.key1, subq.value1, subq.key2, subq.value2, z.id, z.name
+FROM
+(SELECT x.id as key1, x.name as value1, y.id as key2, y.name as value2
+ FROM y JOIN x ON (x.id = y.id)) subq
+ JOIN z ON (subq.key1 = z.id)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@x
+PREHOOK: Input: default@y
+PREHOOK: Input: default@z
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT subq.key1, subq.value1, subq.key2, subq.value2, z.id, z.name
+FROM
+(SELECT x.id as key1, x.name as value1, y.id as key2, y.name as value2
+ FROM y JOIN x ON (x.id = y.id)) subq
+ JOIN z ON (subq.key1 = z.id)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@x
+POSTHOOK: Input: default@y
+POSTHOOK: Input: default@z
+#### A masked pattern was here ####
+2 Joe 2 Tie 2 Tie
+2 Hank 2 Tie 2 Tie
+PREHOOK: query: drop table x
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@x
+PREHOOK: Output: default@x
+POSTHOOK: query: drop table x
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@x
+POSTHOOK: Output: default@x
+PREHOOK: query: drop table y
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@y
+PREHOOK: Output: default@y
+POSTHOOK: query: drop table y
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@y
+POSTHOOK: Output: default@y
+PREHOOK: query: drop table z
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@z
+PREHOOK: Output: default@z
+POSTHOOK: query: drop table z
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@z
+POSTHOOK: Output: default@z