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 [2/46] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,130 @@
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.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: src
+ 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
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ 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
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT src.* FROM src) x
+JOIN
+(SELECT src.* FROM src) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+103231310608
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,130 @@
+PREHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+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: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 100) 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: 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 100) 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)
+ outputColumnNames: _col0
+ 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+-101333194320
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,161 @@
+PREHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+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, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key < 100) and key is not null) and (key < 80)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((key < 80) and key is not null) and (key < 100)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 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 < 100) and key is not null) and (key < 80)) (type: boolean)
+ Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 27 Data size: 286 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: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ 2
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 59 Data size: 629 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 59 Data size: 629 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 = src3.c5 AND src3.c5 < 80
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+-136843922952
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,179 @@
+PREHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200
+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 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 100) 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: 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: 83 Data size: 881 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 < 100) 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)
+ outputColumnNames: _col0
+ 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key < 200) and UDFToDouble(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)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(_col0) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(_col0) (type: double)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 + _col2) is not null (type: boolean)
+ Statistics: Num rows: 46 Data size: 489 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: (_col0 + _col2) (type: double)
+ sort order: +
+ Map-reduce partition columns: (_col0 + _col2) (type: double)
+ Statistics: Num rows: 46 Data size: 489 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col3 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col3}
+ 1
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(src1.c1, src2.c4))
+FROM
+(SELECT src.key as c1, src.value as c2 from src) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src) src2
+ON src1.c1 = src2.c3 AND src1.c1 < 100
+JOIN
+(SELECT src.key as c5, src.value as c6 from src) src3
+ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+-97670109576
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,127 @@
+PREHOOK: query: -- EXCLUDE_HADOOP_MAJOR_VERSIONS(0.20, 0.20S)
+
+CREATE TABLE dest1(c1 INT, c2 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: -- EXCLUDE_HADOOP_MAJOR_VERSIONS(0.20, 0.20S)
+
+CREATE TABLE dest1(c1 INT, c2 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: explain
+FROM src JOIN srcpart ON src.key = srcpart.key AND srcpart.ds = '2008-04-08' and src.key > 100
+INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM src JOIN srcpart ON src.key = srcpart.key AND srcpart.ds = '2008-04-08' and src.key > 100
+INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+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: srcpart
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key > 100) and key is not null) (type: boolean)
+ Statistics: Num rows: 167 Data size: 1774 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: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (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 > 100) and key is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 183 Data size: 1951 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
+ name: default.dest1
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src JOIN srcpart ON src.key = srcpart.key AND srcpart.ds = '2008-04-08' and src.key > 100
+INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
+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: 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
+POSTHOOK: query: FROM src JOIN srcpart ON src.key = srcpart.key AND srcpart.ds = '2008-04-08' and src.key > 100
+INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.c2 SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2)) FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(dest1.c1,dest1.c2)) FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+404554174174
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,134 @@
+PREHOOK: query: explain
+select sum(hash(a.k1,a.v1,a.k2, a.v2))
+from (
+SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+SORT BY k1, v1, k2, v2
+) a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select sum(hash(a.k1,a.v1,a.k2, a.v2))
+from (
+SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+SORT BY k1, v1, k2, v2
+) a
+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: src2
+ 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)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ 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} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col1,_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 sum(hash(a.k1,a.v1,a.k2, a.v2))
+from (
+SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+SORT BY k1, v1, k2, v2
+) a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(hash(a.k1,a.v1,a.k2, a.v2))
+from (
+SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+SORT BY k1, v1, k2, v2
+) a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+524272996896
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,125 @@
+PREHOOK: query: explain
+SELECT sum(hash(subq.key, tab.value))
+FROM
+(select a.key, a.value from src a where a.key > 10 ) subq
+JOIN src tab
+ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value)
+where tab.value < 200
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT sum(hash(subq.key, tab.value))
+FROM
+(select a.key, a.value from src a where a.key > 10 ) subq
+JOIN src tab
+ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value)
+where tab.value < 200
+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: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((((key > 10) and (key > 20)) and key is not null) and value is not null) and (value < 200)) (type: boolean)
+ Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: tab
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((key > 20) and key is not null) and value is not null) and (value < 200)) (type: boolean)
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey1}
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 sum(hash(subq.key, tab.value))
+FROM
+(select a.key, a.value from src a where a.key > 10 ) subq
+JOIN src tab
+ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value)
+where tab.value < 200
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(subq.key, tab.value))
+FROM
+(select a.key, a.value from src a where a.key > 10 ) subq
+JOIN src tab
+ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value)
+where tab.value < 200
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+NULL
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,120 @@
+PREHOOK: query: CREATE TABLE dest1(key1 INT, value1 STRING, key2 INT, value2 STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key1 INT, value1 STRING, key2 INT, value2 STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: explain
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+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: 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)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ 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} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col5) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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
+ name: default.dest1
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
+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
+POSTHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key)
+INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.key2 EXPRESSION [(src)src2.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.value1 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.value2 SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(dest1.key1,dest1.value1,dest1.key2,dest1.value2)) FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+-793937029770
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,196 @@
+PREHOOK: query: explain
+ SELECT sum(hash(a.key, a.value, b.key, b.value))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+ SELECT sum(hash(a.key, a.value, b.key, b.value))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.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 SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 1), Reducer 6 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+ Reducer 6 <- Map 5 (GROUP, 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
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT value)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(value)
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 12 Data size: 91 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: 91 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col1,_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 6
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT sum(hash(a.key, a.value, b.key, b.value))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key, a.value, b.key, b.value))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+379685492277
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join18_multi_distinct.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,200 @@
+PREHOOK: query: explain
+ SELECT sum(hash(a.key, a.value, b.key, b.value1, b.value2))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+ count(distinct(src2.key)) AS value2
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+ SELECT sum(hash(a.key, a.value, b.key, b.value1, b.value2))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+ count(distinct(src2.key)) AS value2
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.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 SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 1), Reducer 6 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+ Reducer 6 <- Map 5 (GROUP, 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
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT value), count(DISTINCT key)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(value)
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 91 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: 91 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1}
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint), _col4 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col1,_col2,_col3,_col4))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 6
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT sum(hash(a.key, a.value, b.key, b.value1, b.value2))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+ count(distinct(src2.key)) AS value2
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key, a.value, b.key, b.value1, b.value2))
+ FROM
+ (
+ SELECT src1.key as key, count(src1.value) AS value FROM src src1 group by src1.key
+ ) a
+ FULL OUTER JOIN
+ (
+ SELECT src2.key as key, count(distinct(src2.value)) AS value1,
+ count(distinct(src2.key)) AS value2
+ FROM src1 src2 group by src2.key
+ ) b
+ ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+40694575227
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,131 @@
+PREHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest1
+POSTHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest1
+PREHOOK: query: explain
+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
+POSTHOOK: query: explain
+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')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+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: 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)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col8
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col8 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1100 Data size: 11686 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
+ name: default.dest1
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+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
+POSTHOOK: 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')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@srcpart
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
+POSTHOOK: Output: default@dest1
+POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src1.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT sum(hash(dest1.key,dest1.value)) FROM dest1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(dest1.key,dest1.value)) FROM dest1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest1
+#### A masked pattern was here ####
+407444119660
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,150 @@
+PREHOOK: query: CREATE TABLE dest_j2(key INT, value STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@dest_j2
+POSTHOOK: query: CREATE TABLE dest_j2(key INT, value STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@dest_j2
+PREHOOK: query: explain
+FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key)
+INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key)
+INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+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 <- Map 4 (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: src2
+ 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 4
+ Map Operator Tree:
+ TableScan
+ alias: src3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: UDFToDouble(key) is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(key) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(key) (type: double)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src1
+ 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
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col5
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 + _col5) is not null (type: boolean)
+ Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: (_col0 + _col5) (type: double)
+ sort order: +
+ Map-reduce partition columns: (_col0 + _col5) (type: double)
+ Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col1}
+ outputColumnNames: _col0, _col11
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1
+ 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
+ name: default.dest_j2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_j2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+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 dest_j2 SELECT src1.key, src3.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@dest_j2
+[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: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key)
+INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@dest_j2
+POSTHOOK: Lineage: dest_j2.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j2.value SIMPLE [(src)src3.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT sum(hash(dest_j2.key,dest_j2.value)) FROM dest_j2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_j2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(dest_j2.key,dest_j2.value)) FROM dest_j2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_j2
+#### A masked pattern was here ####
+33815990627