Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/semijoin.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/semijoin.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/semijoin.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/semijoin.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,2643 @@ +PREHOOK: query: create table t1 as select cast(key as int) key, value from src where key <= 10 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@src +PREHOOK: Output: database:default +PREHOOK: Output: default@t1 +[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: create table t1 as select cast(key as int) key, value from src where key <= 10 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@src +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1 +PREHOOK: query: select * from t1 sort by key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 sort by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +10 val_10 +PREHOOK: query: create table t2 as select cast(2*key as int) key, value from t1 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@t1 +PREHOOK: Output: database:default +PREHOOK: Output: default@t2 +[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: create table t2 as select cast(2*key as int) key, value from t1 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@t1 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t2 +PREHOOK: query: select * from t2 sort by key +PREHOOK: type: QUERY +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t2 sort by key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +4 val_2 +8 val_4 +10 val_5 +10 val_5 +10 val_5 +16 val_8 +18 val_9 +20 val_10 +PREHOOK: query: create table t3 as select * from (select * from t1 union all select * from t2) b +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Output: database:default +PREHOOK: Output: default@t3 +[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: create table t3 as select * from (select * from t1 union all select * from t2) b +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t3 +PREHOOK: query: select * from t3 sort by key, value +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select * from t3 sort by key, value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_4 +8 val_8 +9 val_9 +10 val_10 +10 val_5 +10 val_5 +10 val_5 +16 val_8 +18 val_9 +20 val_10 +PREHOOK: query: create table t4 (key int, value string) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t4 +POSTHOOK: query: create table t4 (key int, value string) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t4 +PREHOOK: query: select * from t4 +PREHOOK: type: QUERY +PREHOOK: Input: default@t4 +#### A masked pattern was here #### +POSTHOOK: query: select * from t4 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t4 +#### A masked pattern was here #### +PREHOOK: query: explain select * from t1 a left semi join t2 b on a.key=b.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t1 a left semi join t2 b on a.key=b.key sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 53 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 t1 a left semi join t2 b on a.key=b.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 a left semi join t2 b on a.key=b.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +4 val_4 +8 val_8 +10 val_10 +PREHOOK: query: explain select * from t2 a left semi join t1 b on b.key=a.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t2 a left semi join t1 b on b.key=a.key sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 95 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 49 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 t2 a left semi join t1 b on b.key=a.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t2 a left semi join t1 b on b.key=a.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +4 val_2 +8 val_4 +10 val_5 +10 val_5 +10 val_5 +PREHOOK: query: explain select * from t1 a left semi join t4 b on b.key=a.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t1 a left semi join t4 b on b.key=a.key sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + 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 + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + 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 * from t1 a left semi join t4 b on b.key=a.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t4 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 a left semi join t4 b on b.key=a.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t4 +#### A masked pattern was here #### +PREHOOK: query: explain select a.value from t1 a left semi join t3 b on (b.key = a.key and b.key < '15') sort by a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.value from t1 a left semi join t3 b on (b.key = a.key and b.key < '15') sort by a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key < 15) and key is not null) (type: boolean) + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int), key (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 35 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 a.value from t1 a left semi join t3 b on (b.key = a.key and b.key < '15') sort by a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select a.value from t1 a left semi join t3 b on (b.key = a.key and b.key < '15') sort by a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +val_0 +val_0 +val_0 +val_10 +val_2 +val_4 +val_5 +val_5 +val_5 +val_8 +val_9 +PREHOOK: query: explain select * from t1 a left semi join t2 b on a.key = b.key and b.value < "val_10" sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t1 a left semi join t2 b on a.key = b.key and b.value < "val_10" sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 95 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: ((value < 'val_10') and key is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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 + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + 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 * from t1 a left semi join t2 b on a.key = b.key and b.value < "val_10" sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 a left semi join t2 b on a.key = b.key and b.value < "val_10" sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +PREHOOK: query: explain select a.value from t1 a left semi join (select key from t3 where key > 5) b on a.key = b.key sort by a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.value from t1 a left semi join (select key from t3 where key > 5) b on a.key = b.key sort by a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: value (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: t3 + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key > 5) and key is not null) (type: boolean) + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 8 Data size: 35 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 8 Data size: 35 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 a.value from t1 a left semi join (select key from t3 where key > 5) b on a.key = b.key sort by a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select a.value from t1 a left semi join (select key from t3 where key > 5) b on a.key = b.key sort by a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +val_10 +val_8 +val_9 +PREHOOK: query: explain select a.value from t1 a left semi join (select key , value from t2 where key > 5) b on a.key = b.key and b.value <= 'val_20' sort by a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.value from t1 a left semi join (select key , value from t2 where key > 5) b on a.key = b.key and b.value <= 'val_20' sort by a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t2 + Statistics: Num rows: 0 Data size: 95 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (((key > 5) and (value <= 'val_20')) and key is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: _col0 (type: int), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + 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 + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string) + outputColumnNames: _col0 + 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 a.value from t1 a left semi join (select key , value from t2 where key > 5) b on a.key = b.key and b.value <= 'val_20' sort by a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select a.value from t1 a left semi join (select key , value from t2 where key > 5) b on a.key = b.key and b.value <= 'val_20' sort by a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +PREHOOK: query: explain select * from t2 a left semi join (select key , value from t1 where key > 2) b on a.key = b.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t2 a left semi join (select key , value from t1 where key > 2) b on a.key = b.key sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key > 2) and key is not null) (type: boolean) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 95 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 17 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 t2 a left semi join (select key , value from t1 where key > 2) b on a.key = b.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t2 a left semi join (select key , value from t1 where key > 2) b on a.key = b.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +4 val_2 +8 val_4 +10 val_5 +10 val_5 +10 val_5 +PREHOOK: query: explain select /*+ mapjoin(b) */ a.key from t3 a left semi join t1 b on a.key = b.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ mapjoin(b) */ a.key from t3 a left semi join t1 b on a.key = b.key sort by a.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) + Reducer 3 <- Reducer 2 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 25 Data size: 101 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(b) */ a.key from t3 a left semi join t1 b on a.key = b.key sort by a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+ mapjoin(b) */ a.key from t3 a left semi join t1 b on a.key = b.key sort by a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +0 +0 +0 +0 +0 +0 +2 +4 +4 +5 +5 +5 +8 +8 +9 +10 +10 +10 +10 +PREHOOK: query: explain select * from t1 a left semi join t2 b on a.key = 2*b.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t1 a left semi join t2 b on a.key = 2*b.key sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (2 * key) is not null (type: boolean) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (2 * _col0) (type: int) + sort order: + + Map-reduce partition columns: (2 * _col0) (type: int) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13 Data size: 53 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13 Data size: 53 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 t1 a left semi join t2 b on a.key = 2*b.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 a left semi join t2 b on a.key = 2*b.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +8 val_8 +PREHOOK: query: explain select * from t1 a join t2 b on a.key = b.key left semi join t3 c on b.key = c.key sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t1 a join t2 b on a.key = b.key left semi join t3 c on b.key = c.key sort by a.key, a.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), 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: b + Statistics: Num rows: 0 Data size: 95 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: value (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 0 Data size: 90 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: int) + sort order: + + Map-reduce partition columns: key (type: int) + 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 + Left Semi Join 1 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + 2 + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: string) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 50 Data size: 202 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 t1 a join t2 b on a.key = b.key left semi join t3 c on b.key = c.key sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select * from t1 a join t2 b on a.key = b.key left semi join t3 c on b.key = c.key sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### 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 +4 val_4 4 val_2 +8 val_8 8 val_4 +10 val_10 10 val_5 +10 val_10 10 val_5 +10 val_10 10 val_5 +PREHOOK: query: explain select * from t3 a left semi join t1 b on a.key = b.key and a.value=b.value sort by a.key, a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from t3 a left semi join t1 b on a.key = b.key and a.value=b.value sort by a.key, a.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 SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 0 Data size: 90 Basic stats: PARTIAL Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Group By Operator + keys: key (type: int), value (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: int), value (type: string) + Statistics: Num rows: 1 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} + 1 + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 203 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 203 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 t3 a left semi join t1 b on a.key = b.key and a.value=b.value sort by a.key, a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select * from t3 a left semi join t1 b on a.key = b.key and a.value=b.value sort by a.key, a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +0 val_0 +2 val_2 +4 val_4 +5 val_5 +5 val_5 +5 val_5 +8 val_8 +9 val_9 +10 val_10 +PREHOOK: query: explain select /*+ mapjoin(b, c) */ a.key from t3 a left semi join t1 b on a.key = b.key left semi join t2 c on a.key = c.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select /*+ mapjoin(b, c) */ a.key from t3 a left semi join t1 b on a.key = b.key left semi join t2 c on a.key = c.key sort by a.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: b + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 11 Data size: 45 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 12 Data size: 49 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + Left Semi Join 0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + 2 + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 50 Data size: 202 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 50 Data size: 202 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(b, c) */ a.key from t3 a left semi join t1 b on a.key = b.key left semi join t2 c on a.key = c.key sort by a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+ mapjoin(b, c) */ a.key from t3 a left semi join t1 b on a.key = b.key left semi join t2 c on a.key = c.key sort by a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +0 +0 +0 +0 +0 +0 +4 +4 +8 +8 +10 +10 +10 +10 +PREHOOK: query: explain select a.key from t3 a left outer join t1 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key from t3 a left outer join t1 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.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: b + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + Left Semi Join 1 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + 2 + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 101 Data size: 407 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 a.key from t3 a left outer join t1 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select a.key from t3 a left outer join t1 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +4 +4 +8 +8 +10 +10 +10 +10 +PREHOOK: query: explain select a.key from t1 a right outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key from t1 a right outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.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: b + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + Left Semi Join 1 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + 2 + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 101 Data size: 407 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 a.key from t1 a right outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select a.key from t1 a right outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +NULL +NULL +NULL +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +4 +4 +8 +8 +10 +10 +10 +10 +PREHOOK: query: explain select a.key from t1 a full outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key from t1 a full outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.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: b + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + Left Semi Join 1 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 + 2 + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 101 Data size: 407 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 101 Data size: 407 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 a.key from t1 a full outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Input: default@t2 +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select a.key from t1 a full outer join t3 b on a.key = b.key left semi join t2 c on b.key = c.key sort by a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Input: default@t2 +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +NULL +NULL +NULL +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +0 +4 +4 +8 +8 +10 +10 +10 +10 +PREHOOK: query: explain select a.key from t3 a left semi join t2 b on a.key = b.key left outer join t1 c on a.key = c.key sort by a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key from t3 a left semi join t2 b on a.key = b.key left outer join t1 c on a.key = c.key sort by a.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: b + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 23 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 22 Data size: 90 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 46 Data size: 185 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Semi Join 0 to 1 + Left Outer Join0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1
[... 613 lines stripped ...]
