http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out deleted file mode 100644 index 793b8be..0000000 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out +++ /dev/null @@ -1,766 +0,0 @@ -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: -- non agg, non corr --- JAVA_VERSION_SPECIFIC_OUTPUT - -explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- non agg, non corr --- JAVA_VERSION_SPECIFIC_OUTPUT - -explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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) - 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 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: -- non agg, corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- non agg, corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 depends on stages: Stage-4 - Stage-6 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_retailprice) - keys: p_mfgr (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: double) - 1 _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_retailprice), max(p_retailprice) - keys: p_mfgr (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean) - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_retailprice), max(p_retailprice) - keys: p_mfgr (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 - _col1) > 600.0) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#1 1173.15 -Manufacturer#2 1690.68 -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: -- agg, non corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- agg, non corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 depends on stages: Stage-4 - Stage-6 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(p_retailprice) - keys: p_mfgr (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_mfgr is null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_retailprice (type: double) - outputColumnNames: _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1), min(_col1) - keys: null (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: double), _col2 (type: double) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: p_mfgr, p_retailprice - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(p_retailprice), min(p_retailprice) - keys: p_mfgr (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#1 1173.15 -Manufacturer#2 1690.68
http://git-wip-us.apache.org/repos/asf/hive/blob/22541610/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out b/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out deleted file mode 100644 index 4e227cd..0000000 --- a/ql/src/test/results/clientpositive/subquery_notin_having.q.java1.8.out +++ /dev/null @@ -1,762 +0,0 @@ -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: -- non agg, non corr --- JAVA_VERSION_SPECIFIC_OUTPUT - -explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- non agg, non corr --- JAVA_VERSION_SPECIFIC_OUTPUT - -explain -select key, count(*) -from src -group by key -having key not in - ( select key from src s1 - where s1.key > '12' - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (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) - 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 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: bigint) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key > '12') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: bigint) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 151 Data size: 1606 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key > '12') and key is null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - 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) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: -- non agg, corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- non agg, corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-5 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 depends on stages: Stage-4 - Stage-6 is a root stage - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string), _col1 (type: double) - 1 _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col3 is null (type: boolean) - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 888 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean) - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1), max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 - _col1) > 600.0) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from (select p_mfgr, min(p_retailprice) l, max(p_retailprice) r, avg(p_retailprice) a from part group by p_mfgr) a - where min(p_retailprice) = l and r - l > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#1 1173.15 -Manufacturer#2 1690.68 -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: -- agg, non corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -POSTHOOK: query: -- agg, non corr -explain -select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1, Stage-4 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-4 is a root stage - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is null (type: boolean) - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: double) - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_mfgr (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: p_mfgr is null (type: boolean) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: null (type: string), p_retailprice (type: double) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1), min(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double), _col2 (type: double) - Reduce Operator Tree: - Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: double), _col2 (type: double) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) > 600.0) (type: boolean) - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 = 0) (type: boolean) - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join JOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-3:MAPRED' is a cross product -PREHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -PREHOOK: type: QUERY -PREHOOK: Input: default@part -#### A masked pattern was here #### -POSTHOOK: query: select b.p_mfgr, min(p_retailprice) -from part b -group by b.p_mfgr -having b.p_mfgr not in - (select p_mfgr - from part a - group by p_mfgr - having max(p_retailprice) - min(p_retailprice) > 600 - ) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@part -#### A masked pattern was here #### -Manufacturer#2 1690.68 -Manufacturer#1 1173.15