http://git-wip-us.apache.org/repos/asf/hive/blob/bda5d51d/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out index 5b3ad71..b347231 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out @@ -1326,16 +1326,19 @@ STAGE PLANS: TableScan alias: e Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string), p_size (type: int) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: p_name is not null (type: boolean) 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) + Select Operator + expressions: p_name (type: string), p_size (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + 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: int) Execution mode: vectorized Map 4 Map Operator Tree: @@ -1365,11 +1368,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col1, _col2, _col3 + 1 _col1 (type: string) + outputColumnNames: _col1, _col2 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col1 + 100) < CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: boolean) + predicate: ((_col1 + 100) < _col2) (type: boolean) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE @@ -1407,15 +1410,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: int), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: boolean) + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -1454,15 +1457,18 @@ STAGE PLANS: TableScan alias: e Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_name (type: string) - outputColumnNames: _col0 + Filter Operator + predicate: p_name is not null (type: boolean) 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) + Select Operator + expressions: p_name (type: string) + outputColumnNames: _col0 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 Execution mode: vectorized Map 4 Map Operator Tree: @@ -1576,16 +1582,19 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Filter Operator + predicate: p_type is not null (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: string) - sort order: + - Map-reduce partition columns: _col4 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Output Operator + key expressions: _col4 (type: string) + sort order: + + Map-reduce partition columns: _col4 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized Map 3 Map Operator Tree: @@ -1615,11 +1624,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col4 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(_col5) > CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean) + predicate: (UDFToDouble(_col5) > _col9) (type: boolean) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) @@ -1642,15 +1651,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (_col1 / _col2) (type: double), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: (_col1 / _col2) (type: double), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double), _col1 (type: boolean) + value expressions: _col0 (type: double) Stage: Stage-0 Fetch Operator @@ -1857,7 +1866,7 @@ POSTHOOK: Input: default@part_null_n0 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null_n0 where part_null_n0.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null_n0) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null_n0 where part_null_n0.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null_n0) @@ -1881,16 +1890,19 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Filter Operator + predicate: p_type is not null (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: string) - sort order: + - Map-reduce partition columns: _col4 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Output Operator + key expressions: _col4 (type: string) + sort order: + + Map-reduce partition columns: _col4 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized Map 4 Map Operator Tree: @@ -1939,11 +1951,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col4 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col5 >= CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean) + predicate: (_col5 >= _col9) (type: boolean) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) @@ -1987,15 +1999,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: int), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: boolean) + value expressions: _col0 (type: int) Reducer 7 Execution mode: vectorized Reduce Operator Tree: @@ -2015,7 +2027,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from part where p_size >= (select min(p_size) from part_null_n0 where part_null_n0.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null_n0) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -3032,16 +3044,19 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_size (type: int) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: p_size is not null (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_size (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string) + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) Execution mode: vectorized Map 3 Map Operator Tree: @@ -3088,11 +3103,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col2 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 like CASE WHEN (_col4 is null) THEN (null) ELSE (_col3) END) (type: boolean) + predicate: (_col1 like _col3) (type: boolean) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int) @@ -3137,15 +3152,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: string), _col0 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: boolean) + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator @@ -3403,7 +3418,7 @@ POSTHOOK: Input: default@part_null_n0 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from part_null_n0 where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null_n0 pp where part_null_n0.p_type = pp.p_type) PREHOOK: type: QUERY POSTHOOK: query: explain select * from part_null_n0 where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null_n0 pp where part_null_n0.p_type = pp.p_type) @@ -3429,14 +3444,17 @@ STAGE PLANS: TableScan alias: part_null_n0 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment_n11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Filter Operator + predicate: p_type is not null (type: boolean) Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment_n11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized Map 5 Map Operator Tree: @@ -3508,15 +3526,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 32560 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: boolean) + value expressions: _col0 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -3544,17 +3562,17 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not CASE WHEN ((_col9 = 0L)) THEN (false) WHEN (_col12 is not null) THEN (true) WHEN (_col3 is null) THEN (null) WHEN ((_col10 < _col9)) THEN (true) ELSE (false) END) (type: boolean) - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col12 is null and _col3 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) + Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: string) sort order: + Map-reduce partition columns: _col4 (type: string) - Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 4 Reduce Operator Tree: @@ -3563,19 +3581,19 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col4 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col13, _col14 - Statistics: Num rows: 7 Data size: 951 Basic stats: COMPLETE Column stats: NONE + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col13 + Statistics: Num rows: 9 Data size: 1223 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not (_col1 like CASE WHEN (_col14 is null) THEN (null) ELSE (_col13) END)) (type: boolean) - Statistics: Num rows: 4 Data size: 543 Basic stats: COMPLETE Column stats: NONE + predicate: (not (_col1 like _col13)) (type: boolean) + Statistics: Num rows: 5 Data size: 679 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 4 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 679 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 543 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 679 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3617,7 +3635,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: select * from part_null_n0 where p_brand NOT IN (select p_name from part) AND p_name NOT LIKE (select min(p_name) from part_null_n0 pp where part_null_n0.p_type = pp.p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -3629,6 +3647,7 @@ POSTHOOK: Input: default@part POSTHOOK: Input: default@part_null_n0 #### A masked pattern was here #### 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and @@ -3649,7 +3668,7 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (GROUP, 2) Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1) Reducer 7 <- Map 6 (GROUP, 2) #### A masked pattern was here #### Vertices: @@ -3681,15 +3700,15 @@ STAGE PLANS: predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 50 Data size: 5999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) + value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized Map 6 Map Operator Tree: @@ -3697,23 +3716,23 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_shipmode = 'AIR') and l_linenumber is not null) (type: boolean) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + predicate: ((l_linenumber = 1) and (l_shipmode = 'AIR')) (type: boolean) + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), l_linenumber (type: int) - outputColumnNames: l_orderkey, l_linenumber - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + expressions: l_orderkey (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(l_orderkey) - keys: l_linenumber (type: int) + aggregations: min(_col1) + keys: 1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized Reducer 2 @@ -3737,12 +3756,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) + sort order: Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) Reducer 4 @@ -3751,20 +3768,20 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col4 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col3, _col5, _col6 - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col5 + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 <> CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean) - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + predicate: (_col1 <> _col5) (type: boolean) + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3777,17 +3794,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: boolean) + sort order: + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -3795,6 +3810,7 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and @@ -3834,6 +3850,7 @@ POSTHOOK: Input: default@lineitem 85951 5952 88035 5560 88362 871 +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: explain select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and @@ -3854,7 +3871,7 @@ STAGE PLANS: Edges: Reducer 2 <- Map 1 (GROUP, 2) Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) - Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1) Reducer 7 <- Map 6 (GROUP, 2) #### A masked pattern was here #### Vertices: @@ -3886,15 +3903,15 @@ STAGE PLANS: predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 50 Data size: 5999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int) + value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized Map 6 Map Operator Tree: @@ -3902,23 +3919,23 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((l_shipmode = 'AIR') and l_linenumber is not null) (type: boolean) - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + predicate: ((l_linenumber = 1) and (l_shipmode = 'AIR')) (type: boolean) + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: l_orderkey (type: int), l_linenumber (type: int) - outputColumnNames: l_orderkey, l_linenumber - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + expressions: l_orderkey (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(l_orderkey) - keys: l_linenumber (type: int) + aggregations: min(_col1) + keys: 1 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized Reducer 2 @@ -3942,12 +3959,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) + sort order: Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int) Reducer 4 @@ -3956,20 +3971,20 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col4 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col3, _col5, _col6 - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col5 + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 <> CASE WHEN (_col6 is null) THEN (null) ELSE (_col5) END) (type: boolean) - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + predicate: (_col1 <> _col5) (type: boolean) + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col3 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 660 Data size: 158981 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3982,17 +3997,15 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE + expressions: _col1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: boolean) + sort order: + Statistics: Num rows: 12 Data size: 1439 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Stage: Stage-0 Fetch Operator @@ -4000,6 +4013,7 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: select p.p_partkey, li.l_suppkey from (select distinct l_partkey as p_partkey from lineitem) p join lineitem li on p.p_partkey = li.l_partkey where li.l_linenumber = 1 and @@ -4123,11 +4137,11 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - 2 _col1 (type: int) - outputColumnNames: _col1, _col2, _col4 + 2 _col0 (type: int) + outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 220 Data size: 26397 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > _col4) (type: boolean) + predicate: (_col1 > _col5) (type: boolean) Statistics: Num rows: 73 Data size: 8759 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: double) @@ -4167,15 +4181,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (_col1 / _col2) (type: double), _col0 (type: int) + expressions: _col0 (type: int), (_col1 / _col2) (type: double) outputColumnNames: _col0, _col1 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + value expressions: _col1 (type: double) Stage: Stage-0 Fetch Operator @@ -4236,7 +4250,7 @@ STAGE PLANS: alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: p_type is not null (type: boolean) + predicate: (p_name is not null and p_type is not null) (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_name (type: string), p_brand (type: string), p_type (type: string) @@ -4294,29 +4308,26 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col2 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (not (_col1 like CASE WHEN (_col4 is null) THEN (null) ELSE (_col3) END)) (type: boolean) + predicate: (not (_col1 like _col3)) (type: boolean) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 is not null and _col1 is not null) (type: boolean) + Group By Operator + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Reducer 6 Execution mode: vectorized Reduce Operator Tree: @@ -4327,15 +4338,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: string), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: boolean) + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator @@ -4653,16 +4664,19 @@ STAGE PLANS: TableScan alias: emps_n4 Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Filter Operator + predicate: deptno is not null (type: boolean) Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) + Select Operator + expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Execution mode: vectorized Map 3 Map Operator Tree: @@ -4692,11 +4706,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col2 (type: int) - 1 _col2 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 > CASE WHEN (_col11 is null) THEN (null) ELSE (_col10) END) (type: boolean) + predicate: (_col1 > _col10) (type: boolean) Statistics: Num rows: 1 Data size: 52 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) @@ -4719,15 +4733,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: string), true (type: boolean), _col0 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: string), _col0 (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col1 (type: int) sort order: + - Map-reduce partition columns: _col2 (type: int) + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: boolean) + value expressions: _col0 (type: string) Stage: Stage-0 Fetch Operator @@ -4929,7 +4943,7 @@ POSTHOOK: Input: default@emps_n4 110 John 40 M Vancouver 2 NULL false true 2002-05-03 120 Wilma 20 F NULL 1 5 NULL true 2005-09-07 130 Alice 40 F Vancouver 2 NULL false true 2007-01-01 -Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from emps_n4 where deptno <> (select sum(deptno) from depts_n3 where depts_n3.name = emps_n4.name) and empno > (select count(name) from depts_n3) PREHOOK: type: QUERY POSTHOOK: query: explain select * from emps_n4 where deptno <> (select sum(deptno) from depts_n3 where depts_n3.name = emps_n4.name) and empno > (select count(name) from depts_n3) @@ -4953,16 +4967,19 @@ STAGE PLANS: TableScan alias: emps_n4 Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Filter Operator + predicate: name is not null (type: boolean) Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) + Select Operator + expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 5 Data size: 238 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) Execution mode: vectorized Map 4 Map Operator Tree: @@ -5011,11 +5028,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + 1 _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToLong(_col2) <> CASE WHEN (_col11 is null) THEN (null) ELSE (_col10) END) (type: boolean) + predicate: (UDFToLong(_col2) <> _col10) (type: boolean) Statistics: Num rows: 5 Data size: 261 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date) @@ -5059,15 +5076,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: bigint), true (type: boolean), _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: _col1 (type: bigint), _col0 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: string) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col2 (type: string) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: boolean) + value expressions: _col0 (type: bigint) Reducer 7 Execution mode: vectorized Reduce Operator Tree: @@ -5636,16 +5653,19 @@ STAGE PLANS: TableScan alias: part Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Filter Operator + predicate: p_type is not null (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: string) - sort order: + - Map-reduce partition columns: _col4 (type: string) + Select Operator + expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + Reduce Output Operator + key expressions: _col4 (type: string) + sort order: + + Map-reduce partition columns: _col4 (type: string) + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized Map 3 Map Operator Tree: @@ -6059,7 +6079,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE WHEN (_col3 is null) THEN ((0 = 0)) ELSE ((_col2 = 0)) END (type: boolean) + predicate: CASE WHEN (_col3 is null) THEN (true) ELSE ((_col2 = 0L)) END (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int) @@ -6149,7 +6169,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@t_n11 #### A masked pattern was here #### 1 1 -Warning: Shuffle Join JOIN[12][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: explain select * from t_n11 where 0 = (select avg(tt_n11.i) from t_n11 tt_n11 where tt_n11.j <> t_n11.i) PREHOOK: type: QUERY POSTHOOK: query: explain select * from t_n11 where 0 = (select avg(tt_n11.i) from t_n11 tt_n11 where tt_n11.j <> t_n11.i) @@ -6173,16 +6193,19 @@ STAGE PLANS: TableScan alias: t_n11 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int), j (type: int) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: i is not null (type: boolean) Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: i (type: int), j (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Execution mode: vectorized Map 3 Map Operator Tree: @@ -6203,9 +6226,8 @@ STAGE PLANS: TableScan alias: t_n11 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int) - outputColumnNames: i + Filter Operator + predicate: i is not null (type: boolean) Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: i (type: int) @@ -6304,7 +6326,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[12][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: select * from t_n11 where 0 = (select avg(tt_n11.i) from t_n11 tt_n11 where tt_n11.j <> t_n11.i) PREHOOK: type: QUERY PREHOOK: Input: default@t_n11 @@ -6385,7 +6407,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 6 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: CASE WHEN (_col3 is null) THEN ((0 = 0)) ELSE ((_col2 = 0)) END (type: boolean) + predicate: CASE WHEN (_col3 is null) THEN (true) ELSE ((_col2 = 0L)) END (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: int) @@ -6457,16 +6479,19 @@ STAGE PLANS: TableScan alias: t_n11 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i (type: int), j (type: int) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: i is not null (type: boolean) Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Select Operator + expressions: i (type: int), j (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Execution mode: vectorized Map 3 Map Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/bda5d51d/ql/src/test/results/clientpositive/spark/subquery_select.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_select.q.out b/ql/src/test/results/clientpositive/spark/subquery_select.q.out index ac7ba50..615f508 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_select.q.out @@ -298,23 +298,19 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col1 (type: int), _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: int) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: boolean) + value expressions: _col2 (type: boolean) Stage: Stage-0 Fetch Operator @@ -623,23 +619,19 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col1 (type: int), _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: int) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: boolean) + value expressions: _col2 (type: boolean) Reducer 2 Reduce Operator Tree: Join Operator @@ -651,7 +643,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (sq_count_check(_col3, true) > 0) (type: boolean) + predicate: (sq_count_check(CASE WHEN (_col3 is null) THEN (0) ELSE (_col3) END, true) > 0) (type: boolean) Statistics: Num rows: 9 Data size: 1112 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: int) @@ -671,14 +663,14 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 + outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 9 Data size: 1223 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: int) Statistics: Num rows: 9 Data size: 1223 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: bigint), _col6 (type: bigint) + value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 4 Reduce Operator Tree: Join Operator @@ -687,10 +679,10 @@ STAGE PLANS: keys: 0 _col0 (type: string), _col1 (type: int) 1 _col1 (type: string), _col0 (type: int) - outputColumnNames: _col1, _col5, _col6, _col9 + outputColumnNames: _col1, _col3, _col4, _col7 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col1 (type: int), CASE WHEN ((_col5 = 0L)) THEN (true) WHEN (_col5 is null) THEN (true) WHEN (_col9 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col6 < _col5)) THEN (null) ELSE (true) END (type: boolean) + expressions: _col1 (type: int), CASE WHEN ((_col3 = 0L)) THEN (true) WHEN (_col3 is null) THEN (true) WHEN (_col7 is not null) THEN (false) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (null) ELSE (true) END (type: boolean) outputColumnNames: _col0, _col1 Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -3010,7 +3002,7 @@ STANDARD ANODIZED TIN true STANDARD BURNISHED TIN true STANDARD PLATED TIN true STANDARD POLISHED STEEL true -Warning: Shuffle Join JOIN[48][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 4' is a cross product +Warning: Shuffle Join JOIN[47][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 4' is a cross product PREHOOK: query: EXPLAIN SELECT p_size, p_size IN ( SELECT MAX(p_size) FROM part p where p.p_type = part.p_type) AND p_name IN (SELECT min(p_name) from part) @@ -3227,23 +3219,19 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: string) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Select Operator + expressions: _col1 (type: int), _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col1 (type: string), _col0 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), _col0 (type: int) Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: boolean) + value expressions: _col2 (type: boolean) Stage: Stage-0 Fetch Operator @@ -3251,7 +3239,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[48][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 4' is a cross product +Warning: Shuffle Join JOIN[47][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 4' is a cross product PREHOOK: query: SELECT p_size, p_size IN ( SELECT MAX(p_size) FROM part p where p.p_type = part.p_type) AND p_name IN (SELECT min(p_name) from part) @@ -4800,7 +4788,7 @@ STAGE PLANS: alias: p Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_size is not null and p_type is not null) (type: boolean) + predicate: (p_partkey is not null and p_size is not null and p_type is not null) (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_type (type: string), p_size (type: int) @@ -5169,7 +5157,7 @@ STAGE PLANS: alias: p Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (p_size is not null and p_type is not null) (type: boolean) + predicate: (p_partkey is not null and p_size is not null and p_type is not null) (type: boolean) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: p_partkey (type: int), p_type (type: string), p_size (type: int)
