PREHOOK: query: create table abcd (a int, b int, c int, d int) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default POSTHOOK: query: create table abcd (a int, b int, c int, d int) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@abcd PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@abcd POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in4.txt' INTO TABLE abcd POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@abcd PREHOOK: query: select * from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd #### A masked pattern was here #### POSTHOOK: query: select * from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### NULL 35 23 6 10 1000 50 1 100 100 10 3 12 NULL 80 2 10 100 NULL 5 10 100 45 4 12 100 75 7 PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: abcd Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col2) keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY PREHOOK: Input: default@abcd #### A masked pattern was here #### POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### NULL 1 1 6 10 2 2 10 12 1 2 9 100 1 1 3 PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: abcd Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1), count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint), _col20 (type: bigint), _col21 (type: bigint), _col22 (type: bigint), _col23 (type: bigint), _col24 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint), _col20 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd #### A masked pattern was here #### POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### 7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4 PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY POSTHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: abcd Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ Map-reduce partition columns: a (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions: d (type: int) Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0), sum(VALUE._col0) keys: KEY._col0 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a PREHOOK: type: QUERY PREHOOK: Input: default@abcd #### A masked pattern was here #### POSTHOOK: query: select a, count(distinct b), count(distinct c), sum(d) from abcd group by a POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### NULL 1 1 6 10 2 2 10 12 1 2 9 100 1 1 3 PREHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY POSTHOOK: query: explain select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: abcd Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions: 1 (type: int) Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint), _col20 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd PREHOOK: type: QUERY PREHOOK: Input: default@abcd #### A masked pattern was here #### POSTHOOK: query: select count(1), count(*), count(a), count(b), count(c), count(d), count(distinct a), count(distinct b), count(distinct c), count(distinct d), count(distinct a,b), count(distinct b,c), count(distinct c,d), count(distinct a,d), count(distinct a,c), count(distinct b,d), count(distinct a,b,c), count(distinct b,c,d), count(distinct a,c,d), count(distinct a,b,d), count(distinct a,b,c,d) from abcd POSTHOOK: type: QUERY POSTHOOK: Input: default@abcd #### A masked pattern was here #### 7 7 6 6 6 7 3 3 6 7 4 5 6 6 5 6 4 5 5 5 4