http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/count.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/count.q.out b/ql/src/test/results/clientpositive/tez/count.q.out deleted file mode 100644 index 9dc2764..0000000 --- a/ql/src/test/results/clientpositive/tez/count.q.out +++ /dev/null @@ -1,877 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS -create table abcd (a int, b int, c int, d int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@abcd -POSTHOOK: query: -- SORT_QUERY_RESULTS -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 #### -10 100 45 4 -10 100 NULL 5 -10 1000 50 1 -100 100 10 3 -12 100 75 7 -12 NULL 80 2 -NULL 35 23 6 -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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: _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 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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 #### -10 2 2 10 -100 1 1 3 -12 1 2 9 -NULL 1 1 6 -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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: _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (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) - 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 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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 #### -10 2 2 10 -100 1 1 3 -12 1 2 9 -NULL 1 1 6 -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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: _col1, _col2, _col3, _col4 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) - sort order: ++++ - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - 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, K EY._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 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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: --first aggregation with literal. gbinfo was generating wrong expression -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: --first aggregation with literal. gbinfo was generating wrong expression -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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: $f1, $f2, $f3, $f4 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1), count(), count($f1), count($f2), count($f3), count($f4), count(DISTINCT $f1), count(DISTINCT $f2), count(DISTINCT $f3), count(DISTINCT $f4), count(DISTINCT $f1, $f2), count(DISTINCT $f2, $f3), count(DISTINCT $f3, $f4), count(DISTINCT $f1, $f4), count(DISTINCT $f1, $f3), count(DISTINCT $f2, $f4), count(DISTINCT $f1, $f2, $f3), count(DISTINCT $f2, $f3, $f4), count(DISTINCT $f1, $f3, $f4), count(DISTINCT $f1, $f2, $f4), count(DISTINCT $f1, $f2, $f3, $f4) - keys: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (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) - 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: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 336 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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 count(distinct b) from abcd group by a -PREHOOK: type: QUERY -POSTHOOK: query: explain select count(distinct b) from abcd group by a -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: abcd - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: a (type: int), b (type: int) - outputColumnNames: a, b - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: a (type: int), b (type: int) - sort order: ++ - Map-reduce partition columns: a (type: int), b (type: int) - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: complete - outputColumnNames: a, b - Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: a (type: int) - sort order: + - Map-reduce partition columns: a (type: int) - Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE - value expressions: b (type: int) - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: a, $f1 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: $f1 (type: bigint) - outputColumnNames: _o__c0 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 17 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(distinct b) from abcd group by a -PREHOOK: type: QUERY -PREHOOK: Input: default@abcd -#### A masked pattern was here #### -POSTHOOK: query: select count(distinct b) from abcd group by a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -1 -1 -1 -2 -PREHOOK: query: explain select count(distinct b) from abcd group by b -PREHOOK: type: QUERY -POSTHOOK: query: explain select count(distinct b) from abcd group by b -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: abcd - Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: b (type: int) - outputColumnNames: b - Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: b (type: int) - sort order: + - Map-reduce partition columns: b (type: int) - Statistics: Num rows: 19 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: b - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: b (type: int) - sort order: + - Map-reduce partition columns: b (type: int) - Statistics: Num rows: 9 Data size: 36 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: count(KEY._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: b, $f1 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: $f1 (type: bigint) - outputColumnNames: _o__c0 - Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 16 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(distinct b) from abcd group by b -PREHOOK: type: QUERY -PREHOOK: Input: default@abcd -#### A masked pattern was here #### -POSTHOOK: query: select count(distinct b) from abcd group by b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -0 -1 -1 -1 -PREHOOK: query: explain select count(distinct b) from abcd group by c -PREHOOK: type: QUERY -POSTHOOK: query: explain select count(distinct b) from abcd group by c -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: abcd - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: b (type: int), c (type: int) - outputColumnNames: b, c - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: b (type: int), c (type: int) - sort order: ++ - Map-reduce partition columns: b (type: int), c (type: int) - Statistics: Num rows: 9 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int), KEY._col1 (type: int) - mode: complete - outputColumnNames: b, c - Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: c (type: int) - sort order: + - Map-reduce partition columns: c (type: int) - Statistics: Num rows: 4 Data size: 34 Basic stats: COMPLETE Column stats: NONE - value expressions: b (type: int) - Reducer 3 - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: c, $f1 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: $f1 (type: bigint) - outputColumnNames: _o__c0 - Statistics: Num rows: 2 Data size: 17 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 17 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(distinct b) from abcd group by c -PREHOOK: type: QUERY -PREHOOK: Input: default@abcd -#### A masked pattern was here #### -POSTHOOK: query: select count(distinct b) from abcd group by c -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -0 -1 -1 -1 -1 -1 -1 -PREHOOK: query: explain select count(b), count(distinct c) from abcd group by d -PREHOOK: type: QUERY -POSTHOOK: query: explain select count(b), count(distinct c) from abcd group by d -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: abcd - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: b (type: int), c (type: int), d (type: int) - outputColumnNames: b, c, d - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: d (type: int), c (type: int) - sort order: ++ - Map-reduce partition columns: d (type: int) - Statistics: Num rows: 6 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: b (type: int) - Reducer 2 - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0), count(DISTINCT KEY._col1:0._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: d, $f1, $f2 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: $f1 (type: bigint), $f2 (type: bigint) - outputColumnNames: _o__c0, _o__c1 - Statistics: Num rows: 3 Data size: 39 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3 Data size: 39 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(b), count(distinct c) from abcd group by d -PREHOOK: type: QUERY -PREHOOK: Input: default@abcd -#### A masked pattern was here #### -POSTHOOK: query: select count(b), count(distinct c) from abcd group by d -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -0 1 -1 0 -1 1 -1 1 -1 1 -1 1 -1 1 -PREHOOK: query: --non distinct aggregate with same column as group by key -explain select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a -PREHOOK: type: QUERY -POSTHOOK: query: --non distinct aggregate with same column as group by key -explain select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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), (d + d) (type: int), (d * 3) (type: int) - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: $f0 (type: int), $f1 (type: int), $f2 (type: int) - sort order: +++ - Map-reduce partition columns: $f0 (type: int) - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: $f3 (type: int), $f4 (type: int), $f5 (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), sum(VALUE._col1), sum(VALUE._col2), sum(KEY._col1:0._col0), sum(KEY._col1:1._col0), sum(KEY._col0), sum(DISTINCT KEY._col1:2._col0), sum(DISTINCT KEY._col1:3._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) 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), sum(d+d), sum(d*3), sum(b), sum(c), sum(a), sum(distinct a), sum(distinct b) from abcd group by a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -10 2 2 10 20 30 1200 95 30 10 1100 -100 1 1 3 6 9 100 10 100 100 100 -12 1 2 9 18 27 100 155 24 12 100 -NULL 1 1 6 12 18 35 23 NULL NULL 35 -PREHOOK: query: --non distinct aggregate with same column as distinct aggregate -explain select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a -PREHOOK: type: QUERY -POSTHOOK: query: --non distinct aggregate with same column as distinct aggregate -explain select a, count(distinct b), count(distinct c), sum(d), sum(c) from abcd group by a -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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), sum(KEY._col1:1._col0) - keys: KEY._col0 (type: int) - mode: complete - outputColumnNames: a, $f1, $f2, $f3, $f4 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select a, count(distinct b), count(distinct c), sum(d), sum(c) 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), sum(c) from abcd group by a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@abcd -#### A masked pattern was here #### -10 2 2 10 95 -100 1 1 3 10 -12 1 2 9 155 -NULL 1 1 6 23 -PREHOOK: query: --aggregation with literal -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: --aggregation with literal -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 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - 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: $f1, $f2, $f3, $f4 - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) - sort order: ++++ - Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - 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, K EY._col0:14._col3) - mode: complete - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - 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.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -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
http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/create_merge_compressed.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/create_merge_compressed.q.out b/ql/src/test/results/clientpositive/tez/create_merge_compressed.q.out deleted file mode 100644 index 58f517c..0000000 --- a/ql/src/test/results/clientpositive/tez/create_merge_compressed.q.out +++ /dev/null @@ -1,138 +0,0 @@ -PREHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_rc_merge_test -POSTHOOK: query: create table src_rc_merge_test(key int, value string) stored as rcfile -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_rc_merge_test -PREHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@src_rc_merge_test -POSTHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' into table src_rc_merge_test -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@src_rc_merge_test -PREHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: query: create table tgt_rc_merge_test(key int, value string) stored as rcfile -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tgt_rc_merge_test -PREHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@src_rc_merge_test -PREHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_rc_merge_test -POSTHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: Lineage: tgt_rc_merge_test.key SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: tgt_rc_merge_test.value SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@src_rc_merge_test -PREHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: query: insert into table tgt_rc_merge_test select * from src_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_rc_merge_test -POSTHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: Lineage: tgt_rc_merge_test.key SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: tgt_rc_merge_test.value SIMPLE [(src_rc_merge_test)src_rc_merge_test.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: show table extended like `tgt_rc_merge_test` -PREHOOK: type: SHOW_TABLESTATUS -POSTHOOK: query: show table extended like `tgt_rc_merge_test` -POSTHOOK: type: SHOW_TABLESTATUS -tableName:tgt_rc_merge_test -#### A masked pattern was here #### -inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat -outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat -columns:struct columns { i32 key, string value} -partitioned:false -partitionColumns: -totalNumberFiles:2 -totalFileSize:342 -maxFileSize:171 -minFileSize:171 -#### A masked pattern was here #### - -PREHOOK: query: select count(1) from tgt_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from tgt_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -10 -PREHOOK: query: select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -46 -751895388 -PREHOOK: query: alter table tgt_rc_merge_test concatenate -PREHOOK: type: ALTER_TABLE_MERGE -PREHOOK: Input: default@tgt_rc_merge_test -PREHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: query: alter table tgt_rc_merge_test concatenate -POSTHOOK: type: ALTER_TABLE_MERGE -POSTHOOK: Input: default@tgt_rc_merge_test -POSTHOOK: Output: default@tgt_rc_merge_test -PREHOOK: query: show table extended like `tgt_rc_merge_test` -PREHOOK: type: SHOW_TABLESTATUS -POSTHOOK: query: show table extended like `tgt_rc_merge_test` -POSTHOOK: type: SHOW_TABLESTATUS -tableName:tgt_rc_merge_test -#### A masked pattern was here #### -inputformat:org.apache.hadoop.hive.ql.io.RCFileInputFormat -outputformat:org.apache.hadoop.hive.ql.io.RCFileOutputFormat -columns:struct columns { i32 key, string value} -partitioned:false -partitionColumns: -totalNumberFiles:1 -totalFileSize:243 -maxFileSize:243 -minFileSize:243 -#### A masked pattern was here #### - -PREHOOK: query: select count(1) from tgt_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -POSTHOOK: query: select count(1) from tgt_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -10 -PREHOOK: query: select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test -PREHOOK: type: QUERY -PREHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -POSTHOOK: query: select sum(hash(key)), sum(hash(value)) from tgt_rc_merge_test -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tgt_rc_merge_test -#### A masked pattern was here #### -46 -751895388 -PREHOOK: query: drop table src_rc_merge_test -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@src_rc_merge_test -PREHOOK: Output: default@src_rc_merge_test -POSTHOOK: query: drop table src_rc_merge_test -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@src_rc_merge_test -POSTHOOK: Output: default@src_rc_merge_test -PREHOOK: query: drop table tgt_rc_merge_test -PREHOOK: type: DROPTABLE -PREHOOK: Input: default@tgt_rc_merge_test -PREHOOK: Output: default@tgt_rc_merge_test -POSTHOOK: query: drop table tgt_rc_merge_test -POSTHOOK: type: DROPTABLE -POSTHOOK: Input: default@tgt_rc_merge_test -POSTHOOK: Output: default@tgt_rc_merge_test http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/cross_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/cross_join.q.out b/ql/src/test/results/clientpositive/tez/cross_join.q.out deleted file mode 100644 index 0d87e87..0000000 --- a/ql/src/test/results/clientpositive/tez/cross_join.q.out +++ /dev/null @@ -1,398 +0,0 @@ -Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: -- current -explain select src.key from src join src src2 -PREHOOK: type: QUERY -POSTHOOK: query: -- current -explain select src.key from src join src src2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Map 3 - Map Operator Tree: - TableScan - alias: src2 - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: -- ansi cross join -explain select src.key from src cross join src src2 -PREHOOK: type: QUERY -POSTHOOK: query: -- ansi cross join -explain select src.key from src cross join src src2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) - Map 3 - Map Operator Tree: - TableScan - alias: src2 - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: -- appending condition is allowed -explain select src.key from src cross join src src2 on src.key=src2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- appending condition is allowed -explain select src.key from src cross join src src2 on src.key=src2.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map 3 - Map Operator Tree: - TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reducer 2 - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE - 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-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product -PREHOOK: query: explain select src.key from src join src src2 -PREHOOK: type: QUERY -POSTHOOK: query: explain select src.key from src join src src2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 2 (BROADCAST_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - input vertices: - 1 Map 2 - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - 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 - Map 2 - Map Operator Tree: - TableScan - alias: src2 - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product -PREHOOK: query: explain select src.key from src cross join src src2 -PREHOOK: type: QUERY -POSTHOOK: query: explain select src.key from src cross join src src2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 2 (BROADCAST_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0 - input vertices: - 1 Map 2 - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE - 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 - Map 2 - Map Operator Tree: - TableScan - alias: src2 - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key -PREHOOK: type: QUERY -POSTHOOK: query: explain select src.key from src cross join src src2 on src.key=src2.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Map 2 (BROADCAST_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - input vertices: - 1 Map 2 - Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE - HybridGraceHashJoin: true - File Output Operator - compressed: false - Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE - 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 - Map 2 - Map Operator Tree: - TableScan - alias: src2 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink -
