PREHOOK: query: -- SORT_QUERY_RESULTS

-- Set merging to false above to make the explain more readable

CREATE TABLE T1(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T1
POSTHOOK: query: -- SORT_QUERY_RESULTS

-- Set merging to false above to make the explain more readable

CREATE TABLE T1(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T1
PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1
PREHOOK: type: LOAD
#### A masked pattern was here ####
PREHOOK: Output: default@t1
POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@t1
PREHOOK: query: -- This tests that cubes and rollups work fine inside sub-queries.
EXPLAIN
SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
PREHOOK: type: QUERY
POSTHOOK: query: -- This tests that cubes and rollups work fine inside sub-queries.
EXPLAIN
SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1, Stage-3
  Stage-3 is a root stage
  Stage-0 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: t1
            Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (a < 3) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Group By Operator
                aggregations: count()
                keys: a (type: string), b (type: string), '0' (type: string)
                mode: hash
                outputColumnNames: _col0, _col1, _col2, _col3
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                  sort order: +++
                  Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                  value expressions: _col3 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
          mode: mergepartial
          outputColumnNames: _col0, _col1, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          pruneGroupingSetId: true
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
            outputColumnNames: _col0, _col1, _col2
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string)
              sort order: +
              Map-reduce partition columns: _col0 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col1 (type: string), _col2 (type: bigint)
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string)
              sort order: +
              Map-reduce partition columns: _col0 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col1 (type: string), _col2 (type: bigint)
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          keys:
            0 _col0 (type: string)
            1 _col0 (type: string)
          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), _col5 (type: bigint)
            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              table:
                  input format: org.apache.hadoop.mapred.TextInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe

  Stage: Stage-3
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: t1
            Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (a < 3) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Group By Operator
                aggregations: count()
                keys: a (type: string), b (type: string), '0' (type: string)
                mode: hash
                outputColumnNames: _col0, _col1, _col2, _col3
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                  sort order: +++
                  Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                  value expressions: _col3 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
          mode: mergepartial
          outputColumnNames: _col0, _col1, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          pruneGroupingSetId: true
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
            outputColumnNames: _col0, _col1, _col2
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-0
    Fetch Operator
      limit: -1
      Processor Tree:
        ListSink

PREHOOK: query: SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
#### A masked pattern was here ####
POSTHOOK: query: SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
#### A masked pattern was here ####
1	1	1	1	1	1
1	1	1	1	NULL	1
1	NULL	1	1	1	1
1	NULL	1	1	NULL	1
2	2	1	2	2	1
2	2	1	2	3	1
2	2	1	2	NULL	2
2	3	1	2	2	1
2	3	1	2	3	1
2	3	1	2	NULL	2
2	NULL	2	2	2	1
2	NULL	2	2	3	1
2	NULL	2	2	NULL	2
PREHOOK: query: -- Since 4 grouping sets would be generated for each sub-query, an additional MR job should be created
-- for each of them
EXPLAIN
SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
PREHOOK: type: QUERY
POSTHOOK: query: -- Since 4 grouping sets would be generated for each sub-query, an additional MR job should be created
-- for each of them
EXPLAIN
SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1
  Stage-3 depends on stages: Stage-2, Stage-5
  Stage-4 is a root stage
  Stage-5 depends on stages: Stage-4
  Stage-0 depends on stages: Stage-3

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: t1
            Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (a < 3) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Group By Operator
                aggregations: count()
                keys: a (type: string), b (type: string)
                mode: hash
                outputColumnNames: _col0, _col1, _col2
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                  value expressions: _col2 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), '0' (type: string)
          mode: partials
          outputColumnNames: _col0, _col1, _col2, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          File Output Operator
            compressed: false
            table:
                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              sort order: +++
              Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col3 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
          mode: final
          outputColumnNames: _col0, _col1, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          pruneGroupingSetId: true
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
            outputColumnNames: _col0, _col1, _col2
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-3
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string)
              sort order: +
              Map-reduce partition columns: _col0 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col1 (type: string), _col2 (type: bigint)
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string)
              sort order: +
              Map-reduce partition columns: _col0 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col1 (type: string), _col2 (type: bigint)
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
          keys:
            0 _col0 (type: string)
            1 _col0 (type: string)
          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: string), _col4 (type: string), _col5 (type: bigint)
            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              table:
                  input format: org.apache.hadoop.mapred.TextInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe

  Stage: Stage-4
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: t1
            Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
            Filter Operator
              predicate: (a < 3) (type: boolean)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              Group By Operator
                aggregations: count()
                keys: a (type: string), b (type: string)
                mode: hash
                outputColumnNames: _col0, _col1, _col2
                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                  value expressions: _col2 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), '0' (type: string)
          mode: partials
          outputColumnNames: _col0, _col1, _col2, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          File Output Operator
            compressed: false
            table:
                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-5
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              sort order: +++
              Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
              value expressions: _col3 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
          mode: final
          outputColumnNames: _col0, _col1, _col3
          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
          pruneGroupingSetId: true
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
            outputColumnNames: _col0, _col1, _col2
            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
            File Output Operator
              compressed: false
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-0
    Fetch Operator
      limit: -1
      Processor Tree:
        ListSink

PREHOOK: query: SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
#### A masked pattern was here ####
POSTHOOK: query: SELECT * FROM
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq1
join
(SELECT a, b, count(*) from T1 where a < 3 group by a, b with cube) subq2
on subq1.a = subq2.a
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
#### A masked pattern was here ####
1	1	1	1	1	1
1	1	1	1	NULL	1
1	NULL	1	1	1	1
1	NULL	1	1	NULL	1
2	2	1	2	2	1
2	2	1	2	3	1
2	2	1	2	NULL	2
2	3	1	2	2	1
2	3	1	2	3	1
2	3	1	2	NULL	2
2	NULL	2	2	2	1
2	NULL	2	2	3	1
2	NULL	2	2	NULL	2