PREHOOK: query: 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: 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: -- Since 4 grouping sets would be generated for the query below, an additional MR job should be created
EXPLAIN
SELECT a, b, count(*) from T1 group by a, b with cube
PREHOOK: type: QUERY
POSTHOOK: query: -- Since 4 grouping sets would be generated for the query below, an additional MR job should be created
EXPLAIN
SELECT a, b, count(*) from T1 group by a, b with cube
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1
  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
            Select Operator
              expressions: a (type: string), b (type: string)
              outputColumnNames: _col0, _col1
              Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
              Group By Operator
                aggregations: count()
                keys: _col0 (type: string), _col1 (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
              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-0
    Fetch Operator
      limit: -1
      Processor Tree:
        ListSink

PREHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, count(*) from T1 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
#### A masked pattern was here ####
NULL	NULL	6
NULL	1	2
NULL	2	3
NULL	3	1
1	NULL	1
1	1	1
2	NULL	2
2	2	1
2	3	1
3	NULL	1
3	2	1
5	NULL	1
5	2	1
8	NULL	1
8	1	1
PREHOOK: query: EXPLAIN
SELECT a, b, sum(c) from T1 group by a, b with cube
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT a, b, sum(c) from T1 group by a, b with cube
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1
  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
            Select Operator
              expressions: a (type: string), b (type: string), c (type: string)
              outputColumnNames: _col0, _col1, _col2
              Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
              Group By Operator
                aggregations: sum(_col2)
                keys: _col0 (type: string), _col1 (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: double)
      Reduce Operator Tree:
        Group By Operator
          aggregations: sum(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: double)
      Reduce Operator Tree:
        Group By Operator
          aggregations: sum(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: double)
            outputColumnNames: _col0, _col1, _col2
            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-0
    Fetch Operator
      limit: -1
      Processor Tree:
        ListSink

PREHOOK: query: SELECT a, b, sum(c) from T1 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, sum(c) from T1 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
#### A masked pattern was here ####
NULL	NULL	23.0
NULL	1	4.0
NULL	2	14.0
NULL	3	5.0
1	NULL	3.0
1	1	3.0
2	NULL	9.0
2	2	4.0
2	3	5.0
3	NULL	8.0
3	2	8.0
5	NULL	2.0
5	2	2.0
8	NULL	1.0
8	1	1.0
PREHOOK: query: CREATE TABLE T2(a STRING, b STRING, c int, d int)
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@T2
POSTHOOK: query: CREATE TABLE T2(a STRING, b STRING, c int, d int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2
PREHOOK: query: INSERT OVERWRITE TABLE T2
SELECT a, b, c, c from T1
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Output: default@t2
POSTHOOK: query: INSERT OVERWRITE TABLE T2
SELECT a, b, c, c from T1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Output: default@t2
POSTHOOK: Lineage: t2.a SIMPLE [(t1)t1.FieldSchema(name:a, type:string, comment:null), ]
POSTHOOK: Lineage: t2.b SIMPLE [(t1)t1.FieldSchema(name:b, type:string, comment:null), ]
POSTHOOK: Lineage: t2.c EXPRESSION [(t1)t1.FieldSchema(name:c, type:string, comment:null), ]
POSTHOOK: Lineage: t2.d EXPRESSION [(t1)t1.FieldSchema(name:c, type:string, comment:null), ]
PREHOOK: query: EXPLAIN
SELECT a, b, sum(c+d) from T2 group by a, b with cube
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT a, b, sum(c+d) from T2 group by a, b with cube
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1
  Stage-0 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: t2
            Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
            Select Operator
              expressions: a (type: string), b (type: string), (c + d) (type: int)
              outputColumnNames: _col0, _col1, _col2
              Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
              Group By Operator
                aggregations: sum(_col2)
                keys: _col0 (type: string), _col1 (type: string)
                mode: hash
                outputColumnNames: _col0, _col1, _col2
                Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: string), _col1 (type: string)
                  sort order: ++
                  Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
                  Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                  value expressions: _col2 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: sum(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), '0' (type: string)
          mode: partials
          outputColumnNames: _col0, _col1, _col2, _col3
          Statistics: Num rows: 24 Data size: 168 Basic stats: COMPLETE Column stats: NONE
          File Output Operator
            compressed: false
            table:
                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              sort order: +++
              Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
              Statistics: Num rows: 24 Data size: 168 Basic stats: COMPLETE Column stats: NONE
              value expressions: _col3 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: sum(VALUE._col0)
          keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
          mode: final
          outputColumnNames: _col0, _col1, _col3
          Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE
          pruneGroupingSetId: true
          Select Operator
            expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
            outputColumnNames: _col0, _col1, _col2
            Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 12 Data size: 84 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
      Processor Tree:
        ListSink

PREHOOK: query: SELECT a, b, sum(c+d) from T2 group by a, b with cube
PREHOOK: type: QUERY
PREHOOK: Input: default@t2
#### A masked pattern was here ####
POSTHOOK: query: SELECT a, b, sum(c+d) from T2 group by a, b with cube
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t2
#### A masked pattern was here ####
NULL	NULL	46
NULL	1	8
NULL	2	28
NULL	3	10
1	NULL	6
1	1	6
2	NULL	18
2	2	8
2	3	10
3	NULL	16
3	2	16
5	NULL	4
5	2	4
8	NULL	2
8	1	2