PREHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@tbl1
POSTHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@tbl1
PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@tbl2
POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@tbl2
PREHOOK: query: insert overwrite table tbl1
select * from src where key < 10
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@tbl1
POSTHOOK: query: insert overwrite table tbl1
select * from src where key < 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@tbl1
POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: insert overwrite table tbl2
select * from src where key < 10
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@tbl2
POSTHOOK: query: insert overwrite table tbl2
select * from src where key < 10
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@tbl2
POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: -- One of the subqueries contains a union, so it should not be converted to a sort-merge join.
explain
select count(*) from 
  (
  select * from
  (select a.key as key, a.value as value from tbl1 a where key < 6
     union all
   select a.key as key, a.value as value from tbl1 a where key < 6
  ) usubq1 ) subq1
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
PREHOOK: type: QUERY
POSTHOOK: query: -- One of the subqueries contains a union, so it should not be converted to a sort-merge join.
explain
select count(*) from 
  (
  select * from
  (select a.key as key, a.value as value from tbl1 a where key < 6
     union all
   select a.key as key, a.value as value from tbl1 a where key < 6
  ) usubq1 ) subq1
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-6 is a root stage
  Stage-5 depends on stages: Stage-6
  Stage-2 depends on stages: Stage-5
  Stage-0 depends on stages: Stage-2

STAGE PLANS:
  Stage: Stage-6
    Map Reduce Local Work
      Alias -> Map Local Tables:
        subq2:a 
          Fetch Operator
            limit: -1
      Alias -> Map Local Operator Tree:
        subq2:a 
          TableScan
            alias: a
            Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: (key < 6) (type: boolean)
              Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
              Select Operator
                expressions: key (type: int)
                outputColumnNames: _col0
                Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                HashTable Sink Operator
                  keys:
                    0 _col0 (type: int)
                    1 _col0 (type: int)

  Stage: Stage-5
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: (key < 6) (type: boolean)
              Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
              Select Operator
                expressions: key (type: int)
                outputColumnNames: _col0
                Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                Union
                  Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col0 (type: int)
                    outputColumnNames: _col0
                    Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                    Map Join Operator
                      condition map:
                           Inner Join 0 to 1
                      keys:
                        0 _col0 (type: int)
                        1 _col0 (type: int)
                      Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        aggregations: count()
                        mode: hash
                        outputColumnNames: _col0
                        Statistics: Num rows: 1 Data size: 8 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
          TableScan
            alias: a
            Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: (key < 6) (type: boolean)
              Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
              Select Operator
                expressions: key (type: int)
                outputColumnNames: _col0
                Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                Union
                  Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col0 (type: int)
                    outputColumnNames: _col0
                    Statistics: Num rows: 6 Data size: 42 Basic stats: COMPLETE Column stats: NONE
                    Map Join Operator
                      condition map:
                           Inner Join 0 to 1
                      keys:
                        0 _col0 (type: int)
                        1 _col0 (type: int)
                      Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        aggregations: count()
                        mode: hash
                        outputColumnNames: _col0
                        Statistics: Num rows: 1 Data size: 8 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
      Local Work:
        Map Reduce Local Work

  Stage: Stage-2
    Map Reduce
      Map Operator Tree:
          TableScan
            Reduce Output Operator
              sort order: 
              Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
              value expressions: _col0 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          mode: mergepartial
          outputColumnNames: _col0
          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: bigint)
            outputColumnNames: _col0
            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 1 Data size: 8 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 count(*) from 
  (
  select * from
  (select a.key as key, a.value as value from tbl1 a where key < 6
     union all
   select a.key as key, a.value as value from tbl1 a where key < 6
  ) usubq1 ) subq1
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tbl1
PREHOOK: Input: default@tbl2
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from 
  (
  select * from
  (select a.key as key, a.value as value from tbl1 a where key < 6
     union all
   select a.key as key, a.value as value from tbl1 a where key < 6
  ) usubq1 ) subq1
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tbl1
POSTHOOK: Input: default@tbl2
#### A masked pattern was here ####
40
PREHOOK: query: -- One of the subqueries contains a groupby, so it should not be converted to a sort-merge join.
explain
select count(*) from 
  (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1 
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
PREHOOK: type: QUERY
POSTHOOK: query: -- One of the subqueries contains a groupby, so it should not be converted to a sort-merge join.
explain
select count(*) from 
  (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1 
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-6 depends on stages: Stage-1
  Stage-3 depends on stages: Stage-6
  Stage-0 depends on stages: Stage-3

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Map Operator Tree:
          TableScan
            alias: a
            Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: (key < 6) (type: boolean)
              Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
              Group By Operator
                aggregations: count()
                bucketGroup: true
                keys: key (type: int)
                mode: hash
                outputColumnNames: _col0, _col1
                Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                Reduce Output Operator
                  key expressions: _col0 (type: int)
                  sort order: +
                  Map-reduce partition columns: _col0 (type: int)
                  Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                  value expressions: _col1 (type: bigint)
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          keys: KEY._col0 (type: int)
          mode: mergepartial
          outputColumnNames: _col0, _col1
          Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: int)
            outputColumnNames: _col0
            Statistics: Num rows: 1 Data size: 7 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-6
    Map Reduce Local Work
      Alias -> Map Local Tables:
        subq2:a 
          Fetch Operator
            limit: -1
      Alias -> Map Local Operator Tree:
        subq2:a 
          TableScan
            alias: a
            Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
            Filter Operator
              predicate: (key < 6) (type: boolean)
              Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
              Select Operator
                expressions: key (type: int)
                outputColumnNames: _col0
                Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
                HashTable Sink Operator
                  keys:
                    0 _col0 (type: int)
                    1 _col0 (type: int)

  Stage: Stage-3
    Map Reduce
      Map Operator Tree:
          TableScan
            Map Join Operator
              condition map:
                   Inner Join 0 to 1
              keys:
                0 _col0 (type: int)
                1 _col0 (type: int)
              Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
              Group By Operator
                aggregations: count()
                mode: hash
                outputColumnNames: _col0
                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                Reduce Output Operator
                  sort order: 
                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                  value expressions: _col0 (type: bigint)
      Local Work:
        Map Reduce Local Work
      Reduce Operator Tree:
        Group By Operator
          aggregations: count(VALUE._col0)
          mode: mergepartial
          outputColumnNames: _col0
          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
          Select Operator
            expressions: _col0 (type: bigint)
            outputColumnNames: _col0
            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
            File Output Operator
              compressed: false
              Statistics: Num rows: 1 Data size: 8 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 count(*) from 
  (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1 
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tbl1
PREHOOK: Input: default@tbl2
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from 
  (select a.key as key, count(*) as value from tbl1 a where key < 6 group by a.key) subq1 
    join
  (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
  on subq1.key = subq2.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tbl1
POSTHOOK: Input: default@tbl2
#### A masked pattern was here ####
8