PREHOOK: query: -- union case: all subqueries are a map-reduce jobs, 3 way union, same input for all sub-queries, followed by filesink

create table tmptable(key string, value int)
PREHOOK: type: CREATETABLE
POSTHOOK: query: -- union case: all subqueries are a map-reduce jobs, 3 way union, same input for all sub-queries, followed by filesink

create table tmptable(key string, value int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: default@tmptable
PREHOOK: query: explain 
insert overwrite table tmptable
  select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
                                        UNION  ALL  
                                            select 'tst2' as key, count(1) as value from src s2
                                        UNION ALL
                                            select 'tst3' as key, count(1) as value from src s3) unionsrc
PREHOOK: type: QUERY
POSTHOOK: query: explain 
insert overwrite table tmptable
  select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
                                        UNION  ALL  
                                            select 'tst2' as key, count(1) as value from src s2
                                        UNION ALL
                                            select 'tst3' as key, count(1) as value from src s3) unionsrc
POSTHOOK: type: QUERY
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) s1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR 'tst1' key) (TOK_SELEXPR (TOK_FUNCTION count 1) value)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) s2)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR 'tst2' key) (TOK_SELEXPR (TOK_FUNCTION count 1) value))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) s3)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR 'tst3' key) (TOK_SELEXPR (TOK_FUNCTION count 1) value))))) unionsrc)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME tmptable))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL unionsrc) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL unionsrc) value)))))

STAGE DEPENDENCIES:
  Stage-1 is a root stage
  Stage-2 depends on stages: Stage-1, Stage-7, Stage-8
  Stage-6 depends on stages: Stage-2 , consists of Stage-5, Stage-4
  Stage-5
  Stage-0 depends on stages: Stage-5, Stage-4
  Stage-3 depends on stages: Stage-0
  Stage-4
  Stage-7 is a root stage
  Stage-8 is a root stage

STAGE PLANS:
  Stage: Stage-1
    Map Reduce
      Alias -> Map Operator Tree:
        null-subquery1-subquery1:unionsrc-subquery1-subquery1:s1 
          TableScan
            alias: s1
            Select Operator
              Group By Operator
                aggregations:
                      expr: count(1)
                bucketGroup: false
                mode: hash
                outputColumnNames: _col0
                Reduce Output Operator
                  sort order: 
                  tag: -1
                  value expressions:
                        expr: _col0
                        type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: count(VALUE._col0)
          bucketGroup: false
          mode: mergepartial
          outputColumnNames: _col0
          Select Operator
            expressions:
                  expr: 'tst1'
                  type: string
                  expr: _col0
                  type: bigint
            outputColumnNames: _col0, _col1
            File Output Operator
              compressed: false
              GlobalTableId: 0
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

  Stage: Stage-2
    Map Reduce
      Alias -> Map Operator Tree:
        file:/tmp/njain/hive_2011-12-07_18-02-38_989_3821093086240595817/-mr-10002 
          Union
            Select Operator
              expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: bigint
              outputColumnNames: _col0, _col1
              Select Operator
                expressions:
                      expr: _col0
                      type: string
                      expr: UDFToInteger(_col1)
                      type: int
                outputColumnNames: _col0, _col1
                File Output Operator
                  compressed: false
                  GlobalTableId: 1
                  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
                      name: default.tmptable
        file:/tmp/njain/hive_2011-12-07_18-02-38_989_3821093086240595817/-mr-10004 
          Union
            Select Operator
              expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: bigint
              outputColumnNames: _col0, _col1
              Select Operator
                expressions:
                      expr: _col0
                      type: string
                      expr: UDFToInteger(_col1)
                      type: int
                outputColumnNames: _col0, _col1
                File Output Operator
                  compressed: false
                  GlobalTableId: 1
                  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
                      name: default.tmptable
        file:/tmp/njain/hive_2011-12-07_18-02-38_989_3821093086240595817/-mr-10005 
          Union
            Select Operator
              expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: bigint
              outputColumnNames: _col0, _col1
              Select Operator
                expressions:
                      expr: _col0
                      type: string
                      expr: UDFToInteger(_col1)
                      type: int
                outputColumnNames: _col0, _col1
                File Output Operator
                  compressed: false
                  GlobalTableId: 1
                  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
                      name: default.tmptable

  Stage: Stage-6
    Conditional Operator

  Stage: Stage-5
    Move Operator
      files:
          hdfs directory: true
          destination: pfile:/data/users/njain/hive_commit2/build/ql/scratchdir/hive_2011-12-07_18-02-38_989_3821093086240595817/-ext-10000

  Stage: Stage-0
    Move Operator
      tables:
          replace: true
          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
              name: default.tmptable

  Stage: Stage-3
    Stats-Aggr Operator

  Stage: Stage-4
    Map Reduce
      Alias -> Map Operator Tree:
        pfile:/data/users/njain/hive_commit2/build/ql/scratchdir/hive_2011-12-07_18-02-38_989_3821093086240595817/-ext-10003 
            File Output Operator
              compressed: false
              GlobalTableId: 0
              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
                  name: default.tmptable

  Stage: Stage-7
    Map Reduce
      Alias -> Map Operator Tree:
        null-subquery1-subquery2:unionsrc-subquery1-subquery2:s2 
          TableScan
            alias: s2
            Select Operator
              Group By Operator
                aggregations:
                      expr: count(1)
                bucketGroup: false
                mode: hash
                outputColumnNames: _col0
                Reduce Output Operator
                  sort order: 
                  tag: -1
                  value expressions:
                        expr: _col0
                        type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: count(VALUE._col0)
          bucketGroup: false
          mode: mergepartial
          outputColumnNames: _col0
          Select Operator
            expressions:
                  expr: 'tst2'
                  type: string
                  expr: _col0
                  type: bigint
            outputColumnNames: _col0, _col1
            File Output Operator
              compressed: false
              GlobalTableId: 0
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

  Stage: Stage-8
    Map Reduce
      Alias -> Map Operator Tree:
        null-subquery2:unionsrc-subquery2:s3 
          TableScan
            alias: s3
            Select Operator
              Group By Operator
                aggregations:
                      expr: count(1)
                bucketGroup: false
                mode: hash
                outputColumnNames: _col0
                Reduce Output Operator
                  sort order: 
                  tag: -1
                  value expressions:
                        expr: _col0
                        type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: count(VALUE._col0)
          bucketGroup: false
          mode: mergepartial
          outputColumnNames: _col0
          Select Operator
            expressions:
                  expr: 'tst3'
                  type: string
                  expr: _col0
                  type: bigint
            outputColumnNames: _col0, _col1
            File Output Operator
              compressed: false
              GlobalTableId: 0
              table:
                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat


PREHOOK: query: insert overwrite table tmptable
  select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
                                        UNION  ALL  
                                            select 'tst2' as key, count(1) as value from src s2
                                        UNION ALL
                                            select 'tst3' as key, count(1) as value from src s3) unionsrc
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@tmptable
POSTHOOK: query: insert overwrite table tmptable
  select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
                                        UNION  ALL  
                                            select 'tst2' as key, count(1) as value from src s2
                                        UNION ALL
                                            select 'tst3' as key, count(1) as value from src s3) unionsrc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@tmptable
POSTHOOK: Lineage: tmptable.key EXPRESSION []
POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, (src)s3.null, ]
PREHOOK: query: select * from tmptable x sort by x.key
PREHOOK: type: QUERY
PREHOOK: Input: default@tmptable
PREHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-02-53_260_7981936505385901161/-mr-10000
POSTHOOK: query: select * from tmptable x sort by x.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@tmptable
POSTHOOK: Output: file:/tmp/njain/hive_2011-12-07_18-02-53_260_7981936505385901161/-mr-10000
POSTHOOK: Lineage: tmptable.key EXPRESSION []
POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, (src)s3.null, ]
tst1	500
tst2	500
tst3	500