Saving all output to "!!{outputDirectory}!!/auto_join27.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/auto_join27.q
>>>  set hive.auto.convert.join = true;
No rows affected 
>>>  
>>>  explain 
SELECT count(1) 
FROM 
( 
SELECT src.key, src.value from src 
UNION ALL 
SELECT DISTINCT src.key, src.value from src 
) src_12 
JOIN 
(SELECT src.key as k, src.value as v from src) src3 
ON src_12.key = src3.k AND src3.k < 200;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECTDI (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value)))))) src_12) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key) k) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) v)))) src3) (AND (= (. (TOK_TABLE_OR_COL src_12) key) (. (TOK_TABLE_OR_COL src3) k)) (< (. (TOK_TABLE_OR_COL src3) k) 200)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-8 depends on stages: Stage-1 , consists of Stage-9, Stage-10, Stage-2'
'  Stage-9 has a backup stage: Stage-2'
'  Stage-6 depends on stages: Stage-9'
'  Stage-3 depends on stages: Stage-2, Stage-6, Stage-7'
'  Stage-10 has a backup stage: Stage-2'
'  Stage-7 depends on stages: Stage-10'
'  Stage-2'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        null-subquery2:src_12-subquery2:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'                outputColumnNames: key, value'
'                Group By Operator'
'                  bucketGroup: false'
'                  keys:'
'                        expr: key'
'                        type: string'
'                        expr: value'
'                        type: string'
'                  mode: hash'
'                  outputColumnNames: _col0, _col1'
'                  Reduce Output Operator'
'                    key expressions:'
'                          expr: _col0'
'                          type: string'
'                          expr: _col1'
'                          type: string'
'                    sort order: ++'
'                    Map-reduce partition columns:'
'                          expr: _col0'
'                          type: string'
'                          expr: _col1'
'                          type: string'
'                    tag: -1'
'      Reduce Operator Tree:'
'        Group By Operator'
'          bucketGroup: false'
'          keys:'
'                expr: KEY._col0'
'                type: string'
'                expr: KEY._col1'
'                type: string'
'          mode: mergepartial'
'          outputColumnNames: _col0, _col1'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'            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'
'    Conditional Operator'
''
'  Stage: Stage-9'
'    Map Reduce Local Work'
'      Alias -> Map Local Tables:'
'        src3:src '
'          Fetch Operator'
'            limit: -1'
'      Alias -> Map Local Operator Tree:'
'        src3:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                outputColumnNames: _col0'
'                HashTable Sink Operator'
'                  condition expressions:'
'                    0 '
'                    1 '
'                  handleSkewJoin: false'
'                  keys:'
'                    0 [Column[_col0]]'
'                    1 [Column[_col0]]'
'                  Position of Big Table: 0'
''
'  Stage: Stage-6'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Map Join Operator'
'                condition map:'
'                     Inner Join 0 to 1'
'                condition expressions:'
'                  0 '
'                  1 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[_col0]]'
'                  1 [Column[_col0]]'
'                Position of Big Table: 0'
'                Select Operator'
'                  Group By Operator'
'                    aggregations:'
'                          expr: count(1)'
'                    bucketGroup: false'
'                    mode: hash'
'                    outputColumnNames: _col0'
'                    File Output Operator'
'                      compressed: false'
'                      GlobalTableId: 0'
'                      table:'
'                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
'        null-subquery1:src_12-subquery1:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'                outputColumnNames: _col0, _col1'
'                Union'
'                  Map Join Operator'
'                    condition map:'
'                         Inner Join 0 to 1'
'                    condition expressions:'
'                      0 '
'                      1 '
'                    handleSkewJoin: false'
'                    keys:'
'                      0 [Column[_col0]]'
'                      1 [Column[_col0]]'
'                    Position of Big Table: 0'
'                    Select Operator'
'                      Group By Operator'
'                        aggregations:'
'                              expr: count(1)'
'                        bucketGroup: false'
'                        mode: hash'
'                        outputColumnNames: _col0'
'                        File Output Operator'
'                          compressed: false'
'                          GlobalTableId: 0'
'                          table:'
'                              input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                              output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
'      Local Work:'
'        Map Reduce Local Work'
''
'  Stage: Stage-3'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'            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: _col0'
'                  type: bigint'
'            outputColumnNames: _col0'
'            File Output Operator'
'              compressed: false'
'              GlobalTableId: 0'
'              table:'
'                  input format: org.apache.hadoop.mapred.TextInputFormat'
'                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
''
'  Stage: Stage-10'
'    Map Reduce Local Work'
'      Alias -> Map Local Tables:'
'        file:!!{hive.exec.scratchdir}!! '
'          Fetch Operator'
'            limit: -1'
'        null-subquery1:src_12-subquery1:src '
'          Fetch Operator'
'            limit: -1'
'      Alias -> Map Local Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 '
'                  1 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[_col0]]'
'                  1 [Column[_col0]]'
'                Position of Big Table: 1'
'        null-subquery1:src_12-subquery1:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'                outputColumnNames: _col0, _col1'
'                Union'
'                  HashTable Sink Operator'
'                    condition expressions:'
'                      0 '
'                      1 '
'                    handleSkewJoin: false'
'                    keys:'
'                      0 [Column[_col0]]'
'                      1 [Column[_col0]]'
'                    Position of Big Table: 1'
''
'  Stage: Stage-7'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src3:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                outputColumnNames: _col0'
'                Map Join Operator'
'                  condition map:'
'                       Inner Join 0 to 1'
'                  condition expressions:'
'                    0 '
'                    1 '
'                  handleSkewJoin: false'
'                  keys:'
'                    0 [Column[_col0]]'
'                    1 [Column[_col0]]'
'                  Position of Big Table: 1'
'                  Select Operator'
'                    Group By Operator'
'                      aggregations:'
'                            expr: count(1)'
'                      bucketGroup: false'
'                      mode: hash'
'                      outputColumnNames: _col0'
'                      File Output Operator'
'                        compressed: false'
'                        GlobalTableId: 0'
'                        table:'
'                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
'      Local Work:'
'        Map Reduce Local Work'
''
'  Stage: Stage-2'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: _col0'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: _col0'
'                      type: string'
'                tag: 0'
'        null-subquery1:src_12-subquery1:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'                outputColumnNames: _col0, _col1'
'                Union'
'                  Reduce Output Operator'
'                    key expressions:'
'                          expr: _col0'
'                          type: string'
'                    sort order: +'
'                    Map-reduce partition columns:'
'                          expr: _col0'
'                          type: string'
'                    tag: 0'
'        src3:src '
'          TableScan'
'            alias: src'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 200)'
'                  type: boolean'
'              Select Operator'
'                expressions:'
'                      expr: key'
'                      type: string'
'                outputColumnNames: _col0'
'                Reduce Output Operator'
'                  key expressions:'
'                        expr: _col0'
'                        type: string'
'                  sort order: +'
'                  Map-reduce partition columns:'
'                        expr: _col0'
'                        type: string'
'                  tag: 1'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Inner Join 0 to 1'
'          condition expressions:'
'            0 '
'            1 '
'          handleSkewJoin: false'
'          Select Operator'
'            Group By Operator'
'              aggregations:'
'                    expr: count(1)'
'              bucketGroup: false'
'              mode: hash'
'              outputColumnNames: _col0'
'              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-0'
'    Fetch Operator'
'      limit: -1'
''
''
387 rows selected 
>>>  
>>>  
>>>  SELECT count(1) 
FROM 
( 
SELECT src.key, src.value from src 
UNION ALL 
SELECT DISTINCT src.key, src.value from src 
) src_12 
JOIN 
(SELECT src.key as k, src.value as v from src) src3 
ON src_12.key = src3.k AND src3.k < 200;
'_c0'
'548'
1 row selected 
>>>  !record