Saving all output to "!!{outputDirectory}!!/mapjoin_filter_on_outerjoin.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/mapjoin_filter_on_outerjoin.q
>>>  set hive.auto.convert.join = false;
No rows affected 
>>>  --HIVE-2101 mapjoin sometimes gives wrong results if there is a filter in the on condition
>>>  
>>>  SELECT * FROM src1 
RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) 
JOIN src src3 ON (src2.key = src3.key AND src3.key < 300) 
SORT BY src1.key, src2.key, src3.key;
'key','value','key','value','key','value'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','146','val_146','146','val_146'
'','','146','val_146','146','val_146'
'','','150','val_150','150','val_150'
'','','213','val_213','213','val_213'
'','','213','val_213','213','val_213'
'','','224','','224','val_224'
'','','224','','224','val_224'
'','','238','val_238','238','val_238'
'','','238','val_238','238','val_238'
'','','255','val_255','255','val_255'
'','','255','val_255','255','val_255'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','278','val_278','278','val_278'
'','','278','val_278','278','val_278'
'','','66','val_66','66','val_66'
'','','98','val_98','98','val_98'
'','','98','val_98','98','val_98'
22 rows selected 
>>>  
>>>  explain 
SELECT /*+ mapjoin(src1, src2) */ * FROM src1 
RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) 
JOIN src src3 ON (src2.key = src3.key AND src3.key < 300) 
SORT BY src1.key, src2.key, src3.key;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1)) (TOK_TABREF (TOK_TABNAME src1) src2) (AND (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)) (< (. (TOK_TABLE_OR_COL src1) key) 10)) (> (. (TOK_TABLE_OR_COL src2) key) 10))) (TOK_TABREF (TOK_TABNAME src) src3) (AND (= (. (TOK_TABLE_OR_COL src2) key) (. (TOK_TABLE_OR_COL src3) key)) (< (. (TOK_TABLE_OR_COL src3) key) 300)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST src1 src2))) (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src2) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src3) key)))))'
''
'STAGE DEPENDENCIES:'
'  Stage-5 is a root stage'
'  Stage-1 depends on stages: Stage-5'
'  Stage-2 depends on stages: Stage-1'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-5'
'    Map Reduce Local Work'
'      Alias -> Map Local Tables:'
'        src1 '
'          Fetch Operator'
'            limit: -1'
'        src2 '
'          Fetch Operator'
'            limit: -1'
'      Alias -> Map Local Operator Tree:'
'        src1 '
'          TableScan'
'            alias: src1'
'            Filter Operator'
'              predicate:'
'                  expr: ((key < 10.0) and (key < 300.0))'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 2'
'        src2 '
'          TableScan'
'            alias: src2'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 2'
''
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src3 '
'          TableScan'
'            alias: src3'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              Map Join Operator'
'                condition map:'
'                     Right Outer Join0 to 1'
'                     Inner Join 1 to 2'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'                Position of Big Table: 2'
'                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}!! '
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col4'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'                  expr: _col8'
'                  type: string'
'                  expr: _col9'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'            Select Operator'
'              expressions:'
'                    expr: _col0'
'                    type: string'
'                    expr: _col1'
'                    type: string'
'                    expr: _col4'
'                    type: string'
'                    expr: _col5'
'                    type: string'
'                    expr: _col8'
'                    type: string'
'                    expr: _col9'
'                    type: string'
'              outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: _col0'
'                      type: string'
'                      expr: _col2'
'                      type: string'
'                      expr: _col4'
'                      type: string'
'                sort order: +++'
'                tag: -1'
'                value expressions:'
'                      expr: _col0'
'                      type: string'
'                      expr: _col1'
'                      type: string'
'                      expr: _col2'
'                      type: string'
'                      expr: _col3'
'                      type: string'
'                      expr: _col4'
'                      type: string'
'                      expr: _col5'
'                      type: string'
'      Reduce Operator Tree:'
'        Extract'
'          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-0'
'    Fetch Operator'
'      limit: -1'
''
''
174 rows selected 
>>>  
>>>  SELECT /*+ mapjoin(src1, src2) */ * FROM src1 
RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) 
JOIN src src3 ON (src2.key = src3.key AND src3.key < 300) 
SORT BY src1.key, src2.key, src3.key;
'key','value','key','value','key','value'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','146','val_146','146','val_146'
'','','146','val_146','146','val_146'
'','','150','val_150','150','val_150'
'','','213','val_213','213','val_213'
'','','213','val_213','213','val_213'
'','','224','','224','val_224'
'','','224','','224','val_224'
'','','238','val_238','238','val_238'
'','','238','val_238','238','val_238'
'','','255','val_255','255','val_255'
'','','255','val_255','255','val_255'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','278','val_278','278','val_278'
'','','278','val_278','278','val_278'
'','','66','val_66','66','val_66'
'','','98','val_98','98','val_98'
'','','98','val_98','98','val_98'
22 rows selected 
>>>  
>>>  set hive.auto.convert.join = true;
No rows affected 
>>>  
>>>  explain 
SELECT * FROM src1 
RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) 
JOIN src src3 ON (src2.key = src3.key AND src3.key < 300) 
SORT BY src1.key, src2.key, src3.key;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1)) (TOK_TABREF (TOK_TABNAME src1) src2) (AND (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)) (< (. (TOK_TABLE_OR_COL src1) key) 10)) (> (. (TOK_TABLE_OR_COL src2) key) 10))) (TOK_TABREF (TOK_TABNAME src) src3) (AND (= (. (TOK_TABLE_OR_COL src2) key) (. (TOK_TABLE_OR_COL src3) key)) (< (. (TOK_TABLE_OR_COL src3) key) 300)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src2) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src3) key)))))'
''
'STAGE DEPENDENCIES:'
'  Stage-7 is a root stage , consists of Stage-8, Stage-9, Stage-1'
'  Stage-8 has a backup stage: Stage-1'
'  Stage-5 depends on stages: Stage-8'
'  Stage-2 depends on stages: Stage-1, Stage-5, Stage-6'
'  Stage-9 has a backup stage: Stage-1'
'  Stage-6 depends on stages: Stage-9'
'  Stage-1'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-7'
'    Conditional Operator'
''
'  Stage: Stage-8'
'    Map Reduce Local Work'
'      Alias -> Map Local Tables:'
'        src1 '
'          Fetch Operator'
'            limit: -1'
'        src3 '
'          Fetch Operator'
'            limit: -1'
'      Alias -> Map Local Operator Tree:'
'        src1 '
'          TableScan'
'            alias: src1'
'            Filter Operator'
'              predicate:'
'                  expr: ((key < 10.0) and (key < 300.0))'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 1'
'        src3 '
'          TableScan'
'            alias: src3'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 1'
''
'  Stage: Stage-5'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src2 '
'          TableScan'
'            alias: src2'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              Map Join Operator'
'                condition map:'
'                     Right Outer Join0 to 1'
'                     Inner Join 1 to 2'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'                Position of Big Table: 1'
'                Select Operator'
'                  expressions:'
'                        expr: _col0'
'                        type: string'
'                        expr: _col1'
'                        type: string'
'                        expr: _col4'
'                        type: string'
'                        expr: _col5'
'                        type: string'
'                        expr: _col8'
'                        type: string'
'                        expr: _col9'
'                        type: string'
'                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5'
'                  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}!! '
'            Reduce Output Operator'
'              key expressions:'
'                    expr: _col0'
'                    type: string'
'                    expr: _col2'
'                    type: string'
'                    expr: _col4'
'                    type: string'
'              sort order: +++'
'              tag: -1'
'              value expressions:'
'                    expr: _col0'
'                    type: string'
'                    expr: _col1'
'                    type: string'
'                    expr: _col2'
'                    type: string'
'                    expr: _col3'
'                    type: string'
'                    expr: _col4'
'                    type: string'
'                    expr: _col5'
'                    type: string'
'      Reduce Operator Tree:'
'        Extract'
'          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-9'
'    Map Reduce Local Work'
'      Alias -> Map Local Tables:'
'        src1 '
'          Fetch Operator'
'            limit: -1'
'        src2 '
'          Fetch Operator'
'            limit: -1'
'      Alias -> Map Local Operator Tree:'
'        src1 '
'          TableScan'
'            alias: src1'
'            Filter Operator'
'              predicate:'
'                  expr: ((key < 10.0) and (key < 300.0))'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 2'
'        src2 '
'          TableScan'
'            alias: src2'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              HashTable Sink Operator'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                Position of Big Table: 2'
''
'  Stage: Stage-6'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src3 '
'          TableScan'
'            alias: src3'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              Map Join Operator'
'                condition map:'
'                     Right Outer Join0 to 1'
'                     Inner Join 1 to 2'
'                condition expressions:'
'                  0 {key} {value}'
'                  1 {key} {value}'
'                  2 {key} {value}'
'                filter predicates:'
'                  0 '
'                  1 {(key > 10.0)}'
'                  2 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key]]'
'                  1 [Column[key]]'
'                  2 [Column[key]]'
'                outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'                Position of Big Table: 2'
'                Select Operator'
'                  expressions:'
'                        expr: _col0'
'                        type: string'
'                        expr: _col1'
'                        type: string'
'                        expr: _col4'
'                        type: string'
'                        expr: _col5'
'                        type: string'
'                        expr: _col8'
'                        type: string'
'                        expr: _col9'
'                        type: string'
'                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5'
'                  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-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        src1 '
'          TableScan'
'            alias: src1'
'            Filter Operator'
'              predicate:'
'                  expr: ((key < 10.0) and (key < 300.0))'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 0'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'        src2 '
'          TableScan'
'            alias: src2'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 1'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'        src3 '
'          TableScan'
'            alias: src3'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 300.0)'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 2'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: value'
'                      type: string'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Right Outer Join0 to 1'
'               Inner Join 1 to 2'
'          condition expressions:'
'            0 {VALUE._col0} {VALUE._col1}'
'            1 {VALUE._col0} {VALUE._col1}'
'            2 {VALUE._col0} {VALUE._col1}'
'          filter predicates:'
'            0 '
'            1 {(VALUE._col0 > 10.0)}'
'            2 '
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col4'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'                  expr: _col8'
'                  type: string'
'                  expr: _col9'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5'
'            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'
''
''
377 rows selected 
>>>  
>>>  SELECT * FROM src1 
RIGHT OUTER JOIN src1 src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) 
JOIN src src3 ON (src2.key = src3.key AND src3.key < 300) 
SORT BY src1.key, src2.key, src3.key;
'key','value','key','value','key','value'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','128','','128','val_128'
'','','146','val_146','146','val_146'
'','','146','val_146','146','val_146'
'','','150','val_150','150','val_150'
'','','213','val_213','213','val_213'
'','','213','val_213','213','val_213'
'','','224','','224','val_224'
'','','224','','224','val_224'
'','','238','val_238','238','val_238'
'','','238','val_238','238','val_238'
'','','255','val_255','255','val_255'
'','','255','val_255','255','val_255'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','273','val_273','273','val_273'
'','','278','val_278','278','val_278'
'','','278','val_278','278','val_278'
'','','66','val_66','66','val_66'
'','','98','val_98','98','val_98'
'','','98','val_98','98','val_98'
22 rows selected 
>>>  !record