Saving all output to "!!{outputDirectory}!!/skewjoinopt10.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/skewjoinopt10.q
>>>  set hive.internal.ddl.list.bucketing.enable=true;
No rows affected 
>>>  set hive.optimize.skewjoin.compiletime = true;
No rows affected 
>>>  
>>>  CREATE TABLE T1(key STRING, value STRING) STORED AS TEXTFILE;
No rows affected 
>>>  
>>>  LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1;
No rows affected 
>>>  
>>>  drop table array_valued_T1;
No rows affected 
>>>  create table array_valued_T1 (key string, value array<string>) SKEWED BY (key) ON ((8));
No rows affected 
>>>  insert overwrite table array_valued_T1 select key, array(value) from T1;
'key','_c1'
No rows selected 
>>>  
>>>  -- This test is to verify the skew join compile optimization when the join is followed by a lateral view
>>>  -- adding a order by at the end to make the results deterministic
>>>  
>>>  explain 
select * from (select a.key as key, b.value as array_val from T1 a join array_valued_T1 b on a.key=b.key) i lateral view explode (array_val) c as val;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_LATERAL_VIEW (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION explode (TOK_TABLE_OR_COL array_val)) val (TOK_TABALIAS c))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME array_valued_T1) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) array_val)))) i))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-2 depends on stages: Stage-1, Stage-3'
'  Stage-3 is a root stage'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        subquery1:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '8'))'
'                  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'
'        subquery1:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '8'))'
'                  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: value'
'                      type: array<string>'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Inner Join 0 to 1'
'          condition expressions:'
'            0 {VALUE._col0}'
'            1 {VALUE._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col5'
'                  type: array<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-2'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                Lateral View Forward'
'                  Select Operator'
'                    SELECT * : (no compute)'
'                    Lateral View Join Operator'
'                      outputColumnNames: _col0, _col1, _col2'
'                      Select Operator'
'                        expressions:'
'                              expr: _col0'
'                              type: string'
'                              expr: _col1'
'                              type: array<string>'
'                              expr: _col2'
'                              type: string'
'                        outputColumnNames: _col0, _col1, _col2'
'                        File Output Operator'
'                          compressed: false'
'                          GlobalTableId: 0'
'                          table:'
'                              input format: org.apache.hadoop.mapred.TextInputFormat'
'                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
'                  Select Operator'
'                    expressions:'
'                          expr: _col1'
'                          type: array<string>'
'                    outputColumnNames: _col0'
'                    UDTF Operator'
'                      function name: explode'
'                      Lateral View Join Operator'
'                        outputColumnNames: _col0, _col1, _col2'
'                        Select Operator'
'                          expressions:'
'                                expr: _col0'
'                                type: string'
'                                expr: _col1'
'                                type: array<string>'
'                                expr: _col2'
'                                type: string'
'                          outputColumnNames: _col0, _col1, _col2'
'                          File Output Operator'
'                            compressed: false'
'                            GlobalTableId: 0'
'                            table:'
'                                input format: org.apache.hadoop.mapred.TextInputFormat'
'                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                Lateral View Forward'
'                  Select Operator'
'                    SELECT * : (no compute)'
'                    Lateral View Join Operator'
'                      outputColumnNames: _col0, _col1, _col2'
'                      Select Operator'
'                        expressions:'
'                              expr: _col0'
'                              type: string'
'                              expr: _col1'
'                              type: array<string>'
'                              expr: _col2'
'                              type: string'
'                        outputColumnNames: _col0, _col1, _col2'
'                        File Output Operator'
'                          compressed: false'
'                          GlobalTableId: 0'
'                          table:'
'                              input format: org.apache.hadoop.mapred.TextInputFormat'
'                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
'                  Select Operator'
'                    expressions:'
'                          expr: _col1'
'                          type: array<string>'
'                    outputColumnNames: _col0'
'                    UDTF Operator'
'                      function name: explode'
'                      Lateral View Join Operator'
'                        outputColumnNames: _col0, _col1, _col2'
'                        Select Operator'
'                          expressions:'
'                                expr: _col0'
'                                type: string'
'                                expr: _col1'
'                                type: array<string>'
'                                expr: _col2'
'                                type: string'
'                          outputColumnNames: _col0, _col1, _col2'
'                          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-3'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        i:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '8')'
'                  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'
'        i:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '8')'
'                  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: value'
'                      type: array<string>'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Inner Join 0 to 1'
'          condition expressions:'
'            0 {VALUE._col0}'
'            1 {VALUE._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col5'
'                  type: array<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-0'
'    Fetch Operator'
'      limit: -1'
''
''
245 rows selected 
>>>  
>>>  select * from (select a.key as key, b.value as array_val from T1 a join array_valued_T1 b on a.key=b.key) i lateral view explode (array_val) c as val 
ORDER BY key, val;
'key','array_val','val'
'1','[11]','11'
'2','[12]','12'
'3','[13]','13'
'7','[17]','17'
'8','[18]','18'
'8','[18]','18'
'8','[28]','28'
'8','[28]','28'
8 rows selected 
>>>  !record