Saving all output to "!!{outputDirectory}!!/auto_join4.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/auto_join4.q >>> set hive.auto.convert.join = true; No rows affected >>> >>> CREATE TABLE dest1(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS TEXTFILE; No rows affected >>> >>> explain FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) src1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key) c1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) value) c2)) (TOK_WHERE (and (> (. (TOK_TABLE_OR_COL src1) key) 10) (< (. (TOK_TABLE_OR_COL src1) key) 20))))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) src2)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) key) c3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) value) c4)) (TOK_WHERE (and (> (. (TOK_TABLE_OR_COL src2) key) 15) (< (. (TOK_TABLE_OR_COL src2) key) 25))))) b) (= (. (TOK_TABLE_OR_COL a) c1) (. (TOK_TABLE_OR_COL b) c3)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) c1) c1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) c2) c2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) c3) c3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) c4) c4)))) c)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL c) c1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL c) c2)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL c) c3)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL c) c4)))))' '' 'STAGE DEPENDENCIES:' ' Stage-5 is a root stage , consists of Stage-6, Stage-1' ' Stage-6 has a backup stage: Stage-1' ' Stage-4 depends on stages: Stage-6' ' Stage-0 depends on stages: Stage-1, Stage-4' ' Stage-2 depends on stages: Stage-0' ' Stage-1' '' 'STAGE PLANS:' ' Stage: Stage-5' ' Conditional Operator' '' ' Stage: Stage-6' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' c:b:src2 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' c:b:src2 ' ' TableScan' ' alias: src2' ' Filter Operator' ' predicate:' ' expr: ((key > 15) and (key < 25))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' HashTable Sink Operator' ' condition expressions:' ' 0 {_col0} {_col1}' ' 1 {_col0} {_col1}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' Position of Big Table: 0' '' ' Stage: Stage-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' c:a:src1 ' ' TableScan' ' alias: src1' ' Filter Operator' ' predicate:' ' expr: ((key > 10) and (key < 20))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Map Join Operator' ' condition map:' ' Left Outer Join0 to 1' ' condition expressions:' ' 0 {_col0} {_col1}' ' 1 {_col0} {_col1}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Position of Big Table: 0' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' expr: _col1' ' type: string' ' expr: UDFToInteger(_col2)' ' type: int' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' 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: auto_join4.dest1' ' Local Work:' ' Map Reduce Local Work' '' ' 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: auto_join4.dest1' '' ' Stage: Stage-2' ' Stats-Aggr Operator' '' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' c:a:src1 ' ' TableScan' ' alias: src1' ' Filter Operator' ' predicate:' ' expr: ((key > 10) and (key < 20))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 0' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' c:b:src2 ' ' TableScan' ' alias: src2' ' Filter Operator' ' predicate:' ' expr: ((key > 15) and (key < 25))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 1' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Left Outer Join0 to 1' ' condition expressions:' ' 0 {VALUE._col0} {VALUE._col1}' ' 1 {VALUE._col0} {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' expr: _col1' ' type: string' ' expr: UDFToInteger(_col2)' ' type: int' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' 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: auto_join4.dest1' '' '' 243 rows selected >>> >>> FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4; '_col0','_col1','_col2','_col3' No rows selected >>> >>> SELECT sum(hash(dest1.c1,dest1.c2,dest1.c3,dest1.c4)) FROM dest1; '_c0' '5079148035' 1 row selected >>> !record