You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2013/07/18 11:16:53 UTC
svn commit: r1504395 [15/15] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/ ql/if/
ql/src/gen/thrift/gen-javabean/org/apache/hadoop/hive/ql/plan/api/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/q...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer9.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer9.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer9.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer9.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,1181 @@
+PREHOOK: query: CREATE TABLE tmp(c1 INT, c2 INT, c3 STRING, c4 STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE tmp(c1 INT, c2 INT, c3 STRING, c4 STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@tmp
+PREHOOK: query: INSERT OVERWRITE TABLE tmp
+SELECT x.key, y.key, x.value, y.value FROM src x JOIN src y ON (x.key = y.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@tmp
+POSTHOOK: query: INSERT OVERWRITE TABLE tmp
+SELECT x.key, y.key, x.value, y.value FROM src x JOIN src y ON (x.key = y.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@tmp
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c1) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) c1) 120)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) c1)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c2) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) c2) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) c2)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TO
K_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (c2 > 100)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c2
+ type: int
+ outputColumnNames: c2
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c2
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ 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:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 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: int
+ expr: _col2
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (c1 < 120)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ outputColumnNames: c1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+103 103 4 4
+104 104 4 4
+105 105 1 1
+111 111 1 1
+113 113 4 4
+114 114 1 1
+116 116 1 1
+118 118 4 4
+119 119 9 9
+PREHOOK: query: -- The merged table scan should be able to load both c1 and c2
+EXPLAIN
+SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The merged table scan should be able to load both c1 and c2
+EXPLAIN
+SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c1) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) c1) 120)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) c1)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c2) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) c2) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) c2)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TO
K_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (c1 < 120)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ outputColumnNames: c1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ yy:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (c2 > 100)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c2
+ type: int
+ outputColumnNames: c2
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c2
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Demux Operator
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 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: int
+ expr: _col2
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 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: int
+ expr: _col2
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: int
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ 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
+
+
+PREHOOK: query: SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1) xx
+JOIN
+(SELECT x1.c2 AS key, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c2) yy
+ON (xx.key = yy.key) ORDER BY xx.key, yy.key, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+103 103 4 4
+104 104 4 4
+105 105 1 1
+111 111 1 1
+113 113 4 4
+114 114 1 1
+116 116 1 1
+118 118 4 4
+119 119 9 9
+PREHOOK: query: EXPLAIN
+SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c1) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c3) key2) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) c1) 120)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) c1) (. (TOK_TABLE_OR_COL x) c3)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c1) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c3) key2) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) c2) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) c1) (. (TOK_TABLE_OR_COL x1) c3)))) yy) (AND (= (. (TOK_TABLE_OR_COL xx) key1) (. (TOK_TABLE_OR_COL yy) key1)) (== (. (TOK_TABLE_OR_COL xx) key2) (. (TOK_TABLE_OR_COL yy) key2))))) (TOK_INSERT (TOK_DESTINATION
(TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key2)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key2)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key1)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key2)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key1)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key2)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (c2 > 100)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ outputColumnNames: c1, c3
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ 1 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col3
+ type: int
+ expr: _col4
+ type: string
+ expr: _col2
+ type: bigint
+ expr: _col5
+ type: bigint
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: int
+ expr: _col3
+ type: string
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ sort order: ++++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: int
+ expr: _col3
+ type: string
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (c1 < 120)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ outputColumnNames: c1, c3
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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
+
+
+PREHOOK: query: SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+103 val_103 103 val_103 4 4
+104 val_104 104 val_104 4 4
+105 val_105 105 val_105 1 1
+111 val_111 111 val_111 1 1
+113 val_113 113 val_113 4 4
+114 val_114 114 val_114 1 1
+116 val_116 116 val_116 1 1
+118 val_118 118 val_118 4 4
+119 val_119 119 val_119 9 9
+PREHOOK: query: EXPLAIN
+SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c1) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) c3) key2) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) c1) 120)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) c1) (. (TOK_TABLE_OR_COL x) c3)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tmp) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c1) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) c3) key2) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) c2) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) c1) (. (TOK_TABLE_OR_COL x1) c3)))) yy) (AND (= (. (TOK_TABLE_OR_COL xx) key1) (. (TOK_TABLE_OR_COL yy) key1)) (== (. (TOK_TABLE_OR_COL xx) key2) (. (TOK_TABLE_OR_COL yy) key2))))) (TOK_INSERT (TOK_DESTINATION
(TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key2)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key2)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key1)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key2)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key1)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key2)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (c1 < 120)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ outputColumnNames: c1, c3
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col2
+ type: bigint
+ yy:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (c2 > 100)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ outputColumnNames: c1, c3
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: c1
+ type: int
+ expr: c3
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Demux Operator
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ 1 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col3
+ type: int
+ expr: _col4
+ type: string
+ expr: _col2
+ type: bigint
+ expr: _col5
+ type: bigint
+ 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
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ 1 {VALUE._col0} {VALUE._col1} {VALUE._col2}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col3
+ type: int
+ expr: _col4
+ type: string
+ expr: _col2
+ type: bigint
+ expr: _col5
+ type: bigint
+ 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-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: int
+ expr: _col3
+ type: string
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ sort order: ++++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: string
+ expr: _col2
+ type: int
+ expr: _col3
+ type: string
+ expr: _col4
+ type: bigint
+ expr: _col5
+ type: bigint
+ 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
+
+
+PREHOOK: query: SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+FROM
+(SELECT x.c1 AS key1, x.c3 AS key2, count(1) AS cnt FROM tmp x WHERE x.c1 < 120 GROUP BY x.c1, x.c3) xx
+JOIN
+(SELECT x1.c1 AS key1, x1.c3 AS key2, count(1) AS cnt FROM tmp x1 WHERE x1.c2 > 100 GROUP BY x1.c1, x1.c3) yy
+ON (xx.key1 = yy.key1 AND xx.key2 == yy.key2) ORDER BY xx.key1, xx.key2, yy.key1, yy.key2, xx.cnt, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmp
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tmp.c1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c2 EXPRESSION [(src)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c3 SIMPLE [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tmp.c4 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+103 val_103 103 val_103 4 4
+104 val_104 104 val_104 4 4
+105 val_105 105 val_105 1 1
+111 val_111 111 val_111 1 1
+113 val_113 113 val_113 4 4
+114 val_114 114 val_114 1 1
+116 val_116 116 val_116 1 1
+118 val_118 118 val_118 4 4
+119 val_119 119 val_119 9 9
Modified: hive/trunk/ql/src/test/results/compiler/plan/groupby2.q.xml
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/compiler/plan/groupby2.q.xml?rev=1504395&r1=1504394&r2=1504395&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/compiler/plan/groupby2.q.xml (original)
+++ hive/trunk/ql/src/test/results/compiler/plan/groupby2.q.xml Thu Jul 18 09:16:52 2013
@@ -193,6 +193,20 @@
</void>
</object>
</void>
+ <void method="put">
+ <string>KEY._col1:0._col0</string>
+ <object id="ExprNodeColumnDesc1" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <void property="column">
+ <string>_col1</string>
+ </void>
+ <void property="tabAlias">
+ <string></string>
+ </void>
+ <void property="typeInfo">
+ <object idref="PrimitiveTypeInfo0"/>
+ </void>
+ </object>
+ </void>
</object>
</void>
<void property="conf">
@@ -214,17 +228,7 @@
<object idref="ExprNodeColumnDesc0"/>
</void>
<void method="add">
- <object class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
- <void property="column">
- <string>_col1</string>
- </void>
- <void property="tabAlias">
- <string></string>
- </void>
- <void property="typeInfo">
- <object idref="PrimitiveTypeInfo0"/>
- </void>
- </object>
+ <object idref="ExprNodeColumnDesc1"/>
</void>
</object>
</void>
@@ -1501,7 +1505,7 @@
</void>
<void method="put">
<string>_col1</string>
- <object id="ExprNodeColumnDesc1" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc2" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col1</string>
</void>
@@ -1515,7 +1519,7 @@
</void>
<void method="put">
<string>_col0</string>
- <object id="ExprNodeColumnDesc2" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc3" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col0</string>
</void>
@@ -1534,10 +1538,10 @@
<void property="colList">
<object class="java.util.ArrayList">
<void method="add">
- <object idref="ExprNodeColumnDesc2"/>
+ <object idref="ExprNodeColumnDesc3"/>
</void>
<void method="add">
- <object idref="ExprNodeColumnDesc1"/>
+ <object idref="ExprNodeColumnDesc2"/>
</void>
<void method="add">
<object idref="ExprNodeGenericFuncDesc2"/>
@@ -1640,7 +1644,7 @@
<object class="java.util.HashMap">
<void method="put">
<string>_col0</string>
- <object id="ExprNodeColumnDesc3" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc4" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>KEY._col0</string>
</void>
@@ -1727,7 +1731,7 @@
<void property="keys">
<object class="java.util.ArrayList">
<void method="add">
- <object idref="ExprNodeColumnDesc3"/>
+ <object idref="ExprNodeColumnDesc4"/>
</void>
</object>
</void>
Modified: hive/trunk/ql/src/test/results/compiler/plan/groupby3.q.xml
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/compiler/plan/groupby3.q.xml?rev=1504395&r1=1504394&r2=1504395&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/compiler/plan/groupby3.q.xml (original)
+++ hive/trunk/ql/src/test/results/compiler/plan/groupby3.q.xml Thu Jul 18 09:16:52 2013
@@ -174,7 +174,26 @@
<void method="add">
<object id="ReduceSinkOperator0" class="org.apache.hadoop.hive.ql.exec.ReduceSinkOperator">
<void property="columnExprMap">
- <object class="java.util.HashMap"/>
+ <object class="java.util.HashMap">
+ <void method="put">
+ <string>KEY._col0:0._col0</string>
+ <object id="ExprNodeColumnDesc0" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <void property="column">
+ <string>_col0</string>
+ </void>
+ <void property="tabAlias">
+ <string></string>
+ </void>
+ <void property="typeInfo">
+ <object id="PrimitiveTypeInfo0" class="org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo">
+ <void property="typeName">
+ <string>string</string>
+ </void>
+ </object>
+ </void>
+ </object>
+ </void>
+ </object>
</void>
<void property="conf">
<object class="org.apache.hadoop.hive.ql.plan.ReduceSinkDesc">
@@ -192,21 +211,7 @@
<void property="keyCols">
<object class="java.util.ArrayList">
<void method="add">
- <object class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
- <void property="column">
- <string>_col0</string>
- </void>
- <void property="tabAlias">
- <string></string>
- </void>
- <void property="typeInfo">
- <object id="PrimitiveTypeInfo0" class="org.apache.hadoop.hive.serde2.typeinfo.PrimitiveTypeInfo">
- <void property="typeName">
- <string>string</string>
- </void>
- </object>
- </void>
- </object>
+ <object idref="ExprNodeColumnDesc0"/>
</void>
</object>
</void>
@@ -1675,7 +1680,7 @@
<object class="java.util.HashMap">
<void method="put">
<string>_col4</string>
- <object id="ExprNodeColumnDesc0" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc1" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col4</string>
</void>
@@ -1689,7 +1694,7 @@
</void>
<void method="put">
<string>_col3</string>
- <object id="ExprNodeColumnDesc1" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc2" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col3</string>
</void>
@@ -1703,7 +1708,7 @@
</void>
<void method="put">
<string>_col2</string>
- <object id="ExprNodeColumnDesc2" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc3" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col2</string>
</void>
@@ -1717,7 +1722,7 @@
</void>
<void method="put">
<string>_col1</string>
- <object id="ExprNodeColumnDesc3" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc4" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col1</string>
</void>
@@ -1731,7 +1736,7 @@
</void>
<void method="put">
<string>_col0</string>
- <object id="ExprNodeColumnDesc4" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
+ <object id="ExprNodeColumnDesc5" class="org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc">
<void property="column">
<string>_col0</string>
</void>
@@ -1750,6 +1755,9 @@
<void property="colList">
<object class="java.util.ArrayList">
<void method="add">
+ <object idref="ExprNodeColumnDesc5"/>
+ </void>
+ <void method="add">
<object idref="ExprNodeColumnDesc4"/>
</void>
<void method="add">
@@ -1761,9 +1769,6 @@
<void method="add">
<object idref="ExprNodeColumnDesc1"/>
</void>
- <void method="add">
- <object idref="ExprNodeColumnDesc0"/>
- </void>
</object>
</void>
<void property="outputColumnNames">