You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by he...@apache.org on 2012/09/30 22:41:03 UTC
svn commit: r1392105 [5/7] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/
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/ql/optimiz...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer4.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer4.q.out?rev=1392105&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer4.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer4.q.out Sun Sep 30 20:41:01 2012
@@ -0,0 +1,2477 @@
+PREHOOK: query: CREATE TABLE T1(key INT, val STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key INT, val STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key INT, val STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key INT, val STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: CREATE TABLE dest_co1(key INT, cnt INT)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_co1(key INT, cnt INT)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co1
+PREHOOK: query: CREATE TABLE dest_co2(key INT, cnt INT)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_co2(key INT, cnt INT)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co2
+PREHOOK: query: -- INNER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- INNER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co1
+
+ 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: default.dest_co1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Correlation Dispatch Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col4
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col4
+ type: int
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co2
+
+ 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: default.dest_co2
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+2 1
+3 1
+8 4
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+2 1
+3 1
+8 4
+PREHOOK: query: -- The case that GROUP BY key is from the left table of LEFT OUTER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The case that GROUP BY key is from the left table of LEFT OUTER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ value expressions:
+ expr: key
+ type: int
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co1
+
+ 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: default.dest_co1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ value expressions:
+ expr: key
+ type: int
+ y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ Reduce Operator Tree:
+ Correlation Dispatch Operator
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co2
+
+ 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: default.dest_co2
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+2 1
+3 1
+4 1
+5 1
+8 4
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+2 1
+3 1
+4 1
+5 1
+8 4
+PREHOOK: query: -- The case that GROUP BY key is from the right table of RIGHT OUTER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The case that GROUP BY key is from the right table of RIGHT OUTER JOIN should be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co1
+
+ 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: default.dest_co1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+ Stage-2 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Correlation Dispatch Operator
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col4
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col4
+ type: int
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co2
+
+ 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: default.dest_co2
+
+ Stage: Stage-2
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+1 1
+2 1
+3 1
+7 1
+8 4
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+1 1
+2 1
+3 1
+7 1
+8 4
+PREHOOK: query: -- The case that GROUP BY key is from the right table of LEFT OUTER JOIN should not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The case that GROUP BY key is from the right table of LEFT OUTER JOIN should not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co1
+
+ 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: default.dest_co1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ value expressions:
+ expr: key
+ type: int
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: int
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co2
+
+ 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: default.dest_co2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT y.key, count(1) FROM T2 x LEFT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY y.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+NULL 2
+2 1
+3 1
+8 4
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+NULL 2
+2 1
+3 1
+8 4
+PREHOOK: query: -- The case that GROUP BY key is from the left table of RIGHT OUTER JOIN should not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The case that GROUP BY key is from the left table of RIGHT OUTER JOIN should not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ value expressions:
+ expr: key
+ type: int
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co1
+
+ 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: default.dest_co1
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME T2) x) (TOK_TABREF (TOK_TABNAME T1) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 0
+ value expressions:
+ expr: key
+ type: int
+ y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: int
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ 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:
+#### A masked pattern was here ####
+ 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
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ outputColumnNames: _col0, _col1
+ 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: default.dest_co2
+
+ 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: default.dest_co2
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT x.key, count(1) FROM T2 x RIGHT OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+NULL 2
+2 1
+3 1
+8 4
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+NULL 2
+2 1
+3 1
+8 4
+PREHOOK: query: -- FULL OUTER JOIN will not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x FULL OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- FULL OUTER JOIN will not be optimized
+EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT x.key, count(1) FROM T2 x FULL OUTER JOIN T1 y ON (x.key = y.key) GROUP BY x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co1.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(t2)x.null, (t1)y.null, ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t1)y.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: dest_co2.key SIMPLE [(t2)x.FieldSchema(name:key, type:int, comment:null), ]
+ABSTRACT SYNTAX TREE:
[... 444 lines stripped ...]