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 [4/7] - 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/correlationoptimizer2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out?rev=1392105&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out Sun Sep 30 20:41:01 2012
@@ -0,0 +1,601 @@
+PREHOOK: query: -- the query is modified from join18.q
+
+CREATE TABLE dest_co1(key1 INT, cnt1 INT, key2 INT, cnt2 INT)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: -- the query is modified from join18.q
+
+CREATE TABLE dest_co1(key1 INT, cnt1 INT, key2 INT, cnt2 INT)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co1
+PREHOOK: query: CREATE TABLE dest_co2(key1 INT, cnt1 INT, key2 INT, cnt2 INT)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_co2(key1 INT, cnt1 INT, key2 INT, cnt2 INT)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co2
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+ Stage-4 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ 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: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: 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: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: UDFToInteger(_col2)
+ type: int
+ expr: UDFToInteger(_col3)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: 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
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ 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
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt)))))
+
+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:
+ a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: value
+ type: string
+ expr: key
+ type: string
+ outputColumnNames: value, key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: value
+ type: string
+ b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: value
+ type: string
+ expr: key
+ type: string
+ outputColumnNames: value, key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: value
+ type: string
+ Reduce Operator Tree:
+ Correlation Dispatch Operator
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ 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: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: UDFToInteger(_col2)
+ type: int
+ expr: UDFToInteger(_col3)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_co2
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ 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: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: UDFToInteger(_col2)
+ type: int
+ expr: UDFToInteger(_col3)
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: 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 a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT a.key, a.cnt, b.key, b.cnt
+FROM
+(SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+JOIN
+(SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ON (a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key1, x.key2, x.cnt1, x.cnt2
+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.key1, x.key2, x.cnt1, x.cnt2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+66 1 66 1
+98 2 98 1
+128 3 128 1
+146 2 146 1
+150 1 150 1
+213 2 213 1
+224 2 224 1
+238 2 238 1
+255 2 255 1
+273 3 273 1
+278 2 278 1
+311 3 311 1
+369 3 369 1
+401 5 401 1
+406 4 406 1
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key1, x.key2, x.cnt1, x.cnt2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key1, x.key2, x.cnt1, x.cnt2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt1 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt2 EXPRESSION [(src1)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key1 EXPRESSION [(src)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.key2 EXPRESSION [(src1)y.FieldSchema(name:key, type:string, comment:default), ]
+66 1 66 1
+98 2 98 1
+128 3 128 1
+146 2 146 1
+150 1 150 1
+213 2 213 1
+224 2 224 1
+238 2 238 1
+255 2 255 1
+273 3 273 1
+278 2 278 1
+311 3 311 1
+369 3 369 1
+401 5 401 1
+406 4 406 1
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out?rev=1392105&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out Sun Sep 30 20:41:01 2012
@@ -0,0 +1,705 @@
+PREHOOK: query: CREATE TABLE dest_co1(key INT, cnt INT, value STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_co1(key INT, cnt INT, value STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co1
+PREHOOK: query: CREATE TABLE dest_co2(key INT, cnt INT, value STRING)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE dest_co2(key INT, cnt INT, value STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@dest_co2
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co1
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt)) (TOK_SELEXPR (. (TOK_T
ABLE_OR_COL d) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-6
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+ Stage-5 is a root stage
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ d:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ d:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: string
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ 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
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ b:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ 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-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ 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: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ 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
+
+
+PREHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@dest_co1
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co1
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: default@dest_co1
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+INSERT OVERWRITE TABLE dest_co2
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_co2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt)) (TOK_SELEXPR (. (TOK_T
ABLE_OR_COL d) value)))))
+
+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:
+ d:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ d:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Forward
+ Correlation Composite Operator
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Correlation Dispatch Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1
+ Correlation Local Simulative Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: string
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: UDFToInteger(_col0)
+ type: int
+ expr: UDFToInteger(_col1)
+ type: int
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ 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 b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@dest_co2
+POSTHOOK: query: INSERT OVERWRITE TABLE dest_co2
+SELECT b.key, b.cnt, d.value
+FROM
+(SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+JOIN
+(SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ON b.key = d.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: default@dest_co2
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co2.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: -- dest_co1 and dest_co2 should be same
+SELECT * FROM dest_co1 x ORDER BY x.key, x.cnt, x.value
+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, x.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co1
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co2.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+66 1 val_66
+98 2 val_98
+98 2 val_98
+128 3
+128 3
+128 3
+146 2 val_146
+146 2 val_146
+150 1 val_150
+213 2 val_213
+213 2 val_213
+224 2
+224 2
+238 2 val_238
+238 2 val_238
+255 2 val_255
+255 2 val_255
+273 3 val_273
+273 3 val_273
+273 3 val_273
+278 2 val_278
+278 2 val_278
+311 3 val_311
+311 3 val_311
+311 3 val_311
+369 3
+369 3
+369 3
+401 5 val_401
+401 5 val_401
+401 5 val_401
+401 5 val_401
+401 5 val_401
+406 4 val_406
+406 4 val_406
+406 4 val_406
+406 4 val_406
+PREHOOK: query: SELECT * FROM dest_co2 x ORDER BY x.key, x.cnt, x.value
+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, x.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@dest_co2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: dest_co1.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.cnt EXPRESSION [(src1)x.null, (src1)x.null, (src)y.null, ]
+POSTHOOK: Lineage: dest_co2.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_co2.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+66 1 val_66
+98 2 val_98
+98 2 val_98
+128 3
+128 3
+128 3
+146 2 val_146
+146 2 val_146
+150 1 val_150
+213 2 val_213
+213 2 val_213
+224 2
+224 2
+238 2 val_238
+238 2 val_238
+255 2 val_255
+255 2 val_255
+273 3 val_273
+273 3 val_273
+273 3 val_273
+278 2 val_278
+278 2 val_278
+311 3 val_311
+311 3 val_311
+311 3 val_311
+369 3
+369 3
+369 3
+401 5 val_401
+401 5 val_401
+401 5 val_401
+401 5 val_401
+401 5 val_401
+406 4 val_406
+406 4 val_406
+406 4 val_406
+406 4 val_406