http://git-wip-us.apache.org/repos/asf/hive/blob/6d19df3a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cbo_rp_join1.q.out
b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out
new file mode 100644
index 0000000..69ce6d2
--- /dev/null
+++ b/ql/src/test/results/clientpositive/cbo_rp_join1.q.out
@@ -0,0 +1,426 @@
+PREHOOK: query: CREATE TABLE myinput1(key int, value int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@myinput1
+POSTHOOK: query: CREATE TABLE myinput1(key int, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@myinput1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE
myinput1
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@myinput1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE
myinput1
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@myinput1
+Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (key = 40) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: 40 (type: int), value (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (key = 40) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: 40 (type: int), value (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Select Operator
+ expressions: hash(_col0,_col1,_col2,_col3) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40
+PREHOOK: type: QUERY
+PREHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND b.key = 40
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+NULL
+Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.value = 40 AND a.key
= a.value AND b.key = 40
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.value = 40 AND a.key
= a.value AND b.key = 40
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: ((key = 40) and (value = 40)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: 40 (type: int), 40 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (key = 40) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: 40 (type: int), value (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Select Operator
+ expressions: hash(_col0,_col1,_col2,_col3) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = a.value AND b.key = 40
+PREHOOK: type: QUERY
+PREHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = a.value AND b.key = 40
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+NULL
+PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key
= 40
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key
= 40
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (key = 40) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: value (type: int)
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (key = 40) (type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: value (type: int)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col1,_col5,_col6))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key = 40
+PREHOOK: type: QUERY
+PREHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key = 40 AND a.key = b.key AND b.key = 40
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+NULL
+Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key
= a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM
myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key
= a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (((key > 40) and (value > 50)) and (key = value))
(type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
+ Filter Operator
+ predicate: (((key > 40) and (value > 50)) and (key = value))
(type: boolean)
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Select Operator
+ expressions: hash(_col0,_col1,_col2,_col3) (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column
stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column
stats: NONE
+ 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[12][tables = [$hdt$_0, $hdt$_1]] in Stage
'Stage-1:MAPRED' is a cross product
+PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value
AND b.key > 40 AND b.value > 50 AND b.key = b.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a
FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value
AND b.key > 40 AND b.value > 50 AND b.key = b.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@myinput1
+#### A masked pattern was here ####
+3078400
