http://git-wip-us.apache.org/repos/asf/hive/blob/0049a21f/ql/src/test/results/clientpositive/llap/except_distinct.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/except_distinct.q.out
b/ql/src/test/results/clientpositive/llap/except_distinct.q.out
new file mode 100644
index 0000000..5a19350
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/except_distinct.q.out
@@ -0,0 +1,894 @@
+PREHOOK: query: create table a(key int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@a
+POSTHOOK: query: create table a(key int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@a
+PREHOOK: query: insert into table a values
(0),(1),(2),(2),(2),(2),(3),(NULL),(NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__1
+PREHOOK: Output: default@a
+POSTHOOK: query: insert into table a values
(0),(1),(2),(2),(2),(2),(3),(NULL),(NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__1
+POSTHOOK: Output: default@a
+POSTHOOK: Lineage: a.key EXPRESSION
[(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: create table b(key bigint)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@b
+POSTHOOK: query: create table b(key bigint)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@b
+PREHOOK: query: insert into table b values
(1),(2),(2),(3),(5),(5),(NULL),(NULL),(NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__2
+PREHOOK: Output: default@b
+POSTHOOK: query: insert into table b values
(1),(2),(2),(3),(5),(5),(NULL),(NULL),(NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__2
+POSTHOOK: Output: default@b
+POSTHOOK: Lineage: b.key EXPRESSION
[(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+PREHOOK: query: select * from a except distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from a except distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+0
+PREHOOK: query: drop table a
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@a
+PREHOOK: Output: default@a
+POSTHOOK: query: drop table a
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@a
+POSTHOOK: Output: default@a
+PREHOOK: query: drop table b
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@b
+PREHOOK: Output: default@b
+POSTHOOK: query: drop table b
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@b
+POSTHOOK: Output: default@b
+PREHOOK: query: create table a(key int, value int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@a
+POSTHOOK: query: create table a(key int, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@a
+PREHOOK: query: insert into table a values (1,2),(1,2),(1,3),(2,3),(2,2)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__3
+PREHOOK: Output: default@a
+POSTHOOK: query: insert into table a values (1,2),(1,2),(1,3),(2,3),(2,2)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__3
+POSTHOOK: Output: default@a
+POSTHOOK: Lineage: a.key EXPRESSION
[(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+POSTHOOK: Lineage: a.value EXPRESSION
[(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col2,
type:string, comment:), ]
+PREHOOK: query: create table b(key int, value int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@b
+POSTHOOK: query: create table b(key int, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@b
+PREHOOK: query: insert into table b values (1,2),(2,3),(2,2),(2,2),(2,20)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@values__tmp__table__4
+PREHOOK: Output: default@b
+POSTHOOK: query: insert into table b values (1,2),(2,3),(2,2),(2,2),(2,20)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@values__tmp__table__4
+POSTHOOK: Output: default@b
+POSTHOOK: Lineage: b.key EXPRESSION
[(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1,
type:string, comment:), ]
+POSTHOOK: Lineage: b.value EXPRESSION
[(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col2,
type:string, comment:), ]
+PREHOOK: query: select * from a except distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from a except distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+1 3
+PREHOOK: query: select * from b except distinct select * from a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from b except distinct select * from a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+2 20
+PREHOOK: query: select * from b except distinct select * from a intersect
distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from b except distinct select * from a intersect
distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+2 20
+PREHOOK: query: select * from b except distinct select * from a except
distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from b except distinct select * from a except
distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+PREHOOK: query: select * from a except distinct select * from b union all
select * from a except distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from a except distinct select * from b union all
select * from a except distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+1 3
+PREHOOK: query: select * from a except distinct select * from b union select *
from a except distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from a except distinct select * from b union select
* from a except distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+1 3
+PREHOOK: query: select * from a except distinct select * from b except
distinct select * from a except distinct select * from b
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from a except distinct select * from b except
distinct select * from a except distinct select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+PREHOOK: query: select * from (select a.key, b.value from a join b on
a.key=b.key)sub1
+except distinct
+select * from (select a.key, b.value from a join b on a.key=b.key)sub2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from (select a.key, b.value from a join b on
a.key=b.key)sub1
+except distinct
+select * from (select a.key, b.value from a join b on a.key=b.key)sub2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+PREHOOK: query: select * from (select a.key, b.value from a join b on
a.key=b.key)sub1
+except distinct
+select * from (select b.value as key, a.key as value from a join b on
a.key=b.key)sub2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select * from (select a.key, b.value from a join b on
a.key=b.key)sub1
+except distinct
+select * from (select b.value as key, a.key as value from a join b on
a.key=b.key)sub2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+1 2
+2 3
+2 20
+PREHOOK: query: explain select * from src except distinct select * from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select * from src except distinct select * from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Union 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 2
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 97000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 48500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type:
boolean)
+ Statistics: Num rows: 41 Data size: 7954 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 41 Data size: 7298 Basic stats:
COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 41 Data size: 7298 Basic stats:
COMPLETE Column stats: COMPLETE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 1
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 97000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 48500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select * from src except distinct select * from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src except distinct select * from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain select * from src except distinct select * from src
except distinct select * from src except distinct select * from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select * from src except distinct select * from src
except distinct select * from src except distinct select * from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 10 <- Map 9 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 12 <- Map 11 (SIMPLE_EDGE), Union 5 (CONTAINS)
+ Reducer 14 <- Map 13 (SIMPLE_EDGE), Union 7 (CONTAINS)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
+ Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS)
+ Reducer 8 <- Union 7 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 89000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 46500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 10
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 1
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 97000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 48500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Reducer 12
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 1
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 291 Data size: 56454 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 145 Data size: 28130 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 145 Data size: 28130 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Reducer 14
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 1
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 274 Data size: 53156 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 137 Data size: 26578 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 137 Data size: 26578 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 46500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 2
(type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string),
_col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 97000 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type:
string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string),
_col1 (type: string)
+ Statistics: Num rows: 250 Data size: 48500 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type:
bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 250 Data size: 48500 Basic stats:
COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type:
boolean)
+ Statistics: Num rows: 41 Data size: 7954 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 41 Data size: 7954 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 41 Data size: 7626 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type:
string), 2 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 41 Data size: 7954 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type:
string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 291 Data size: 56454 Basic
stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 145 Data size: 28130 Basic
stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1
(type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type:
string), _col1 (type: string)
+ Statistics: Num rows: 145 Data size: 28130 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3
(type: bigint)
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 145 Data size: 28130 Basic stats:
COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type:
boolean)
+ Statistics: Num rows: 24 Data size: 4656 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 24 Data size: 4656 Basic stats:
COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 24 Data size: 4464 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type:
string), 2 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 24 Data size: 4656 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type:
string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 274 Data size: 53156 Basic
stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 137 Data size: 26578 Basic
stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1
(type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type:
string), _col1 (type: string)
+ Statistics: Num rows: 137 Data size: 26578 Basic
stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3
(type: bigint)
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 137 Data size: 26578 Basic stats:
COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type:
boolean)
+ Statistics: Num rows: 22 Data size: 4268 Basic stats:
COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 22 Data size: 3916 Basic stats:
COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 22 Data size: 3916 Basic stats:
COMPLETE Column stats: COMPLETE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Union 3
+ Vertex: Union 3
+ Union 5
+ Vertex: Union 5
+ Union 7
+ Vertex: Union 7
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select * from src except distinct select * from src except
distinct select * from src except distinct select * from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src except distinct select * from src except
distinct select * from src except distinct select * from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain select value from a group by value except distinct
select key from b group by key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select value from a group by value except distinct
select key from b group by key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Union 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: value (type: int)
+ outputColumnNames: value
+ Statistics: Num rows: 5 Data size: 15 Basic stats:
COMPLETE Column stats: NONE
+ Group By Operator
+ keys: value (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 15 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 15 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: key
+ Statistics: Num rows: 5 Data size: 16 Basic stats:
COMPLETE Column stats: NONE
+ Group By Operator
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 16 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 5 Data size: 16 Basic stats:
COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE
Column stats: NONE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: int)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), 2 (type: bigint), _col1
(type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: bigint),
(_col1 * _col2) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1), sum(_col2)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint), _col2
(type: bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 > 0) and ((_col1 * 2) = _col2)) (type:
boolean)
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 3 Basic stats:
COMPLETE Column stats: NONE
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE
Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: int)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), 1 (type: bigint), _col1
(type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: bigint),
(_col1 * _col2) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1), sum(_col2)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 6 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint), _col2
(type: bigint)
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select value from a group by value except distinct select key
from b group by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@a
+PREHOOK: Input: default@b
+#### A masked pattern was here ####
+POSTHOOK: query: select value from a group by value except distinct select key
from b group by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+3
