You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2016/10/25 21:43:29 UTC
[10/28] hive git commit: HIVE-12765: Support Intersect (distinct/all)
Except (distinct/all) Minus (distinct/all) (Pengcheng Xiong,
reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/0049a21f/ql/src/test/queries/clientpositive/intersect_all.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/intersect_all.q b/ql/src/test/queries/clientpositive/intersect_all.q
new file mode 100644
index 0000000..a0d4afd
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/intersect_all.q
@@ -0,0 +1,42 @@
+set hive.mapred.mode=nonstrict;
+set hive.cbo.enable=true;
+
+create table a(key int, value int);
+
+insert into table a values (1,2),(1,2),(1,3),(2,3);
+
+create table b(key int, value int);
+
+insert into table b values (1,2),(2,3);
+
+select key, value, count(1) as c from a group by key, value;
+
+select * from a intersect all select * from b;
+
+select * from b intersect all select * from a intersect all select * from b;
+
+select * from a intersect all select * from b union all select * from a intersect all select * from b;
+
+select * from a intersect all select * from b union select * from a intersect all select * from b;
+
+select * from a intersect all select * from b intersect all select * from a intersect all select * from b;
+
+select * from (select a.key, b.value from a join b on a.key=b.key)sub1
+intersect all
+select * from (select a.key, b.value from a join b on a.key=b.key)sub2;
+
+select * from (select a.key, b.value from a join b on a.key=b.key)sub1
+intersect all
+select * from (select b.value as key, a.key as value from a join b on a.key=b.key)sub2;
+
+explain select * from src intersect all select * from src;
+
+select * from src intersect all select * from src;
+
+explain select * from src intersect all select * from src intersect all select * from src intersect all select * from src;
+
+select * from src intersect all select * from src intersect all select * from src intersect all select * from src;
+
+explain select value from a group by value intersect all select key from b group by key;
+
+select value from a group by value intersect all select key from b group by key;
http://git-wip-us.apache.org/repos/asf/hive/blob/0049a21f/ql/src/test/queries/clientpositive/intersect_distinct.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/intersect_distinct.q b/ql/src/test/queries/clientpositive/intersect_distinct.q
new file mode 100644
index 0000000..aa8155a
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/intersect_distinct.q
@@ -0,0 +1,42 @@
+set hive.mapred.mode=nonstrict;
+set hive.cbo.enable=true;
+
+create table a(key int, value int);
+
+insert into table a values (1,2),(1,2),(1,3),(2,3);
+
+create table b(key int, value int);
+
+insert into table b values (1,2),(2,3);
+
+select key, count(1) as c from a group by key intersect all select value, max(key) as c from b group by value;
+
+select * from a intersect distinct select * from b;
+
+select * from b intersect distinct select * from a intersect distinct select * from b;
+
+select * from a intersect distinct select * from b union all select * from a intersect distinct select * from b;
+
+select * from a intersect distinct select * from b union select * from a intersect distinct select * from b;
+
+select * from a intersect distinct select * from b intersect distinct select * from a intersect distinct select * from b;
+
+select * from (select a.key, b.value from a join b on a.key=b.key)sub1
+intersect distinct
+select * from (select a.key, b.value from a join b on a.key=b.key)sub2;
+
+select * from (select a.key, b.value from a join b on a.key=b.key)sub1
+intersect distinct
+select * from (select b.value as key, a.key as value from a join b on a.key=b.key)sub2;
+
+explain select * from src intersect distinct select * from src;
+
+select * from src intersect distinct select * from src;
+
+explain select * from src intersect distinct select * from src intersect distinct select * from src intersect distinct select * from src;
+
+select * from src intersect distinct select * from src intersect distinct select * from src intersect distinct select * from src;
+
+explain select value from a group by value intersect distinct select key from b group by key;
+
+select value from a group by value intersect distinct select key from b group by key;
http://git-wip-us.apache.org/repos/asf/hive/blob/0049a21f/ql/src/test/queries/clientpositive/intersect_merge.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/intersect_merge.q b/ql/src/test/queries/clientpositive/intersect_merge.q
new file mode 100644
index 0000000..0d8789e
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/intersect_merge.q
@@ -0,0 +1,27 @@
+set hive.mapred.mode=nonstrict;
+set hive.cbo.enable=true;
+
+create table a(key int, value int);
+
+insert into table a values (1,2),(1,2),(1,3),(2,3);
+
+create table b(key int, value int);
+
+insert into table b values (1,2),(2,3);
+
+explain select * from b intersect distinct select * from a intersect distinct select * from b intersect distinct select * from a intersect distinct select * from b;
+
+explain (select * from b intersect distinct select * from a) intersect distinct (select * from b intersect distinct select * from a);
+
+explain select * from b intersect distinct (select * from a intersect distinct (select * from b intersect distinct (select * from a intersect distinct select * from b)));
+
+explain (((select * from b intersect distinct select * from a) intersect distinct select * from b) intersect distinct select * from a) intersect distinct select * from b;
+
+explain select * from b intersect distinct (select * from a intersect distinct select * from b) intersect distinct select * from a intersect distinct select * from b;
+
+explain select * from b intersect distinct (select * from a intersect all select * from b);
+
+explain select * from b intersect all (select * from a intersect all select * from b);
+
+explain select * from b intersect all (select * from a intersect distinct select * from b);
+
http://git-wip-us.apache.org/repos/asf/hive/blob/0049a21f/ql/src/test/results/clientpositive/except_all.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/except_all.q.out b/ql/src/test/results/clientpositive/except_all.q.out
new file mode 100644
index 0000000..17313c1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/except_all.q.out
@@ -0,0 +1,986 @@
+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 all 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 all select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+0
+2
+2
+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 all 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 all select * from b
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+1 2
+1 3
+PREHOOK: query: select * from b except all 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 all select * from a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@a
+POSTHOOK: Input: default@b
+#### A masked pattern was here ####
+2 2
+2 20
+PREHOOK: query: select * from b except all 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 all 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 2
+2 20
+PREHOOK: query: select * from b except 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 b except 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 ####
+PREHOOK: query: select * from a except all 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 all 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 all 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 all 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 all 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 all 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 all
+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 all
+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 all
+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 all
+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
+1 2
+1 2
+2 3
+2 3
+2 20
+2 20
+PREHOOK: query: explain select * from src except all select * from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select * from src except all select * from src
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-3
+ Stage-3 is a root stage
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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
+ Union
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), (_col2 * _col3) (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col4, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ TableScan
+ Union
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), (_col2 * _col3) (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col4, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ((2 * _col2) - (3 * _col3)) (type: bigint), _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ UDTF Operator
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ function name: UDTFReplicateRows
+ Select Operator
+ expressions: col1 (type: string), col2 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 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
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select * from src except all select * from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select * from src except all select * from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+PREHOOK: query: explain select * from src except all select * from src except distinct select * from src except distinct select * from src
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select * from src except all 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-2 depends on stages: Stage-1, Stage-6
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3, Stage-7
+ Stage-5 depends on stages: Stage-4, Stage-8
+ Stage-6 is a root stage
+ Stage-7 is a root stage
+ Stage-8 is a root stage
+ Stage-0 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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
+ Union
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), (_col2 * _col3) (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col4, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ TableScan
+ Union
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), (_col2 * _col3) (type: bigint), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col4, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4), sum(_col3)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ((2 * _col2) - (3 * _col3)) (type: bigint), _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ UDTF Operator
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ function name: UDTFReplicateRows
+ Select Operator
+ expressions: col1 (type: string), col2 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 2 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 125 Data size: 1328 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-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Union
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ 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: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ 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: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ TableScan
+ Union
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ 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: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ 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: 375 Data size: 3984 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ 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: 187 Data size: 1986 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type: boolean)
+ Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(2)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 15 Data size: 159 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), 2 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 15 Data size: 159 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-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Union
+ Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ 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: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ 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: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ TableScan
+ Union
+ Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint), (_col2 * _col3) (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ 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: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ 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: 265 Data size: 2815 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ 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: 132 Data size: 1402 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col2 > 0) and ((_col2 * 2) = _col3)) (type: boolean)
+ Statistics: Num rows: 22 Data size: 233 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 22 Data size: 233 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 22 Data size: 233 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
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string), _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ 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: 2656 Basic stats: COMPLETE Column stats: NONE
+ 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: 2656 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-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select * from src except all 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 all 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-2 depends on stages: Stage-1, Stage-3
+ Stage-3 is a root stage
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ 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
+ 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
+ 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
+ Union
+ Statistics: Num rows: 2 Data size: 6 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)
+ TableScan
+ Union
+ Statistics: Num rows: 2 Data size: 6 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)
+ 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
+
+ Stage: Stage-3
+ Map Reduce
+ 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
+ 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
+ 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-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