You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by br...@apache.org on 2014/08/20 02:48:00 UTC
svn commit: r1619017 [3/4] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union28.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union28.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union28.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union28.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,247 @@
+PREHOOK: query: create table union_subq_union(key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@union_subq_union
+POSTHOOK: query: create table union_subq_union(key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@union_subq_union
+PREHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+ Stage-6 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 4 <- Map 3 (GROUP)
+ Reducer 6 <- Map 5 (GROUP)
+ Union 2 <- Map 1 (NONE), Reducer 4 (NONE), Reducer 6 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 29 Data size: 5812 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: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 29 Data size: 5812 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: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Reducer 4
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Reducer 6
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Union 2
+ Vertex: Union 2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-6
+ Stats-Aggr Operator
+
+PREHOOK: query: insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@union_subq_union
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@union_subq_union
+POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: select * from union_subq_union order by key, value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+POSTHOOK: query: select * from union_subq_union order by key, value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+2 val_2
+2 val_2
+2 val_2
+4 val_4
+4 val_4
+4 val_4
+5 val_5
+5 val_5
+5 val_5
+5 val_5
+5 val_5
+8 val_8
+8 val_8
+8 val_8
+9 val_9
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union29.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union29.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union29.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union29.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,197 @@
+PREHOOK: query: create table union_subq_union(key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@union_subq_union
+POSTHOOK: query: create table union_subq_union(key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@union_subq_union
+PREHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value from src
+ union all
+ select key, value from src
+ ) subq
+) a
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value from src
+ union all
+ select key, value from src
+ ) subq
+) a
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+ Stage-6 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Union 2 <- Map 1 (NONE), Map 3 (NONE), Map 4 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Union 2
+ Vertex: Union 2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-6
+ Stats-Aggr Operator
+
+PREHOOK: query: insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value from src
+ union all
+ select key, value from src
+ ) subq
+) a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@union_subq_union
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table union_subq_union
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value from src
+ union all
+ select key, value from src
+ ) subq
+) a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@union_subq_union
+POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: select * from union_subq_union order by key, value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+POSTHOOK: query: select * from union_subq_union order by key, value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+2 val_2
+2 val_2
+2 val_2
+4 val_4
+4 val_4
+4 val_4
+5 val_5
+5 val_5
+5 val_5
+5 val_5
+5 val_5
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union3.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union3.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union3.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,278 @@
+PREHOOK: query: -- SORT_BEFORE_DIFF
+
+explain
+SELECT *
+FROM (
+ SELECT 1 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 2 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 3 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+ UNION ALL
+ SELECT 4 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+) a
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_BEFORE_DIFF
+
+explain
+SELECT *
+FROM (
+ SELECT 1 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 2 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 3 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+ UNION ALL
+ SELECT 4 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+) a
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 10 <- Map 9 (GROUP)
+ Reducer 11 <- Reducer 10 (GROUP SORT)
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 5 <- Map 4 (GROUP)
+ Reducer 7 <- Map 6 (GROUP)
+ Reducer 8 <- Reducer 7 (GROUP SORT)
+ Union 3 <- Reducer 11 (NONE), Reducer 2 (NONE), Reducer 5 (NONE), Reducer 8 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reducer 10
+ Reduce Operator Tree:
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ expressions: 2 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reducer 11
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ Limit
+ Number of rows: 1
+ Select Operator
+ expressions: 4 (type: int)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 5
+ Reduce Operator Tree:
+ Select Operator
+ Limit
+ Number of rows: 1
+ Select Operator
+ expressions: 3 (type: int)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 7
+ Reduce Operator Tree:
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Limit
+ Number of rows: 1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ expressions: 1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Reducer 8
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: CREATE TABLE union_out (id int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@union_out
+POSTHOOK: query: CREATE TABLE union_out (id int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@union_out
+PREHOOK: query: insert overwrite table union_out
+SELECT *
+FROM (
+ SELECT 1 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 2 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 3 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+ UNION ALL
+ SELECT 4 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+) a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@union_out
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table union_out
+SELECT *
+FROM (
+ SELECT 1 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 2 AS id
+ FROM (SELECT * FROM src LIMIT 1) s1
+ CLUSTER BY id
+ UNION ALL
+ SELECT 3 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+ UNION ALL
+ SELECT 4 AS id
+ FROM (SELECT * FROM src LIMIT 1) s2
+) a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@union_out
+POSTHOOK: Lineage: union_out.id EXPRESSION []
+PREHOOK: query: select * from union_out cluster by id
+PREHOOK: type: QUERY
+PREHOOK: Input: default@union_out
+#### A masked pattern was here ####
+POSTHOOK: query: select * from union_out cluster by id
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@union_out
+#### A masked pattern was here ####
+1
+2
+3
+4
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union30.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union30.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union30.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union30.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,306 @@
+PREHOOK: query: create table union_subq_union(key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@union_subq_union
+POSTHOOK: query: create table union_subq_union(key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@union_subq_union
+PREHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+
+union all
+
+select key, value from src
+) aa
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+insert overwrite table union_subq_union
+select * from (
+
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+
+union all
+
+select key, value from src
+) aa
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+ Stage-6 depends on stages: Stage-0
+ Stage-7 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 5 <- Map 4 (GROUP)
+ Union 3 <- Map 6 (NONE), Map 7 (NONE), Reducer 2 (NONE), Reducer 5 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 29 Data size: 5812 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: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 29 Data size: 5812 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: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Reducer 2
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Reducer 5
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.union_subq_union
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-6
+ Stats-Aggr Operator
+
+ Stage: Stage-7
+ Stats-Aggr Operator
+
+PREHOOK: query: insert overwrite table union_subq_union
+select * from (
+
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+
+union all
+
+select key, value from src
+) aa
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@union_subq_union
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table union_subq_union
+select * from (
+
+select * from (
+ select key, value from src
+ union all
+ select key, value from
+ (
+ select key, value, count(1) from src group by key, value
+ union all
+ select key, value, count(1) from src group by key, value
+ ) subq
+) a
+
+union all
+
+select key, value from src
+) aa
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@union_subq_union
+POSTHOOK: Lineage: union_subq_union.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: union_subq_union.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: select * from union_subq_union order by key, value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+POSTHOOK: query: select * from union_subq_union order by key, value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@union_subq_union
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+0 val_0
+2 val_2
+2 val_2
+2 val_2
+2 val_2
+4 val_4
+4 val_4
+4 val_4
+4 val_4
+5 val_5
+5 val_5
+5 val_5
+5 val_5
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union33.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union33.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union33.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union33.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,356 @@
+PREHOOK: query: -- SORT_BEFORE_DIFF
+-- This tests that a union all with a map only subquery on one side and a
+-- subquery involving two map reduce jobs on the other runs correctly.
+
+CREATE TABLE test_src (key STRING, value STRING)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@test_src
+POSTHOOK: query: -- SORT_BEFORE_DIFF
+-- This tests that a union all with a map only subquery on one side and a
+-- subquery involving two map reduce jobs on the other runs correctly.
+
+CREATE TABLE test_src (key STRING, value STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@test_src
+PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, value FROM src
+ WHERE key = 0
+UNION ALL
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+)a
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, value FROM src
+ WHERE key = 0
+UNION ALL
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+)a
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 4 <- Map 3 (GROUP SORT)
+ Reducer 5 <- Reducer 4 (GROUP)
+ Union 2 <- Map 1 (NONE), Reducer 5 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Filter Operator
+ predicate: (key = 0) (type: boolean)
+ Select Operator
+ expressions: '0' (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: partials
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), UDFToString(_col1) (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+ Union 2
+ Vertex: Union 2
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, value FROM src
+ WHERE key = 0
+UNION ALL
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+)a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_src
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, value FROM src
+ WHERE key = 0
+UNION ALL
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+)a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_src
+POSTHOOK: Lineage: test_src.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_src.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), (src)src.null, ]
+PREHOOK: query: SELECT COUNT(*) FROM test_src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT COUNT(*) FROM test_src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_src
+#### A masked pattern was here ####
+312
+PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+UNION ALL
+ SELECT key, value FROM src
+ WHERE key = 0
+)a
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+UNION ALL
+ SELECT key, value FROM src
+ WHERE key = 0
+)a
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+ Reducer 3 <- Reducer 2 (GROUP)
+ Union 4 <- Map 5 (NONE), Reducer 3 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Filter Operator
+ predicate: (key = 0) (type: boolean)
+ Select Operator
+ expressions: '0' (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: partials
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: final
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), UDFToString(_col1) (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+ Union 4
+ Vertex: Union 4
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.test_src
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+PREHOOK: query: INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+UNION ALL
+ SELECT key, value FROM src
+ WHERE key = 0
+)a
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@test_src
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: INSERT OVERWRITE TABLE test_src
+SELECT key, value FROM (
+ SELECT key, COUNT(*) AS value FROM src
+ GROUP BY key
+UNION ALL
+ SELECT key, value FROM src
+ WHERE key = 0
+)a
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@test_src
+POSTHOOK: Lineage: test_src.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: test_src.value EXPRESSION [(src)src.null, (src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: SELECT COUNT(*) FROM test_src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@test_src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT COUNT(*) FROM test_src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@test_src
+#### A masked pattern was here ####
+312
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union4.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union4.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union4.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,167 @@
+PREHOOK: query: -- union case: both subqueries are map-reduce jobs on same input, followed by filesink
+
+
+create table tmptable(key string, value int)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tmptable
+POSTHOOK: query: -- union case: both subqueries are map-reduce jobs on same input, followed by filesink
+
+
+create table tmptable(key string, value int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tmptable
+PREHOOK: query: explain
+insert overwrite table tmptable
+ select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+insert overwrite table tmptable
+ select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 5 <- Map 4 (GROUP)
+ Union 3 <- Reducer 2 (NONE), Reducer 5 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: s2
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: 'tst1' (type: string), _col0 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: 'tst2' (type: string), _col0 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+PREHOOK: query: insert overwrite table tmptable
+select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@tmptable
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table tmptable
+select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@tmptable
+POSTHOOK: Lineage: tmptable.key EXPRESSION []
+POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, ]
+PREHOOK: query: select * from tmptable x sort by x.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmptable
+#### A masked pattern was here ####
+POSTHOOK: query: select * from tmptable x sort by x.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmptable
+#### A masked pattern was here ####
+tst1 500
+tst2 500
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union5.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union5.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union5.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union5.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,148 @@
+PREHOOK: query: -- SORT_BEFORE_DIFF
+-- union case: both subqueries are map-reduce jobs on same input, followed by reduce sink
+
+explain
+ select unionsrc.key, count(1) FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc group by unionsrc.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- SORT_BEFORE_DIFF
+-- union case: both subqueries are map-reduce jobs on same input, followed by reduce sink
+
+explain
+ select unionsrc.key, count(1) FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc group by unionsrc.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 4 <- Union 3 (GROUP)
+ Reducer 6 <- Map 5 (GROUP)
+ Union 3 <- Reducer 2 (NONE), Reducer 6 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: s2
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: 'tst1' (type: string)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
+ Reducer 6
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: 'tst2' (type: string)
+ outputColumnNames: _col0
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ value expressions: _col1 (type: bigint)
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select unionsrc.key, count(1) FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc group by unionsrc.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select unionsrc.key, count(1) FROM (select 'tst1' as key, count(1) as value from src s1
+ UNION ALL
+ select 'tst2' as key, count(1) as value from src s2) unionsrc group by unionsrc.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+tst2 1
+tst1 1
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/union6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/union6.q.out?rev=1619017&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/union6.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/union6.q.out Wed Aug 20 00:47:59 2014
@@ -0,0 +1,174 @@
+PREHOOK: query: -- union case: 1 subquery is a map-reduce job, different inputs for sub-queries, followed by filesink
+
+
+create table tmptable(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@tmptable
+POSTHOOK: query: -- union case: 1 subquery is a map-reduce job, different inputs for sub-queries, followed by filesink
+
+
+create table tmptable(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tmptable
+PREHOOK: query: explain
+insert overwrite table tmptable
+ select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1
+ UNION ALL
+ select s2.key as key, s2.value as value from src1 s2) unionsrc
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+insert overwrite table tmptable
+ select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1
+ UNION ALL
+ select s2.key as key, s2.value as value from src1 s2) unionsrc
+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-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0
+ Stage-5 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Union 3 <- Map 4 (NONE), Reducer 2 (NONE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: s1
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Select Operator
+ Statistics: Num rows: 0 Data size: 5812 Basic stats: PARTIAL Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: s2
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions: 'tst1' (type: string), UDFToString(_col0) (type: string)
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+ Union 3
+ Vertex: Union 3
+
+ Stage: Stage-2
+ Dependency Collection
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: true
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmptable
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+PREHOOK: query: insert overwrite table tmptable
+select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1
+ UNION ALL
+ select s2.key as key, s2.value as value from src1 s2) unionsrc
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+PREHOOK: Output: default@tmptable
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to
+POSTHOOK: query: insert overwrite table tmptable
+select unionsrc.key, unionsrc.value FROM (select 'tst1' as key, cast(count(1) as string) as value from src s1
+ UNION ALL
+ select s2.key as key, s2.value as value from src1 s2) unionsrc
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+POSTHOOK: Output: default@tmptable
+POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: select * from tmptable x sort by x.key, x.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tmptable
+#### A masked pattern was here ####
+POSTHOOK: query: select * from tmptable x sort by x.key, x.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tmptable
+#### A masked pattern was here ####
+
+
+
+
+ val_165
+ val_193
+ val_265
+ val_27
+ val_409
+ val_484
+128
+146 val_146
+150 val_150
+213 val_213
+224
+238 val_238
+255 val_255
+273 val_273
+278 val_278
+311 val_311
+369
+401 val_401
+406 val_406
+66 val_66
+98 val_98
+tst1 500