You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/27 20:57:03 UTC
svn commit: r1634671 [27/46] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/parquet_join.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/parquet_join.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/parquet_join.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/parquet_join.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,367 @@
+PREHOOK: query: drop table if exists staging
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table if exists staging
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table if exists parquet_jointable1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table if exists parquet_jointable1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table if exists parquet_jointable2
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table if exists parquet_jointable2
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table if exists parquet_jointable1_bucketed_sorted
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table if exists parquet_jointable1_bucketed_sorted
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table if exists parquet_jointable2_bucketed_sorted
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table if exists parquet_jointable2_bucketed_sorted
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table staging (key int, value string) stored as textfile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@staging
+POSTHOOK: query: create table staging (key int, value string) stored as textfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@staging
+PREHOOK: query: insert into table staging select distinct key, value from src order by key limit 2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@staging
+[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 into table staging select distinct key, value from src order by key limit 2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@staging
+POSTHOOK: Lineage: staging.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: staging.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: create table parquet_jointable1 stored as parquet as select * from staging
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@staging
+PREHOOK: Output: database:default
+PREHOOK: Output: default@parquet_jointable1
+[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: create table parquet_jointable1 stored as parquet as select * from staging
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@staging
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@parquet_jointable1
+PREHOOK: query: create table parquet_jointable2 stored as parquet as select key,key+1,concat(value,"value") as myvalue from staging
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@staging
+PREHOOK: Output: database:default
+PREHOOK: Output: default@parquet_jointable2
+[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: create table parquet_jointable2 stored as parquet as select key,key+1,concat(value,"value") as myvalue from staging
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@staging
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@parquet_jointable2
+PREHOOK: query: -- MR join
+
+explain select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- MR join
+
+explain select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.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 PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: p2
+ Statistics: Num rows: 4 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 217 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 217 Basic stats: COMPLETE Column stats: NONE
+ value expressions: myvalue (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 74 Data size: 296 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col1}
+ outputColumnNames: _col7
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col7 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@parquet_jointable1
+PREHOOK: Input: default@parquet_jointable2
+#### A masked pattern was here ####
+POSTHOOK: query: select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@parquet_jointable1
+POSTHOOK: Input: default@parquet_jointable2
+#### A masked pattern was here ####
+val_0value
+val_10value
+PREHOOK: query: -- The two tables involved in the join have differing number of columns(table1-2,table2-3). In case of Map and SMB join,
+-- when the second table is loaded, the column indices in hive.io.file.readcolumn.ids refer to columns of both the first and the second table
+-- and hence the parquet schema/types passed to ParquetInputSplit should contain only the column indexes belonging to second/current table
+
+-- Map join
+
+explain select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The two tables involved in the join have differing number of columns(table1-2,table2-3). In case of Map and SMB join,
+-- when the second table is loaded, the column indices in hive.io.file.readcolumn.ids refer to columns of both the first and the second table
+-- and hence the parquet schema/types passed to ParquetInputSplit should contain only the column indexes belonging to second/current table
+
+-- Map join
+
+explain select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.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 PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: p2
+ Statistics: Num rows: 4 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 217 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 217 Basic stats: COMPLETE Column stats: NONE
+ value expressions: myvalue (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 74 Data size: 296 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 37 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col1}
+ outputColumnNames: _col7
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col7 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 40 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@parquet_jointable1
+PREHOOK: Input: default@parquet_jointable2
+#### A masked pattern was here ####
+POSTHOOK: query: select p2.myvalue from parquet_jointable1 p1 join parquet_jointable2 p2 on p1.key=p2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@parquet_jointable1
+POSTHOOK: Input: default@parquet_jointable2
+#### A masked pattern was here ####
+val_0value
+val_10value
+PREHOOK: query: -- SMB join
+
+create table parquet_jointable1_bucketed_sorted (key int,value string) clustered by (key) sorted by (key ASC) INTO 1 BUCKETS stored as parquet
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@parquet_jointable1_bucketed_sorted
+POSTHOOK: query: -- SMB join
+
+create table parquet_jointable1_bucketed_sorted (key int,value string) clustered by (key) sorted by (key ASC) INTO 1 BUCKETS stored as parquet
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@parquet_jointable1_bucketed_sorted
+PREHOOK: query: insert overwrite table parquet_jointable1_bucketed_sorted select key,concat(value,"value1") as value from staging cluster by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@staging
+PREHOOK: Output: default@parquet_jointable1_bucketed_sorted
+[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 parquet_jointable1_bucketed_sorted select key,concat(value,"value1") as value from staging cluster by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@staging
+POSTHOOK: Output: default@parquet_jointable1_bucketed_sorted
+POSTHOOK: Lineage: parquet_jointable1_bucketed_sorted.key SIMPLE [(staging)staging.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: parquet_jointable1_bucketed_sorted.value EXPRESSION [(staging)staging.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: create table parquet_jointable2_bucketed_sorted (key int,value1 string, value2 string) clustered by (key) sorted by (key ASC) INTO 1 BUCKETS stored as parquet
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@parquet_jointable2_bucketed_sorted
+POSTHOOK: query: create table parquet_jointable2_bucketed_sorted (key int,value1 string, value2 string) clustered by (key) sorted by (key ASC) INTO 1 BUCKETS stored as parquet
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@parquet_jointable2_bucketed_sorted
+PREHOOK: query: insert overwrite table parquet_jointable2_bucketed_sorted select key,concat(value,"value2-1") as value1,concat(value,"value2-2") as value2 from staging cluster by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@staging
+PREHOOK: Output: default@parquet_jointable2_bucketed_sorted
+[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 parquet_jointable2_bucketed_sorted select key,concat(value,"value2-1") as value1,concat(value,"value2-2") as value2 from staging cluster by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@staging
+POSTHOOK: Output: default@parquet_jointable2_bucketed_sorted
+POSTHOOK: Lineage: parquet_jointable2_bucketed_sorted.key SIMPLE [(staging)staging.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: parquet_jointable2_bucketed_sorted.value1 EXPRESSION [(staging)staging.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: parquet_jointable2_bucketed_sorted.value2 EXPRESSION [(staging)staging.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain select p1.value,p2.value2 from parquet_jointable1_bucketed_sorted p1 join parquet_jointable2_bucketed_sorted p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select p1.value,p2.value2 from parquet_jointable1_bucketed_sorted p1 join parquet_jointable2_bucketed_sorted p2 on p1.key=p2.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 PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: p2
+ Statistics: Num rows: 5 Data size: 526 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 3 Data size: 315 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value2 (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 3 Data size: 334 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col1}
+ outputColumnNames: _col1, _col7
+ Statistics: Num rows: 3 Data size: 346 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 346 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 346 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p1.value,p2.value2 from parquet_jointable1_bucketed_sorted p1 join parquet_jointable2_bucketed_sorted p2 on p1.key=p2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@parquet_jointable1_bucketed_sorted
+PREHOOK: Input: default@parquet_jointable2_bucketed_sorted
+#### A masked pattern was here ####
+POSTHOOK: query: select p1.value,p2.value2 from parquet_jointable1_bucketed_sorted p1 join parquet_jointable2_bucketed_sorted p2 on p1.key=p2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@parquet_jointable1_bucketed_sorted
+POSTHOOK: Input: default@parquet_jointable2_bucketed_sorted
+#### A masked pattern was here ####
+val_0value1 val_0value2-2
+val_10value1 val_10value2-2
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,250 @@
+PREHOOK: query: EXPLAIN
+SELECT src1.c1, count(1)
+FROM
+(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4')
+GROUP BY src1.c1
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT src1.c1, count(1)
+FROM
+(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4')
+GROUP BY src1.c1
+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 PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean)
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 < '400') and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 2 Data size: 21 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: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((key > '1') and (key < '400')) and key is not null) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 < '400') and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: EXPLAIN
+SELECT src1.c1, count(1)
+FROM
+(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4')
+GROUP BY src1.c1
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT src1.c1, count(1)
+FROM
+(SELECT src.key AS c1, src.value AS c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key AS c3, src.value AS c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' AND (src1.c2 < 'val_50' OR src1.c1 > '2') AND (src2.c3 > '50' OR src1.c1 < '50') AND (src2.c3 <> '4')
+GROUP BY src1.c1
+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 PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean)
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 9 Data size: 95 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((key > '1') and (key < '400')) and key is not null) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 9 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join.q.out?rev=1634671&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join.q.out Mon Oct 27 19:56:58 2014
@@ -0,0 +1,1074 @@
+PREHOOK: query: EXPLAIN
+SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+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 PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean)
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 < '400') and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 2 Data size: 21 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: 2 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((key > '1') and (key < '400')) and key is not null) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col0 < '400') and _col0 is not null) (type: boolean)
+ Statistics: Num rows: 1 Data size: 10 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: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+200 val_200
+200 val_200
+200 val_200
+200 val_200
+201 val_201
+202 val_202
+203 val_203
+203 val_203
+203 val_203
+203 val_203
+205 val_205
+205 val_205
+205 val_205
+205 val_205
+207 val_207
+207 val_207
+207 val_207
+207 val_207
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+209 val_209
+209 val_209
+209 val_209
+209 val_209
+213 val_213
+213 val_213
+213 val_213
+213 val_213
+214 val_214
+216 val_216
+216 val_216
+216 val_216
+216 val_216
+217 val_217
+217 val_217
+217 val_217
+217 val_217
+218 val_218
+219 val_219
+219 val_219
+219 val_219
+219 val_219
+221 val_221
+221 val_221
+221 val_221
+221 val_221
+222 val_222
+223 val_223
+223 val_223
+223 val_223
+223 val_223
+224 val_224
+224 val_224
+224 val_224
+224 val_224
+226 val_226
+228 val_228
+229 val_229
+229 val_229
+229 val_229
+229 val_229
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+233 val_233
+233 val_233
+233 val_233
+233 val_233
+235 val_235
+237 val_237
+237 val_237
+237 val_237
+237 val_237
+238 val_238
+238 val_238
+238 val_238
+238 val_238
+239 val_239
+239 val_239
+239 val_239
+239 val_239
+24 val_24
+24 val_24
+24 val_24
+24 val_24
+241 val_241
+242 val_242
+242 val_242
+242 val_242
+242 val_242
+244 val_244
+247 val_247
+248 val_248
+249 val_249
+252 val_252
+255 val_255
+255 val_255
+255 val_255
+255 val_255
+256 val_256
+256 val_256
+256 val_256
+256 val_256
+257 val_257
+258 val_258
+26 val_26
+26 val_26
+26 val_26
+26 val_26
+260 val_260
+262 val_262
+263 val_263
+265 val_265
+265 val_265
+265 val_265
+265 val_265
+266 val_266
+27 val_27
+272 val_272
+272 val_272
+272 val_272
+272 val_272
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+274 val_274
+275 val_275
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+278 val_278
+278 val_278
+278 val_278
+278 val_278
+28 val_28
+280 val_280
+280 val_280
+280 val_280
+280 val_280
+281 val_281
+281 val_281
+281 val_281
+281 val_281
+282 val_282
+282 val_282
+282 val_282
+282 val_282
+283 val_283
+284 val_284
+285 val_285
+286 val_286
+287 val_287
+288 val_288
+288 val_288
+288 val_288
+288 val_288
+289 val_289
+291 val_291
+292 val_292
+296 val_296
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+30 val_30
+302 val_302
+305 val_305
+306 val_306
+307 val_307
+307 val_307
+307 val_307
+307 val_307
+308 val_308
+309 val_309
+309 val_309
+309 val_309
+309 val_309
+310 val_310
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+315 val_315
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+317 val_317
+317 val_317
+317 val_317
+317 val_317
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+321 val_321
+321 val_321
+321 val_321
+321 val_321
+322 val_322
+322 val_322
+322 val_322
+322 val_322
+323 val_323
+325 val_325
+325 val_325
+325 val_325
+325 val_325
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+33 val_33
+331 val_331
+331 val_331
+331 val_331
+331 val_331
+332 val_332
+333 val_333
+333 val_333
+333 val_333
+333 val_333
+335 val_335
+336 val_336
+338 val_338
+339 val_339
+34 val_34
+341 val_341
+342 val_342
+342 val_342
+342 val_342
+342 val_342
+344 val_344
+344 val_344
+344 val_344
+344 val_344
+345 val_345
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+351 val_351
+353 val_353
+353 val_353
+353 val_353
+353 val_353
+356 val_356
+360 val_360
+362 val_362
+364 val_364
+365 val_365
+366 val_366
+367 val_367
+367 val_367
+367 val_367
+367 val_367
+368 val_368
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+37 val_37
+37 val_37
+37 val_37
+37 val_37
+373 val_373
+374 val_374
+375 val_375
+377 val_377
+378 val_378
+379 val_379
+382 val_382
+382 val_382
+382 val_382
+382 val_382
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+386 val_386
+389 val_389
+392 val_392
+393 val_393
+394 val_394
+395 val_395
+395 val_395
+395 val_395
+395 val_395
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+397 val_397
+397 val_397
+397 val_397
+397 val_397
+399 val_399
+399 val_399
+399 val_399
+399 val_399
+PREHOOK: query: EXPLAIN
+SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+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 PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((((key > '2') and (key < '400')) and key is not null) and (key <> '4')) and (key > '20')) (type: boolean)
+ Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 95 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: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((((key > '1') and (key < '400')) and key is not null) and (key > '20')) and ((value < 'val_50') or (key > '2'))) and (key <> '4')) (type: boolean)
+ Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 9 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((_col0 > '20') and ((_col1 < 'val_50') or (_col0 > '2'))) and ((_col2 > '50') or (_col0 < '50'))) and (_col2 <> '4')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT src1.c1, src2.c4
+FROM
+(SELECT src.key as c1, src.value as c2 from src where src.key > '1' ) src1
+JOIN
+(SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2
+ON src1.c1 = src2.c3 AND src1.c1 < '400'
+WHERE src1.c1 > '20' and (src1.c2 < 'val_50' or src1.c1 > '2') and (src2.c3 > '50' or src1.c1 < '50') and (src2.c3 <> '4')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+200 val_200
+200 val_200
+200 val_200
+200 val_200
+201 val_201
+202 val_202
+203 val_203
+203 val_203
+203 val_203
+203 val_203
+205 val_205
+205 val_205
+205 val_205
+205 val_205
+207 val_207
+207 val_207
+207 val_207
+207 val_207
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+208 val_208
+209 val_209
+209 val_209
+209 val_209
+209 val_209
+213 val_213
+213 val_213
+213 val_213
+213 val_213
+214 val_214
+216 val_216
+216 val_216
+216 val_216
+216 val_216
+217 val_217
+217 val_217
+217 val_217
+217 val_217
+218 val_218
+219 val_219
+219 val_219
+219 val_219
+219 val_219
+221 val_221
+221 val_221
+221 val_221
+221 val_221
+222 val_222
+223 val_223
+223 val_223
+223 val_223
+223 val_223
+224 val_224
+224 val_224
+224 val_224
+224 val_224
+226 val_226
+228 val_228
+229 val_229
+229 val_229
+229 val_229
+229 val_229
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+230 val_230
+233 val_233
+233 val_233
+233 val_233
+233 val_233
+235 val_235
+237 val_237
+237 val_237
+237 val_237
+237 val_237
+238 val_238
+238 val_238
+238 val_238
+238 val_238
+239 val_239
+239 val_239
+239 val_239
+239 val_239
+24 val_24
+24 val_24
+24 val_24
+24 val_24
+241 val_241
+242 val_242
+242 val_242
+242 val_242
+242 val_242
+244 val_244
+247 val_247
+248 val_248
+249 val_249
+252 val_252
+255 val_255
+255 val_255
+255 val_255
+255 val_255
+256 val_256
+256 val_256
+256 val_256
+256 val_256
+257 val_257
+258 val_258
+26 val_26
+26 val_26
+26 val_26
+26 val_26
+260 val_260
+262 val_262
+263 val_263
+265 val_265
+265 val_265
+265 val_265
+265 val_265
+266 val_266
+27 val_27
+272 val_272
+272 val_272
+272 val_272
+272 val_272
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+273 val_273
+274 val_274
+275 val_275
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+277 val_277
+278 val_278
+278 val_278
+278 val_278
+278 val_278
+28 val_28
+280 val_280
+280 val_280
+280 val_280
+280 val_280
+281 val_281
+281 val_281
+281 val_281
+281 val_281
+282 val_282
+282 val_282
+282 val_282
+282 val_282
+283 val_283
+284 val_284
+285 val_285
+286 val_286
+287 val_287
+288 val_288
+288 val_288
+288 val_288
+288 val_288
+289 val_289
+291 val_291
+292 val_292
+296 val_296
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+298 val_298
+30 val_30
+302 val_302
+305 val_305
+306 val_306
+307 val_307
+307 val_307
+307 val_307
+307 val_307
+308 val_308
+309 val_309
+309 val_309
+309 val_309
+309 val_309
+310 val_310
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+311 val_311
+315 val_315
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+316 val_316
+317 val_317
+317 val_317
+317 val_317
+317 val_317
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+318 val_318
+321 val_321
+321 val_321
+321 val_321
+321 val_321
+322 val_322
+322 val_322
+322 val_322
+322 val_322
+323 val_323
+325 val_325
+325 val_325
+325 val_325
+325 val_325
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+327 val_327
+33 val_33
+331 val_331
+331 val_331
+331 val_331
+331 val_331
+332 val_332
+333 val_333
+333 val_333
+333 val_333
+333 val_333
+335 val_335
+336 val_336
+338 val_338
+339 val_339
+34 val_34
+341 val_341
+342 val_342
+342 val_342
+342 val_342
+342 val_342
+344 val_344
+344 val_344
+344 val_344
+344 val_344
+345 val_345
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+348 val_348
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+35 val_35
+351 val_351
+353 val_353
+353 val_353
+353 val_353
+353 val_353
+356 val_356
+360 val_360
+362 val_362
+364 val_364
+365 val_365
+366 val_366
+367 val_367
+367 val_367
+367 val_367
+367 val_367
+368 val_368
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+369 val_369
+37 val_37
+37 val_37
+37 val_37
+37 val_37
+373 val_373
+374 val_374
+375 val_375
+377 val_377
+378 val_378
+379 val_379
+382 val_382
+382 val_382
+382 val_382
+382 val_382
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+384 val_384
+386 val_386
+389 val_389
+392 val_392
+393 val_393
+394 val_394
+395 val_395
+395 val_395
+395 val_395
+395 val_395
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+396 val_396
+397 val_397
+397 val_397
+397 val_397
+397 val_397
+399 val_399
+399 val_399
+399 val_399
+399 val_399