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 2015/09/09 09:08:34 UTC
[04/50] [abbrv] hive git commit: HIVE-11573: PointLookupOptimizer can
be pessimistic at a low nDV (Gopal V, reviewed by Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/pointlookup2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out
new file mode 100644
index 0000000..55edd90
--- /dev/null
+++ b/ql/src/test/results/clientpositive/pointlookup2.q.out
@@ -0,0 +1,1647 @@
+PREHOOK: query: drop table pcr_t1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table pcr_t1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table pcr_t2
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table pcr_t2
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table pcr_t3
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table pcr_t3
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@pcr_t1
+POSTHOOK: query: create table pcr_t1 (key int, value string) partitioned by (ds string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@pcr_t1
+PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@pcr_t1@ds=2000-04-08
+POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-08') select * from src where key < 20 order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@pcr_t1@ds=2000-04-08
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-08).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@pcr_t1@ds=2000-04-09
+POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-09') select * from src where key < 20 order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@pcr_t1@ds=2000-04-09
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-09).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@pcr_t1@ds=2000-04-10
+POSTHOOK: query: insert overwrite table pcr_t1 partition (ds='2000-04-10') select * from src where key < 20 order by key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@pcr_t1@ds=2000-04-10
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: pcr_t1 PARTITION(ds=2000-04-10).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+PREHOOK: query: create table pcr_t2 (ds string, key int, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@pcr_t2
+POSTHOOK: query: create table pcr_t2 (ds string, key int, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@pcr_t2
+PREHOOK: query: from pcr_t1
+insert overwrite table pcr_t2 select ds, key, value where ds='2000-04-08'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@pcr_t1
+PREHOOK: Input: default@pcr_t1@ds=2000-04-08
+PREHOOK: Output: default@pcr_t2
+POSTHOOK: query: from pcr_t1
+insert overwrite table pcr_t2 select ds, key, value where ds='2000-04-08'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@pcr_t1
+POSTHOOK: Input: default@pcr_t1@ds=2000-04-08
+POSTHOOK: Output: default@pcr_t2
+POSTHOOK: Lineage: pcr_t2.ds SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:ds, type:string, comment:null), ]
+POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: from pcr_t1
+insert overwrite table pcr_t2 select ds, key, value where ds='2000-04-08' and key=2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@pcr_t1
+PREHOOK: Input: default@pcr_t1@ds=2000-04-08
+PREHOOK: Output: default@pcr_t2
+POSTHOOK: query: from pcr_t1
+insert overwrite table pcr_t2 select ds, key, value where ds='2000-04-08' and key=2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@pcr_t1
+POSTHOOK: Input: default@pcr_t1@ds=2000-04-08
+POSTHOOK: Output: default@pcr_t2
+POSTHOOK: Lineage: pcr_t2.ds SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:ds, type:string, comment:null), ]
+POSTHOOK: Lineage: pcr_t2.key SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: pcr_t2.value SIMPLE [(pcr_t1)pcr_t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain extended
+select key, value, ds
+from pcr_t1
+where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2)
+order by key, value, ds
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select key, value, ds
+from pcr_t1
+where (ds='2000-04-08' and key=1) or (ds='2000-04-09' and key=2)
+order by key, value, ds
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_TABLE_OR_COL
+ key
+ TOK_SELEXPR
+ TOK_TABLE_OR_COL
+ value
+ TOK_SELEXPR
+ TOK_TABLE_OR_COL
+ ds
+ TOK_WHERE
+ or
+ and
+ =
+ TOK_TABLE_OR_COL
+ ds
+ '2000-04-08'
+ =
+ TOK_TABLE_OR_COL
+ key
+ 1
+ and
+ =
+ TOK_TABLE_OR_COL
+ ds
+ '2000-04-09'
+ =
+ TOK_TABLE_OR_COL
+ key
+ 2
+ TOK_ORDERBY
+ TOK_TABSORTCOLNAMEASC
+ TOK_TABLE_OR_COL
+ key
+ TOK_TABSORTCOLNAMEASC
+ TOK_TABLE_OR_COL
+ value
+ TOK_TABSORTCOLNAMEASC
+ TOK_TABLE_OR_COL
+ ds
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: pcr_t1
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+ Truncated Path -> Alias:
+ /pcr_t1/ds=2000-04-08 [pcr_t1]
+ /pcr_t1/ds=2000-04-09 [pcr_t1]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types int:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t1 t2
+on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08'
+order by t1.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t1 t2
+on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-08'
+order by t1.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t1
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t2
+ and
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+ .
+ TOK_TABLE_OR_COL
+ t2
+ key
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ ds
+ '2000-04-08'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ ds
+ '2000-04-08'
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_ALLCOLREF
+ TOK_ORDERBY
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 80 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: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: value (type: string)
+ auto parallelism: false
+ TableScan
+ alias: t2
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 80 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: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+ Truncated Path -> Alias:
+ /pcr_t1/ds=2000-04-08 [t1, t2]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col6, _col7
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-08' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int:string:string:int:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t1 t2
+on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09'
+order by t1.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t1 t2
+on t1.key=t2.key and t1.ds='2000-04-08' and t2.ds='2000-04-09'
+order by t1.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t1
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t2
+ and
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+ .
+ TOK_TABLE_OR_COL
+ t2
+ key
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ ds
+ '2000-04-08'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ ds
+ '2000-04-09'
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_ALLCOLREF
+ TOK_ORDERBY
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 80 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: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: value (type: string)
+ auto parallelism: false
+ TableScan
+ alias: t2
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 80 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: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+ Truncated Path -> Alias:
+ /pcr_t1/ds=2000-04-08 [t1]
+ /pcr_t1/ds=2000-04-09 [t2]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col6, _col7
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-09' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int:string:string:int:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t2 t2
+where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2)
+order by t2.key, t2.value, t1.ds
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t2 t2
+where (t1.ds='2000-04-08' and t2.key=1) or (t1.ds='2000-04-09' and t2.key=2)
+order by t2.key, t2.value, t1.ds
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t1
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t2
+ t2
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_ALLCOLREF
+ TOK_WHERE
+ or
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ ds
+ '2000-04-08'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ key
+ 1
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ ds
+ '2000-04-09'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ key
+ 2
+ TOK_ORDERBY
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t2
+ key
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t2
+ value
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t1
+ ds
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: key (type: int), value (type: string), ds (type: string)
+ auto parallelism: false
+ TableScan
+ alias: t2
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: ds (type: string), key (type: int), value (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: pcr_t2
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns ds,key,value
+ columns.comments
+ columns.types string:int:string
+#### A masked pattern was here ####
+ name default.pcr_t2
+ numFiles 1
+ numRows 1
+ rawDataSize 18
+ serialization.ddl struct pcr_t2 { string ds, i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 19
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns ds,key,value
+ columns.comments
+ columns.types string:int:string
+#### A masked pattern was here ####
+ name default.pcr_t2
+ numFiles 1
+ numRows 1
+ rawDataSize 18
+ serialization.ddl struct pcr_t2 { string ds, i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 19
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t2
+ name: default.pcr_t2
+ Truncated Path -> Alias:
+ /pcr_t1/ds=2000-04-08 [t1]
+ /pcr_t1/ds=2000-04-09 [t1]
+ /pcr_t2 [t2]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col8
+ Statistics: Num rows: 44 Data size: 352 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: ((_col2) IN ('2000-04-08', '2000-04-09') and (struct(_col7,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09'))) (type: boolean)
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string)
+ sort order: +++
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int:string:string:string:int:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t2 t2
+where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2)
+order by t1.key, t1.value, t2.ds
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended
+select *
+from pcr_t1 t1 join pcr_t2 t2
+where (t2.ds='2000-04-08' and t1.key=1) or (t2.ds='2000-04-09' and t1.key=2)
+order by t1.key, t1.value, t2.ds
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+
+TOK_QUERY
+ TOK_FROM
+ TOK_JOIN
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t1
+ t1
+ TOK_TABREF
+ TOK_TABNAME
+ pcr_t2
+ t2
+ TOK_INSERT
+ TOK_DESTINATION
+ TOK_DIR
+ TOK_TMP_FILE
+ TOK_SELECT
+ TOK_SELEXPR
+ TOK_ALLCOLREF
+ TOK_WHERE
+ or
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ ds
+ '2000-04-08'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+ 1
+ and
+ =
+ .
+ TOK_TABLE_OR_COL
+ t2
+ ds
+ '2000-04-09'
+ =
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+ 2
+ TOK_ORDERBY
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t1
+ key
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t1
+ value
+ TOK_TABSORTCOLNAMEASC
+ .
+ TOK_TABLE_OR_COL
+ t2
+ ds
+
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: t1
+ Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: key (type: int), value (type: string), ds (type: string)
+ auto parallelism: false
+ TableScan
+ alias: t2
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: ds (type: string), key (type: int), value (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-08
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-09
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2000-04-10
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2000-04-10
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ numFiles 1
+ numRows 20
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 160
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 180
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value
+ columns.comments
+ columns.types int:string
+#### A masked pattern was here ####
+ name default.pcr_t1
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct pcr_t1 { i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t1
+ name: default.pcr_t1
+#### A masked pattern was here ####
+ Partition
+ base file name: pcr_t2
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns ds,key,value
+ columns.comments
+ columns.types string:int:string
+#### A masked pattern was here ####
+ name default.pcr_t2
+ numFiles 1
+ numRows 1
+ rawDataSize 18
+ serialization.ddl struct pcr_t2 { string ds, i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 19
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns ds,key,value
+ columns.comments
+ columns.types string:int:string
+#### A masked pattern was here ####
+ name default.pcr_t2
+ numFiles 1
+ numRows 1
+ rawDataSize 18
+ serialization.ddl struct pcr_t2 { string ds, i32 key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 19
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.pcr_t2
+ name: default.pcr_t2
+ Truncated Path -> Alias:
+ /pcr_t1/ds=2000-04-08 [t1]
+ /pcr_t1/ds=2000-04-09 [t1]
+ /pcr_t1/ds=2000-04-10 [t1]
+ /pcr_t2 [t2]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col8
+ Statistics: Num rows: 66 Data size: 528 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ isSamplingPred: false
+ predicate: (struct(_col0,_col6)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ sort order: +++
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int:string:string:string:int:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: drop table pcr_t1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@pcr_t1
+PREHOOK: Output: default@pcr_t1
+POSTHOOK: query: drop table pcr_t1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@pcr_t1
+POSTHOOK: Output: default@pcr_t1
+PREHOOK: query: drop table pcr_t2
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@pcr_t2
+PREHOOK: Output: default@pcr_t2
+POSTHOOK: query: drop table pcr_t2
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@pcr_t2
+POSTHOOK: Output: default@pcr_t2
+PREHOOK: query: drop table pcr_t3
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table pcr_t3
+POSTHOOK: type: DROPTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/ppd_transform.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ppd_transform.q.out b/ql/src/test/results/clientpositive/ppd_transform.q.out
index f536767..17248e4 100644
--- a/ql/src/test/results/clientpositive/ppd_transform.q.out
+++ b/ql/src/test/results/clientpositive/ppd_transform.q.out
@@ -390,21 +390,21 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0) IN ('a', 'b') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 = 'a') or (_col0 = 'b')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 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
Filter Operator
- predicate: (_col0) IN ('c', 'd') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 = 'c') or (_col0 = 'd')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/spark/pcr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/pcr.q.out b/ql/src/test/results/clientpositive/spark/pcr.q.out
index 5aa0df8..fb08f10 100644
--- a/ql/src/test/results/clientpositive/spark/pcr.q.out
+++ b/ql/src/test/results/clientpositive/spark/pcr.q.out
@@ -2534,16 +2534,16 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (struct(key,ds)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
- Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ predicate: (((ds = '2000-04-08') and (key = 1)) or ((ds = '2000-04-09') and (key = 2))) (type: boolean)
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int), value (type: string), ds (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
tag: -1
auto parallelism: false
Path -> Alias:
@@ -2648,13 +2648,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/spark/ppd_transform.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/ppd_transform.q.out b/ql/src/test/results/clientpositive/spark/ppd_transform.q.out
index a6e6e38..52a847a 100644
--- a/ql/src/test/results/clientpositive/spark/ppd_transform.q.out
+++ b/ql/src/test/results/clientpositive/spark/ppd_transform.q.out
@@ -405,21 +405,21 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col0) IN ('a', 'b') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 = 'a') or (_col0 = 'b')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 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
Filter Operator
- predicate: (_col0) IN ('c', 'd') (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col0 = 'c') or (_col0 = 'd')) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
index 54003c3..c2250e6 100644
--- a/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorized_case.q.out
@@ -45,7 +45,7 @@ STAGE PLANS:
TableScan
alias: alltypesorc
Filter Operator
- predicate: (csmallint) IN (418, 12205, 10583) (type: boolean)
+ predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean)
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
index e8a9786..9756b0c 100644
--- a/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainuser_1.q.out
@@ -2909,7 +2909,7 @@ Stage-0
Select Operator [SEL_2]
outputColumnNames:["_col0"]
Filter Operator [FIL_4]
- predicate:(c_int) IN (-6, 6) (type: boolean)
+ predicate:((c_int = -6) or (c_int = 6)) (type: boolean)
TableScan [TS_0]
alias:cbo_t1
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/vectorized_case.q.out b/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
index 54003c3..c2250e6 100644
--- a/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/tez/vectorized_case.q.out
@@ -45,7 +45,7 @@ STAGE PLANS:
TableScan
alias: alltypesorc
Filter Operator
- predicate: (csmallint) IN (418, 12205, 10583) (type: boolean)
+ predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean)
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
http://git-wip-us.apache.org/repos/asf/hive/blob/b247cac4/ql/src/test/results/clientpositive/vectorized_case.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vectorized_case.q.out b/ql/src/test/results/clientpositive/vectorized_case.q.out
index 9e47014..73bf12d 100644
--- a/ql/src/test/results/clientpositive/vectorized_case.q.out
+++ b/ql/src/test/results/clientpositive/vectorized_case.q.out
@@ -46,19 +46,20 @@ STAGE PLANS:
alias: alltypesorc
Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint) IN (418, 12205, 10583) (type: boolean)
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((csmallint = 418) or (csmallint = 12205) or (csmallint = 10583)) (type: boolean)
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: csmallint (type: smallint), CASE WHEN ((csmallint = 418)) THEN ('a') WHEN ((csmallint = 12205)) THEN ('b') ELSE ('c') END (type: string), CASE (csmallint) WHEN (418) THEN ('a') WHEN (12205) THEN ('b') ELSE ('c') END (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 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
+ Execution mode: vectorized
Stage: Stage-0
Fetch Operator