You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by rh...@apache.org on 2013/11/18 20:29:27 UTC
svn commit: r1543120 [4/16] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ data/files/
ql/src/java/org/apache/hadoop/hive/ql/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/ ql/src/java/org/a...
Added: hive/trunk/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out?rev=1543120&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/annotate_stats_groupby.q.out Mon Nov 18 19:29:24 2013
@@ -0,0 +1,1750 @@
+PREHOOK: query: create table if not exists loc_staging (
+ state string,
+ locid int,
+ zip bigint,
+ year int
+) row format delimited fields terminated by '|' stored as textfile
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table if not exists loc_staging (
+ state string,
+ locid int,
+ zip bigint,
+ year int
+) row format delimited fields terminated by '|' stored as textfile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@loc_staging
+PREHOOK: query: create table loc_orc like loc_staging
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table loc_orc like loc_staging
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@loc_orc
+PREHOOK: query: alter table loc_orc set fileformat orc
+PREHOOK: type: ALTERTABLE_FILEFORMAT
+PREHOOK: Input: default@loc_orc
+PREHOOK: Output: default@loc_orc
+POSTHOOK: query: alter table loc_orc set fileformat orc
+POSTHOOK: type: ALTERTABLE_FILEFORMAT
+POSTHOOK: Input: default@loc_orc
+POSTHOOK: Output: default@loc_orc
+PREHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging
+PREHOOK: type: LOAD
+PREHOOK: Output: default@loc_staging
+POSTHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@loc_staging
+PREHOOK: query: insert overwrite table loc_orc select * from loc_staging
+PREHOOK: type: QUERY
+PREHOOK: Input: default@loc_staging
+PREHOOK: Output: default@loc_orc
+POSTHOOK: query: insert overwrite table loc_orc select * from loc_staging
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@loc_staging
+POSTHOOK: Output: default@loc_orc
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+PREHOOK: query: -- numRows: 8 rawDataSize: 796
+explain extended select * from loc_orc
+PREHOOK: type: QUERY
+POSTHOOK: query: -- numRows: 8 rawDataSize: 796
+explain extended select * from loc_orc
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))
+
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: NONE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: zip
+ type: bigint
+ expr: year
+ type: int
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: NONE
+ ListSink
+
+
+PREHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year
+PREHOOK: type: QUERY
+PREHOOK: Input: default@loc_orc
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@loc_orc
+#### A masked pattern was here ####
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+PREHOOK: query: -- only one distinct value in year column + 1 NULL value
+-- map-side GBY: numRows: 8 (map-side will not do any reduction)
+-- reduce-side GBY: numRows: 2
+explain extended select year from loc_orc group by year
+PREHOOK: type: QUERY
+POSTHOOK: query: -- only one distinct value in year column + 1 NULL value
+-- map-side GBY: numRows: 8 (map-side will not do any reduction)
+-- reduce-side GBY: numRows: 2
+explain extended select year from loc_orc group by year
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL year))) (TOK_GROUPBY (TOK_TABLE_OR_COL year))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: year
+ type: int
+ outputColumnNames: year
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: year
+ type: int
+ mode: hash
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 8 dataSize: 28 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ Statistics:
+ numRows: 8 dataSize: 28 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY: numRows: 8
+-- reduce-side GBY: numRows: 4
+explain extended select state,locid from loc_orc group by state,locid
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY: numRows: 8
+-- reduce-side GBY: numRows: 4
+explain extended select state,locid from loc_orc group by state,locid
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_GROUPBY (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 8 dataSize: 720 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ Statistics:
+ numRows: 8 dataSize: 720 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 4 dataSize: 360 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 4 dataSize: 360 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 4 dataSize: 360 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 32 reduce-side GBY numRows: 16
+explain extended select state,locid from loc_orc group by state,locid with cube
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 32 reduce-side GBY numRows: 16
+explain extended select state,locid from loc_orc group by state,locid with cube
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 32 dataSize: 3184 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 32 dataSize: 3184 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 16 dataSize: 2800 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 16 dataSize: 1440 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 16 dataSize: 1440 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 24 reduce-side GBY numRows: 12
+explain extended select state,locid from loc_orc group by state,locid with rollup
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 24 reduce-side GBY numRows: 12
+explain extended select state,locid from loc_orc group by state,locid with rollup
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_ROLLUP_GROUPBY (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 24 dataSize: 2388 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 24 dataSize: 2388 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 12 dataSize: 2100 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 12 dataSize: 1080 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 12 dataSize: 1080 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 8 reduce-side GBY numRows: 4
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state))
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 8 reduce-side GBY numRows: 4
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state))
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_GROUPING_SETS (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL state)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 4 dataSize: 700 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 4 dataSize: 360 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 4 dataSize: 360 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 16 reduce-side GBY numRows: 8
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state),(locid))
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 16 reduce-side GBY numRows: 8
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state),(locid))
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_GROUPING_SETS (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL state)) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL locid)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 8 dataSize: 1400 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 8 dataSize: 720 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 8 dataSize: 720 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 24 reduce-side GBY numRows: 12
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state),(locid),())
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 24 reduce-side GBY numRows: 12
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state),(locid),())
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_GROUPING_SETS (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL state)) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL locid)) TOK_GROUPING_SETS_EXPRESSION)))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 24 dataSize: 2388 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 24 dataSize: 2388 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 12 dataSize: 2100 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 12 dataSize: 1080 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 12 dataSize: 1080 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 32 reduce-side GBY numRows: 16
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state,locid),(state),(locid),())
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 32 reduce-side GBY numRows: 16
+explain extended select state,locid from loc_orc group by state,locid grouping sets((state,locid),(state),(locid),())
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_GROUPING_SETS (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid)) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL state)) (TOK_GROUPING_SETS_EXPRESSION (TOK_TABLE_OR_COL locid)) TOK_GROUPING_SETS_EXPRESSION)))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 32 dataSize: 3184 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 32 dataSize: 3184 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 16 dataSize: 2800 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 16 dataSize: 1440 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 16 dataSize: 1440 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY: numRows: 80 (map-side will not do any reduction)
+-- reduce-side GBY: numRows: 2 Reason: numDistinct of year is 2. numRows = min(80/2, 2)
+explain extended select year from loc_orc group by year
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY: numRows: 80 (map-side will not do any reduction)
+-- reduce-side GBY: numRows: 2 Reason: numDistinct of year is 2. numRows = min(80/2, 2)
+explain extended select year from loc_orc group by year
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL year))) (TOK_GROUPBY (TOK_TABLE_OR_COL year))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: year
+ type: int
+ outputColumnNames: year
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: year
+ type: int
+ mode: hash
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 80 dataSize: 280 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ Statistics:
+ numRows: 80 dataSize: 280 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 2 dataSize: 8 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types int
+ escape.delim \
+ hive.serialization.extend.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
+
+
+PREHOOK: query: -- map-side GBY numRows: 320 reduce-side GBY numRows: 42 Reason: numDistinct of state and locid are 6,7 resp. numRows = min(320/2, 6*7)
+explain extended select state,locid from loc_orc group by state,locid with cube
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map-side GBY numRows: 320 reduce-side GBY numRows: 42 Reason: numDistinct of state and locid are 6,7 resp. numRows = min(320/2, 6*7)
+explain extended select state,locid from loc_orc group by state,locid with cube
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ]
+POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ]
+POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)) (TOK_SELEXPR (TOK_TABLE_OR_COL locid))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL state) (TOK_TABLE_OR_COL locid))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ loc_orc
+ TableScan
+ alias: loc_orc
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ GatherStats: false
+ Select Operator
+ expressions:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ outputColumnNames: state, locid
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: state
+ type: string
+ expr: locid
+ type: int
+ expr: '0'
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 320 dataSize: 31840 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ sort order: +++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ expr: _col2
+ type: string
+ Statistics:
+ numRows: 320 dataSize: 31840 basicStatsState: COMPLETE colStatsState: COMPLETE
+ tag: -1
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: loc_orc
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+
+ input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns state,locid,zip,year
+ columns.types string:int:bigint:int
+ field.delim |
+#### A masked pattern was here ####
+ name default.loc_orc
+ numFiles 1
+ numRows 8
+ rawDataSize 796
+ serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year}
+ serialization.format |
+ serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ totalSize 489
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+ name: default.loc_orc
+ name: default.loc_orc
+ Truncated Path -> Alias:
+ /loc_orc [loc_orc]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: int
+ expr: KEY._col2
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics:
+ numRows: 42 dataSize: 7350 basicStatsState: COMPLETE colStatsState: COMPLETE
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: int
+ outputColumnNames: _col0, _col1
+ Statistics:
+ numRows: 42 dataSize: 3780 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 42 dataSize: 3780 basicStatsState: COMPLETE colStatsState: COMPLETE
+#### 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
+ columns.types string:int
+ escape.delim \
+ hive.serialization.extend.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
+
+