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 [3/16] - 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_filter.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/annotate_stats_filter.q.out?rev=1543120&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/annotate_stats_filter.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/annotate_stats_filter.q.out Mon Nov 18 19:29:24 2013
@@ -0,0 +1,2470 @@
+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: -- column stats are not COMPLETE, so stats are not updated
+-- numRows: 8 rawDataSize: 796
+explain extended select * from loc_orc where state='OH'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- column stats are not COMPLETE, so stats are not updated
+-- numRows: 8 rawDataSize: 796
+explain extended select * from loc_orc where state='OH'
+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)) (TOK_WHERE (= (TOK_TABLE_OR_COL state) 'OH'))))
+
+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: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (state = 'OH')
+ type: boolean
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: NONE
+ 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
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: 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
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+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: -- state column has 5 distincts. numRows/countDistincts
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where state='OH'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- state column has 5 distincts. numRows/countDistincts
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where state='OH'
+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)) (TOK_WHERE (= (TOK_TABLE_OR_COL state) 'OH'))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (state = 'OH')
+ type: boolean
+ Statistics:
+ numRows: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 1 dataSize: 102 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- not equals comparison shouldn't affect number of rows. rawDataSize is 792 and not 796 because of rounding off issue with avgColLen. avgColLen uses integers and not double.
+-- numRows: 8 rawDataSize: 804
+explain extended select * from loc_orc where state!='OH'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- not equals comparison shouldn't affect number of rows. rawDataSize is 792 and not 796 because of rounding off issue with avgColLen. avgColLen uses integers and not double.
+-- numRows: 8 rawDataSize: 804
+explain extended select * from loc_orc where state!='OH'
+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)) (TOK_WHERE (!= (TOK_TABLE_OR_COL state) 'OH'))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (state <> 'OH')
+ type: boolean
+ Statistics:
+ numRows: 8 dataSize: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 8 dataSize: 804 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: explain extended select * from loc_orc where state<>'OH'
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended select * from loc_orc where state<>'OH'
+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)) (TOK_WHERE (<> (TOK_TABLE_OR_COL state) 'OH'))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (state <> 'OH')
+ type: boolean
+ Statistics:
+ numRows: 8 dataSize: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 8 dataSize: 804 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- nulls are treated as constant equality comparison
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where zip is null
+PREHOOK: type: QUERY
+POSTHOOK: query: -- nulls are treated as constant equality comparison
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where zip is null
+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)) (TOK_WHERE (TOK_FUNCTION TOK_ISNULL (TOK_TABLE_OR_COL zip)))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: zip is null
+ type: boolean
+ Statistics:
+ numRows: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 1 dataSize: 102 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where !(zip is not null)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where !(zip is not null)
+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)) (TOK_WHERE (! (TOK_FUNCTION TOK_ISNOTNULL (TOK_TABLE_OR_COL zip))))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (not zip is not null)
+ type: boolean
+ Statistics:
+ numRows: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 1 dataSize: 102 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- not nulls are treated as inverse of nulls
+-- numRows: 7 rawDataSize: 702
+explain extended select * from loc_orc where zip is not null
+PREHOOK: type: QUERY
+POSTHOOK: query: -- not nulls are treated as inverse of nulls
+-- numRows: 7 rawDataSize: 702
+explain extended select * from loc_orc where zip is not null
+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)) (TOK_WHERE (TOK_FUNCTION TOK_ISNOTNULL (TOK_TABLE_OR_COL zip)))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: zip is not null
+ type: boolean
+ Statistics:
+ numRows: 7 dataSize: 702 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 7 dataSize: 702 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 7 dataSize: 702 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- numRows: 7 rawDataSize: 702
+explain extended select * from loc_orc where !(zip is null)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- numRows: 7 rawDataSize: 702
+explain extended select * from loc_orc where !(zip is null)
+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)) (TOK_WHERE (! (TOK_FUNCTION TOK_ISNULL (TOK_TABLE_OR_COL zip))))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (not zip is null)
+ type: boolean
+ Statistics:
+ numRows: 7 dataSize: 702 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 7 dataSize: 702 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 7 dataSize: 702 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- NOT evaluation. true will pass all rows, false will not pass any rows
+-- numRows: 8 rawDataSize: 804
+explain extended select * from loc_orc where !false
+PREHOOK: type: QUERY
+POSTHOOK: query: -- NOT evaluation. true will pass all rows, false will not pass any rows
+-- numRows: 8 rawDataSize: 804
+explain extended select * from loc_orc where !false
+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)) (TOK_WHERE (! false))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (not false)
+ type: boolean
+ Statistics:
+ numRows: 8 dataSize: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 804 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 8 dataSize: 804 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- numRows: 0 rawDataSize: 0
+explain extended select * from loc_orc where !true
+PREHOOK: type: QUERY
+POSTHOOK: query: -- numRows: 0 rawDataSize: 0
+explain extended select * from loc_orc where !true
+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)) (TOK_WHERE (! true))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (not true)
+ type: boolean
+ Statistics:
+ numRows: 0 dataSize: 0 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 0 dataSize: 0 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 0 dataSize: 0 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- OR evaluation. 1 row for OH and 1 row for CA
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where state='OH' or state='CA'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- OR evaluation. 1 row for OH and 1 row for CA
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where state='OH' or state='CA'
+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)) (TOK_WHERE (or (= (TOK_TABLE_OR_COL state) 'OH') (= (TOK_TABLE_OR_COL state) 'CA')))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: ((state = 'OH') or (state = 'CA'))
+ type: boolean
+ Statistics:
+ numRows: 2 dataSize: 204 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 2 dataSize: 204 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 2 dataSize: 204 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- AND evaluation. cascadingly apply rules. 8/2 = 4/2 = 2
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where year=2001 and year is null
+PREHOOK: type: QUERY
+POSTHOOK: query: -- AND evaluation. cascadingly apply rules. 8/2 = 4/2 = 2
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where year=2001 and year is null
+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)) (TOK_WHERE (and (= (TOK_TABLE_OR_COL year) 2001) (TOK_FUNCTION TOK_ISNULL (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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: ((year = 2001) and year is null)
+ type: boolean
+ Statistics:
+ numRows: 2 dataSize: 204 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 2 dataSize: 204 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 2 dataSize: 204 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where year=2001 and state='OH' and state='FL'
+PREHOOK: type: QUERY
+POSTHOOK: query: -- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where year=2001 and state='OH' and state='FL'
+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)) (TOK_WHERE (and (and (= (TOK_TABLE_OR_COL year) 2001) (= (TOK_TABLE_OR_COL state) 'OH')) (= (TOK_TABLE_OR_COL state) 'FL')))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (((year = 2001) and (state = 'OH')) and (state = 'FL'))
+ type: boolean
+ Statistics:
+ numRows: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 1 dataSize: 102 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- AND and OR together. left expr will yield 1 row and right will yield 1 row
+-- numRows: 3 rawDataSize: 306
+explain extended select * from loc_orc where (year=2001 and year is null) or (state='CA')
+PREHOOK: type: QUERY
+POSTHOOK: query: -- AND and OR together. left expr will yield 1 row and right will yield 1 row
+-- numRows: 3 rawDataSize: 306
+explain extended select * from loc_orc where (year=2001 and year is null) or (state='CA')
+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)) (TOK_WHERE (or (and (= (TOK_TABLE_OR_COL year) 2001) (TOK_FUNCTION TOK_ISNULL (TOK_TABLE_OR_COL year))) (= (TOK_TABLE_OR_COL state) 'CA')))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (((year = 2001) and year is null) or (state = 'CA'))
+ type: boolean
+ Statistics:
+ numRows: 3 dataSize: 306 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 3 dataSize: 306 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 3 dataSize: 306 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- AND and OR together. left expr will yield 8 rows and right will yield 1 row
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where (year=2001 or year is null) and (state='CA')
+PREHOOK: type: QUERY
+POSTHOOK: query: -- AND and OR together. left expr will yield 8 rows and right will yield 1 row
+-- numRows: 1 rawDataSize: 102
+explain extended select * from loc_orc where (year=2001 or year is null) and (state='CA')
+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)) (TOK_WHERE (and (or (= (TOK_TABLE_OR_COL year) 2001) (TOK_FUNCTION TOK_ISNULL (TOK_TABLE_OR_COL year))) (= (TOK_TABLE_OR_COL state) 'CA')))))
+
+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
+ Filter Operator
+ isSamplingPred: false
+ predicate:
+ expr: (((year = 2001) or year is null) and (state = 'CA'))
+ type: boolean
+ Statistics:
+ numRows: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ 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: 1 dataSize: 102 basicStatsState: COMPLETE colStatsState: COMPLETE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics:
+ numRows: 1 dataSize: 102 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,_col2,_col3
+ columns.types string:int:bigint: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
+ 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]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: -- all inequality conditions rows/3 is the rules
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where locid < 30
+PREHOOK: type: QUERY
+POSTHOOK: query: -- all inequality conditions rows/3 is the rules
+-- numRows: 2 rawDataSize: 204
+explain extended select * from loc_orc where locid < 30
+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:
[... 480 lines stripped ...]