http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/bucket4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket4.q.out b/ql/src/test/results/clientpositive/bucket4.q.out deleted file mode 100644 index d06c7ed..0000000 --- a/ql/src/test/results/clientpositive/bucket4.q.out +++ /dev/null @@ -1,467 +0,0 @@ -PREHOOK: query: CREATE TABLE bucket4_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@bucket4_1 -POSTHOOK: query: CREATE TABLE bucket4_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@bucket4_1 -PREHOOK: query: explain extended -insert overwrite table bucket4_1 -select * from src -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -insert overwrite table bucket4_1 -select * from src -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 2 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.bucket4_1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucket4_1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket4_1 - TotalFiles: 2 - GatherStats: true - MultiFileSpray: true - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.bucket4_1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucket4_1 { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket4_1 - - Stage: Stage-2 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: insert overwrite table bucket4_1 -select * from src -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@bucket4_1 -POSTHOOK: query: insert overwrite table bucket4_1 -select * from src -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@bucket4_1 -POSTHOOK: Lineage: bucket4_1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: bucket4_1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain -select * from bucket4_1 tablesample (bucket 1 out of 2) s -PREHOOK: type: QUERY -POSTHOOK: query: explain -select * from bucket4_1 tablesample (bucket 1 out of 2) s -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: s - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from bucket4_1 tablesample (bucket 1 out of 2) s -PREHOOK: type: QUERY -PREHOOK: Input: default@bucket4_1 -#### A masked pattern was here #### -POSTHOOK: query: select * from bucket4_1 tablesample (bucket 1 out of 2) s -POSTHOOK: type: QUERY -POSTHOOK: Input: default@bucket4_1 -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -8 val_8 -10 val_10 -12 val_12 -12 val_12 -18 val_18 -18 val_18 -20 val_20 -24 val_24 -24 val_24 -26 val_26 -26 val_26 -28 val_28 -30 val_30 -34 val_34 -42 val_42 -42 val_42 -44 val_44 -54 val_54 -58 val_58 -58 val_58 -64 val_64 -66 val_66 -70 val_70 -70 val_70 -70 val_70 -72 val_72 -72 val_72 -74 val_74 -76 val_76 -76 val_76 -78 val_78 -80 val_80 -82 val_82 -84 val_84 -84 val_84 -86 val_86 -90 val_90 -90 val_90 -90 val_90 -92 val_92 -96 val_96 -98 val_98 -98 val_98 -100 val_100 -100 val_100 -104 val_104 -104 val_104 -114 val_114 -116 val_116 -118 val_118 -118 val_118 -120 val_120 -120 val_120 -126 val_126 -128 val_128 -128 val_128 -128 val_128 -134 val_134 -134 val_134 -136 val_136 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -146 val_146 -146 val_146 -150 val_150 -152 val_152 -152 val_152 -156 val_156 -158 val_158 -160 val_160 -162 val_162 -164 val_164 -164 val_164 -166 val_166 -168 val_168 -170 val_170 -172 val_172 -172 val_172 -174 val_174 -174 val_174 -176 val_176 -176 val_176 -178 val_178 -180 val_180 -186 val_186 -190 val_190 -192 val_192 -194 val_194 -196 val_196 -200 val_200 -200 val_200 -202 val_202 -208 val_208 -208 val_208 -208 val_208 -214 val_214 -216 val_216 -216 val_216 -218 val_218 -222 val_222 -224 val_224 -224 val_224 -226 val_226 -228 val_228 -230 val_230 -230 val_230 -230 val_230 -230 val_230 -230 val_230 -238 val_238 -238 val_238 -242 val_242 -242 val_242 -244 val_244 -248 val_248 -252 val_252 -256 val_256 -256 val_256 -258 val_258 -260 val_260 -262 val_262 -266 val_266 -272 val_272 -272 val_272 -274 val_274 -278 val_278 -278 val_278 -280 val_280 -280 val_280 -282 val_282 -282 val_282 -284 val_284 -286 val_286 -288 val_288 -288 val_288 -292 val_292 -296 val_296 -298 val_298 -298 val_298 -298 val_298 -302 val_302 -306 val_306 -308 val_308 -310 val_310 -316 val_316 -316 val_316 -316 val_316 -318 val_318 -318 val_318 -318 val_318 -322 val_322 -322 val_322 -332 val_332 -336 val_336 -338 val_338 -342 val_342 -342 val_342 -344 val_344 -344 val_344 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -348 val_348 -356 val_356 -360 val_360 -362 val_362 -364 val_364 -366 val_366 -368 val_368 -374 val_374 -378 val_378 -382 val_382 -382 val_382 -384 val_384 -384 val_384 -384 val_384 -386 val_386 -392 val_392 -394 val_394 -396 val_396 -396 val_396 -396 val_396 -400 val_400 -402 val_402 -404 val_404 -404 val_404 -406 val_406 -406 val_406 -406 val_406 -406 val_406 -414 val_414 -414 val_414 -418 val_418 -424 val_424 -424 val_424 -430 val_430 -430 val_430 -430 val_430 -432 val_432 -436 val_436 -438 val_438 -438 val_438 -438 val_438 -444 val_444 -446 val_446 -448 val_448 -452 val_452 -454 val_454 -454 val_454 -454 val_454 -458 val_458 -458 val_458 -460 val_460 -462 val_462 -462 val_462 -466 val_466 -466 val_466 -466 val_466 -468 val_468 -468 val_468 -468 val_468 -468 val_468 -470 val_470 -472 val_472 -478 val_478 -478 val_478 -480 val_480 -480 val_480 -480 val_480 -482 val_482 -484 val_484 -490 val_490 -492 val_492 -492 val_492 -494 val_494 -496 val_496 -498 val_498 -498 val_498 -498 val_498
http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/bucket5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket5.q.out b/ql/src/test/results/clientpositive/bucket5.q.out deleted file mode 100644 index 30994a7..0000000 --- a/ql/src/test/results/clientpositive/bucket5.q.out +++ /dev/null @@ -1,610 +0,0 @@ -PREHOOK: query: -- Tests that when a multi insert inserts into a bucketed table and a table which is not bucketed --- the bucketed table is not merged and the table which is not bucketed is - -CREATE TABLE bucketed_table(key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@bucketed_table -POSTHOOK: query: -- Tests that when a multi insert inserts into a bucketed table and a table which is not bucketed --- the bucketed table is not merged and the table which is not bucketed is - -CREATE TABLE bucketed_table(key INT, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@bucketed_table -PREHOOK: query: CREATE TABLE unbucketed_table(key INT, value STRING) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@unbucketed_table -POSTHOOK: query: CREATE TABLE unbucketed_table(key INT, value STRING) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@unbucketed_table -PREHOOK: query: EXPLAIN EXTENDED -FROM src -INSERT OVERWRITE TABLE bucketed_table SELECT key, value -INSERT OVERWRITE TABLE unbucketed_table SELECT key, value cluster by key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED -FROM src -INSERT OVERWRITE TABLE bucketed_table SELECT key, value -INSERT OVERWRITE TABLE unbucketed_table SELECT key, value cluster by key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-10 depends on stages: Stage-4 , consists of Stage-7, Stage-6, Stage-8 - Stage-7 - Stage-1 depends on stages: Stage-7, Stage-6, Stage-9 - Stage-5 depends on stages: Stage-1 - Stage-6 - Stage-8 - Stage-9 depends on stages: Stage-8 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToInteger(_col0) (type: int) - null sort order: a - sort order: + - Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 0 - rawDataSize 0 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: UDFToInteger(VALUE._col0) (type: int), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.bucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketed_table - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - - Stage: Stage-0 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 - bucket_field_name key - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.bucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct bucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucketed_table - - Stage: Stage-3 - Stats-Aggr Operator -#### A masked pattern was here #### - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -mr-10004 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Truncated Path -> Alias: -#### A masked pattern was here #### - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: UDFToInteger(KEY.reducesinkkey0) (type: int), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 2 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - TotalFiles: 1 - GatherStats: true - MultiFileSpray: false - - Stage: Stage-10 - Conditional Operator - - Stage: Stage-7 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - - Stage: Stage-1 - Move Operator - tables: - replace: true -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - - Stage: Stage-5 - Stats-Aggr Operator -#### A masked pattern was here #### - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10005 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - name: default.unbucketed_table - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: -ext-10005 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.unbucketed_table - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct unbucketed_table { i32 key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.unbucketed_table - name: default.unbucketed_table - Truncated Path -> Alias: -#### A masked pattern was here #### - - Stage: Stage-9 - Move Operator - files: - hdfs directory: true -#### A masked pattern was here #### - -PREHOOK: query: FROM src -INSERT OVERWRITE TABLE bucketed_table SELECT key, value -INSERT OVERWRITE TABLE unbucketed_table SELECT key, value cluster by key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@bucketed_table -PREHOOK: Output: default@unbucketed_table -POSTHOOK: query: FROM src -INSERT OVERWRITE TABLE bucketed_table SELECT key, value -INSERT OVERWRITE TABLE unbucketed_table SELECT key, value cluster by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@bucketed_table -POSTHOOK: Output: default@unbucketed_table -POSTHOOK: Lineage: bucketed_table.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: bucketed_table.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: unbucketed_table.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: unbucketed_table.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: DESC FORMATTED bucketed_table -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@bucketed_table -POSTHOOK: query: DESC FORMATTED bucketed_table -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@bucketed_table -# col_name data_type comment - -key int -value string - -# Detailed Table Information -Database: default -#### A masked pattern was here #### -Retention: 0 -#### A masked pattern was here #### -Table Type: MANAGED_TABLE -Table Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - SORTBUCKETCOLSPREFIX TRUE - numFiles 2 - numRows 500 - rawDataSize 5312 - totalSize 5812 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: 2 -Bucket Columns: [key] -Sort Columns: [Order(col:key, order:1)] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 1 OUT OF 2) s LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 1 OUT OF 2) s LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -2 val_2 -4 val_4 -8 val_8 -10 val_10 -12 val_12 -12 val_12 -18 val_18 -PREHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 2 OUT OF 2) s LIMIT 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -POSTHOOK: query: SELECT * FROM bucketed_table TABLESAMPLE (BUCKET 2 OUT OF 2) s LIMIT 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -5 val_5 -5 val_5 -5 val_5 -9 val_9 -11 val_11 -15 val_15 -15 val_15 -17 val_17 -19 val_19 -27 val_27 -PREHOOK: query: -- Should be 2 (not merged) -SELECT COUNT(DISTINCT INPUT__FILE__NAME) FROM bucketed_table -PREHOOK: type: QUERY -PREHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -POSTHOOK: query: -- Should be 2 (not merged) -SELECT COUNT(DISTINCT INPUT__FILE__NAME) FROM bucketed_table -POSTHOOK: type: QUERY -POSTHOOK: Input: default@bucketed_table -#### A masked pattern was here #### -2 -PREHOOK: query: -- Should be 1 (merged) -SELECT COUNT(DISTINCT INPUT__FILE__NAME) FROM unbucketed_table -PREHOOK: type: QUERY -PREHOOK: Input: default@unbucketed_table -#### A masked pattern was here #### -POSTHOOK: query: -- Should be 1 (merged) -SELECT COUNT(DISTINCT INPUT__FILE__NAME) FROM unbucketed_table -POSTHOOK: type: QUERY -POSTHOOK: Input: default@unbucketed_table -#### A masked pattern was here #### -1 http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/bucket6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/bucket6.q.out b/ql/src/test/results/clientpositive/bucket6.q.out deleted file mode 100644 index c7f696f..0000000 --- a/ql/src/test/results/clientpositive/bucket6.q.out +++ /dev/null @@ -1,189 +0,0 @@ -PREHOOK: query: CREATE TABLE src_bucket(key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@src_bucket -POSTHOOK: query: CREATE TABLE src_bucket(key STRING, value STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@src_bucket -PREHOOK: query: explain -insert into table src_bucket select key,value from srcpart -PREHOOK: type: QUERY -POSTHOOK: query: explain -insert into table src_bucket select key,value from srcpart -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 116 Data size: 23248 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_bucket - - Stage: Stage-0 - Move Operator - tables: - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.src_bucket - - Stage: Stage-2 - Stats-Aggr Operator - -PREHOOK: query: insert into table src_bucket select key,value from srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -PREHOOK: Output: default@src_bucket -POSTHOOK: query: insert into table src_bucket select key,value from srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -POSTHOOK: Output: default@src_bucket -POSTHOOK: Lineage: src_bucket.key SIMPLE [(srcpart)srcpart.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: src_bucket.value SIMPLE [(srcpart)srcpart.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from src_bucket limit 100 -PREHOOK: type: QUERY -PREHOOK: Input: default@src_bucket -#### A masked pattern was here #### -POSTHOOK: query: select * from src_bucket limit 100 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src_bucket -#### A masked pattern was here #### -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -0 val_0 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -103 val_103 -105 val_105 -105 val_105 -105 val_105 -105 val_105 -11 val_11 -11 val_11 -11 val_11 -11 val_11 -114 val_114 -114 val_114 -114 val_114 -114 val_114 -116 val_116 -116 val_116 -116 val_116 -116 val_116 -118 val_118 -118 val_118 -118 val_118 -118 val_118 -118 val_118 -118 val_118 -118 val_118 -118 val_118 -125 val_125 -125 val_125 -125 val_125 -125 val_125 -125 val_125 -125 val_125 -125 val_125 -125 val_125 -129 val_129 -129 val_129 -129 val_129 -129 val_129 -129 val_129 -129 val_129 -129 val_129 -129 val_129 -134 val_134 -134 val_134 -134 val_134 -134 val_134 -134 val_134 -134 val_134 -134 val_134 -134 val_134 -136 val_136 -136 val_136 -136 val_136 -136 val_136 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -138 val_138 -143 val_143 -143 val_143 -143 val_143 -143 val_143 -145 val_145 -145 val_145 -145 val_145 -145 val_145 -149 val_149 -149 val_149 -149 val_149 -149 val_149
