PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@filter_join_breaktask POSTHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@filter_join_breaktask PREHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') SELECT key, value from src1 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 POSTHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') SELECT key, value from src1 POSTHOOK: type: QUERY POSTHOOK: Input: default@src1 POSTHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).key EXPRESSION [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: EXPLAIN EXTENDED SELECT f.key, g.value FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED SELECT f.key, g.value FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_JOIN TOK_TABREF TOK_TABNAME filter_join_breaktask f TOK_TABREF TOK_TABNAME filter_join_breaktask m AND AND AND = . TOK_TABLE_OR_COL f key . TOK_TABLE_OR_COL m key = . TOK_TABLE_OR_COL f ds '2008-04-08' = . TOK_TABLE_OR_COL m ds '2008-04-08' TOK_FUNCTION TOK_ISNOTNULL . TOK_TABLE_OR_COL f key TOK_TABREF TOK_TABNAME filter_join_breaktask g AND AND AND AND = . TOK_TABLE_OR_COL g value . TOK_TABLE_OR_COL m value = . TOK_TABLE_OR_COL g ds '2008-04-08' = . TOK_TABLE_OR_COL m ds '2008-04-08' TOK_FUNCTION TOK_ISNOTNULL . TOK_TABLE_OR_COL m value != . TOK_TABLE_OR_COL m value '' TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_SELEXPR . TOK_TABLE_OR_COL f key TOK_SELEXPR . TOK_TABLE_OR_COL g value STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 depends on stages: Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: f Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false TableScan alias: m Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: ((key is not null and value is not null) and (value <> '')) (type: boolean) Statistics: Num rows: 7 Data size: 59 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: key (type: int) sort order: + Map-reduce partition columns: key (type: int) Statistics: Num rows: 7 Data size: 59 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: value (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: ds=2008-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.filter_join_breaktask numFiles 1 numRows 25 partition_columns ds partition_columns.types string rawDataSize 211 serialization.ddl struct filter_join_breaktask { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 236 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.filter_join_breaktask partition_columns ds partition_columns.types string serialization.ddl struct filter_join_breaktask { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: /filter_join_breaktask/ds=2008-04-08 [f, m] Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col7 Statistics: Num rows: 14 Data size: 119 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,_col7 columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-2 Map Reduce Map Operator Tree: TableScan GatherStats: false Reduce Output Operator key expressions: _col7 (type: string) sort order: + Map-reduce partition columns: _col7 (type: string) Statistics: Num rows: 14 Data size: 119 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col0 (type: int) auto parallelism: false TableScan alias: g Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: ((value <> '') and value is not null) (type: boolean) Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: value (type: string) sort order: + Map-reduce partition columns: value (type: string) Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10003 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col7 columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col7 columns.types int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition base file name: ds=2008-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.filter_join_breaktask numFiles 1 numRows 25 partition_columns ds partition_columns.types string rawDataSize 211 serialization.ddl struct filter_join_breaktask { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 236 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.filter_join_breaktask partition_columns ds partition_columns.types string serialization.ddl struct filter_join_breaktask { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.filter_join_breaktask name: default.filter_join_breaktask Truncated Path -> Alias: /filter_join_breaktask/ds=2008-04-08 [g] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col7 (type: string) 1 value (type: string) outputColumnNames: _col0, _col13 Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col13 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types int:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: ListSink PREHOOK: query: SELECT f.key, g.value FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') PREHOOK: type: QUERY PREHOOK: Input: default@filter_join_breaktask PREHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 #### A masked pattern was here #### POSTHOOK: query: SELECT f.key, g.value FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') POSTHOOK: type: QUERY POSTHOOK: Input: default@filter_join_breaktask POSTHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 #### A masked pattern was here #### 146 val_146 150 val_150 213 val_213 238 val_238 255 val_255 273 val_273 278 val_278 311 val_311 401 val_401 406 val_406 66 val_66 98 val_98