PREHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest1(key STRING, c1 INT, c2 STRING, c3 INT, c4 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest1 PREHOOK: query: EXPLAIN EXTENDED FROM srcpart src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) WHERE src.ds = '2008-04-08' GROUP BY substr(src.key,1,1) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED FROM srcpart src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) WHERE src.ds = '2008-04-08' GROUP BY substr(src.key,1,1) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart) src)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTION concat (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1) (TOK_FUNCTION sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5)))) (TOK_SELEXPR (TOK_FUNCTIONDI sum (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) value) 5))) (TOK_SELEXPR (TOK_FUNCTIONDI count (. (TOK_TABLE_OR_COL src) value)))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL src) ds) '2008-04-08')) (TOK_GROUPBY (TOK_FUNCTION substr (. (TOK_TABLE_OR_COL src) key) 1 1)))) 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 Alias -> Map Operator Tree: src TableScan alias: src GatherStats: false Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: key, value Reduce Output Operator key expressions: expr: substr(key, 1, 1) type: string expr: substr(value, 5) type: string expr: value type: string sort order: +++ Map-reduce partition columns: expr: substr(key, 1, 1) type: string tag: -1 Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 11 properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.srcpart numFiles 1 numRows 0 partition_columns ds/hr rawDataSize 0 serialization.ddl struct srcpart { 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.types string:string #### A masked pattern was here #### name default.srcpart numFiles 4 numPartitions 4 numRows 0 partition_columns ds/hr rawDataSize 0 serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 23248 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart #### A masked pattern was here #### Partition base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 12 properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.srcpart numFiles 1 numRows 0 partition_columns ds/hr rawDataSize 0 serialization.ddl struct srcpart { 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.types string:string #### A masked pattern was here #### name default.srcpart numFiles 4 numPartitions 4 numRows 0 partition_columns ds/hr rawDataSize 0 serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 23248 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart Truncated Path -> Alias: /srcpart/ds=2008-04-08/hr=11 [src] /srcpart/ds=2008-04-08/hr=12 [src] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: expr: count(DISTINCT KEY._col1:0._col0) expr: sum(KEY._col1:1._col0) expr: sum(DISTINCT KEY._col1:1._col0) expr: count(DISTINCT KEY._col1:2._col0) bucketGroup: false keys: expr: KEY._col0 type: string mode: complete outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int expr: concat(_col0, _col2) type: string expr: UDFToInteger(_col3) type: int expr: UDFToInteger(_col4) type: int outputColumnNames: _col0, _col1, _col2, _col3, _col4 File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,c1,c2,c3,c4 columns.types string:int:string:int:int #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} 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.dest1 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: bucket_count -1 columns key,c1,c2,c3,c4 columns.types string:int:string:int:int #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { string key, i32 c1, string c2, i32 c3, i32 c4} 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.dest1 #### A masked pattern was here #### Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### PREHOOK: query: FROM srcpart src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) WHERE src.ds = '2008-04-08' GROUP BY substr(src.key,1,1) 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: Output: default@dest1 POSTHOOK: query: FROM srcpart src INSERT OVERWRITE TABLE dest1 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))), sum(DISTINCT substr(src.value, 5)), count(DISTINCT src.value) WHERE src.ds = '2008-04-08' GROUP BY substr(src.key,1,1) 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: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 #### A masked pattern was here #### POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### POSTHOOK: Lineage: dest1.c1 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), (srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(srcpart)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 EXPRESSION [(srcpart)src.null, ] POSTHOOK: Lineage: dest1.key EXPRESSION [(srcpart)src.FieldSchema(name:key, type:string, comment:default), ] 0 1 00.0 0 1 1 71 132828.0 10044 71 2 69 251142.0 15780 69 3 62 364008.0 20119 62 4 74 4105526.0 30965 74 5 6 5794.0 278 6 6 5 6796.0 331 5 7 6 71470.0 447 6 8 8 81524.0 595 8 9 7 92094.0 577 7