PREHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_g2 POSTHOOK: query: CREATE TABLE dest_g2(key STRING, c1 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_g2 PREHOOK: query: CREATE TABLE dest_g3(key STRING, c1 INT, c2 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_g3 POSTHOOK: query: CREATE TABLE dest_g3(key STRING, c1 INT, c2 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_g3 PREHOOK: query: -- SORT_QUERY_RESULTS EXPLAIN FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT src.key) WHERE substr(src.key,1,1) >= 5 GROUP BY substr(src.key,1,1) INSERT OVERWRITE TABLE dest_g3 SELECT substr(src.key,1,1), count(DISTINCT src.key), count(src.value) WHERE substr(src.key,1,1) < 5 GROUP BY substr(src.key,1,1) PREHOOK: type: QUERY POSTHOOK: query: -- SORT_QUERY_RESULTS EXPLAIN FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT src.key) WHERE substr(src.key,1,1) >= 5 GROUP BY substr(src.key,1,1) INSERT OVERWRITE TABLE dest_g3 SELECT substr(src.key,1,1), count(DISTINCT src.key), count(src.value) WHERE substr(src.key,1,1) < 5 GROUP BY substr(src.key,1,1) 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-1 depends on stages: Stage-2 Stage-4 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((substr(key, 1, 1) >= 5) or (substr(key, 1, 1) < 5)) (type: boolean) Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: substr(key, 1, 1) (type: string), key (type: string) sort order: ++ Map-reduce partition columns: substr(key, 1, 1) (type: string) Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE value expressions: value (type: string) Reduce Operator Tree: Forward Statistics: Num rows: 332 Data size: 3527 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (KEY._col0 >= 5) (type: boolean) Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 55 Data size: 584 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.dest_g2 Filter Operator predicate: (KEY._col0 < 5) (type: boolean) Statistics: Num rows: 110 Data size: 1168 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(DISTINCT KEY._col1:0._col0), count(VALUE._col0) keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 55 Data size: 584 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.dest_g3 Stage: Stage-0 Move Operator tables: replace: true 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.dest_g2 Stage: Stage-3 Stats-Aggr Operator Stage: Stage-1 Move Operator tables: replace: true 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.dest_g3 Stage: Stage-4 Stats-Aggr Operator PREHOOK: query: FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT src.key) WHERE substr(src.key,1,1) >= 5 GROUP BY substr(src.key,1,1) INSERT OVERWRITE TABLE dest_g3 SELECT substr(src.key,1,1), count(DISTINCT src.key), count(src.value) WHERE substr(src.key,1,1) < 5 GROUP BY substr(src.key,1,1) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest_g2 PREHOOK: Output: default@dest_g3 POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT src.key) WHERE substr(src.key,1,1) >= 5 GROUP BY substr(src.key,1,1) INSERT OVERWRITE TABLE dest_g3 SELECT substr(src.key,1,1), count(DISTINCT src.key), count(src.value) WHERE substr(src.key,1,1) < 5 GROUP BY substr(src.key,1,1) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest_g2 POSTHOOK: Output: default@dest_g3 POSTHOOK: Lineage: dest_g2.c1 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest_g2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_g3.c1 EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest_g3.c2 EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_g3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: SELECT * FROM dest_g2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_g2 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM dest_g2 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_g2 #### A masked pattern was here #### 5 6 6 5 7 6 8 8 9 7 PREHOOK: query: SELECT * FROM dest_g3 PREHOOK: type: QUERY PREHOOK: Input: default@dest_g3 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM dest_g3 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_g3 #### A masked pattern was here #### 0 1 3 1 71 115 2 69 111 3 62 99 4 74 124 PREHOOK: query: DROP TABLE dest_g2 PREHOOK: type: DROPTABLE PREHOOK: Input: default@dest_g2 PREHOOK: Output: default@dest_g2 POSTHOOK: query: DROP TABLE dest_g2 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@dest_g2 POSTHOOK: Output: default@dest_g2 PREHOOK: query: DROP TABLE dest_g3 PREHOOK: type: DROPTABLE PREHOOK: Input: default@dest_g3 PREHOOK: Output: default@dest_g3 POSTHOOK: query: DROP TABLE dest_g3 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@dest_g3 POSTHOOK: Output: default@dest_g3