PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest1(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest1 POSTHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest1(c1 INT, c2 STRING, c3 INT, c4 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 PREHOOK: query: EXPLAIN FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AND c.c1 IS NOT NULL PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AND c.c1 IS NOT NULL 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: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) TableScan alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 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: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: Left Outer Join0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is null (type: boolean) Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(null) (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 30 Data size: 321 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.dest1 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.dest1 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AND c.c1 IS NOT NULL PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest1 POSTHOOK: query: FROM ( FROM ( FROM src src1 SELECT src1.key AS c1, src1.value AS c2 WHERE src1.key > 10 and src1.key < 20 ) a LEFT OUTER JOIN ( FROM src src2 SELECT src2.key AS c3, src2.value AS c4 WHERE src2.key > 15 and src2.key < 25 ) b ON (a.c1 = b.c3) SELECT a.c1 AS c1, a.c2 AS c2, b.c3 AS c3, b.c4 AS c4 ) c INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4 where c.c3 IS NULL AND c.c1 IS NOT NULL POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.c1 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c2 SIMPLE [(src)src1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c3 EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.c4 SIMPLE [(src)src1.FieldSchema(name:value, 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 #### 11 val_11 NULL NULL 12 val_12 NULL NULL 12 val_12 NULL NULL 15 val_15 NULL NULL 15 val_15 NULL NULL