PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE DEST1(key ARRAY, value BIGINT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@DEST1 POSTHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE DEST1(key ARRAY, value BIGINT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@DEST1 PREHOOK: query: CREATE TABLE DEST2(key MAP, value BIGINT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@DEST2 POSTHOOK: query: CREATE TABLE DEST2(key MAP, value BIGINT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@DEST2 PREHOOK: query: EXPLAIN FROM SRC INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM SRC INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 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 Spark Edges: Reducer 2 <- Map 6 (GROUP, 2) Reducer 4 <- Map 7 (GROUP, 2) Reducer 3 <- Reducer 2 (GROUP, 1) Reducer 5 <- Reducer 4 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 6 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: array(key) (type: array) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: array) sort order: + Map-reduce partition columns: _col0 (type: array) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Map 7 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: map(key:value) (type: map) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: map) sort order: + Map-reduce partition columns: _col0 (type: map) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: array) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: array), _col1 (type: bigint) Reducer 3 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: array), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 10 Data size: 100 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 Reducer 4 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: map) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: map), _col1 (type: bigint) Reducer 5 Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: map), VALUE._col1 (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 10 Data size: 100 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.dest2 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-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.dest2 Stage: Stage-4 Stats-Aggr Operator PREHOOK: query: FROM SRC INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@dest1 PREHOOK: Output: default@dest2 POSTHOOK: query: FROM SRC INSERT OVERWRITE TABLE DEST1 SELECT ARRAY(SRC.key), COUNT(1) GROUP BY ARRAY(SRC.key) limit 10 INSERT OVERWRITE TABLE DEST2 SELECT MAP(SRC.key, SRC.value), COUNT(1) GROUP BY MAP(SRC.key, SRC.value) limit 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest1.value EXPRESSION [(src)src.null, ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), (src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.value EXPRESSION [(src)src.null, ] 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 #### ["166"] 1 ["169"] 4 ["238"] 2 ["258"] 1 ["306"] 1 ["384"] 3 ["392"] 1 ["435"] 1 ["455"] 1 ["468"] 4 PREHOOK: query: SELECT DEST2.* FROM DEST2 PREHOOK: type: QUERY PREHOOK: Input: default@dest2 #### A masked pattern was here #### POSTHOOK: query: SELECT DEST2.* FROM DEST2 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest2 #### A masked pattern was here #### {"120":"val_120"} 2 {"129":"val_129"} 2 {"160":"val_160"} 1 {"26":"val_26"} 2 {"27":"val_27"} 1 {"288":"val_288"} 2 {"298":"val_298"} 3 {"30":"val_30"} 1 {"311":"val_311"} 3 {"74":"val_74"} 1