PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@T1 PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1 PREHOOK: type: LOAD PREHOOK: Output: default@t1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1 POSTHOOK: type: LOAD POSTHOOK: Output: default@t1 PREHOOK: query: EXPLAIN SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: key type: string expr: val type: string expr: '0' type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col3 type: bigint outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube ORDER BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### POSTHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube ORDER BY key, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### NULL NULL 6 NULL 11 1 NULL 12 1 NULL 13 1 NULL 17 1 NULL 18 1 NULL 28 1 1 NULL 1 1 11 1 2 NULL 1 2 12 1 3 NULL 1 3 13 1 7 NULL 1 7 17 1 8 NULL 2 8 18 1 8 28 1 PREHOOK: query: EXPLAIN SELECT key, count(distinct val) FROM T1 GROUP BY key with cube PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT key, count(distinct val) FROM T1 GROUP BY key with cube POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL val)))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: count(DISTINCT val) bucketGroup: false keys: expr: key type: string expr: '0' type: string expr: val type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(DISTINCT KEY._col2:0._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string mode: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col2 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: SELECT key, count(distinct val) FROM T1 GROUP BY key with cube ORDER BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### POSTHOOK: query: SELECT key, count(distinct val) FROM T1 GROUP BY key with cube ORDER BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### NULL 6 1 1 2 1 3 1 7 1 8 2 PREHOOK: query: EXPLAIN SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: key type: string expr: val type: string expr: '0' type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: rand() type: double tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: partials outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: final outputColumnNames: _col0, _col1, _col2, _col3 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col3 type: bigint outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube ORDER BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### POSTHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val with cube ORDER BY key, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### NULL NULL 6 NULL 11 1 NULL 12 1 NULL 13 1 NULL 17 1 NULL 18 1 NULL 28 1 1 NULL 1 1 11 1 2 NULL 1 2 12 1 3 NULL 1 3 13 1 7 NULL 1 7 17 1 8 NULL 2 8 18 1 8 28 1 PREHOOK: query: EXPLAIN SELECT key, count(distinct val) FROM T1 GROUP BY key with cube PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT key, count(distinct val) FROM T1 GROUP BY key with cube POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONDI count (TOK_TABLE_OR_COL val)))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: count(DISTINCT val) bucketGroup: false keys: expr: key type: string expr: '0' type: string expr: val type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(DISTINCT KEY._col2:0._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string mode: partials outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string sort order: ++ Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col2 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string mode: final outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col2 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: SELECT key, count(distinct val) FROM T1 GROUP BY key with cube ORDER BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### POSTHOOK: query: SELECT key, count(distinct val) FROM T1 GROUP BY key with cube ORDER BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 #### A masked pattern was here #### NULL 6 1 1 2 1 3 1 7 1 8 2 PREHOOK: query: CREATE TABLE T2(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE T2(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@T2 PREHOOK: query: CREATE TABLE T3(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE T3(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@T3 PREHOOK: query: EXPLAIN FROM T1 INSERT OVERWRITE TABLE T2 SELECT key, val, count(1) group by key, val with cube INSERT OVERWRITE TABLE T3 SELECT key, val, sum(1) group by key, val with cube PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FROM T1 INSERT OVERWRITE TABLE T2 SELECT key, val, count(1) group by key, val with cube INSERT OVERWRITE TABLE T3 SELECT key, val, sum(1) group by key, val with cube POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME T2))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME T3))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION sum 1))) (TOK_CUBE_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val)))) STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 Stage-4 depends on stages: Stage-0 Stage-5 depends on stages: Stage-2 Stage-6 depends on stages: Stage-5 Stage-1 depends on stages: Stage-6 Stage-7 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: count(1) bucketGroup: false keys: expr: key type: string expr: val type: string expr: '0' type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: rand() type: double tag: -1 value expressions: expr: _col3 type: bigint Select Operator expressions: expr: key type: string expr: val type: string outputColumnNames: key, val Group By Operator aggregations: expr: sum(1) bucketGroup: false keys: expr: key type: string expr: val type: string expr: '0' type: string mode: hash outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: partials outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: final outputColumnNames: _col0, _col1, _col2, _col3 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col3 type: bigint outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: UDFToInteger(_col2) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 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.t2 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.t2 Stage: Stage-4 Stats-Aggr Operator Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: rand() type: double tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: sum(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: partials outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-6 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 type: string sort order: +++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 type: string tag: -1 value expressions: expr: _col3 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: sum(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string expr: KEY._col1 type: string expr: KEY._col2 type: string mode: final outputColumnNames: _col0, _col1, _col2, _col3 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col3 type: bigint outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: UDFToInteger(_col2) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 2 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.t3 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.t3 Stage: Stage-7 Stats-Aggr Operator PREHOOK: query: FROM T1 INSERT OVERWRITE TABLE T2 SELECT key, val, count(1) group by key, val with cube INSERT OVERWRITE TABLE T3 SELECT key, val, sum(1) group by key, val with cube PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Output: default@t2 PREHOOK: Output: default@t3 POSTHOOK: query: FROM T1 INSERT OVERWRITE TABLE T2 SELECT key, val, count(1) group by key, val with cube INSERT OVERWRITE TABLE T3 SELECT key, val, sum(1) group by key, val with cube POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@t2 POSTHOOK: Output: default@t3 POSTHOOK: Lineage: t2.key1 SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t2.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: t2.val EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: t3.key1 SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t3.key2 SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: t3.val EXPRESSION [(t1)t1.null, ]