PREHOOK: query: CREATE TABLE T1(key STRING, val STRING) CLUSTERED BY (key, val) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING) CLUSTERED BY (key, val) SORTED BY (key) INTO 2 BUCKETS 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: -- perform an insert to make sure there are 2 files INSERT OVERWRITE TABLE T1 select key, val from T1 PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Output: default@t1 POSTHOOK: query: -- perform an insert to make sure there are 2 files INSERT OVERWRITE TABLE T1 select key, val from T1 POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@t1 POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: CREATE TABLE outputTbl1(key STRING, cnt INT) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE outputTbl1(key STRING, cnt INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@outputTbl1 POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: -- The plan should not be converted to a map-side group by. -- However, there should no hash-based aggregation on the map-side EXPLAIN INSERT OVERWRITE TABLE outputTbl1 SELECT key, count(1) FROM T1 GROUP BY key PREHOOK: type: QUERY POSTHOOK: query: -- The plan should not be converted to a map-side group by. -- However, there should no hash-based aggregation on the map-side EXPLAIN INSERT OVERWRITE TABLE outputTbl1 SELECT key, count(1) FROM T1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) 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: t1 TableScan alias: t1 Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) bucketGroup: true keys: expr: key type: string mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col1 type: bigint Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) bucketGroup: false keys: expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int outputColumnNames: _col0, _col1 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.outputtbl1 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.outputtbl1 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE outputTbl1 SELECT key, count(1) FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Output: default@outputtbl1 POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl1 SELECT key, count(1) FROM T1 GROUP BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl1 POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl1 ORDER BY key PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM outputTbl1 ORDER BY key POSTHOOK: type: QUERY POSTHOOK: Input: default@outputtbl1 #### A masked pattern was here #### POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] 1 1 2 1 3 1 7 1 8 2 PREHOOK: query: CREATE TABLE outputTbl2(key STRING, val STRING, cnt INT) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE outputTbl2(key STRING, val STRING, cnt INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@outputTbl2 POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: -- The plan should not be converted to a map-side group by. -- Hash-based aggregations should be performed on the map-side EXPLAIN INSERT OVERWRITE TABLE outputTbl2 SELECT key, val, count(1) FROM T1 GROUP BY key, val PREHOOK: type: QUERY POSTHOOK: query: -- The plan should not be converted to a map-side group by. -- Hash-based aggregations should be performed on the map-side EXPLAIN INSERT OVERWRITE TABLE outputTbl2 SELECT key, val, count(1) FROM T1 GROUP BY key, val POSTHOOK: type: QUERY POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl2))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL val)))) 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: 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 mode: hash outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: expr: _col0 type: string expr: _col1 type: string sort order: ++ Map-reduce partition columns: expr: _col0 type: string expr: _col1 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: mergepartial outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col2 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.outputtbl2 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.outputtbl2 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE outputTbl2 SELECT key, val, count(1) FROM T1 GROUP BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Output: default@outputtbl2 POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl2 SELECT key, val, count(1) FROM T1 GROUP BY key, val POSTHOOK: type: QUERY POSTHOOK: Input: default@t1 POSTHOOK: Output: default@outputtbl2 POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl2.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] PREHOOK: query: SELECT * FROM outputTbl2 ORDER BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl2 #### A masked pattern was here #### POSTHOOK: query: SELECT * FROM outputTbl2 ORDER BY key, val POSTHOOK: type: QUERY POSTHOOK: Input: default@outputtbl2 #### A masked pattern was here #### POSTHOOK: Lineage: outputtbl1.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.cnt EXPRESSION [(t1)t1.null, ] POSTHOOK: Lineage: outputtbl2.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] POSTHOOK: Lineage: t1.key SIMPLE [(t1)t1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: t1.val SIMPLE [(t1)t1.FieldSchema(name:val, type:string, comment:null), ] 1 11 1 2 12 1 3 13 1 7 17 1 8 18 1 8 28 1