PREHOOK: query: -- This is to test the union->selectstar->filesink optimization -- Union of 2 subqueries is performed (all of which are mapred queries) -- followed by select star and a file sink in 2 output tables. -- The optimiaztion does not take affect since it is a multi-table insert. -- It does not matter, whether the output is merged or not. In this case, -- merging is turned off create table inputTbl1(key string, val string) stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: -- This is to test the union->selectstar->filesink optimization -- Union of 2 subqueries is performed (all of which are mapred queries) -- followed by select star and a file sink in 2 output tables. -- The optimiaztion does not take affect since it is a multi-table insert. -- It does not matter, whether the output is merged or not. In this case, -- merging is turned off create table inputTbl1(key string, val string) stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@inputTbl1 PREHOOK: query: create table outputTbl1(key string, values bigint) stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: create table outputTbl1(key string, values bigint) stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@outputTbl1 PREHOOK: query: create table outputTbl2(key string, values bigint) stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: create table outputTbl2(key string, values bigint) stored as textfile POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@outputTbl2 PREHOOK: query: load data local inpath '../data/files/T1.txt' into table inputTbl1 PREHOOK: type: LOAD PREHOOK: Output: default@inputtbl1 POSTHOOK: query: load data local inpath '../data/files/T1.txt' into table inputTbl1 POSTHOOK: type: LOAD POSTHOOK: Output: default@inputtbl1 PREHOOK: query: explain FROM ( SELECT key, count(1) as values from inputTbl1 group by key UNION ALL SELECT key, count(1) as values from inputTbl1 group by key ) a insert overwrite table outputTbl1 select * insert overwrite table outputTbl2 select * PREHOOK: type: QUERY POSTHOOK: query: explain FROM ( SELECT key, count(1) as values from inputTbl1 group by key UNION ALL SELECT key, count(1) as values from inputTbl1 group by key ) a insert overwrite table outputTbl1 select * insert overwrite table outputTbl2 select * POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME inputTbl1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1) values)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME inputTbl1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1) values)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))) a)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl2))) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-2 is a root stage Stage-3 depends on stages: Stage-2, Stage-4 Stage-0 depends on stages: Stage-3 Stage-1 depends on stages: Stage-3 Stage-4 is a root stage STAGE PLANS: Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: null-subquery2:a-subquery2:inputtbl1 TableScan alias: inputtbl1 Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) bucketGroup: false 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 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 #### TableScan Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint 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 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 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.outputtbl2 #### A masked pattern was here #### TableScan Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint 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 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 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.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.outputtbl1 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.outputtbl2 Stage: Stage-4 Map Reduce Alias -> Map Operator Tree: null-subquery1:a-subquery1:inputtbl1 TableScan alias: inputtbl1 Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) bucketGroup: false 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 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat PREHOOK: query: FROM ( SELECT key, count(1) as values from inputTbl1 group by key UNION ALL SELECT key, count(1) as values from inputTbl1 group by key ) a insert overwrite table outputTbl1 select * insert overwrite table outputTbl2 select * PREHOOK: type: QUERY PREHOOK: Input: default@inputtbl1 PREHOOK: Output: default@outputtbl1 PREHOOK: Output: default@outputtbl2 POSTHOOK: query: FROM ( SELECT key, count(1) as values from inputTbl1 group by key UNION ALL SELECT key, count(1) as values from inputTbl1 group by key ) a insert overwrite table outputTbl1 select * insert overwrite table outputTbl2 select * POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 POSTHOOK: Output: default@outputtbl2 POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] POSTHOOK: Lineage: outputtbl2.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] PREHOOK: query: select * from outputTbl1 order by key, values PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl1 #### A masked pattern was here #### POSTHOOK: query: select * from outputTbl1 order by key, values POSTHOOK: type: QUERY POSTHOOK: Input: default@outputtbl1 #### A masked pattern was here #### POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] POSTHOOK: Lineage: outputtbl2.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] 1 1 1 1 2 1 2 1 3 1 3 1 7 1 7 1 8 2 8 2 PREHOOK: query: select * from outputTbl2 order by key, values PREHOOK: type: QUERY PREHOOK: Input: default@outputtbl2 #### A masked pattern was here #### POSTHOOK: query: select * from outputTbl2 order by key, values POSTHOOK: type: QUERY POSTHOOK: Input: default@outputtbl2 #### A masked pattern was here #### POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] POSTHOOK: Lineage: outputtbl2.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl2.values EXPRESSION [(inputtbl1)inputtbl1.null, (inputtbl1)inputtbl1.null, ] 1 1 1 1 2 1 2 1 3 1 3 1 7 1 7 1 8 2 8 2