PREHOOK: query: -- This is to test the union->remove->filesink optimization -- Union of 3 subqueries is performed (all of which are map-only queries) -- followed by select star and a file sink. -- There is no need for any optimization, since the whole query can be processed in -- a single map-only job -- It does not matter, whether the output is merged or not. In this case, merging is turned -- off -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) -- Since this test creates sub-directories for the output table outputTbl1, it might be easier -- to run the test only on hadoop 23 create table inputTbl1(key string, val string) stored as textfile PREHOOK: type: CREATETABLE POSTHOOK: query: -- This is to test the union->remove->filesink optimization -- Union of 3 subqueries is performed (all of which are map-only queries) -- followed by select star and a file sink. -- There is no need for any optimization, since the whole query can be processed in -- a single map-only job -- It does not matter, whether the output is merged or not. In this case, merging is turned -- off -- INCLUDE_HADOOP_MAJOR_VERSIONS(0.23) -- Since this test creates sub-directories for the output table outputTbl1, it might be easier -- to run the test only on hadoop 23 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: 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 insert overwrite table outputTbl1 SELECT * FROM ( SELECT key, 1 as values from inputTbl1 UNION ALL SELECT key, 2 as values from inputTbl1 UNION ALL SELECT key, 3 as values from inputTbl1 ) a PREHOOK: type: QUERY POSTHOOK: query: explain insert overwrite table outputTbl1 SELECT * FROM ( SELECT key, 1 as values from inputTbl1 UNION ALL SELECT key, 2 as values from inputTbl1 UNION ALL SELECT key, 3 as values from inputTbl1 ) a POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (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 1 values)))) (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 2 values))))) (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 3 values))))) a)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME outputTbl1))) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery1-subquery1:a-subquery1-subquery1:inputtbl1 TableScan alias: inputtbl1 Select Operator expressions: expr: key type: string expr: 1 type: int outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: int outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: UDFToLong(_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 null-subquery1-subquery2:a-subquery1-subquery2:inputtbl1 TableScan alias: inputtbl1 Select Operator expressions: expr: key type: string expr: 2 type: int outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: int outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: UDFToLong(_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 null-subquery2:a-subquery2:inputtbl1 TableScan alias: inputtbl1 Select Operator expressions: expr: key type: string expr: 3 type: int outputColumnNames: _col0, _col1 Union Select Operator expressions: expr: _col0 type: string expr: _col1 type: int outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: UDFToLong(_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 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 PREHOOK: query: insert overwrite table outputTbl1 SELECT * FROM ( SELECT key, 1 as values from inputTbl1 UNION ALL SELECT key, 2 as values from inputTbl1 UNION ALL SELECT key, 3 as values from inputTbl1 ) a PREHOOK: type: QUERY PREHOOK: Input: default@inputtbl1 PREHOOK: Output: default@outputtbl1 POSTHOOK: query: insert overwrite table outputTbl1 SELECT * FROM ( SELECT key, 1 as values from inputTbl1 UNION ALL SELECT key, 2 as values from inputTbl1 UNION ALL SELECT key, 3 as values from inputTbl1 ) a POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE POSTHOOK: query: desc formatted outputTbl1 POSTHOOK: type: DESCTABLE POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [] # col_name data_type comment key string None values bigint None # Detailed Table Information Database: default #### A masked pattern was here #### Protect Mode: None Retention: 0 #### A masked pattern was here #### Table Type: MANAGED_TABLE Table Parameters: #### A masked pattern was here #### # Storage Information SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe InputFormat: org.apache.hadoop.mapred.TextInputFormat OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Compressed: No Num Buckets: -1 Bucket Columns: [] Sort Columns: [] Storage Desc Params: serialization.format 1 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), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: outputtbl1.values EXPRESSION [] 1 1 1 2 1 3 2 1 2 2 2 3 3 1 3 2 3 3 7 1 7 2 7 3 8 1 8 1 8 2 8 2 8 3 8 3