Return-Path: X-Original-To: apmail-hive-commits-archive@www.apache.org Delivered-To: apmail-hive-commits-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 5571E10B9A for ; Mon, 18 Nov 2013 19:30:41 +0000 (UTC) Received: (qmail 58990 invoked by uid 500); 18 Nov 2013 19:30:41 -0000 Delivered-To: apmail-hive-commits-archive@hive.apache.org Received: (qmail 58957 invoked by uid 500); 18 Nov 2013 19:30:41 -0000 Mailing-List: contact commits-help@hive.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hive-dev@hive.apache.org Delivered-To: mailing list commits@hive.apache.org Received: (qmail 58949 invoked by uid 99); 18 Nov 2013 19:30:41 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 18 Nov 2013 19:30:41 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=5.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.4] (HELO eris.apache.org) (140.211.11.4) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 18 Nov 2013 19:30:21 +0000 Received: from eris.apache.org (localhost [127.0.0.1]) by eris.apache.org (Postfix) with ESMTP id B48B02388BFF; Mon, 18 Nov 2013 19:29:35 +0000 (UTC) Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Subject: svn commit: r1543120 [9/16] - in /hive/trunk: common/src/java/org/apache/hadoop/hive/conf/ data/files/ ql/src/java/org/apache/hadoop/hive/ql/ ql/src/java/org/apache/hadoop/hive/ql/exec/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ ql/src/java/org/a... Date: Mon, 18 Nov 2013 19:29:27 -0000 To: commits@hive.apache.org From: rhbutani@apache.org X-Mailer: svnmailer-1.0.9 Message-Id: <20131118192935.B48B02388BFF@eris.apache.org> X-Virus-Checked: Checked by ClamAV on apache.org Added: hive/trunk/ql/src/test/results/clientpositive/annotate_stats_table.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/annotate_stats_table.q.out?rev=1543120&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/annotate_stats_table.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/annotate_stats_table.q.out Mon Nov 18 19:29:24 2013 @@ -0,0 +1,698 @@ +PREHOOK: query: create table if not exists emp_staging ( + lastname string, + deptid int +) row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table if not exists emp_staging ( + lastname string, + deptid int +) row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@emp_staging +PREHOOK: query: create table if not exists emp_orc like emp_staging +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table if not exists emp_orc like emp_staging +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@emp_orc +PREHOOK: query: alter table emp_orc set fileformat orc +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: default@emp_orc +PREHOOK: Output: default@emp_orc +POSTHOOK: query: alter table emp_orc set fileformat orc +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: default@emp_orc +POSTHOOK: Output: default@emp_orc +PREHOOK: query: -- basicStatState: NONE colStatState: NONE +explain extended select * from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: NONE colStatState: NONE +explain extended select * from emp_orc +POSTHOOK: type: QUERY +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: emp_orc + Statistics: + numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 0 dataSize: 0 basicStatsState: NONE colStatsState: NONE + ListSink + + +PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/emp.txt' OVERWRITE INTO TABLE emp_staging +PREHOOK: type: LOAD +PREHOOK: Output: default@emp_staging +POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/emp.txt' OVERWRITE INTO TABLE emp_staging +POSTHOOK: type: LOAD +POSTHOOK: Output: default@emp_staging +PREHOOK: query: insert overwrite table emp_orc select * from emp_staging +PREHOOK: type: QUERY +PREHOOK: Input: default@emp_staging +PREHOOK: Output: default@emp_orc +POSTHOOK: query: insert overwrite table emp_orc select * from emp_staging +POSTHOOK: type: QUERY +POSTHOOK: Input: default@emp_staging +POSTHOOK: Output: default@emp_orc +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +PREHOOK: query: -- stats are disabled. basic stats will report the file size but not raw data size. so initial statistics will be PARTIAL + +-- basicStatState: PARTIAL colStatState: NONE +explain extended select * from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- stats are disabled. basic stats will report the file size but not raw data size. so initial statistics will be PARTIAL + +-- basicStatState: PARTIAL colStatState: NONE +explain extended select * from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: emp_orc + Statistics: + numRows: 0 dataSize: 349 basicStatsState: PARTIAL colStatsState: NONE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 0 dataSize: 349 basicStatsState: PARTIAL colStatsState: NONE + ListSink + + +PREHOOK: query: -- table level analyze statistics +analyze table emp_orc compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@emp_orc +PREHOOK: Output: default@emp_orc +POSTHOOK: query: -- table level analyze statistics +analyze table emp_orc compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@emp_orc +POSTHOOK: Output: default@emp_orc +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +PREHOOK: query: -- basicStatState: COMPLETE colStatState: NONE +explain extended select * from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: NONE +explain extended select * from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: NONE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: NONE + ListSink + + +PREHOOK: query: -- column level partial statistics +analyze table emp_orc compute statistics for columns deptid +PREHOOK: type: QUERY +PREHOOK: Input: default@emp_orc +#### A masked pattern was here #### +POSTHOOK: query: -- column level partial statistics +analyze table emp_orc compute statistics for columns deptid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@emp_orc +#### A masked pattern was here #### +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +PREHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select * from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: PARTIAL +explain extended select * from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: PARTIAL + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: PARTIAL + ListSink + + +PREHOOK: query: -- all selected columns have statistics +-- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select deptid from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- all selected columns have statistics +-- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select deptid from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL deptid))))) + +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: + emp_orc + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: deptid + type: int + outputColumnNames: _col0 + Statistics: + numRows: 6 dataSize: 20 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 6 dataSize: 20 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: emp_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.emp_orc + name: default.emp_orc + Truncated Path -> Alias: + /emp_orc [emp_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- column level complete statistics +analyze table emp_orc compute statistics for columns lastname,deptid +PREHOOK: type: QUERY +PREHOOK: Input: default@emp_orc +#### A masked pattern was here #### +POSTHOOK: query: -- column level complete statistics +analyze table emp_orc compute statistics for columns lastname,deptid +POSTHOOK: type: QUERY +POSTHOOK: Input: default@emp_orc +#### A masked pattern was here #### +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +PREHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select * from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select * from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + ListSink + + +PREHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select lastname from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select lastname from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL lastname))))) + +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: + emp_orc + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + outputColumnNames: _col0 + Statistics: + numRows: 6 dataSize: 546 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 6 dataSize: 546 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: emp_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.emp_orc + name: default.emp_orc + Truncated Path -> Alias: + /emp_orc [emp_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select deptid from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select deptid from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL deptid))))) + +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: + emp_orc + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: deptid + type: int + outputColumnNames: _col0 + Statistics: + numRows: 6 dataSize: 20 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 6 dataSize: 20 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: emp_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.emp_orc + name: default.emp_orc + Truncated Path -> Alias: + /emp_orc [emp_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select lastname,deptid from emp_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- basicStatState: COMPLETE colStatState: COMPLETE +explain extended select lastname,deptid from emp_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: emp_orc.deptid SIMPLE [(emp_staging)emp_staging.FieldSchema(name:deptid, type:int, comment:null), ] +POSTHOOK: Lineage: emp_orc.lastname SIMPLE [(emp_staging)emp_staging.FieldSchema(name:lastname, type:string, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME emp_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL lastname)) (TOK_SELEXPR (TOK_TABLE_OR_COL deptid))))) + +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: + emp_orc + TableScan + alias: emp_orc + Statistics: + numRows: 6 dataSize: 349 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: lastname + type: string + expr: deptid + type: int + outputColumnNames: _col0, _col1 + Statistics: + numRows: 6 dataSize: 566 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 6 dataSize: 566 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1 + columns.types string:int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: emp_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns lastname,deptid + columns.types string:int + field.delim | +#### A masked pattern was here #### + name default.emp_orc + numFiles 1 + numRows 6 + rawDataSize 0 + serialization.ddl struct emp_orc { string lastname, i32 deptid} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 349 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.emp_orc + name: default.emp_orc + Truncated Path -> Alias: + /emp_orc [emp_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + Added: hive/trunk/ql/src/test/results/clientpositive/annotate_stats_union.q.out URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/annotate_stats_union.q.out?rev=1543120&view=auto ============================================================================== --- hive/trunk/ql/src/test/results/clientpositive/annotate_stats_union.q.out (added) +++ hive/trunk/ql/src/test/results/clientpositive/annotate_stats_union.q.out Mon Nov 18 19:29:24 2013 @@ -0,0 +1,1127 @@ +PREHOOK: query: create table if not exists loc_staging ( + state string, + locid int, + zip bigint, + year int +) row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table if not exists loc_staging ( + state string, + locid int, + zip bigint, + year int +) row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@loc_staging +PREHOOK: query: create table loc_orc like loc_staging +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table loc_orc like loc_staging +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: default@loc_orc +PREHOOK: query: alter table loc_orc set fileformat orc +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: default@loc_orc +PREHOOK: Output: default@loc_orc +POSTHOOK: query: alter table loc_orc set fileformat orc +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: default@loc_orc +POSTHOOK: Output: default@loc_orc +PREHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging +PREHOOK: type: LOAD +PREHOOK: Output: default@loc_staging +POSTHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging +POSTHOOK: type: LOAD +POSTHOOK: Output: default@loc_staging +PREHOOK: query: insert overwrite table loc_orc select * from loc_staging +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_staging +PREHOOK: Output: default@loc_orc +POSTHOOK: query: insert overwrite table loc_orc select * from loc_staging +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_staging +POSTHOOK: Output: default@loc_orc +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year +PREHOOK: type: QUERY +PREHOOK: Input: default@loc_orc +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year +POSTHOOK: type: QUERY +POSTHOOK: Input: default@loc_orc +#### A masked pattern was here #### +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: -- numRows: 8 rawDataSize: 688 +explain extended select state from loc_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 8 rawDataSize: 688 +explain extended select state from loc_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state))))) + +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: + loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc + name: default.loc_orc + Truncated Path -> Alias: + /loc_orc [loc_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from loc_orc union all select state from loc_orc) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from loc_orc union all select state from loc_orc) tmp +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)))))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +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: + null-subquery1:tmp-subquery1:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + null-subquery2:tmp-subquery2:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc + name: default.loc_orc + Truncated Path -> Alias: + /loc_orc [null-subquery1:tmp-subquery1:loc_orc, null-subquery2:tmp-subquery2:loc_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- numRows: 8 rawDataSize: 796 +explain extended select * from loc_orc +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 8 rawDataSize: 796 +explain extended select * from loc_orc +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +STAGE DEPENDENCIES: + Stage-0 is a root stage + +STAGE PLANS: + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + expr: locid + type: int + expr: zip + type: bigint + expr: year + type: int + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + ListSink + + +PREHOOK: query: -- numRows: 16 rawDataSize: 1592 +explain extended select * from (select * from loc_orc union all select * from loc_orc) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 16 rawDataSize: 1592 +explain extended select * from (select * from loc_orc union all select * from loc_orc) tmp +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +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: + null-subquery1:tmp-subquery1:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + expr: locid + type: int + expr: zip + type: bigint + expr: year + type: int + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + expr: _col1 + type: int + expr: _col2 + type: bigint + expr: _col3 + type: int + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:int:bigint:int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + null-subquery2:tmp-subquery2:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + expr: locid + type: int + expr: zip + type: bigint + expr: year + type: int + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + expr: _col1 + type: int + expr: _col2 + type: bigint + expr: _col3 + type: int + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1592 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:int:bigint:int + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc + name: default.loc_orc + Truncated Path -> Alias: + /loc_orc [null-subquery1:tmp-subquery1:loc_orc, null-subquery2:tmp-subquery2:loc_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: create database test +PREHOOK: type: CREATEDATABASE +POSTHOOK: query: create database test +POSTHOOK: type: CREATEDATABASE +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: use test +PREHOOK: type: SWITCHDATABASE +POSTHOOK: query: use test +POSTHOOK: type: SWITCHDATABASE +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: create table if not exists loc_staging ( + state string, + locid int, + zip bigint, + year int +) row format delimited fields terminated by '|' stored as textfile +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table if not exists loc_staging ( + state string, + locid int, + zip bigint, + year int +) row format delimited fields terminated by '|' stored as textfile +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: test@loc_staging +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: create table loc_orc like loc_staging +PREHOOK: type: CREATETABLE +POSTHOOK: query: create table loc_orc like loc_staging +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: test@loc_orc +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: alter table loc_orc set fileformat orc +PREHOOK: type: ALTERTABLE_FILEFORMAT +PREHOOK: Input: test@loc_orc +PREHOOK: Output: test@loc_orc +POSTHOOK: query: alter table loc_orc set fileformat orc +POSTHOOK: type: ALTERTABLE_FILEFORMAT +POSTHOOK: Input: test@loc_orc +POSTHOOK: Output: test@loc_orc +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging +PREHOOK: type: LOAD +PREHOOK: Output: test@loc_staging +POSTHOOK: query: load data local inpath '../../data/files/loc.txt' overwrite into table loc_staging +POSTHOOK: type: LOAD +POSTHOOK: Output: test@loc_staging +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: insert overwrite table loc_orc select * from loc_staging +PREHOOK: type: QUERY +PREHOOK: Input: test@loc_staging +PREHOOK: Output: test@loc_orc +POSTHOOK: query: insert overwrite table loc_orc select * from loc_staging +POSTHOOK: type: QUERY +POSTHOOK: Input: test@loc_staging +POSTHOOK: Output: test@loc_orc +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: analyze table loc_staging compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: test@loc_staging +PREHOOK: Output: test@loc_staging +POSTHOOK: query: analyze table loc_staging compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: test@loc_staging +POSTHOOK: Output: test@loc_staging +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: analyze table loc_staging compute statistics for columns state,locid,zip,year +PREHOOK: type: QUERY +PREHOOK: Input: test@loc_staging +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_staging compute statistics for columns state,locid,zip,year +POSTHOOK: type: QUERY +POSTHOOK: Input: test@loc_staging +#### A masked pattern was here #### +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year +PREHOOK: type: QUERY +PREHOOK: Input: test@loc_orc +#### A masked pattern was here #### +POSTHOOK: query: analyze table loc_orc compute statistics for columns state,locid,zip,year +POSTHOOK: type: QUERY +POSTHOOK: Input: test@loc_orc +#### A masked pattern was here #### +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +PREHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from default.loc_orc union all select state from test.loc_orc) temp +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from default.loc_orc union all select state from test.loc_orc) temp +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME default loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)))))) temp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +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: + null-subquery1:temp-subquery1:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + null-subquery2:temp-subquery2:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name default.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: default.loc_orc + name: default.loc_orc +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: test.loc_orc + name: test.loc_orc + Truncated Path -> Alias: + /loc_orc [null-subquery1:temp-subquery1:loc_orc] + /test.db/loc_orc [null-subquery2:temp-subquery2:loc_orc] + + Stage: Stage-0 + Fetch Operator + limit: -1 + + +PREHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from test.loc_staging union all select state from test.loc_orc) temp +PREHOOK: type: QUERY +POSTHOOK: query: -- numRows: 16 rawDataSize: 1376 +explain extended select * from (select state from test.loc_staging union all select state from test.loc_orc) temp +POSTHOOK: type: QUERY +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.locid SIMPLE [(loc_staging)loc_staging.FieldSchema(name:locid, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.state SIMPLE [(loc_staging)loc_staging.FieldSchema(name:state, type:string, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.year SIMPLE [(loc_staging)loc_staging.FieldSchema(name:year, type:int, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +POSTHOOK: Lineage: loc_orc.zip SIMPLE [(loc_staging)loc_staging.FieldSchema(name:zip, type:bigint, comment:null), ] +ABSTRACT SYNTAX TREE: + (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test loc_staging))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME test loc_orc))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL state)))))) temp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) + +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: + null-subquery1:temp-subquery1:loc_staging + TableScan + alias: loc_staging + Statistics: + numRows: 8 dataSize: 117 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + null-subquery2:temp-subquery2:loc_orc + TableScan + alias: loc_orc + Statistics: + numRows: 8 dataSize: 796 basicStatsState: COMPLETE colStatsState: COMPLETE + GatherStats: false + Select Operator + expressions: + expr: state + type: string + outputColumnNames: _col0 + Statistics: + numRows: 8 dataSize: 688 basicStatsState: COMPLETE colStatsState: COMPLETE + Union + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + Select Operator + expressions: + expr: _col0 + type: string + outputColumnNames: _col0 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: + numRows: 16 dataSize: 1376 basicStatsState: COMPLETE colStatsState: COMPLETE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + columns _col0 + columns.types string + escape.delim \ + hive.serialization.extend.nesting.levels true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: loc_orc + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + + input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat + output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_orc + numFiles 1 + numRows 8 + rawDataSize 796 + serialization.ddl struct loc_orc { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.ql.io.orc.OrcSerde + totalSize 489 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde + name: test.loc_orc + name: test.loc_orc +#### A masked pattern was here #### + Partition + base file name: loc_staging + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_staging + numFiles 1 + numRows 8 + rawDataSize 117 + serialization.ddl struct loc_staging { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 125 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + COLUMN_STATS_ACCURATE true + bucket_count -1 + columns state,locid,zip,year + columns.types string:int:bigint:int + field.delim | +#### A masked pattern was here #### + name test.loc_staging + numFiles 1 + numRows 8 + rawDataSize 117 + serialization.ddl struct loc_staging { string state, i32 locid, i64 zip, i32 year} + serialization.format | + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 125 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: test.loc_staging + name: test.loc_staging + Truncated Path -> Alias: + /test.db/loc_orc [null-subquery2:temp-subquery2:loc_orc] + /test.db/loc_staging [null-subquery1:temp-subquery1:loc_staging] + + Stage: Stage-0 + Fetch Operator + limit: -1 + +