FAQ
Author: heyongqiang
Date: Wed Feb 1 15:08:21 2012
New Revision: 1239161

URL: http://svn.apache.org/viewvc?rev=1239161&view=rev
Log:
HIVE-2769 [jira] union with a multi-table insert is not working
(Namit Jain via Yongqiang He)

Summary:
https://issues.apache.org/jira/browse/HIVE-2769

HIVE-2769



Test Plan: EMPTY

Reviewers: JIRA, heyongqiang

Reviewed By: heyongqiang

CC: heyongqiang

Differential Revision: https://reviews.facebook.net/D1545

Added:
hive/trunk/ql/src/test/queries/clientpositive/union31.q
hive/trunk/ql/src/test/results/clientpositive/union31.q.out
Modified:
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRRedSink3.java
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java

Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRRedSink3.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRRedSink3.java?rev=1239161&r1=1239160&r2=1239161&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRRedSink3.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMRRedSink3.java Wed Feb 1 15:08:21 2012
@@ -26,13 +26,10 @@ import java.util.Stack;
import org.apache.hadoop.hive.ql.exec.Operator;
import org.apache.hadoop.hive.ql.exec.ReduceSinkOperator;
import org.apache.hadoop.hive.ql.exec.Task;
-import org.apache.hadoop.hive.ql.exec.UnionOperator;
import org.apache.hadoop.hive.ql.lib.Node;
import org.apache.hadoop.hive.ql.lib.NodeProcessor;
import org.apache.hadoop.hive.ql.lib.NodeProcessorCtx;
import org.apache.hadoop.hive.ql.optimizer.GenMRProcContext.GenMapRedCtx;
-import org.apache.hadoop.hive.ql.optimizer.unionproc.UnionProcContext;
-import org.apache.hadoop.hive.ql.parse.ParseContext;
import org.apache.hadoop.hive.ql.parse.SemanticException;
import org.apache.hadoop.hive.ql.plan.MapredWork;

@@ -63,17 +60,15 @@ public class GenMRRedSink3 implements No
Map<Operator<? extends Serializable>, GenMapRedCtx> mapCurrCtx = ctx
.getMapCurrCtx();
GenMapRedCtx mapredCtx = mapCurrCtx.get(ctx.getCurrUnionOp());
+
Task<? extends Serializable> unionTask = null;
if(mapredCtx != null) {
unionTask = mapredCtx.getCurrTask();
} else {
- Operator<? extends Serializable> topOp = ctx.getCurrTopOp();
- if(topOp == null) {
- return null;
- }
unionTask = ctx.getCurrTask();
}

+
MapredWork plan = (MapredWork) unionTask.getWork();
HashMap<Operator<? extends Serializable>, Task<? extends Serializable>> opTaskMap = ctx
.getOpTaskMap();
@@ -85,7 +80,7 @@ public class GenMRRedSink3 implements No
if (reducerTask == null) {
// When the reducer is encountered for the first time
if (plan.getReducer() == null) {
- GenMapRedUtils.initUnionPlan(op, ctx);
+ GenMapRedUtils.initUnionPlan(op, ctx, unionTask);
// When union is followed by a multi-table insert
} else {
GenMapRedUtils.splitPlan(op, ctx);
@@ -94,7 +89,7 @@ public class GenMRRedSink3 implements No
// The union is already initialized. However, the union is walked from
// another input
// initUnionPlan is idempotent
- GenMapRedUtils.initUnionPlan(op, ctx);
+ GenMapRedUtils.initUnionPlan(op, ctx, unionTask);
} else {
GenMapRedUtils.joinUnionPlan(ctx, unionTask, reducerTask, false);
ctx.setCurrTask(reducerTask);

Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java?rev=1239161&r1=1239160&r2=1239161&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/GenMapRedUtils.java Wed Feb 1 15:08:21 2012
@@ -293,16 +293,15 @@ public final class GenMapRedUtils {
* processing context
*/
public static void initUnionPlan(ReduceSinkOperator op,
- GenMRProcContext opProcCtx) throws SemanticException {
+ GenMRProcContext opProcCtx,
+ Task<? extends Serializable> unionTask) throws SemanticException {
Operator<? extends Serializable> reducer = op.getChildOperators().get(0);
- Map<Operator<? extends Serializable>, GenMapRedCtx> mapCurrCtx = opProcCtx.getMapCurrCtx();
- GenMapRedCtx mapredCtx = mapCurrCtx.get(op.getParentOperators().get(0));
- Task<? extends Serializable> currTask = mapredCtx.getCurrTask();
- MapredWork plan = (MapredWork) currTask.getWork();
+
+ MapredWork plan = (MapredWork) unionTask.getWork();
HashMap<Operator<? extends Serializable>, Task<? extends Serializable>> opTaskMap =
opProcCtx.getOpTaskMap();

- opTaskMap.put(reducer, currTask);
+ opTaskMap.put(reducer, unionTask);
plan.setReducer(reducer);
ReduceSinkDesc desc = op.getConf();

@@ -312,7 +311,7 @@ public final class GenMapRedUtils {
plan.setNeedsTagging(true);
}

- initUnionPlan(opProcCtx, currTask, false);
+ initUnionPlan(opProcCtx, unionTask, false);
}

private static void setUnionPlan(GenMRProcContext opProcCtx,
@@ -366,10 +365,13 @@ public final class GenMapRedUtils {
throws SemanticException {
MapredWork plan = (MapredWork) currTask.getWork();
UnionOperator currUnionOp = opProcCtx.getCurrUnionOp();
- assert currUnionOp != null;
- GenMRUnionCtx uCtx = opProcCtx.getUnionTask(currUnionOp);
- assert uCtx != null;
- setUnionPlan(opProcCtx, local, plan, uCtx, false);
+ // In case of lateral views followed by a join, the same tree
+ // can be traversed more than one
+ if (currUnionOp != null) {
+ GenMRUnionCtx uCtx = opProcCtx.getUnionTask(currUnionOp);
+ assert uCtx != null;
+ setUnionPlan(opProcCtx, local, plan, uCtx, false);
+ }
}

/*

Added: hive/trunk/ql/src/test/queries/clientpositive/union31.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/union31.q?rev=1239161&view=auto
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/union31.q (added)
+++ hive/trunk/ql/src/test/queries/clientpositive/union31.q Wed Feb 1 15:08:21 2012
@@ -0,0 +1,97 @@
+drop table t1;
+drop table t2;
+
+
+create table t1 as select * from src where key < 10;
+create table t2 as select * from src where key < 10;
+
+create table t3(key string, cnt int);
+create table t4(value string, cnt int);
+
+explain
+from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value;
+
+from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value;
+
+select * from t3;
+select * from t4;
+
+create table t5(c1 string, cnt int);
+create table t6(c1 string, cnt int);
+
+explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1;
+
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1;
+
+select * from t5;
+select * from t6;
+
+drop table t1;
+drop table t2;
+
+create table t1 as select * from src where key < 10;
+create table t2 as select key, count(1) as cnt from src where key < 10 group by key;
+
+create table t7(c1 string, cnt int);
+create table t8(c1 string, cnt int);
+
+explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1;
+
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1;
+
+select * from t7;
+select * from t8;

Added: hive/trunk/ql/src/test/results/clientpositive/union31.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/union31.q.out?rev=1239161&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/union31.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/union31.q.out Wed Feb 1 15:08:21 2012
@@ -0,0 +1,1177 @@
+PREHOOK: query: drop table t1
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table t1
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: drop table t2
+PREHOOK: type: DROPTABLE
+POSTHOOK: query: drop table t2
+POSTHOOK: type: DROPTABLE
+PREHOOK: query: create table t1 as select * from src where key < 10
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+POSTHOOK: query: create table t1 as select * from src where key < 10
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@t1
+PREHOOK: query: create table t2 as select * from src where key < 10
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+POSTHOOK: query: create table t2 as select * from src where key < 10
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@t2
+PREHOOK: query: create table t3(key string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t3(key string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t3
+PREHOOK: query: create table t4(value string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t4(value string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t4
+PREHOOK: query: explain
+from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))) x)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t3))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t4))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL value))))
+
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-0 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:x-subquery1:t1
+ TableScan
+ alias: t1
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ 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
+ Select Operator
+ expressions:
+ expr: _col1
+ type: string
+ outputColumnNames: _col1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col1
+ type: string
+ mode: hash
+ 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
+ null-subquery2:x-subquery2:t2
+ TableScan
+ alias: t2
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ 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
+ Select Operator
+ expressions:
+ expr: _col1
+ type: string
+ outputColumnNames: _col1
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col1
+ type: string
+ mode: hash
+ 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
+ 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.t3
+
+ 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.t3
+
+ Stage: Stage-3
+ Stats-Aggr Operator
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ 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: 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.t4
+
+ 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.t4
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+
+PREHOOK: query: from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@t3
+PREHOOK: Output: default@t4
+POSTHOOK: query: from
+(select * from t1
+ union all
+ select * from t2
+) x
+insert overwrite table t3
+ select key, count(1) group by key
+insert overwrite table t4
+ select value, count(1) group by value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@t3
+POSTHOOK: Output: default@t4
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select * from t3
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t3
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t3
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t3
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+0 6
+2 2
+4 2
+5 6
+8 2
+9 2
+PREHOOK: query: select * from t4
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t4
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t4
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t4
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+val_0 6
+val_2 2
+val_4 2
+val_5 6
+val_8 2
+val_9 2
+PREHOOK: query: create table t5(c1 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t5(c1 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t5
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: create table t6(c1 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t6(c1 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t6
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key) c1) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key) c1) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (TOK_TABLE_OR_COL key))))) x)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t5))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL c1)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_TABLE_OR_COL cnt)))) (TOK_GROUPBY (TOK_TABLE_OR_COL c1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t6))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL c1)) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_TABLE_OR_COL cnt)))) (TOK_GROUPBY (TOK_TABLE_OR_COL c1))))
+
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+ Stage-6 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:x-subquery2:t2
+ TableScan
+ alias: t2
+ 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
+ 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
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ 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:
+ Forward
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ 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.t5
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ 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: 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.t6
+
+ 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.t5
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ 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.t6
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:x-subquery1:t1
+ TableScan
+ alias: t1
+ 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 as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@t5
+PREHOOK: Output: default@t6
+POSTHOOK: query: from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, count(1) as cnt from t2 group by key
+) x
+insert overwrite table t5
+ select c1, sum(cnt) group by c1
+insert overwrite table t6
+ select c1, sum(cnt) group by c1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@t5
+POSTHOOK: Output: default@t6
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: select * from t5
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t5
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t5
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t5
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+0 6
+2 2
+4 2
+5 6
+8 2
+9 2
+PREHOOK: query: select * from t6
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t6
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t6
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t6
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+0 6
+2 2
+4 2
+5 6
+8 2
+9 2
+PREHOOK: query: drop table t1
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@t1
+PREHOOK: Output: default@t1
+POSTHOOK: query: drop table t1
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@t1
+POSTHOOK: Output: default@t1
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: drop table t2
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@t2
+POSTHOOK: query: drop table t2
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@t2
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: create table t1 as select * from src where key < 10
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+POSTHOOK: query: create table t1 as select * from src where key < 10
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@t1
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: create table t2 as select key, count(1) as cnt from src where key < 10 group by key
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+POSTHOOK: query: create table t2 as select key, count(1) as cnt from src where key < 10 group by key
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@t2
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: create table t7(c1 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t7(c1 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t7
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: create table t8(c1 string, cnt int)
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: create table t8(c1 string, cnt int)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@t8
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key) c1) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME t2))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key) c1) (TOK_SELEXPR (TOK_TABLE_OR_COL cnt)))))) x)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t7))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL c1)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL c1))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME t8))) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL c1)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL c1))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage
+ Stage-3 depends on stages: Stage-6
+ Stage-0 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0
+ Stage-1 depends on stages: Stage-3
+ Stage-5 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:x-subquery1:t1
+ TableScan
+ alias: t1
+ 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
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ null-subquery2:x-subquery2:t2
+ TableScan
+ alias: t2
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: cnt
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Union
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: 1
+ type: int
+ Reduce Operator Tree:
+ Forward
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ 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.t7
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: complete
+ 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: 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.t8
+
+ 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.t7
+
+ Stage: Stage-4
+ Stats-Aggr Operator
+
+ 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.t8
+
+ Stage: Stage-5
+ Stats-Aggr Operator
+
+
+PREHOOK: query: from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@t7
+PREHOOK: Output: default@t8
+POSTHOOK: query: from
+(
+ select key as c1, count(1) as cnt from t1 group by key
+ union all
+ select key as c1, cnt from t2
+) x
+insert overwrite table t7
+ select c1, count(1) group by c1
+insert overwrite table t8
+ select c1, count(1) group by c1
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@t7
+POSTHOOK: Output: default@t8
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t7.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t7.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t8.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t8.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+PREHOOK: query: select * from t7
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t7
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t7
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t7
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t7.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t7.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t8.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t8.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+0 2
+2 2
+4 2
+5 2
+8 2
+9 2
+PREHOOK: query: select * from t8
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t8
+#### A masked pattern was here ####
+POSTHOOK: query: select * from t8
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t8
+#### A masked pattern was here ####
+POSTHOOK: Lineage: t3.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t3.key EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t4.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t4.value EXPRESSION [(t2)t2.FieldSchema(name:value, type:string, comment:null), (t1)t1.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t5.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t6.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t6.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t7.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t7.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+POSTHOOK: Lineage: t8.c1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), (t1)t1.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: t8.cnt EXPRESSION [(t2)t2.null, (t1)t1.null, ]
+0 2
+2 2
+4 2
+5 2
+8 2
+9 2

Search Discussions

Related Discussions

Discussion Navigation
viewthread | post
Discussion Overview
groupcommits @
categorieshive, hadoop
postedFeb 1, '12 at 3:08p
activeFeb 1, '12 at 3:08p
posts1
users1
websitehive.apache.org

1 user in discussion

Heyongqiang: 1 post

People

Translate

site design / logo © 2021 Grokbase