diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java index ba28bc7..2dc66f7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ColumnPrunerProcFactory.java @@ -18,16 +18,6 @@ package org.apache.hadoop.hive.ql.optimizer; -import java.util.ArrayList; -import java.util.Collections; -import java.util.HashMap; -import java.util.HashSet; -import java.util.Iterator; -import java.util.List; -import java.util.Map; -import java.util.Set; -import java.util.Stack; - import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; import org.apache.hadoop.hive.ql.exec.AbstractMapJoinOperator; @@ -39,7 +29,6 @@ import org.apache.hadoop.hive.ql.exec.LateralViewForwardOperator; import org.apache.hadoop.hive.ql.exec.LateralViewJoinOperator; import org.apache.hadoop.hive.ql.exec.LimitOperator; -import org.apache.hadoop.hive.ql.exec.MapJoinOperator; import org.apache.hadoop.hive.ql.exec.Operator; import org.apache.hadoop.hive.ql.exec.OperatorFactory; import org.apache.hadoop.hive.ql.exec.PTFOperator; @@ -76,6 +65,16 @@ import org.apache.hadoop.hive.serde2.objectinspector.StructField; import org.apache.hadoop.hive.serde2.objectinspector.StructObjectInspector; +import java.util.ArrayList; +import java.util.Collections; +import java.util.HashMap; +import java.util.HashSet; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.Stack; + /** * Factory for generating the different node processors used by ColumnPruner. */ @@ -600,8 +599,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx ctx, // revert output cols of SEL(*) to ExprNodeColumnDesc String[] tabcol = rr.reverseLookup(col); ColumnInfo colInfo = rr.get(tabcol[0], tabcol[1]); - ExprNodeColumnDesc colExpr = new ExprNodeColumnDesc(colInfo.getType(), - colInfo.getInternalName(), colInfo.getTabAlias(), colInfo.getIsVirtualCol()); + ExprNodeColumnDesc colExpr = new ExprNodeColumnDesc(colInfo); colList.add(colExpr); outputColNames.add(col); } diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java index d79879c..477be1d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/SortedDynPartitionOptimizer.java @@ -18,14 +18,8 @@ package org.apache.hadoop.hive.ql.optimizer; -import java.io.Serializable; -import java.util.ArrayList; -import java.util.Arrays; -import java.util.LinkedHashMap; -import java.util.List; -import java.util.Map; -import java.util.Set; -import java.util.Stack; +import com.google.common.collect.Lists; +import com.google.common.collect.Maps; import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; @@ -72,8 +66,14 @@ import org.apache.hadoop.hive.ql.plan.TableDesc; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; -import com.google.common.collect.Lists; -import com.google.common.collect.Maps; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.Stack; /** * When dynamic partitioning (with or without bucketing and sorting) is enabled, this optimization @@ -209,8 +209,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, ArrayList newValueCols = Lists.newArrayList(); Map colExprMap = Maps.newHashMap(); for (ColumnInfo ci : valColInfo) { - newValueCols.add(new ExprNodeColumnDesc(ci.getType(), ci.getInternalName(), ci - .getTabAlias(), ci.isHiddenVirtualCol())); + newValueCols.add(new ExprNodeColumnDesc(ci)); colExprMap.put(ci.getInternalName(), newValueCols.get(newValueCols.size() - 1)); } ReduceSinkDesc rsConf = getReduceSinkDesc(partitionPositions, sortPositions, sortOrder, @@ -476,8 +475,7 @@ public ReduceSinkDesc getReduceSinkDesc(List partitionPositions, for (Integer idx : pos) { ColumnInfo ci = colInfos.get(idx); - ExprNodeColumnDesc encd = new ExprNodeColumnDesc(ci.getType(), ci.getInternalName(), - ci.getTabAlias(), ci.isHiddenVirtualCol()); + ExprNodeColumnDesc encd = new ExprNodeColumnDesc(ci); cols.add(encd); } diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/JoinCondTypeCheckProcFactory.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/JoinCondTypeCheckProcFactory.java index 406c18e..38156c6 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/JoinCondTypeCheckProcFactory.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/optiq/translator/JoinCondTypeCheckProcFactory.java @@ -17,15 +17,6 @@ */ package org.apache.hadoop.hive.ql.optimizer.optiq.translator; -import java.util.ArrayList; -import java.util.Collection; -import java.util.HashMap; -import java.util.HashSet; -import java.util.List; -import java.util.Map; -import java.util.Set; -import java.util.Stack; - import org.apache.hadoop.hive.ql.ErrorMsg; import org.apache.hadoop.hive.ql.exec.ColumnInfo; import org.apache.hadoop.hive.ql.exec.FunctionInfo; @@ -47,6 +38,15 @@ import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPAnd; import org.apache.hadoop.hive.ql.udf.generic.GenericUDFOPOr; +import java.util.ArrayList; +import java.util.Collection; +import java.util.HashMap; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.Stack; + /** * JoinCondTypeCheckProcFactory is used by Optiq planner(CBO) to generate Join Conditions from Join Condition AST. * Reasons for sub class: @@ -99,8 +99,7 @@ public Object process(Node nd, Stack stack, NodeProcessorCtx procCtx, if (!qualifiedAccess) { colInfo = getColInfo(ctx, null, tableOrCol, expr); // It's a column. - return new ExprNodeColumnDesc(colInfo.getType(), colInfo.getInternalName(), - colInfo.getTabAlias(), colInfo.getIsVirtualCol()); + return new ExprNodeColumnDesc(colInfo); } else if (hasTableAlias(ctx, tableOrCol, expr)) { return null; } else { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/GenMRSkewJoinProcessor.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/GenMRSkewJoinProcessor.java index 8afe218..7b4709f 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/GenMRSkewJoinProcessor.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/GenMRSkewJoinProcessor.java @@ -18,13 +18,6 @@ package org.apache.hadoop.hive.ql.optimizer.physical; -import java.io.Serializable; -import java.util.ArrayList; -import java.util.HashMap; -import java.util.LinkedHashMap; -import java.util.List; -import java.util.Map; - import org.apache.hadoop.fs.Path; import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.ql.exec.ColumnInfo; @@ -60,6 +53,13 @@ import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.LinkedHashMap; +import java.util.List; +import java.util.Map; + /** * GenMRSkewJoinProcessor. * @@ -192,9 +192,7 @@ public static void processSkewJoin(JoinOperator joinOp, String newColName = i + "_VALUE_" + k; // any name, it does not matter. ColumnInfo columnInfo = new ColumnInfo(newColName, type, alias.toString(), false); columnInfos.add(columnInfo); - newValueExpr.add(new ExprNodeColumnDesc( - columnInfo.getType(), columnInfo.getInternalName(), - columnInfo.getTabAlias(), false)); + newValueExpr.add(new ExprNodeColumnDesc(columnInfo)); if (!first) { colNames = colNames + ","; colTypes = colTypes + ","; @@ -216,9 +214,7 @@ public static void processSkewJoin(JoinOperator joinOp, ColumnInfo columnInfo = new ColumnInfo(joinKeys.get(k), TypeInfoFactory .getPrimitiveTypeInfo(joinKeyTypes.get(k)), alias.toString(), false); columnInfos.add(columnInfo); - newKeyExpr.add(new ExprNodeColumnDesc( - columnInfo.getType(), columnInfo.getInternalName(), - columnInfo.getTabAlias(), false)); + newKeyExpr.add(new ExprNodeColumnDesc(columnInfo)); } newJoinValues.put(alias, newValueExpr); diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java index 9c944b6..5bf4da2 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -4133,9 +4133,7 @@ private Operator genGroupByPlanGroupByOperator1(QBParseInfo parseInfo, throw new SemanticException(ErrorMsg.INVALID_COLUMN.getMsg(grpbyExpr)); } - groupByKeys.add(new ExprNodeColumnDesc(exprInfo.getType(), exprInfo - .getInternalName(), exprInfo.getTabAlias(), exprInfo - .getIsVirtualCol())); + groupByKeys.add(new ExprNodeColumnDesc(exprInfo)); String field = getColumnInternalName(i); outputColumnNames.add(field); ColumnInfo oColInfo = new ColumnInfo(field, exprInfo.getType(), "", false); @@ -6931,9 +6929,7 @@ private Operator genReduceSinkPlanForSortingBucketing(Table tab, Operator input, for (ColumnInfo colInfo : inputRR.getColumnInfos()) { String internalName = getColumnInternalName(i++); outputColumns.add(internalName); - valueCols.add(new ExprNodeColumnDesc(colInfo.getType(), colInfo - .getInternalName(), colInfo.getTabAlias(), colInfo - .getIsVirtualCol())); + valueCols.add(new ExprNodeColumnDesc(colInfo)); colExprMap.put(internalName, valueCols .get(valueCols.size() - 1)); } @@ -7062,8 +7058,7 @@ private Operator genReduceSinkPlan(String dest, QB qb, Operator input, ColumnInfo colInfo = columnInfos.get(i); String[] nm = inputRR.reverseLookup(colInfo.getInternalName()); String[] nm2 = inputRR.getAlternateMappings(colInfo.getInternalName()); - ExprNodeColumnDesc value = new ExprNodeColumnDesc(colInfo.getType(), - colInfo.getInternalName(), colInfo.getTabAlias(), colInfo.getIsVirtualCol()); + ExprNodeColumnDesc value = new ExprNodeColumnDesc(colInfo); // backtrack can be null when input is script operator ExprNodeDesc valueBack = ExprNodeDescUtils.backtrack(value, dummy, input); @@ -7315,8 +7310,7 @@ private Operator genJoinReduceSinkChild(QB qb, ExprNodeDesc[] joinKeys, ColumnInfo colInfo = columns.get(i); String[] nm = inputRR.reverseLookup(colInfo.getInternalName()); String[] nm2 = inputRR.getAlternateMappings(colInfo.getInternalName()); - ExprNodeDesc expr = new ExprNodeColumnDesc(colInfo.getType(), - colInfo.getInternalName(), colInfo.getTabAlias(), colInfo.getIsVirtualCol()); + ExprNodeDesc expr = new ExprNodeColumnDesc(colInfo); // backtrack can be null when input is script operator ExprNodeDesc exprBack = ExprNodeDescUtils.backtrack(expr, dummy, child); @@ -8404,12 +8398,9 @@ private Operator insertSelectAllPlanForGroupBy(Operator input) new HashMap(); for (int i = 0; i < columns.size(); i++) { ColumnInfo col = columns.get(i); - colList.add(new ExprNodeColumnDesc(col.getType(), col.getInternalName(), - col.getTabAlias(), col.getIsVirtualCol())); + colList.add(new ExprNodeColumnDesc(col)); columnNames.add(col.getInternalName()); - columnExprMap.put(col.getInternalName(), - new ExprNodeColumnDesc(col.getType(), col.getInternalName(), - col.getTabAlias(), col.getIsVirtualCol())); + columnExprMap.put(col.getInternalName(), new ExprNodeColumnDesc(col)); } Operator output = putOpInsertMap(OperatorFactory.getAndMakeChild( new SelectDesc(colList, columnNames, true), new RowSchema(inputRR @@ -9266,8 +9257,7 @@ private ExprNodeDesc genSamplePredicate(TableSample ts, for (String col : bucketCols) { ColumnInfo ci = rwsch.get(alias, col); // TODO: change type to the one in the table schema - args.add(new ExprNodeColumnDesc(ci.getType(), ci.getInternalName(), ci - .getTabAlias(), ci.getIsVirtualCol())); + args.add(new ExprNodeColumnDesc(ci)); } } else { for (ASTNode expr : ts.getExprs()) { @@ -9848,8 +9838,7 @@ private Operator genLateralViewPlan(QB qb, Operator op, ASTNode lateralViewTree) for (ColumnInfo col : source.getColumnInfos()) { String[] tabCol = source.reverseLookup(col.getInternalName()); lvForwardRR.put(tabCol[0], tabCol[1], col); - ExprNodeDesc colExpr = new ExprNodeColumnDesc(col.getType(), col.getInternalName(), - col.getTabAlias(), false); + ExprNodeDesc colExpr = new ExprNodeColumnDesc(col); colList.add(colExpr); colNames.add(colExpr.getName()); lvfColExprMap.put(col.getInternalName(), colExpr); @@ -9938,8 +9927,7 @@ private void LVmergeRowResolvers(RowResolver source, RowResolver dest, String tableAlias = tableCol[0]; String colAlias = tableCol[1]; dest.put(tableAlias, colAlias, newCol); - colExprMap.put(internalName, new ExprNodeColumnDesc(c.getType(), c.getInternalName(), - c.getTabAlias(), c.getIsVirtualCol())); + colExprMap.put(internalName, new ExprNodeColumnDesc(c)); } } @@ -12000,9 +11988,7 @@ void buildPTFReduceSinkDetails(PartitionedTableFunctionDef tabDef, */ int pos = 0; for (ColumnInfo colInfo : colInfoList) { - ExprNodeDesc valueColExpr = new ExprNodeColumnDesc(colInfo.getType(), colInfo - .getInternalName(), colInfo.getTabAlias(), colInfo - .getIsVirtualCol()); + ExprNodeDesc valueColExpr = new ExprNodeColumnDesc(colInfo); valueCols.add(valueColExpr); String internalName = SemanticAnalyzer.getColumnInternalName(pos++); outputColumnNames.add(internalName); @@ -12247,9 +12233,7 @@ private Operator genReduceSinkPlanForWindowing(WindowingSpec spec, RowResolver rsNewRR = new RowResolver(); int pos = 0; for (ColumnInfo colInfo : colInfoList) { - ExprNodeDesc valueColExpr = new ExprNodeColumnDesc(colInfo.getType(), colInfo - .getInternalName(), colInfo.getTabAlias(), colInfo - .getIsVirtualCol()); + ExprNodeDesc valueColExpr = new ExprNodeColumnDesc(colInfo); valueCols.add(valueColExpr); String internalName = SemanticAnalyzer.getColumnInternalName(pos++); outputColumnNames.add(internalName); diff --git ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java index 250208e..9a32054 100755 --- ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java +++ ql/src/java/org/apache/hadoop/hive/ql/plan/ExprNodeColumnDesc.java @@ -18,14 +18,15 @@ package org.apache.hadoop.hive.ql.plan; -import java.io.Serializable; -import java.util.ArrayList; -import java.util.List; - import org.apache.commons.lang.builder.HashCodeBuilder; +import org.apache.hadoop.hive.ql.exec.ColumnInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo; import org.apache.hadoop.hive.serde2.typeinfo.TypeInfoFactory; +import java.io.Serializable; +import java.util.ArrayList; +import java.util.List; + /** * ExprNodeColumnDesc. * @@ -56,6 +57,10 @@ public ExprNodeColumnDesc() { } + public ExprNodeColumnDesc(ColumnInfo ci) { + this(ci.getType(), ci.getInternalName(), ci.getTabAlias(), ci.getIsVirtualCol()); + } + public ExprNodeColumnDesc(TypeInfo typeInfo, String column, String tabAlias, boolean isPartitionColOrVirtualCol) { super(typeInfo); diff --git ql/src/test/results/clientpositive/lateral_view_ppd.q.out ql/src/test/results/clientpositive/lateral_view_ppd.q.out index 1220030..b186192 100644 --- ql/src/test/results/clientpositive/lateral_view_ppd.q.out +++ ql/src/test/results/clientpositive/lateral_view_ppd.q.out @@ -175,23 +175,44 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((ds = '2008-04-08') and (hr = '12')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: value - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col1, _col7 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col7 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 12 + Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE + 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 + Select Operator + expressions: array(1,2,3) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + function name: explode Lateral View Join Operator outputColumnNames: _col1, _col7 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col7 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 12 Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -202,30 +223,6 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Select Operator - expressions: array(1,2,3) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col1, _col7 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col7 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 12 - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 12 Data size: 120 Basic stats: COMPLETE Column stats: NONE - 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 Stage: Stage-0 Fetch Operator @@ -236,18 +233,12 @@ STAGE PLANS: PREHOOK: query: SELECT value, myCol FROM (SELECT * FROM srcpart LATERAL VIEW explode(array(1,2,3)) myTable AS myCol) a WHERE ds='2008-04-08' AND hr="12" LIMIT 12 PREHOOK: type: QUERY PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: SELECT value, myCol FROM (SELECT * FROM srcpart LATERAL VIEW explode(array(1,2,3)) myTable AS myCol) a WHERE ds='2008-04-08' AND hr="12" LIMIT 12 POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### val_238 1 val_238 2 diff --git ql/src/test/results/clientpositive/union26.q.out ql/src/test/results/clientpositive/union26.q.out index cdc558a..4f9e0d4 100644 --- ql/src/test/results/clientpositive/union26.q.out +++ ql/src/test/results/clientpositive/union26.q.out @@ -103,91 +103,88 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((ds = '2008-04-08') and (hr = '11')) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Lateral View Forward - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: key, value - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Lateral View Forward + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Lateral View Join Operator + outputColumnNames: _col0, _col1, _col7 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Union + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(1) + keys: _col0 (type: string), _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Select Operator + expressions: array(1,2,3) (type: array) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + UDTF Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + function name: explode Lateral View Join Operator outputColumnNames: _col0, _col1, _col7 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Union - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) - Select Operator - expressions: array(1,2,3) (type: array) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - UDTF Operator - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - function name: explode - Lateral View Join Operator - outputColumnNames: _col0, _col1, _col7 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4000 Data size: 42496 Basic stats: COMPLETE Column stats: NONE - Union - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) TableScan Union - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 4275 Data size: 45417 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1275 Data size: 13545 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator @@ -195,14 +192,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2137 Data size: 22703 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 637 Data size: 6767 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2137 Data size: 22703 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 637 Data size: 6767 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2137 Data size: 22703 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 637 Data size: 6767 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -238,8 +235,6 @@ PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: SELECT count(1) as counts, @@ -265,8 +260,6 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 10 100 val_100 10 103 val_103 @@ -601,8 +594,6 @@ PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: SELECT count(1) as counts, @@ -628,8 +619,6 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 10 100 val_100 10 103 val_103 @@ -964,8 +953,6 @@ PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: SELECT count(1) as counts, @@ -991,8 +978,6 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 10 100 val_100 10 103 val_103