diff --git hbase-handler/src/test/results/positive/hbase_pushdown.q.out hbase-handler/src/test/results/positive/hbase_pushdown.q.out index be96eec..c867f6e 100644 --- hbase-handler/src/test/results/positive/hbase_pushdown.q.out +++ hbase-handler/src/test/results/positive/hbase_pushdown.q.out @@ -94,7 +94,7 @@ STAGE PLANS: predicate: (value like '%90%') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 90 (type: int), value (type: string) + expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -142,7 +142,7 @@ STAGE PLANS: predicate: (value like '%90%') (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 90 (type: int), value (type: string) + expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -194,7 +194,7 @@ STAGE PLANS: predicate: ((value like '%90%') and (key = UDFToInteger(value))) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: 90 (type: int), value (type: string) + expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator diff --git hbase-handler/src/test/results/positive/hbase_queries.q.out hbase-handler/src/test/results/positive/hbase_queries.q.out index 3907bc9..0bdc8d9 100644 --- hbase-handler/src/test/results/positive/hbase_queries.q.out +++ hbase-handler/src/test/results/positive/hbase_queries.q.out @@ -121,7 +121,7 @@ STAGE PLANS: alias: hbase_table_1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int) @@ -136,7 +136,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -494,7 +494,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(key) @@ -529,7 +529,7 @@ STAGE PLANS: alias: hbase_table_1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java index 8f48e7d..b5b4c54 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/Optimizer.java @@ -22,8 +22,6 @@ import java.util.List; import java.util.Set; -import org.slf4j.Logger; -import org.slf4j.LoggerFactory; import org.apache.hadoop.hive.conf.HiveConf; import org.apache.hadoop.hive.ql.optimizer.calcite.translator.HiveOpConverterPostProc; import org.apache.hadoop.hive.ql.optimizer.correlation.CorrelationOptimizer; @@ -40,7 +38,10 @@ import org.apache.hadoop.hive.ql.parse.SemanticException; import org.apache.hadoop.hive.ql.ppd.PredicatePushDown; import org.apache.hadoop.hive.ql.ppd.PredicateTransitivePropagate; +import org.apache.hadoop.hive.ql.ppd.SimplePredicatePushDown; import org.apache.hadoop.hive.ql.ppd.SyntheticJoinPredicate; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; import com.google.common.base.Splitter; import com.google.common.base.Strings; @@ -91,18 +92,23 @@ public void initialize(HiveConf hiveConf) { transformations.add(new PartitionColumnsSeparator()); } - if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTPPD)) { + if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTPPD) && + !pctx.getContext().isCboSucceeded()) { transformations.add(new PredicateTransitivePropagate()); if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTCONSTANTPROPAGATION)) { transformations.add(new ConstantPropagate()); } transformations.add(new SyntheticJoinPredicate()); transformations.add(new PredicatePushDown()); + } else if (pctx.getContext().isCboSucceeded()) { +// transformations.add(new PredicateTransitivePropagate()); + transformations.add(new SyntheticJoinPredicate()); + transformations.add(new SimplePredicatePushDown()); } if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTCONSTANTPROPAGATION)) { // We run constant propagation twice because after predicate pushdown, filter expressions // are combined and may become eligible for reduction (like is not null filter). - transformations.add(new ConstantPropagate()); + transformations.add(new ConstantPropagate()); } if (HiveConf.getBoolVar(hiveConf, HiveConf.ConfVars.HIVEOPTPPD)) { diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java index db625c1..5fe3e7a 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/reloperators/HiveProject.java @@ -169,7 +169,7 @@ public static RelNode projectMapping(RelNode rel, Mapping mapping, List public Project copy(RelTraitSet traitSet, RelNode input, List exps, RelDataType rowType) { assert traitSet.containsIfApplicable(HiveRelNode.CONVENTION); HiveProject hp = new HiveProject(getCluster(), traitSet, input, exps, rowType, getFlags()); - if (this.isSysnthetic()) { + if (this.isSynthetic()) { hp.setSynthetic(); } @@ -195,7 +195,7 @@ public void setSynthetic() { this.isSysnthetic = true; } - public boolean isSysnthetic() { + public boolean isSynthetic() { return isSysnthetic; } diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTSTransposeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTSTransposeRule.java index 8321504..f81c21b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTSTransposeRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTSTransposeRule.java @@ -58,7 +58,7 @@ public boolean matches(RelOptRuleCall call) { // 2. If ProjectRel is not synthetic then PPD would have already pushed // relevant pieces down and hence no point in running PPD again. // 3. For synthetic Projects we don't care about non deterministic UDFs - if (!projRel.isSysnthetic()) { + if (!projRel.isSynthetic()) { return false; } diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTransposeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTransposeRule.java index 7e484b9..d5c8530 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTransposeRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterProjectTransposeRule.java @@ -25,23 +25,37 @@ import org.apache.calcite.rel.rules.FilterProjectTransposeRule; import org.apache.calcite.rex.RexNode; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveProject; public class HiveFilterProjectTransposeRule extends FilterProjectTransposeRule { + public static final HiveFilterProjectTransposeRule INSTANCE_DETERMINISTIC = + new HiveFilterProjectTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, + HiveProject.class, HiveProject.DEFAULT_PROJECT_FACTORY, true); + + public static final HiveFilterProjectTransposeRule INSTANCE = + new HiveFilterProjectTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, + HiveProject.class, HiveProject.DEFAULT_PROJECT_FACTORY, false); + + private final boolean onlyDeterministic; + public HiveFilterProjectTransposeRule(Class filterClass, FilterFactory filterFactory, Class projectClass, - ProjectFactory projectFactory) { + ProjectFactory projectFactory, boolean onlyDeterministic) { super(filterClass, filterFactory, projectClass, projectFactory); + this.onlyDeterministic = onlyDeterministic; } @Override public boolean matches(RelOptRuleCall call) { final Filter filterRel = call.rel(0); RexNode condition = filterRel.getCondition(); - if (!HiveCalciteUtil.isDeterministic(condition)) { + if (this.onlyDeterministic && !HiveCalciteUtil.isDeterministic(condition)) { return false; } return super.matches(call); } + } diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterSortTransposeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterSortTransposeRule.java new file mode 100644 index 0000000..cfd879f --- /dev/null +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveFilterSortTransposeRule.java @@ -0,0 +1,71 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.ql.optimizer.calcite.rules; + +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.rel.RelNode; +import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveSortLimit; + +import com.google.common.collect.ImmutableList; + +public class HiveFilterSortTransposeRule extends RelOptRule { + + public static final HiveFilterSortTransposeRule INSTANCE = + new HiveFilterSortTransposeRule(); + + //~ Constructors ----------------------------------------------------------- + + /** + * Creates a HiveFilterSortTransposeRule. + */ + private HiveFilterSortTransposeRule() { + super( + operand( + HiveFilter.class, + operand(HiveSortLimit.class, any()))); + } + + //~ Methods ---------------------------------------------------------------- + + public boolean matches(RelOptRuleCall call) { + final HiveSortLimit sort = call.rel(1); + + // If sort contains a limit operation, we bail out + if (HiveCalciteUtil.limitRelNode(sort)) { + return false; + } + + return true; + } + + public void onMatch(RelOptRuleCall call) { + final HiveFilter filter = call.rel(0); + final HiveSortLimit sort = call.rel(1); + + final RelNode newFilter = filter.copy(sort.getInput().getTraitSet(), + ImmutableList.of(sort.getInput())); + final HiveSortLimit newSort = sort.copy(sort.getTraitSet(), + newFilter, sort.collation, sort.offset, sort.fetch); + + call.transformTo(newSort); + } + +} diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinAddNotNullRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinAddNotNullRule.java index 2a415d5..5e9e46d 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinAddNotNullRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveJoinAddNotNullRule.java @@ -36,18 +36,12 @@ import org.apache.calcite.rex.RexNode; import org.apache.calcite.rex.RexUtil; import org.apache.calcite.sql.SqlKind; -import org.apache.calcite.sql.SqlOperator; -import org.apache.calcite.sql.type.SqlTypeName; -import org.apache.hadoop.hive.ql.exec.FunctionRegistry; +import org.apache.calcite.sql.fun.SqlStdOperatorTable; import org.apache.hadoop.hive.ql.optimizer.calcite.CalciteSemanticException; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil.JoinLeafPredicateInfo; import org.apache.hadoop.hive.ql.optimizer.calcite.HiveCalciteUtil.JoinPredicateInfo; import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveFilter; -import org.apache.hadoop.hive.ql.optimizer.calcite.translator.SqlFunctionConverter; -import org.apache.hadoop.hive.ql.parse.SemanticException; - -import com.google.common.collect.ImmutableList; public final class HiveJoinAddNotNullRule extends RelOptRule { @@ -145,9 +139,6 @@ public void onMatch(RelOptRuleCall call) { boolean added = false; - final RelDataType returnType = cluster.getTypeFactory(). - createSqlType(SqlTypeName.BOOLEAN); - final Map newConditions; if (input instanceof HiveFilter) { newConditions = splitCondition(((HiveFilter) input).getCondition()); @@ -156,23 +147,17 @@ public void onMatch(RelOptRuleCall call) { newConditions = new HashMap(); } for (int pos : inputKeyPositions) { - try { - RelDataType keyType = input.getRowType().getFieldList().get(pos).getType(); - // Nothing to do if key cannot be null - if (!keyType.isNullable()) { - continue; - } - SqlOperator funcCall = SqlFunctionConverter.getCalciteOperator(NOT_NULL_FUNC_NAME, - FunctionRegistry.getFunctionInfo(NOT_NULL_FUNC_NAME).getGenericUDF(), - ImmutableList.of(keyType), returnType); - RexNode cond = rexBuilder.makeCall(funcCall, rexBuilder.makeInputRef(input, pos)); - String digest = cond.toString(); - if (!newConditions.containsKey(digest)) { - newConditions.put(digest,cond); - added = true; - } - } catch (SemanticException e) { - throw new AssertionError(e.getMessage()); + RelDataType keyType = input.getRowType().getFieldList().get(pos).getType(); + // Nothing to do if key cannot be null + if (!keyType.isNullable()) { + continue; + } + RexNode cond = rexBuilder.makeCall(SqlStdOperatorTable.IS_NOT_NULL, + rexBuilder.makeInputRef(input, pos)); + String digest = cond.toString(); + if (!newConditions.containsKey(digest)) { + newConditions.put(digest,cond); + added = true; } } // Nothing will be added to the expression diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortMergeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortMergeRule.java index efde665..31efe6b 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortMergeRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortMergeRule.java @@ -1,4 +1,4 @@ -/* +/** * Licensed to the Apache Software Foundation (ASF) under one * or more contributor license agreements. See the NOTICE file * distributed with this work for additional information @@ -7,7 +7,7 @@ * "License"); you may not use this file except in compliance * with the License. You may obtain a copy of the License at * - * http://www.apache.org/licenses/LICENSE-2.0 + * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectTransposeRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectTransposeRule.java index feec3c2..e2f7815 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectTransposeRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSortProjectTransposeRule.java @@ -1,4 +1,4 @@ -/* +/** * Licensed to the Apache Software Foundation (ASF) under one * or more contributor license agreements. See the NOTICE file * distributed with this work for additional information @@ -7,7 +7,7 @@ * "License"); you may not use this file except in compliance * with the License. You may obtain a copy of the License at * - * http://www.apache.org/licenses/LICENSE-2.0 + * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, diff --git ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java index 36a12bf..a448bc8 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -21,12 +21,12 @@ import java.lang.reflect.InvocationTargetException; import java.lang.reflect.UndeclaredThrowableException; import java.math.BigDecimal; +import java.util.AbstractMap.SimpleEntry; import java.util.ArrayList; import java.util.BitSet; import java.util.Collections; import java.util.EnumSet; import java.util.HashMap; -import java.util.AbstractMap.SimpleEntry; import java.util.HashSet; import java.util.Iterator; import java.util.LinkedHashMap; @@ -142,6 +142,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterProjectTSTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterProjectTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterSetOpTransposeRule; +import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveFilterSortTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveInsertExchange4JoinRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveJoinAddNotNullRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveJoinCommuteRule; @@ -487,6 +488,11 @@ static String canHandleQbForCbo(QueryProperties queryProperties, HiveConf conf, } @Override + boolean isCBOExecuted() { + return runCBO; + } + + @Override boolean continueJoinMerge() { return !(runCBO && disableSemJoinReordering); } @@ -994,8 +1000,10 @@ public RelNode apply(RelOptCluster cluster, RelOptSchema relOptSchema, SchemaPlu HiveAggregate.HIVE_AGGR_REL_FACTORY, HiveUnion.UNION_REL_FACTORY); calciteOptimizedPlan = fieldTrimmer.trim(calciteOptimizedPlan); calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, false, mdProvider.getMetadataProvider(), - HepMatchOrder.BOTTOM_UP, ProjectRemoveRule.INSTANCE, - new ProjectMergeRule(false, HiveProject.DEFAULT_PROJECT_FACTORY)); + new ProjectMergeRule(true, HiveProject.DEFAULT_PROJECT_FACTORY)); + calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, true, mdProvider.getMetadataProvider(), + new HiveFilterProjectTSTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, + HiveProject.class, HiveProject.DEFAULT_PROJECT_FACTORY, HiveTableScan.class)); // 8.2. Introduce exchange operators below join/multijoin operators calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, false, mdProvider.getMetadataProvider(), @@ -1062,10 +1070,9 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv // TODO: Add in ReduceExpressionrules (Constant folding) to below once // HIVE-11927 is fixed. perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER); - basePlan = hepPlan(basePlan, true, mdProvider, new HiveFilterProjectTransposeRule( - Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, HiveProject.class, - HiveProject.DEFAULT_PROJECT_FACTORY), new HiveFilterSetOpTransposeRule( - HiveFilter.DEFAULT_FILTER_FACTORY), HiveFilterJoinRule.JOIN, + basePlan = hepPlan(basePlan, true, mdProvider, HiveFilterProjectTransposeRule.INSTANCE_DETERMINISTIC, + new HiveFilterSetOpTransposeRule(HiveFilter.DEFAULT_FILTER_FACTORY), + HiveFilterSortTransposeRule.INSTANCE, HiveFilterJoinRule.JOIN, HiveFilterJoinRule.FILTER_ON_JOIN, new HiveFilterAggregateTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, Aggregate.class), new FilterMergeRule( HiveFilter.DEFAULT_FILTER_FACTORY)); @@ -1115,10 +1122,9 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv // TODO: Add in ReduceExpressionrules (Constant folding) to below once // HIVE-11927 is fixed. perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER); - basePlan = hepPlan(basePlan, true, mdProvider, new HiveFilterProjectTransposeRule( - Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, HiveProject.class, - HiveProject.DEFAULT_PROJECT_FACTORY), new HiveFilterSetOpTransposeRule( - HiveFilter.DEFAULT_FILTER_FACTORY), HiveFilterJoinRule.JOIN, + basePlan = hepPlan(basePlan, true, mdProvider, HiveFilterProjectTransposeRule.INSTANCE_DETERMINISTIC, + new HiveFilterSetOpTransposeRule(HiveFilter.DEFAULT_FILTER_FACTORY), + HiveFilterSortTransposeRule.INSTANCE, HiveFilterJoinRule.JOIN, HiveFilterJoinRule.FILTER_ON_JOIN, new HiveFilterAggregateTransposeRule(Filter.class, HiveFilter.DEFAULT_FILTER_FACTORY, Aggregate.class), new FilterMergeRule( HiveFilter.DEFAULT_FILTER_FACTORY)); @@ -1166,6 +1172,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv HiveProject.DEFAULT_PROJECT_FACTORY, HiveTableScan.class)); perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: Prejoin ordering transformation, Rerun PPD"); + return basePlan; } 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 27549dc..ea776ca 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java @@ -7566,7 +7566,9 @@ private Operator genJoinOperator(QB qb, QBJoinTree joinTree, for (int i = 0; i < srcOps.length; i++) { // generate a ReduceSink operator for the join String[] srcs = baseSrc[i] != null ? new String[] {baseSrc[i]} : joinTree.getLeftAliases(); - srcOps[i] = genNotNullFilterForJoinSourcePlan(qb, srcOps[i], joinTree, joinKeys[i]); + if (!isCBOExecuted()) { + srcOps[i] = genNotNullFilterForJoinSourcePlan(qb, srcOps[i], joinTree, joinKeys[i]); + } srcOps[i] = genJoinReduceSinkChild(qb, joinKeys[i], srcOps[i], srcs, joinTree.getNextTag()); } @@ -8436,6 +8438,10 @@ private void mergeJoins(QB qb, QBJoinTree node, QBJoinTree target, int pos, int[ return new ObjectPair(res, tgtToNodeExprMap); } + boolean isCBOExecuted() { + return false; + } + boolean continueJoinMerge() { return true; } diff --git ql/src/java/org/apache/hadoop/hive/ql/ppd/SimplePredicatePushDown.java ql/src/java/org/apache/hadoop/hive/ql/ppd/SimplePredicatePushDown.java new file mode 100644 index 0000000..ffa50f3 --- /dev/null +++ ql/src/java/org/apache/hadoop/hive/ql/ppd/SimplePredicatePushDown.java @@ -0,0 +1,79 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.ql.ppd; + +import java.util.ArrayList; +import java.util.LinkedHashMap; +import java.util.Map; + +import org.apache.hadoop.hive.ql.exec.FilterOperator; +import org.apache.hadoop.hive.ql.exec.Operator; +import org.apache.hadoop.hive.ql.exec.TableScanOperator; +import org.apache.hadoop.hive.ql.lib.DefaultGraphWalker; +import org.apache.hadoop.hive.ql.lib.DefaultRuleDispatcher; +import org.apache.hadoop.hive.ql.lib.Dispatcher; +import org.apache.hadoop.hive.ql.lib.GraphWalker; +import org.apache.hadoop.hive.ql.lib.Node; +import org.apache.hadoop.hive.ql.lib.NodeProcessor; +import org.apache.hadoop.hive.ql.lib.Rule; +import org.apache.hadoop.hive.ql.lib.RuleRegExp; +import org.apache.hadoop.hive.ql.optimizer.Transform; +import org.apache.hadoop.hive.ql.parse.ParseContext; +import org.apache.hadoop.hive.ql.parse.SemanticException; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class SimplePredicatePushDown extends Transform { + + private static final Logger LOG = LoggerFactory.getLogger(SimplePredicatePushDown.class); + private ParseContext pGraphContext; + + @Override + public ParseContext transform(ParseContext pctx) throws SemanticException { + pGraphContext = pctx; + + // create a the context for walking operators + OpWalkerInfo opWalkerInfo = new OpWalkerInfo(pGraphContext); + + Map opRules = new LinkedHashMap(); + opRules.put(new RuleRegExp("R1", "(" + + TableScanOperator.getOperatorName() + "%" + + FilterOperator.getOperatorName() + "%)"), + OpProcFactory.getFilterProc()); + opRules.put(new RuleRegExp("R2", + TableScanOperator.getOperatorName() + "%"), + OpProcFactory.getTSProc()); + + // The dispatcher fires the processor corresponding to the closest matching + // rule and passes the context along + Dispatcher disp = new DefaultRuleDispatcher(OpProcFactory.getDefaultProc(), + opRules, opWalkerInfo); + GraphWalker ogw = new DefaultGraphWalker(disp); + + // Create a list of topop nodes + ArrayList topNodes = new ArrayList(); + topNodes.addAll(pGraphContext.getTopOps().values()); + ogw.startWalking(topNodes, null); + + if (LOG.isDebugEnabled()) { + LOG.debug("After PPD:\n" + Operator.toString(pctx.getTopOps().values())); + } + return pGraphContext; + } + +} diff --git ql/src/test/results/clientpositive/auto_join12.q.out ql/src/test/results/clientpositive/auto_join12.q.out index 6f08aa8..6e3804a 100644 --- ql/src/test/results/clientpositive/auto_join12.q.out +++ ql/src/test/results/clientpositive/auto_join12.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/auto_join13.q.out ql/src/test/results/clientpositive/auto_join13.q.out index d29818c..fa03d2c 100644 --- ql/src/test/results/clientpositive/auto_join13.q.out +++ ql/src/test/results/clientpositive/auto_join13.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -88,30 +88,27 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col1, _col2 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(_col2,_col1) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col2,_col1) (type: int) + Group By Operator + aggregations: sum(_col0) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/auto_join16.q.out ql/src/test/results/clientpositive/auto_join16.q.out index 38738ed..7f5d576 100644 --- ql/src/test/results/clientpositive/auto_join16.q.out +++ ql/src/test/results/clientpositive/auto_join16.q.out @@ -32,7 +32,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and value is not null) and key is not null) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -50,7 +50,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and value is not null) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/auto_join2.q.out ql/src/test/results/clientpositive/auto_join2.q.out index ce40ff3..26d16ee 100644 --- ql/src/test/results/clientpositive/auto_join2.q.out +++ ql/src/test/results/clientpositive/auto_join2.q.out @@ -51,7 +51,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -83,29 +83,26 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 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 - name: default.dest_j2 + 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.dest_j2 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/auto_join33.q.out ql/src/test/results/clientpositive/auto_join33.q.out index 8b13bd0..b7aed2c 100644 --- ql/src/test/results/clientpositive/auto_join33.q.out +++ ql/src/test/results/clientpositive/auto_join33.q.out @@ -34,7 +34,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) + 1.0) < 10.0) and key is not null) and (UDFToDouble(key) + 1.0) is not null) (type: boolean) + predicate: (((UDFToDouble(key) + 1.0) < 10.0) and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -42,8 +42,8 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 (UDFToDouble(_col0) + 1.0) (type: double) - 1 (UDFToDouble(_col0) + 2.0) (type: double) + 0 (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + 1 (UDFToDouble(_col0) + UDFToDouble(2)) (type: double) Stage: Stage-3 Map Reduce @@ -52,7 +52,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) + 2.0) < 10.0) and key is not null) and (UDFToDouble(key) + 2.0) is not null) (type: boolean) + predicate: (((UDFToDouble(key) + 2.0) < 10.0) and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -62,8 +62,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) + 1.0) (type: double) - 1 (UDFToDouble(_col0) + 2.0) (type: double) + 0 (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + 1 (UDFToDouble(_col0) + UDFToDouble(2)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/auto_join8.q.out ql/src/test/results/clientpositive/auto_join8.q.out index 80dd575..fa9d524 100644 --- ql/src/test/results/clientpositive/auto_join8.q.out +++ ql/src/test/results/clientpositive/auto_join8.q.out @@ -55,7 +55,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -73,7 +73,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/auto_join_filters.q.out ql/src/test/results/clientpositive/auto_join_filters.q.out index e0ed373..2fdf470 100644 --- ql/src/test/results/clientpositive/auto_join_filters.q.out +++ ql/src/test/results/clientpositive/auto_join_filters.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -300,7 +300,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in2.txt' into table sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_input2 -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -310,7 +310,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -320,7 +320,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/auto_join_nulls.q.out ql/src/test/results/clientpositive/auto_join_nulls.q.out index 954bf06..4af5535 100644 --- ql/src/test/results/clientpositive/auto_join_nulls.q.out +++ ql/src/test/results/clientpositive/auto_join_nulls.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/auto_join_stats.q.out ql/src/test/results/clientpositive/auto_join_stats.q.out index feb8186..9d9e111 100644 --- ql/src/test/results/clientpositive/auto_join_stats.q.out +++ ql/src/test/results/clientpositive/auto_join_stats.q.out @@ -91,15 +91,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -115,7 +112,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -192,15 +189,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -246,15 +240,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -361,15 +352,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -388,7 +376,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -403,7 +391,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -426,24 +414,21 @@ STAGE PLANS: 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 665 Data size: 7069 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 + 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 Local Work: Map Reduce Local Work @@ -491,15 +476,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Local Work: Map Reduce Local Work @@ -545,15 +527,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/auto_join_stats2.q.out ql/src/test/results/clientpositive/auto_join_stats2.q.out index e0d0146..007ea03 100644 --- ql/src/test/results/clientpositive/auto_join_stats2.q.out +++ ql/src/test/results/clientpositive/auto_join_stats2.q.out @@ -60,7 +60,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -92,24 +92,21 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 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 + 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 Local Work: Map Reduce Local Work @@ -198,7 +195,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -213,7 +210,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -245,9 +242,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -255,25 +257,14 @@ STAGE PLANS: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 665 Data size: 7069 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 + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 665 Data size: 7069 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 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/auto_join_without_localtask.q.out ql/src/test/results/clientpositive/auto_join_without_localtask.q.out index c63016d..d40b165 100644 --- ql/src/test/results/clientpositive/auto_join_without_localtask.q.out +++ ql/src/test/results/clientpositive/auto_join_without_localtask.q.out @@ -704,7 +704,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -889,7 +889,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -937,7 +937,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out index 096f5d4..e7c915e 100644 --- ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/auto_smb_mapjoin_14.q.out @@ -904,14 +904,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -922,14 +919,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out index 30853c4..69ae0bf 100644 --- ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out +++ ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out @@ -138,7 +138,7 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_medium@ds=2008-04-08 -Warning: Map Join MAPJOIN[36][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key @@ -697,7 +697,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[36][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big diff --git ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out index 3e8dbcf..cb87f76 100644 --- ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out +++ ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out @@ -430,7 +430,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -451,7 +451,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -821,7 +821,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -842,7 +842,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out index e6c2832..9c2c55d 100644 --- ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out +++ ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out @@ -1085,13 +1085,10 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Stage: Stage-2 Map Reduce @@ -1106,25 +1103,22 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out index 5c09fe0..663f005 100644 --- ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out +++ ql/src/test/results/clientpositive/cbo_rp_auto_join1.q.out @@ -746,7 +746,7 @@ STAGE PLANS: alias: subq2:subq1:a Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) + predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) @@ -867,7 +867,7 @@ STAGE PLANS: alias: subq2:subq1:a Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) + predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) @@ -1450,7 +1450,7 @@ STAGE PLANS: alias: a:subq2:subq1:a Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) + predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) diff --git ql/src/test/results/clientpositive/cbo_rp_join0.q.out ql/src/test/results/clientpositive/cbo_rp_join0.q.out index 3c6bb73..64bc50d 100644 --- ql/src/test/results/clientpositive/cbo_rp_join0.q.out +++ ql/src/test/results/clientpositive/cbo_rp_join0.q.out @@ -714,19 +714,16 @@ STAGE PLANS: TableScan alias: cbo_t4:cbo_t1 Statistics: Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string), c_int (type: int) - outputColumnNames: key, c_int - Statistics: Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: c_int (type: int) + Select Operator + expressions: key (type: string), c_int (type: int) + outputColumnNames: key, c_int + Statistics: Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: c_int (type: int) Reduce Operator Tree: Join Operator condition map: @@ -739,14 +736,14 @@ STAGE PLANS: 2 key (type: string) 3 key (type: string) outputColumnNames: key, c_int, key0, c_int0, key1, c_int2 - Statistics: Num rows: 1458 Data size: 389286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1620 Data size: 432540 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), c_int (type: int), key0 (type: string), c_int0 (type: int), key1 (type: string), c_int2 (type: int) outputColumnNames: key, c_int, p, q, x, b - Statistics: Num rows: 1458 Data size: 389286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1620 Data size: 432540 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1458 Data size: 389286 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1620 Data size: 432540 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/cbo_rp_join1.q.out ql/src/test/results/clientpositive/cbo_rp_join1.q.out index e770028..da286e9 100644 --- ql/src/test/results/clientpositive/cbo_rp_join1.q.out +++ ql/src/test/results/clientpositive/cbo_rp_join1.q.out @@ -31,12 +31,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = 40) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: @@ -45,12 +45,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = 40) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: @@ -136,12 +136,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key = 40) and (value = 40)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), 40 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col1 = 40) and (_col0 = 40)) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: @@ -150,12 +150,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = 40) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: @@ -240,12 +240,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = 40) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) @@ -256,12 +256,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 40) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 40 (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 = 40) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) @@ -348,12 +348,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key > 40) and (value > 50)) and (key = value)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col0 = _col1) and (_col1 > 50)) and (_col0 > 40)) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: @@ -362,12 +362,12 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key > 40) and (value > 50)) and (key = value)) (type: boolean) - Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: key (type: int), value (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((_col0 = _col1) and (_col1 > 50)) and (_col0 > 40)) (type: boolean) Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: diff --git ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out index b14caa8..79f76bf 100644 --- ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out +++ ql/src/test/results/clientpositive/cbo_rp_lineage2.q.out @@ -10,7 +10,7 @@ PREHOOK: query: select * from src1 where key is not null and value is not null l PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","database":"default","hash":"b5b224847b2333e790a2c229434a04c8","queryText":"select * from src1 where key is not null and value is not null limit 3","edges":[],"vertices":[]} +{"version":"1.0","engine":"mr","database":"default","hash":"b5b224847b2333e790a2c229434a04c8","queryText":"select * from src1 where key is not null and value is not null limit 3","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2,3],"targets":[0,1],"expression":"(src1.key is not null and src1.value is not null)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"src1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"src1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 238 val_238 311 val_311 @@ -485,7 +485,7 @@ PREHOOK: query: select * from src1 where length(key) > 2 PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","database":"default","hash":"4028c94d222d5dd221f651d414386972","queryText":"select * from src1 where length(key) > 2","edges":[],"vertices":[]} +{"version":"1.0","engine":"mr","database":"default","hash":"4028c94d222d5dd221f651d414386972","queryText":"select * from src1 where length(key) > 2","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0,1],"expression":"(length(src1.key) > 2)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"src1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"src1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 238 val_238 311 val_311 255 val_255 @@ -503,7 +503,7 @@ PREHOOK: query: select * from src1 where length(key) > 2 and value > 'a' PREHOOK: type: QUERY PREHOOK: Input: default@src1 #### A masked pattern was here #### -{"version":"1.0","engine":"mr","database":"default","hash":"5727531f7743cfcd60d634d8c835515f","queryText":"select * from src1 where length(key) > 2 and value > 'a'","edges":[],"vertices":[]} +{"version":"1.0","engine":"mr","database":"default","hash":"5727531f7743cfcd60d634d8c835515f","queryText":"select * from src1 where length(key) > 2 and value > 'a'","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2,3],"targets":[0,1],"expression":"((length(src1.key) > 2) and (src1.value > 'a'))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"src1.key"},{"id":1,"vertexType":"COLUMN","vertexId":"src1.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]} 238 val_238 311 val_311 255 val_255 @@ -593,7 +593,7 @@ PREHOOK: Input: default@dept PREHOOK: Input: default@emp PREHOOK: Input: default@project PREHOOK: Output: default@tgt -{"version":"1.0","engine":"mr","database":"default","hash":"f59797e0422d2e51515063374dfac361","queryText":"INSERT INTO TABLE tgt\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept d ON d.dept_id = em.dept_id\n ) emd JOIN project p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.emp_id is not null and emd:em:e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.emp_id = emd:em:m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"emd:em:m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12,9],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.dept_id = emd:d.dept_id AND emd:em:e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"emd:d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept.dept_name"},{"id":7,"vertexType":"COLUMN","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept.dept_id"}]} +{"version":"1.0","engine":"mr","database":"default","hash":"f59797e0422d2e51515063374dfac361","queryText":"INSERT INTO TABLE tgt\nSELECT emd.dept_name, emd.name, emd.emp_id, emd.mgr_id, p.project_id, p.project_name\nFROM (\n SELECT d.dept_name, em.name, em.emp_id, em.mgr_id, em.dept_id\n FROM (\n SELECT e.name, e.dept_id, e.emp_id emp_id, m.emp_id mgr_id\n FROM emp e JOIN emp m ON e.emp_id = m.emp_id\n ) em\n JOIN dept d ON d.dept_id = em.dept_id\n ) emd JOIN project p ON emd.dept_id = p.project_id","edges":[{"sources":[6],"targets":[0],"edgeType":"PROJECTION"},{"sources":[7],"targets":[1],"edgeType":"PROJECTION"},{"sources":[8],"targets":[2,3],"edgeType":"PROJECTION"},{"sources":[9],"targets":[4],"edgeType":"PROJECTION"},{"sources":[10],"targets":[5],"edgeType":"PROJECTION"},{"sources":[8,11],"targets":[0,1,2,3,4,5],"expression":"(e.emp_id is not null and e.dept_id is not null)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.emp_id = emd:em:m.emp_id)","edgeType":"PREDICATE"},{"sources":[8],"targets":[0,1,2,3,4,5],"expression":"m.emp_id is not null","edgeType":"PREDICATE"},{"sources":[11,12,9],"targets":[0,1,2,3,4,5],"expression":"(emd:em:e.dept_id = emd:d.dept_id AND emd:em:e.dept_id = p.project_id)","edgeType":"PREDICATE"},{"sources":[12],"targets":[0,1,2,3,4,5],"expression":"d.dept_id is not null","edgeType":"PREDICATE"},{"sources":[9],"targets":[0,1,2,3,4,5],"expression":"p.project_id is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.tgt.dept_name"},{"id":1,"vertexType":"COLUMN","vertexId":"default.tgt.name"},{"id":2,"vertexType":"COLUMN","vertexId":"default.tgt.emp_id"},{"id":3,"vertexType":"COLUMN","vertexId":"default.tgt.mgr_id"},{"id":4,"vertexType":"COLUMN","vertexId":"default.tgt.proj_id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.tgt.proj_name"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dept.dept_name"},{"id":7,"vertexType":"COLUMN","vertexId":"default.emp.name"},{"id":8,"vertexType":"COLUMN","vertexId":"default.emp.emp_id"},{"id":9,"vertexType":"COLUMN","vertexId":"default.project.project_id"},{"id":10,"vertexType":"COLUMN","vertexId":"default.project.project_name"},{"id":11,"vertexType":"COLUMN","vertexId":"default.emp.dept_id"},{"id":12,"vertexType":"COLUMN","vertexId":"default.dept.dept_id"}]} PREHOOK: query: drop table if exists dest_l2 PREHOOK: type: DROPTABLE PREHOOK: query: create table dest_l2 (id int, c1 tinyint, c2 int, c3 bigint) stored as textfile diff --git ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out index 2630537..6be2546 100644 --- ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out +++ ql/src/test/results/clientpositive/cbo_rp_outer_join_ppr.q.java1.7.out @@ -398,13 +398,13 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: key, value, key0, value0 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key0) > 15.0)) and (UDFToDouble(key0) < 25.0)) (type: boolean) - Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) - outputColumnNames: key, value, key0, value0 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0) and (UDFToDouble(key0) > 15.0) and (UDFToDouble(key0) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -780,13 +780,13 @@ STAGE PLANS: 1 key (type: string) outputColumnNames: key, value, key0, value0 Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) - Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) - outputColumnNames: key, value, key0, value0 + Select Operator + expressions: key (type: string), value (type: string), key0 (type: string), value0 (type: string) + outputColumnNames: key, value, key0, value0 + Statistics: Num rows: 122 Data size: 1296 Basic stats: COMPLETE Column stats: NONE + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/constprog_partitioner.q.out ql/src/test/results/clientpositive/constprog_partitioner.q.out index 08c0aeb..a379c91 100644 --- ql/src/test/results/clientpositive/constprog_partitioner.q.out +++ ql/src/test/results/clientpositive/constprog_partitioner.q.out @@ -124,7 +124,7 @@ STAGE PLANS: alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + predicate: ((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) diff --git ql/src/test/results/clientpositive/cross_join.q.out ql/src/test/results/clientpositive/cross_join.q.out index f36496e..0438336 100644 --- ql/src/test/results/clientpositive/cross_join.q.out +++ ql/src/test/results/clientpositive/cross_join.q.out @@ -179,7 +179,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain select src.key from src join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src join src src2 @@ -242,7 +242,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain select src.key from src cross join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src cross join src src2 diff --git ql/src/test/results/clientpositive/cross_product_check_1.q.out ql/src/test/results/clientpositive/cross_product_check_1.q.out index e7d6900..d9143c8 100644 --- ql/src/test/results/clientpositive/cross_product_check_1.q.out +++ ql/src/test/results/clientpositive/cross_product_check_1.q.out @@ -86,7 +86,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -190,7 +190,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -446,7 +446,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/cross_product_check_2.q.out ql/src/test/results/clientpositive/cross_product_check_2.q.out index df438c9..04dbc76 100644 --- ql/src/test/results/clientpositive/cross_product_check_2.q.out +++ ql/src/test/results/clientpositive/cross_product_check_2.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -93,7 +93,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -187,7 +187,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-5:MAPRED' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -323,8 +323,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-5:MAPRED' is a cross product -Warning: Map Join MAPJOIN[29][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-5:MAPRED' is a cross product +Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 @@ -446,9 +446,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[50][bigTable=?] in task 'Stage-7:MAPRED' is a cross product -Warning: Map Join MAPJOIN[43][bigTable=?] in task 'Stage-6:MAPRED' is a cross product -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[47][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[40][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index b85d387..3153c7e 100644 --- ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -1080,14 +1080,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator @@ -1317,14 +1317,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/explain_logical.q.out ql/src/test/results/clientpositive/explain_logical.q.out index d302918..8124b7a 100644 --- ql/src/test/results/clientpositive/explain_logical.q.out +++ ql/src/test/results/clientpositive/explain_logical.q.out @@ -361,19 +361,19 @@ $hdt$_0:s1 TableScan (TS_0) alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_13) + Filter Operator (FIL_11) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_2) expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_7) + Reduce Output Operator (RS_6) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_10) + Join Operator (JOIN_8) condition map: Inner Join 0 to 1 keys: @@ -381,11 +381,11 @@ $hdt$_0:s1 1 _col0 (type: string) outputColumnNames: _col0, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_11) + Select Operator (SEL_9) expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_12) + File Output Operator (FS_10) compressed: false Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE table: @@ -396,20 +396,20 @@ $hdt$_1:s2 TableScan (TS_3) alias: s2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_14) + Filter Operator (FIL_12) predicate: key is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_5) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_9) + Reduce Output Operator (RS_7) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_10) + Join Operator (JOIN_8) condition map: Inner Join 0 to 1 keys: @@ -507,19 +507,19 @@ $hdt$_0:srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_13) + Filter Operator (FIL_11) predicate: key is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_2) expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_7) + Reduce Output Operator (RS_6) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_10) + Join Operator (JOIN_8) condition map: Inner Join 0 to 1 keys: @@ -527,11 +527,11 @@ $hdt$_0:srcpart 1 _col0 (type: string) outputColumnNames: _col0, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_11) + Select Operator (SEL_9) expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_12) + File Output Operator (FS_10) compressed: false Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE table: @@ -542,20 +542,20 @@ $hdt$_1:src2 TableScan (TS_3) alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_14) + Filter Operator (FIL_12) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_5) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_9) + Reduce Output Operator (RS_7) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_10) + Join Operator (JOIN_8) condition map: Inner Join 0 to 1 keys: @@ -589,20 +589,20 @@ $hdt$_0:srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_18) + Filter Operator (FIL_15) predicate: key is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_2) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_10) + Reduce Output Operator (RS_9) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_15) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 Inner Join 0 to 2 @@ -612,11 +612,11 @@ $hdt$_0:srcpart 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_16) + Select Operator (SEL_13) expressions: _col2 (type: string), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_17) + File Output Operator (FS_14) compressed: false Statistics: Num rows: 4400 Data size: 46745 Basic stats: COMPLETE Column stats: NONE table: @@ -627,19 +627,19 @@ $hdt$_1:src TableScan (TS_3) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_19) + Filter Operator (FIL_16) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_5) expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_12) + Reduce Output Operator (RS_10) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Join Operator (JOIN_15) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 Inner Join 0 to 2 @@ -653,20 +653,20 @@ $hdt$_2:src TableScan (TS_6) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_20) + Filter Operator (FIL_17) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_8) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_14) + Reduce Output Operator (RS_11) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_15) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 Inner Join 0 to 2 @@ -804,7 +804,7 @@ $hdt$_0:src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_19) + Filter Operator (FIL_17) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator (GBY_3) @@ -825,13 +825,13 @@ $hdt$_0:src mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_11) + Reduce Output Operator (RS_10) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Join Operator (JOIN_14) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 keys: @@ -839,20 +839,20 @@ $hdt$_0:src 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator (SEL_15) + Select Operator (SEL_13) expressions: _col0 (type: string), _col1 (type: bigint), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_16) + Reduce Output Operator (RS_14) key expressions: _col0 (type: string) sort order: + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: string) - Select Operator (SEL_17) + Select Operator (SEL_15) expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_18) + File Output Operator (FS_16) compressed: false Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: @@ -863,20 +863,20 @@ $hdt$_1:src TableScan (TS_7) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator (FIL_20) + Filter Operator (FIL_18) predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_9) expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_13) + Reduce Output Operator (RS_11) key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Join Operator (JOIN_14) + Join Operator (JOIN_12) condition map: Inner Join 0 to 1 keys: diff --git ql/src/test/results/clientpositive/filter_cond_pushdown.q.out ql/src/test/results/clientpositive/filter_cond_pushdown.q.out index b1cfb25..5e0edbc 100644 --- ql/src/test/results/clientpositive/filter_cond_pushdown.q.out +++ ql/src/test/results/clientpositive/filter_cond_pushdown.q.out @@ -283,7 +283,7 @@ STAGE PLANS: alias: t2 Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), c_int (type: int), c_float (type: float) diff --git ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out index 231d98f..171a19f 100644 --- ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out +++ ql/src/test/results/clientpositive/fold_eq_with_case_when.q.out @@ -104,7 +104,7 @@ STAGE PLANS: predicate: (key = '238') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '238' (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -176,7 +176,7 @@ STAGE PLANS: predicate: (key = '238') (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '238' (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -209,7 +209,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE (key) WHEN ('238') THEN (CASE WHEN ((key <> '238')) THEN (true) WHEN ((key = '23')) THEN (true) END) END (type: int) + predicate: CASE (key) WHEN ('238') THEN (CASE WHEN ((key <> '238')) THEN ((1 = 1)) WHEN ((key = '23')) THEN ((1 = 1)) END) END (type: int) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/fouter_join_ppr.q.out ql/src/test/results/clientpositive/fouter_join_ppr.q.out index 56c5176..f701122 100644 --- ql/src/test/results/clientpositive/fouter_join_ppr.q.out +++ ql/src/test/results/clientpositive/fouter_join_ppr.q.out @@ -398,7 +398,7 @@ STAGE PLANS: Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col2) > 15.0)) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -867,7 +867,7 @@ STAGE PLANS: Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col3) > 15.0)) and (UDFToDouble(_col3) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col3) > 15.0) and (UDFToDouble(_col3) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string) diff --git ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out index 3db64e6..66acb74 100644 --- ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out +++ ql/src/test/results/clientpositive/groupby_grouping_sets4.q.out @@ -74,16 +74,19 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -148,16 +151,19 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -274,16 +280,19 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -372,16 +381,19 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE pruneGroupingSetId: true - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2 Data size: 72 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/groupby_position.q.out ql/src/test/results/clientpositive/groupby_position.q.out index ade6cb5..3222a60 100644 --- ql/src/test/results/clientpositive/groupby_position.q.out +++ ql/src/test/results/clientpositive/groupby_position.q.out @@ -647,7 +647,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/having2.q.out ql/src/test/results/clientpositive/having2.q.out index 65d97d0..eaacc71 100644 --- ql/src/test/results/clientpositive/having2.q.out +++ ql/src/test/results/clientpositive/having2.q.out @@ -345,7 +345,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col1 <= 4074689.000000041) and (_col2 <= 822.0)) and (_col3 > 4)) (type: boolean) + predicate: ((_col1 <= 4074689.000000041) and (_col2 <= 822.0) and (_col3 > 4)) (type: boolean) Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -467,20 +467,24 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((_col1 <= 4074689.000000041) and (_col2 <= 822.0)) and (_col3 > 4)) (type: boolean) - Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double), _col3 (type: bigint) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 4074689.000000041) and (_col3 <= 822.0) and (_col4 > 4)) (type: boolean) Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 106 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 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 106 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 @@ -590,20 +594,24 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((_col1 <= 4074689.000000041) and (_col2 <= 822.0)) and (_col3 > 4)) (type: boolean) - Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col0 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: double), _col2 (type: double), _col3 (type: bigint) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 4074689.000000041) and (_col3 <= 822.0) and (_col4 > 4)) (type: boolean) Statistics: Num rows: 10 Data size: 106 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 106 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 + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 106 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 diff --git ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out index 61a5fa4..325ed2c 100644 --- ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out +++ ql/src/test/results/clientpositive/infer_bucket_sort_map_operators.q.out @@ -245,7 +245,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 is not null and UDFToDouble(_col1) is not null) (type: boolean) + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) @@ -257,7 +257,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) diff --git ql/src/test/results/clientpositive/join12.q.out ql/src/test/results/clientpositive/join12.q.out index 672777f..397e2e3 100644 --- ql/src/test/results/clientpositive/join12.q.out +++ ql/src/test/results/clientpositive/join12.q.out @@ -36,7 +36,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/join13.q.out ql/src/test/results/clientpositive/join13.q.out index ff873e4..3ccff63 100644 --- ql/src/test/results/clientpositive/join13.q.out +++ ql/src/test/results/clientpositive/join13.q.out @@ -73,15 +73,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -97,7 +94,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/join16.q.out ql/src/test/results/clientpositive/join16.q.out index de88802..c525eb5 100644 --- ql/src/test/results/clientpositive/join16.q.out +++ ql/src/test/results/clientpositive/join16.q.out @@ -14,7 +14,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and value is not null) and key is not null) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -29,7 +29,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and value is not null) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/join2.q.out ql/src/test/results/clientpositive/join2.q.out index ef35f8f..1ad7285 100644 --- ql/src/test/results/clientpositive/join2.q.out +++ ql/src/test/results/clientpositive/join2.q.out @@ -67,15 +67,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -91,7 +88,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/join8.q.out ql/src/test/results/clientpositive/join8.q.out index 493341d..bb3cb8f 100644 --- ql/src/test/results/clientpositive/join8.q.out +++ ql/src/test/results/clientpositive/join8.q.out @@ -53,7 +53,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -69,7 +69,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out index 517345e..2ce9a87 100644 --- ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out +++ ql/src/test/results/clientpositive/join_cond_pushdown_1.q.out @@ -281,7 +281,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey = 1 and p3.p_name = p2.p_name PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out index a96e134..a361439 100644 --- ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out +++ ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out @@ -287,7 +287,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey = 1 and p3.p_name = p2.p_name diff --git ql/src/test/results/clientpositive/join_reorder.q.out ql/src/test/results/clientpositive/join_reorder.q.out index f71f4e1..c79e36f 100644 --- ql/src/test/results/clientpositive/join_reorder.q.out +++ ql/src/test/results/clientpositive/join_reorder.q.out @@ -68,7 +68,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -84,16 +84,16 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToDouble(key) + 1.0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (UDFToDouble(_col0) + 1.0) (type: double) + key expressions: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) + 1.0) (type: double) + Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reduce Operator Tree: @@ -102,7 +102,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 (UDFToDouble(_col0) + 1.0) (type: double) + 1 (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 79348f3..2b6dbbf 100644 --- ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -1449,21 +1449,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col2 (type: string) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: b - Partition key expr: ds - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 2 Execution mode: llap Map 2 Map Operator Tree: diff --git ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out index 824f0fd..4f04960 100644 --- ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out +++ ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out @@ -260,7 +260,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -279,7 +279,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -640,7 +640,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: value (type: string) @@ -659,7 +659,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/llap/constprog_dpp.q.out ql/src/test/results/clientpositive/llap/constprog_dpp.q.out index a1addb7..50a271c 100644 --- ql/src/test/results/clientpositive/llap/constprog_dpp.q.out +++ ql/src/test/results/clientpositive/llap/constprog_dpp.q.out @@ -55,7 +55,7 @@ Stage-0 compressed:false Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL 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"} - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0"] diff --git ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out index c6dc55c..c28bf93 100644 --- ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out @@ -238,21 +238,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -463,6 +448,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -493,21 +479,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Map 6 Map Operator Tree: @@ -527,21 +498,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -810,6 +766,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -839,36 +796,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -1104,21 +1031,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -1322,29 +1234,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1355,21 +1264,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -1451,20 +1345,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1484,21 +1375,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -1580,29 +1456,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1694,20 +1567,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and (UDFToDouble(hr) * 2.0) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1735,7 +1605,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1821,29 +1691,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) + sort order: + + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - sort order: + - Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1854,21 +1721,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToString(_col0) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -2046,21 +1898,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2098,7 +1935,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2196,7 +2033,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2238,6 +2075,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2267,36 +2105,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -2410,21 +2218,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -2501,21 +2294,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 Execution mode: llap Map 4 Map Operator Tree: @@ -2624,21 +2402,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -2706,6 +2469,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2735,30 +2499,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE @@ -2866,10 +2615,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -3117,21 +2866,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: uber Reduce Operator Tree: @@ -3153,21 +2887,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3323,21 +3042,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: uber Reduce Operator Tree: @@ -3359,21 +3063,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3426,16 +3115,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 10 Map Operator Tree: @@ -3462,16 +3155,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 7 Map Operator Tree: @@ -3513,36 +3210,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Reducer 2 Execution mode: uber Reduce Operator Tree: @@ -3608,36 +3275,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Union 3 Vertex: Union 3 Union 9 @@ -3735,21 +3372,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -3829,6 +3451,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3883,21 +3506,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Map 4 Map Operator Tree: @@ -3917,21 +3525,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4011,6 +3604,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -4054,36 +3648,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4203,21 +3767,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4269,43 +3818,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -4316,21 +3862,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4393,34 +3924,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) - 1 _col0 (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) * 2.0) (type: double) + 1 _col0 (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: @@ -4440,21 +3968,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4710,21 +4223,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber @@ -4946,6 +4444,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4999,30 +4498,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE @@ -5095,10 +4579,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -5326,21 +4810,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 7 Execution mode: uber Reduce Operator Tree: @@ -5362,21 +4831,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 5 Vertex: Union 5 @@ -5461,43 +4915,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_orc - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), UDFToDouble(_col1) (type: double) - 1 _col0 (type: string), UDFToDouble(_col2) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + predicate: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5508,36 +4959,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: ds - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: UDFToDouble(_col2) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber diff --git ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out index 0bd466e..f2ed9a1 100644 --- ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out +++ ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out @@ -217,21 +217,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -755,21 +740,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: llap @@ -907,21 +877,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg_01 - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Execution mode: llap Map 4 Map Operator Tree: @@ -970,21 +925,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg_01 - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 4 Execution mode: llap Union 2 Vertex: Union 2 diff --git ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out index bf82492..9fac69f 100644 --- ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out +++ ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out @@ -140,7 +140,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: decimal(6,2)) Statistics: Num rows: 1049 Data size: 117488 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(4,0)) Execution mode: llap Reducer 2 Execution mode: uber diff --git ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index 09b9ca4..56f0165 100644 --- ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -63,7 +63,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -81,7 +81,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -235,7 +235,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -254,7 +254,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -272,7 +272,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -424,7 +424,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -443,7 +443,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -461,7 +461,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index 051fbe3..9eef871 100644 --- ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -63,7 +63,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -81,7 +81,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -235,7 +235,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -254,7 +254,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -272,7 +272,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -424,7 +424,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -443,7 +443,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -461,7 +461,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index 5ceefe1..fbd6e28 100644 --- ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -238,21 +238,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -463,6 +448,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -493,21 +479,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Map 6 Map Operator Tree: @@ -527,21 +498,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -810,6 +766,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -839,36 +796,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -1104,21 +1031,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -1322,29 +1234,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1355,21 +1264,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -1451,20 +1345,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1484,21 +1375,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -1580,29 +1456,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1694,20 +1567,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and (UDFToDouble(hr) * 2.0) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1735,7 +1605,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1821,29 +1691,26 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) + sort order: + + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - sort order: + - Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1854,21 +1721,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToString(_col0) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -2046,21 +1898,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2098,7 +1935,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2196,7 +2033,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2238,6 +2075,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2267,36 +2105,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -2410,21 +2218,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -2501,21 +2294,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 Execution mode: vectorized, llap Map 4 Map Operator Tree: @@ -2624,21 +2402,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -2706,6 +2469,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2735,30 +2499,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE @@ -2866,10 +2615,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -3117,21 +2866,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: vectorized, uber Reduce Operator Tree: @@ -3153,21 +2887,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3323,21 +3042,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: vectorized, uber Reduce Operator Tree: @@ -3359,21 +3063,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3426,16 +3115,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 10 Map Operator Tree: @@ -3462,16 +3155,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 7 Map Operator Tree: @@ -3513,36 +3210,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Reducer 2 Execution mode: vectorized, uber Reduce Operator Tree: @@ -3608,36 +3275,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Union 3 Vertex: Union 3 Union 9 @@ -3735,21 +3372,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -3829,6 +3451,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3883,21 +3506,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Map 4 Map Operator Tree: @@ -3917,21 +3525,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4011,6 +3604,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -4054,36 +3648,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4203,21 +3767,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4269,43 +3818,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -4316,21 +3862,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4393,34 +3924,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) - 1 _col0 (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) * 2.0) (type: double) + 1 _col0 (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: @@ -4440,21 +3968,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4710,21 +4223,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4946,6 +4444,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4999,30 +4498,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized, llap Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE @@ -5095,10 +4579,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -5326,21 +4810,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 7 Execution mode: vectorized, uber Reduce Operator Tree: @@ -5362,21 +4831,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 5 Vertex: Union 5 @@ -5461,43 +4915,40 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_orc - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), UDFToDouble(_col1) (type: double) - 1 _col0 (type: string), UDFToDouble(_col2) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + predicate: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5508,36 +4959,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: ds - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: UDFToDouble(_col2) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber diff --git ql/src/test/results/clientpositive/louter_join_ppr.q.out ql/src/test/results/clientpositive/louter_join_ppr.q.out index 84dce67..b80c68e 100644 --- ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -993,7 +993,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 14c6f18..416634b 100644 --- ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -512,7 +512,7 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_450') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_450') and key is not null) (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/multiMapJoin1.q.out ql/src/test/results/clientpositive/multiMapJoin1.q.out index 02b2707..e2efec0 100644 --- ql/src/test/results/clientpositive/multiMapJoin1.q.out +++ ql/src/test/results/clientpositive/multiMapJoin1.q.out @@ -878,8 +878,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1323,7 +1323,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col3 (type: string) Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: smalltbl2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -1405,8 +1405,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1461,8 +1461,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -1744,8 +1744,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -2038,8 +2038,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -2390,8 +2390,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2835,7 +2835,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col3 (type: string) Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) TableScan alias: smalltbl2 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -2917,8 +2917,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -2973,8 +2973,8 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index 9a24ad8..83be55d 100644 --- ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -188,7 +188,7 @@ POSTHOOK: Input: default@src1 406 val_406 25 66 val_66 25 98 val_98 25 -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- Then, we convert the join to MapJoin. EXPLAIN SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count @@ -296,7 +296,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * diff --git ql/src/test/results/clientpositive/orc_llap.q.out ql/src/test/results/clientpositive/orc_llap.q.out index f67fcc6..7ab3d14 100644 --- ql/src/test/results/clientpositive/orc_llap.q.out +++ ql/src/test/results/clientpositive/orc_llap.q.out @@ -121,7 +121,7 @@ POSTHOOK: Output: default@orc_llap_small POSTHOOK: Lineage: orc_llap_small.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] POSTHOOK: Lineage: orc_llap_small.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] POSTHOOK: Lineage: orc_llap_small.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- Cross join with no projection - do it on small table explain select count(1) from orc_llap_small y join orc_llap_small x @@ -202,7 +202,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: select count(1) from orc_llap_small y join orc_llap_small x PREHOOK: type: QUERY PREHOOK: Input: default@orc_llap_small @@ -636,7 +636,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@llap_temp_table #### A masked pattern was here #### -735462183586256 -Warning: Map Join MAPJOIN[12][bigTable=?] in task 'Stage-4:MAPRED' is a cross product +Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-4:MAPRED' is a cross product PREHOOK: query: -- multi-stripe test insert into table orc_llap select ctinyint + i, csmallint + i, cint + i, cbigint + i, cfloat + i, cdouble + i, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 diff --git ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out index f6d8388..1d4f9d8 100644 --- ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out +++ ql/src/test/results/clientpositive/orc_predicate_pushdown.q.out @@ -768,7 +768,7 @@ STAGE PLANS: alias: orc_pred Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -834,10 +834,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: orc_pred - filterExpr: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + filterExpr: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 4 Data size: 1186 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) diff --git ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out index b257221..66d1fb3 100644 --- ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out +++ ql/src/test/results/clientpositive/outer_join_ppr.q.java1.7.out @@ -400,7 +400,7 @@ STAGE PLANS: Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col2) > 15.0)) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out index b322ef1..3e1413b 100644 --- ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out +++ ql/src/test/results/clientpositive/parquet_predicate_pushdown.q.out @@ -756,7 +756,7 @@ STAGE PLANS: alias: tbl_pred Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) @@ -822,10 +822,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: tbl_pred - filterExpr: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + filterExpr: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 1049 Data size: 11539 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((d >= 10.0) and (d < 12.0)) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) + predicate: (((((((d >= 10.0) and (d < 12.0)) and t is not null) and (s like '%son')) and (not (s like '%car%'))) and (t > 0)) and si BETWEEN 300 AND 400) (type: boolean) Statistics: Num rows: 4 Data size: 44 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: t (type: tinyint), si (type: smallint), d (type: double), s (type: string) diff --git ql/src/test/results/clientpositive/ppd_gby_join.q.out ql/src/test/results/clientpositive/ppd_gby_join.q.out index 09dfb82..907fb67 100644 --- ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -41,14 +41,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -59,14 +56,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ppd_join.q.out ql/src/test/results/clientpositive/ppd_join.q.out index f284237..94bee7a 100644 --- ql/src/test/results/clientpositive/ppd_join.q.out +++ ql/src/test/results/clientpositive/ppd_join.q.out @@ -38,14 +38,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -56,15 +53,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ppd_join2.q.out ql/src/test/results/clientpositive/ppd_join2.q.out index fe2ad46..6fa3e81 100644 --- ql/src/test/results/clientpositive/ppd_join2.q.out +++ ql/src/test/results/clientpositive/ppd_join2.q.out @@ -45,15 +45,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -64,15 +61,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -89,15 +83,12 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -112,14 +103,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col1 (type: string) @@ -1735,7 +1723,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and value is not null) and key is not null) (type: boolean) + predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/ppd_join3.q.out ql/src/test/results/clientpositive/ppd_join3.q.out index 64744aa..cd5b9c6 100644 --- ql/src/test/results/clientpositive/ppd_join3.q.out +++ ql/src/test/results/clientpositive/ppd_join3.q.out @@ -45,14 +45,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -63,15 +60,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -88,15 +82,12 @@ STAGE PLANS: expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce @@ -111,14 +102,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE TableScan Reduce Output Operator key expressions: _col0 (type: string) @@ -1791,7 +1779,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and (key <> '13')) and (key <> '1')) and key is not null) (type: boolean) + predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/ppd_join5.q.out ql/src/test/results/clientpositive/ppd_join5.q.out index 02ea658..b68229e 100644 --- ql/src/test/results/clientpositive/ppd_join5.q.out +++ ql/src/test/results/clientpositive/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -148,7 +148,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from ( select a.*,b.d d1,c.d d2 from @@ -271,7 +271,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from ( select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) diff --git ql/src/test/results/clientpositive/ppd_join_filter.q.out ql/src/test/results/clientpositive/ppd_join_filter.q.out index f5662c7..e3b19d4 100644 --- ql/src/test/results/clientpositive/ppd_join_filter.q.out +++ ql/src/test/results/clientpositive/ppd_join_filter.q.out @@ -215,27 +215,23 @@ STAGE PLANS: expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string,double,double + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -252,17 +248,13 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + tag: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -1051,27 +1043,23 @@ STAGE PLANS: expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col2 - columns.types string,double,double - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string,double,double + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-1 Map Reduce @@ -1088,17 +1076,13 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + tag: 0 + auto parallelism: false TableScan GatherStats: false Reduce Output Operator diff --git ql/src/test/results/clientpositive/ppd_outer_join2.q.out ql/src/test/results/clientpositive/ppd_outer_join2.q.out index c7ade80..3872ad7 100644 --- ql/src/test/results/clientpositive/ppd_outer_join2.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join2.q.out @@ -38,15 +38,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -57,15 +54,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ppd_outer_join3.q.out ql/src/test/results/clientpositive/ppd_outer_join3.q.out index 5de6823..8a7ec51 100644 --- ql/src/test/results/clientpositive/ppd_outer_join3.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join3.q.out @@ -38,15 +38,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -57,15 +54,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ppd_outer_join4.q.out ql/src/test/results/clientpositive/ppd_outer_join4.q.out index be47139..d26049e 100644 --- ql/src/test/results/clientpositive/ppd_outer_join4.q.out +++ ql/src/test/results/clientpositive/ppd_outer_join4.q.out @@ -44,14 +44,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -62,15 +59,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -81,15 +75,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: @@ -411,7 +402,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((sqrt(key) <> 13.0) and (key < '25')) and (key > '15')) and (key < '20')) and (key > '10')) and key is not null) (type: boolean) + predicate: ((((((sqrt(key) <> 13.0) and (key < '25')) and (key > '15')) and (key < '20')) and key is not null) and (key > '10')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -426,7 +417,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and (sqrt(key) <> 13.0)) and key is not null) (type: boolean) + predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/ppd_random.q.out ql/src/test/results/clientpositive/ppd_random.q.out index 5f12432..5a890c5 100644 --- ql/src/test/results/clientpositive/ppd_random.q.out +++ ql/src/test/results/clientpositive/ppd_random.q.out @@ -34,14 +34,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -52,15 +49,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ppd_repeated_alias.q.out ql/src/test/results/clientpositive/ppd_repeated_alias.q.out index 573f595..9a21b5c 100644 --- ql/src/test/results/clientpositive/ppd_repeated_alias.q.out +++ ql/src/test/results/clientpositive/ppd_repeated_alias.q.out @@ -263,7 +263,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- Q4: here, the filter c.bar should be created under the first join but above the second explain select c.foo, d.bar from (select c.foo, b.bar, c.blah from pokes c left outer join pokes b on c.foo=b.foo) c left outer join pokes d where d.foo=1 and c.bar=2 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/ppd_udf_case.q.out ql/src/test/results/clientpositive/ppd_udf_case.q.out index f466a29..2b407a6 100644 --- ql/src/test/results/clientpositive/ppd_udf_case.q.out +++ ql/src/test/results/clientpositive/ppd_udf_case.q.out @@ -43,15 +43,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + value expressions: _col1 (type: string), _col3 (type: string) TableScan alias: a Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -62,15 +59,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: string) + value expressions: _col1 (type: string), _col3 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out index 46c154b..8409350 100644 --- ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out +++ ql/src/test/results/clientpositive/ptfgroupbyjoin.q.out @@ -76,8 +76,9 @@ STAGE PLANS: TableScan alias: tlb1 Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: fkey is not null (type: boolean) + Select Operator + expressions: id (type: int), fkey (type: int) + outputColumnNames: id, fkey Statistics: Num rows: 2 Data size: 18 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: id (type: int), fkey (type: int) @@ -95,12 +96,15 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Filter Operator + predicate: _col1 is not null (type: boolean) + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -249,12 +253,12 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + Select Operator + expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: int), row_number_window_0 (type: int) - outputColumnNames: _col0, _col1, _col2 + Filter Operator + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -393,15 +397,12 @@ STAGE PLANS: Filter Operator predicate: _col1 is not null (type: boolean) Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -423,15 +424,12 @@ STAGE PLANS: expressions: fid (type: int), name (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 6 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/router_join_ppr.q.out ql/src/test/results/clientpositive/router_join_ppr.q.out index 46cdb30..ebf8c5a 100644 --- ql/src/test/results/clientpositive/router_join_ppr.q.out +++ ql/src/test/results/clientpositive/router_join_ppr.q.out @@ -1367,7 +1367,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/skewjoin.q.out ql/src/test/results/clientpositive/skewjoin.q.out index 947e67a..32803f0 100644 --- ql/src/test/results/clientpositive/skewjoin.q.out +++ ql/src/test/results/clientpositive/skewjoin.q.out @@ -768,7 +768,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and UDFToDouble(substring(value, 5)) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -783,16 +783,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and (UDFToDouble(substring(value, 5)) + 1.0) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reduce Operator Tree: @@ -802,7 +802,7 @@ STAGE PLANS: handleSkewJoin: true keys: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) - 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -954,7 +954,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/skewjoinopt18.q.out ql/src/test/results/clientpositive/skewjoinopt18.q.out index 925ebc5..9b98615 100644 --- ql/src/test/results/clientpositive/skewjoinopt18.q.out +++ ql/src/test/results/clientpositive/skewjoinopt18.q.out @@ -86,7 +86,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) @@ -102,7 +102,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_join12.q.out ql/src/test/results/clientpositive/spark/auto_join12.q.out index 3c7877f..57ae673 100644 --- ql/src/test/results/clientpositive/spark/auto_join12.q.out +++ ql/src/test/results/clientpositive/spark/auto_join12.q.out @@ -36,7 +36,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_join13.q.out ql/src/test/results/clientpositive/spark/auto_join13.q.out index b46de18..97c73f8 100644 --- ql/src/test/results/clientpositive/spark/auto_join13.q.out +++ ql/src/test/results/clientpositive/spark/auto_join13.q.out @@ -54,7 +54,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -95,32 +95,29 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col1, _col2 - input vertices: - 1 Map 4 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hash(_col2,_col1) (type: int) + outputColumnNames: _col0 Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hash(_col2,_col1) (type: int) + Group By Operator + aggregations: sum(_col0) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - mode: hash - outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 diff --git ql/src/test/results/clientpositive/spark/auto_join16.q.out ql/src/test/results/clientpositive/spark/auto_join16.q.out index 6da1c50..9b726e6 100644 --- ql/src/test/results/clientpositive/spark/auto_join16.q.out +++ ql/src/test/results/clientpositive/spark/auto_join16.q.out @@ -30,7 +30,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and value is not null) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -55,7 +55,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and value is not null) and key is not null) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_join2.q.out ql/src/test/results/clientpositive/spark/auto_join2.q.out index 10b12a9..a885837 100644 --- ql/src/test/results/clientpositive/spark/auto_join2.q.out +++ ql/src/test/results/clientpositive/spark/auto_join2.q.out @@ -49,7 +49,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -88,31 +88,28 @@ STAGE PLANS: input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 3 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col3 + input vertices: + 1 Map 3 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col3 (type: string) - outputColumnNames: _col0, _col1 + File Output Operator + compressed: false Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 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 - name: default.dest_j2 + 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.dest_j2 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/spark/auto_join8.q.out ql/src/test/results/clientpositive/spark/auto_join8.q.out index 7c4ed3a..19b10da 100644 --- ql/src/test/results/clientpositive/spark/auto_join8.q.out +++ ql/src/test/results/clientpositive/spark/auto_join8.q.out @@ -53,7 +53,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -76,7 +76,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_join_filters.q.out ql/src/test/results/clientpositive/spark/auto_join_filters.q.out index 601b27d..84810d5 100644 --- ql/src/test/results/clientpositive/spark/auto_join_filters.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_filters.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -300,7 +300,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in2.txt' into table sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_input2 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -310,7 +310,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -320,7 +320,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out index 0024b24..15f4791 100644 --- ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/spark/auto_join_stats.q.out ql/src/test/results/clientpositive/spark/auto_join_stats.q.out index e826380..2691eac 100644 --- ql/src/test/results/clientpositive/spark/auto_join_stats.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_stats.q.out @@ -48,7 +48,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -113,26 +113,23 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 - input vertices: - 1 Map 4 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 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 + 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 @@ -196,7 +193,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -214,7 +211,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -279,9 +276,16 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -290,28 +294,15 @@ STAGE PLANS: 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2 input vertices: - 1 Map 4 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 - input vertices: - 1 Map 5 - Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 665 Data size: 7069 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 + 1 Map 5 + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 665 Data size: 7069 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 diff --git ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out index 4062faf..de135aa 100644 --- ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out @@ -58,7 +58,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -97,26 +97,23 @@ STAGE PLANS: input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 - input vertices: - 1 Map 3 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 3 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 605 Data size: 6427 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 + 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 Local Work: Map Reduce Local Work @@ -200,7 +197,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -218,7 +215,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -257,9 +254,16 @@ STAGE PLANS: input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + 1 UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 3 + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -268,28 +272,15 @@ STAGE PLANS: 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col2 input vertices: - 1 Map 3 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1, _col2 - input vertices: - 1 Map 4 - Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 665 Data size: 7069 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 + 1 Map 4 + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 665 Data size: 7069 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 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out index 659c305..f055a59 100644 --- ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out +++ ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out @@ -337,7 +337,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out index 0c96d4c..4ad0bd5 100644 --- ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out @@ -938,14 +938,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -958,14 +955,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out index 89251b7..4b6affc 100644 --- ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out +++ ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out @@ -138,7 +138,7 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_medium@ds=2008-04-08 -Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key @@ -627,7 +627,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big diff --git ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out index 0609bc8..41b2b0a 100644 --- ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out +++ ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out @@ -450,7 +450,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -475,7 +475,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -867,7 +867,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -892,7 +892,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out index be42791..c5ea18d 100644 --- ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out +++ ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out @@ -1075,13 +1075,10 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1103,27 +1100,24 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 diff --git ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out index a54b03c..0df4597 100644 --- ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out +++ ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out @@ -268,7 +268,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -291,7 +291,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -670,7 +670,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: value (type: string) @@ -706,7 +706,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out index 8a6ab82..5c80b2b 100644 --- ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out +++ ql/src/test/results/clientpositive/spark/constprog_partitioner.q.out @@ -139,7 +139,7 @@ STAGE PLANS: alias: li Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + predicate: ((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) diff --git ql/src/test/results/clientpositive/spark/cross_join.q.out ql/src/test/results/clientpositive/spark/cross_join.q.out index d136913..7c8118c 100644 --- ql/src/test/results/clientpositive/spark/cross_join.q.out +++ ql/src/test/results/clientpositive/spark/cross_join.q.out @@ -203,7 +203,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select src.key from src join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src join src src2 @@ -271,7 +271,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select src.key from src cross join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src cross join src src2 diff --git ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out index 5b03dcf..0656cd5 100644 --- ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out +++ ql/src/test/results/clientpositive/spark/cross_product_check_1.q.out @@ -94,7 +94,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -198,7 +198,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -434,7 +434,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[25][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out index 93c502d..0ec321b 100644 --- ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out +++ ql/src/test/results/clientpositive/spark/cross_product_check_2.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -98,7 +98,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -205,7 +205,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -339,8 +339,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-1:MAPRED' is a cross product -Warning: Map Join MAPJOIN[25][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 @@ -460,7 +460,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out index b597ebd..9043fb1 100644 --- ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out @@ -932,14 +932,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator @@ -1015,14 +1015,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) - outputColumnNames: _col0, _col1, _col3, _col4, _col5 + expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col4 (type: double), _col5 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator - expressions: _col1 (type: int), _col0 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: double), CASE (_col5) WHEN (0) THEN (null) ELSE ((_col4 / _col5)) END (type: double) outputColumnNames: _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Reduce Output Operator diff --git ql/src/test/results/clientpositive/spark/groupby_position.q.out ql/src/test/results/clientpositive/spark/groupby_position.q.out index 81e4a1d..a691c7b 100644 --- ql/src/test/results/clientpositive/spark/groupby_position.q.out +++ ql/src/test/results/clientpositive/spark/groupby_position.q.out @@ -586,7 +586,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out index fe124c6..57a6d59 100644 --- ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out +++ ql/src/test/results/clientpositive/spark/infer_bucket_sort_map_operators.q.out @@ -209,7 +209,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col1 is not null and UDFToDouble(_col1) is not null) (type: boolean) + predicate: _col1 is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col1) (type: double) @@ -223,7 +223,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) diff --git ql/src/test/results/clientpositive/spark/join12.q.out ql/src/test/results/clientpositive/spark/join12.q.out index cca05a9..b2a0b2c 100644 --- ql/src/test/results/clientpositive/spark/join12.q.out +++ ql/src/test/results/clientpositive/spark/join12.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/join13.q.out ql/src/test/results/clientpositive/spark/join13.q.out index 6ed8ca0..5b38f8c 100644 --- ql/src/test/results/clientpositive/spark/join13.q.out +++ ql/src/test/results/clientpositive/spark/join13.q.out @@ -77,7 +77,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean) + predicate: (UDFToDouble(key) < 200.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -98,15 +98,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean) + Reduce Output Operator + key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Reducer 3 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/join16.q.out ql/src/test/results/clientpositive/spark/join16.q.out index 2c40151..bbac169 100644 --- ql/src/test/results/clientpositive/spark/join16.q.out +++ ql/src/test/results/clientpositive/spark/join16.q.out @@ -19,7 +19,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(value) < 200.0)) and value is not null) and key is not null) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -36,7 +36,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) and value is not null) (type: boolean) + predicate: (((((UDFToDouble(value) < 200.0) and (UDFToDouble(key) > 20.0)) and value is not null) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/join2.q.out ql/src/test/results/clientpositive/spark/join2.q.out index 9ee6df0..2c6311b 100644 --- ql/src/test/results/clientpositive/spark/join2.q.out +++ ql/src/test/results/clientpositive/spark/join2.q.out @@ -71,7 +71,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -93,15 +93,12 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) + Reduce Output Operator + key expressions: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) + value expressions: _col0 (type: string) Reducer 3 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/join8.q.out ql/src/test/results/clientpositive/spark/join8.q.out index bcf98c6..0516220 100644 --- ql/src/test/results/clientpositive/spark/join8.q.out +++ ql/src/test/results/clientpositive/spark/join8.q.out @@ -58,7 +58,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -76,7 +76,7 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out index e22cab5..b75d951 100644 --- ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out +++ ql/src/test/results/clientpositive/spark/join_cond_pushdown_1.q.out @@ -301,7 +301,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 on p2.p_partkey = 1 and p3.p_name = p2.p_name PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out index ae8cf04..e2886d3 100644 --- ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out +++ ql/src/test/results/clientpositive/spark/join_cond_pushdown_3.q.out @@ -307,7 +307,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[16][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part p1 join part p2 join part p3 where p2.p_partkey = 1 and p3.p_name = p2.p_name diff --git ql/src/test/results/clientpositive/spark/join_reorder.q.out ql/src/test/results/clientpositive/spark/join_reorder.q.out index 10cd56c..4933df4 100644 --- ql/src/test/results/clientpositive/spark/join_reorder.q.out +++ ql/src/test/results/clientpositive/spark/join_reorder.q.out @@ -73,7 +73,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) @@ -91,16 +91,16 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToDouble(key) + 1.0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (UDFToDouble(_col0) + 1.0) (type: double) + key expressions: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) + 1.0) (type: double) + Map-reduce partition columns: (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 2 @@ -110,7 +110,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 (UDFToDouble(_col0) + 1.0) (type: double) + 1 (UDFToDouble(_col0) + UDFToDouble(1)) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out index 767855b..78eccab 100644 --- ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out +++ ql/src/test/results/clientpositive/spark/louter_join_ppr.q.out @@ -1073,7 +1073,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out index 3a126f6..26c8958 100644 --- ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out +++ ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out @@ -532,7 +532,7 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_450') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_450') and key is not null) (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out index a3c4be7..7ac6bf8 100644 --- ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out +++ ql/src/test/results/clientpositive/spark/outer_join_ppr.q.java1.7.out @@ -412,7 +412,7 @@ STAGE PLANS: Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Filter Operator isSamplingPred: false - predicate: ((((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0)) and (UDFToDouble(_col2) > 15.0)) and (UDFToDouble(_col2) < 25.0)) (type: boolean) + predicate: ((UDFToDouble(_col0) > 10.0) and (UDFToDouble(_col0) < 20.0) and (UDFToDouble(_col2) > 15.0) and (UDFToDouble(_col2) < 25.0)) (type: boolean) Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false diff --git ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out index 08275f3..691ae3d 100644 --- ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out +++ ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out @@ -46,14 +46,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -66,14 +63,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/ppd_join.q.out ql/src/test/results/clientpositive/spark/ppd_join.q.out index 2357adc..e843826 100644 --- ql/src/test/results/clientpositive/spark/ppd_join.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join.q.out @@ -43,14 +43,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 4 Data size: 42 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -63,15 +60,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/ppd_join2.q.out ql/src/test/results/clientpositive/spark/ppd_join2.q.out index 68cbc5a..ddf93ba 100644 --- ql/src/test/results/clientpositive/spark/ppd_join2.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join2.q.out @@ -50,14 +50,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -70,15 +67,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan @@ -91,15 +85,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -138,15 +129,12 @@ STAGE PLANS: expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col3 (type: string) Stage: Stage-0 Fetch Operator @@ -1757,7 +1745,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and value is not null) and key is not null) (type: boolean) + predicate: ((((((((key <> '302') and (key <> '311')) and ((value <> 'val_50') or (key > '1'))) and (key < '400')) and (key <> '305')) and (key <> '14')) and key is not null) and value is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/ppd_join3.q.out ql/src/test/results/clientpositive/spark/ppd_join3.q.out index 573b352..074eb8a 100644 --- ql/src/test/results/clientpositive/spark/ppd_join3.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join3.q.out @@ -50,14 +50,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -70,14 +67,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map 5 Map Operator Tree: TableScan @@ -90,15 +84,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -137,15 +128,12 @@ STAGE PLANS: expressions: _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col2 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: string) + value expressions: _col2 (type: string) Stage: Stage-0 Fetch Operator @@ -1813,7 +1801,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and (key <> '13')) and (key <> '1')) and key is not null) (type: boolean) + predicate: (((((((((key <> '11') and (key > '0')) and ((value <> 'val_500') or (key > '1'))) and (key < '400')) and (key <> '12')) and (key <> '4')) and key is not null) and (key <> '13')) and (key <> '1')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/ppd_join5.q.out ql/src/test/results/clientpositive/spark/ppd_join5.q.out index 377d8ac..8b51969 100644 --- ql/src/test/results/clientpositive/spark/ppd_join5.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join5.q.out @@ -32,7 +32,7 @@ POSTHOOK: Lineage: t1.id1 SIMPLE [] POSTHOOK: Lineage: t1.id2 SIMPLE [] POSTHOOK: Lineage: t2.d SIMPLE [] POSTHOOK: Lineage: t2.id SIMPLE [] -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) @@ -148,7 +148,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from ( select a.*,b.d d1,c.d d2 from @@ -271,7 +271,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[15][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from ( select a.*,b.d d1,c.d d2 from t1 a join t2 b on (a.id1 = b.id) diff --git ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out index b1a3e49..fd2d590 100644 --- ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out +++ ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out @@ -145,17 +145,13 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + tag: 0 + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -332,18 +328,14 @@ STAGE PLANS: expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: false Stage: Stage-0 Fetch Operator @@ -911,17 +903,13 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - tag: 0 - auto parallelism: false + tag: 0 + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -1098,18 +1086,14 @@ STAGE PLANS: expressions: _col0 (type: string), (UDFToDouble(_col1) + 2.0) (type: double), (UDFToDouble(_col1) + 3.0) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Filter Operator - isSamplingPred: false - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: double), _col2 (type: double) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: double), _col2 (type: double) + auto parallelism: false Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out index ea95e18..563c0d0 100644 --- ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out +++ ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out @@ -43,15 +43,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan @@ -64,15 +61,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/ppd_outer_join3.q.out ql/src/test/results/clientpositive/spark/ppd_outer_join3.q.out index c54029b..4018878 100644 --- ql/src/test/results/clientpositive/spark/ppd_outer_join3.q.out +++ ql/src/test/results/clientpositive/spark/ppd_outer_join3.q.out @@ -43,15 +43,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Map 3 Map Operator Tree: TableScan @@ -64,15 +61,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator diff --git ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out index 9ac30c7..b9d79ca 100644 --- ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out +++ ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out @@ -49,14 +49,11 @@ STAGE PLANS: expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -69,15 +66,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan @@ -90,15 +84,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Reducer 2 Reduce Operator Tree: Join Operator @@ -426,7 +417,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((sqrt(key) <> 13.0) and (key < '25')) and (key > '15')) and (key < '20')) and (key > '10')) and key is not null) (type: boolean) + predicate: ((((((sqrt(key) <> 13.0) and (key < '25')) and (key > '15')) and (key < '20')) and key is not null) and (key > '10')) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -443,7 +434,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and (sqrt(key) <> 13.0)) and key is not null) (type: boolean) + predicate: ((((((key > '10') and (key < '20')) and (key > '15')) and (key < '25')) and key is not null) and (sqrt(key) <> 13.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/router_join_ppr.q.out ql/src/test/results/clientpositive/spark/router_join_ppr.q.out index 0734d71..86091f6 100644 --- ql/src/test/results/clientpositive/spark/router_join_ppr.q.out +++ ql/src/test/results/clientpositive/spark/router_join_ppr.q.out @@ -1508,7 +1508,7 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and key is not null) and (UDFToDouble(key) > 10.0)) (type: boolean) Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoin.q.out ql/src/test/results/clientpositive/spark/skewjoin.q.out index ec5d4cd..8770f90 100644 --- ql/src/test/results/clientpositive/spark/skewjoin.q.out +++ ql/src/test/results/clientpositive/spark/skewjoin.q.out @@ -823,7 +823,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and UDFToDouble(substring(value, 5)) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -840,16 +840,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and (UDFToDouble(substring(value, 5)) + 1.0) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + key expressions: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + Map-reduce partition columns: _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 @@ -860,7 +860,7 @@ STAGE PLANS: handleSkewJoin: true keys: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) - 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + 1.0) (type: double) + 1 _col0 (type: string), (UDFToDouble(substring(_col1, 5)) + UDFToDouble(1)) (type: double) outputColumnNames: _col2, _col3 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator @@ -1026,7 +1026,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out index 1994d2f..457fb05 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out @@ -91,7 +91,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), val (type: string) @@ -109,7 +109,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) diff --git ql/src/test/results/clientpositive/spark/subquery_exists.q.out ql/src/test/results/clientpositive/spark/subquery_exists.q.out index 06c34b9..b7b5f53 100644 --- ql/src/test/results/clientpositive/spark/subquery_exists.q.out +++ ql/src/test/results/clientpositive/spark/subquery_exists.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_9') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/spark/subquery_in.q.out ql/src/test/results/clientpositive/spark/subquery_in.q.out index ec18be8..e2feb9a 100644 --- ql/src/test/results/clientpositive/spark/subquery_in.q.out +++ ql/src/test/results/clientpositive/spark/subquery_in.q.out @@ -282,15 +282,12 @@ STAGE PLANS: expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is not null (type: boolean) + Reduce Output Operator + key expressions: _col2 (type: double) + sort order: + + Map-reduce partition columns: _col2 (type: double) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: double) - sort order: + - Map-reduce partition columns: _col2 (type: double) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + value expressions: _col0 (type: string), _col1 (type: int) Map 3 Map Operator Tree: TableScan @@ -301,7 +298,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reducer 2 Reduce Operator Tree: Join Operator @@ -346,22 +342,26 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + Select Operator + expressions: _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col0) - mode: hash + Select Operator + expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: struct) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: struct) Reducer 5 Reduce Operator Tree: Group By Operator @@ -470,7 +470,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reducer 2 Reduce Operator Tree: Join Operator @@ -519,25 +518,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Reducer 5 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out index 7be8eca..f2c7b08 100644 --- ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out +++ ql/src/test/results/clientpositive/spark/table_access_keys_stats.q.out @@ -277,7 +277,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -296,7 +296,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key,val Table:default@t2 @@ -330,7 +330,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -351,7 +351,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -369,7 +369,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -390,7 +390,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -411,7 +411,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 @@ -435,7 +435,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -472,7 +472,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 @@ -503,13 +503,13 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 Keys:key -Operator:GBY_18 +Operator:GBY_16 Table:default@t3 Keys:val @@ -541,7 +541,7 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 diff --git ql/src/test/results/clientpositive/spark/union_remove_19.q.out ql/src/test/results/clientpositive/spark/union_remove_19.q.out index d57c399..398b610 100644 --- ql/src/test/results/clientpositive/spark/union_remove_19.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_19.q.out @@ -251,25 +251,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '7' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -278,10 +278,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 14 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -294,10 +294,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 14 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out index 296c256..14a90e5 100644 --- ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/spark/vector_mapjoin_reduce.q.out @@ -202,7 +202,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + predicate: ((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) @@ -262,7 +262,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) + predicate: ((((l_linenumber = 1) and l_partkey is not null) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) diff --git ql/src/test/results/clientpositive/subquery_exists.q.out ql/src/test/results/clientpositive/subquery_exists.q.out index 9683e08..bcfbdaf 100644 --- ql/src/test/results/clientpositive/subquery_exists.q.out +++ ql/src/test/results/clientpositive/subquery_exists.q.out @@ -36,7 +36,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_9') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/subquery_in.q.out ql/src/test/results/clientpositive/subquery_in.q.out index cb30789..5f5acbf 100644 --- ql/src/test/results/clientpositive/subquery_in.q.out +++ ql/src/test/results/clientpositive/subquery_in.q.out @@ -259,7 +259,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -286,24 +285,28 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + Select Operator + expressions: _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col0) - mode: hash + Select Operator + expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -347,15 +350,12 @@ STAGE PLANS: expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is not null (type: boolean) + Reduce Output Operator + key expressions: _col2 (type: double) + sort order: + + Map-reduce partition columns: _col2 (type: double) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: double) - sort order: + - Map-reduce partition columns: _col2 (type: double) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + value expressions: _col0 (type: string), _col1 (type: int) TableScan Reduce Output Operator key expressions: _col0 (type: double) @@ -443,7 +443,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -470,25 +469,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce diff --git ql/src/test/results/clientpositive/subquery_in_having.q.out ql/src/test/results/clientpositive/subquery_in_having.q.out index 73250bd..2fc67ed 100644 --- ql/src/test/results/clientpositive/subquery_in_having.q.out +++ ql/src/test/results/clientpositive/subquery_in_having.q.out @@ -375,13 +375,13 @@ STAGE PLANS: Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: bigint) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col1 (type: string) + expressions: _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1347,12 +1347,12 @@ STAGE PLANS: window function: GenericUDAFFirstValueEvaluator window frame: PRECEDING(MAX)~ Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: first_value_window_0 is not null (type: boolean) + Select Operator + expressions: first_value_window_0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: first_value_window_0 (type: string) - outputColumnNames: _col0 + Filter Operator + predicate: _col0 is not null (type: boolean) Statistics: Num rows: 15 Data size: 3173 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) diff --git ql/src/test/results/clientpositive/subquery_notin.q.out ql/src/test/results/clientpositive/subquery_notin.q.out index ed86079..4f40218 100644 --- ql/src/test/results/clientpositive/subquery_notin.q.out +++ ql/src/test/results/clientpositive/subquery_notin.q.out @@ -326,7 +326,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Reduce Operator Tree: Select Operator @@ -354,22 +353,26 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator + Select Operator + expressions: _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and (_col0 is null or _col1 is null)) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -482,7 +485,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Reduce Operator Tree: Select Operator @@ -510,19 +512,23 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col2 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -611,7 +617,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -638,24 +643,28 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + Select Operator + expressions: _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col0) - mode: hash + Select Operator + expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -778,7 +787,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -805,24 +813,28 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + Select Operator + expressions: _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col0) - mode: hash + Select Operator + expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col0) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-6 Map Reduce @@ -939,7 +951,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -966,25 +977,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col2 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -1131,7 +1146,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -1158,25 +1172,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col2 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-7 Map Reduce diff --git ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out index 7b7ccda..d6c6edc 100644 --- ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out +++ ql/src/test/results/clientpositive/subquery_notin_having.q.java1.7.out @@ -354,7 +354,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean) + predicate: (((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean) Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out index 3241787..b0c7e0d 100644 --- ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out +++ ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out @@ -212,7 +212,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p2_mfgr (type: string) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -239,25 +238,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: ((_col2 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -381,7 +384,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int) @@ -408,25 +410,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-3 Map Reduce @@ -748,13 +754,13 @@ STAGE PLANS: Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: bigint) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col2 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is not null (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: bigint), _col1 (type: string) + expressions: _col2 (type: bigint), _col0 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -816,7 +822,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Reduce Operator Tree: Select Operator @@ -844,22 +849,26 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator + Select Operator + expressions: _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and (_col0 is null or _col1 is null)) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-4 Map Reduce @@ -972,7 +981,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 value expressions: p_name (type: string) Reduce Operator Tree: Select Operator @@ -1000,19 +1008,23 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col1 (type: string), _col2 (type: string), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col2 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/subquery_views.q.out ql/src/test/results/clientpositive/subquery_views.q.out index 00c9bd8..76e53d3 100644 --- ql/src/test/results/clientpositive/subquery_views.q.out +++ ql/src/test/results/clientpositive/subquery_views.q.out @@ -220,7 +220,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value > 'val_11') and key is not null) (type: boolean) + predicate: (value > 'val_11') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), key (type: string) @@ -375,7 +375,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_11') and (key < '11')) and key is not null) (type: boolean) + predicate: ((value > 'val_11') and (key < '11')) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), key (type: string) diff --git ql/src/test/results/clientpositive/table_access_keys_stats.q.out ql/src/test/results/clientpositive/table_access_keys_stats.q.out index 7be8eca..f2c7b08 100644 --- ql/src/test/results/clientpositive/table_access_keys_stats.q.out +++ ql/src/test/results/clientpositive/table_access_keys_stats.q.out @@ -277,7 +277,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -296,7 +296,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key,val Table:default@t2 @@ -330,7 +330,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -351,7 +351,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -369,7 +369,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -390,7 +390,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val Table:default@t2 @@ -411,7 +411,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 @@ -435,7 +435,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:key Table:default@t2 @@ -472,7 +472,7 @@ PREHOOK: type: QUERY PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 @@ -503,13 +503,13 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 Keys:key -Operator:GBY_18 +Operator:GBY_16 Table:default@t3 Keys:val @@ -541,7 +541,7 @@ PREHOOK: Input: default@t1 PREHOOK: Input: default@t2 PREHOOK: Input: default@t3 #### A masked pattern was here #### -Operator:JOIN_10 +Operator:JOIN_8 Table:default@t1 Keys:val,key Table:default@t2 diff --git ql/src/test/results/clientpositive/tez/auto_join_filters.q.out ql/src/test/results/clientpositive/tez/auto_join_filters.q.out index d44fff3..1559d4b 100644 --- ql/src/test/results/clientpositive/tez/auto_join_filters.q.out +++ ql/src/test/results/clientpositive/tez/auto_join_filters.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -300,7 +300,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in2.txt' into table sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@smb_input2 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -310,7 +310,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -320,7 +320,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 2' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 @@ -330,7 +330,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@myinput1 #### A masked pattern was here #### 3078400 -Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a FULL OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out index a390851..5b68bb7 100644 --- ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out +++ ql/src/test/results/clientpositive/tez/auto_join_nulls.q.out @@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in1.txt' INTO TABLE my POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/auto_sortmerge_join_12.q.out ql/src/test/results/clientpositive/tez/auto_sortmerge_join_12.q.out index 17f0229..09a10bd 100644 --- ql/src/test/results/clientpositive/tez/auto_sortmerge_join_12.q.out +++ ql/src/test/results/clientpositive/tez/auto_sortmerge_join_12.q.out @@ -138,7 +138,7 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_medium@ds=2008-04-08 -Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Map 3' is a cross product +Warning: Map Join MAPJOIN[35][bigTable=?] in task 'Map 3' is a cross product PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key @@ -619,7 +619,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[39][bigTable=?] in task 'Map 3' is a cross product +Warning: Map Join MAPJOIN[35][bigTable=?] in task 'Map 3' is a cross product PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big diff --git ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out index 2956bf8..521485a 100644 --- ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out +++ ql/src/test/results/clientpositive/tez/auto_sortmerge_join_6.q.out @@ -483,7 +483,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -494,7 +494,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -519,7 +519,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -955,7 +955,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -966,7 +966,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) @@ -991,7 +991,7 @@ STAGE PLANS: alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/tez/auto_sortmerge_join_9.q.out ql/src/test/results/clientpositive/tez/auto_sortmerge_join_9.q.out index fbd0bb8..984a9f2 100644 --- ql/src/test/results/clientpositive/tez/auto_sortmerge_join_9.q.out +++ ql/src/test/results/clientpositive/tez/auto_sortmerge_join_9.q.out @@ -1258,28 +1258,25 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 3 - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan @@ -1292,14 +1289,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out index 9582334..8423544 100644 --- ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out +++ ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out @@ -1413,21 +1413,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col2 (type: string) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: b - Partition key expr: ds - Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 2 Map 2 Map Operator Tree: TableScan diff --git ql/src/test/results/clientpositive/tez/bucket_map_join_tez2.q.out ql/src/test/results/clientpositive/tez/bucket_map_join_tez2.q.out index 6adf820..d2d8fd5 100644 --- ql/src/test/results/clientpositive/tez/bucket_map_join_tez2.q.out +++ ql/src/test/results/clientpositive/tez/bucket_map_join_tez2.q.out @@ -257,7 +257,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) @@ -275,7 +275,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -626,7 +626,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: value (type: string) @@ -644,7 +644,7 @@ STAGE PLANS: alias: tab Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) diff --git ql/src/test/results/clientpositive/tez/constprog_dpp.q.out ql/src/test/results/clientpositive/tez/constprog_dpp.q.out index acebd05..8a57907 100644 --- ql/src/test/results/clientpositive/tez/constprog_dpp.q.out +++ ql/src/test/results/clientpositive/tez/constprog_dpp.q.out @@ -55,7 +55,7 @@ Stage-0 compressed:false Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL 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"} - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_20] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0"] diff --git ql/src/test/results/clientpositive/tez/cross_join.q.out ql/src/test/results/clientpositive/tez/cross_join.q.out index de3edbb..d397bd4 100644 --- ql/src/test/results/clientpositive/tez/cross_join.q.out +++ ql/src/test/results/clientpositive/tez/cross_join.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- current explain select src.key from src join src src2 PREHOOK: type: QUERY @@ -63,7 +63,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- ansi cross join explain select src.key from src cross join src src2 PREHOOK: type: QUERY @@ -203,7 +203,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select src.key from src join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src join src src2 @@ -262,7 +262,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select src.key from src cross join src src2 PREHOOK: type: QUERY POSTHOOK: query: explain select src.key from src cross join src src2 diff --git ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out index 0e7c681..4262eea 100644 --- ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out +++ ql/src/test/results/clientpositive/tez/cross_product_check_1.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Shuffle Join MERGEJOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -94,7 +94,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[25][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -198,7 +198,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -324,8 +324,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product -Warning: Shuffle Join MERGEJOIN[25][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 @@ -434,7 +434,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[34][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out index efd8b5d..f1f85ea 100644 --- ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out +++ ql/src/test/results/clientpositive/tez/cross_product_check_2.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@src POSTHOOK: Output: database:default POSTHOOK: Output: default@B -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select * from A join B PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join B @@ -90,7 +90,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[25][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A PREHOOK: type: QUERY POSTHOOK: query: explain select * from B d1 join B d2 on d1.key = d2.key join A @@ -184,7 +184,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[30][bigTable=?] in task 'Reducer 3' is a cross product +Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 on d1.key = d2.key @@ -301,8 +301,8 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Map 2' is a cross product -Warning: Map Join MAPJOIN[25][bigTable=?] in task 'Reducer 3' is a cross product +Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 2' is a cross product +Warning: Map Join MAPJOIN[24][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 PREHOOK: type: QUERY POSTHOOK: query: explain select * from A join (select d1.key from B d1 join B d2 where 1 = 1 group by d1.key) od1 @@ -402,7 +402,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[34][bigTable=?] in task 'Reducer 4' is a cross product +Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Reducer 4' is a cross product PREHOOK: query: explain select * from (select A.key from A group by key) ss join (select d1.key from B d1 join B d2 on d1.key = d2.key where 1 = 1 group by d1.key) od1 diff --git ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out index d4b670d..26a94f5 100644 --- ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/dynamic_partition_pruning.q.out @@ -235,21 +235,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -453,6 +438,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -482,21 +468,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Map 6 Map Operator Tree: TableScan @@ -515,21 +486,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -788,6 +744,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -816,36 +773,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -1073,21 +1000,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -1284,28 +1196,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1316,21 +1225,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -1409,20 +1303,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -1441,21 +1332,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -1534,28 +1410,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1644,20 +1517,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and (UDFToDouble(hr) * 2.0) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -1682,7 +1552,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1767,28 +1637,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) + sort order: + + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - sort order: + - Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1799,21 +1666,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToString(_col0) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -1983,21 +1835,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2035,7 +1872,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2129,7 +1966,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2171,6 +2008,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2199,36 +2037,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -2338,21 +2146,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -2426,21 +2219,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 Map 4 Map Operator Tree: TableScan @@ -2544,21 +2322,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -2623,6 +2386,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2651,29 +2415,14 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE @@ -2777,10 +2526,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -3016,21 +2765,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Reduce Operator Tree: Group By Operator @@ -3051,21 +2785,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3215,21 +2934,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Reduce Operator Tree: Group By Operator @@ -3250,21 +2954,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3317,16 +3006,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 10 Map Operator Tree: TableScan @@ -3351,16 +3044,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3399,36 +3096,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Reducer 2 Reduce Operator Tree: Group By Operator @@ -3490,36 +3157,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Union 3 Vertex: Union 3 Union 9 @@ -3616,21 +3253,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -3708,6 +3330,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3761,21 +3384,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Map 4 Map Operator Tree: TableScan @@ -3794,21 +3402,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -3886,6 +3479,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3928,36 +3522,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 27 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -4074,21 +3638,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -4138,42 +3687,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 14 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -4184,21 +3730,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -4259,34 +3790,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) - 1 _col0 (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) * 2.0) (type: double) + 1 _col0 (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan @@ -4305,21 +3833,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -4568,21 +4081,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -4796,6 +4294,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4848,29 +4347,14 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE @@ -4941,10 +4425,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -5163,21 +4647,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 7 Reduce Operator Tree: Group By Operator @@ -5198,21 +4667,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 5 Vertex: Union 5 @@ -5297,42 +4751,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_orc - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), UDFToDouble(_col1) (type: double) - 1 _col0 (type: string), UDFToDouble(_col2) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 108 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + predicate: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5343,36 +4794,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: ds - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: UDFToDouble(_col2) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 54 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out index bc5638c..ab8e0db 100644 --- ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out +++ ql/src/test/results/clientpositive/tez/dynamic_partition_pruning_2.q.out @@ -216,21 +216,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -742,21 +727,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator @@ -890,21 +860,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg_01 - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 1 Map 4 Map Operator Tree: TableScan @@ -951,21 +906,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: agg_01 - Partition key expr: dim_shops_id - Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE - Target column: dim_shops_id - Target Vertex: Map 4 Union 2 Vertex: Union 2 diff --git ql/src/test/results/clientpositive/tez/explainuser_1.q.out ql/src/test/results/clientpositive/tez/explainuser_1.q.out index c081309..23e8098 100644 --- ql/src/test/results/clientpositive/tez/explainuser_1.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_1.q.out @@ -512,128 +512,128 @@ Stage-0 limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_50] + File Output Operator [FS_42] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_49] + Select Operator [SEL_41] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_48] + Reduce Output Operator [RS_40] key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Select Operator [SEL_46] + Select Operator [SEL_38] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_45] + Group By Operator [GBY_37] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_44] + Reduce Output Operator [RS_36] key expressions:_col0 (type: bigint), _col1 (type: int) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_43] + Group By Operator [GBY_35] aggregations:["count()"] keys:_col2 (type: bigint), _col6 (type: int) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_42] + Select Operator [SEL_34] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_56] + Filter Operator [FIL_33] predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_62] + Merge Join Operator [MERGEJOIN_52] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col6"] | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_39] + | Reduce Output Operator [RS_31] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Select Operator [SEL_35] + | Select Operator [SEL_29] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_60] + | Filter Operator [FIL_50] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_33] + | TableScan [TS_27] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_30] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_32] + Select Operator [SEL_26] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_57] + Filter Operator [FIL_25] predicate:((_col1 + _col4) >= 0) (type: boolean) Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_61] + Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Select Operator [SEL_22] + | Select Operator [SEL_20] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_21] + | Reduce Output Operator [RS_19] | key expressions:_col3 (type: double), _col2 (type: bigint) | sort order:-+ | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [SEL_19] + | Select Operator [SEL_17] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_18] + | Group By Operator [GBY_16] | | aggregations:["sum(VALUE._col0)"] | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) | sort order:+++ | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_16] + | Group By Operator [GBY_14] | aggregations:["sum(c_int)"] | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_59] + | Filter Operator [FIL_49] | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_13] + | TableScan [TS_11] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_22] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -668,7 +668,7 @@ Stage-0 keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_58] + Filter Operator [FIL_48] predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] @@ -695,86 +695,86 @@ Stage-0 limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_43] + File Output Operator [FS_39] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_42] + Select Operator [SEL_38] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_41] + Reduce Output Operator [RS_37] key expressions:(UDFToLong(_col0) % _col1) (type: bigint), _col0 (type: int) sort order:+- Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint), _col2 (type: bigint) - Select Operator [SEL_39] + Select Operator [SEL_35] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_38] + Group By Operator [GBY_34] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_33] key expressions:_col0 (type: bigint), _col1 (type: int) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_36] + Group By Operator [GBY_32] aggregations:["count()"] keys:_col2 (type: bigint), _col6 (type: int) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_35] + Select Operator [SEL_31] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:((((UDFToLong(_col6) + _col2) >= 0) and ((_col1 > 0) or (_col6 >= 0))) and ((_col6 >= 1) or (_col2 >= 1))) (type: boolean) + Filter Operator [FIL_30] + predicate:(((_col1 > 0) or (_col6 >= 0)) and ((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0)) (type: boolean) Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_54] + Merge Join Operator [MERGEJOIN_48] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col6"] | Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_32] + | Reduce Output Operator [RS_28] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Select Operator [SEL_28] + | Select Operator [SEL_26] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_52] + | Filter Operator [FIL_46] | predicate:((c_int > 0) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_26] + | TableScan [TS_24] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_30] + Reduce Output Operator [RS_27] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_25] + Select Operator [SEL_23] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_49] + Filter Operator [FIL_22] predicate:((_col1 + _col4) >= 0) (type: boolean) Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_53] + Merge Join Operator [MERGEJOIN_47] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_21] + | Reduce Output Operator [RS_19] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -809,40 +809,40 @@ Stage-0 | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_50] + | Filter Operator [FIL_44] | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_20] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) - Select Operator [SEL_19] + Select Operator [SEL_17] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_18] + Group By Operator [GBY_16] | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_15] key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_16] + Group By Operator [GBY_14] keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_51] - predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Filter Operator [FIL_45] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] + TableScan [TS_11] alias:cbo_t2 Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE @@ -891,10 +891,10 @@ Stage-0 Select Operator [SEL_26] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] + Filter Operator [FIL_25] predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_37] + Merge Join Operator [MERGEJOIN_36] | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col6"] @@ -948,7 +948,7 @@ Stage-0 | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_35] + | Filter Operator [FIL_34] | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] @@ -978,7 +978,7 @@ Stage-0 keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_36] + Filter Operator [FIL_35] predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_11] @@ -1041,10 +1041,10 @@ Stage-0 Select Operator [SEL_30] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_39] - predicate:(((((_col1 + _col4) >= 0) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) and ((_col6 >= 1) or (_col2 >= 1))) (type: boolean) + Filter Operator [FIL_29] + predicate:(((_col1 + _col4) >= 0) and ((_col1 > 0) or (_col6 >= 0)) and ((_col6 >= 1) or (_col2 >= 1)) and ((UDFToLong(_col6) + _col2) >= 0)) (type: boolean) Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_43] + Merge Join Operator [MERGEJOIN_42] | condition map:[{"":"Outer Join 0 to 1"},{"":"Right Outer Join0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col6"] @@ -1059,7 +1059,7 @@ Stage-0 | Select Operator [SEL_24] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_42] + | Filter Operator [FIL_41] | predicate:(c_int > 0) (type: boolean) | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_22] @@ -1101,7 +1101,7 @@ Stage-0 | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_40] + | Filter Operator [FIL_39] | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] @@ -1143,7 +1143,7 @@ Stage-0 keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_41] + Filter Operator [FIL_40] predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_11] @@ -1168,77 +1168,77 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_37] + File Output Operator [FS_33] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_36] + Select Operator [SEL_32] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_35] + Group By Operator [GBY_31] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_34] + Reduce Output Operator [RS_30] key expressions:_col0 (type: bigint), _col1 (type: int) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_33] + Group By Operator [GBY_29] aggregations:["count()"] keys:_col2 (type: bigint), _col6 (type: int) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_32] + Select Operator [SEL_28] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_43] + Filter Operator [FIL_27] predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_49] + Merge Join Operator [MERGEJOIN_43] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col6"] | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_25] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Select Operator [SEL_25] + | Select Operator [SEL_23] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_47] + | Filter Operator [FIL_41] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_23] + | TableScan [TS_21] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_24] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_22] + Select Operator [SEL_20] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_44] + Filter Operator [FIL_19] predicate:((_col1 + _col4) >= 0) (type: boolean) Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_48] + Merge Join Operator [MERGEJOIN_42] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_16] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1264,14 +1264,14 @@ Stage-0 | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_45] + | Filter Operator [FIL_39] | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_17] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -1294,7 +1294,7 @@ Stage-0 keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_46] + Filter Operator [FIL_40] predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_8] @@ -1619,17 +1619,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_12] + File Output Operator [FS_10] compressed:false Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_17] + Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 18 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1637,14 +1637,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_15] + | Filter Operator [FIL_13] | predicate:(UDFToDouble(key) >= 1.0) (type: boolean) | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -1652,7 +1652,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_16] + Filter Operator [FIL_14] predicate:(UDFToDouble(key) >= 1.0) (type: boolean) Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -1680,7 +1680,7 @@ Stage-0 Select Operator [SEL_7] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_11] + Merge Join Operator [MERGEJOIN_10] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col3"] @@ -1779,20 +1779,20 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_17] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_16] + Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_24] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col4","_col5","_col6"] | Statistics:Num rows: 291 Data size: 29391 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] + | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1801,14 +1801,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_24] + | Filter Operator [FIL_21] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1488 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1817,14 +1817,14 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Filter Operator [FIL_22] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_14] + Reduce Output Operator [RS_11] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -1833,7 +1833,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_23] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -1854,20 +1854,20 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_17] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_16] + Select Operator [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_24] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3","_col4"] | Statistics:Num rows: 291 Data size: 51798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] + | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1876,14 +1876,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_24] + | Filter Operator [FIL_21] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1891,14 +1891,14 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Filter Operator [FIL_22] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_14] + Reduce Output Operator [RS_11] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -1907,7 +1907,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_23] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -1929,23 +1929,23 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_21] + File Output Operator [FS_19] compressed:false - Statistics:Num rows: 14 Data size: 1414 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 6 Data size: 606 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_20] + Select Operator [SEL_18] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - Statistics:Num rows: 14 Data size: 1414 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Statistics:Num rows: 6 Data size: 606 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_17] predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) - Statistics:Num rows: 14 Data size: 1414 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_33] + Statistics:Num rows: 6 Data size: 606 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_28] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 21 Data size: 2121 Basic stats: COMPLETE Column stats: COMPLETE + | Statistics:Num rows: 10 Data size: 1010 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_15] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1954,27 +1954,27 @@ Stage-0 | Select Operator [SEL_13] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_31] + | Filter Operator [FIL_26] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_11] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_14] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ - Statistics:Num rows: 6 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 3 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: float), _col3 (type: string), _col4 (type: int) - Filter Operator [FIL_28] + Filter Operator [FIL_9] predicate:(((_col1 + _col4) = 2) and ((_col4 + 1) = 2)) (type: boolean) - Statistics:Num rows: 6 Data size: 1092 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_32] + Statistics:Num rows: 3 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - | Statistics:Num rows: 25 Data size: 4550 Basic stats: COMPLETE Column stats: COMPLETE + | Statistics:Num rows: 15 Data size: 2730 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) @@ -1985,7 +1985,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_29] + | Filter Operator [FIL_24] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] @@ -1996,14 +1996,14 @@ Stage-0 key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ - Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 5 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_30] - predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) - Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_25] + predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] alias:cbo_t2 Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE @@ -2024,15 +2024,15 @@ Stage-0 Reducer 2 File Output Operator [FS_14] compressed:false - Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_13] outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] - predicate:((((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0))) and ((_col4 + 1) = 2)) (type: boolean) - Statistics:Num rows: 12 Data size: 1212 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_21] + Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_12] + predicate:(((_col1 + _col4) = 2) and ((_col1 > 0) or (_col6 >= 0)) and ((_col4 + 1) = 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 8 Data size: 808 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3","_col4","_col6"] @@ -2047,7 +2047,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_19] + | Filter Operator [FIL_17] | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] @@ -2063,7 +2063,7 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 445 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] @@ -2361,95 +2361,95 @@ Stage-0 limit:5 Stage-1 Reducer 7 - File Output Operator [FS_53] + File Output Operator [FS_49] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Limit [LIM_52] + Limit [LIM_48] Number of rows:5 Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_51] + Select Operator [SEL_47] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_50] + Reduce Output Operator [RS_46] key expressions:(UDFToLong(_col0) + _col1) (type: bigint), _col1 (type: bigint) sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Select Operator [SEL_48] + Select Operator [SEL_44] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_47] + Group By Operator [GBY_43] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_46] + Reduce Output Operator [RS_42] key expressions:_col0 (type: bigint), _col1 (type: int) Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_45] + Group By Operator [GBY_41] aggregations:["count()"] keys:_col2 (type: bigint), _col6 (type: int) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_44] + Select Operator [SEL_40] outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_59] + Filter Operator [FIL_39] predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_67] + Merge Join Operator [MERGEJOIN_59] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col6"] | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_41] + | Reduce Output Operator [RS_37] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Select Operator [SEL_37] + | Select Operator [SEL_35] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_65] + | Filter Operator [FIL_57] | predicate:key is not null (type: boolean) | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_35] + | TableScan [TS_33] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_39] + Reduce Output Operator [RS_36] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_34] + Select Operator [SEL_32] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_60] + Filter Operator [FIL_31] predicate:((_col1 + _col4) >= 0) (type: boolean) Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_66] + Merge Join Operator [MERGEJOIN_58] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] + | Reduce Output Operator [RS_29] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: int) - | Filter Operator [FIL_63] + | Filter Operator [FIL_26] | predicate:_col0 is not null (type: boolean) | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE | Limit [LIM_24] @@ -2484,20 +2484,20 @@ Stage-0 | keys:key (type: string), c_int (type: int), c_float (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_64] + | Filter Operator [FIL_56] | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_14] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_29] + Reduce Output Operator [RS_28] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int), _col2 (type: bigint) - Filter Operator [FIL_61] + Filter Operator [FIL_12] predicate:_col0 is not null (type: boolean) Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE Limit [LIM_10] @@ -2532,7 +2532,7 @@ Stage-0 keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_62] + Filter Operator [FIL_55] predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] @@ -2553,20 +2553,20 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_14] + File Output Operator [FS_12] compressed:false Statistics:Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_13] + Select Operator [SEL_11] outputColumnNames:["_col0"] Statistics:Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_19] + Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1"] | Statistics:Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -2575,14 +2575,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_17] + | Filter Operator [FIL_15] | predicate:((((c_int + 1) = 2) and key is not null) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) | Statistics:Num rows: 6 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -2594,7 +2594,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_16] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -2615,20 +2615,20 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_21] + File Output Operator [FS_18] compressed:false Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_20] + Select Operator [SEL_17] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_31] + Merge Join Operator [MERGEJOIN_28] | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 12 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_14] + | Reduce Output Operator [RS_13] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -2637,14 +2637,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_28] + | Filter Operator [FIL_25] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:cbo_t1 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_16] + | Reduce Output Operator [RS_14] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -2656,14 +2656,14 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 5 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_29] + | Filter Operator [FIL_26] | predicate:((((c_int + 1) = 2) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) | Statistics:Num rows: 5 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:cbo_t2 | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_18] + Reduce Output Operator [RS_15] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -2675,7 +2675,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0"] Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_30] + Filter Operator [FIL_27] predicate:key is not null (type: boolean) Statistics:Num rows: 18 Data size: 1360 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -2702,153 +2702,150 @@ Stage-0 limit:-1 Stage-1 Reducer 6 - File Output Operator [FS_47] + File Output Operator [FS_41] compressed:false Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_46] + Select Operator [SEL_40] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_45] + Reduce Output Operator [RS_39] key expressions:_col1 (type: bigint), _col0 (type: string) sort order:++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_43] + Group By Operator [GBY_37] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string), KEY._col1 (type: bigint) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_42] + Reduce Output Operator [RS_36] key expressions:_col0 (type: string), _col1 (type: bigint) Map-reduce partition columns:_col0 (type: string), _col1 (type: bigint) sort order:++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: bigint) - Group By Operator [GBY_41] + Group By Operator [GBY_35] aggregations:["count()"] keys:_col0 (type: string), _col1 (type: bigint) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_60] + Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Left Semi Join 0 to 1"},{"":"Left Semi Join 0 to 2"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_38] + | Reduce Output Operator [RS_32] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 3 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_32] + | Group By Operator [GBY_29] | keys:_col0 (type: string) | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 170 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_28] + | Select Operator [SEL_25] | outputColumnNames:["_col0"] | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_58] + | Filter Operator [FIL_50] | predicate:(UDFToDouble(key) > 0.0) (type: boolean) | Statistics:Num rows: 6 Data size: 425 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_26] + | TableScan [TS_23] | alias:cbo_t3 | Statistics:Num rows: 20 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_34] + | Reduce Output Operator [RS_30] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: bigint) - | Select Operator [SEL_9] + | Select Operator [SEL_10] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_8] - | key expressions:_col3 (type: double), _col2 (type: bigint) + | Reduce Output Operator [RS_9] + | key expressions:_col2 (type: double), _col1 (type: bigint) | sort order:-+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) - | Filter Operator [FIL_54] - | predicate:(((_col1 + 1) >= 0) and ((_col1 > 0) or (UDFToDouble(_col0) >= 0.0))) (type: boolean) - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_6] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_55] - | predicate:(((UDFToDouble(_col0) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col0) >= 1.0) or (_col3 >= 1))) (type: boolean) - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_59] - | outputColumnNames:["_col0","_col1","_col3"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_5] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_4] - | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) - | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) - | sort order:+++ + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_7] + | predicate:(((UDFToDouble(_col2) >= 1.0) or (_col3 >= 1)) and ((UDFToDouble(_col2) + UDFToDouble(_col3)) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_6] + | outputColumnNames:["_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_5] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_3] + | aggregations:["sum(c_int)"] + | keys:key (type: string), c_int (type: int), c_float (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_3] - | aggregations:["sum(c_int)"] - | keys:key (type: string), c_int (type: int), c_float (type: float) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_56] - | predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_48] + | predicate:((((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (((c_int + 1) + 1) >= 0)) and (((c_int + 1) > 0) or (UDFToDouble(key) >= 0.0))) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_36] + Reduce Output Operator [RS_31] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_30] + Group By Operator [GBY_27] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_22] + Select Operator [SEL_21] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 85 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_21] + Reduce Output Operator [RS_20] key expressions:_col1 (type: double), _col0 (type: string) sort order:-+ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_19] + Select Operator [SEL_18] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_18] + Group By Operator [GBY_17] | aggregations:["sum(VALUE._col0)"] | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_16] key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_16] + Group By Operator [GBY_15] aggregations:["sum(c_int)"] keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_57] + Filter Operator [FIL_49] predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] + TableScan [TS_12] alias:cbo_t2 Statistics:Num rows: 20 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE @@ -2911,48 +2908,52 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Group By Operator [GBY_14] + Group By Operator [GBY_12] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_11] + Select Operator [SEL_9] outputColumnNames:["_col0"] Statistics:Num rows: 400 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"'2014' (type: string)","1":"'2014' (type: string)"} | Statistics:Num rows: 400 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:'2014' (type: string) | Map-reduce partition columns:'2014' (type: string) | sort order:+ - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + | Statistics:Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | Statistics:Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:'2014' (type: string) Map-reduce partition columns:'2014' (type: string) sort order:+ - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_3] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Statistics:Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_5] + Statistics:Num rows: 20 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo b @@ -2988,7 +2989,7 @@ Stage-0 Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_17] + Filter Operator [FIL_13] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_19] @@ -3075,7 +3076,7 @@ Stage-0 Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_17] + Filter Operator [FIL_13] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE Merge Join Operator [MERGEJOIN_19] @@ -3161,17 +3162,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_14] + File Output Operator [FS_12] compressed:false Statistics:Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_19] + Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: string), _col0 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col1 (type: string), _col0 (type: string) | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) | sort order:++ @@ -3179,14 +3180,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_17] - | predicate:(((value > 'val_9') and key is not null) and value is not null) (type: boolean) + | Filter Operator [FIL_15] + | predicate:((value > 'val_9') and key is not null) (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ @@ -3198,7 +3199,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_16] predicate:(((value > 'val_9') and key is not null) and value is not null) (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3233,17 +3234,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_14] + File Output Operator [FS_12] compressed:false Statistics:Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_19] + Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: string), _col0 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col1 (type: string), _col0 (type: string) | Map-reduce partition columns:_col1 (type: string), _col0 (type: string) | sort order:++ @@ -3251,14 +3252,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_17] - | predicate:(((value > 'val_9') and key is not null) and value is not null) (type: boolean) + | Filter Operator [FIL_15] + | predicate:((value > 'val_9') and key is not null) (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ @@ -3270,7 +3271,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_16] predicate:(((value > 'val_9') and key is not null) and value is not null) (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3295,17 +3296,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_14] + File Output Operator [FS_12] compressed:false Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_19] + Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -3314,14 +3315,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_17] + | Filter Operator [FIL_15] | predicate:(key > '9') (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src_cbo | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -3333,7 +3334,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_16] predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3362,32 +3363,32 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_26] + File Output Operator [FS_22] compressed:false Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_25] + Select Operator [SEL_21] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_36] + Merge Join Operator [MERGEJOIN_32] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col2","_col4"] | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_21] + | Reduce Output Operator [RS_18] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: int) - | Merge Join Operator [MERGEJOIN_35] + | Merge Join Operator [MERGEJOIN_31] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: int), _col3 (type: int)","1":"_col0 (type: int), _col1 (type: int)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_16] + | | Reduce Output Operator [RS_15] | | key expressions:_col0 (type: int), _col3 (type: int) | | Map-reduce partition columns:_col0 (type: int), _col3 (type: int) | | sort order:++ @@ -3396,14 +3397,14 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_32] - | | predicate:(((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) + | | Filter Operator [FIL_28] + | | predicate:((((l_linenumber = 1) and l_partkey is not null) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:lineitem | | Statistics:Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 4 [SIMPLE_EDGE] - | Reduce Output Operator [RS_18] + | Reduce Output Operator [RS_16] | key expressions:_col0 (type: int), _col1 (type: int) | Map-reduce partition columns:_col0 (type: int), _col1 (type: int) | sort order:++ @@ -3415,14 +3416,14 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_33] - | predicate:(((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + | Filter Operator [FIL_29] + | predicate:((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:lineitem | Statistics:Num rows: 100 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] + Reduce Output Operator [RS_19] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ @@ -3441,7 +3442,7 @@ Stage-0 keys:l_partkey (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] + Filter Operator [FIL_30] predicate:l_partkey is not null (type: boolean) Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -3473,49 +3474,49 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_35] + File Output Operator [FS_31] compressed:false Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_48] + Merge Join Operator [MERGEJOIN_42] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col2 (type: bigint)","1":"_col0 (type: bigint)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_30] + | Reduce Output Operator [RS_27] | key expressions:_col2 (type: bigint) | Map-reduce partition columns:_col2 (type: bigint) | sort order:+ | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) - | Filter Operator [FIL_41] + | Filter Operator [FIL_15] | predicate:_col2 is not null (type: boolean) | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_16] + | Group By Operator [GBY_14] | | aggregations:["count(VALUE._col0)"] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_13] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: bigint) - | Group By Operator [GBY_14] + | Group By Operator [GBY_12] | aggregations:["count()"] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE - | Merge Join Operator [MERGEJOIN_47] + | Merge Join Operator [MERGEJOIN_41] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_9] + | | Reduce Output Operator [RS_8] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -3524,14 +3525,14 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_42] + | | Filter Operator [FIL_37] | | predicate:(key > '8') (type: boolean) | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:b | | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_11] + | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -3543,52 +3544,52 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_43] + | Filter Operator [FIL_38] | predicate:(key > '8') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:b | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] + Reduce Output Operator [RS_28] key expressions:_col0 (type: bigint) Map-reduce partition columns:_col0 (type: bigint) sort order:+ Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_28] + Group By Operator [GBY_26] keys:_col0 (type: bigint) outputColumnNames:["_col0"] Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_26] + Select Operator [SEL_24] outputColumnNames:["_col0"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_44] + Filter Operator [FIL_23] predicate:_col1 is not null (type: boolean) Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_46] + Select Operator [SEL_40] outputColumnNames:["_col1"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_24] + Group By Operator [GBY_22] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] + Reduce Output Operator [RS_21] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_22] + Group By Operator [GBY_20] aggregations:["count()"] keys:key (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_45] + Filter Operator [FIL_39] predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_19] + TableScan [TS_17] alias:b Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE @@ -3616,17 +3617,17 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_23] + File Output Operator [FS_21] compressed:false Statistics:Num rows: 6 Data size: 1362 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_28] + Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 6 Data size: 1362 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_18] + | Reduce Output Operator [RS_17] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -3652,14 +3653,14 @@ Stage-0 | keys:p_name (type: string), p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_26] + | Filter Operator [FIL_24] | predicate:p_name is not null (type: boolean) | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:part | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_18] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -3668,12 +3669,12 @@ Stage-0 keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 13 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_11] - outputColumnNames:["_col0"] + Filter Operator [FIL_13] + predicate:_col0 is not null (type: boolean) Statistics:Num rows: 26 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_27] - predicate:first_value_window_0 is not null (type: boolean) - Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_11] + outputColumnNames:["_col0"] + Statistics:Num rows: 26 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"name:":"windowingtablefunction","order by:":"_col5","partition by:":"_col2"}] Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE @@ -3720,28 +3721,28 @@ Stage-0 Reducer 4 File Output Operator [FS_26] compressed:false - Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_25] | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_24] key expressions:_col0 (type: string) sort order:+ - Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: string) Select Operator [SEL_23] outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_29] + Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_22] predicate:_col3 is null (type: boolean) - Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_34] + Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_32] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] - | Statistics:Num rows: 605 Data size: 107690 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 404 Data size: 107060 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] | Reduce Output Operator [RS_20] | key expressions:_col0 (type: string) @@ -3751,7 +3752,7 @@ Stage-0 | Select Operator [SEL_14] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_32] + | Filter Operator [FIL_30] | predicate:(key > '2') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_12] @@ -3762,13 +3763,13 @@ Stage-0 key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ - Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: string) - Merge Join Operator [MERGEJOIN_33] + Merge Join Operator [MERGEJOIN_31] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_16] | sort order: @@ -3783,10 +3784,10 @@ Stage-0 |<-Reducer 6 [SIMPLE_EDGE] Reduce Output Operator [RS_17] sort order: - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_9] - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_30] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_11] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_8] @@ -3804,7 +3805,7 @@ Stage-0 Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_31] + Filter Operator [FIL_29] predicate:((key > '2') and key is null) (type: boolean) Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3841,19 +3842,19 @@ Stage-0 Reducer 3 File Output Operator [FS_24] compressed:false - Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_23] outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_27] + Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_22] predicate:_col4 is null (type: boolean) - Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_32] + Statistics:Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_30] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] | Reduce Output Operator [RS_20] | key expressions:_col0 (type: string), _col1 (type: string) @@ -3863,7 +3864,7 @@ Stage-0 | Select Operator [SEL_14] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_30] + | Filter Operator [FIL_28] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_12] @@ -3874,13 +3875,13 @@ Stage-0 key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ - Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col2 (type: int) - Merge Join Operator [MERGEJOIN_31] + Merge Join Operator [MERGEJOIN_29] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] | Reduce Output Operator [RS_16] | sort order: @@ -3895,10 +3896,10 @@ Stage-0 |<-Reducer 5 [SIMPLE_EDGE] Reduce Output Operator [RS_17] sort order: - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_9] - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_28] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_11] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_10] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_8] @@ -3916,7 +3917,7 @@ Stage-0 Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_29] + Filter Operator [FIL_27] predicate:((p_size < 10) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3955,40 +3956,40 @@ Stage-0 Reducer 4 File Output Operator [FS_37] compressed:false - Statistics:Num rows: 15 Data size: 1966 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_36] | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 15 Data size: 1966 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_35] key expressions:_col0 (type: string) sort order:+ - Statistics:Num rows: 15 Data size: 1966 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: int) Select Operator [SEL_34] outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 15 Data size: 1966 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_40] + Statistics:Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_33] predicate:_col3 is null (type: boolean) - Statistics:Num rows: 15 Data size: 1966 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_47] + Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_43] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"UDFToDouble(_col1) (type: double)","1":"_col0 (type: double)"} | outputColumnNames:["_col0","_col1","_col3"] - | Statistics:Num rows: 30 Data size: 3932 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_30] | key expressions:UDFToDouble(_col1) (type: double) | Map-reduce partition columns:UDFToDouble(_col1) (type: double) | sort order:+ - | Statistics:Num rows: 28 Data size: 3575 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int) - | Merge Join Operator [MERGEJOIN_46] + | Merge Join Operator [MERGEJOIN_42] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{} | | outputColumnNames:["_col0","_col1"] - | | Statistics:Num rows: 28 Data size: 3575 Basic stats: COMPLETE Column stats: NONE + | | Statistics:Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] | | Reduce Output Operator [RS_27] | | sort order: @@ -4003,19 +4004,19 @@ Stage-0 | |<-Reducer 6 [SIMPLE_EDGE] | Reduce Output Operator [RS_28] | sort order: - | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - | Select Operator [SEL_16] - | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - | Filter Operator [FIL_41] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_18] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_17] | predicate:(_col0 = 0) (type: boolean) | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_15] | aggregations:["count()"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] + | Select Operator [SEL_11] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_42] + | Filter Operator [FIL_10] | predicate:_col0 is null (type: boolean) | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_8] @@ -4031,7 +4032,7 @@ Stage-0 | aggregations:["avg(p_size)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - | Filter Operator [FIL_43] + | Filter Operator [FIL_40] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] @@ -4056,7 +4057,7 @@ Stage-0 aggregations:["avg(p_size)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_45] + Filter Operator [FIL_41] predicate:(p_size < 10) (type: boolean) Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_19] @@ -4101,28 +4102,28 @@ Stage-0 Reducer 5 File Output Operator [FS_39] compressed:false - Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE 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 [SEL_38] | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] Reduce Output Operator [RS_37] key expressions:_col0 (type: string) sort order:+ - Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE + Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: double) Select Operator [SEL_36] outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_42] + Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_35] predicate:_col3 is null (type: boolean) - Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_48] + Statistics:Num rows: 1 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_43] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: double)","1":"_col0 (type: string), _col1 (type: double)"} | outputColumnNames:["_col0","_col1","_col3"] - | Statistics:Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 1 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 10 [SIMPLE_EDGE] | Reduce Output Operator [RS_33] | key expressions:_col0 (type: string), _col1 (type: double) @@ -4132,7 +4133,7 @@ Stage-0 | Select Operator [SEL_27] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_45] + | Filter Operator [FIL_26] | predicate:((_col2 - _col1) > 600.0) (type: boolean) | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_25] @@ -4152,20 +4153,23 @@ Stage-0 | keys:p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_21] - | alias:b + | Select Operator [SEL_22] + | outputColumnNames:["p_mfgr","p_retailprice"] | Statistics:Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_21] + | alias:b + | Statistics:Num rows: 26 Data size: 2756 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] Reduce Output Operator [RS_32] key expressions:_col0 (type: string), _col1 (type: double) Map-reduce partition columns:_col0 (type: string), _col1 (type: double) sort order:++ - Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_47] + Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_42] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] | Reduce Output Operator [RS_29] | sort order: @@ -4197,10 +4201,10 @@ Stage-0 |<-Reducer 8 [SIMPLE_EDGE] Reduce Output Operator [RS_30] sort order: - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_18] - Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_43] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_20] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_19] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_17] @@ -4218,8 +4222,8 @@ Stage-0 Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_13] Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_44] - predicate:((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean) + Filter Operator [FIL_12] + predicate:(((_col2 - _col1) > 600.0) and (_col0 is null or _col1 is null)) (type: boolean) Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator [GBY_11] | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] @@ -4420,50 +4424,50 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_22] + File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Group By Operator [GBY_20] + Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) - Group By Operator [GBY_18] + Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_16] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_15] + Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_14] + Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_13] + Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -4471,14 +4475,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:x | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -4486,7 +4490,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_24] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -4517,50 +4521,50 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_22] + File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Group By Operator [GBY_20] + Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) - Group By Operator [GBY_18] + Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_16] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_15] + Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_14] + Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_13] + Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -4568,14 +4572,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:x | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -4583,7 +4587,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_24] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -4614,51 +4618,51 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_22] + File Output Operator [FS_20] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Group By Operator [GBY_20] + Group By Operator [GBY_18] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) - Group By Operator [GBY_18] + Group By Operator [GBY_16] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_16] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_15] + Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_14] + Reduce Output Operator [RS_12] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_13] + Group By Operator [GBY_11] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator [MAPJOIN_27] + Map Join Operator [MAPJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [BROADCAST_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -4666,7 +4670,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] @@ -4675,7 +4679,7 @@ Stage-0 |<-Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_24] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -4706,50 +4710,50 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_24] + File Output Operator [FS_22] compressed:false Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Group By Operator [GBY_22] + Group By Operator [GBY_20] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_21] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint), _col1 (type: bigint) - Group By Operator [GBY_20] + Group By Operator [GBY_18] aggregations:["sum(_col0)","sum(_col1)"] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_18] + Select Operator [SEL_16] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_17] + Group By Operator [GBY_15] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_16] + Reduce Output Operator [RS_14] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_15] + Group By Operator [GBY_13] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_29] + Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -4757,14 +4761,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_27] + | Filter Operator [FIL_25] | predicate:key is not null (type: boolean) | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:x | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -4776,7 +4780,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_28] + Filter Operator [FIL_26] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -5153,7 +5157,7 @@ Stage-0 compressed:true Statistics:Num rows: 250000 Data size: 21750000 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_11] + Merge Join Operator [MERGEJOIN_10] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0"] @@ -6295,17 +6299,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_14] + File Output Operator [FS_12] compressed:true Statistics:Num rows: 2 Data size: 13 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"} - Merge Join Operator [MERGEJOIN_19] + Merge Join Operator [MERGEJOIN_17] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 13 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_8] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ @@ -6314,14 +6318,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_17] + | Filter Operator [FIL_15] | predicate:id is not null (type: boolean) | Statistics:Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:sales | Statistics:Num rows: 1 Data size: 13 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_9] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ @@ -6333,7 +6337,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_18] + Filter Operator [FIL_16] predicate:id is not null (type: boolean) Statistics:Num rows: 2 Data size: 12 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -6371,30 +6375,30 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_30] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) - | Map Join Operator [MAPJOIN_29] + | Map Join Operator [MAPJOIN_25] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 1":"_col0 (type: string)","Map 3":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 3 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_12] + | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -6402,7 +6406,7 @@ Stage-0 | | Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_27] + | | Filter Operator [FIL_23] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_3] @@ -6411,14 +6415,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_26] - | predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + | Filter Operator [FIL_22] + | predicate:((value > 'val_450') and key is not null) (type: boolean) | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:srcpart | Statistics:Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -6426,7 +6430,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_28] + Filter Operator [FIL_24] predicate:(value > 'val_450') (type: boolean) Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -6448,30 +6452,30 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_30] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) - | Map Join Operator [MAPJOIN_29] + | Map Join Operator [MAPJOIN_25] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 1":"_col0 (type: string)","Map 3":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 3 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_12] + | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -6479,7 +6483,7 @@ Stage-0 | | Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_27] + | | Filter Operator [FIL_23] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_3] @@ -6488,14 +6492,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_26] - | predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + | Filter Operator [FIL_22] + | predicate:((value > 'val_450') and key is not null) (type: boolean) | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:srcpart | Statistics:Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -6503,7 +6507,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_28] + Filter Operator [FIL_24] predicate:(value > 'val_450') (type: boolean) Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -6525,30 +6529,30 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:true Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_30] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 555 Data size: 48285 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string) - | Map Join Operator [MAPJOIN_29] + | Map Join Operator [MAPJOIN_25] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 1":"_col0 (type: string)","Map 3":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 241 Data size: 42898 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 3 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_12] + | | Reduce Output Operator [RS_10] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -6556,7 +6560,7 @@ Stage-0 | | Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_27] + | | Filter Operator [FIL_23] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_3] @@ -6565,14 +6569,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_26] - | predicate:(((value > 'val_450') and key is not null) and value is not null) (type: boolean) + | Filter Operator [FIL_22] + | predicate:((value > 'val_450') and key is not null) (type: boolean) | Statistics:Num rows: 666 Data size: 118548 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:srcpart | Statistics:Num rows: 2000 Data size: 356000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -6580,7 +6584,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col0"] Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_28] + Filter Operator [FIL_24] predicate:(value > 'val_450') (type: boolean) Statistics:Num rows: 166 Data size: 15106 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_6] @@ -8137,20 +8141,20 @@ Stage-3 Dependency Collection{} Stage-1 Reducer 2 - File Output Operator [FS_13] + File Output Operator [FS_11] compressed:true Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE 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.dest_j1"} - Select Operator [SEL_11] + Select Operator [SEL_9] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1219 Data size: 115805 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_18] + Merge Join Operator [MERGEJOIN_16] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col2"] | Statistics:Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -8158,14 +8162,14 @@ Stage-3 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_16] + | Filter Operator [FIL_14] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src1 | Statistics:Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -8174,7 +8178,7 @@ Stage-3 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_17] + Filter Operator [FIL_15] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -8455,17 +8459,17 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_12] + File Output Operator [FS_10] compressed:true Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE 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"} - Merge Join Operator [MERGEJOIN_17] + Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1219 Data size: 433964 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -8474,14 +8478,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_15] + | Filter Operator [FIL_13] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:src | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -8490,7 +8494,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_16] + Filter Operator [FIL_14] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -8577,40 +8581,40 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_18] + File Output Operator [FS_16] compressed:true Statistics:Num rows: 1 Data size: 16 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"} - Group By Operator [GBY_16] + Group By Operator [GBY_14] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_13] sort order: Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint), _col1 (type: bigint) - Group By Operator [GBY_14] + Group By Operator [GBY_12] | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: int), _col1 (type: int) - Select Operator [SEL_11] + Select Operator [SEL_9] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_23] + Map Join Operator [MAPJOIN_21] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | outputColumnNames:["_col0","_col2"] | Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -8619,7 +8623,7 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_22] + | Filter Operator [FIL_20] | predicate:key is not null (type: boolean) | Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -8628,7 +8632,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_21] + Filter Operator [FIL_19] predicate:key is not null (type: boolean) Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -8651,35 +8655,35 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_18] + File Output Operator [FS_16] compressed:true Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [GBY_16] + Group By Operator [GBY_14] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_13] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_14] + Group By Operator [GBY_12] | aggregations:["count(1)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] Map-reduce partition columns:rand() (type: double) sort order: Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_23] + Map Join Operator [MAPJOIN_21] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col0 (type: string)","Map 4":"_col0 (type: string)"} | Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] - | Reduce Output Operator [RS_9] + | Reduce Output Operator [RS_7] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -8687,7 +8691,7 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_22] + | Filter Operator [FIL_20] | predicate:key is not null (type: boolean) | Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -8696,7 +8700,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_21] + Filter Operator [FIL_19] predicate:key is not null (type: boolean) Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -8745,16 +8749,16 @@ Stage-0 Select Operator [SEL_7] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_17] + Map Join Operator [MAPJOIN_16] | condition map:[{"":"Left Outer Join0 to 1"}] | HybridGraceHashJoin:true - | keys:{"Map 1":"UDFToDouble(_col0) (type: double)","Map 4":"(UDFToDouble(_col0) + UDFToDouble(1)) (type: double)"} + | keys:{"Map 1":"UDFToDouble(_col0) (type: double)","Map 4":"(UDFToDouble(_col0) + 1.0) (type: double)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [BROADCAST_EDGE] | Reduce Output Operator [RS_5] - | key expressions:(UDFToDouble(_col0) + UDFToDouble(1)) (type: double) - | Map-reduce partition columns:(UDFToDouble(_col0) + UDFToDouble(1)) (type: double) + | key expressions:(UDFToDouble(_col0) + 1.0) (type: double) + | Map-reduce partition columns:(UDFToDouble(_col0) + 1.0) (type: double) | sort order:+ | Statistics:Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: string) diff --git ql/src/test/results/clientpositive/tez/explainuser_2.q.out ql/src/test/results/clientpositive/tez/explainuser_2.q.out index 61a9580..d12c1e9 100644 --- ql/src/test/results/clientpositive/tez/explainuser_2.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_2.q.out @@ -189,20 +189,20 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:false Statistics:Num rows: 605 Data size: 6427 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 [SEL_19] + Select Operator [SEL_15] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_30] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col3 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col3","_col6"] | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_13] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -211,26 +211,26 @@ Stage-0 | Select Operator [SEL_8] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_28] + | Filter Operator [FIL_24] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_6] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_12] key expressions:_col3 (type: string) Map-reduce partition columns:_col3 (type: string) sort order:+ Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: string) - Merge Join Operator [MERGEJOIN_29] + Merge Join Operator [MERGEJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0","_col3"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] + | Reduce Output Operator [RS_9] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -238,14 +238,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_26] + | Filter Operator [FIL_22] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:z | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_10] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -254,7 +254,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_27] + Filter Operator [FIL_23] predicate:(key is not null and value is not null) (type: boolean) Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -335,79 +335,79 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_55] compressed:false Statistics:Num rows: 100 Data size: 1000 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"} - Limit [LIM_68] + Limit [LIM_54] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_53] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_52] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Select Operator [SEL_65] + Select Operator [SEL_51] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_64] + Group By Operator [GBY_50] | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] + Reduce Output Operator [RS_49] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] + Group By Operator [GBY_48] aggregations:["count(_col13)","count(_col21)","count(_col3)"] keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_61] + Select Operator [SEL_47] outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_111] + Merge Join Operator [MERGEJOIN_97] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string), _col3 (type: string)","1":"_col15 (type: string), _col17 (type: string)"} | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] | Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE |<-Reducer 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_59] + | Reduce Output Operator [RS_45] | key expressions:_col15 (type: string), _col17 (type: string) | Map-reduce partition columns:_col15 (type: string), _col17 (type: string) | sort order:++ | Statistics:Num rows: 1464 Data size: 15552 Basic stats: COMPLETE Column stats: NONE | value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) - | Select Operator [SEL_50] - | outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + | Select Operator [SEL_40] + | outputColumnNames:["_col6","_col7","_col14","_col15","_col17"] | Statistics:Num rows: 1464 Data size: 15552 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_110] + | Merge Join Operator [MERGEJOIN_96] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col4 (type: string), _col6 (type: string)","1":"_col2 (type: string), _col4 (type: string)"} | | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] | | Statistics:Num rows: 1464 Data size: 15552 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 10 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_46] + | | Reduce Output Operator [RS_37] | | key expressions:_col4 (type: string), _col6 (type: string) | | Map-reduce partition columns:_col4 (type: string), _col6 (type: string) | | sort order:++ | | Statistics:Num rows: 1331 Data size: 14139 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col2 (type: string), _col3 (type: string) - | | Merge Join Operator [MERGEJOIN_108] + | | Merge Join Operator [MERGEJOIN_94] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"0":"_col3 (type: string)","1":"_col1 (type: string)"} | | | outputColumnNames:["_col2","_col3","_col4","_col6"] | | | Statistics:Num rows: 1331 Data size: 14139 Basic stats: COMPLETE Column stats: NONE | | |<-Map 14 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_43] + | | | Reduce Output Operator [RS_35] | | | key expressions:_col1 (type: string) | | | Map-reduce partition columns:_col1 (type: string) | | | sort order:+ @@ -415,26 +415,26 @@ Stage-0 | | | Select Operator [SEL_17] | | | outputColumnNames:["_col1"] | | | Statistics:Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_102] + | | | Filter Operator [FIL_88] | | | predicate:((key = 'src1key') and value is not null) (type: boolean) | | | Statistics:Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_15] | | | alias:src1 | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | |<-Reducer 9 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_41] + | | Reduce Output Operator [RS_34] | | key expressions:_col3 (type: string) | | Map-reduce partition columns:_col3 (type: string) | | sort order:+ | | Statistics:Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col2 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_107] + | | Merge Join Operator [MERGEJOIN_93] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | | | outputColumnNames:["_col2","_col3","_col4","_col6"] | | | Statistics:Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE | | |<-Map 13 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_38] + | | | Reduce Output Operator [RS_32] | | | key expressions:_col0 (type: string) | | | Map-reduce partition columns:_col0 (type: string) | | | sort order:+ @@ -442,26 +442,26 @@ Stage-0 | | | Select Operator [SEL_14] | | | outputColumnNames:["_col0"] | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_101] + | | | Filter Operator [FIL_87] | | | predicate:((value = 'd1value') and key is not null) (type: boolean) | | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_12] | | | alias:d1 | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | |<-Reducer 8 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_36] + | | Reduce Output Operator [RS_31] | | key expressions:_col2 (type: string) | | Map-reduce partition columns:_col2 (type: string) | | sort order:+ | | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_106] + | | Merge Join Operator [MERGEJOIN_92] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | keys:{"0":"_col1 (type: string)","1":"_col3 (type: string)"} | | | outputColumnNames:["_col2","_col3","_col4","_col6"] | | | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE | | |<-Map 12 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_33] + | | | Reduce Output Operator [RS_29] | | | key expressions:_col3 (type: string) | | | Map-reduce partition columns:_col3 (type: string) | | | sort order:+ @@ -470,14 +470,14 @@ Stage-0 | | | Select Operator [SEL_11] | | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] | | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_100] + | | | Filter Operator [FIL_86] | | | predicate:(((((k3 is not null and (v3 = 'ssv3')) and k2 is not null) and k1 is not null) and v1 is not null) and v2 is not null) (type: boolean) | | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE | | | TableScan [TS_9] | | | alias:ss | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE | | |<-Map 7 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_31] + | | Reduce Output Operator [RS_28] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ @@ -485,26 +485,26 @@ Stage-0 | | Select Operator [SEL_8] | | outputColumnNames:["_col1"] | | Statistics:Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_99] + | | Filter Operator [FIL_85] | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) | | Statistics:Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_6] | | alias:srcpart | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 16 [SIMPLE_EDGE] - | Reduce Output Operator [RS_48] + | Reduce Output Operator [RS_38] | key expressions:_col2 (type: string), _col4 (type: string) | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) | sort order:++ | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | value expressions:_col3 (type: string), _col5 (type: string) - | Merge Join Operator [MERGEJOIN_109] + | Merge Join Operator [MERGEJOIN_95] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col3","_col4","_col5"] | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | |<-Map 15 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_25] + | | Reduce Output Operator [RS_24] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -513,14 +513,14 @@ Stage-0 | | Select Operator [SEL_20] | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] + | | Filter Operator [FIL_89] | | predicate:((((((v1 = 'srv1') and k3 is not null) and k2 is not null) and v3 is not null) and v2 is not null) and k1 is not null) (type: boolean) | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_18] | | alias:sr | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE | |<-Map 17 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_25] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -528,26 +528,26 @@ Stage-0 | Select Operator [SEL_23] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] + | Filter Operator [FIL_90] | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_21] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_57] + Reduce Output Operator [RS_44] key expressions:_col1 (type: string), _col3 (type: string) Map-reduce partition columns:_col1 (type: string), _col3 (type: string) sort order:++ Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: string) - Merge Join Operator [MERGEJOIN_105] + Merge Join Operator [MERGEJOIN_91] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2","_col3"] | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_52] + | Reduce Output Operator [RS_41] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -556,14 +556,14 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_97] + | Filter Operator [FIL_83] | predicate:((v3 is not null and v2 is not null) and k1 is not null) (type: boolean) | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:cs | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_54] + Reduce Output Operator [RS_42] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ @@ -571,7 +571,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_98] + Filter Operator [FIL_84] predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -616,148 +616,148 @@ Stage-0 limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_67] + File Output Operator [FS_59] compressed:false Statistics:Num rows: 550 Data size: 5843 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"} - Group By Operator [GBY_65] + Group By Operator [GBY_57] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 6 [SIMPLE_EDGE] |<-Reducer 15 [CONTAINS] - | Reduce Output Operator [RS_64] + | Reduce Output Operator [RS_56] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_63] + | Group By Operator [GBY_55] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_59] + | Select Operator [SEL_51] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_93] + | Merge Join Operator [MERGEJOIN_85] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 18 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_57] + | | Reduce Output Operator [RS_49] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_48] + | | Select Operator [SEL_44] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_89] + | | Filter Operator [FIL_81] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_46] + | | TableScan [TS_42] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 14 [SIMPLE_EDGE] - | Reduce Output Operator [RS_55] + | Reduce Output Operator [RS_48] | key expressions:_col2 (type: string) | Map-reduce partition columns:_col2 (type: string) | sort order:+ | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: string) - | Merge Join Operator [MERGEJOIN_92] + | Merge Join Operator [MERGEJOIN_84] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE | |<-Map 17 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_52] + | | Reduce Output Operator [RS_46] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_45] + | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_88] + | | Filter Operator [FIL_80] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_43] + | | TableScan [TS_39] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 13 [SIMPLE_EDGE] - | Reduce Output Operator [RS_50] + | Reduce Output Operator [RS_45] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_42] + | Select Operator [SEL_38] | outputColumnNames:["_col1"] | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_41] + | Group By Operator [GBY_37] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 12 [SIMPLE_EDGE] | |<-Map 11 [CONTAINS] - | | Reduce Output Operator [RS_40] + | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_39] + | | Group By Operator [GBY_35] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_32] + | | Select Operator [SEL_28] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_86] + | | Filter Operator [FIL_78] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_30] + | | TableScan [TS_26] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 16 [CONTAINS] - | Reduce Output Operator [RS_40] + | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_39] + | Group By Operator [GBY_35] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_35] + | Select Operator [SEL_31] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_87] + | Filter Operator [FIL_79] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_33] + | TableScan [TS_29] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 5 [CONTAINS] - Reduce Output Operator [RS_64] + Reduce Output Operator [RS_56] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_63] + Group By Operator [GBY_55] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_29] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_91] + Merge Join Operator [MERGEJOIN_83] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -765,26 +765,26 @@ Stage-0 | Select Operator [SEL_18] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_85] + | Filter Operator [FIL_77] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_16] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] + Reduce Output Operator [RS_22] key expressions:_col2 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:+ Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) - Merge Join Operator [MERGEJOIN_90] + Merge Join Operator [MERGEJOIN_82] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE |<-Map 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_20] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -793,14 +793,14 @@ Stage-0 | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_84] + | Filter Operator [FIL_76] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -826,7 +826,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_82] + | Filter Operator [FIL_74] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -845,7 +845,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_83] + Filter Operator [FIL_75] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -910,378 +910,378 @@ Stage-0 limit:-1 Stage-1 Reducer 9 - File Output Operator [FS_134] + File Output Operator [FS_122] compressed:false Statistics:Num rows: 550 Data size: 5843 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"} - Group By Operator [GBY_132] + Group By Operator [GBY_120] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 8 [SIMPLE_EDGE] |<-Reducer 32 [CONTAINS] - | Reduce Output Operator [RS_131] + | Reduce Output Operator [RS_119] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_130] + | Group By Operator [GBY_118] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_126] + | Select Operator [SEL_114] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_182] + | Merge Join Operator [MERGEJOIN_170] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col5"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 37 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_124] + | | Reduce Output Operator [RS_112] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_115] + | | Select Operator [SEL_107] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_176] + | | Filter Operator [FIL_164] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_113] + | | TableScan [TS_105] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 31 [SIMPLE_EDGE] - | Reduce Output Operator [RS_122] + | Reduce Output Operator [RS_111] | key expressions:_col2 (type: string) | Map-reduce partition columns:_col2 (type: string) | sort order:+ | Statistics:Num rows: 484 Data size: 5131 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_181] + | Merge Join Operator [MERGEJOIN_169] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | | outputColumnNames:["_col2"] | | Statistics:Num rows: 484 Data size: 5131 Basic stats: COMPLETE Column stats: NONE | |<-Map 36 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_119] + | | Reduce Output Operator [RS_109] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_112] + | | Select Operator [SEL_104] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_175] + | | Filter Operator [FIL_163] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_110] + | | TableScan [TS_102] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 30 [SIMPLE_EDGE] - | Reduce Output Operator [RS_117] + | Reduce Output Operator [RS_108] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_109] + | Select Operator [SEL_101] | outputColumnNames:["_col1"] | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_108] + | Group By Operator [GBY_100] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE | |<-Union 29 [SIMPLE_EDGE] | |<-Map 35 [CONTAINS] - | | Reduce Output Operator [RS_107] + | | Reduce Output Operator [RS_99] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_106] + | | Group By Operator [GBY_98] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_102] + | | Select Operator [SEL_94] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_174] + | | Filter Operator [FIL_162] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_100] + | | TableScan [TS_92] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 28 [CONTAINS] - | Reduce Output Operator [RS_107] + | Reduce Output Operator [RS_99] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_106] + | Group By Operator [GBY_98] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_98] + | Group By Operator [GBY_90] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 27 [SIMPLE_EDGE] | |<-Map 34 [CONTAINS] - | | Reduce Output Operator [RS_97] + | | Reduce Output Operator [RS_89] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_96] + | | Group By Operator [GBY_88] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_92] + | | Select Operator [SEL_84] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_173] + | | Filter Operator [FIL_161] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_90] + | | TableScan [TS_82] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 26 [CONTAINS] - | Reduce Output Operator [RS_97] + | Reduce Output Operator [RS_89] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_96] + | Group By Operator [GBY_88] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_88] + | Group By Operator [GBY_80] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 25 [SIMPLE_EDGE] | |<-Map 24 [CONTAINS] - | | Reduce Output Operator [RS_87] + | | Reduce Output Operator [RS_79] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_86] + | | Group By Operator [GBY_78] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_79] + | | Select Operator [SEL_71] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_171] + | | Filter Operator [FIL_159] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_77] + | | TableScan [TS_69] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 33 [CONTAINS] - | Reduce Output Operator [RS_87] + | Reduce Output Operator [RS_79] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_86] + | Group By Operator [GBY_78] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_82] + | Select Operator [SEL_74] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_172] + | Filter Operator [FIL_160] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_80] + | TableScan [TS_72] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 7 [CONTAINS] - Reduce Output Operator [RS_131] + Reduce Output Operator [RS_119] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_130] + Group By Operator [GBY_118] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_75] + Group By Operator [GBY_67] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 6 [SIMPLE_EDGE] |<-Reducer 19 [CONTAINS] - | Reduce Output Operator [RS_74] + | Reduce Output Operator [RS_66] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_73] + | Group By Operator [GBY_65] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_69] + | Select Operator [SEL_61] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_180] + | Merge Join Operator [MERGEJOIN_168] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col5"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 23 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_67] + | | Reduce Output Operator [RS_59] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_58] + | | Select Operator [SEL_54] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_170] + | | Filter Operator [FIL_158] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_56] + | | TableScan [TS_52] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 18 [SIMPLE_EDGE] - | Reduce Output Operator [RS_65] + | Reduce Output Operator [RS_58] | key expressions:_col2 (type: string) | Map-reduce partition columns:_col2 (type: string) | sort order:+ | Statistics:Num rows: 419 Data size: 4431 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_179] + | Merge Join Operator [MERGEJOIN_167] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | | outputColumnNames:["_col2"] | | Statistics:Num rows: 419 Data size: 4431 Basic stats: COMPLETE Column stats: NONE | |<-Map 22 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_62] + | | Reduce Output Operator [RS_56] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_55] + | | Select Operator [SEL_51] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_169] + | | Filter Operator [FIL_157] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_53] + | | TableScan [TS_49] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 17 [SIMPLE_EDGE] - | Reduce Output Operator [RS_60] + | Reduce Output Operator [RS_55] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_52] + | Select Operator [SEL_48] | outputColumnNames:["_col1"] | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_51] + | Group By Operator [GBY_47] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 16 [SIMPLE_EDGE] | |<-Map 21 [CONTAINS] - | | Reduce Output Operator [RS_50] + | | Reduce Output Operator [RS_46] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_49] + | | Group By Operator [GBY_45] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_45] + | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_168] + | | Filter Operator [FIL_156] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_43] + | | TableScan [TS_39] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 15 [CONTAINS] - | Reduce Output Operator [RS_50] + | Reduce Output Operator [RS_46] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_49] + | Group By Operator [GBY_45] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_41] + | Group By Operator [GBY_37] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 14 [SIMPLE_EDGE] | |<-Map 13 [CONTAINS] - | | Reduce Output Operator [RS_40] + | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_39] + | | Group By Operator [GBY_35] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_32] + | | Select Operator [SEL_28] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_166] + | | Filter Operator [FIL_154] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_30] + | | TableScan [TS_26] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 20 [CONTAINS] - | Reduce Output Operator [RS_40] + | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_39] + | Group By Operator [GBY_35] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_35] + | Select Operator [SEL_31] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_167] + | Filter Operator [FIL_155] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_33] + | TableScan [TS_29] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 5 [CONTAINS] - Reduce Output Operator [RS_74] + Reduce Output Operator [RS_66] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_73] + Group By Operator [GBY_65] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_29] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_178] + Merge Join Operator [MERGEJOIN_166] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col2","_col5"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 12 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1290,25 +1290,25 @@ Stage-0 | Select Operator [SEL_18] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_165] + | Filter Operator [FIL_153] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_16] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] + Reduce Output Operator [RS_22] key expressions:_col2 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:+ Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_177] + Merge Join Operator [MERGEJOIN_165] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col2"] | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_20] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -1317,14 +1317,14 @@ Stage-0 | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_164] + | Filter Operator [FIL_152] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -1350,7 +1350,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_162] + | Filter Operator [FIL_150] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -1369,7 +1369,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_163] + Filter Operator [FIL_151] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -1396,21 +1396,21 @@ Stage-0 limit:-1 Stage-1 Map 1 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:false Statistics:Num rows: 605 Data size: 6427 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 [SEL_19] + Select Operator [SEL_15] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_30] + Map Join Operator [MAPJOIN_26] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col3 (type: string)","Map 3":"_col0 (type: string)"} | outputColumnNames:["_col0","_col3","_col6"] | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [BROADCAST_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_13] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1419,20 +1419,20 @@ Stage-0 | Select Operator [SEL_8] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_28] + | Filter Operator [FIL_24] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_6] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_29] + |<-Map Join Operator [MAPJOIN_25] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col1 (type: string)"} | outputColumnNames:["_col0","_col3"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 2 [BROADCAST_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -1441,7 +1441,7 @@ Stage-0 | Select Operator [SEL_5] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_27] + | Filter Operator [FIL_23] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -1450,7 +1450,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_26] + Filter Operator [FIL_22] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -1527,66 +1527,66 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_55] compressed:false Statistics:Num rows: 100 Data size: 1000 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"} - Limit [LIM_68] + Limit [LIM_54] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_53] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_52] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Select Operator [SEL_65] + Select Operator [SEL_51] outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_64] + Group By Operator [GBY_50] | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 805 Data size: 8553 Basic stats: COMPLETE Column stats: NONE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] + Reduce Output Operator [RS_49] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] + Group By Operator [GBY_48] aggregations:["count(_col13)","count(_col21)","count(_col3)"] keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_61] + Select Operator [SEL_47] outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_111] + Map Join Operator [MAPJOIN_97] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 1":"_col1 (type: string), _col3 (type: string)","Map 3":"_col15 (type: string), _col17 (type: string)"} | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] | Statistics:Num rows: 1610 Data size: 17107 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [BROADCAST_EDGE] - | Reduce Output Operator [RS_57] + | Reduce Output Operator [RS_44] | key expressions:_col1 (type: string), _col3 (type: string) | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) | sort order:++ | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | value expressions:_col2 (type: string) - | Map Join Operator [MAPJOIN_105] + | Map Join Operator [MAPJOIN_91] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2","_col3"] | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | |<-Map 2 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_54] + | | Reduce Output Operator [RS_42] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -1594,7 +1594,7 @@ Stage-0 | | Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_98] + | | Filter Operator [FIL_84] | | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -1603,36 +1603,36 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_97] + | Filter Operator [FIL_83] | predicate:((v3 is not null and v2 is not null) and k1 is not null) (type: boolean) | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:cs | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_50] - outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + |<-Select Operator [SEL_40] + outputColumnNames:["_col6","_col7","_col14","_col15","_col17"] Statistics:Num rows: 1464 Data size: 15552 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_110] + Map Join Operator [MAPJOIN_96] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 3":"_col4 (type: string), _col6 (type: string)","Map 10":"_col2 (type: string), _col4 (type: string)"} | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] | Statistics:Num rows: 1464 Data size: 15552 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [BROADCAST_EDGE] - | Reduce Output Operator [RS_48] + | Reduce Output Operator [RS_38] | key expressions:_col2 (type: string), _col4 (type: string) | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) | sort order:++ | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | value expressions:_col3 (type: string), _col5 (type: string) - | Map Join Operator [MAPJOIN_109] + | Map Join Operator [MAPJOIN_95] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 9":"_col0 (type: string)","Map 10":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col3","_col4","_col5"] | | Statistics:Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE | |<-Map 9 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_25] + | | Reduce Output Operator [RS_24] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ @@ -1641,7 +1641,7 @@ Stage-0 | | Select Operator [SEL_20] | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] + | | Filter Operator [FIL_89] | | predicate:((((((v1 = 'srv1') and k3 is not null) and k2 is not null) and v3 is not null) and v2 is not null) and k1 is not null) (type: boolean) | | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_18] @@ -1650,20 +1650,20 @@ Stage-0 | |<-Select Operator [SEL_23] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] + | Filter Operator [FIL_90] | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_21] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_108] + |<-Map Join Operator [MAPJOIN_94] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 3":"_col3 (type: string)","Map 8":"_col1 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] | Statistics:Num rows: 1331 Data size: 14139 Basic stats: COMPLETE Column stats: NONE |<-Map 8 [BROADCAST_EDGE] - | Reduce Output Operator [RS_43] + | Reduce Output Operator [RS_35] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -1671,20 +1671,20 @@ Stage-0 | Select Operator [SEL_17] | outputColumnNames:["_col1"] | Statistics:Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_102] + | Filter Operator [FIL_88] | predicate:((key = 'src1key') and value is not null) (type: boolean) | Statistics:Num rows: 12 Data size: 91 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_15] | alias:src1 | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_107] + |<-Map Join Operator [MAPJOIN_93] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 3":"_col2 (type: string)","Map 7":"_col0 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] | Statistics:Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [BROADCAST_EDGE] - | Reduce Output Operator [RS_38] + | Reduce Output Operator [RS_32] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1692,20 +1692,20 @@ Stage-0 | Select Operator [SEL_14] | outputColumnNames:["_col0"] | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_101] + | Filter Operator [FIL_87] | predicate:((value = 'd1value') and key is not null) (type: boolean) | Statistics:Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_12] | alias:d1 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_106] + |<-Map Join Operator [MAPJOIN_92] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 3":"_col1 (type: string)","Map 6":"_col3 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [BROADCAST_EDGE] - | Reduce Output Operator [RS_33] + | Reduce Output Operator [RS_29] | key expressions:_col3 (type: string) | Map-reduce partition columns:_col3 (type: string) | sort order:+ @@ -1714,7 +1714,7 @@ Stage-0 | Select Operator [SEL_11] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_100] + | Filter Operator [FIL_86] | predicate:(((((k3 is not null and (v3 = 'ssv3')) and k2 is not null) and k1 is not null) and v1 is not null) and v2 is not null) (type: boolean) | Statistics:Num rows: 42 Data size: 1455 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_9] @@ -1723,7 +1723,7 @@ Stage-0 |<-Select Operator [SEL_8] outputColumnNames:["_col1"] Statistics:Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_99] + Filter Operator [FIL_85] predicate:((key = 'srcpartkey') and value is not null) (type: boolean) Statistics:Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE TableScan [TS_6] @@ -1764,138 +1764,138 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_67] + File Output Operator [FS_59] compressed:false Statistics:Num rows: 550 Data size: 5843 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"} - Group By Operator [GBY_65] + Group By Operator [GBY_57] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 4 [SIMPLE_EDGE] |<-Reducer 11 [CONTAINS] - | Reduce Output Operator [RS_64] + | Reduce Output Operator [RS_56] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_63] + | Group By Operator [GBY_55] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_59] + | Select Operator [SEL_51] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_93] + | Map Join Operator [MAPJOIN_85] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 11":"_col2 (type: string)","Map 14":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 14 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_57] + | | Reduce Output Operator [RS_49] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_48] + | | Select Operator [SEL_44] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_89] + | | Filter Operator [FIL_81] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_46] + | | TableScan [TS_42] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | |<-Map Join Operator [MAPJOIN_92] + | |<-Map Join Operator [MAPJOIN_84] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 11":"_col1 (type: string)","Map 13":"_col1 (type: string)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE | |<-Map 13 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_52] + | | Reduce Output Operator [RS_46] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_45] + | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_88] + | | Filter Operator [FIL_80] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_43] + | | TableScan [TS_39] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_42] + | |<-Select Operator [SEL_38] | outputColumnNames:["_col1"] | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_41] + | Group By Operator [GBY_37] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 10 [SIMPLE_EDGE] | |<-Map 12 [CONTAINS] - | | Reduce Output Operator [RS_40] + | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_39] + | | Group By Operator [GBY_35] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_35] + | | Select Operator [SEL_31] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_87] + | | Filter Operator [FIL_79] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_33] + | | TableScan [TS_29] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Map 9 [CONTAINS] - | Reduce Output Operator [RS_40] + | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_39] + | Group By Operator [GBY_35] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_32] + | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_86] + | Filter Operator [FIL_78] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_30] + | TableScan [TS_26] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [CONTAINS] - Reduce Output Operator [RS_64] + Reduce Output Operator [RS_56] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_63] + Group By Operator [GBY_55] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_29] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_91] + Map Join Operator [MAPJOIN_83] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Reducer 3":"_col2 (type: string)","Map 8":"_col0 (type: string)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 8 [BROADCAST_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -1903,20 +1903,20 @@ Stage-0 | Select Operator [SEL_18] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_85] + | Filter Operator [FIL_77] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_16] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_90] + |<-Map Join Operator [MAPJOIN_82] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Reducer 3":"_col1 (type: string)","Map 7":"_col1 (type: string)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [BROADCAST_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_20] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -1925,7 +1925,7 @@ Stage-0 | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_84] + | Filter Operator [FIL_76] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] @@ -1952,7 +1952,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_82] + | Filter Operator [FIL_74] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -1971,7 +1971,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_83] + Filter Operator [FIL_75] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -2030,359 +2030,359 @@ Stage-0 limit:-1 Stage-1 Reducer 7 - File Output Operator [FS_134] + File Output Operator [FS_122] compressed:false Statistics:Num rows: 550 Data size: 5843 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"} - Group By Operator [GBY_132] + Group By Operator [GBY_120] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 6 [SIMPLE_EDGE] |<-Reducer 26 [CONTAINS] - | Reduce Output Operator [RS_131] + | Reduce Output Operator [RS_119] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_130] + | Group By Operator [GBY_118] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_126] + | Select Operator [SEL_114] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_182] + | Map Join Operator [MAPJOIN_170] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 26":"_col2 (type: string)","Map 31":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col5"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 31 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_124] + | | Reduce Output Operator [RS_112] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_115] + | | Select Operator [SEL_107] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_176] + | | Filter Operator [FIL_164] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_113] + | | TableScan [TS_105] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | |<-Map Join Operator [MAPJOIN_181] + | |<-Map Join Operator [MAPJOIN_169] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 26":"_col1 (type: string)","Map 30":"_col1 (type: string)"} | | outputColumnNames:["_col2"] | | Statistics:Num rows: 484 Data size: 5131 Basic stats: COMPLETE Column stats: NONE | |<-Map 30 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_119] + | | Reduce Output Operator [RS_109] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_112] + | | Select Operator [SEL_104] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_175] + | | Filter Operator [FIL_163] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_110] + | | TableScan [TS_102] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_109] + | |<-Select Operator [SEL_101] | outputColumnNames:["_col1"] | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_108] + | Group By Operator [GBY_100] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE | |<-Union 25 [SIMPLE_EDGE] | |<-Map 29 [CONTAINS] - | | Reduce Output Operator [RS_107] + | | Reduce Output Operator [RS_99] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_106] + | | Group By Operator [GBY_98] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_102] + | | Select Operator [SEL_94] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_174] + | | Filter Operator [FIL_162] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_100] + | | TableScan [TS_92] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 24 [CONTAINS] - | Reduce Output Operator [RS_107] + | Reduce Output Operator [RS_99] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_106] + | Group By Operator [GBY_98] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_98] + | Group By Operator [GBY_90] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 23 [SIMPLE_EDGE] | |<-Map 28 [CONTAINS] - | | Reduce Output Operator [RS_97] + | | Reduce Output Operator [RS_89] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_96] + | | Group By Operator [GBY_88] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_92] + | | Select Operator [SEL_84] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_173] + | | Filter Operator [FIL_161] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_90] + | | TableScan [TS_82] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 22 [CONTAINS] - | Reduce Output Operator [RS_97] + | Reduce Output Operator [RS_89] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_96] + | Group By Operator [GBY_88] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_88] + | Group By Operator [GBY_80] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 21 [SIMPLE_EDGE] | |<-Map 20 [CONTAINS] - | | Reduce Output Operator [RS_87] + | | Reduce Output Operator [RS_79] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_86] + | | Group By Operator [GBY_78] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_79] + | | Select Operator [SEL_71] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_171] + | | Filter Operator [FIL_159] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_77] + | | TableScan [TS_69] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 27 [CONTAINS] - | Reduce Output Operator [RS_87] + | Reduce Output Operator [RS_79] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_86] + | Group By Operator [GBY_78] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_82] + | Select Operator [SEL_74] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_172] + | Filter Operator [FIL_160] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_80] + | TableScan [TS_72] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 5 [CONTAINS] - Reduce Output Operator [RS_131] + Reduce Output Operator [RS_119] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_130] + Group By Operator [GBY_118] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_75] + Group By Operator [GBY_67] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Union 4 [SIMPLE_EDGE] |<-Reducer 15 [CONTAINS] - | Reduce Output Operator [RS_74] + | Reduce Output Operator [RS_66] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_73] + | Group By Operator [GBY_65] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_69] + | Select Operator [SEL_61] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_180] + | Map Join Operator [MAPJOIN_168] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 15":"_col2 (type: string)","Map 19":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col5"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 19 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_67] + | | Reduce Output Operator [RS_59] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_58] + | | Select Operator [SEL_54] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_170] + | | Filter Operator [FIL_158] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_56] + | | TableScan [TS_52] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | |<-Map Join Operator [MAPJOIN_179] + | |<-Map Join Operator [MAPJOIN_167] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Reducer 15":"_col1 (type: string)","Map 18":"_col1 (type: string)"} | | outputColumnNames:["_col2"] | | Statistics:Num rows: 419 Data size: 4431 Basic stats: COMPLETE Column stats: NONE | |<-Map 18 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_62] + | | Reduce Output Operator [RS_56] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_55] + | | Select Operator [SEL_51] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_169] + | | Filter Operator [FIL_157] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_53] + | | TableScan [TS_49] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_52] + | |<-Select Operator [SEL_48] | outputColumnNames:["_col1"] | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_51] + | Group By Operator [GBY_47] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 14 [SIMPLE_EDGE] | |<-Map 17 [CONTAINS] - | | Reduce Output Operator [RS_50] + | | Reduce Output Operator [RS_46] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_49] + | | Group By Operator [GBY_45] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_45] + | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_168] + | | Filter Operator [FIL_156] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_43] + | | TableScan [TS_39] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 13 [CONTAINS] - | Reduce Output Operator [RS_50] + | Reduce Output Operator [RS_46] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_49] + | Group By Operator [GBY_45] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_41] + | Group By Operator [GBY_37] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 12 [SIMPLE_EDGE] | |<-Map 11 [CONTAINS] - | | Reduce Output Operator [RS_40] + | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_39] + | | Group By Operator [GBY_35] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_32] + | | Select Operator [SEL_28] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_166] + | | Filter Operator [FIL_154] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_30] + | | TableScan [TS_26] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 16 [CONTAINS] - | Reduce Output Operator [RS_40] + | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_39] + | Group By Operator [GBY_35] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_35] + | Select Operator [SEL_31] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_167] + | Filter Operator [FIL_155] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_33] + | TableScan [TS_29] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [CONTAINS] - Reduce Output Operator [RS_74] + Reduce Output Operator [RS_66] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_73] + Group By Operator [GBY_65] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_29] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_178] + Map Join Operator [MAPJOIN_166] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Reducer 3":"_col2 (type: string)","Map 10":"_col0 (type: string)"} | outputColumnNames:["_col2","_col5"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [BROADCAST_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -2391,20 +2391,20 @@ Stage-0 | Select Operator [SEL_18] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_165] + | Filter Operator [FIL_153] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_16] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_177] + |<-Map Join Operator [MAPJOIN_165] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Reducer 3":"_col1 (type: string)","Map 9":"_col1 (type: string)"} | outputColumnNames:["_col2"] | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE |<-Map 9 [BROADCAST_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_20] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -2413,7 +2413,7 @@ Stage-0 | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_164] + | Filter Operator [FIL_152] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] @@ -2440,7 +2440,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_162] + | Filter Operator [FIL_150] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -2459,7 +2459,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_163] + Filter Operator [FIL_151] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -2611,11 +2611,11 @@ Stage-0 limit:-1 Stage-1 Map 1 - File Output Operator [FS_12] + File Output Operator [FS_10] compressed:false Statistics:Num rows: 266 Data size: 2822 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"} - Merge Join Operator [MERGEJOIN_17] + Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0","_col1"] @@ -2624,7 +2624,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_16] + | Filter Operator [FIL_14] | predicate:key is not null (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -2633,7 +2633,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_15] + Filter Operator [FIL_13] predicate:key is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -2656,23 +2656,23 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:false Statistics:Num rows: 292 Data size: 3104 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"} - Merge Join Operator [MERGEJOIN_31] + Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 292 Data size: 3104 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: int) - | Merge Join Operator [MERGEJOIN_29] + | Merge Join Operator [MERGEJOIN_25] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col0","_col1"] @@ -2681,7 +2681,7 @@ Stage-0 | |<-Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_27] + | | Filter Operator [FIL_23] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -2690,14 +2690,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_26] + | Filter Operator [FIL_22] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -2705,7 +2705,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col1"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_28] + Filter Operator [FIL_24] predicate:value is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE TableScan [TS_6] @@ -2725,11 +2725,11 @@ Stage-0 limit:-1 Stage-1 Map 1 - File Output Operator [FS_12] + File Output Operator [FS_10] compressed:false Statistics:Num rows: 266 Data size: 2822 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"} - Merge Join Operator [MERGEJOIN_17] + Merge Join Operator [MERGEJOIN_15] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0","_col1"] @@ -2738,7 +2738,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_16] + | Filter Operator [FIL_14] | predicate:key is not null (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -2747,7 +2747,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_15] + Filter Operator [FIL_13] predicate:key is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -2770,23 +2770,23 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_20] + File Output Operator [FS_16] compressed:false Statistics:Num rows: 292 Data size: 3104 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"} - Merge Join Operator [MERGEJOIN_31] + Merge Join Operator [MERGEJOIN_27] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 292 Data size: 3104 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: int) - | Merge Join Operator [MERGEJOIN_29] + | Merge Join Operator [MERGEJOIN_25] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col0","_col1"] @@ -2795,7 +2795,7 @@ Stage-0 | |<-Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_27] + | | Filter Operator [FIL_23] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -2804,14 +2804,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_26] + | Filter Operator [FIL_22] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -2819,7 +2819,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col1"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_28] + Filter Operator [FIL_24] predicate:value is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE TableScan [TS_6] @@ -2851,50 +2851,50 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_30] + File Output Operator [FS_26] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [GBY_28] + Group By Operator [GBY_24] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_23] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_26] + Group By Operator [GBY_22] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_43] + Merge Join Operator [MERGEJOIN_39] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 558 Data size: 5926 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_19] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_19] + | Select Operator [SEL_17] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_40] + | Filter Operator [FIL_36] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_17] + | TableScan [TS_15] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 2 [SIMPLE_EDGE] |<-Map 1 [CONTAINS] - | Reduce Output Operator [RS_21] + | Reduce Output Operator [RS_18] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 508 Data size: 5388 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_41] + | Merge Join Operator [MERGEJOIN_37] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col0"] @@ -2903,7 +2903,7 @@ Stage-0 | |<-Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_38] + | | Filter Operator [FIL_34] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -2912,25 +2912,25 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_37] + | Filter Operator [FIL_33] | predicate:key is not null (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [CONTAINS] - Reduce Output Operator [RS_21] + Reduce Output Operator [RS_18] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 508 Data size: 5388 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_14] + Select Operator [SEL_12] outputColumnNames:["_col0"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_39] + Filter Operator [FIL_35] predicate:key is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_12] + TableScan [TS_10] alias:s1 Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE @@ -2959,77 +2959,77 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_38] + File Output Operator [FS_32] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [GBY_36] + Group By Operator [GBY_30] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_35] + Reduce Output Operator [RS_29] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_34] + Group By Operator [GBY_28] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_57] + Merge Join Operator [MERGEJOIN_51] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 587 Data size: 6237 Basic stats: COMPLETE Column stats: NONE |<-Map 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] + | Reduce Output Operator [RS_25] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_27] + | Select Operator [SEL_23] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_53] + | Filter Operator [FIL_47] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_25] + | TableScan [TS_21] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 3 [SIMPLE_EDGE] |<-Map 8 [CONTAINS] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_24] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 534 Data size: 5670 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_22] + | Select Operator [SEL_18] | outputColumnNames:["_col0"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_52] + | Filter Operator [FIL_46] | predicate:key is not null (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_20] + | TableScan [TS_16] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_29] + Reduce Output Operator [RS_24] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 534 Data size: 5670 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_56] + Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 292 Data size: 3104 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_15] + | Reduce Output Operator [RS_12] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE | value expressions:_col0 (type: int) - | Merge Join Operator [MERGEJOIN_54] + | Merge Join Operator [MERGEJOIN_48] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col0","_col1"] @@ -3038,7 +3038,7 @@ Stage-0 | |<-Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_50] + | | Filter Operator [FIL_44] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -3047,14 +3047,14 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_49] + | Filter Operator [FIL_43] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_13] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ @@ -3062,7 +3062,7 @@ Stage-0 Select Operator [SEL_8] outputColumnNames:["_col1"] Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_51] + Filter Operator [FIL_45] predicate:value is not null (type: boolean) Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE TableScan [TS_6] @@ -3118,276 +3118,276 @@ Stage-0 Stage-1 Union 4 |<-Map 18 [CONTAINS] - | File Output Operator [FS_90] + | File Output Operator [FS_78] | compressed:false | Statistics:Num rows: 3550 Data size: 37482 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 [SEL_88] + | Select Operator [SEL_76] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_135] + | Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 16":"_col1 (type: string)","Map 18":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col3"] | | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE | |<-Map 16 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_84] + | | Reduce Output Operator [RS_73] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col3 (type: string) - | | Map Join Operator [MAPJOIN_134] + | | Map Join Operator [MAPJOIN_122] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | HybridGraceHashJoin:true | | | keys:{"Map 16":"_col0 (type: string)","Map 17":"_col0 (type: string)"} | | | outputColumnNames:["_col0","_col1","_col3"] | | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | |<-Map 17 [BROADCAST_EDGE] - | | | Reduce Output Operator [RS_81] + | | | Reduce Output Operator [RS_71] | | | key expressions:_col0 (type: string) | | | Map-reduce partition columns:_col0 (type: string) | | | sort order:+ | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col1 (type: string) - | | | Select Operator [SEL_61] + | | | Select Operator [SEL_53] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_125] + | | | Filter Operator [FIL_113] | | | predicate:key is not null (type: boolean) | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_59] + | | | TableScan [TS_51] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | |<-Select Operator [SEL_58] + | | |<-Select Operator [SEL_50] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_124] + | | Filter Operator [FIL_112] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_56] + | | TableScan [TS_48] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Reduce Output Operator [RS_140] + | | Reduce Output Operator [RS_128] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col3 (type: string) - | | Please refer to the previous Map Join Operator [MAPJOIN_134] - | | Reduce Output Operator [RS_141] + | | Please refer to the previous Map Join Operator [MAPJOIN_122] + | | Reduce Output Operator [RS_129] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col3 (type: string) - | | Please refer to the previous Map Join Operator [MAPJOIN_134] - | | Reduce Output Operator [RS_142] + | | Please refer to the previous Map Join Operator [MAPJOIN_122] + | | Reduce Output Operator [RS_130] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col3 (type: string) - | | Please refer to the previous Map Join Operator [MAPJOIN_134] - | |<-Select Operator [SEL_64] + | | Please refer to the previous Map Join Operator [MAPJOIN_122] + | |<-Select Operator [SEL_56] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_126] + | Filter Operator [FIL_114] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_62] + | TableScan [TS_54] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map 19 [CONTAINS] - | File Output Operator [FS_90] + | File Output Operator [FS_78] | compressed:false | Statistics:Num rows: 3550 Data size: 37482 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 [SEL_88] + | Select Operator [SEL_76] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_135] + | Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 16":"_col1 (type: string)","Map 19":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col3"] | | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE | |<- Please refer to the previous Map 16 [BROADCAST_EDGE] - | |<-Select Operator [SEL_67] + | |<-Select Operator [SEL_59] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_127] + | Filter Operator [FIL_115] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_65] + | TableScan [TS_57] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 20 [CONTAINS] - | File Output Operator [FS_90] + | File Output Operator [FS_78] | compressed:false | Statistics:Num rows: 3550 Data size: 37482 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 [SEL_88] + | Select Operator [SEL_76] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_135] + | Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 16":"_col1 (type: string)","Map 20":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col3"] | | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE | |<- Please refer to the previous Map 16 [BROADCAST_EDGE] - | |<-Select Operator [SEL_72] + | |<-Select Operator [SEL_64] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_128] + | Filter Operator [FIL_116] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_70] + | TableScan [TS_62] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map 21 [CONTAINS] - | File Output Operator [FS_90] + | File Output Operator [FS_78] | compressed:false | Statistics:Num rows: 3550 Data size: 37482 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 [SEL_88] + | Select Operator [SEL_76] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_135] + | Map Join Operator [MAPJOIN_123] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 16":"_col1 (type: string)","Map 21":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col3"] | | Statistics:Num rows: 1677 Data size: 17739 Basic stats: COMPLETE Column stats: NONE | |<- Please refer to the previous Map 16 [BROADCAST_EDGE] - | |<-Select Operator [SEL_76] + | |<-Select Operator [SEL_68] | outputColumnNames:["_col0"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_129] + | Filter Operator [FIL_117] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_74] + | TableScan [TS_66] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 11 [CONTAINS] - | File Output Operator [FS_90] + | File Output Operator [FS_78] | compressed:false | Statistics:Num rows: 3550 Data size: 37482 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 [SEL_53] + | Select Operator [SEL_45] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1239 Data size: 13085 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_133] + | Merge Join Operator [MERGEJOIN_121] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col1","_col4"] | | Statistics:Num rows: 1239 Data size: 13085 Basic stats: COMPLETE Column stats: NONE | |<-Map 15 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_51] + | | Reduce Output Operator [RS_43] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_42] + | | Select Operator [SEL_38] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_123] + | | Filter Operator [FIL_111] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_40] + | | TableScan [TS_36] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_49] + | Reduce Output Operator [RS_42] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 1127 Data size: 11896 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_132] + | Merge Join Operator [MERGEJOIN_120] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: string)","1":"_col1 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 1127 Data size: 11896 Basic stats: COMPLETE Column stats: NONE | |<-Map 14 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_46] + | | Reduce Output Operator [RS_40] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_39] + | | Select Operator [SEL_35] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_122] + | | Filter Operator [FIL_110] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_37] + | | TableScan [TS_33] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Union 9 [SIMPLE_EDGE] | |<-Map 12 [CONTAINS] - | | Reduce Output Operator [RS_44] + | | Reduce Output Operator [RS_39] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_30] + | | Select Operator [SEL_26] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_120] + | | Filter Operator [FIL_108] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_28] + | | TableScan [TS_24] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Map 13 [CONTAINS] - | | Reduce Output Operator [RS_44] + | | Reduce Output Operator [RS_39] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_35] + | | Select Operator [SEL_31] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_121] + | | Filter Operator [FIL_109] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_33] + | | TableScan [TS_29] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Map 8 [CONTAINS] - | Reduce Output Operator [RS_44] + | Reduce Output Operator [RS_39] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_27] + | Select Operator [SEL_23] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_119] + | Filter Operator [FIL_107] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_25] + | TableScan [TS_21] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [CONTAINS] - File Output Operator [FS_90] + File Output Operator [FS_78] compressed:false Statistics:Num rows: 3550 Data size: 37482 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 [SEL_24] + Select Operator [SEL_20] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 634 Data size: 6658 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_131] + Merge Join Operator [MERGEJOIN_119] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col1","_col4"] | Statistics:Num rows: 634 Data size: 6658 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_18] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -3396,7 +3396,7 @@ Stage-0 | Select Operator [SEL_13] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_118] + | Filter Operator [FIL_106] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_11] @@ -3404,19 +3404,19 @@ Stage-0 | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Union 2 [SIMPLE_EDGE] |<-Map 1 [CONTAINS] - | Reduce Output Operator [RS_20] + | Reduce Output Operator [RS_17] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 577 Data size: 6053 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_130] + | Map Join Operator [MAPJOIN_118] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 1":"_col0 (type: string)","Map 6":"_col1 (type: string)"} | | outputColumnNames:["_col1"] | | Statistics:Num rows: 577 Data size: 6053 Basic stats: COMPLETE Column stats: NONE | |<-Map 6 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_17] + | | Reduce Output Operator [RS_15] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ @@ -3425,13 +3425,13 @@ Stage-0 | | Select Operator [SEL_10] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_117] + | | Filter Operator [FIL_105] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_8] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Reduce Output Operator [RS_136] + | | Reduce Output Operator [RS_124] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ @@ -3441,19 +3441,19 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_115] + | Filter Operator [FIL_103] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:x | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map 5 [CONTAINS] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_17] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 577 Data size: 6053 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_130] + Map Join Operator [MAPJOIN_118] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Map 5":"_col0 (type: string)","Map 6":"_col1 (type: string)"} @@ -3463,7 +3463,7 @@ Stage-0 |<-Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_116] + Filter Operator [FIL_104] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] @@ -3526,368 +3526,368 @@ Stage-0 limit:-1 Stage-1 Reducer 8 - File Output Operator [FS_134] + File Output Operator [FS_122] compressed:false Statistics:Num rows: 530 Data size: 5624 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"} - Group By Operator [GBY_132] + Group By Operator [GBY_120] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 530 Data size: 5624 Basic stats: COMPLETE Column stats: NONE |<-Union 7 [SIMPLE_EDGE] |<-Reducer 31 [CONTAINS] - | Reduce Output Operator [RS_131] + | Reduce Output Operator [RS_119] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1061 Data size: 11260 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_130] + | Group By Operator [GBY_118] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1061 Data size: 11260 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_126] + | Select Operator [SEL_114] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 484 Data size: 5131 Basic stats: COMPLETE Column stats: NONE - | Map Join Operator [MAPJOIN_179] + | Map Join Operator [MAPJOIN_167] | | condition map:[{"":"Inner Join 0 to 1"}] | | HybridGraceHashJoin:true | | keys:{"Map 23":"_col1 (type: string)","Reducer 31":"_col1 (type: string)"} | | outputColumnNames:["_col0","_col3"] | | Statistics:Num rows: 484 Data size: 5131 Basic stats: COMPLETE Column stats: NONE | |<-Map 23 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_122] + | | Reduce Output Operator [RS_111] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string), _col3 (type: string) - | | Map Join Operator [MAPJOIN_178] + | | Map Join Operator [MAPJOIN_166] | | | condition map:[{"":"Inner Join 0 to 1"}] | | | HybridGraceHashJoin:true | | | keys:{"Map 23":"_col0 (type: string)","Map 24":"_col0 (type: string)"} | | | outputColumnNames:["_col0","_col1","_col3"] | | | Statistics:Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE | | |<-Map 24 [BROADCAST_EDGE] - | | | Reduce Output Operator [RS_119] + | | | Reduce Output Operator [RS_109] | | | key expressions:_col0 (type: string) | | | Map-reduce partition columns:_col0 (type: string) | | | sort order:+ | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | | | value expressions:_col1 (type: string) - | | | Select Operator [SEL_82] + | | | Select Operator [SEL_74] | | | outputColumnNames:["_col0","_col1"] | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_169] + | | | Filter Operator [FIL_157] | | | predicate:key is not null (type: boolean) | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_80] + | | | TableScan [TS_72] | | | alias:x | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | |<-Select Operator [SEL_79] + | | |<-Select Operator [SEL_71] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_168] + | | Filter Operator [FIL_156] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_77] + | | TableScan [TS_69] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_115] + | |<-Select Operator [SEL_107] | outputColumnNames:["_col1"] | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_114] + | Group By Operator [GBY_106] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 440 Data size: 4665 Basic stats: COMPLETE Column stats: NONE | |<-Union 30 [SIMPLE_EDGE] | |<-Map 34 [CONTAINS] - | | Reduce Output Operator [RS_113] + | | Reduce Output Operator [RS_105] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_112] + | | Group By Operator [GBY_104] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_108] + | | Select Operator [SEL_100] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_173] + | | Filter Operator [FIL_161] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_106] + | | TableScan [TS_98] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 29 [CONTAINS] - | Reduce Output Operator [RS_113] + | Reduce Output Operator [RS_105] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_112] + | Group By Operator [GBY_104] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 881 Data size: 9341 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_104] + | Group By Operator [GBY_96] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 28 [SIMPLE_EDGE] | |<-Map 33 [CONTAINS] - | | Reduce Output Operator [RS_103] + | | Reduce Output Operator [RS_95] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_102] + | | Group By Operator [GBY_94] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_98] + | | Select Operator [SEL_90] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_172] + | | Filter Operator [FIL_160] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_96] + | | TableScan [TS_88] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 27 [CONTAINS] - | Reduce Output Operator [RS_103] + | Reduce Output Operator [RS_95] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_102] + | Group By Operator [GBY_94] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_94] + | Group By Operator [GBY_86] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 26 [SIMPLE_EDGE] | |<-Map 25 [CONTAINS] - | | Reduce Output Operator [RS_93] + | | Reduce Output Operator [RS_85] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_92] + | | Group By Operator [GBY_84] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_85] + | | Select Operator [SEL_77] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_170] + | | Filter Operator [FIL_158] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_83] + | | TableScan [TS_75] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 32 [CONTAINS] - | Reduce Output Operator [RS_93] + | Reduce Output Operator [RS_85] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_92] + | Group By Operator [GBY_84] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_88] + | Select Operator [SEL_80] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_171] + | Filter Operator [FIL_159] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_86] + | TableScan [TS_78] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 6 [CONTAINS] - Reduce Output Operator [RS_131] + Reduce Output Operator [RS_119] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1061 Data size: 11260 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_130] + Group By Operator [GBY_118] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1061 Data size: 11260 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_75] + Group By Operator [GBY_67] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 577 Data size: 6129 Basic stats: COMPLETE Column stats: NONE |<-Union 5 [SIMPLE_EDGE] |<-Reducer 18 [CONTAINS] - | Reduce Output Operator [RS_74] + | Reduce Output Operator [RS_66] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 1155 Data size: 12270 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_73] + | Group By Operator [GBY_65] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1155 Data size: 12270 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_69] + | Select Operator [SEL_61] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_177] + | Merge Join Operator [MERGEJOIN_165] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col2","_col5"] | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE | |<-Map 22 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_67] + | | Reduce Output Operator [RS_59] | | key expressions:_col0 (type: string) | | Map-reduce partition columns:_col0 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col1 (type: string) - | | Select Operator [SEL_58] + | | Select Operator [SEL_54] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_167] + | | Filter Operator [FIL_155] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_56] + | | TableScan [TS_52] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 17 [SIMPLE_EDGE] - | Reduce Output Operator [RS_65] + | Reduce Output Operator [RS_58] | key expressions:_col2 (type: string) | Map-reduce partition columns:_col2 (type: string) | sort order:+ | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_176] + | Merge Join Operator [MERGEJOIN_164] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | | outputColumnNames:["_col2"] | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE | |<-Map 21 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_62] + | | Reduce Output Operator [RS_56] | | key expressions:_col1 (type: string) | | Map-reduce partition columns:_col1 (type: string) | | sort order:+ | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | | value expressions:_col0 (type: string) - | | Select Operator [SEL_55] + | | Select Operator [SEL_51] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_166] + | | Filter Operator [FIL_154] | | predicate:(key is not null and value is not null) (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_53] + | | TableScan [TS_49] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 16 [SIMPLE_EDGE] - | Reduce Output Operator [RS_60] + | Reduce Output Operator [RS_55] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_52] + | Select Operator [SEL_48] | outputColumnNames:["_col1"] | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_51] + | Group By Operator [GBY_47] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 381 Data size: 4029 Basic stats: COMPLETE Column stats: NONE | |<-Union 15 [SIMPLE_EDGE] | |<-Map 20 [CONTAINS] - | | Reduce Output Operator [RS_50] + | | Reduce Output Operator [RS_46] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_49] + | | Group By Operator [GBY_45] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_45] + | | Select Operator [SEL_41] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_165] + | | Filter Operator [FIL_153] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_43] + | | TableScan [TS_39] | | alias:y | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | |<-Reducer 14 [CONTAINS] - | Reduce Output Operator [RS_50] + | Reduce Output Operator [RS_46] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_49] + | Group By Operator [GBY_45] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 762 Data size: 8058 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_41] + | Group By Operator [GBY_37] | | keys:KEY._col0 (type: string), KEY._col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE | |<-Union 13 [SIMPLE_EDGE] | |<-Map 12 [CONTAINS] - | | Reduce Output Operator [RS_40] + | | Reduce Output Operator [RS_36] | | key expressions:_col0 (type: string), _col1 (type: string) | | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | | sort order:++ | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Group By Operator [GBY_39] + | | Group By Operator [GBY_35] | | keys:_col0 (type: string), _col1 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_32] + | | Select Operator [SEL_28] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_163] + | | Filter Operator [FIL_151] | | predicate:value is not null (type: boolean) | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_30] + | | TableScan [TS_26] | | alias:x | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | |<-Map 19 [CONTAINS] - | Reduce Output Operator [RS_40] + | Reduce Output Operator [RS_36] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Group By Operator [GBY_39] + | Group By Operator [GBY_35] | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_35] + | Select Operator [SEL_31] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_164] + | Filter Operator [FIL_152] | predicate:value is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_33] + | TableScan [TS_29] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [CONTAINS] - Reduce Output Operator [RS_74] + Reduce Output Operator [RS_66] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 1155 Data size: 12270 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_73] + Group By Operator [GBY_65] keys:_col0 (type: string), _col1 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1155 Data size: 12270 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_29] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_175] + Merge Join Operator [MERGEJOIN_163] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col2","_col5"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_23] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ @@ -3896,26 +3896,26 @@ Stage-0 | Select Operator [SEL_18] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_162] + | Filter Operator [FIL_150] | predicate:key is not null (type: boolean) | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_16] | alias:y | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] + Reduce Output Operator [RS_22] key expressions:_col2 (type: string) Map-reduce partition columns:_col2 (type: string) sort order:+ Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_174] + Map Join Operator [MAPJOIN_162] | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true | keys:{"Reducer 3":"_col1 (type: string)","Map 10":"_col1 (type: string)"} | outputColumnNames:["_col2"] | Statistics:Num rows: 288 Data size: 3020 Basic stats: COMPLETE Column stats: NONE |<-Map 10 [BROADCAST_EDGE] - | Reduce Output Operator [RS_22] + | Reduce Output Operator [RS_20] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -3924,7 +3924,7 @@ Stage-0 | Select Operator [SEL_15] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_161] + | Filter Operator [FIL_149] | predicate:(key is not null and value is not null) (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_13] @@ -3951,7 +3951,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_159] + | Filter Operator [FIL_147] | predicate:value is not null (type: boolean) | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -3970,7 +3970,7 @@ Stage-0 Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_160] + Filter Operator [FIL_148] predicate:value is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] diff --git ql/src/test/results/clientpositive/tez/explainuser_3.q.out ql/src/test/results/clientpositive/tez/explainuser_3.q.out index 33d9457..e2db163 100644 --- ql/src/test/results/clientpositive/tez/explainuser_3.q.out +++ ql/src/test/results/clientpositive/tez/explainuser_3.q.out @@ -719,14 +719,14 @@ Stage-0 limit:-1 Stage-1 Map 2 - File Output Operator [FS_12] + File Output Operator [FS_10] compressed:false Statistics:Num rows: 550 Data size: 5843 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 [SEL_11] + Select Operator [SEL_9] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_17] + Map Join Operator [MAPJOIN_15] | BucketMapJoin:true | condition map:[{"":"Inner Join 0 to 1"}] | HybridGraceHashJoin:true @@ -734,7 +734,7 @@ Stage-0 | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [CUSTOM_EDGE] - | Reduce Output Operator [RS_7] + | Reduce Output Operator [RS_6] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ @@ -743,7 +743,7 @@ Stage-0 | Select Operator [SEL_2] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_15] + | Filter Operator [FIL_13] | predicate:key is not null (type: boolean) | Statistics:Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] @@ -752,7 +752,7 @@ Stage-0 |<-Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_16] + Filter Operator [FIL_14] predicate:key is not null (type: boolean) Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TableScan [TS_3] diff --git ql/src/test/results/clientpositive/tez/mapjoin_decimal.q.out ql/src/test/results/clientpositive/tez/mapjoin_decimal.q.out index 3c7b406..012c28e 100644 --- ql/src/test/results/clientpositive/tez/mapjoin_decimal.q.out +++ ql/src/test/results/clientpositive/tez/mapjoin_decimal.q.out @@ -139,7 +139,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: decimal(6,2)) Statistics: Num rows: 1049 Data size: 117488 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(4,0)) Reducer 2 Reduce Operator Tree: Select Operator diff --git ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out index 485e1c1..63b9462 100644 --- ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/mapjoin_mapjoin.q.out @@ -490,7 +490,7 @@ STAGE PLANS: alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_450') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_450') and key is not null) (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/tez/mergejoin.q.out ql/src/test/results/clientpositive/tez/mergejoin.q.out index 15c204d..4b2d963 100644 --- ql/src/test/results/clientpositive/tez/mergejoin.q.out +++ ql/src/test/results/clientpositive/tez/mergejoin.q.out @@ -2711,7 +2711,7 @@ NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 -Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select * from (select * from tab where tab.key = 0)a join diff --git ql/src/test/results/clientpositive/tez/metadataonly1.q.out ql/src/test/results/clientpositive/tez/metadataonly1.q.out index 4ef71f8..eb78d96 100644 --- ql/src/test/results/clientpositive/tez/metadataonly1.q.out +++ ql/src/test/results/clientpositive/tez/metadataonly1.q.out @@ -910,21 +910,6 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: true - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: a2 - Partition key expr: ds - Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/tez/skewjoin.q.out ql/src/test/results/clientpositive/tez/skewjoin.q.out index 70d2418..026e458 100644 --- ql/src/test/results/clientpositive/tez/skewjoin.q.out +++ ql/src/test/results/clientpositive/tez/skewjoin.q.out @@ -705,7 +705,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and UDFToDouble(substring(value, 5)) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -722,7 +722,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((value is not null and key is not null) and (UDFToDouble(substring(value, 5)) + 1.0) is not null) (type: boolean) + predicate: (value is not null and key is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -837,7 +837,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) and key is not null) (type: boolean) + predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) < 80.0)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/tez/subquery_exists.q.out ql/src/test/results/clientpositive/tez/subquery_exists.q.out index 66b48d4..dd36263 100644 --- ql/src/test/results/clientpositive/tez/subquery_exists.q.out +++ ql/src/test/results/clientpositive/tez/subquery_exists.q.out @@ -41,7 +41,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((value > 'val_9') and key is not null) and value is not null) (type: boolean) + predicate: ((value > 'val_9') and key is not null) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) diff --git ql/src/test/results/clientpositive/tez/subquery_in.q.out ql/src/test/results/clientpositive/tez/subquery_in.q.out index ff75000..688f979 100644 --- ql/src/test/results/clientpositive/tez/subquery_in.q.out +++ ql/src/test/results/clientpositive/tez/subquery_in.q.out @@ -282,15 +282,12 @@ STAGE PLANS: expressions: p_name (type: string), p_size (type: int), UDFToDouble(p_size) (type: double) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col2 is not null (type: boolean) + Reduce Output Operator + key expressions: _col2 (type: double) + sort order: + + Map-reduce partition columns: _col2 (type: double) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: double) - sort order: + - Map-reduce partition columns: _col2 (type: double) - Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int) + value expressions: _col0 (type: string), _col1 (type: int) Map 3 Map Operator Tree: TableScan @@ -301,7 +298,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -346,22 +342,26 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (rank_window_0 <= 2) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int) - outputColumnNames: _col0 + Select Operator + expressions: _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 <= 2) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: avg(_col0) - mode: hash + Select Operator + expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Reduce Output Operator - sort order: + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col0) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - value expressions: _col0 (type: struct) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions: _col0 (type: struct) Reducer 5 Reduce Operator Tree: Group By Operator @@ -470,7 +470,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: p_mfgr (type: string) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 Reducer 2 Reduce Operator Tree: Merge Join Operator @@ -519,25 +518,29 @@ STAGE PLANS: window frame: PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((rank_window_0 <= 2) and _col2 is not null) (type: boolean) - Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string), _col5 (type: int) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col2 (type: string), _col5 (type: int), rank_window_0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 <= 2) and _col0 is not null) (type: boolean) Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1) - keys: _col0 (type: string) - mode: hash + Select Operator + expressions: _col0 (type: string), _col1 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + aggregations: min(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) Reducer 5 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_2.q.out ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_2.q.out index c9e712d..322462b 100644 --- ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_2.q.out +++ ql/src/test/results/clientpositive/tez/tez_dynpart_hashjoin_2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -62,7 +62,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -79,7 +79,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -230,7 +230,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -248,7 +248,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -265,7 +265,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -414,7 +414,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -432,7 +432,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -449,7 +449,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_2.q.out ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_2.q.out index e71a4ef..d45ff04 100644 --- ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_2.q.out +++ ql/src/test/results/clientpositive/tez/tez_vector_dynpart_hashjoin_2.q.out @@ -44,7 +44,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -62,7 +62,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -79,7 +79,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -230,7 +230,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -249,7 +249,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -266,7 +266,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -416,7 +416,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((csmallint < 100) and UDFToInteger(csmallint) is not null) (type: boolean) + predicate: (csmallint < 100) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -435,7 +435,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and UDFToInteger(key) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -452,7 +452,7 @@ STAGE PLANS: alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key is not null and (UDFToInteger(key) + 0) is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) diff --git ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out index 2cff3ef..874d397 100644 --- ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out +++ ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out @@ -5355,15 +5355,17 @@ STAGE PLANS: TableScan alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Map 11 Map Operator Tree: TableScan @@ -5413,15 +5415,17 @@ STAGE PLANS: TableScan alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Reducer 10 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/tez/vector_auto_smb_mapjoin_14.q.out ql/src/test/results/clientpositive/tez/vector_auto_smb_mapjoin_14.q.out index 9b62353..1032f52 100644 --- ql/src/test/results/clientpositive/tez/vector_auto_smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/tez/vector_auto_smb_mapjoin_14.q.out @@ -64,24 +64,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE @@ -89,7 +89,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:key is not null (type: boolean) | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -98,7 +98,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:key is not null (type: boolean) Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -153,40 +153,40 @@ Stage-0 limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_21] + File Output Operator [FS_19] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_31] + Group By Operator [OP_29] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] vectorized - Reduce Output Operator [RS_18] + Reduce Output Operator [RS_16] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [OP_30] + Group By Operator [OP_28] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator [OP_29] + Select Operator [OP_27] Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE - Group By Operator [OP_28] + Group By Operator [OP_26] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE - Group By Operator [GBY_12] + Group By Operator [GBY_10] keys:_col0 (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_26] + Merge Join Operator [MERGEJOIN_24] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0"] @@ -195,7 +195,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_25] + | Filter Operator [FIL_23] | predicate:key is not null (type: boolean) | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -204,7 +204,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_24] + Filter Operator [FIL_22] predicate:key is not null (type: boolean) Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -286,43 +286,43 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_38] + File Output Operator [FS_32] compressed:false Statistics:Num rows: 5 Data size: 511 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 [SEL_37] + Select Operator [SEL_31] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 511 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_55] + Merge Join Operator [MERGEJOIN_49] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 5 Data size: 511 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] vectorized - | Reduce Output Operator [RS_57] + | Reduce Output Operator [RS_51] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: bigint) - | Group By Operator [OP_56] + | Group By Operator [OP_50] | | aggregations:["count(VALUE._col0)"] | | keys:KEY._col0 (type: int) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_13] + | Reduce Output Operator [RS_11] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE | value expressions:_col1 (type: bigint) - | Group By Operator [GBY_12] + | Group By Operator [GBY_10] | aggregations:["count()"] | keys:_col0 (type: int) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_51] + | Merge Join Operator [MERGEJOIN_45] | | condition map:[{"":"Inner Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col0"] @@ -331,7 +331,7 @@ Stage-0 | |<-Select Operator [SEL_5] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_48] + | | Filter Operator [FIL_42] | | predicate:key is not null (type: boolean) | | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE | | TableScan [TS_3] @@ -340,58 +340,58 @@ Stage-0 | |<-Select Operator [SEL_2] | outputColumnNames:["_col0"] | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_47] + | Filter Operator [FIL_41] | predicate:key is not null (type: boolean) | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_0] | alias:a | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE |<-Reducer 6 [SIMPLE_EDGE] vectorized - Reduce Output Operator [RS_59] + Reduce Output Operator [RS_53] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: bigint) - Group By Operator [OP_58] + Group By Operator [OP_52] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: NONE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_29] + Reduce Output Operator [RS_25] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: bigint) - Group By Operator [GBY_28] + Group By Operator [GBY_24] aggregations:["count()"] keys:_col0 (type: int) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_53] + Merge Join Operator [MERGEJOIN_47] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col0"] | Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE | - |<-Select Operator [SEL_21] + |<-Select Operator [SEL_19] | outputColumnNames:["_col0"] | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_50] + | Filter Operator [FIL_44] | predicate:key is not null (type: boolean) | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_19] + | TableScan [TS_17] | alias:b | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_18] + |<-Select Operator [SEL_16] outputColumnNames:["_col0"] Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_49] + Filter Operator [FIL_43] predicate:key is not null (type: boolean) Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_16] + TableScan [TS_14] alias:a Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE @@ -467,24 +467,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE @@ -492,7 +492,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(key < 6) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -501,7 +501,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(key < 6) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -565,24 +565,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: NONE @@ -590,7 +590,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -599,7 +599,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -687,24 +687,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: NONE @@ -712,7 +712,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -721,7 +721,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -799,24 +799,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE @@ -824,7 +824,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(key < 8) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -833,7 +833,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(key < 8) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -888,63 +888,57 @@ Stage-0 limit:-1 Stage-1 Reducer 3 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_32] + Group By Operator [OP_26] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_23] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] vectorized - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_22] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_26] - | predicate:_col0 is not null (type: boolean) + | Select Operator [OP_21] + | outputColumnNames:["_col0"] | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Select Operator [OP_25] - | outputColumnNames:["_col0"] + | Filter Operator [FIL_20] + | predicate:(key + 1) is not null (type: boolean) | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_24] - | predicate:(key + 1) is not null (type: boolean) + | TableScan [TS_0] + | alias:a | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_0] - | alias:a - | Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE |<-Map 4 [SIMPLE_EDGE] vectorized - Reduce Output Operator [RS_31] + Reduce Output Operator [RS_25] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_30] - predicate:_col0 is not null (type: boolean) + Select Operator [OP_24] + outputColumnNames:["_col0"] Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Select Operator [OP_29] - outputColumnNames:["_col0"] + Filter Operator [FIL_23] + predicate:(key + 1) is not null (type: boolean) Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_28] - predicate:(key + 1) is not null (type: boolean) + TableScan [TS_3] + alias:a Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_3] - alias:a - Statistics:Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: select count(*) from (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a) subq1 @@ -989,24 +983,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 3 Data size: 306 Basic stats: COMPLETE Column stats: NONE @@ -1014,7 +1008,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(key < 6) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -1023,7 +1017,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(key < 6) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -1079,24 +1073,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_21] + File Output Operator [FS_18] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_34] + Group By Operator [OP_31] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_18] + Reduce Output Operator [RS_15] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_17] + Group By Operator [GBY_14] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_31] + Merge Join Operator [MERGEJOIN_28] | condition map:[{"":"Inner Join 0 to 1"},{"":"Inner Join 0 to 2"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)","2":"_col0 (type: int)"} | Statistics:Num rows: 6 Data size: 613 Basic stats: COMPLETE Column stats: NONE @@ -1104,7 +1098,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_29] + | Filter Operator [FIL_26] | predicate:(key < 6) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -1114,7 +1108,7 @@ Stage-0 |<-Select Operator [SEL_8] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_30] + | Filter Operator [FIL_27] | predicate:(key < 6) (type: boolean) | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_6] @@ -1123,7 +1117,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_28] + Filter Operator [FIL_25] predicate:(key < 6) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] @@ -1195,24 +1189,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 vectorized - File Output Operator [FS_16] + File Output Operator [FS_14] compressed:false Statistics:Num rows: 1 Data size: 8 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"} - Group By Operator [OP_23] + Group By Operator [OP_21] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_11] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_10] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_21] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | Statistics:Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: NONE @@ -1220,7 +1214,7 @@ Stage-0 |<-Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_20] + | Filter Operator [FIL_18] | predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE | TableScan [TS_3] @@ -1229,7 +1223,7 @@ Stage-0 |<-Select Operator [SEL_2] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_19] + Filter Operator [FIL_17] predicate:(((key < 8) and (key < 6)) and key is not null) (type: boolean) Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] diff --git ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out index 2392fa2..c13ac6c 100644 --- ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out +++ ql/src/test/results/clientpositive/tez/vector_binary_join_groupby.q.out @@ -193,7 +193,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(*)) FROM hundredorc t1 JOIN hundredorc t2 ON t2.bin = t2.bin PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/tez/vector_char_mapjoin1.q.out ql/src/test/results/clientpositive/tez/vector_char_mapjoin1.q.out index 6e266af..6a74408 100644 --- ql/src/test/results/clientpositive/tez/vector_char_mapjoin1.q.out +++ ql/src/test/results/clientpositive/tez/vector_char_mapjoin1.q.out @@ -257,7 +257,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col1 (type: char(20)) Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: char(10)) + value expressions: _col0 (type: int) Execution mode: vectorized Map 2 Map Operator Tree: @@ -352,7 +352,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c2 is not null and UDFToString(c2) is not null) (type: boolean) + predicate: c2 is not null (type: boolean) Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: char(10)) diff --git ql/src/test/results/clientpositive/tez/vector_decimal_mapjoin.q.out ql/src/test/results/clientpositive/tez/vector_decimal_mapjoin.q.out index ec8d0b0..0c76602 100644 --- ql/src/test/results/clientpositive/tez/vector_decimal_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vector_decimal_mapjoin.q.out @@ -137,7 +137,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: decimal(6,2)) Statistics: Num rows: 1049 Data size: 117488 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: decimal(4,0)) Execution mode: vectorized Stage: Stage-0 diff --git ql/src/test/results/clientpositive/tez/vector_interval_mapjoin.q.out ql/src/test/results/clientpositive/tez/vector_interval_mapjoin.q.out index cc9103d..42ce499 100644 --- ql/src/test/results/clientpositive/tez/vector_interval_mapjoin.q.out +++ ql/src/test/results/clientpositive/tez/vector_interval_mapjoin.q.out @@ -177,31 +177,28 @@ STAGE PLANS: expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: interval_day_time), _col0 (type: string) - 1 _col1 (type: interval_day_time), _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: interval_day_time), _col0 (type: string) + 1 _col1 (type: interval_day_time), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Map 2 + Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2 - input vertices: - 1 Map 2 Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1100 Data size: 506290 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 + 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 Execution mode: vectorized Map 2 Map Operator Tree: @@ -215,14 +212,11 @@ STAGE PLANS: expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) + Reduce Output Operator + key expressions: _col1 (type: interval_day_time), _col0 (type: string) + sort order: ++ + Map-reduce partition columns: _col1 (type: interval_day_time), _col0 (type: string) Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: interval_day_time), _col0 (type: string) - sort order: ++ - Map-reduce partition columns: _col1 (type: interval_day_time), _col0 (type: string) - Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Stage: Stage-0 diff --git ql/src/test/results/clientpositive/tez/vector_join_filters.q.out ql/src/test/results/clientpositive/tez/vector_join_filters.q.out index fb73843..cc8122a 100644 --- ql/src/test/results/clientpositive/tez/vector_join_filters.q.out +++ ql/src/test/results/clientpositive/tez/vector_join_filters.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@myinput1_txt POSTHOOK: Output: database:default POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out index 2d84f42..3c9ce0a 100644 --- ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out +++ ql/src/test/results/clientpositive/tez/vector_join_nulls.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@myinput1_txt POSTHOOK: Output: database:default POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out index 7eb28f8..1372309 100644 --- ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/tez/vector_mapjoin_reduce.q.out @@ -195,7 +195,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) + predicate: ((((l_linenumber = 1) and l_partkey is not null) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) @@ -240,7 +240,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + predicate: ((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) diff --git ql/src/test/results/clientpositive/tez/vector_varchar_mapjoin1.q.out ql/src/test/results/clientpositive/tez/vector_varchar_mapjoin1.q.out index 30600e5..64af51b 100644 --- ql/src/test/results/clientpositive/tez/vector_varchar_mapjoin1.q.out +++ ql/src/test/results/clientpositive/tez/vector_varchar_mapjoin1.q.out @@ -340,7 +340,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c2 is not null and UDFToString(c2) is not null) (type: boolean) + predicate: c2 is not null (type: boolean) Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10)) diff --git ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out index 4f6cb91..3109f7f 100644 --- ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out +++ ql/src/test/results/clientpositive/tez/vectorized_dynamic_partition_pruning.q.out @@ -236,21 +236,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -458,6 +443,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -487,21 +473,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Map 6 Map Operator Tree: @@ -521,21 +492,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -799,6 +755,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -827,36 +784,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1088,21 +1015,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1303,28 +1215,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1335,21 +1244,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1430,20 +1324,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -1462,21 +1353,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1557,28 +1433,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1669,20 +1542,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (hr is not null and (UDFToDouble(hr) * 2.0) is not null) (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + sort order: + + Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0) (type: double) - sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan @@ -1708,7 +1578,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) + 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1794,28 +1664,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) + sort order: + + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - sort order: + - Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1826,21 +1693,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToString(_col0) (type: string) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToString(_col0) (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToString((UDFToDouble(hr) * 2.0)) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2014,21 +1866,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2066,7 +1903,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2162,7 +1999,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -2204,6 +2041,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2232,36 +2070,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2373,21 +2181,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2463,21 +2256,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 4 Execution mode: vectorized Map 4 Map Operator Tree: @@ -2583,21 +2361,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2664,6 +2427,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2692,30 +2456,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE @@ -2821,10 +2570,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -3066,21 +2815,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: vectorized Reduce Operator Tree: @@ -3102,21 +2836,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3268,21 +2987,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 8 Execution mode: vectorized Reduce Operator Tree: @@ -3304,21 +3008,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 6 Vertex: Union 6 @@ -3371,16 +3060,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 10 Map Operator Tree: TableScan @@ -3405,16 +3098,20 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: ds (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator + expressions: ds (type: string) + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Group By Operator + keys: ds (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map 7 Map Operator Tree: TableScan @@ -3454,36 +3151,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Reducer 2 Execution mode: vectorized Reduce Operator Tree: @@ -3548,36 +3215,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 5 Union 3 Vertex: Union 3 Union 9 @@ -3674,21 +3311,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -3768,6 +3390,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3821,21 +3444,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Map 4 Map Operator Tree: @@ -3855,21 +3463,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -3949,6 +3542,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -3991,36 +3585,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), _col2 (type: string) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: hr - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -4139,21 +3703,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -4205,42 +3754,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 UDFToDouble(_col0) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: ((UDFToDouble(hour) = 11.0) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -4251,21 +3797,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -4328,34 +3859,31 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + Select Operator + expressions: hr (type: string) + outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: hr (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 (UDFToDouble(_col0) * 2.0) (type: double) - 1 _col0 (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 (UDFToDouble(_col0) * 2.0) (type: double) + 1 _col0 (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan @@ -4374,21 +3902,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: (UDFToDouble(hr) * 2.0) - Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -4641,21 +4154,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Reducer 2 Execution mode: vectorized @@ -4875,6 +4373,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4927,30 +4426,15 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: srcpart_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and (UDFToDouble(hr) = 11.0)) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE @@ -5023,10 +4507,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + filterExpr: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hr) = 13.0) and ds is not null) (type: boolean) + predicate: (((UDFToDouble(hr) = 13.0) and ds is not null) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: ds (type: string) @@ -5251,21 +4735,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Reducer 7 Execution mode: vectorized Reduce Operator Tree: @@ -5287,21 +4756,6 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 2 Data size: 168 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 Union 5 Vertex: Union 5 @@ -5386,42 +4840,39 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_orc - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: UDFToDouble(hr) is not null (type: boolean) + Select Operator + expressions: ds (type: string), hr (type: int) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string), hr (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string), UDFToDouble(_col1) (type: double) - 1 _col0 (type: string), UDFToDouble(_col2) (type: double) - input vertices: - 1 Map 3 - Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string), UDFToDouble(_col1) (type: double) + 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + input vertices: + 1 Map 3 + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Map 3 Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + predicate: ((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -5432,36 +4883,6 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: ds - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Target column: ds - Target Vertex: Map 1 - Select Operator - expressions: UDFToDouble(_col2) (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: double) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target Input: srcpart_orc - Partition key expr: UDFToDouble(hr) - Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE - Target column: hr - Target Vertex: Map 1 Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/union_remove_19.q.out ql/src/test/results/clientpositive/union_remove_19.q.out index c1f688e..40e154c 100644 --- ql/src/test/results/clientpositive/union_remove_19.q.out +++ ql/src/test/results/clientpositive/union_remove_19.q.out @@ -262,25 +262,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '7' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -288,10 +288,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -313,25 +313,25 @@ STAGE PLANS: Map Operator Tree: TableScan alias: inputtbl1 - Statistics: Num rows: 10 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '7' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 15 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator @@ -339,10 +339,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 7 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git ql/src/test/results/clientpositive/vector_auto_smb_mapjoin_14.q.out ql/src/test/results/clientpositive/vector_auto_smb_mapjoin_14.q.out index c5eedb5..2337b29 100644 --- ql/src/test/results/clientpositive/vector_auto_smb_mapjoin_14.q.out +++ ql/src/test/results/clientpositive/vector_auto_smb_mapjoin_14.q.out @@ -912,14 +912,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE TableScan alias: a Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE @@ -930,14 +927,11 @@ STAGE PLANS: expressions: (key + 1) (type: int) outputColumnNames: _col0 Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: diff --git ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out index 1febdbe..682e902 100644 --- ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out +++ ql/src/test/results/clientpositive/vector_binary_join_groupby.q.out @@ -190,7 +190,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(*)) FROM hundredorc t1 JOIN hundredorc t2 ON t2.bin = t2.bin PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out index 0b89bec..7ca3790 100644 --- ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out +++ ql/src/test/results/clientpositive/vector_char_mapjoin1.q.out @@ -362,7 +362,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c2 is not null and UDFToString(c2) is not null) (type: boolean) + predicate: c2 is not null (type: boolean) Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: char(10)) diff --git ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out index c410086..7cd7eb0 100644 --- ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out +++ ql/src/test/results/clientpositive/vector_interval_mapjoin.q.out @@ -178,13 +178,10 @@ STAGE PLANS: expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 458448 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: interval_day_time), _col0 (type: string) - 1 _col1 (type: interval_day_time), _col0 (type: string) + HashTable Sink Operator + keys: + 0 _col1 (type: interval_day_time), _col0 (type: string) + 1 _col1 (type: interval_day_time), _col0 (type: string) Stage: Stage-3 Map Reduce @@ -199,28 +196,25 @@ STAGE PLANS: expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time) outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 460264 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: interval_day_time), _col0 (type: string) - 1 _col1 (type: interval_day_time), _col0 (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: interval_day_time), _col0 (type: string) + 1 _col1 (type: interval_day_time), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time) - outputColumnNames: _col0, _col1, _col2 + File Output Operator + compressed: false Statistics: Num rows: 1100 Data size: 506290 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1100 Data size: 506290 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 + 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 Execution mode: vectorized Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/vector_join_filters.q.out ql/src/test/results/clientpositive/vector_join_filters.q.out index f33c7e0..61e5b2a 100644 --- ql/src/test/results/clientpositive/vector_join_filters.q.out +++ ql/src/test/results/clientpositive/vector_join_filters.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@myinput1_txt POSTHOOK: Output: database:default POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/vector_join_nulls.q.out ql/src/test/results/clientpositive/vector_join_nulls.q.out index 1ff5a0c..7b59cc4 100644 --- ql/src/test/results/clientpositive/vector_join_nulls.q.out +++ ql/src/test/results/clientpositive/vector_join_nulls.q.out @@ -28,7 +28,7 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@myinput1_txt POSTHOOK: Output: database:default POSTHOOK: Output: default@myinput1 -Warning: Map Join MAPJOIN[18][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b PREHOOK: type: QUERY PREHOOK: Input: default@myinput1 diff --git ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out index dd40f28..760928f 100644 --- ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out +++ ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out @@ -466,7 +466,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) + predicate: ((((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int) @@ -489,7 +489,7 @@ STAGE PLANS: alias: lineitem Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((l_linenumber = 1) and l_partkey is not null) and l_orderkey is not null) (type: boolean) + predicate: ((((l_linenumber = 1) and l_partkey is not null) and l_linenumber is not null) and l_orderkey is not null) (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int) diff --git ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out index 33dbf9e..e816367 100644 --- ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out +++ ql/src/test/results/clientpositive/vector_varchar_mapjoin1.q.out @@ -350,7 +350,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (c2 is not null and UDFToString(c2) is not null) (type: boolean) + predicate: c2 is not null (type: boolean) Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c2 (type: varchar(10))