diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java index 32d1de1..7b2a1a9 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/StatsOptimizer.java @@ -728,19 +728,6 @@ else if (udaf instanceof GenericUDAFCount) { cselOpTocgbyOp.put(index, nameToIndex.get(exprColumnNodeDesc.getColumn())); } } - // cselOpTocgbyOp may be 0 to 1, where the 0th position of cgbyOp is '1' and 1st position of cgbyOp is count('1') - // Thus, we need to adjust it to the correct position. - List> list = new ArrayList<>(cselOpTocgbyOp.entrySet()); - Collections.sort(list, new Comparator>() { - public int compare(Entry o1, Entry o2) { - return (o1.getValue()).compareTo(o2.getValue()); - } - }); - cselOpTocgbyOp.clear(); - // adjust cselOpTocgbyOp - for (int index = 0; index < list.size(); index++) { - cselOpTocgbyOp.put(list.get(index).getKey(), index); - } List oneRowWithConstant = new ArrayList<>(); for (int pos = 0; pos < cselOp.getSchema().getSignature().size(); pos++) { if (posToConstant.containsKey(pos)) { @@ -748,7 +735,9 @@ public int compare(Entry o1, Entry o2) { oneRowWithConstant.add(posToConstant.get(pos)); } else { // This position is an aggregation. - oneRowWithConstant.add(oneRow.get(cselOpTocgbyOp.get(pos))); + // As we store in oneRow only the aggregate results, we need to adjust to the correct position + // if there are keys in the GBy operator. + oneRowWithConstant.add(oneRow.get(cselOpTocgbyOp.get(pos) - cgbyOp.getConf().getKeys().size())); } ColumnInfo colInfo = cselOp.getSchema().getSignature().get(pos); colNames.add(colInfo.getInternalName()); diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateReduceRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateReduceRule.java new file mode 100644 index 0000000..5c5c0a0 --- /dev/null +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveAggregateReduceRule.java @@ -0,0 +1,126 @@ +/** + * 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 java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; + +import org.apache.calcite.plan.RelOptRule; +import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.AggregateCall; +import org.apache.calcite.rex.RexBuilder; +import org.apache.calcite.rex.RexNode; +import org.apache.calcite.sql.SqlKind; +import org.apache.calcite.tools.RelBuilder; +import org.apache.hadoop.hive.ql.optimizer.calcite.HiveRelFactories; +import org.apache.hadoop.hive.ql.optimizer.calcite.reloperators.HiveAggregate; + +import com.google.common.collect.Lists; + +/** + * Planner rule that reduces aggregate functions in + * {@link org.apache.calcite.rel.core.Aggregate}s to simpler forms. + * + *

Rewrites: + *

    + * + *
  • COUNT(x) → COUNT(*) if x is not nullable + *
+ */ +public class HiveAggregateReduceRule extends RelOptRule { + + /** The singleton. */ + public static final HiveAggregateReduceRule INSTANCE = + new HiveAggregateReduceRule(); + + /** Private constructor. */ + private HiveAggregateReduceRule() { + super(operand(HiveAggregate.class, any()), + HiveRelFactories.HIVE_BUILDER, null); + } + + @Override + public void onMatch(RelOptRuleCall call) { + final RelBuilder relBuilder = call.builder(); + final Aggregate aggRel = (Aggregate) call.rel(0); + final RexBuilder rexBuilder = aggRel.getCluster().getRexBuilder(); + + // We try to rewrite COUNT(x) into COUNT(*) if x is not nullable. + // We remove duplicate aggregate calls as well. + boolean rewrite = false; + boolean identity = true; + final Map mapping = new HashMap<>(); + final List indexes = new ArrayList<>(); + final List aggCalls = aggRel.getAggCallList(); + final List newAggCalls = new ArrayList<>(aggCalls.size()); + int nextIdx = aggRel.getGroupCount() + aggRel.getIndicatorCount(); + for (int i = 0; i < aggCalls.size(); i++) { + AggregateCall aggCall = aggCalls.get(i); + if (aggCall.getAggregation().getKind() == SqlKind.COUNT && !aggCall.isDistinct()) { + final List args = aggCall.getArgList(); + final List nullableArgs = new ArrayList<>(args.size()); + for (int arg : args) { + if (aggRel.getInput().getRowType().getFieldList().get(arg).getType().isNullable()) { + nullableArgs.add(arg); + } + } + if (nullableArgs.size() != args.size()) { + aggCall = aggCall.copy(nullableArgs, aggCall.filterArg); + rewrite = true; + } + } + Integer idx = mapping.get(aggCall); + if (idx == null) { + newAggCalls.add(aggCall); + idx = nextIdx++; + mapping.put(aggCall, idx); + } else { + rewrite = true; + identity = false; + } + indexes.add(idx); + } + + if (rewrite) { + // We trigger the transform + final Aggregate newAggregate = aggRel.copy(aggRel.getTraitSet(), aggRel.getInput(), + aggRel.indicator, aggRel.getGroupSet(), aggRel.getGroupSets(), + newAggCalls); + if (identity) { + call.transformTo(newAggregate); + } else { + final int offset = aggRel.getGroupCount() + aggRel.getIndicatorCount(); + final List projList = Lists.newArrayList(); + for (int i = 0; i < offset; ++i) { + projList.add( + rexBuilder.makeInputRef( + aggRel.getRowType().getFieldList().get(i).getType(), i)); + } + for (int i = offset; i < aggRel.getRowType().getFieldCount(); ++i) { + projList.add( + rexBuilder.makeInputRef( + aggRel.getRowType().getFieldList().get(i).getType(), indexes.get(i-offset))); + } + call.transformTo(relBuilder.push(newAggregate).project(projList).build()); + } + } + } + +} diff --git ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSemiJoinRule.java ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSemiJoinRule.java index e400896..7799090 100644 --- ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSemiJoinRule.java +++ ql/src/java/org/apache/hadoop/hive/ql/optimizer/calcite/rules/HiveSemiJoinRule.java @@ -19,10 +19,12 @@ import org.apache.calcite.plan.RelOptCluster; import org.apache.calcite.plan.RelOptRule; import org.apache.calcite.plan.RelOptRuleCall; +import org.apache.calcite.plan.RelOptRuleOperand; import org.apache.calcite.plan.RelOptUtil; import org.apache.calcite.plan.hep.HepRelVertex; import org.apache.calcite.rel.RelNode; import org.apache.calcite.rel.core.Aggregate; +import org.apache.calcite.rel.core.AggregateCall; import org.apache.calcite.rel.core.Join; import org.apache.calcite.rel.core.JoinInfo; import org.apache.calcite.rel.core.JoinRelType; @@ -36,6 +38,7 @@ import org.slf4j.Logger; import org.slf4j.LoggerFactory; +import com.google.common.collect.ImmutableList; import com.google.common.collect.Lists; import java.util.ArrayList; @@ -49,34 +52,29 @@ * TODO Remove this rule and use Calcite's SemiJoinRule. Not possible currently * since Calcite doesnt use RelBuilder for this rule and we want to generate HiveSemiJoin rel here. */ -public class HiveSemiJoinRule extends RelOptRule { +public abstract class HiveSemiJoinRule extends RelOptRule { - public static final HiveSemiJoinRule INSTANCE = new HiveSemiJoinRule(HiveRelFactories.HIVE_BUILDER); protected static final Logger LOG = LoggerFactory.getLogger(HiveSemiJoinRule.class); - private HiveSemiJoinRule(RelBuilderFactory relBuilder) { - super( - operand(Project.class, - some( - operand(Join.class, - some(operand(RelNode.class, any()), - operand(Aggregate.class, any()))))), relBuilder, null); + public static final HiveProjectToSemiJoinRule INSTANCE_PROJECT = + new HiveProjectToSemiJoinRule(HiveRelFactories.HIVE_BUILDER); + + public static final HiveAggregateToSemiJoinRule INSTANCE_AGGREGATE = + new HiveAggregateToSemiJoinRule(HiveRelFactories.HIVE_BUILDER); + + private HiveSemiJoinRule(RelOptRuleOperand operand, RelBuilderFactory relBuilder) { + super(operand, relBuilder, null); } - @Override public void onMatch(RelOptRuleCall call) { + protected void perform(RelOptRuleCall call, ImmutableBitSet topRefs, + RelNode topOperator, Join join, RelNode left, Aggregate aggregate) { LOG.debug("Matched HiveSemiJoinRule"); - final Project project = call.rel(0); - final Join join = call.rel(1); - final RelNode left = call.rel(2); - final Aggregate aggregate = call.rel(3); final RelOptCluster cluster = join.getCluster(); final RexBuilder rexBuilder = cluster.getRexBuilder(); - final ImmutableBitSet bits = - RelOptUtil.InputFinder.bits(project.getProjects(), null); final ImmutableBitSet rightBits = ImmutableBitSet.range(left.getRowType().getFieldCount(), join.getRowType().getFieldCount()); - if (bits.intersects(rightBits)) { + if (topRefs.intersects(rightBits)) { return; } final JoinInfo joinInfo = join.analyzeCondition(); @@ -88,7 +86,7 @@ private HiveSemiJoinRule(RelBuilderFactory relBuilder) { } if(join.getJoinType() == JoinRelType.LEFT) { // since for LEFT join we are only interested in rows from LEFT we can get rid of right side - call.transformTo(call.builder().push(left).project(project.getProjects(), project.getRowType().getFieldNames()).build()); + call.transformTo(topOperator.copy(topOperator.getTraitSet(), ImmutableList.of(left))); return; } if (join.getJoinType() != JoinRelType.INNER) { @@ -126,8 +124,68 @@ private HiveSemiJoinRule(RelBuilderFactory relBuilder) { else { semi = call.builder().push(left).push(aggregate.getInput()).semiJoin(newCondition).build(); } - call.transformTo(call.builder().push(semi).project(project.getProjects(), project.getRowType().getFieldNames()).build()); + call.transformTo(topOperator.copy(topOperator.getTraitSet(), ImmutableList.of(semi))); + } + + /** SemiJoinRule that matches a Project on top of a Join with an Aggregate + * as its right child. */ + public static class HiveProjectToSemiJoinRule extends HiveSemiJoinRule { + + /** Creates a HiveProjectToSemiJoinRule. */ + public HiveProjectToSemiJoinRule(RelBuilderFactory relBuilder) { + super( + operand(Project.class, + some(operand(Join.class, + some( + operand(RelNode.class, any()), + operand(Aggregate.class, any()))))), + relBuilder); + } + + @Override public void onMatch(RelOptRuleCall call) { + final Project project = call.rel(0); + final Join join = call.rel(1); + final RelNode left = call.rel(2); + final Aggregate aggregate = call.rel(3); + final ImmutableBitSet topRefs = + RelOptUtil.InputFinder.bits(project.getChildExps(), null); + perform(call, topRefs, project, join, left, aggregate); + } } + + /** SemiJoinRule that matches a Aggregate on top of a Join with an Aggregate + * as its right child. */ + public static class HiveAggregateToSemiJoinRule extends HiveSemiJoinRule { + + /** Creates a HiveAggregateToSemiJoinRule. */ + public HiveAggregateToSemiJoinRule(RelBuilderFactory relBuilder) { + super( + operand(Aggregate.class, + some(operand(Join.class, + some( + operand(RelNode.class, any()), + operand(Aggregate.class, any()))))), + relBuilder); + } + + @Override public void onMatch(RelOptRuleCall call) { + final Aggregate topAggregate = call.rel(0); + final Join join = call.rel(1); + final RelNode left = call.rel(2); + final Aggregate aggregate = call.rel(3); + // Gather columns used by aggregate operator + final ImmutableBitSet.Builder topRefs = ImmutableBitSet.builder(); + topRefs.addAll(topAggregate.getGroupSet()); + for (AggregateCall aggCall : topAggregate.getAggCallList()) { + topRefs.addAll(aggCall.getArgList()); + if (aggCall.filterArg != -1) { + topRefs.set(aggCall.filterArg); + } + } + perform(call, topRefs.build(), topAggregate, join, left, aggregate); + } + } + } // End SemiJoinRule.java 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 931e074..88054e7 100644 --- ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java +++ ql/src/java/org/apache/hadoop/hive/ql/parse/CalcitePlanner.java @@ -171,6 +171,7 @@ import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveAggregateJoinTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveAggregateProjectMergeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveAggregatePullUpConstantsRule; +import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveAggregateReduceRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveDruidProjectFilterTransposeRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveExceptRewriteRule; import org.apache.hadoop.hive.ql.optimizer.calcite.rules.HiveExpandDistinctAggregatesRule; @@ -1523,7 +1524,8 @@ public RelOptMaterialization apply(RelOptMaterialization materialization) { // run this rule at later stages, since many calcite rules cant deal with semijoin if (conf.getBoolVar(ConfVars.SEMIJOIN_CONVERSION)) { perfLogger.PerfLogBegin(this.getClass().getName(), PerfLogger.OPTIMIZER); - calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, false, mdProvider.getMetadataProvider(), null, HiveSemiJoinRule.INSTANCE); + calciteOptimizedPlan = hepPlan(calciteOptimizedPlan, false, mdProvider.getMetadataProvider(), null, + HiveSemiJoinRule.INSTANCE_PROJECT, HiveSemiJoinRule.INSTANCE_AGGREGATE); perfLogger.PerfLogEnd(this.getClass().getName(), PerfLogger.OPTIMIZER, "Calcite: Semijoin conversion"); } @@ -1682,6 +1684,7 @@ private RelNode applyPreJoinOrderingTransforms(RelNode basePlan, RelMetadataProv rules.add(HiveReduceExpressionsRule.PROJECT_INSTANCE); rules.add(HiveReduceExpressionsRule.FILTER_INSTANCE); rules.add(HiveReduceExpressionsRule.JOIN_INSTANCE); + rules.add(HiveAggregateReduceRule.INSTANCE); if (conf.getBoolVar(HiveConf.ConfVars.HIVEPOINTLOOKUPOPTIMIZER)) { rules.add(new HivePointLookupOptimizerRule.FilterCondition(minNumORClauses)); rules.add(new HivePointLookupOptimizerRule.JoinCondition(minNumORClauses)); diff --git ql/src/test/results/clientpositive/auto_join26.q.out ql/src/test/results/clientpositive/auto_join26.q.out index b05145d..e6d966f 100644 --- ql/src/test/results/clientpositive/auto_join26.q.out +++ ql/src/test/results/clientpositive/auto_join26.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:x + $hdt$_0:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:x + $hdt$_0:x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -66,7 +66,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -124,7 +124,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ] POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/auto_join27.q.out ql/src/test/results/clientpositive/auto_join27.q.out index 3d4d355..ba67d1a 100644 --- ql/src/test/results/clientpositive/auto_join27.q.out +++ ql/src/test/results/clientpositive/auto_join27.q.out @@ -69,11 +69,11 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:src + $hdt$_1:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:src + $hdt$_1:src TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -112,7 +112,7 @@ STAGE PLANS: 1 _col0 (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -133,7 +133,7 @@ STAGE PLANS: 1 _col0 (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/combine2.q.out ql/src/test/results/clientpositive/combine2.q.out index 6188345..d4194c8 100644 --- ql/src/test/results/clientpositive/combine2.q.out +++ ql/src/test/results/clientpositive/combine2.q.out @@ -164,11 +164,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/constGby.q.out ql/src/test/results/clientpositive/constGby.q.out index fd8ecc2..7115be3 100644 --- ql/src/test/results/clientpositive/constGby.q.out +++ ql/src/test/results/clientpositive/constGby.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: 1 (type: int) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/correlationoptimizer10.q.out ql/src/test/results/clientpositive/correlationoptimizer10.q.out index 6745eb4..8a8920e 100644 --- ql/src/test/results/clientpositive/correlationoptimizer10.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer10.q.out @@ -62,7 +62,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -271,7 +271,7 @@ STAGE PLANS: Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/correlationoptimizer11.q.out ql/src/test/results/clientpositive/correlationoptimizer11.q.out index 00006a6..cf22507 100644 --- ql/src/test/results/clientpositive/correlationoptimizer11.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer11.q.out @@ -93,7 +93,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 110 Data size: 1177 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -225,7 +225,7 @@ STAGE PLANS: Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -330,7 +330,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -473,7 +473,7 @@ STAGE PLANS: Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/correlationoptimizer13.q.out ql/src/test/results/clientpositive/correlationoptimizer13.q.out index 21219ca..6a8fe70 100644 --- ql/src/test/results/clientpositive/correlationoptimizer13.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer13.q.out @@ -51,22 +51,18 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c3 (type: string), c1 (type: int) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: c1 (type: int), c3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col1 (type: int), _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) TableScan alias: x1 Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE @@ -74,12 +70,12 @@ STAGE PLANS: predicate: ((c2 > 100) and (c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c3 (type: string), c1 (type: int) - outputColumnNames: _col0, _col1 + expressions: c1 (type: int), c3 (type: string) + outputColumnNames: c1, c3 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: int), _col0 (type: string) + aggregations: count() + keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/correlationoptimizer15.q.out ql/src/test/results/clientpositive/correlationoptimizer15.q.out index a142867..2d813b2 100644 --- ql/src/test/results/clientpositive/correlationoptimizer15.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer15.q.out @@ -63,7 +63,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -303,7 +303,7 @@ STAGE PLANS: Mux Operator Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/correlationoptimizer7.q.out ql/src/test/results/clientpositive/correlationoptimizer7.q.out index efcb46b..82fecab 100644 --- ql/src/test/results/clientpositive/correlationoptimizer7.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer7.q.out @@ -25,11 +25,11 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -67,7 +67,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -205,11 +205,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -263,7 +263,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -388,11 +388,11 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -430,7 +430,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -568,11 +568,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_1:y + $hdt$_0:$hdt$_1:y TableScan alias: y Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -626,7 +626,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/correlationoptimizer8.q.out ql/src/test/results/clientpositive/correlationoptimizer8.q.out index 1d930f8..f3cb988 100644 --- ql/src/test/results/clientpositive/correlationoptimizer8.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer8.q.out @@ -32,22 +32,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -129,22 +125,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -232,44 +224,36 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -444,22 +428,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -536,11 +516,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE @@ -657,22 +637,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -681,11 +657,11 @@ STAGE PLANS: Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE @@ -874,22 +850,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -971,22 +943,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), value (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1046,22 +1014,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1140,22 +1104,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/correlationoptimizer9.q.out ql/src/test/results/clientpositive/correlationoptimizer9.q.out index e3f11ef..be54d33 100644 --- ql/src/test/results/clientpositive/correlationoptimizer9.q.out +++ ql/src/test/results/clientpositive/correlationoptimizer9.q.out @@ -52,22 +52,18 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: c1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 114 Data size: 2546 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: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -129,22 +125,18 @@ STAGE PLANS: Filter Operator predicate: ((c2 > 100) and (c2 < 120)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c2 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: c2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 114 Data size: 2546 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: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -222,44 +214,36 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and (c1 > 100)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: c1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 114 Data size: 2546 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: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) TableScan alias: x1 Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((c2 > 100) and (c2 < 120)) (type: boolean) Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c2 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: c2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 114 Data size: 2546 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: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Demux Operator Statistics: Num rows: 228 Data size: 5092 Basic stats: COMPLETE Column stats: NONE @@ -383,22 +367,18 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c3 (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: c1 (type: int), c3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -462,11 +442,11 @@ STAGE PLANS: Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c3 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: c1, c3 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: string) + aggregations: count() + keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE @@ -553,22 +533,18 @@ STAGE PLANS: Filter Operator predicate: ((c1 < 120) and c3 is not null) (type: boolean) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: c1 (type: int), c3 (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: c1 (type: int), c3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 342 Data size: 7639 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) TableScan alias: x1 Statistics: Num rows: 1028 Data size: 22964 Basic stats: COMPLETE Column stats: NONE @@ -577,11 +553,11 @@ STAGE PLANS: Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c1 (type: int), c3 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: c1, c3 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: string) + aggregations: count() + keys: c1 (type: int), c3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 114 Data size: 2546 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/count_dist_rewrite.q.out ql/src/test/results/clientpositive/count_dist_rewrite.q.out index ceda918..d6ff5b7 100644 --- ql/src/test/results/clientpositive/count_dist_rewrite.q.out +++ ql/src/test/results/clientpositive/count_dist_rewrite.q.out @@ -365,11 +365,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -565,11 +565,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), stddev(_col1) - keys: _col1 (type: string) + aggregations: count(), stddev(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/create_view.q.out ql/src/test/results/clientpositive/create_view.q.out index d3b858a..823b716 100644 --- ql/src/test/results/clientpositive/create_view.q.out +++ ql/src/test/results/clientpositive/create_view.q.out @@ -1279,8 +1279,8 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@view14 POSTHOOK: Lineage: view14.k1 EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: view14.k2 EXPRESSION [(src)s4.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: view14.v1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: view14.v2 EXPRESSION [(src)s4.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: view14.v1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: view14.v2 EXPRESSION [(src)s3.null, (src)s4.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: DESCRIBE EXTENDED view14 PREHOOK: type: DESCTABLE PREHOOK: Input: default@view14 diff --git ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out index 1a0e46c..873a41d 100644 --- ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/dynamic_rdd_cache.q.out @@ -418,7 +418,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -553,7 +553,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -587,7 +587,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -662,7 +662,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -770,7 +770,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/except_all.q.out ql/src/test/results/clientpositive/except_all.q.out index 61c1967..4c8c4d2 100644 --- ql/src/test/results/clientpositive/except_all.q.out +++ ql/src/test/results/clientpositive/except_all.q.out @@ -221,11 +221,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -328,11 +328,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -398,11 +398,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -487,11 +487,11 @@ STAGE PLANS: function name: UDTFReplicateRows Select Operator expressions: col1 (type: string), col2 (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: col1, col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: col1 (type: string), col2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -586,7 +586,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 31 Data size: 329 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -673,11 +673,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -713,11 +713,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -753,11 +753,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -837,7 +837,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 @@ -943,7 +943,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/explain_logical.q.out ql/src/test/results/clientpositive/explain_logical.q.out index fb91a3b..4024f20 100644 --- ql/src/test/results/clientpositive/explain_logical.q.out +++ ql/src/test/results/clientpositive/explain_logical.q.out @@ -73,33 +73,33 @@ POSTHOOK: query: EXPLAIN LOGICAL SELECT key, count(1) FROM srcpart WHERE ds IS NOT NULL GROUP BY key POSTHOOK: type: QUERY LOGICAL PLAN: -$hdt$_0:srcpart +srcpart TableScan (TS_0) alias: srcpart Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_2) expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_4) - aggregations: count(1) - keys: _col0 (type: string) + Group By Operator (GBY_3) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_5) + Reduce Output Operator (RS_4) 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: bigint) - Group By Operator (GBY_6) + Group By Operator (GBY_5) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_8) + File Output Operator (FS_7) compressed: false Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE table: @@ -114,33 +114,33 @@ POSTHOOK: query: EXPLAIN LOGICAL SELECT key, count(1) FROM (SELECT key, value FROM src) subq1 GROUP BY key POSTHOOK: type: QUERY LOGICAL PLAN: -$hdt$_0:src +src TableScan (TS_0) alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator (SEL_1) expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator (GBY_3) - aggregations: count(1) - keys: _col0 (type: string) + Group By Operator (GBY_2) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator (RS_4) + Reduce Output Operator (RS_3) 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: bigint) - Group By Operator (GBY_5) + Group By Operator (GBY_4) aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator (FS_7) + File Output Operator (FS_6) compressed: false Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: diff --git ql/src/test/results/clientpositive/fold_case.q.out ql/src/test/results/clientpositive/fold_case.q.out index b2f9807..156608f 100644 --- ql/src/test/results/clientpositive/fold_case.q.out +++ ql/src/test/results/clientpositive/fold_case.q.out @@ -21,7 +21,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -72,7 +72,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -123,7 +123,7 @@ STAGE PLANS: predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -190,7 +190,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -241,7 +241,7 @@ STAGE PLANS: predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -292,7 +292,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -421,7 +421,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby4_map.q.out ql/src/test/results/clientpositive/groupby4_map.q.out index a8a7fbe..97915e7 100644 --- ql/src/test/results/clientpositive/groupby4_map.q.out +++ ql/src/test/results/clientpositive/groupby4_map.q.out @@ -27,7 +27,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -75,7 +75,7 @@ POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.key EXPRESSION [] +POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.null, ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/groupby4_map_skew.q.out ql/src/test/results/clientpositive/groupby4_map_skew.q.out index 3f38895..ae83f7a 100644 --- ql/src/test/results/clientpositive/groupby4_map_skew.q.out +++ ql/src/test/results/clientpositive/groupby4_map_skew.q.out @@ -27,7 +27,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -75,7 +75,7 @@ POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.key EXPRESSION [] +POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.null, ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/groupby_cube1.q.out ql/src/test/results/clientpositive/groupby_cube1.q.out index fd70a2c..9acccf3 100644 --- ql/src/test/results/clientpositive/groupby_cube1.q.out +++ ql/src/test/results/clientpositive/groupby_cube1.q.out @@ -33,11 +33,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -92,11 +92,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -180,7 +180,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 @@ -334,11 +334,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_position.q.out ql/src/test/results/clientpositive/groupby_position.q.out index 3ded69c..0a6c4a4 100644 --- ql/src/test/results/clientpositive/groupby_position.q.out +++ ql/src/test/results/clientpositive/groupby_position.q.out @@ -419,22 +419,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <= 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/groupby_rollup1.q.out ql/src/test/results/clientpositive/groupby_rollup1.q.out index 5fd011e..e050d0a 100644 --- ql/src/test/results/clientpositive/groupby_rollup1.q.out +++ ql/src/test/results/clientpositive/groupby_rollup1.q.out @@ -33,11 +33,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE @@ -185,11 +185,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_11.q.out ql/src/test/results/clientpositive/groupby_sort_11.q.out index fe6bbb3..23c89f9 100644 --- ql/src/test/results/clientpositive/groupby_sort_11.q.out +++ ql/src/test/results/clientpositive/groupby_sort_11.q.out @@ -99,12 +99,12 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -161,12 +161,12 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -234,12 +234,12 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0), count(1), count(_col0), sum(DISTINCT _col0) + aggregations: count(DISTINCT key), count(), count(key), sum(DISTINCT key) bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_1_23.q.out ql/src/test/results/clientpositive/groupby_sort_1_23.q.out index 9865af4..1f12c52 100644 --- ql/src/test/results/clientpositive/groupby_sort_1_23.q.out +++ ql/src/test/results/clientpositive/groupby_sort_1_23.q.out @@ -62,11 +62,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -160,7 +160,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -439,11 +439,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -510,7 +510,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -643,11 +643,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -741,7 +741,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1017,11 +1017,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1115,7 +1115,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1399,11 +1399,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1497,7 +1497,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1777,11 +1777,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1848,7 +1848,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1980,7 +1980,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2179,11 +2179,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2260,7 +2260,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2403,11 +2403,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2455,11 +2455,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2555,7 +2555,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1, null-subquery2:$hdt$_0-subquery2:t1] Stage: Stage-7 Conditional Operator @@ -2856,7 +2856,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 @@ -2965,11 +2965,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3127,7 +3127,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] #### A masked pattern was here #### Stage: Stage-8 @@ -3422,25 +3422,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3449,25 +3445,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -3522,7 +3514,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1, $hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_0:t1, $hdt$_1:t1] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -3666,25 +3658,21 @@ STAGE PLANS: isSamplingPred: false 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), val (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -3739,7 +3727,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -3778,25 +3766,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -3884,7 +3868,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -3968,12 +3952,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -4040,7 +4024,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -4171,11 +4155,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -4269,7 +4253,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -4556,11 +4540,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -4654,7 +4638,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -4940,11 +4924,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5038,7 +5022,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5331,11 +5315,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5429,7 +5413,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator diff --git ql/src/test/results/clientpositive/groupby_sort_2.q.out ql/src/test/results/clientpositive/groupby_sort_2.q.out index de6bf14..bb6273e 100644 --- ql/src/test/results/clientpositive/groupby_sort_2.q.out +++ ql/src/test/results/clientpositive/groupby_sort_2.q.out @@ -56,12 +56,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: string) - outputColumnNames: _col0 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: val (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_3.q.out ql/src/test/results/clientpositive/groupby_sort_3.q.out index da1db8c..2dae25d 100644 --- ql/src/test/results/clientpositive/groupby_sort_3.q.out +++ ql/src/test/results/clientpositive/groupby_sort_3.q.out @@ -61,11 +61,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -196,11 +196,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_4.q.out ql/src/test/results/clientpositive/groupby_sort_4.q.out index ae2ae66..70e8ac7 100644 --- ql/src/test/results/clientpositive/groupby_sort_4.q.out +++ ql/src/test/results/clientpositive/groupby_sort_4.q.out @@ -56,12 +56,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -159,11 +159,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_5.q.out ql/src/test/results/clientpositive/groupby_sort_5.q.out index 40b9769..db18928 100644 --- ql/src/test/results/clientpositive/groupby_sort_5.q.out +++ ql/src/test/results/clientpositive/groupby_sort_5.q.out @@ -61,11 +61,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -224,11 +224,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -390,12 +390,12 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_6.q.out ql/src/test/results/clientpositive/groupby_sort_6.q.out index 93e3f26..60019e7 100644 --- ql/src/test/results/clientpositive/groupby_sort_6.q.out +++ ql/src/test/results/clientpositive/groupby_sort_6.q.out @@ -41,11 +41,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -191,11 +191,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -328,11 +328,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -395,7 +395,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1/ds=2 [$hdt$_0:t1] + /t1/ds=2 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/groupby_sort_7.q.out ql/src/test/results/clientpositive/groupby_sort_7.q.out index 21b0a37..9d535e2 100644 --- ql/src/test/results/clientpositive/groupby_sort_7.q.out +++ ql/src/test/results/clientpositive/groupby_sort_7.q.out @@ -64,11 +64,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_9.q.out ql/src/test/results/clientpositive/groupby_sort_9.q.out index aa9e32e..e73727a 100644 --- ql/src/test/results/clientpositive/groupby_sort_9.q.out +++ ql/src/test/results/clientpositive/groupby_sort_9.q.out @@ -60,12 +60,12 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12 Data size: 48 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out index 16deb92..fba8adb 100644 --- ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out +++ ql/src/test/results/clientpositive/groupby_sort_skew_1_23.q.out @@ -62,11 +62,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -160,7 +160,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -440,11 +440,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -511,7 +511,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -712,11 +712,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -810,7 +810,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1086,11 +1086,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1184,7 +1184,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1468,11 +1468,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1566,7 +1566,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-7 Conditional Operator @@ -1847,11 +1847,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1918,7 +1918,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2119,7 +2119,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2387,11 +2387,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2468,7 +2468,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -2679,11 +2679,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2731,11 +2731,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2831,7 +2831,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1, null-subquery2:$hdt$_0-subquery2:t1] Stage: Stage-7 Conditional Operator @@ -3133,7 +3133,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 @@ -3310,11 +3310,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3472,7 +3472,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] #### A masked pattern was here #### Stage: Stage-8 @@ -3767,25 +3767,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan alias: t1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3794,25 +3790,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -3867,7 +3859,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1, $hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_0:t1, $hdt$_1:t1] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -4012,25 +4004,21 @@ STAGE PLANS: isSamplingPred: false 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), val (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -4085,7 +4073,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -4192,25 +4180,21 @@ STAGE PLANS: isSamplingPred: false 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) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false TableScan GatherStats: false Reduce Output Operator @@ -4298,7 +4282,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] #### A masked pattern was here #### Needs Tagging: true Reduce Operator Tree: @@ -4383,12 +4367,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -4455,7 +4439,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -4654,11 +4638,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -4752,7 +4736,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5039,11 +5023,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5137,7 +5121,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5423,11 +5407,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5521,7 +5505,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator @@ -5814,11 +5798,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -5912,7 +5896,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-7 Conditional Operator diff --git ql/src/test/results/clientpositive/groupby_sort_test_1.q.out ql/src/test/results/clientpositive/groupby_sort_test_1.q.out index 5b94c0e..d06cd7c 100644 --- ql/src/test/results/clientpositive/groupby_sort_test_1.q.out +++ ql/src/test/results/clientpositive/groupby_sort_test_1.q.out @@ -61,11 +61,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out index 3e29664..a448ef3 100644 --- ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out +++ ql/src/test/results/clientpositive/infer_bucket_sort_grouping_operators.q.out @@ -34,11 +34,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), value (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1500 Data size: 15936 Basic stats: COMPLETE Column stats: NONE @@ -1466,11 +1466,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), value (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -1644,11 +1644,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), value (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/input30.q.out ql/src/test/results/clientpositive/input30.q.out index 130f22d..478cea1 100644 --- ql/src/test/results/clientpositive/input30.q.out +++ ql/src/test/results/clientpositive/input30.q.out @@ -38,7 +38,7 @@ STAGE PLANS: predicate: (((hash(rand(460476415)) & 2147483647) % 32) = 0) (type: boolean) Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -88,7 +88,7 @@ select count(1) from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tst_dest30 -POSTHOOK: Lineage: tst_dest30.a EXPRESSION [] +POSTHOOK: Lineage: tst_dest30.a EXPRESSION [(src)src.null, ] PREHOOK: query: select * from tst_dest30 PREHOOK: type: QUERY PREHOOK: Input: default@tst_dest30 @@ -121,7 +121,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/input31.q.out ql/src/test/results/clientpositive/input31.q.out index 264ebe5..ea2c8f9 100644 --- ql/src/test/results/clientpositive/input31.q.out +++ ql/src/test/results/clientpositive/input31.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5301 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -90,7 +90,7 @@ select count(1) from srcbucket POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@tst_dest31 -POSTHOOK: Lineage: tst_dest31.a EXPRESSION [] +POSTHOOK: Lineage: tst_dest31.a EXPRESSION [(srcbucket)srcbucket.null, ] PREHOOK: query: select * from tst_dest31 PREHOOK: type: QUERY PREHOOK: Input: default@tst_dest31 diff --git ql/src/test/results/clientpositive/input32.q.out ql/src/test/results/clientpositive/input32.q.out index c8fdfd4..d3426a8 100644 --- ql/src/test/results/clientpositive/input32.q.out +++ ql/src/test/results/clientpositive/input32.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -87,7 +87,7 @@ select count(1) from srcbucket POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@tst_dest32 -POSTHOOK: Lineage: tst_dest32.a EXPRESSION [] +POSTHOOK: Lineage: tst_dest32.a EXPRESSION [(srcbucket)srcbucket.null, ] PREHOOK: query: select * from tst_dest32 PREHOOK: type: QUERY PREHOOK: Input: default@tst_dest32 diff --git ql/src/test/results/clientpositive/input39.q.out ql/src/test/results/clientpositive/input39.q.out index e5b42a7..3000404 100644 --- ql/src/test/results/clientpositive/input39.q.out +++ ql/src/test/results/clientpositive/input39.q.out @@ -110,7 +110,7 @@ STAGE PLANS: 1 _col0 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/input41.q.out ql/src/test/results/clientpositive/input41.q.out index 871f198..7cc1007 100644 --- ql/src/test/results/clientpositive/input41.q.out +++ ql/src/test/results/clientpositive/input41.q.out @@ -26,7 +26,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@srcpart POSTHOOK: Output: default@dest_sp -POSTHOOK: Lineage: dest_sp.cnt EXPRESSION [] +POSTHOOK: Lineage: dest_sp.cnt EXPRESSION [(src)src.null, (srcpart)srcpart.null, ] PREHOOK: query: select * from dest_sp x order by x.cnt limit 2 PREHOOK: type: QUERY PREHOOK: Input: default@dest_sp diff --git ql/src/test/results/clientpositive/join29.q.out ql/src/test/results/clientpositive/join29.q.out index b53143d..ef02385 100644 --- ql/src/test/results/clientpositive/join29.q.out +++ ql/src/test/results/clientpositive/join29.q.out @@ -40,22 +40,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -216,22 +212,18 @@ STAGE PLANS: Filter Operator 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 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/join30.q.out ql/src/test/results/clientpositive/join30.q.out index 3bd6db1..f06c70a 100644 --- ql/src/test/results/clientpositive/join30.q.out +++ ql/src/test/results/clientpositive/join30.q.out @@ -24,11 +24,11 @@ STAGE PLANS: Stage: Stage-6 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:x + $hdt$_0:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:x + $hdt$_0:x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE @@ -66,7 +66,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -124,7 +124,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ] POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/join31.q.out ql/src/test/results/clientpositive/join31.q.out index 32eab4f..e055b5d 100644 --- ql/src/test/results/clientpositive/join31.q.out +++ ql/src/test/results/clientpositive/join31.q.out @@ -63,11 +63,11 @@ STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:y + $hdt$_1:y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:y + $hdt$_1:y TableScan alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -101,7 +101,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/join35.q.out ql/src/test/results/clientpositive/join35.q.out index 7ece4ef..ade6646 100644 --- ql/src/test/results/clientpositive/join35.q.out +++ ql/src/test/results/clientpositive/join35.q.out @@ -46,25 +46,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + 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) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -115,7 +111,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:x] + /src [$hdt$_0-subquery1:$hdt$_0-subquery1:x] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -411,25 +407,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + 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) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -480,7 +472,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery2:$hdt$_0-subquery2:$hdt$_0:x1] + /src [$hdt$_0-subquery2:$hdt$_0-subquery2:x1] Needs Tagging: false Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/join38.q.out ql/src/test/results/clientpositive/join38.q.out index de66a59..2857de3 100644 --- ql/src/test/results/clientpositive/join38.q.out +++ ql/src/test/results/clientpositive/join38.q.out @@ -57,11 +57,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:b + $hdt$_1:b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:b + $hdt$_1:b TableScan alias: b Statistics: Num rows: 2 Data size: 126 Basic stats: COMPLETE Column stats: NONE @@ -98,22 +98,18 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Local Work: Map Reduce Local Work Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/join40.q.out ql/src/test/results/clientpositive/join40.q.out index 52b31d3..d615495 100644 --- ql/src/test/results/clientpositive/join40.q.out +++ ql/src/test/results/clientpositive/join40.q.out @@ -3734,11 +3734,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a + $hdt$_0:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a + $hdt$_0:a TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -3775,7 +3775,7 @@ STAGE PLANS: 1 _col0 (type: string) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out index 325d568..37f5484 100644 --- ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out +++ ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out @@ -316,11 +316,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: y (type: string) - outputColumnNames: _col0 + outputColumnNames: y Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: y (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -382,7 +382,7 @@ STAGE PLANS: name: default.fact_daily name: default.fact_daily Truncated Path -> Alias: - /fact_tz/ds=1/x=484 [$hdt$_0:fact_daily] + /fact_tz/ds=1/x=484 [fact_daily] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -454,7 +454,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: 484 (type: int) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/bucket_groupby.q.out ql/src/test/results/clientpositive/llap/bucket_groupby.q.out index d68797f..5913768 100644 --- ql/src/test/results/clientpositive/llap/bucket_groupby.q.out +++ ql/src/test/results/clientpositive/llap/bucket_groupby.q.out @@ -66,11 +66,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -194,11 +194,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -298,7 +298,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -379,7 +379,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -458,11 +458,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -560,11 +560,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -661,11 +661,11 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE @@ -1046,11 +1046,11 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE @@ -1161,12 +1161,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -1264,11 +1264,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -1358,10 +1358,10 @@ STAGE PLANS: alias: clustergroupby Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Select Operator @@ -1467,12 +1467,12 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE @@ -1569,12 +1569,12 @@ STAGE PLANS: alias: clustergroupby Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string), _col0 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out index e7e86d5..b970dd6 100644 --- ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out +++ ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out @@ -74,7 +74,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -222,7 +222,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -362,7 +362,7 @@ STAGE PLANS: 0 Map 1 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -517,7 +517,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -670,7 +670,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -812,7 +812,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -954,7 +954,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1095,22 +1095,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1241,22 +1237,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1384,22 +1376,18 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 Statistics: Num rows: 25 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Group By Operator + aggregations: count() + keys: _col0 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1519,22 +1507,18 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 Statistics: Num rows: 25 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Group By Operator + aggregations: count() + keys: _col0 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 12 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1657,22 +1641,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1803,22 +1783,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1950,7 +1926,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2092,7 +2068,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 43000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2234,7 +2210,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 525 Data size: 45150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2376,7 +2352,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 525 Data size: 45150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2525,7 +2501,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2674,7 +2650,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 60 Data size: 10500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -2822,7 +2798,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2970,7 +2946,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out index 8e85c02..6067c77 100644 --- ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out +++ ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out @@ -1437,7 +1437,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 217 Data size: 18879 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1625,7 +1625,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 217 Data size: 18879 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out index 21de860..f1af97d 100644 --- ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out +++ ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out @@ -162,22 +162,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 6 Execution mode: llap Reduce Operator Tree: @@ -383,22 +379,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 6 Execution mode: llap Reduce Operator Tree: @@ -562,22 +554,18 @@ STAGE PLANS: input vertices: 1 Map 6 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs Map 6 @@ -819,22 +807,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 6 Execution mode: llap Reduce Operator Tree: @@ -1040,22 +1024,18 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 6 Execution mode: llap Reduce Operator Tree: @@ -1219,22 +1199,18 @@ STAGE PLANS: input vertices: 1 Map 6 Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 60 Data size: 5160 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 14 Data size: 1316 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs Map 6 diff --git ql/src/test/results/clientpositive/llap/correlationoptimizer4.q.out ql/src/test/results/clientpositive/llap/correlationoptimizer4.q.out index 2de4cae..0f8ce65 100644 --- ql/src/test/results/clientpositive/llap/correlationoptimizer4.q.out +++ ql/src/test/results/clientpositive/llap/correlationoptimizer4.q.out @@ -142,22 +142,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -317,22 +313,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -447,22 +439,18 @@ STAGE PLANS: 1 Map 4 2 Map 5 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs Map 4 @@ -654,7 +642,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -816,7 +804,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -977,22 +965,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1143,22 +1127,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col2 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1309,22 +1289,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col2 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1475,22 +1451,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1641,22 +1613,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -1807,22 +1775,18 @@ STAGE PLANS: 2 _col0 (type: int) outputColumnNames: _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 15 Data size: 66 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: 15 Data size: 66 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out index c09a076..9b71d3e 100644 --- ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out +++ ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out @@ -118,7 +118,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -174,7 +174,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -362,7 +362,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -418,7 +418,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -540,7 +540,7 @@ STAGE PLANS: 1 Map 3 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -595,7 +595,7 @@ STAGE PLANS: 1 Map 6 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -764,22 +764,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -909,22 +905,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1115,7 +1107,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1296,7 +1288,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1459,7 +1451,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1662,7 +1654,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -1896,7 +1888,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2114,7 +2106,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2308,7 +2300,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -2526,7 +2518,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -3270,7 +3262,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -3337,7 +3329,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -3526,7 +3518,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -3582,7 +3574,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -3704,7 +3696,7 @@ STAGE PLANS: 1 Map 3 Statistics: Num rows: 44 Data size: 3784 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -3759,7 +3751,7 @@ STAGE PLANS: 1 Map 6 Statistics: Num rows: 1219 Data size: 216982 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/llap/count.q.out ql/src/test/results/clientpositive/llap/count.q.out index 2953718..0ef26e5 100644 --- ql/src/test/results/clientpositive/llap/count.q.out +++ ql/src/test/results/clientpositive/llap/count.q.out @@ -126,36 +126,40 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -263,10 +267,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Execution mode: llap @@ -275,17 +279,21 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -325,36 +333,40 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: $f1, $f2, $f3, $f4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count($f1), count($f2), count($f3), count($f4), count(DISTINCT $f1), count(DISTINCT $f2), count(DISTINCT $f3), count(DISTINCT $f4), count(DISTINCT $f1, $f2), count(DISTINCT $f2, $f3), count(DISTINCT $f3, $f4), count(DISTINCT $f1, $f4), count(DISTINCT $f1, $f3), count(DISTINCT $f2, $f4), count(DISTINCT $f1, $f2, $f3), count(DISTINCT $f2, $f3, $f4), count(DISTINCT $f1, $f3, $f4), count(DISTINCT $f1, $f2, $f4), count(DISTINCT $f1, $f2, $f3, $f4) - keys: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint) + outputColumnNames: $f0, $f00, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -865,10 +877,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: $f1, $f2, $f3, $f4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Execution mode: llap @@ -877,17 +889,21 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint) + outputColumnNames: $f0, $f00, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/count_dist_rewrite.q.out ql/src/test/results/clientpositive/llap/count_dist_rewrite.q.out index 844c833..6d41136 100644 --- ql/src/test/results/clientpositive/llap/count_dist_rewrite.q.out +++ ql/src/test/results/clientpositive/llap/count_dist_rewrite.q.out @@ -375,11 +375,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE @@ -577,11 +577,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), stddev(_col1) - keys: _col1 (type: string) + aggregations: count(), stddev(key) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col3 Statistics: Num rows: 205 Data size: 35875 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/except_distinct.q.out ql/src/test/results/clientpositive/llap/except_distinct.q.out index 4dd596e..7d2222b 100644 --- ql/src/test/results/clientpositive/llap/except_distinct.q.out +++ ql/src/test/results/clientpositive/llap/except_distinct.q.out @@ -218,11 +218,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -241,11 +241,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -384,11 +384,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -398,24 +398,12 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ @@ -431,11 +419,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -551,7 +539,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(2) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -593,7 +581,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 4656 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(2) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -760,7 +748,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 @@ -817,7 +805,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/explainuser_1.q.out ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 64a4821..2e01fc2 100644 --- ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -164,13 +164,13 @@ Stage-0 limit:-1 Stage-1 Reducer 2 llap - File Output Operator [FS_8] - Group By Operator [GBY_6] (rows=1 width=8) + File Output Operator [FS_7] + Group By Operator [GBY_5] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_5] - Group By Operator [GBY_4] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + PARTITION_ONLY_SHUFFLE [RS_4] + Group By Operator [GBY_3] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] Select Operator [SEL_2] (rows=500 width=102) TableScan [TS_0] (rows=500 width=102) default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:COMPLETE @@ -862,7 +862,7 @@ Stage-0 Reduce Output Operator [RS_25] PartitionCols:_col0 Group By Operator [GBY_24] (rows=1 width=95) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 Select Operator [SEL_5] (rows=1 width=87) Output:["_col0"] Group By Operator [GBY_4] (rows=1 width=8) @@ -879,7 +879,7 @@ Stage-0 Reduce Output Operator [RS_25] PartitionCols:_col0 Group By Operator [GBY_24] (rows=1 width=95) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 Select Operator [SEL_12] (rows=1 width=87) Output:["_col0"] Group By Operator [GBY_11] (rows=1 width=8) @@ -896,7 +896,7 @@ Stage-0 Reduce Output Operator [RS_25] PartitionCols:_col0 Group By Operator [GBY_24] (rows=1 width=95) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 Select Operator [SEL_20] (rows=1 width=87) Output:["_col0"] Group By Operator [GBY_19] (rows=1 width=8) @@ -2674,30 +2674,30 @@ Stage-0 limit:-1 Stage-1 Reducer 4 llap - File Output Operator [FS_20] - Group By Operator [GBY_18] (rows=1 width=16) + File Output Operator [FS_19] + Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_17] - Group By Operator [GBY_16] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_16] + Group By Operator [GBY_15] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_14] (rows=14 width=94) + Select Operator [SEL_13] (rows=14 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_13] (rows=14 width=94) + Group By Operator [GBY_12] (rows=14 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap - SHUFFLE [RS_12] + SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_11] (rows=14 width=94) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 - Merge Join Operator [MERGEJOIN_25] (rows=60 width=86) + Group By Operator [GBY_10] (rows=14 width=94) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 + Merge Join Operator [MERGEJOIN_24] (rows=60 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:_col0 Select Operator [SEL_2] (rows=25 width=86) Output:["_col0"] - Filter Operator [FIL_23] (rows=25 width=86) + Filter Operator [FIL_22] (rows=25 width=86) predicate:key is not null TableScan [TS_0] (rows=25 width=86) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2706,7 +2706,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] - Filter Operator [FIL_24] (rows=500 width=87) + Filter Operator [FIL_23] (rows=500 width=87) predicate:key is not null TableScan [TS_3] (rows=500 width=87) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2735,30 +2735,30 @@ Stage-0 limit:-1 Stage-1 Reducer 4 llap - File Output Operator [FS_20] - Group By Operator [GBY_18] (rows=1 width=16) + File Output Operator [FS_19] + Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_17] - Group By Operator [GBY_16] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_16] + Group By Operator [GBY_15] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_14] (rows=14 width=94) + Select Operator [SEL_13] (rows=14 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_13] (rows=14 width=94) + Group By Operator [GBY_12] (rows=14 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap - SHUFFLE [RS_12] + SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_11] (rows=14 width=94) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 - Merge Join Operator [MERGEJOIN_25] (rows=60 width=86) + Group By Operator [GBY_10] (rows=14 width=94) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 + Merge Join Operator [MERGEJOIN_24] (rows=60 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] PartitionCols:_col0 Select Operator [SEL_2] (rows=25 width=86) Output:["_col0"] - Filter Operator [FIL_23] (rows=25 width=86) + Filter Operator [FIL_22] (rows=25 width=86) predicate:key is not null TableScan [TS_0] (rows=25 width=86) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2767,7 +2767,7 @@ Stage-0 PartitionCols:_col0 Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] - Filter Operator [FIL_24] (rows=500 width=87) + Filter Operator [FIL_23] (rows=500 width=87) predicate:key is not null TableScan [TS_3] (rows=500 width=87) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2796,36 +2796,36 @@ Stage-0 limit:-1 Stage-1 Reducer 4 llap - File Output Operator [FS_20] - Group By Operator [GBY_18] (rows=1 width=16) + File Output Operator [FS_19] + Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_17] - Group By Operator [GBY_16] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_16] + Group By Operator [GBY_15] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_14] (rows=14 width=94) + Select Operator [SEL_13] (rows=14 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_13] (rows=14 width=94) + Group By Operator [GBY_12] (rows=14 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Map 2 [SIMPLE_EDGE] llap - SHUFFLE [RS_12] + SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_11] (rows=14 width=94) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 - Map Join Operator [MAPJOIN_25] (rows=60 width=86) + Group By Operator [GBY_10] (rows=14 width=94) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 + Map Join Operator [MAPJOIN_24] (rows=60 width=86) Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col0"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_6] PartitionCols:_col0 Select Operator [SEL_2] (rows=25 width=86) Output:["_col0"] - Filter Operator [FIL_23] (rows=25 width=86) + Filter Operator [FIL_22] (rows=25 width=86) predicate:key is not null TableScan [TS_0] (rows=25 width=86) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] <-Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] - Filter Operator [FIL_24] (rows=500 width=87) + Filter Operator [FIL_23] (rows=500 width=87) predicate:key is not null TableScan [TS_3] (rows=500 width=87) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2854,30 +2854,30 @@ Stage-0 limit:-1 Stage-1 Reducer 4 llap - File Output Operator [FS_22] - Group By Operator [GBY_20] (rows=1 width=16) + File Output Operator [FS_21] + Group By Operator [GBY_19] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_19] - Group By Operator [GBY_18] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_18] + Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_16] (rows=12 width=94) + Select Operator [SEL_15] (rows=12 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_15] (rows=12 width=94) + Group By Operator [GBY_14] (rows=12 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap - SHUFFLE [RS_14] + SHUFFLE [RS_13] PartitionCols:_col0 - Group By Operator [GBY_13] (rows=12 width=94) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 - Merge Join Operator [MERGEJOIN_27] (rows=25 width=86) + Group By Operator [GBY_12] (rows=12 width=94) + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 + Merge Join Operator [MERGEJOIN_26] (rows=25 width=86) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:_col0 Select Operator [SEL_2] (rows=25 width=86) Output:["_col0"] - Filter Operator [FIL_25] (rows=25 width=86) + Filter Operator [FIL_24] (rows=25 width=86) predicate:key is not null TableScan [TS_0] (rows=25 width=86) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -2888,7 +2888,7 @@ Stage-0 Output:["_col0"],keys:_col0 Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] - Filter Operator [FIL_26] (rows=500 width=87) + Filter Operator [FIL_25] (rows=500 width=87) predicate:key is not null TableScan [TS_3] (rows=500 width=87) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] @@ -3050,11 +3050,11 @@ Stage-0 limit:-1 Stage-1 Reducer 2 llap - File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + File Output Operator [FS_5] + Group By Operator [GBY_3] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_3] + PARTITION_ONLY_SHUFFLE [RS_2] Select Operator [SEL_1] (rows=5 width=6) TableScan [TS_0] (rows=5 width=6) default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:COMPLETE @@ -3122,11 +3122,11 @@ Stage-0 limit:-1 Stage-1 Reducer 2 llap - File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + File Output Operator [FS_5] + Group By Operator [GBY_3] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_3] + PARTITION_ONLY_SHUFFLE [RS_2] Select Operator [SEL_1] (rows=5 width=6) TableScan [TS_0] (rows=5 width=6) default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:COMPLETE @@ -5670,30 +5670,30 @@ Stage-0 limit:-1 Stage-1 Reducer 3 llap - File Output Operator [FS_16] - Group By Operator [GBY_14] (rows=1 width=8) + File Output Operator [FS_15] + Group By Operator [GBY_13] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_13] - Group By Operator [GBY_12] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + PARTITION_ONLY_SHUFFLE [RS_12] + Group By Operator [GBY_11] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_11] + PARTITION_ONLY_SHUFFLE [RS_10] PartitionCols:rand() - Map Join Operator [MAPJOIN_21] (rows=1 width=33) + Map Join Operator [MAPJOIN_20] (rows=1 width=33) Conds:SEL_2._col0=RS_7._col0(Inner) <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_7] PartitionCols:_col0 Select Operator [SEL_5] (rows=1 width=30) Output:["_col0"] - Filter Operator [FIL_20] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=30) predicate:key is not null TableScan [TS_3] (rows=1 width=30) default@t1,b,Tbl:COMPLETE,Col:NONE,Output:["key"] <-Select Operator [SEL_2] (rows=1 width=30) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_18] (rows=1 width=30) predicate:key is not null TableScan [TS_0] (rows=1 width=30) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key"] diff --git ql/src/test/results/clientpositive/llap/explainuser_2.q.out ql/src/test/results/clientpositive/llap/explainuser_2.q.out index 42d5f85..f8a6526 100644 --- ql/src/test/results/clientpositive/llap/explainuser_2.q.out +++ ql/src/test/results/clientpositive/llap/explainuser_2.q.out @@ -3224,52 +3224,52 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 5 llap - File Output Operator [FS_22] + File Output Operator [FS_21] table:{"name:":"default.dest1"} - Select Operator [SEL_20] (rows=1 width=272) + Select Operator [SEL_19] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_19] (rows=1 width=96) + Group By Operator [GBY_18] (rows=1 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] + SHUFFLE [RS_17] PartitionCols:_col0 - Group By Operator [GBY_17] (rows=1 width=280) + Group By Operator [GBY_16] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Group By Operator [GBY_14] (rows=1 width=272) + Group By Operator [GBY_13] (rows=1 width=272) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] llap - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=1 width=272) + Group By Operator [GBY_11] (rows=1 width=272) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_8] (rows=500 width=10) + Select Operator [SEL_7] (rows=500 width=10) Output:["_col0","_col1"] - TableScan [TS_7] (rows=500 width=10) + TableScan [TS_6] (rows=500 width=10) Output:["key","value"] <-Reducer 2 [CONTAINS] llap - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=1 width=272) + Group By Operator [GBY_11] (rows=1 width=272) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_6] (rows=1 width=272) + Select Operator [SEL_5] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_5] (rows=1 width=8) + Group By Operator [GBY_4] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_4] - Group By Operator [GBY_3] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + PARTITION_ONLY_SHUFFLE [RS_3] + Group By Operator [GBY_2] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] Select Operator [SEL_1] (rows=500 width=10) TableScan [TS_0] (rows=500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - File Output Operator [FS_29] + File Output Operator [FS_28] table:{"name:":"default.dest2"} - Select Operator [SEL_27] (rows=1 width=456) + Select Operator [SEL_26] (rows=1 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_26] (rows=1 width=464) + Group By Operator [GBY_25] (rows=1 width=464) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1 - Please refer to the previous Group By Operator [GBY_14] + Please refer to the previous Group By Operator [GBY_13] Stage-5 Stats-Aggr Operator Stage-1 @@ -3398,68 +3398,68 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 llap - File Output Operator [FS_19] + File Output Operator [FS_18] table:{"name:":"default.dest1"} - Select Operator [SEL_17] (rows=1 width=272) + Select Operator [SEL_16] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_16] (rows=1 width=96) + Group By Operator [GBY_15] (rows=1 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] llap - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_14] PartitionCols:_col0 - Group By Operator [GBY_14] (rows=1 width=280) + Group By Operator [GBY_13] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_8] (rows=500 width=10) + Select Operator [SEL_7] (rows=500 width=10) Output:["_col0","_col1"] - TableScan [TS_7] (rows=500 width=10) + TableScan [TS_6] (rows=500 width=10) Output:["key","value"] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_21] (rows=1 width=464) + Group By Operator [GBY_20] (rows=1 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_8] + Please refer to the previous Select Operator [SEL_7] <-Map 7 [CONTAINS] llap - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_14] PartitionCols:_col0 - Group By Operator [GBY_14] (rows=1 width=280) + Group By Operator [GBY_13] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_11] (rows=500 width=10) + Select Operator [SEL_10] (rows=500 width=10) Output:["_col0","_col1"] - TableScan [TS_10] (rows=500 width=10) + TableScan [TS_9] (rows=500 width=10) Output:["key","value"] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_21] (rows=1 width=464) + Group By Operator [GBY_20] (rows=1 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_11] + Please refer to the previous Select Operator [SEL_10] <-Reducer 2 [CONTAINS] llap - Reduce Output Operator [RS_15] + Reduce Output Operator [RS_14] PartitionCols:_col0 - Group By Operator [GBY_14] (rows=1 width=280) + Group By Operator [GBY_13] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_6] (rows=1 width=272) + Select Operator [SEL_5] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_5] (rows=1 width=8) + Group By Operator [GBY_4] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_4] - Group By Operator [GBY_3] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + PARTITION_ONLY_SHUFFLE [RS_3] + Group By Operator [GBY_2] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] Select Operator [SEL_1] (rows=500 width=10) TableScan [TS_0] (rows=500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_21] (rows=1 width=464) + Group By Operator [GBY_20] (rows=1 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_6] + Please refer to the previous Select Operator [SEL_5] Reducer 5 llap - File Output Operator [FS_26] + File Output Operator [FS_25] table:{"name:":"default.dest2"} - Select Operator [SEL_24] (rows=1 width=456) + Select Operator [SEL_23] (rows=1 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_23] (rows=1 width=280) + Group By Operator [GBY_22] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5 @@ -3506,54 +3506,54 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 llap - File Output Operator [FS_17] + File Output Operator [FS_16] table:{"name:":"default.dest1"} - Select Operator [SEL_15] (rows=1 width=272) + Select Operator [SEL_14] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=1 width=96) + Group By Operator [GBY_13] (rows=1 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] llap - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=1 width=280) + Group By Operator [GBY_11] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_8] (rows=500 width=10) + Select Operator [SEL_7] (rows=500 width=10) Output:["_col0","_col1"] - TableScan [TS_7] (rows=500 width=10) + TableScan [TS_6] (rows=500 width=10) Output:["key","value"] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] PartitionCols:_col0, _col1 - Group By Operator [GBY_19] (rows=1 width=464) + Group By Operator [GBY_18] (rows=1 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_8] + Please refer to the previous Select Operator [SEL_7] <-Reducer 2 [CONTAINS] llap - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=1 width=280) + Group By Operator [GBY_11] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_6] (rows=1 width=272) + Select Operator [SEL_5] (rows=1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_5] (rows=1 width=8) + Group By Operator [GBY_4] (rows=1 width=8) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_4] - Group By Operator [GBY_3] (rows=1 width=8) - Output:["_col0"],aggregations:["count(1)"] + PARTITION_ONLY_SHUFFLE [RS_3] + Group By Operator [GBY_2] (rows=1 width=8) + Output:["_col0"],aggregations:["count()"] Select Operator [SEL_1] (rows=500 width=10) TableScan [TS_0] (rows=500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] PartitionCols:_col0, _col1 - Group By Operator [GBY_19] (rows=1 width=464) + Group By Operator [GBY_18] (rows=1 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_6] + Please refer to the previous Select Operator [SEL_5] Reducer 5 llap - File Output Operator [FS_24] + File Output Operator [FS_23] table:{"name:":"default.dest2"} - Select Operator [SEL_22] (rows=1 width=456) + Select Operator [SEL_21] (rows=1 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_21] (rows=1 width=280) + Group By Operator [GBY_20] (rows=1 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5 diff --git ql/src/test/results/clientpositive/llap/intersect_all.q.out ql/src/test/results/clientpositive/llap/intersect_all.q.out index 2422090..1a3a035 100644 --- ql/src/test/results/clientpositive/llap/intersect_all.q.out +++ ql/src/test/results/clientpositive/llap/intersect_all.q.out @@ -158,11 +158,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -181,11 +181,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -813,11 +813,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -836,11 +836,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -859,11 +859,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -882,11 +882,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -1598,7 +1598,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 @@ -1654,7 +1654,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/intersect_distinct.q.out ql/src/test/results/clientpositive/llap/intersect_distinct.q.out index 6921d53..a871ba3 100644 --- ql/src/test/results/clientpositive/llap/intersect_distinct.q.out +++ ql/src/test/results/clientpositive/llap/intersect_distinct.q.out @@ -156,11 +156,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -179,11 +179,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -613,11 +613,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -636,11 +636,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -659,11 +659,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -682,11 +682,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -1200,7 +1200,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 @@ -1249,7 +1249,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/intersect_merge.q.out ql/src/test/results/clientpositive/llap/intersect_merge.q.out index cf86a32..654cd64 100644 --- ql/src/test/results/clientpositive/llap/intersect_merge.q.out +++ ql/src/test/results/clientpositive/llap/intersect_merge.q.out @@ -58,11 +58,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -81,11 +81,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -104,11 +104,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -127,11 +127,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -150,11 +150,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -330,11 +330,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -353,11 +353,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -376,11 +376,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -399,11 +399,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -559,11 +559,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -582,11 +582,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -605,11 +605,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -628,11 +628,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -651,11 +651,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -832,11 +832,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -855,11 +855,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -878,11 +878,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -901,11 +901,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -924,11 +924,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1105,11 +1105,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1128,11 +1128,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1151,11 +1151,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1174,11 +1174,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1197,11 +1197,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1376,11 +1376,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1399,11 +1399,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1422,11 +1422,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1559,11 +1559,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1582,11 +1582,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1605,11 +1605,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1750,11 +1750,11 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE @@ -1779,11 +1779,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: int), _col1 (type: int) + aggregations: count() + keys: key (type: int), value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1884,7 +1884,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int), _col1 (type: int) mode: complete outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/llap/limit_pushdown.q.out ql/src/test/results/clientpositive/llap/limit_pushdown.q.out index d1d6664..93315e6 100644 --- ql/src/test/results/clientpositive/llap/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/llap/limit_pushdown.q.out @@ -917,11 +917,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/lineage2.q.out ql/src/test/results/clientpositive/llap/lineage2.q.out index 79590a7..051cba9 100644 --- ql/src/test/results/clientpositive/llap/lineage2.q.out +++ ql/src/test/results/clientpositive/llap/lineage2.q.out @@ -140,7 +140,7 @@ PREHOOK: query: select key, count(1) a from dest1 group by key PREHOOK: type: QUERY PREHOOK: Input: default@dest1 #### A masked pattern was here #### -{"version":"1.0","engine":"tez","database":"default","hash":"3901b5e3a164064736b3234355046340","queryText":"select key, count(1) a from dest1 group by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"count(1)","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"a"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest1.key"},{"id":3,"vertexType":"TABLE","vertexId":"default.dest1"}]} +{"version":"1.0","engine":"tez","database":"default","hash":"3901b5e3a164064736b3234355046340","queryText":"select key, count(1) a from dest1 group by key","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"count(*)","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"key"},{"id":1,"vertexType":"COLUMN","vertexId":"a"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest1.key"},{"id":3,"vertexType":"TABLE","vertexId":"default.dest1"}]} 128 2 213 2 278 2 diff --git ql/src/test/results/clientpositive/llap/merge1.q.out ql/src/test/results/clientpositive/llap/merge1.q.out index 4bcb728..8021b67 100644 --- ql/src/test/results/clientpositive/llap/merge1.q.out +++ ql/src/test/results/clientpositive/llap/merge1.q.out @@ -35,11 +35,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/merge2.q.out ql/src/test/results/clientpositive/llap/merge2.q.out index aa0567b..7bcdd2d 100644 --- ql/src/test/results/clientpositive/llap/merge2.q.out +++ ql/src/test/results/clientpositive/llap/merge2.q.out @@ -35,11 +35,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out index 81483f1..594e7e7 100644 --- ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out +++ ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out @@ -204,31 +204,35 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -264,31 +268,35 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -324,31 +332,31 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -388,31 +396,31 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 1054697 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Execution mode: llap LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out index 4b3a846..48e58e1 100644 --- ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out +++ ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out @@ -1311,18 +1311,18 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 2.0E-5 Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: key (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: key (type: string) Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 2.0E-5 Execution mode: llap @@ -1331,7 +1331,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -1375,7 +1375,7 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out index 8aeb029..1f667c0 100644 --- ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out +++ ql/src/test/results/clientpositive/llap/skewjoinopt15.q.out @@ -332,7 +332,7 @@ STAGE PLANS: 1 _col0 (type: int) Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -435,7 +435,7 @@ STAGE PLANS: 1 _col0 (type: int) Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/llap/subquery_null_agg.q.out ql/src/test/results/clientpositive/llap/subquery_null_agg.q.out index dde2384..54954c0 100644 --- ql/src/test/results/clientpositive/llap/subquery_null_agg.q.out +++ ql/src/test/results/clientpositive/llap/subquery_null_agg.q.out @@ -6,8 +6,8 @@ POSTHOOK: query: CREATE TABLE table_7 (int_col INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@table_7 -Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product -Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[28][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain SELECT (t1.int_col) * (t1.int_col) AS int_col @@ -75,14 +75,14 @@ STAGE PLANS: predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE Group By Operator - aggregations: count(), count(false) + aggregations: count() mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Filter Operator predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -108,10 +108,10 @@ STAGE PLANS: 0 1 outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: llap @@ -122,18 +122,18 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1, _col3 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col3 is null or (_col1 = 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + predicate: (_col2 is null or (_col1 = 0)) (type: boolean) + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: null (type: double) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -142,21 +142,14 @@ STAGE PLANS: Execution mode: llap Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) + aggregations: count(VALUE._col0) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: ((_col1 >= _col0) or (_col0 = 0)) (type: boolean) - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint) Reducer 5 Execution mode: llap Reduce Operator Tree: diff --git ql/src/test/results/clientpositive/llap/subquery_scalar.q.out ql/src/test/results/clientpositive/llap/subquery_scalar.q.out index 4bd2ed0..2a1448b 100644 --- ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -2921,7 +2921,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 @@ -2962,7 +2962,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 @@ -3028,7 +3028,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 @@ -3112,7 +3112,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: bigint) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out index d240039..8545922 100644 --- ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out +++ ql/src/test/results/clientpositive/llap/table_access_keys_stats.q.out @@ -18,7 +18,7 @@ PREHOOK: query: SELECT key, count(1) FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -31,7 +31,7 @@ PREHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -45,7 +45,7 @@ PREHOOK: query: SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -58,7 +58,7 @@ PREHOOK: query: SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -71,7 +71,7 @@ PREHOOK: query: SELECT 1, key, count(1) FROM T1 GROUP BY 1, key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -84,7 +84,7 @@ PREHOOK: query: SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -98,7 +98,7 @@ PREHOOK: query: SELECT key, 1, val, 2, count(1) FROM T1 GROUP BY key, 1, val, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -123,7 +123,7 @@ group by key + key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -140,11 +140,11 @@ SELECT key, count(1) as c FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key -Operator:GBY_10 +Operator:GBY_8 Table:default@t1 Keys:key @@ -166,11 +166,11 @@ ON subq1.key = subq2.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key @@ -188,11 +188,11 @@ ORDER BY subq1.key ASC, subq1.c ASC, subq2.key ASC, subq2.val ASC, subq2.c ASC PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key,val @@ -208,7 +208,7 @@ group by key, constant, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -231,7 +231,7 @@ GROUP BY key, constant3, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -566,11 +566,11 @@ ON subq1.key = subq2.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key diff --git ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out index 07640a7..5e0d072 100644 --- ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out +++ ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out @@ -68,7 +68,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -283,10 +283,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), (src)s0.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), (src)s0.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), (src)s0.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -1008,7 +1008,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1188,10 +1188,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s0.FieldSchema(name:key, type:string, comment:default), (src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s0.FieldSchema(name:key, type:string, comment:default), (src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -1911,7 +1911,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2089,10 +2089,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s0.FieldSchema(name:key, type:string, comment:default), (src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s0.FieldSchema(name:key, type:string, comment:default), (src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s0.FieldSchema(name:value, type:string, comment:default), (src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -2772,7 +2772,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2944,10 +2944,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -3627,7 +3627,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3791,10 +3791,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/llap/union2.q.out ql/src/test/results/clientpositive/llap/union2.q.out index 8b889af..4bc56fb 100644 --- ql/src/test/results/clientpositive/llap/union2.q.out +++ ql/src/test/results/clientpositive/llap/union2.q.out @@ -30,7 +30,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -50,7 +50,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/union4.q.out ql/src/test/results/clientpositive/llap/union4.q.out index b9ca42d..796bc60 100644 --- ql/src/test/results/clientpositive/llap/union4.q.out +++ ql/src/test/results/clientpositive/llap/union4.q.out @@ -41,7 +41,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -59,7 +59,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -151,7 +151,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/llap/union5.q.out ql/src/test/results/clientpositive/llap/union5.q.out index c6a8712..a087912 100644 --- ql/src/test/results/clientpositive/llap/union5.q.out +++ ql/src/test/results/clientpositive/llap/union5.q.out @@ -75,7 +75,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -115,7 +115,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/llap/union6.q.out ql/src/test/results/clientpositive/llap/union6.q.out index dca14c1..4043e3c 100644 --- ql/src/test/results/clientpositive/llap/union6.q.out +++ ql/src/test/results/clientpositive/llap/union6.q.out @@ -41,7 +41,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -126,7 +126,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from tmptable x sort by x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/llap/union7.q.out ql/src/test/results/clientpositive/llap/union7.q.out index 61a5ea4..4af80e9 100644 --- ql/src/test/results/clientpositive/llap/union7.q.out +++ ql/src/test/results/clientpositive/llap/union7.q.out @@ -52,7 +52,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -78,7 +78,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -128,20 +128,20 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 #### A masked pattern was here #### - 10 128 1 -146 1 -150 1 213 1 -224 1 +278 1 +369 1 +tst1 1 + 10 +150 1 238 1 +66 1 +146 1 +224 1 255 1 273 1 -278 1 311 1 -369 1 401 1 406 1 -66 1 98 1 -tst1 1 diff --git ql/src/test/results/clientpositive/llap/union9.q.out ql/src/test/results/clientpositive/llap/union9.q.out index 94e6c02..1f9fe2c 100644 --- ql/src/test/results/clientpositive/llap/union9.q.out +++ ql/src/test/results/clientpositive/llap/union9.q.out @@ -33,7 +33,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -53,7 +53,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -73,7 +73,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out index ead0909..602d576 100644 --- ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out +++ ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out @@ -48,7 +48,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -70,7 +70,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -224,7 +224,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, (src)s3.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable @@ -274,7 +274,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -296,7 +296,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -359,7 +359,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -495,7 +495,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -513,7 +513,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -531,7 +531,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -689,7 +689,7 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@tmptable12 POSTHOOK: Lineage: tmptable12.key EXPRESSION [] -POSTHOOK: Lineage: tmptable12.value EXPRESSION [] +POSTHOOK: Lineage: tmptable12.value EXPRESSION [(src)s1.null, (src1)s2.null, (srcbucket)s3.null, ] PREHOOK: query: select * from tmptable12 x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable12 @@ -1163,7 +1163,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1186,7 +1186,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 3536 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -1300,7 +1300,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -1405,7 +1405,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 19 Data size: 5168 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -2484,7 +2484,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2740,7 +2740,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -2902,10 +2902,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 @@ -3598,7 +3598,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -3730,10 +3730,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest118 POSTHOOK: Output: default@dest218 POSTHOOK: Lineage: dest118.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest118.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest118.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest218.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest218.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest218.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest218.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest218.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST118.* FROM DEST118 SORT BY DEST118.key, DEST118.value PREHOOK: type: QUERY PREHOOK: Input: default@dest118 @@ -4426,7 +4426,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -4568,10 +4568,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest119 POSTHOOK: Output: default@dest219 POSTHOOK: Lineage: dest119.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest119.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest119.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest219.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest219.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest219.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest219.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest219.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST119.* FROM DEST119 SORT BY DEST119.key, DEST119.value PREHOOK: type: QUERY PREHOOK: Input: default@dest119 @@ -5284,7 +5284,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -5373,7 +5373,7 @@ STAGE PLANS: alias: s1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -7783,25 +7783,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: true + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: true Execution mode: llap LLAP IO: no inputs Path -> Alias: @@ -8848,7 +8844,7 @@ STAGE PLANS: Position of Big Table: 0 Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -9260,7 +9256,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 375 Data size: 66750 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 @@ -10855,11 +10851,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -10878,11 +10874,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -11672,11 +11668,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -11716,11 +11712,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 46500 Basic stats: COMPLETE Column stats: COMPLETE @@ -12281,11 +12277,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -12304,11 +12300,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -12613,11 +12609,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -14490,7 +14486,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -14508,7 +14504,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -14616,7 +14612,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable @@ -14659,7 +14655,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -14677,7 +14673,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -14722,7 +14718,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -14831,7 +14827,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -14936,7 +14932,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from tmptable x sort by x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable @@ -15000,7 +14996,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -15066,7 +15062,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 3536 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 @@ -15691,7 +15687,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/union_remove_26.q.out ql/src/test/results/clientpositive/llap/union_remove_26.q.out index 67fef54..9ddc2c8 100644 --- ql/src/test/results/clientpositive/llap/union_remove_26.q.out +++ ql/src/test/results/clientpositive/llap/union_remove_26.q.out @@ -155,10 +155,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -175,10 +175,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -195,10 +195,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -375,11 +375,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: int) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col2), max(_col2) - keys: _col0 (type: string) + aggregations: count(), min(val), max(val) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE @@ -398,11 +398,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: int) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col2), max(_col2) - keys: _col0 (type: string) + aggregations: count(), min(val), max(val) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 303 Basic stats: COMPLETE Column stats: COMPLETE @@ -421,11 +421,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: string), val (type: int) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col2), max(_col2) - keys: _col0 (type: string) + aggregations: count(), min(val), max(val) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: COMPLETE @@ -550,10 +550,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -570,10 +570,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -590,10 +590,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -713,10 +713,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -733,10 +733,10 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE @@ -753,10 +753,10 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: val (type: int) - outputColumnNames: _col1 + outputColumnNames: val Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1), min(_col1), max(_col1) + aggregations: count(), min(val), max(val) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/llap/vector_between_in.q.out ql/src/test/results/clientpositive/llap/vector_between_in.q.out index 80c3060..664e342 100644 --- ql/src/test/results/clientpositive/llap/vector_between_in.q.out +++ ql/src/test/results/clientpositive/llap/vector_between_in.q.out @@ -1112,9 +1112,9 @@ STAGE PLANS: selectExpressions: LongColumnInList(col 3, values [-67, -171]) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1254,9 +1254,9 @@ STAGE PLANS: selectExpressions: DecimalColumnInList(col 1, values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1396,9 +1396,9 @@ STAGE PLANS: selectExpressions: VectorUDFAdaptor(cdate BETWEEN 1969-12-30 AND 1970-01-02) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1538,9 +1538,9 @@ STAGE PLANS: selectExpressions: VectorUDFAdaptor(cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true diff --git ql/src/test/results/clientpositive/llap/vector_count.q.out ql/src/test/results/clientpositive/llap/vector_count.q.out index 21d92cd..c1a24cc 100644 --- ql/src/test/results/clientpositive/llap/vector_count.q.out +++ ql/src/test/results/clientpositive/llap/vector_count.q.out @@ -185,26 +185,26 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3] Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 4:long) -> bigint, VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true keyExpressions: col 0, col 1, col 2, col 3 native: false vectorProcessingMode: HASH - projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) @@ -215,7 +215,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: No DISTINCT columns IS false Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -235,17 +235,21 @@ STAGE PLANS: vectorized: false Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -389,14 +393,14 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3] Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Reduce Sink Vectorization: className: VectorReduceSinkOperator @@ -423,17 +427,21 @@ STAGE PLANS: vectorized: false Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/llap/vector_groupby_cube1.q.out ql/src/test/results/clientpositive/llap/vector_groupby_cube1.q.out index 2fa1efe..0b3406f 100644 --- ql/src/test/results/clientpositive/llap/vector_groupby_cube1.q.out +++ ql/src/test/results/clientpositive/llap/vector_groupby_cube1.q.out @@ -39,11 +39,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -108,11 +108,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -206,7 +206,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 @@ -380,11 +380,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/llap/vector_groupby_rollup1.q.out ql/src/test/results/clientpositive/llap/vector_groupby_rollup1.q.out index e737f0b..d1002e4 100644 --- ql/src/test/results/clientpositive/llap/vector_groupby_rollup1.q.out +++ ql/src/test/results/clientpositive/llap/vector_groupby_rollup1.q.out @@ -51,11 +51,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE @@ -223,11 +223,11 @@ STAGE PLANS: Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 18 Data size: 3078 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out index f66a0c4..03c6d3f 100644 --- ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out +++ ql/src/test/results/clientpositive/llap/vector_mr_diff_schema_alias.q.out @@ -360,23 +360,19 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 4 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: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: bigint) + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: bigint) Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: diff --git ql/src/test/results/clientpositive/merge1.q.out ql/src/test/results/clientpositive/merge1.q.out index 2487bf7..7423d83 100644 --- ql/src/test/results/clientpositive/merge1.q.out +++ ql/src/test/results/clientpositive/merge1.q.out @@ -33,11 +33,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/merge2.q.out ql/src/test/results/clientpositive/merge2.q.out index a8b4bd5..bbc55d8 100644 --- ql/src/test/results/clientpositive/merge2.q.out +++ ql/src/test/results/clientpositive/merge2.q.out @@ -33,11 +33,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/metadata_only_queries.q.out ql/src/test/results/clientpositive/metadata_only_queries.q.out index 82b4a41..72a90fb 100644 --- ql/src/test/results/clientpositive/metadata_only_queries.q.out +++ ql/src/test/results/clientpositive/metadata_only_queries.q.out @@ -198,27 +198,31 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -248,27 +252,31 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -298,27 +306,27 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -352,27 +360,27 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git ql/src/test/results/clientpositive/notable_alias1.q.out ql/src/test/results/clientpositive/notable_alias1.q.out index 200b31c..677545d 100644 --- ql/src/test/results/clientpositive/notable_alias1.q.out +++ ql/src/test/results/clientpositive/notable_alias1.q.out @@ -29,22 +29,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/notable_alias2.q.out ql/src/test/results/clientpositive/notable_alias2.q.out index 4df8073..66d0b2a 100644 --- ql/src/test/results/clientpositive/notable_alias2.q.out +++ ql/src/test/results/clientpositive/notable_alias2.q.out @@ -29,22 +29,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) < 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/nullgroup.q.out ql/src/test/results/clientpositive/nullgroup.q.out index 497010f..53c74b4 100644 --- ql/src/test/results/clientpositive/nullgroup.q.out +++ ql/src/test/results/clientpositive/nullgroup.q.out @@ -21,7 +21,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -81,7 +81,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -147,7 +147,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() mode: partial1 outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -222,7 +222,7 @@ STAGE PLANS: Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() mode: complete outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup2.q.out ql/src/test/results/clientpositive/nullgroup2.q.out index 1f4ebb3..3886a98 100644 --- ql/src/test/results/clientpositive/nullgroup2.q.out +++ ql/src/test/results/clientpositive/nullgroup2.q.out @@ -19,22 +19,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) 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: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -108,22 +104,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -174,18 +166,14 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) 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: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 @@ -256,18 +244,14 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (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 Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/nullgroup3.q.out ql/src/test/results/clientpositive/nullgroup3.q.out index bc7bfaa..fe23f39 100644 --- ql/src/test/results/clientpositive/nullgroup3.q.out +++ ql/src/test/results/clientpositive/nullgroup3.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -131,7 +131,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -226,7 +226,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 5812 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -321,7 +321,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup4.q.out ql/src/test/results/clientpositive/nullgroup4.q.out index d4c8e6a..b687c55 100644 --- ql/src/test/results/clientpositive/nullgroup4.q.out +++ ql/src/test/results/clientpositive/nullgroup4.q.out @@ -21,11 +21,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1) - keys: _col1 (type: string) + aggregations: count(), count(DISTINCT value) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -108,11 +108,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -201,16 +201,16 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: partial1 outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -280,15 +280,15 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out index 5349b17..7076579 100644 --- ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out +++ ql/src/test/results/clientpositive/nullgroup4_multi_distinct.q.out @@ -20,11 +20,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col1 (type: string), _col2 (type: string) + aggregations: count(), count(DISTINCT _col0), count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -84,15 +84,15 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/partition_boolexpr.q.out ql/src/test/results/clientpositive/partition_boolexpr.q.out index 0f2a85d..b605260 100644 --- ql/src/test/results/clientpositive/partition_boolexpr.q.out +++ ql/src/test/results/clientpositive/partition_boolexpr.q.out @@ -58,7 +58,7 @@ STAGE PLANS: predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -149,7 +149,7 @@ STAGE PLANS: predicate: false (type: boolean) Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/perf/query38.q.out ql/src/test/results/clientpositive/perf/query38.q.out index 1fae4e2..81fc9f3 100644 --- ql/src/test/results/clientpositive/perf/query38.q.out +++ ql/src/test/results/clientpositive/perf/query38.q.out @@ -62,145 +62,151 @@ Stage-0 limit:100 Stage-1 Reducer 7 - File Output Operator [FS_92] - Limit [LIM_91] (rows=1 width=16) + File Output Operator [FS_89] + Limit [LIM_88] (rows=1 width=16) Number of rows:100 - Group By Operator [GBY_89] (rows=1 width=16) + Group By Operator [GBY_86] (rows=1 width=16) Output:["_col0"],aggregations:["count(VALUE._col0)"] <-Reducer 6 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_88] - Group By Operator [GBY_87] (rows=1 width=16) + PARTITION_ONLY_SHUFFLE [RS_85] + Group By Operator [GBY_84] (rows=1 width=16) Output:["_col0"],aggregations:["count()"] - Select Operator [SEL_85] (rows=1 width=108) - Filter Operator [FIL_84] (rows=1 width=108) + Select Operator [SEL_82] (rows=1 width=108) + Filter Operator [FIL_81] (rows=1 width=108) predicate:(_col3 = 3) - Select Operator [SEL_117] (rows=152458212 width=108) + Select Operator [SEL_114] (rows=152458212 width=108) Output:["_col3"] - Group By Operator [GBY_83] (rows=152458212 width=108) + Group By Operator [GBY_80] (rows=152458212 width=108) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 <-Union 5 [SIMPLE_EDGE] <-Reducer 11 [CONTAINS] - Reduce Output Operator [RS_82] + Reduce Output Operator [RS_79] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_81] (rows=304916424 width=108) + Group By Operator [GBY_78] (rows=304916424 width=108) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_50] (rows=87116929 width=135) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_44] (rows=174233858 width=135) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 10 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_42] (rows=348467716 width=135) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_121] (rows=348467716 width=135) - Conds:RS_38._col1=RS_39._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_39] - PartitionCols:_col0 - Select Operator [SEL_8] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_110] (rows=80000000 width=860) - predicate:c_customer_sk is not null - TableScan [TS_6] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_38] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_120] (rows=316788826 width=135) - Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col3"] - <-Map 8 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=8116 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_109] (rows=8116 width=1119) - predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] - <-Map 16 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col0 - Select Operator [SEL_28] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_111] (rows=287989836 width=135) - predicate:(cs_sold_date_sk is not null and cs_bill_customer_sk is not null) - TableScan [TS_26] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] + Group By Operator [GBY_48] (rows=87116929 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_44] (rows=174233858 width=135) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_43] (rows=174233858 width=135) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_41] (rows=348467716 width=135) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_118] (rows=348467716 width=135) + Conds:RS_37._col1=RS_38._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=80000000 width=860) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_107] (rows=80000000 width=860) + predicate:c_customer_sk is not null + TableScan [TS_6] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_117] (rows=316788826 width=135) + Conds:RS_34._col0=RS_35._col0(Inner),Output:["_col1","_col3"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=8116 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_106] (rows=8116 width=1119) + predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] + <-Map 16 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col0 + Select Operator [SEL_27] (rows=287989836 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_108] (rows=287989836 width=135) + predicate:(cs_sold_date_sk is not null and cs_bill_customer_sk is not null) + TableScan [TS_25] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] <-Reducer 14 [CONTAINS] - Reduce Output Operator [RS_82] + Reduce Output Operator [RS_79] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_81] (rows=304916424 width=108) + Group By Operator [GBY_78] (rows=304916424 width=108) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_77] (rows=43560808 width=135) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_71] (rows=87121617 width=135) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_70] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_69] (rows=174243235 width=135) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_123] (rows=174243235 width=135) - Conds:RS_65._col1=RS_66._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_66] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_8] - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_65] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_122] (rows=158402938 width=135) - Conds:RS_62._col0=RS_63._col0(Inner),Output:["_col1","_col3"] - <-Map 8 [SIMPLE_EDGE] - SHUFFLE [RS_63] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_5] - <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_62] - PartitionCols:_col0 - Select Operator [SEL_55] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_114] (rows=144002668 width=135) - predicate:(ws_sold_date_sk is not null and ws_bill_customer_sk is not null) - TableScan [TS_53] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + Group By Operator [GBY_74] (rows=43560808 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_70] (rows=87121617 width=135) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_69] (rows=87121617 width=135) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 13 [SIMPLE_EDGE] + SHUFFLE [RS_68] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_67] (rows=174243235 width=135) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_120] (rows=174243235 width=135) + Conds:RS_63._col1=RS_64._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_64] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_8] + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_63] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_119] (rows=158402938 width=135) + Conds:RS_60._col0=RS_61._col0(Inner),Output:["_col1","_col3"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_61] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_60] + PartitionCols:_col0 + Select Operator [SEL_53] (rows=144002668 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_111] (rows=144002668 width=135) + predicate:(ws_sold_date_sk is not null and ws_bill_customer_sk is not null) + TableScan [TS_51] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 4 [CONTAINS] - Reduce Output Operator [RS_82] + Reduce Output Operator [RS_79] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_81] (rows=304916424 width=108) + Group By Operator [GBY_78] (rows=304916424 width=108) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(_col3)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_24] (rows=174238687 width=88) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_18] (rows=348477374 width=88) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_16] (rows=696954748 width=88) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_119] (rows=696954748 width=88) - Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_13] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_8] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_118] (rows=633595212 width=88) - Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col3"] - <-Map 8 [SIMPLE_EDGE] - SHUFFLE [RS_10] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_5] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_9] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=575995635 width=88) - Output:["_col0","_col1"] - Filter Operator [FIL_108] (rows=575995635 width=88) - predicate:(ss_sold_date_sk is not null and ss_customer_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] + Group By Operator [GBY_23] (rows=174238687 width=88) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_19] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_18] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_16] (rows=696954748 width=88) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_116] (rows=696954748 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_8] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_115] (rows=633595212 width=88) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col3"] + <-Map 8 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_105] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_customer_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] diff --git ql/src/test/results/clientpositive/perf/query72.q.out ql/src/test/results/clientpositive/perf/query72.q.out index e178d62..4d18fb3 100644 --- ql/src/test/results/clientpositive/perf/query72.q.out +++ ql/src/test/results/clientpositive/perf/query72.q.out @@ -86,17 +86,17 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4","_col5"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_72] - Group By Operator [GBY_70] (rows=37725837 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_69] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_68] (rows=75451675 width=135) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col3)","count(_col4)","count()"],keys:_col0, _col1, _col2 - Select Operator [SEL_66] (rows=75451675 width=135) - Output:["_col0","_col1","_col2","_col3","_col4"] + Select Operator [SEL_70] (rows=37725837 width=135) + Output:["_col0","_col1","_col2","_col5"] + Group By Operator [GBY_69] (rows=37725837 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_68] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_67] (rows=75451675 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col17, _col15, _col24 Merge Join Operator [MERGEJOIN_142] (rows=75451675 width=135) - Conds:RS_63._col0, _col1=RS_64._col4, _col6(Right Outer),Output:["_col15","_col17","_col24","_col30"] + Conds:RS_63._col0, _col1=RS_64._col4, _col6(Right Outer),Output:["_col15","_col17","_col24"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_63] PartitionCols:_col0, _col1 @@ -110,11 +110,11 @@ Stage-0 SHUFFLE [RS_64] PartitionCols:_col4, _col6 Select Operator [SEL_62] (rows=68592431 width=135) - Output:["_col4","_col6","_col13","_col15","_col22","_col28"] + Output:["_col4","_col6","_col13","_col15","_col22"] Filter Operator [FIL_61] (rows=68592431 width=135) predicate:(UDFToDouble(_col28) > (UDFToDouble(_col17) + 5.0)) Merge Join Operator [MERGEJOIN_141] (rows=205777295 width=135) - Conds:RS_58._col9=RS_59._col0(Inner),Output:["_col5","_col7","_col12","_col14","_col17","_col18","_col24","_col28"] + Conds:RS_58._col9=RS_59._col0(Inner),Output:["_col5","_col7","_col12","_col14","_col17","_col18","_col28"] <-Map 23 [SIMPLE_EDGE] SHUFFLE [RS_59] PartitionCols:_col0 @@ -128,7 +128,7 @@ Stage-0 SHUFFLE [RS_58] PartitionCols:_col9 Merge Join Operator [MERGEJOIN_140] (rows=187070265 width=135) - Conds:RS_55._col0, _col18=RS_56._col0, _col1(Inner),Output:["_col5","_col7","_col9","_col12","_col14","_col17","_col18","_col24"] + Conds:RS_55._col0, _col18=RS_56._col0, _col1(Inner),Output:["_col5","_col7","_col9","_col12","_col14","_col17","_col18"] <-Map 22 [SIMPLE_EDGE] SHUFFLE [RS_56] PartitionCols:_col0, _col1 @@ -144,14 +144,14 @@ Stage-0 Filter Operator [FIL_54] (rows=170063874 width=135) predicate:(_col3 < _col15) Merge Join Operator [MERGEJOIN_139] (rows=510191624 width=135) - Conds:RS_51._col1=RS_52._col6(Inner),Output:["_col0","_col3","_col5","_col7","_col9","_col12","_col14","_col15","_col17","_col18","_col24"] + Conds:RS_51._col1=RS_52._col6(Inner),Output:["_col0","_col3","_col5","_col7","_col9","_col12","_col14","_col15","_col17","_col18"] <-Reducer 16 [SIMPLE_EDGE] SHUFFLE [RS_52] PartitionCols:_col6 Select Operator [SEL_41] (rows=463810558 width=135) - Output:["_col1","_col3","_col6","_col8","_col9","_col11","_col12","_col18"] + Output:["_col1","_col3","_col6","_col8","_col9","_col11","_col12"] Merge Join Operator [MERGEJOIN_138] (rows=463810558 width=135) - Conds:RS_38._col4=RS_39._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16","_col18"] + Conds:RS_38._col4=RS_39._col0(Inner),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col18"] <-Map 21 [SIMPLE_EDGE] SHUFFLE [RS_39] PartitionCols:_col0 @@ -165,7 +165,7 @@ Stage-0 SHUFFLE [RS_38] PartitionCols:_col4 Merge Join Operator [MERGEJOIN_137] (rows=421645953 width=135) - Conds:RS_35._col5=RS_36._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10","_col16"] + Conds:RS_35._col5=RS_36._col0(Left Outer),Output:["_col1","_col4","_col6","_col7","_col9","_col10"] <-Map 20 [SIMPLE_EDGE] SHUFFLE [RS_36] PartitionCols:_col0 diff --git ql/src/test/results/clientpositive/perf/query8.q.out ql/src/test/results/clientpositive/perf/query8.q.out index bab0a80..f170883 100644 --- ql/src/test/results/clientpositive/perf/query8.q.out +++ ql/src/test/results/clientpositive/perf/query8.q.out @@ -282,7 +282,7 @@ Stage-0 SHUFFLE [RS_31] PartitionCols:_col0 Group By Operator [GBY_30] (rows=7333333 width=1014) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 Select Operator [SEL_28] (rows=7333333 width=1014) Output:["_col0"] Filter Operator [FIL_27] (rows=7333333 width=1014) @@ -325,7 +325,7 @@ Stage-0 SHUFFLE [RS_11] PartitionCols:_col0 Group By Operator [GBY_10] (rows=20000000 width=1014) - Output:["_col0","_col1"],aggregations:["count(1)"],keys:_col0 + Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 Select Operator [SEL_8] (rows=20000000 width=1014) Output:["_col0"] Filter Operator [FIL_81] (rows=20000000 width=1014) diff --git ql/src/test/results/clientpositive/perf/query87.q.out ql/src/test/results/clientpositive/perf/query87.q.out index 88dc197..a64d384 100644 --- ql/src/test/results/clientpositive/perf/query87.q.out +++ ql/src/test/results/clientpositive/perf/query87.q.out @@ -83,51 +83,53 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 Select Operator [SEL_92] (rows=54450625 width=129) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_90] (rows=43560808 width=135) + Select Operator [SEL_89] (rows=43560808 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_89] (rows=43560808 width=135) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_83] (rows=87121617 width=135) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 15 [SIMPLE_EDGE] - SHUFFLE [RS_82] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_81] (rows=174243235 width=135) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_135] (rows=174243235 width=135) - Conds:RS_77._col1=RS_78._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_78] - PartitionCols:_col0 - Select Operator [SEL_8] (rows=80000000 width=860) - Output:["_col0","_col1","_col2"] - Filter Operator [FIL_122] (rows=80000000 width=860) - predicate:c_customer_sk is not null - TableScan [TS_6] (rows=80000000 width=860) - default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] - <-Reducer 14 [SIMPLE_EDGE] - SHUFFLE [RS_77] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_134] (rows=158402938 width=135) - Conds:RS_74._col0=RS_75._col0(Inner),Output:["_col1","_col3"] - <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_75] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=8116 width=1119) - Output:["_col0","_col1"] - Filter Operator [FIL_121] (rows=8116 width=1119) - predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) - TableScan [TS_3] (rows=73049 width=1119) - default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] - <-Map 19 [SIMPLE_EDGE] - SHUFFLE [RS_74] - PartitionCols:_col0 - Select Operator [SEL_67] (rows=144002668 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_126] (rows=144002668 width=135) - predicate:(ws_sold_date_sk is not null and ws_bill_customer_sk is not null) - TableScan [TS_65] (rows=144002668 width=135) - default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] + Group By Operator [GBY_88] (rows=43560808 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_84] (rows=87121617 width=135) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_83] (rows=87121617 width=135) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 15 [SIMPLE_EDGE] + SHUFFLE [RS_82] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_81] (rows=174243235 width=135) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_135] (rows=174243235 width=135) + Conds:RS_77._col1=RS_78._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_78] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=80000000 width=860) + Output:["_col0","_col1","_col2"] + Filter Operator [FIL_122] (rows=80000000 width=860) + predicate:c_customer_sk is not null + TableScan [TS_6] (rows=80000000 width=860) + default@customer,customer,Tbl:COMPLETE,Col:NONE,Output:["c_customer_sk","c_first_name","c_last_name"] + <-Reducer 14 [SIMPLE_EDGE] + SHUFFLE [RS_77] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_134] (rows=158402938 width=135) + Conds:RS_74._col0=RS_75._col0(Inner),Output:["_col1","_col3"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_75] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=8116 width=1119) + Output:["_col0","_col1"] + Filter Operator [FIL_121] (rows=8116 width=1119) + predicate:(d_month_seq BETWEEN 1212 AND 1223 and d_date_sk is not null) + TableScan [TS_3] (rows=73049 width=1119) + default@date_dim,date_dim,Tbl:COMPLETE,Col:NONE,Output:["d_date_sk","d_date","d_month_seq"] + <-Map 19 [SIMPLE_EDGE] + SHUFFLE [RS_74] + PartitionCols:_col0 + Select Operator [SEL_67] (rows=144002668 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_126] (rows=144002668 width=135) + predicate:(ws_sold_date_sk is not null and ws_bill_customer_sk is not null) + TableScan [TS_65] (rows=144002668 width=135) + default@web_sales,web_sales,Tbl:COMPLETE,Col:NONE,Output:["ws_sold_date_sk","ws_bill_customer_sk"] <-Reducer 6 [CONTAINS] Reduce Output Operator [RS_95] PartitionCols:_col0, _col1, _col2 @@ -138,7 +140,7 @@ Stage-0 Select Operator [SEL_64] (rows=10889817 width=103) Output:["_col0","_col1","_col2","_col3","_col4"] Group By Operator [GBY_63] (rows=10889817 width=103) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(2)"],keys:_col0, _col1, _col2 + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col0, _col1, _col2 Select Operator [SEL_59] (rows=21779634 width=103) Output:["_col0","_col1","_col2"] Filter Operator [FIL_58] (rows=21779634 width=103) @@ -153,41 +155,43 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 Select Operator [SEL_53] (rows=261355616 width=103) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_51] (rows=87116929 width=135) + Select Operator [SEL_50] (rows=87116929 width=135) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_50] (rows=87116929 width=135) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(1)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_44] (rows=174233858 width=135) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 12 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_42] (rows=348467716 width=135) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_133] (rows=348467716 width=135) - Conds:RS_38._col1=RS_39._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_39] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_8] - <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_38] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_132] (rows=316788826 width=135) - Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col3"] - <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_5] - <-Map 18 [SIMPLE_EDGE] - SHUFFLE [RS_35] - PartitionCols:_col0 - Select Operator [SEL_28] (rows=287989836 width=135) - Output:["_col0","_col1"] - Filter Operator [FIL_123] (rows=287989836 width=135) - predicate:(cs_sold_date_sk is not null and cs_bill_customer_sk is not null) - TableScan [TS_26] (rows=287989836 width=135) - default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] + Group By Operator [GBY_49] (rows=87116929 width=135) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_45] (rows=174233858 width=135) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_44] (rows=174233858 width=135) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 12 [SIMPLE_EDGE] + SHUFFLE [RS_43] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_42] (rows=348467716 width=135) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_133] (rows=348467716 width=135) + Conds:RS_38._col1=RS_39._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_39] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_8] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_132] (rows=316788826 width=135) + Conds:RS_35._col0=RS_36._col0(Inner),Output:["_col1","_col3"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_36] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Map 18 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col0 + Select Operator [SEL_28] (rows=287989836 width=135) + Output:["_col0","_col1"] + Filter Operator [FIL_123] (rows=287989836 width=135) + predicate:(cs_sold_date_sk is not null and cs_bill_customer_sk is not null) + TableScan [TS_26] (rows=287989836 width=135) + default@catalog_sales,catalog_sales,Tbl:COMPLETE,Col:NONE,Output:["cs_sold_date_sk","cs_bill_customer_sk"] <-Reducer 4 [CONTAINS] Reduce Output Operator [RS_56] PartitionCols:_col0, _col1, _col2 @@ -195,39 +199,41 @@ Stage-0 Output:["_col0","_col1","_col2","_col3","_col4"],aggregations:["sum(_col3)","sum(_col4)"],keys:_col0, _col1, _col2 Select Operator [SEL_53] (rows=261355616 width=103) Output:["_col0","_col1","_col2","_col3","_col4"] - Select Operator [SEL_25] (rows=174238687 width=88) + Select Operator [SEL_24] (rows=174238687 width=88) Output:["_col0","_col1","_col2","_col3","_col4"] - Group By Operator [GBY_24] (rows=174238687 width=88) - Output:["_col0","_col1","_col2","_col3"],aggregations:["count(2)"],keys:_col0, _col1, _col2 - Group By Operator [GBY_18] (rows=348477374 width=88) - Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_17] - PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_16] (rows=696954748 width=88) - Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 - Merge Join Operator [MERGEJOIN_131] (rows=696954748 width=88) - Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col3","_col6","_col7"] - <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_13] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_8] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_12] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_130] (rows=633595212 width=88) - Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col3"] - <-Map 10 [SIMPLE_EDGE] - SHUFFLE [RS_10] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_5] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_9] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=575995635 width=88) - Output:["_col0","_col1"] - Filter Operator [FIL_120] (rows=575995635 width=88) - predicate:(ss_sold_date_sk is not null and ss_customer_sk is not null) - TableScan [TS_0] (rows=575995635 width=88) - default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] + Group By Operator [GBY_23] (rows=174238687 width=88) + Output:["_col0","_col1","_col2","_col3"],aggregations:["count()"],keys:_col1, _col0, _col2 + Select Operator [SEL_19] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"] + Group By Operator [GBY_18] (rows=348477374 width=88) + Output:["_col0","_col1","_col2"],keys:KEY._col0, KEY._col1, KEY._col2 + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_17] + PartitionCols:_col0, _col1, _col2 + Group By Operator [GBY_16] (rows=696954748 width=88) + Output:["_col0","_col1","_col2"],keys:_col7, _col6, _col3 + Merge Join Operator [MERGEJOIN_131] (rows=696954748 width=88) + Conds:RS_12._col1=RS_13._col0(Inner),Output:["_col3","_col6","_col7"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_13] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_8] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_12] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_130] (rows=633595212 width=88) + Conds:RS_9._col0=RS_10._col0(Inner),Output:["_col1","_col3"] + <-Map 10 [SIMPLE_EDGE] + SHUFFLE [RS_10] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_9] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=575995635 width=88) + Output:["_col0","_col1"] + Filter Operator [FIL_120] (rows=575995635 width=88) + predicate:(ss_sold_date_sk is not null and ss_customer_sk is not null) + TableScan [TS_0] (rows=575995635 width=88) + default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_sold_date_sk","ss_customer_sk"] diff --git ql/src/test/results/clientpositive/plan_json.q.out ql/src/test/results/clientpositive/plan_json.q.out index ba6d0be..ac9fdec 100644 --- ql/src/test/results/clientpositive/plan_json.q.out +++ ql/src/test/results/clientpositive/plan_json.q.out @@ -2,4 +2,4 @@ PREHOOK: query: EXPLAIN FORMATTED SELECT count(1) FROM src PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN FORMATTED SELECT count(1) FROM src POSTHOOK: type: QUERY -{"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_8"}}}}}} +{"STAGE DEPENDENCIES":{"Stage-0":{"ROOT STAGE":"TRUE"}},"STAGE PLANS":{"Stage-0":{"Fetch Operator":{"limit:":"1","Processor Tree:":{"ListSink":{"OperatorId:":"LIST_SINK_7"}}}}}} diff --git ql/src/test/results/clientpositive/ppd_gby_join.q.out ql/src/test/results/clientpositive/ppd_gby_join.q.out index a160410..ed91def 100644 --- ql/src/test/results/clientpositive/ppd_gby_join.q.out +++ ql/src/test/results/clientpositive/ppd_gby_join.q.out @@ -74,7 +74,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -344,7 +344,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/setop_subq.q.out ql/src/test/results/clientpositive/setop_subq.q.out index 418fdfd..ac20c4c 100644 --- ql/src/test/results/clientpositive/setop_subq.q.out +++ ql/src/test/results/clientpositive/setop_subq.q.out @@ -87,11 +87,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -178,11 +178,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -231,11 +231,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -322,11 +322,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -375,11 +375,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -466,11 +466,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out index a194536..ad9e08a 100644 --- ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out +++ ql/src/test/results/clientpositive/skewjoin_mapjoin1.q.out @@ -325,14 +325,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a + $hdt$_0:a Fetch Operator limit: -1 subquery1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a + $hdt$_0:a TableScan alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -386,7 +386,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -414,7 +414,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -470,14 +470,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a + $hdt$_0:a Fetch Operator limit: -1 subquery1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a + $hdt$_0:a TableScan alias: a Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -531,7 +531,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -559,7 +559,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out index 474d527..de65931 100644 --- ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out +++ ql/src/test/results/clientpositive/skewjoin_mapjoin10.q.out @@ -357,14 +357,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a + $hdt$_0:a Fetch Operator limit: -1 subquery1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a + $hdt$_0:a TableScan alias: a Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -418,7 +418,7 @@ STAGE PLANS: Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -446,7 +446,7 @@ STAGE PLANS: Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -502,14 +502,14 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a + $hdt$_0:a Fetch Operator limit: -1 subquery1:a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a + $hdt$_0:a TableScan alias: a Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -563,7 +563,7 @@ STAGE PLANS: Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -591,7 +591,7 @@ STAGE PLANS: Union Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out index 663eb12..56196df 100644 --- ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out +++ ql/src/test/results/clientpositive/skewjoin_mapjoin5.q.out @@ -211,22 +211,18 @@ STAGE PLANS: Filter Operator 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) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/skewjoinopt1.q.out ql/src/test/results/clientpositive/skewjoinopt1.q.out index 053653b..82d4cbc 100644 --- ql/src/test/results/clientpositive/skewjoinopt1.q.out +++ ql/src/test/results/clientpositive/skewjoinopt1.q.out @@ -424,7 +424,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -436,7 +436,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -588,7 +588,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -600,7 +600,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/skewjoinopt2.q.out ql/src/test/results/clientpositive/skewjoinopt2.q.out index 54b2228..1b52ca7 100644 --- ql/src/test/results/clientpositive/skewjoinopt2.q.out +++ ql/src/test/results/clientpositive/skewjoinopt2.q.out @@ -413,7 +413,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -428,7 +428,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -587,7 +587,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -602,7 +602,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/skewjoinopt9.q.out ql/src/test/results/clientpositive/skewjoinopt9.q.out index 2af317e..7b77322 100644 --- ql/src/test/results/clientpositive/skewjoinopt9.q.out +++ ql/src/test/results/clientpositive/skewjoinopt9.q.out @@ -198,22 +198,18 @@ STAGE PLANS: Filter Operator 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) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/spark/auto_join26.q.out ql/src/test/results/clientpositive/spark/auto_join26.q.out index a0deaab..bfb3564 100644 --- ql/src/test/results/clientpositive/spark/auto_join26.q.out +++ ql/src/test/results/clientpositive/spark/auto_join26.q.out @@ -73,7 +73,7 @@ STAGE PLANS: 0 Map 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -132,7 +132,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ] POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/spark/auto_join27.q.out ql/src/test/results/clientpositive/spark/auto_join27.q.out index 8e85e3d..e49335e 100644 --- ql/src/test/results/clientpositive/spark/auto_join27.q.out +++ ql/src/test/results/clientpositive/spark/auto_join27.q.out @@ -97,7 +97,7 @@ STAGE PLANS: 1 _col0 (type: string) Statistics: Num rows: 273 Data size: 2908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/count.q.out ql/src/test/results/clientpositive/spark/count.q.out index eac2edd..8df0d68 100644 --- ql/src/test/results/clientpositive/spark/count.q.out +++ ql/src/test/results/clientpositive/spark/count.q.out @@ -121,33 +121,37 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -250,26 +254,30 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -308,33 +316,37 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: $f1, $f2, $f3, $f4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count($f1), count($f2), count($f3), count($f4), count(DISTINCT $f1), count(DISTINCT $f2), count(DISTINCT $f3), count(DISTINCT $f4), count(DISTINCT $f1, $f2), count(DISTINCT $f2, $f3), count(DISTINCT $f3, $f4), count(DISTINCT $f1, $f4), count(DISTINCT $f1, $f3), count(DISTINCT $f2, $f4), count(DISTINCT $f1, $f2, $f3), count(DISTINCT $f2, $f3, $f4), count(DISTINCT $f1, $f3, $f4), count(DISTINCT $f1, $f2, $f4), count(DISTINCT $f1, $f2, $f3, $f4) - keys: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: mergepartial - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint) + outputColumnNames: $f0, $f00, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 320 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -817,26 +829,30 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: $f1, $f2, $f3, $f4 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: $f1 (type: int), $f2 (type: int), $f3 (type: int), $f4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) mode: complete - outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19, $f20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: $f0, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: $f0 (type: bigint), $f0 (type: bigint), $f1 (type: bigint), $f2 (type: bigint), $f3 (type: bigint), $f4 (type: bigint), $f5 (type: bigint), $f6 (type: bigint), $f7 (type: bigint), $f8 (type: bigint), $f9 (type: bigint), $f10 (type: bigint), $f11 (type: bigint), $f12 (type: bigint), $f13 (type: bigint), $f14 (type: bigint), $f15 (type: bigint), $f16 (type: bigint), $f17 (type: bigint), $f18 (type: bigint), $f19 (type: bigint) + outputColumnNames: $f0, $f00, $f1, $f2, $f3, $f4, $f5, $f6, $f7, $f8, $f9, $f10, $f11, $f12, $f13, $f14, $f15, $f16, $f17, $f18, $f19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator 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 38ea9bd..c5ccb2f 100644 --- ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out +++ ql/src/test/results/clientpositive/spark/dynamic_rdd_cache.q.out @@ -353,7 +353,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -369,7 +369,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -385,7 +385,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -531,7 +531,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -565,7 +565,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/spark/groupby4_map.q.out ql/src/test/results/clientpositive/spark/groupby4_map.q.out index 39536bb..7cb3600 100644 --- ql/src/test/results/clientpositive/spark/groupby4_map.q.out +++ ql/src/test/results/clientpositive/spark/groupby4_map.q.out @@ -32,7 +32,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -81,7 +81,7 @@ POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.key EXPRESSION [] +POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.null, ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out index 535e770..ef287ad 100644 --- ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out +++ ql/src/test/results/clientpositive/spark/groupby4_map_skew.q.out @@ -32,7 +32,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -81,7 +81,7 @@ POSTHOOK: query: FROM src INSERT OVERWRITE TABLE dest1 SELECT count(1) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 -POSTHOOK: Lineage: dest1.key EXPRESSION [] +POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.null, ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/spark/groupby_cube1.q.out ql/src/test/results/clientpositive/spark/groupby_cube1.q.out index cace096..52c87ef 100644 --- ql/src/test/results/clientpositive/spark/groupby_cube1.q.out +++ ql/src/test/results/clientpositive/spark/groupby_cube1.q.out @@ -38,11 +38,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -103,11 +103,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE @@ -197,7 +197,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 @@ -363,11 +363,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 4 Data size: 120 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/groupby_position.q.out ql/src/test/results/clientpositive/spark/groupby_position.q.out index 49eb3ed..163c5ab 100644 --- ql/src/test/results/clientpositive/spark/groupby_position.q.out +++ ql/src/test/results/clientpositive/spark/groupby_position.q.out @@ -426,22 +426,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <= 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out index 6d087b2..68670ab 100644 --- ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out +++ ql/src/test/results/clientpositive/spark/groupby_rollup1.q.out @@ -38,11 +38,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE @@ -202,11 +202,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + aggregations: count() + keys: key (type: string), val (type: string), 0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 90 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out index e2c1a91..8292e3a 100644 --- ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out +++ ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out @@ -60,11 +60,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -158,7 +158,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -253,11 +253,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -324,7 +324,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -456,11 +456,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -554,7 +554,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -639,11 +639,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -737,7 +737,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -830,11 +830,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -928,7 +928,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -1024,11 +1024,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1095,7 +1095,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1233,7 +1233,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -1438,11 +1438,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1519,7 +1519,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1661,11 +1661,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1759,7 +1759,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] Map 2 Map Operator Tree: TableScan @@ -1768,11 +1768,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1866,7 +1866,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery2:$hdt$_0-subquery2:t1] Stage: Stage-0 Move Operator @@ -1974,11 +1974,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2072,7 +2072,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] Map 2 Map Operator Tree: TableScan @@ -2084,7 +2084,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 @@ -2311,25 +2311,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2384,7 +2380,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Map 3 Map Operator Tree: TableScan @@ -2395,25 +2391,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2468,7 +2460,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -2618,25 +2610,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2691,7 +2679,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Map 3 Map Operator Tree: TableScan @@ -2702,25 +2690,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2775,7 +2759,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -2882,12 +2866,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -2954,7 +2938,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -3084,11 +3068,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3182,7 +3166,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3278,11 +3262,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3376,7 +3360,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3471,11 +3455,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3569,7 +3553,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3671,11 +3655,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3769,7 +3753,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out index 6745d7e..4284726 100644 --- ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out +++ ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out @@ -60,11 +60,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -158,7 +158,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -254,11 +254,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -325,7 +325,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -475,11 +475,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -573,7 +573,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -658,11 +658,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -756,7 +756,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -849,11 +849,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col1 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -947,7 +947,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Stage: Stage-0 Move Operator @@ -1044,11 +1044,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -1115,7 +1115,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:t1] + /t1 [t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1272,7 +1272,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -1496,11 +1496,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1577,7 +1577,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -1737,11 +1737,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1835,7 +1835,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] Map 2 Map Operator Tree: TableScan @@ -1844,11 +1844,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1942,7 +1942,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1] + /t1 [null-subquery2:$hdt$_0-subquery2:t1] Stage: Stage-0 Move Operator @@ -2051,11 +2051,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: final outputColumnNames: _col0, _col1 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -2149,7 +2149,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1] + /t1 [null-subquery1:$hdt$_0-subquery1:t1] Map 2 Map Operator Tree: TableScan @@ -2161,7 +2161,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1 @@ -2406,25 +2406,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2479,7 +2475,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Map 3 Map Operator Tree: TableScan @@ -2490,25 +2486,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2563,7 +2555,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -2714,25 +2706,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: final - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: final + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: 0 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2787,7 +2775,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_0:$hdt$_0:t1] + /t1 [$hdt$_0:t1] Map 3 Map Operator Tree: TableScan @@ -2798,25 +2786,21 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: key (type: string), val (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: rand() (type: double) Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col2 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col2 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2871,7 +2855,7 @@ STAGE PLANS: name: default.t1 name: default.t1 Truncated Path -> Alias: - /t1 [$hdt$_1:$hdt$_1:t1] + /t1 [$hdt$_1:t1] Reducer 2 Needs Tagging: true Reduce Operator Tree: @@ -2997,12 +2981,12 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() bucketGroup: true - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -3069,7 +3053,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Reducer 2 Needs Tagging: false Reduce Operator Tree: @@ -3217,11 +3201,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3315,7 +3299,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3411,11 +3395,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col2 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3509,7 +3493,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3604,11 +3588,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3702,7 +3686,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator @@ -3804,11 +3788,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: key (type: string), val (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, val Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), val (type: string) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -3902,7 +3886,7 @@ STAGE PLANS: name: default.t2 name: default.t2 Truncated Path -> Alias: - /t2 [$hdt$_0:t2] + /t2 [t2] Stage: Stage-0 Move Operator diff --git ql/src/test/results/clientpositive/spark/join29.q.out ql/src/test/results/clientpositive/spark/join29.q.out index 573628f..88929fe 100644 --- ql/src/test/results/clientpositive/spark/join29.q.out +++ ql/src/test/results/clientpositive/spark/join29.q.out @@ -39,22 +39,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Local Work: Map Reduce Local Work @@ -84,22 +80,18 @@ STAGE PLANS: Filter Operator 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 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reducer 4 Local Work: Map Reduce Local Work diff --git ql/src/test/results/clientpositive/spark/join30.q.out ql/src/test/results/clientpositive/spark/join30.q.out index 3584f8c..23650ff 100644 --- ql/src/test/results/clientpositive/spark/join30.q.out +++ ql/src/test/results/clientpositive/spark/join30.q.out @@ -73,7 +73,7 @@ STAGE PLANS: 0 Map 1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -132,7 +132,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 -POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, ] +POSTHOOK: Lineage: dest_j1.cnt EXPRESSION [(src1)x.null, (src)y.null, ] POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY diff --git ql/src/test/results/clientpositive/spark/join31.q.out ql/src/test/results/clientpositive/spark/join31.q.out index 3fee7b8..4edb4ef 100644 --- ql/src/test/results/clientpositive/spark/join31.q.out +++ ql/src/test/results/clientpositive/spark/join31.q.out @@ -100,7 +100,7 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/join35.q.out ql/src/test/results/clientpositive/spark/join35.q.out index 74e8ee9..54f68af 100644 --- ql/src/test/results/clientpositive/spark/join35.q.out +++ ql/src/test/results/clientpositive/spark/join35.q.out @@ -50,25 +50,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + 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) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -119,7 +115,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:x] + /src [$hdt$_0-subquery1:$hdt$_0-subquery1:x] Map 4 Map Operator Tree: TableScan @@ -130,25 +126,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -199,7 +191,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0-subquery2:$hdt$_0-subquery2:$hdt$_0:x1] + /src [$hdt$_0-subquery2:$hdt$_0-subquery2:x1] Map 6 Map Operator Tree: TableScan diff --git ql/src/test/results/clientpositive/spark/join38.q.out ql/src/test/results/clientpositive/spark/join38.q.out index 7e4b790..f4f31c0 100644 --- ql/src/test/results/clientpositive/spark/join38.q.out +++ ql/src/test/results/clientpositive/spark/join38.q.out @@ -105,22 +105,18 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count() + keys: _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: bigint) + value expressions: _col2 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 diff --git ql/src/test/results/clientpositive/spark/limit_pushdown.q.out ql/src/test/results/clientpositive/spark/limit_pushdown.q.out index 19c1e5f..ac74eaf 100644 --- ql/src/test/results/clientpositive/spark/limit_pushdown.q.out +++ ql/src/test/results/clientpositive/spark/limit_pushdown.q.out @@ -879,11 +879,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -901,11 +901,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/merge1.q.out ql/src/test/results/clientpositive/spark/merge1.q.out index d5b1e9f..8e671e9 100644 --- ql/src/test/results/clientpositive/spark/merge1.q.out +++ ql/src/test/results/clientpositive/spark/merge1.q.out @@ -38,11 +38,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/merge2.q.out ql/src/test/results/clientpositive/spark/merge2.q.out index d780dc2..24116cb 100644 --- ql/src/test/results/clientpositive/spark/merge2.q.out +++ ql/src/test/results/clientpositive/spark/merge2.q.out @@ -38,11 +38,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out index 79fc6ae..2891c7d 100644 --- ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out +++ ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out @@ -203,28 +203,32 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -259,28 +263,32 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col0 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -315,28 +323,28 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9999 Data size: 1030908 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -375,28 +383,28 @@ STAGE PLANS: outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), sum(1), sum(0.2), count(1), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) + aggregations: count(), sum(1), sum(0.2), count(_col2), count(_col3), count(_col4), count(_col5), max(_col6), min(_col7) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(11,1)), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), count(VALUE._col7), max(VALUE._col8), min(VALUE._col9) + aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(VALUE._col6), max(VALUE._col7), min(VALUE._col8) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col3 (type: bigint), _col4 (type: bigint), 7 (type: decimal(2,0)), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: int), _col9 (type: bigint) + expressions: _col0 (type: bigint), '1' (type: string), _col1 (type: bigint), _col2 (type: decimal(11,1)), 2 (type: int), _col0 (type: bigint), _col3 (type: bigint), 7 (type: decimal(2,0)), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: int), _col8 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git ql/src/test/results/clientpositive/spark/nullgroup.q.out ql/src/test/results/clientpositive/spark/nullgroup.q.out index 1c2ae5c..aa99ae3 100644 --- ql/src/test/results/clientpositive/spark/nullgroup.q.out +++ ql/src/test/results/clientpositive/spark/nullgroup.q.out @@ -26,7 +26,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -92,7 +92,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -165,7 +165,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() mode: partial1 outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -236,7 +236,7 @@ STAGE PLANS: Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() mode: complete outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/nullgroup2.q.out ql/src/test/results/clientpositive/spark/nullgroup2.q.out index 8fcea35..1c6c505 100644 --- ql/src/test/results/clientpositive/spark/nullgroup2.q.out +++ ql/src/test/results/clientpositive/spark/nullgroup2.q.out @@ -24,22 +24,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) 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: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator @@ -109,22 +105,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator @@ -181,19 +173,15 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: rand() (type: double) 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: rand() (type: double) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0, _col1 @@ -259,19 +247,15 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 9999.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (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 Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1) + aggregations: count() keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/nullgroup4.q.out ql/src/test/results/clientpositive/spark/nullgroup4.q.out index 63afe9b..061bd1b 100644 --- ql/src/test/results/clientpositive/spark/nullgroup4.q.out +++ ql/src/test/results/clientpositive/spark/nullgroup4.q.out @@ -26,11 +26,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1) - keys: _col1 (type: string) + aggregations: count(), count(DISTINCT value) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -109,11 +109,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col1 (type: string) + aggregations: count() + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -198,17 +198,17 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: partial1 outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -273,16 +273,16 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col1 + outputColumnNames: value Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: value (type: string) sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0) mode: complete outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/nullgroup4_multi_distinct.q.out ql/src/test/results/clientpositive/spark/nullgroup4_multi_distinct.q.out index 3b46ce8..7f5bfaa 100644 --- ql/src/test/results/clientpositive/spark/nullgroup4_multi_distinct.q.out +++ ql/src/test/results/clientpositive/spark/nullgroup4_multi_distinct.q.out @@ -25,11 +25,11 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col1 (type: string), _col2 (type: string) + aggregations: count(), count(DISTINCT _col0), count(DISTINCT _col1) + keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE @@ -95,16 +95,16 @@ STAGE PLANS: Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), substr(value, 5) (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator - aggregations: count(1), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) + aggregations: count(), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0) mode: complete outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE 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 1610847..d01674e 100644 --- ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out +++ ql/src/test/results/clientpositive/spark/ppd_gby_join.q.out @@ -82,7 +82,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -350,7 +350,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 4 Data size: 46 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/skewjoinopt1.q.out ql/src/test/results/clientpositive/spark/skewjoinopt1.q.out index cae8702..ae6031e 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt1.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt1.q.out @@ -416,7 +416,7 @@ STAGE PLANS: Inner Join 0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -445,7 +445,7 @@ STAGE PLANS: Inner Join 0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -565,7 +565,7 @@ STAGE PLANS: Right Outer Join 0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -594,7 +594,7 @@ STAGE PLANS: Right Outer Join 0 to 1 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out index 43ed467..2e76cad 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out @@ -448,7 +448,7 @@ STAGE PLANS: Inner Join 0 to 1 Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -477,7 +477,7 @@ STAGE PLANS: Inner Join 0 to 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -597,7 +597,7 @@ STAGE PLANS: Right Outer Join 0 to 1 Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -626,7 +626,7 @@ STAGE PLANS: Right Outer Join 0 to 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out index 3c46e95..c1314b4 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out @@ -405,7 +405,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -439,7 +439,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -564,7 +564,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -598,7 +598,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out index ece2e1c..7619c88 100644 --- ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out +++ ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out @@ -191,22 +191,18 @@ STAGE PLANS: Filter Operator 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) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Map 4 Map Operator Tree: TableScan diff --git ql/src/test/results/clientpositive/spark/stats1.q.out ql/src/test/results/clientpositive/spark/stats1.q.out index e691f51..13690db 100644 --- ql/src/test/results/clientpositive/spark/stats1.q.out +++ ql/src/test/results/clientpositive/spark/stats1.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -117,7 +117,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT * FROM tmptable x SORT BY x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable 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 a4ceff6..9291c01 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 @@ -18,7 +18,7 @@ PREHOOK: query: SELECT key, count(1) FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -31,7 +31,7 @@ PREHOOK: query: SELECT key, val, count(1) FROM T1 GROUP BY key, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -45,7 +45,7 @@ PREHOOK: query: SELECT key, count(1) FROM (SELECT key, val FROM T1) subq1 GROUP PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -58,7 +58,7 @@ PREHOOK: query: SELECT k, count(1) FROM (SELECT key as k, val as v FROM T1) subq PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -71,7 +71,7 @@ PREHOOK: query: SELECT 1, key, count(1) FROM T1 GROUP BY 1, key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -84,7 +84,7 @@ PREHOOK: query: SELECT key, 1, val, count(1) FROM T1 GROUP BY key, 1, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -98,7 +98,7 @@ PREHOOK: query: SELECT key, 1, val, 2, count(1) FROM T1 GROUP BY key, 1, val, 2 PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -123,7 +123,7 @@ group by key + key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key @@ -140,11 +140,11 @@ SELECT key, count(1) as c FROM T1 GROUP BY key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key -Operator:GBY_10 +Operator:GBY_8 Table:default@t1 Keys:key @@ -166,11 +166,11 @@ ON subq1.key = subq2.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key @@ -188,11 +188,11 @@ ORDER BY subq1.key ASC, subq1.c ASC, subq2.key ASC, subq2.val ASC, subq2.c ASC PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key,val @@ -208,7 +208,7 @@ group by key, constant, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -231,7 +231,7 @@ GROUP BY key, constant3, val PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_3 +Operator:GBY_2 Table:default@t1 Keys:key,val @@ -566,11 +566,11 @@ ON subq1.key = subq2.key PREHOOK: type: QUERY PREHOOK: Input: default@t1 #### A masked pattern was here #### -Operator:GBY_4 +Operator:GBY_3 Table:default@t1 Keys:key -Operator:GBY_12 +Operator:GBY_10 Table:default@t1 Keys:key diff --git ql/src/test/results/clientpositive/spark/union10.q.out ql/src/test/results/clientpositive/spark/union10.q.out index 2b3afec..ea1bebb 100644 --- ql/src/test/results/clientpositive/spark/union10.q.out +++ ql/src/test/results/clientpositive/spark/union10.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -60,7 +60,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -76,7 +76,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -186,7 +186,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, (src)s3.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/spark/union11.q.out ql/src/test/results/clientpositive/spark/union11.q.out index ff8cca1..1cb355c 100644 --- ql/src/test/results/clientpositive/spark/union11.q.out +++ ql/src/test/results/clientpositive/spark/union11.q.out @@ -92,7 +92,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -130,7 +130,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -153,7 +153,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union12.q.out ql/src/test/results/clientpositive/spark/union12.q.out index e9cd26c..0639956 100644 --- ql/src/test/results/clientpositive/spark/union12.q.out +++ ql/src/test/results/clientpositive/spark/union12.q.out @@ -44,7 +44,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -60,7 +60,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -76,7 +76,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -190,7 +190,7 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.null, (srcbucket)s3.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/spark/union14.q.out ql/src/test/results/clientpositive/spark/union14.q.out index 0b99f68..d3ede70 100644 --- ql/src/test/results/clientpositive/spark/union14.q.out +++ ql/src/test/results/clientpositive/spark/union14.q.out @@ -32,7 +32,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -88,7 +88,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union15.q.out ql/src/test/results/clientpositive/spark/union15.q.out index 339bcbb..77ed543 100644 --- ql/src/test/results/clientpositive/spark/union15.q.out +++ ql/src/test/results/clientpositive/spark/union15.q.out @@ -52,7 +52,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -73,7 +73,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -96,7 +96,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union16.q.out ql/src/test/results/clientpositive/spark/union16.q.out index a150893..5a5838a 100644 --- ql/src/test/results/clientpositive/spark/union16.q.out +++ ql/src/test/results/clientpositive/spark/union16.q.out @@ -83,7 +83,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/spark/union17.q.out ql/src/test/results/clientpositive/spark/union17.q.out index bcb95e4..a967c07 100644 --- ql/src/test/results/clientpositive/spark/union17.q.out +++ ql/src/test/results/clientpositive/spark/union17.q.out @@ -53,7 +53,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -231,10 +231,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/spark/union18.q.out ql/src/test/results/clientpositive/spark/union18.q.out index dad2050..653c54c 100644 --- ql/src/test/results/clientpositive/spark/union18.q.out +++ ql/src/test/results/clientpositive/spark/union18.q.out @@ -50,7 +50,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -164,10 +164,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 SORT BY DEST1.key, DEST1.value PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/spark/union19.q.out ql/src/test/results/clientpositive/spark/union19.q.out index 31795b2..fe5902f 100644 --- ql/src/test/results/clientpositive/spark/union19.q.out +++ ql/src/test/results/clientpositive/spark/union19.q.out @@ -51,7 +51,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -193,10 +193,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 SORT BY DEST1.key, DEST1.value PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/spark/union2.q.out ql/src/test/results/clientpositive/spark/union2.q.out index f8ccc49..b0a6f5f 100644 --- ql/src/test/results/clientpositive/spark/union2.q.out +++ ql/src/test/results/clientpositive/spark/union2.q.out @@ -27,7 +27,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -45,7 +45,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/spark/union20.q.out ql/src/test/results/clientpositive/spark/union20.q.out index 2141861..bb77c42 100644 --- ql/src/test/results/clientpositive/spark/union20.q.out +++ ql/src/test/results/clientpositive/spark/union20.q.out @@ -41,7 +41,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -75,7 +75,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/spark/union24.q.out ql/src/test/results/clientpositive/spark/union24.q.out index 6f7e04f..a901f49 100644 --- ql/src/test/results/clientpositive/spark/union24.q.out +++ ql/src/test/results/clientpositive/spark/union24.q.out @@ -165,7 +165,7 @@ STAGE PLANS: name: default.src2 name: default.src2 Truncated Path -> Alias: - /src2 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1:src2] + /src2 [null-subquery1-subquery1-subquery1:$hdt$_2-subquery1-subquery1-subquery1:src2] Map 2 Map Operator Tree: TableScan @@ -252,7 +252,7 @@ STAGE PLANS: name: default.src3 name: default.src3 Truncated Path -> Alias: - /src3 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src3] + /src3 [null-subquery1-subquery1-subquery2:$hdt$_2-subquery1-subquery1-subquery2:src3] Map 3 Map Operator Tree: TableScan @@ -339,7 +339,7 @@ STAGE PLANS: name: default.src4 name: default.src4 Truncated Path -> Alias: - /src4 [null-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src4] + /src4 [null-subquery1-subquery2:$hdt$_2-subquery1-subquery2:src4] Map 4 Map Operator Tree: TableScan @@ -350,25 +350,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -419,7 +415,7 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src5 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:src5] + /src5 [null-subquery2:$hdt$_2-subquery2:src5] Reducer 5 Needs Tagging: false Reduce Operator Tree: @@ -627,7 +623,7 @@ STAGE PLANS: name: default.src2 name: default.src2 Truncated Path -> Alias: - /src2 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1:src2] + /src2 [null-subquery1-subquery1:$hdt$_1-subquery1-subquery1:src2] Map 2 Map Operator Tree: TableScan @@ -714,7 +710,7 @@ STAGE PLANS: name: default.src3 name: default.src3 Truncated Path -> Alias: - /src3 [null-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src3] + /src3 [null-subquery1-subquery2:$hdt$_1-subquery1-subquery2:src3] Map 3 Map Operator Tree: TableScan @@ -787,7 +783,7 @@ STAGE PLANS: name: default.src4 name: default.src4 Truncated Path -> Alias: - /src4 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:a] + /src4 [null-subquery2:$hdt$_1-subquery2:$hdt$_1:a] Map 5 Map Operator Tree: TableScan @@ -861,7 +857,7 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src5 [null-subquery2:$hdt$_0-subquery2:$hdt$_1:b] + /src5 [null-subquery2:$hdt$_1-subquery2:$hdt$_2:b] Reducer 4 Needs Tagging: true Reduce Operator Tree: @@ -1063,7 +1059,7 @@ STAGE PLANS: name: default.src2 name: default.src2 Truncated Path -> Alias: - /src2 [null-subquery1:$hdt$_0-subquery1-subquery1:$hdt$_0-subquery1:src2] + /src2 [null-subquery1-subquery1:$hdt$_1-subquery1-subquery1:src2] Map 2 Map Operator Tree: TableScan @@ -1150,7 +1146,7 @@ STAGE PLANS: name: default.src3 name: default.src3 Truncated Path -> Alias: - /src3 [null-subquery1:$hdt$_0-subquery1-subquery2:$hdt$_0-subquery2:src3] + /src3 [null-subquery1-subquery2:$hdt$_1-subquery1-subquery2:src3] Map 3 Map Operator Tree: TableScan @@ -1223,7 +1219,7 @@ STAGE PLANS: name: default.src4 name: default.src4 Truncated Path -> Alias: - /src4 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:a] + /src4 [null-subquery2:$hdt$_1-subquery2:$hdt$_1:a] Map 6 Map Operator Tree: TableScan @@ -1296,7 +1292,7 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src5 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_1:b] + /src5 [null-subquery2:$hdt$_1-subquery2:$hdt$_2:b] Reducer 4 Needs Tagging: true Reduce Operator Tree: @@ -1309,7 +1305,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union25.q.out ql/src/test/results/clientpositive/spark/union25.q.out index 5eb5cdd..559b318 100644 --- ql/src/test/results/clientpositive/spark/union25.q.out +++ ql/src/test/results/clientpositive/spark/union25.q.out @@ -80,7 +80,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -161,7 +161,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/spark/union31.q.out ql/src/test/results/clientpositive/spark/union31.q.out index 1dc8db2..10f8bdb 100644 --- ql/src/test/results/clientpositive/spark/union31.q.out +++ ql/src/test/results/clientpositive/spark/union31.q.out @@ -373,11 +373,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -394,11 +394,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -667,11 +667,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union4.q.out ql/src/test/results/clientpositive/spark/union4.q.out index 45705e9..cb8c6a2 100644 --- ql/src/test/results/clientpositive/spark/union4.q.out +++ ql/src/test/results/clientpositive/spark/union4.q.out @@ -39,7 +39,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -55,7 +55,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -138,7 +138,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/spark/union5.q.out ql/src/test/results/clientpositive/spark/union5.q.out index 111caa2..dc55108 100644 --- ql/src/test/results/clientpositive/spark/union5.q.out +++ ql/src/test/results/clientpositive/spark/union5.q.out @@ -69,7 +69,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -107,7 +107,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union6.q.out ql/src/test/results/clientpositive/spark/union6.q.out index d419c9a..6f61839 100644 --- ql/src/test/results/clientpositive/spark/union6.q.out +++ ql/src/test/results/clientpositive/spark/union6.q.out @@ -38,7 +38,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -113,7 +113,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from tmptable x sort by x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/spark/union7.q.out ql/src/test/results/clientpositive/spark/union7.q.out index 6cc5d6d..9f99c18 100644 --- ql/src/test/results/clientpositive/spark/union7.q.out +++ ql/src/test/results/clientpositive/spark/union7.q.out @@ -48,7 +48,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -71,7 +71,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/spark/union9.q.out ql/src/test/results/clientpositive/spark/union9.q.out index 53c6e7d..56997e8 100644 --- ql/src/test/results/clientpositive/spark/union9.q.out +++ ql/src/test/results/clientpositive/spark/union9.q.out @@ -29,7 +29,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -47,7 +47,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -65,7 +65,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/spark/union_remove_1.q.out ql/src/test/results/clientpositive/spark/union_remove_1.q.out index 384079e..1cc1303 100644 --- ql/src/test/results/clientpositive/spark/union_remove_1.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_1.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_10.q.out ql/src/test/results/clientpositive/spark/union_remove_10.q.out index 5ccad1c..7ae8479 100644 --- ql/src/test/results/clientpositive/spark/union_remove_10.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_10.q.out @@ -88,11 +88,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_13.q.out ql/src/test/results/clientpositive/spark/union_remove_13.q.out index f4107e7..0d0d841 100644 --- ql/src/test/results/clientpositive/spark/union_remove_13.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_13.q.out @@ -89,11 +89,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_15.q.out ql/src/test/results/clientpositive/spark/union_remove_15.q.out index e350ac0..96ee309 100644 --- ql/src/test/results/clientpositive/spark/union_remove_15.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_15.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_16.q.out ql/src/test/results/clientpositive/spark/union_remove_16.q.out index c392102..8ea2b00 100644 --- ql/src/test/results/clientpositive/spark/union_remove_16.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_16.q.out @@ -64,11 +64,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_18.q.out ql/src/test/results/clientpositive/spark/union_remove_18.q.out index e3a8e62..62c3598 100644 --- ql/src/test/results/clientpositive/spark/union_remove_18.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_18.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), ds (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE 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 a5b5a40..0ec066e 100644 --- ql/src/test/results/clientpositive/spark/union_remove_19.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_19.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -226,22 +226,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator @@ -361,22 +357,18 @@ STAGE PLANS: Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Group By Operator diff --git ql/src/test/results/clientpositive/spark/union_remove_2.q.out ql/src/test/results/clientpositive/spark/union_remove_2.q.out index 6dd8bab..928f266 100644 --- ql/src/test/results/clientpositive/spark/union_remove_2.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_2.q.out @@ -62,11 +62,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_20.q.out ql/src/test/results/clientpositive/spark/union_remove_20.q.out index f1491de..1bc3d57 100644 --- ql/src/test/results/clientpositive/spark/union_remove_20.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_20.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_22.q.out ql/src/test/results/clientpositive/spark/union_remove_22.q.out index af3ea4b..2f9941d 100644 --- ql/src/test/results/clientpositive/spark/union_remove_22.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_22.q.out @@ -235,11 +235,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_23.q.out ql/src/test/results/clientpositive/spark/union_remove_23.q.out index 2c21b0a..dcc8635 100644 --- ql/src/test/results/clientpositive/spark/union_remove_23.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_23.q.out @@ -96,11 +96,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -121,7 +121,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -198,7 +198,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)a.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)a.null, (inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)a.null, (inputtbl1)b.null, (inputtbl1)inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git ql/src/test/results/clientpositive/spark/union_remove_24.q.out ql/src/test/results/clientpositive/spark/union_remove_24.q.out index 2a9e4f6..8f7187b 100644 --- ql/src/test/results/clientpositive/spark/union_remove_24.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_24.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_25.q.out ql/src/test/results/clientpositive/spark/union_remove_25.q.out index 9fec1d4..1949a90 100644 --- ql/src/test/results/clientpositive/spark/union_remove_25.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_25.q.out @@ -75,11 +75,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_4.q.out ql/src/test/results/clientpositive/spark/union_remove_4.q.out index 33e8f51..b31ae64 100644 --- ql/src/test/results/clientpositive/spark/union_remove_4.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_4.q.out @@ -64,11 +64,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_5.q.out ql/src/test/results/clientpositive/spark/union_remove_5.q.out index 104ca01..1380180 100644 --- ql/src/test/results/clientpositive/spark/union_remove_5.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_5.q.out @@ -67,11 +67,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_6.q.out ql/src/test/results/clientpositive/spark/union_remove_6.q.out index ac4aaf3..5680345 100644 --- ql/src/test/results/clientpositive/spark/union_remove_6.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_6.q.out @@ -68,11 +68,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out index 868cda5..f2c9911 100644 --- ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_6_subq.q.out @@ -72,11 +72,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -256,7 +256,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -374,11 +374,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_7.q.out ql/src/test/results/clientpositive/spark/union_remove_7.q.out index cff02a7..7341d98 100644 --- ql/src/test/results/clientpositive/spark/union_remove_7.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_7.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_8.q.out ql/src/test/results/clientpositive/spark/union_remove_8.q.out index 769e00f..06ba030 100644 --- ql/src/test/results/clientpositive/spark/union_remove_8.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_8.q.out @@ -62,11 +62,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_remove_9.q.out ql/src/test/results/clientpositive/spark/union_remove_9.q.out index ab557b1..183169b 100644 --- ql/src/test/results/clientpositive/spark/union_remove_9.q.out +++ ql/src/test/results/clientpositive/spark/union_remove_9.q.out @@ -71,11 +71,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/union_view.q.out ql/src/test/results/clientpositive/spark/union_view.q.out index a5970c0..f77c927 100644 --- ql/src/test/results/clientpositive/spark/union_view.q.out +++ ql/src/test/results/clientpositive/spark/union_view.q.out @@ -519,7 +519,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -541,7 +541,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -563,7 +563,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -617,7 +617,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -636,7 +636,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -658,7 +658,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -712,7 +712,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -734,7 +734,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -753,7 +753,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -899,7 +899,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -921,7 +921,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -940,7 +940,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/spark/vector_between_in.q.out ql/src/test/results/clientpositive/spark/vector_between_in.q.out index 2f87841..976d9d9 100644 --- ql/src/test/results/clientpositive/spark/vector_between_in.q.out +++ ql/src/test/results/clientpositive/spark/vector_between_in.q.out @@ -1095,9 +1095,9 @@ STAGE PLANS: selectExpressions: LongColumnInList(col 3, values [-67, -171]) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1235,9 +1235,9 @@ STAGE PLANS: selectExpressions: DecimalColumnInList(col 1, values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1375,9 +1375,9 @@ STAGE PLANS: selectExpressions: VectorUDFAdaptor(cdate BETWEEN 1969-12-30 AND 1970-01-02) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true @@ -1515,9 +1515,9 @@ STAGE PLANS: selectExpressions: VectorUDFAdaptor(cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351) -> 4:boolean Statistics: Num rows: 12288 Data size: 2467616 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 5:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true diff --git ql/src/test/results/clientpositive/stats1.q.out ql/src/test/results/clientpositive/stats1.q.out index 2d5b4f8..5c6049b 100644 --- ql/src/test/results/clientpositive/stats1.q.out +++ ql/src/test/results/clientpositive/stats1.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -125,7 +125,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT * FROM tmptable x SORT BY x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/subq2.q.out ql/src/test/results/clientpositive/subq2.q.out index b402e09..213388c 100644 --- ql/src/test/results/clientpositive/subq2.q.out +++ ql/src/test/results/clientpositive/subq2.q.out @@ -22,22 +22,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) >= 90.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/symlink_text_input_format.q.out ql/src/test/results/clientpositive/symlink_text_input_format.q.out index a5a862c..bde6dd2 100644 --- ql/src/test/results/clientpositive/symlink_text_input_format.q.out +++ ql/src/test/results/clientpositive/symlink_text_input_format.q.out @@ -178,7 +178,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -387,7 +387,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out index 9ced7ad..0916565 100644 --- ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out +++ ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out @@ -1746,44 +1746,44 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 5 - File Output Operator [FS_19] + File Output Operator [FS_18] table:{"name:":"default.dest1"} - Select Operator [SEL_17] (rows=205/310 width=272) + Select Operator [SEL_16] (rows=205/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_16] (rows=205/310 width=96) + Group By Operator [GBY_15] (rows=205/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_15] + SHUFFLE [RS_14] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=501/310 width=272) + Group By Operator [GBY_11] (rows=501/310 width=272) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] PartitionCols:_col0, _col1 - Select Operator [SEL_7] (rows=500/500 width=178) + Select Operator [SEL_6] (rows=500/500 width=178) Output:["_col0","_col1"] - TableScan [TS_6] (rows=500/500 width=178) + TableScan [TS_5] (rows=500/500 width=178) Output:["key","value"] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] PartitionCols:_col0, _col1 - Select Operator [SEL_5] (rows=1/1 width=272) + Select Operator [SEL_4] (rows=1/1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_4] (rows=1/1 width=8) - Output:["_col0"],aggregations:["count(1)"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_3] + PARTITION_ONLY_SHUFFLE [RS_2] Select Operator [SEL_1] (rows=500/500 width=10) TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - File Output Operator [FS_25] + File Output Operator [FS_24] table:{"name:":"default.dest2"} - Select Operator [SEL_23] (rows=501/310 width=456) + Select Operator [SEL_22] (rows=501/310 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_22] (rows=501/310 width=280) + Group By Operator [GBY_21] (rows=501/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1 - Please refer to the previous Group By Operator [GBY_12] + Please refer to the previous Group By Operator [GBY_11] Stage-5 Stats-Aggr Operator Stage-1 @@ -1978,54 +1978,54 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 - File Output Operator [FS_17] + File Output Operator [FS_16] table:{"name:":"default.dest1"} - Select Operator [SEL_15] (rows=205/310 width=272) + Select Operator [SEL_14] (rows=205/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=205/310 width=96) + Group By Operator [GBY_13] (rows=205/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0 - Select Operator [SEL_7] (rows=500/500 width=178) + Select Operator [SEL_6] (rows=500/500 width=178) Output:["_col0","_col1"] - TableScan [TS_6] (rows=500/500 width=178) + TableScan [TS_5] (rows=500/500 width=178) Output:["key","value"] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_18] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_7] + Please refer to the previous Select Operator [SEL_6] <-Map 7 [CONTAINS] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0 - Select Operator [SEL_10] (rows=500/500 width=178) + Select Operator [SEL_9] (rows=500/500 width=178) Output:["_col0","_col1"] - TableScan [TS_9] (rows=500/500 width=178) + TableScan [TS_8] (rows=500/500 width=178) Output:["key","value"] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_18] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_10] + Please refer to the previous Select Operator [SEL_9] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1/1 width=272) + Select Operator [SEL_4] (rows=1/1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_4] (rows=1/1 width=8) - Output:["_col0"],aggregations:["count(1)"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_3] + PARTITION_ONLY_SHUFFLE [RS_2] Select Operator [SEL_1] (rows=500/500 width=10) TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_18] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_5] + Please refer to the previous Select Operator [SEL_4] Reducer 5 - File Output Operator [FS_23] + File Output Operator [FS_22] table:{"name:":"default.dest2"} - Select Operator [SEL_21] (rows=1001/310 width=456) + Select Operator [SEL_20] (rows=1001/310 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_20] (rows=1001/310 width=280) + Group By Operator [GBY_19] (rows=1001/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5 @@ -2096,44 +2096,44 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 - File Output Operator [FS_15] + File Output Operator [FS_14] table:{"name:":"default.dest1"} - Select Operator [SEL_13] (rows=205/310 width=272) + Select Operator [SEL_12] (rows=205/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_12] (rows=205/310 width=96) + Group By Operator [GBY_11] (rows=205/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] PartitionCols:_col0 - Select Operator [SEL_7] (rows=500/500 width=178) + Select Operator [SEL_6] (rows=500/500 width=178) Output:["_col0","_col1"] - TableScan [TS_6] (rows=500/500 width=178) + TableScan [TS_5] (rows=500/500 width=178) Output:["key","value"] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_16] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_7] + Please refer to the previous Select Operator [SEL_6] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1/1 width=272) + Select Operator [SEL_4] (rows=1/1 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_4] (rows=1/1 width=8) - Output:["_col0"],aggregations:["count(1)"] + Group By Operator [GBY_3] (rows=1/1 width=8) + Output:["_col0"],aggregations:["count()"] <-Map 1 [CUSTOM_SIMPLE_EDGE] - PARTITION_ONLY_SHUFFLE [RS_3] + PARTITION_ONLY_SHUFFLE [RS_2] Select Operator [SEL_1] (rows=500/500 width=10) TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_16] PartitionCols:_col0, _col1 - Please refer to the previous Select Operator [SEL_5] + Please refer to the previous Select Operator [SEL_4] Reducer 5 - File Output Operator [FS_21] + File Output Operator [FS_20] table:{"name:":"default.dest2"} - Select Operator [SEL_19] (rows=501/310 width=456) + Select Operator [SEL_18] (rows=501/310 width=456) Output:["_col0","_col1","_col2"] - Group By Operator [GBY_18] (rows=501/310 width=280) + Group By Operator [GBY_17] (rows=501/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5 diff --git ql/src/test/results/clientpositive/udtf_explode.q.out ql/src/test/results/clientpositive/udtf_explode.q.out index 2b19296..d0da547 100644 --- ql/src/test/results/clientpositive/udtf_explode.q.out +++ ql/src/test/results/clientpositive/udtf_explode.q.out @@ -141,7 +141,7 @@ STAGE PLANS: Number of rows: 3 Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 @@ -406,7 +406,7 @@ STAGE PLANS: Number of rows: 3 Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/union10.q.out ql/src/test/results/clientpositive/union10.q.out index 85eabf5..e14e5e0 100644 --- ql/src/test/results/clientpositive/union10.q.out +++ ql/src/test/results/clientpositive/union10.q.out @@ -45,7 +45,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -180,7 +180,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -214,7 +214,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -258,7 +258,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, (src)s3.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/union11.q.out ql/src/test/results/clientpositive/union11.q.out index 99944d7..520cd43 100644 --- ql/src/test/results/clientpositive/union11.q.out +++ ql/src/test/results/clientpositive/union11.q.out @@ -63,7 +63,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -78,7 +78,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -93,7 +93,7 @@ STAGE PLANS: Union Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union12.q.out ql/src/test/results/clientpositive/union12.q.out index 1b02d16..10540f9 100644 --- ql/src/test/results/clientpositive/union12.q.out +++ ql/src/test/results/clientpositive/union12.q.out @@ -45,7 +45,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -180,7 +180,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -214,7 +214,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 10603 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -262,7 +262,7 @@ POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.null, (srcbucket)s3.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/union14.q.out ql/src/test/results/clientpositive/union14.q.out index 9c59283..968a826 100644 --- ql/src/test/results/clientpositive/union14.q.out +++ ql/src/test/results/clientpositive/union14.q.out @@ -65,7 +65,7 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -80,7 +80,7 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union15.q.out ql/src/test/results/clientpositive/union15.q.out index 323e099..31915e9 100644 --- ql/src/test/results/clientpositive/union15.q.out +++ ql/src/test/results/clientpositive/union15.q.out @@ -61,7 +61,7 @@ STAGE PLANS: Union Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -82,7 +82,7 @@ STAGE PLANS: Union Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -103,7 +103,7 @@ STAGE PLANS: Union Statistics: Num rows: 51 Data size: 390 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union16.q.out ql/src/test/results/clientpositive/union16.q.out index 35bad61..5403477 100644 --- ql/src/test/results/clientpositive/union16.q.out +++ ql/src/test/results/clientpositive/union16.q.out @@ -80,7 +80,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -98,7 +98,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -116,7 +116,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -134,7 +134,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -152,7 +152,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -170,7 +170,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -188,7 +188,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -206,7 +206,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -224,7 +224,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -242,7 +242,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -260,7 +260,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -278,7 +278,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -296,7 +296,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -314,7 +314,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -332,7 +332,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -350,7 +350,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -368,7 +368,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -386,7 +386,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -404,7 +404,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -422,7 +422,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -440,7 +440,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -458,7 +458,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -476,7 +476,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -494,7 +494,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -512,7 +512,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 12500 Data size: 100000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union17.q.out ql/src/test/results/clientpositive/union17.q.out index 18e06e1..bff29f6 100644 --- ql/src/test/results/clientpositive/union17.q.out +++ ql/src/test/results/clientpositive/union17.q.out @@ -47,7 +47,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -227,10 +227,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/union18.q.out ql/src/test/results/clientpositive/union18.q.out index caa664c..702ff10 100644 --- ql/src/test/results/clientpositive/union18.q.out +++ ql/src/test/results/clientpositive/union18.q.out @@ -56,7 +56,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -260,10 +260,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 SORT BY DEST1.key, DEST1.value PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/union19.q.out ql/src/test/results/clientpositive/union19.q.out index 5ce5905..3553091 100644 --- ql/src/test/results/clientpositive/union19.q.out +++ ql/src/test/results/clientpositive/union19.q.out @@ -46,7 +46,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -199,10 +199,10 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@dest1 POSTHOOK: Output: default@dest2 POSTHOOK: Lineage: dest1.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest1.value EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest2.key EXPRESSION [(src)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val1 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: dest2.val2 EXPRESSION [(src)s1.null, (src)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: SELECT DEST1.* FROM DEST1 SORT BY DEST1.key, DEST1.value PREHOOK: type: QUERY PREHOOK: Input: default@dest1 diff --git ql/src/test/results/clientpositive/union2.q.out ql/src/test/results/clientpositive/union2.q.out index cf75125..dbd5966 100644 --- ql/src/test/results/clientpositive/union2.q.out +++ ql/src/test/results/clientpositive/union2.q.out @@ -24,7 +24,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -42,7 +42,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union20.q.out ql/src/test/results/clientpositive/union20.q.out index ae55a8b..d911b90 100644 --- ql/src/test/results/clientpositive/union20.q.out +++ ql/src/test/results/clientpositive/union20.q.out @@ -36,7 +36,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -144,7 +144,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union24.q.out ql/src/test/results/clientpositive/union24.q.out index ae4d2a7..8f8c170 100644 --- ql/src/test/results/clientpositive/union24.q.out +++ ql/src/test/results/clientpositive/union24.q.out @@ -85,25 +85,21 @@ STAGE PLANS: isSamplingPred: false predicate: (UDFToDouble(key) < 10.0) (type: boolean) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: false + tag: -1 + value expressions: _col1 (type: bigint) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -154,7 +150,7 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src5 [null-subquery2:$hdt$_2-subquery2:$hdt$_2:src5] + /src5 [null-subquery2:$hdt$_2-subquery2:src5] Needs Tagging: false Reduce Operator Tree: Group By Operator @@ -1184,8 +1180,8 @@ STAGE PLANS: name: default.src5 name: default.src5 Truncated Path -> Alias: - /src4 [null-subquery2:$hdt$_1-subquery2:$hdt$_1:$hdt$_1:a] - /src5 [null-subquery2:$hdt$_1-subquery2:$hdt$_1:$hdt$_2:b] + /src4 [null-subquery2:$hdt$_1-subquery2:$hdt$_1:a] + /src5 [null-subquery2:$hdt$_1-subquery2:$hdt$_2:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -1197,7 +1193,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union25.q.out ql/src/test/results/clientpositive/union25.q.out index e9e9a28..a287a97 100644 --- ql/src/test/results/clientpositive/union25.q.out +++ ql/src/test/results/clientpositive/union25.q.out @@ -135,7 +135,7 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -150,7 +150,7 @@ STAGE PLANS: Union Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/union31.q.out ql/src/test/results/clientpositive/union31.q.out index 4c26c7b..b7a63fc 100644 --- ql/src/test/results/clientpositive/union31.q.out +++ ql/src/test/results/clientpositive/union31.q.out @@ -356,11 +356,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -479,11 +479,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE @@ -666,11 +666,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union4.q.out ql/src/test/results/clientpositive/union4.q.out index 0821589..f3cd59c 100644 --- ql/src/test/results/clientpositive/union4.q.out +++ ql/src/test/results/clientpositive/union4.q.out @@ -40,7 +40,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -160,7 +160,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -200,7 +200,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [] -POSTHOOK: Lineage: tmptable.value EXPRESSION [] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src)s2.null, ] PREHOOK: query: select * from tmptable x sort by x.key PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/union5.q.out ql/src/test/results/clientpositive/union5.q.out index 8cc52f3..e5a5387 100644 --- ql/src/test/results/clientpositive/union5.q.out +++ ql/src/test/results/clientpositive/union5.q.out @@ -58,7 +58,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -73,7 +73,7 @@ STAGE PLANS: Union Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union6.q.out ql/src/test/results/clientpositive/union6.q.out index 8448d86..fc66cf1 100644 --- ql/src/test/results/clientpositive/union6.q.out +++ ql/src/test/results/clientpositive/union6.q.out @@ -39,7 +39,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -165,7 +165,7 @@ POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@tmptable POSTHOOK: Lineage: tmptable.key EXPRESSION [(src1)s2.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tmptable.value EXPRESSION [(src1)s2.FieldSchema(name:value, type:string, comment:default), ] +POSTHOOK: Lineage: tmptable.value EXPRESSION [(src)s1.null, (src1)s2.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from tmptable x sort by x.key, x.value PREHOOK: type: QUERY PREHOOK: Input: default@tmptable diff --git ql/src/test/results/clientpositive/union7.q.out ql/src/test/results/clientpositive/union7.q.out index 6eb4036..0cd5b92 100644 --- ql/src/test/results/clientpositive/union7.q.out +++ ql/src/test/results/clientpositive/union7.q.out @@ -57,7 +57,7 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -78,7 +78,7 @@ STAGE PLANS: Union Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 diff --git ql/src/test/results/clientpositive/union9.q.out ql/src/test/results/clientpositive/union9.q.out index 7e3b7d4..6883f02 100644 --- ql/src/test/results/clientpositive/union9.q.out +++ ql/src/test/results/clientpositive/union9.q.out @@ -26,7 +26,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -44,7 +44,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -62,7 +62,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1500 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE diff --git ql/src/test/results/clientpositive/union_pos_alias.q.out ql/src/test/results/clientpositive/union_pos_alias.q.out index 8ffbc2a..bb161f8 100644 --- ql/src/test/results/clientpositive/union_pos_alias.q.out +++ ql/src/test/results/clientpositive/union_pos_alias.q.out @@ -27,7 +27,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -101,7 +101,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -135,7 +135,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -470,7 +470,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -571,7 +571,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 27 Data size: 286 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: int), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 diff --git ql/src/test/results/clientpositive/union_remove_1.q.out ql/src/test/results/clientpositive/union_remove_1.q.out index 2be8d57..d611a64 100644 --- ql/src/test/results/clientpositive/union_remove_1.q.out +++ ql/src/test/results/clientpositive/union_remove_1.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -102,11 +102,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_10.q.out ql/src/test/results/clientpositive/union_remove_10.q.out index 5bf4d51..ef78a20 100644 --- ql/src/test/results/clientpositive/union_remove_10.q.out +++ ql/src/test/results/clientpositive/union_remove_10.q.out @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_13.q.out ql/src/test/results/clientpositive/union_remove_13.q.out index 2c584e0..95acdc3 100644 --- ql/src/test/results/clientpositive/union_remove_13.q.out +++ ql/src/test/results/clientpositive/union_remove_13.q.out @@ -62,11 +62,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_15.q.out ql/src/test/results/clientpositive/union_remove_15.q.out index eeef27f..206eda9 100644 --- ql/src/test/results/clientpositive/union_remove_15.q.out +++ ql/src/test/results/clientpositive/union_remove_15.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -108,11 +108,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_16.q.out ql/src/test/results/clientpositive/union_remove_16.q.out index f6757cc..8cc31f3 100644 --- ql/src/test/results/clientpositive/union_remove_16.q.out +++ ql/src/test/results/clientpositive/union_remove_16.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -142,11 +142,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_18.q.out ql/src/test/results/clientpositive/union_remove_18.q.out index d99a6ce..e592481 100644 --- ql/src/test/results/clientpositive/union_remove_18.q.out +++ ql/src/test/results/clientpositive/union_remove_18.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), ds (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -108,11 +108,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), ds (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, ds Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), ds (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_19.q.out ql/src/test/results/clientpositive/union_remove_19.q.out index 8a3a73f..b7e7e5c 100644 --- ql/src/test/results/clientpositive/union_remove_19.q.out +++ ql/src/test/results/clientpositive/union_remove_19.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -102,11 +102,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -237,22 +237,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -288,22 +284,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) = 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -391,22 +383,18 @@ STAGE PLANS: Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -446,22 +434,18 @@ STAGE PLANS: Filter Operator predicate: ((UDFToDouble(key) + UDFToDouble(key)) >= 7.0) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 30 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: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) diff --git ql/src/test/results/clientpositive/union_remove_2.q.out ql/src/test/results/clientpositive/union_remove_2.q.out index 8a841c0..088f1fd 100644 --- ql/src/test/results/clientpositive/union_remove_2.q.out +++ ql/src/test/results/clientpositive/union_remove_2.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_20.q.out ql/src/test/results/clientpositive/union_remove_20.q.out index 9e78e22..25d8792 100644 --- ql/src/test/results/clientpositive/union_remove_20.q.out +++ ql/src/test/results/clientpositive/union_remove_20.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -106,11 +106,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_22.q.out ql/src/test/results/clientpositive/union_remove_22.q.out index f1e0326..cf0b3b6 100644 --- ql/src/test/results/clientpositive/union_remove_22.q.out +++ ql/src/test/results/clientpositive/union_remove_22.q.out @@ -246,11 +246,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -298,11 +298,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_23.q.out ql/src/test/results/clientpositive/union_remove_23.q.out index 5ccc085..15a1417 100644 --- ql/src/test/results/clientpositive/union_remove_23.q.out +++ ql/src/test/results/clientpositive/union_remove_23.q.out @@ -92,7 +92,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 @@ -148,11 +148,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -201,7 +201,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@inputtbl1 POSTHOOK: Output: default@outputtbl1 POSTHOOK: Lineage: outputtbl1.key EXPRESSION [(inputtbl1)a.FieldSchema(name:key, type:string, comment:null), (inputtbl1)inputtbl1.FieldSchema(name:key, type:string, comment:null), ] -POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)a.null, (inputtbl1)inputtbl1.null, ] +POSTHOOK: Lineage: outputtbl1.values EXPRESSION [(inputtbl1)a.null, (inputtbl1)b.null, (inputtbl1)inputtbl1.null, ] PREHOOK: query: desc formatted outputTbl1 PREHOOK: type: DESCTABLE PREHOOK: Input: default@outputtbl1 diff --git ql/src/test/results/clientpositive/union_remove_24.q.out ql/src/test/results/clientpositive/union_remove_24.q.out index 5cbb0b0..d50d9d1 100644 --- ql/src/test/results/clientpositive/union_remove_24.q.out +++ ql/src/test/results/clientpositive/union_remove_24.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -106,11 +106,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_25.q.out ql/src/test/results/clientpositive/union_remove_25.q.out index f967fc6..787783e 100644 --- ql/src/test/results/clientpositive/union_remove_25.q.out +++ ql/src/test/results/clientpositive/union_remove_25.q.out @@ -70,11 +70,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -120,11 +120,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_4.q.out ql/src/test/results/clientpositive/union_remove_4.q.out index 593bb6e..98d0f85 100644 --- ql/src/test/results/clientpositive/union_remove_4.q.out +++ ql/src/test/results/clientpositive/union_remove_4.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -146,11 +146,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_5.q.out ql/src/test/results/clientpositive/union_remove_5.q.out index aaf4654..3671058 100644 --- ql/src/test/results/clientpositive/union_remove_5.q.out +++ ql/src/test/results/clientpositive/union_remove_5.q.out @@ -64,11 +64,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_6.q.out ql/src/test/results/clientpositive/union_remove_6.q.out index ece7000..c08177d 100644 --- ql/src/test/results/clientpositive/union_remove_6.q.out +++ ql/src/test/results/clientpositive/union_remove_6.q.out @@ -64,11 +64,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -162,11 +162,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_6_subq.q.out ql/src/test/results/clientpositive/union_remove_6_subq.q.out index 0bd00c9..5b9e631 100644 --- ql/src/test/results/clientpositive/union_remove_6_subq.q.out +++ ql/src/test/results/clientpositive/union_remove_6_subq.q.out @@ -68,11 +68,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -166,11 +166,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -290,7 +290,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -365,7 +365,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE @@ -440,11 +440,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -547,11 +547,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_7.q.out ql/src/test/results/clientpositive/union_remove_7.q.out index 5bdd4ba..dbd9838 100644 --- ql/src/test/results/clientpositive/union_remove_7.q.out +++ ql/src/test/results/clientpositive/union_remove_7.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE @@ -102,11 +102,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_8.q.out ql/src/test/results/clientpositive/union_remove_8.q.out index aedec8b..83cf4b4 100644 --- ql/src/test/results/clientpositive/union_remove_8.q.out +++ ql/src/test/results/clientpositive/union_remove_8.q.out @@ -59,11 +59,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_remove_9.q.out ql/src/test/results/clientpositive/union_remove_9.q.out index af7c2e4..e27b126 100644 --- ql/src/test/results/clientpositive/union_remove_9.q.out +++ ql/src/test/results/clientpositive/union_remove_9.q.out @@ -67,11 +67,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string) + aggregations: count() + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/union_view.q.out ql/src/test/results/clientpositive/union_view.q.out index 29f6758..8712b48 100644 --- ql/src/test/results/clientpositive/union_view.q.out +++ ql/src/test/results/clientpositive/union_view.q.out @@ -727,7 +727,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -751,7 +751,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -775,7 +775,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -851,7 +851,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -872,7 +872,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -896,7 +896,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -972,7 +972,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -996,7 +996,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1017,7 +1017,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1216,7 +1216,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1240,7 +1240,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1261,7 +1261,7 @@ STAGE PLANS: Select Operator Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git ql/src/test/results/clientpositive/vector_count.q.out ql/src/test/results/clientpositive/vector_count.q.out index 1068c78..0270926 100644 --- ql/src/test/results/clientpositive/vector_count.q.out +++ ql/src/test/results/clientpositive/vector_count.q.out @@ -175,26 +175,26 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3] Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1), count(), count(_col1), count(_col2), count(_col3), count(_col4), count(DISTINCT _col1), count(DISTINCT _col2), count(DISTINCT _col3), count(DISTINCT _col4), count(DISTINCT _col1, _col2), count(DISTINCT _col2, _col3), count(DISTINCT _col3, _col4), count(DISTINCT _col1, _col4), count(DISTINCT _col1, _col3), count(DISTINCT _col2, _col4), count(DISTINCT _col1, _col2, _col3), count(DISTINCT _col2, _col3, _col4), count(DISTINCT _col1, _col3, _col4), count(DISTINCT _col1, _col2, _col4), count(DISTINCT _col1, _col2, _col3, _col4) + aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d) Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 4:long) -> bigint, VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 3) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 2) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 1) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint, VectorUDAFCount(col 0) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true keyExpressions: col 0, col 1, col 2, col 3 native: false vectorProcessingMode: HASH - projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] - keys: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] + keys: a (type: int), b (type: int), c (type: int), d (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int) @@ -205,7 +205,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false, No DISTINCT columns IS false Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint) + value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint) Execution mode: vectorized Map Vectorization: enabled: true @@ -221,7 +221,7 @@ STAGE PLANS: enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(VALUE._col5), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) Group By Vectorization: groupByMode: MERGEPARTIAL vectorOutput: false @@ -229,15 +229,19 @@ STAGE PLANS: vectorProcessingMode: NONE projectedOutputColumns: null mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -371,14 +375,14 @@ STAGE PLANS: projectedOutputColumns: [0, 1, 2, 3] Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col1, _col2, _col3, _col4 + outputColumnNames: a, b, c, d Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumns: [0, 1, 2, 3] Statistics: Num rows: 7 Data size: 100 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int) + key expressions: a (type: int), b (type: int), c (type: int), d (type: int) sort order: ++++ Reduce Sink Vectorization: className: VectorReduceSinkOperator @@ -401,7 +405,7 @@ STAGE PLANS: enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Reduce Operator Tree: Group By Operator - aggregations: count(1), count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) + aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3) Group By Vectorization: groupByMode: COMPLETE vectorOutput: false @@ -409,15 +413,19 @@ STAGE PLANS: vectorProcessingMode: NONE projectedOutputColumns: null mode: complete - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out index 0fa8e2f..a659b9e 100644 --- ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out +++ ql/src/test/results/clientpositive/vector_mr_diff_schema_alias.q.out @@ -343,22 +343,18 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col3 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: _col3 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Group By Operator - aggregations: count(1) - 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 + 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/vectorized_mapjoin2.q.out ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out index 5334c16..1127f8a 100644 --- ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out +++ ql/src/test/results/clientpositive/vectorized_mapjoin2.q.out @@ -47,11 +47,11 @@ STAGE PLANS: Stage: Stage-5 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:x + $hdt$_0:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:x + $hdt$_0:x TableScan alias: x Statistics: Num rows: 45 Data size: 181 Basic stats: COMPLETE Column stats: NONE @@ -104,9 +104,9 @@ STAGE PLANS: nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Statistics: Num rows: 49 Data size: 199 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count() Group By Vectorization: - aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 0:long) -> bigint + aggregators: VectorUDAFCountStar(*) -> bigint className: VectorGroupByOperator groupByMode: HASH vectorOutput: true diff --git ql/src/test/results/clientpositive/view_cbo.q.out ql/src/test/results/clientpositive/view_cbo.q.out index 97b7ca5..135b380 100644 --- ql/src/test/results/clientpositive/view_cbo.q.out +++ ql/src/test/results/clientpositive/view_cbo.q.out @@ -678,11 +678,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(2) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -783,11 +783,11 @@ STAGE PLANS: 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 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count() + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE