wangyum commented on a change in pull request #33404: URL: https://github.com/apache/spark/pull/33404#discussion_r672388764
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregatesInLeftSemiAntiJoin.scala ########## @@ -0,0 +1,40 @@ +/* + * 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.spark.sql.catalyst.optimizer + +import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Join, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.catalyst.trees.TreePattern.{AGGREGATE, LEFT_SEMI_OR_ANTI_JOIN} + +/** + * Remove the redundant aggregation from left semi/anti join if the same aggregation has already + * been done on left side. + */ +object RemoveRedundantAggregatesInLeftSemiAntiJoin extends Rule[LogicalPlan] { Review comment: How about just add this rule to `RemoveRedundantAggregates`? ```patch Index: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala (revision 86a828aa4e27676ec74dab28b1fb3db996f9c637) +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala (date 1626706341253) @@ -20,7 +20,8 @@ import org.apache.spark.sql.catalyst.analysis.PullOutNondeterministic import org.apache.spark.sql.catalyst.expressions.{AliasHelper, AttributeSet} import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression -import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Join, LogicalPlan} import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.catalyst.trees.TreePattern.AGGREGATE @@ -29,7 +30,7 @@ * only goal is to keep distinct values, while its parent aggregate would ignore duplicate values. */ object RemoveRedundantAggregates extends Rule[LogicalPlan] with AliasHelper { - def apply(plan: LogicalPlan): LogicalPlan = plan.transformUpWithPruning( + def apply(plan: LogicalPlan): LogicalPlan = plan.transformDownWithPruning( _.containsPattern(AGGREGATE), ruleId) { case upper @ Aggregate(_, _, lower: Aggregate) if isLowerRedundant(upper, lower) => val aliasMap = getAliasMap(lower) @@ -47,6 +48,13 @@ } else { newAggregate } + + case agg @ Aggregate(groupingExps, aggExps, + j @ Join(left: Aggregate, _, LeftSemi | LeftAnti, _, _)) if agg.groupOnly && left.groupOnly && + aggExps.forall(e => left.aggregateExpressions.exists(_.semanticEquals(e))) && + groupingExps.length == left.groupingExpressions.length && + groupingExps.zip(left.groupingExpressions).forall(e => e._1.semanticEquals(e._2)) => + j } private def isLowerRedundant(upper: Aggregate, lower: Aggregate): Boolean = { ``` ########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregatesInLeftSemiAntiJoin.scala ########## @@ -0,0 +1,40 @@ +/* + * 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.spark.sql.catalyst.optimizer + +import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Join, LogicalPlan} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.catalyst.trees.TreePattern.{AGGREGATE, LEFT_SEMI_OR_ANTI_JOIN} + +/** + * Remove the redundant aggregation from left semi/anti join if the same aggregation has already + * been done on left side. + */ +object RemoveRedundantAggregatesInLeftSemiAntiJoin extends Rule[LogicalPlan] { Review comment: How about just add this rule to `RemoveRedundantAggregates`? This is because `Distinct(Join(Distinct(left), right, LeftSemi/ LeftAnti, condition, None))` is a very common case. ```patch Index: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala IDEA additional info: Subsystem: com.intellij.openapi.diff.impl.patch.CharsetEP <+>UTF-8 =================================================================== diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala (revision 86a828aa4e27676ec74dab28b1fb3db996f9c637) +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RemoveRedundantAggregates.scala (date 1626706341253) @@ -20,7 +20,8 @@ import org.apache.spark.sql.catalyst.analysis.PullOutNondeterministic import org.apache.spark.sql.catalyst.expressions.{AliasHelper, AttributeSet} import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression -import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan} +import org.apache.spark.sql.catalyst.plans.{LeftAnti, LeftSemi} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, Join, LogicalPlan} import org.apache.spark.sql.catalyst.rules.Rule import org.apache.spark.sql.catalyst.trees.TreePattern.AGGREGATE @@ -29,7 +30,7 @@ * only goal is to keep distinct values, while its parent aggregate would ignore duplicate values. */ object RemoveRedundantAggregates extends Rule[LogicalPlan] with AliasHelper { - def apply(plan: LogicalPlan): LogicalPlan = plan.transformUpWithPruning( + def apply(plan: LogicalPlan): LogicalPlan = plan.transformDownWithPruning( _.containsPattern(AGGREGATE), ruleId) { case upper @ Aggregate(_, _, lower: Aggregate) if isLowerRedundant(upper, lower) => val aliasMap = getAliasMap(lower) @@ -47,6 +48,13 @@ } else { newAggregate } + + case agg @ Aggregate(groupingExps, aggExps, + j @ Join(left: Aggregate, _, LeftSemi | LeftAnti, _, _)) if agg.groupOnly && left.groupOnly && + aggExps.forall(e => left.aggregateExpressions.exists(_.semanticEquals(e))) && + groupingExps.length == left.groupingExpressions.length && + groupingExps.zip(left.groupingExpressions).forall(e => e._1.semanticEquals(e._2)) => + j } private def isLowerRedundant(upper: Aggregate, lower: Aggregate): Boolean = { ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
