aokolnychyi commented on a change in pull request #35395: URL: https://github.com/apache/spark/pull/35395#discussion_r840957181
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/OptimizeMetadataOnlyDeleteFromTable.scala ########## @@ -0,0 +1,84 @@ +/* + * 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.execution.datasources.v2 + +import org.apache.spark.sql.catalyst.expressions.{Expression, PredicateHelper, SubqueryExpression} +import org.apache.spark.sql.catalyst.expressions.Literal.TrueLiteral +import org.apache.spark.sql.catalyst.plans.logical.{DeleteFromTable, DeleteFromTableWithFilters, LogicalPlan, ReplaceData, RowLevelWrite} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.{SupportsDelete, TruncatableTable} +import org.apache.spark.sql.connector.write.RowLevelOperation +import org.apache.spark.sql.connector.write.RowLevelOperation.Command.DELETE +import org.apache.spark.sql.execution.datasources.DataSourceStrategy +import org.apache.spark.sql.sources + +/** + * A rule that replaces a rewritten DELETE operation with a delete using filters if the data source + * can handle this DELETE command without executing the plan that operates on individual or groups + * of rows. + * + * Note this rule must be run after expression optimization but before scan planning. + */ +object OptimizeMetadataOnlyDeleteFromTable extends Rule[LogicalPlan] with PredicateHelper { + + override def apply(plan: LogicalPlan): LogicalPlan = plan transform { + case RewrittenRowLevelCommand(rowLevelPlan, DELETE, cond, relation: DataSourceV2Relation) => + relation.table match { + case table: SupportsDelete if !SubqueryExpression.hasSubquery(cond) => + val predicates = splitConjunctivePredicates(cond) + val normalizedPredicates = DataSourceStrategy.normalizeExprs(predicates, relation.output) + val filters = toDataSourceFilters(normalizedPredicates) + val allPredicatesTranslated = normalizedPredicates.size == filters.length + if (allPredicatesTranslated && table.canDeleteWhere(filters)) { + logDebug(s"Switching to delete with filters: ${filters.mkString("[", ", ", "]")}") + DeleteFromTableWithFilters(relation, filters) Review comment: I construct `DeleteFromTableWithFilters` to avoid calling `canDeleteWhere` one more time later. For some data sources, checking if a delete using filters is possible is not cheap. The purpose of the new delete node is to avoid doing that work twice. -- 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]
