cloud-fan commented on a change in pull request #35395: URL: https://github.com/apache/spark/pull/35395#discussion_r836187326
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/OptimizeMetadataOnlyDeleteFromTable.scala ########## @@ -0,0 +1,68 @@ +/* + * 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} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.{SupportsDelete, TruncatableTable} +import org.apache.spark.sql.execution.datasources.DataSourceStrategy +import org.apache.spark.sql.sources + +/** + * Checks whether a delete using filters is possible and nullifies the rewrite plan + * if the source can handle this delete without executing the rewrite plan. + * + * 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 d @ DeleteFromTable(relation: DataSourceV2Relation, cond, Some(_)) => Review comment: I know in general it's better to put optimizations in optimizer rules, but we can simplify the code quite a lot if we can do this in the rewrite rule `RewriteDeleteFromTable`. We can statically know if a v2 `Table` extends `SupportsDelete`, if the delete condition contain subquery or not, if the delete condition can be translated to data source filters. which means we don't need to rewrite `DeleteFromTable` when not necessary at the analysis phase. Then the rewrite rule can be quite simple: 1. If the delete is metadata-only, keep the `DeleteFromTable` unchanged. 2. Otherwise, if the table supports row-level operation, rewrite to `ReplaceData` This means we don't need to introduce the nested command concept, and we don't need to add a new field to `DeleteFromTable`, and we don't need the new logical plan `DeleteFromTableWithFilters`. -- 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]
