rdblue commented on a change in pull request #1738: URL: https://github.com/apache/iceberg/pull/1738#discussion_r519072847
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/optimizer/RewriteDelete.scala ########## @@ -0,0 +1,160 @@ +/* + * 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 java.util.UUID +import org.apache.spark.sql.{sources, AnalysisException} +import org.apache.spark.sql.catalyst.analysis.Resolver +import org.apache.spark.sql.catalyst.expressions.{Alias, Attribute, AttributeReference, EqualNullSafe, Expression, InputFileName, Literal, Not, PredicateHelper, SubqueryExpression} +import org.apache.spark.sql.catalyst.expressions.Literal.FalseLiteral +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, DeleteFromTable, DynamicFileFilter, Filter, LocalRelation, LogicalPlan, OverwriteFiles, Project} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.{SupportsMetadataOnlyDeletes, Table} +import org.apache.spark.sql.connector.write.{LogicalWriteInfo, LogicalWriteInfoImpl, RowLevelOperationsBuilder, SupportsPushDownRowLevelFilters} +import org.apache.spark.sql.execution.datasources.DataSourceStrategy +import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2Relation, DataSourceV2ScanRelation} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.{BooleanType, StructType} +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +// TODO: should be part of early scan push down after the delete condition is optimized +object RewriteDelete extends Rule[LogicalPlan] with PredicateHelper { + + import org.apache.spark.sql.execution.datasources.v2.ExtendedDataSourceV2Implicits._ + + private val FILE_NAME_COL = "_file" + + override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators { + // no need to execute this delete as the condition is false + case DeleteFromTable(_, Some(FalseLiteral)) => + LocalRelation() + + // don't rewrite deletes that can be answered using metadata only operations + case d @ DeleteFromTable(r: DataSourceV2Relation, Some(cond)) if isMetadataOnlyOperation(r, cond) => + d Review comment: I think I noted elsewhere, but I'd prefer to use a subclass of `OverwriteFiles` that first attempts to run this as a metadata delete, and then runs the replace query if that throws `IllegalArgumentException` to signal that the delete cannot be done in metadata. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
