rdblue commented on a change in pull request #29066: URL: https://github.com/apache/spark/pull/29066#discussion_r536246244
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2Writes.scala ########## @@ -0,0 +1,187 @@ +/* + * 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 java.util.UUID + +import org.apache.spark.SparkException +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst +import org.apache.spark.sql.catalyst.analysis.Resolver +import org.apache.spark.sql.catalyst.expressions.{NamedExpression, PredicateHelper, SortOrder} +import org.apache.spark.sql.catalyst.plans.logical.{AppendData, LogicalPlan, OverwriteByExpression, OverwritePartitionsDynamic, RepartitionByExpression, Sort} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.Table +import org.apache.spark.sql.connector.distributions.{ClusteredDistribution, OrderedDistribution, UnspecifiedDistribution} +import org.apache.spark.sql.connector.expressions.{Expression, FieldReference, IdentityTransform, NullOrdering, SortDirection, SortValue} +import org.apache.spark.sql.connector.write.{LogicalWriteInfoImpl, RequiresDistributionAndOrdering, SupportsDynamicOverwrite, SupportsOverwrite, SupportsTruncate, Write, WriteBuilder} +import org.apache.spark.sql.execution.datasources.DataSourceStrategy +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.sources.{AlwaysTrue, Filter} + +/** + * A rule that constructs [[Write]]s. + * + * This rule does resolution in the optimizer because some nodes like [[OverwriteByExpression]] + * must undergo the expression optimization before we can construct a logical write. + */ +object V2Writes extends Rule[LogicalPlan] with PredicateHelper { + + import DataSourceV2Implicits._ + + override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown { + case append @ AppendData(relation: DataSourceV2Relation, query, options, _, None) => + val writeBuilder = newWriteBuilder(relation.table, query, options) + val write = writeBuilder.build() + append.copy(write = Some(write), query = addDistributionAndOrdering(write, query)) + + case overwrite @ OverwriteByExpression( + relation: DataSourceV2Relation, deleteExpr, query, options, _, None) => + // fail if any filter cannot be converted. correctness depends on removing all matching data. + val filters = splitConjunctivePredicates(deleteExpr).flatMap { p => + val filter = DataSourceStrategy.translateFilter(p, supportNestedPredicatePushdown = true) + if (filter.isEmpty) { + throw new AnalysisException(s"Cannot translate expression to source filter: $p") + } + filter + }.toArray + + val table = relation.table + val writeBuilder = newWriteBuilder(table, query, options) + val write = writeBuilder match { + case builder: SupportsTruncate if isTruncate(filters) => + builder.truncate().build() + case builder: SupportsOverwrite => Review comment: If the source doesn't implement `truncate`, then it gets `overwrite(true)`: https://github.com/apache/spark/blob/master/sql/catalyst/src/main/java/org/apache/spark/sql/connector/write/SupportsOverwrite.java#L46-L48 ---------------------------------------------------------------- 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]
