rdblue commented on a change in pull request #25348: [SPARK-28554][SQL] Adds a v1 fallback writer implementation for v2 data source codepaths URL: https://github.com/apache/spark/pull/25348#discussion_r315453490
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V1FallbackWriters.scala ########## @@ -0,0 +1,108 @@ +/* + * 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 scala.collection.JavaConverters._ + +import org.apache.spark.SparkException +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{Dataset, SaveMode} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.sources.{AlwaysTrue, CreatableRelationProvider, Filter, InsertableRelation} +import org.apache.spark.sql.sources.v2.Table +import org.apache.spark.sql.sources.v2.writer._ +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +/** + * Physical plan node for append into a v2 table using V1 write interfaces. + * + * Rows in the output data set are appended. + */ +case class AppendDataExecV1( + writeBuilder: V1WriteBuilder, + plan: LogicalPlan) extends V1FallbackWriters { + + override protected def doExecute(): RDD[InternalRow] = { + writeWithV1(writeBuilder.buildForV1Write()) + } +} + +/** + * Physical plan node for overwrite into a v2 table with V1 write interfaces. Note that when this + * interface is used, the atomicity of the operation depends solely on the target data source. + * + * Overwrites data in a table matched by a set of filters. Rows matching all of the filters will be + * deleted and rows in the output data set are appended. + * + * This plan is used to implement SaveMode.Overwrite. The behavior of SaveMode.Overwrite is to + * truncate the table -- delete all rows -- and append the output data set. This uses the filter + * AlwaysTrue to delete all rows. + */ +case class OverwriteByExpressionExecV1( + table: Table, + writeBuilder: V1WriteBuilder, + deleteWhere: Array[Filter], + plan: LogicalPlan) extends V1FallbackWriters { + + private def isTruncate(filters: Array[Filter]): Boolean = { + filters.length == 1 && filters(0).isInstanceOf[AlwaysTrue] + } + + override protected def doExecute(): RDD[InternalRow] = { + writeBuilder match { + case builder: SupportsTruncate if isTruncate(deleteWhere) => + writeWithV1(builder.truncate().asV1Builder.buildForV1Write()) Review comment: Update: if the builder can't be passed in, then `asV1Builder` is still needed. ---------------------------------------------------------------- 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] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
