ulysses-you commented on a change in pull request #34568: URL: https://github.com/apache/spark/pull/34568#discussion_r808663145
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/V1Writes.scala ########## @@ -0,0 +1,148 @@ +/* + * 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 + +import org.apache.spark.sql.catalyst.catalog.BucketSpec +import org.apache.spark.sql.catalyst.expressions.{Ascending, Attribute, AttributeSet, BitwiseAnd, HiveHash, Literal, Pmod, SortOrder} +import org.apache.spark.sql.catalyst.plans.logical.{LogicalPlan, Sort} +import org.apache.spark.sql.catalyst.plans.physical.HashPartitioning +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.execution.command.DataWritingCommand +import org.apache.spark.sql.internal.SQLConf + +/** + * V1 write includes both datasoruce and hive, that requires a specific ordering of data. + * It should be resolved by [[V1Writes]]. + * + * TODO(SPARK-37333): Specify the required distribution at V1Write + */ +trait V1Write extends DataWritingCommand with V1WritesHelper { + def partitionColumns: Seq[Attribute] = Seq.empty + def numStaticPartitions: Int = 0 + def bucketSpec: Option[BucketSpec] = None + def options: Map[String, String] = Map.empty + + final def requiredOrdering: Seq[SortOrder] = { + getSortOrder( + outputColumns, + partitionColumns, + numStaticPartitions, + bucketSpec, + options) + } +} + +/** + * A rule that makes sure the v1 write requirement, e.g. requiredOrdering + */ +object V1Writes extends Rule[LogicalPlan] with V1WritesHelper { + override def apply(plan: LogicalPlan): LogicalPlan = plan match { + case write: V1Write => + val partitionSet = AttributeSet(write.partitionColumns) + val dataColumns = write.outputColumns.filterNot(partitionSet.contains) + val sortColumns = getBucketSortColumns(write.bucketSpec, dataColumns) + val newQuery = prepareQuery(write.query, write.requiredOrdering, sortColumns) + write.withNewChildren(newQuery :: Nil) + + case _ => plan + } +} + +trait V1WritesHelper { Review comment: The idea of the `V1WritesHelper` is from the `AdaptiveSparkPlanHelper` which also contains some util methods. And there are many place in sql use the helper even if they are not stateful. Personally, I don't have a big option about utility and helper. -- 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]
