peter-toth commented on code in PR #54330: URL: https://github.com/apache/spark/pull/54330#discussion_r2826743636
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/GroupPartitionsExec.scala: ########## @@ -0,0 +1,220 @@ +/* + * 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.mutable.ArrayBuffer + +import org.apache.spark.Partition +import org.apache.spark.rdd.{CoalescedRDD, PartitionCoalescer, PartitionGroup, RDD} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.plans.physical.{KeyedPartitioning, Partitioning} +import org.apache.spark.sql.catalyst.util.InternalRowComparableWrapper +import org.apache.spark.sql.connector.catalog.functions.Reducer +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.types.DataType + +/** + * Physical operator that groups input partitions by their partition keys. + * + * This operator is used to coalesce partitions from bucketed/partitioned data sources + * where multiple input partitions share the same partition key. It's commonly used in + * storage-partitioned joins to align partitions from different sides of the join. + * + * @param child The child plan providing bucketed/partitioned input + * @param joinKeyPositions Optional projection to select a subset of the partitioning key + * for join compatibility (e.g., when join keys are a subset of + * partition keys) + * @param commonPartitionKeys Optional sequence of expected partition key values and their + * split counts, used for partially clustered data + * @param reducers Optional reducers to apply to partition keys for grouping compatibility + * @param applyPartialClustering Whether to apply partial clustering for skewed data + * @param replicatePartitions Whether to replicate partitions across multiple keys + */ +case class GroupPartitionsExec( + child: SparkPlan, + joinKeyPositions: Option[Seq[Int]] = None, + commonPartitionKeys: Option[Seq[(InternalRow, Int)]] = None, + reducers: Option[Seq[Option[Reducer[_, _]]]] = None, + applyPartialClustering: Boolean = false, + replicatePartitions: Boolean = false + ) extends UnaryExecNode { + + override def outputPartitioning: Partitioning = { + child.outputPartitioning match { + case p: Partitioning with Expression => + p.transform { + case k: KeyedPartitioning => + val projectedExpressions = projectExpressions(k.expressions) + val projectedDataTypes = projectedExpressions.map(_.dataType) + k.copy(expressions = projectedExpressions, + partitionKeys = groupedPartitions.map(_._1), + originalPartitionKeys = projectKeys(k.originalPartitionKeys, projectedDataTypes)) + }.asInstanceOf[Partitioning] + case o => o + } + } + + private def projectExpressions(expressions: Seq[Expression]) = { + joinKeyPositions match { + case Some(projectionPositions) => + projectionPositions.map(expressions) + case _ => expressions + } + } + + private def projectKeys(keys: Seq[InternalRow], dataTypes: Seq[DataType]) = { + joinKeyPositions match { + case Some(projectionPositions) => + keys.map(KeyedPartitioning.projectKey(_, projectionPositions, dataTypes)) + case _ => keys + } + } + + /** + * Extracts the first KeyedPartitioning from the child's output partitioning. + * The child must have a KeyedPartitioning in its partitioning scheme. + */ + lazy val firstKeyedPartitioning = { + child.outputPartitioning.asInstanceOf[Partitioning with Expression].collectFirst { + case k: KeyedPartitioning => k + }.get Review Comment: fixed in https://github.com/apache/spark/pull/54330/commits/d58cafedfd6da01de1a39eb1ac0dc6622f614b21 -- 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]
