aokolnychyi commented on a change in pull request #3461: URL: https://github.com/apache/iceberg/pull/3461#discussion_r745142890
########## File path: spark/v3.2/spark-extensions/src/main/scala/org/apache/spark/sql/execution/datasources/v2/ExtendedDistributionAndOrderingUtils.scala ########## @@ -0,0 +1,84 @@ +/* + * 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 org.apache.spark.sql.catalyst.expressions.Expression +import org.apache.spark.sql.catalyst.expressions.ExtendedV2ExpressionUtils.toCatalyst +import org.apache.spark.sql.catalyst.expressions.SortOrder +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.catalyst.plans.logical.RepartitionByExpression +import org.apache.spark.sql.catalyst.plans.logical.Sort +import org.apache.spark.sql.connector.distributions.ClusteredDistribution +import org.apache.spark.sql.connector.distributions.OrderedDistribution +import org.apache.spark.sql.connector.distributions.UnspecifiedDistribution +import org.apache.spark.sql.connector.write.RequiresDistributionAndOrdering +import org.apache.spark.sql.connector.write.Write +import org.apache.spark.sql.errors.QueryCompilationErrors +import org.apache.spark.sql.internal.SQLConf + +/** + * A rule that is inspired by DistributionAndOrderingUtils in Spark but supports Iceberg transforms. + * + * Note that similarly to the original rule in Spark, it does not let AQE pick the number of shuffle + * partitions. See SPARK-34230 for context. + */ +object ExtendedDistributionAndOrderingUtils { + + def prepareQuery(write: Write, query: LogicalPlan, conf: SQLConf): LogicalPlan = write match { + case write: RequiresDistributionAndOrdering => + val numPartitions = write.requiredNumPartitions() + val distribution = write.requiredDistribution match { + case d: OrderedDistribution => d.ordering.map(e => toCatalyst(e, query)) + case d: ClusteredDistribution => d.clustering.map(e => toCatalyst(e, query)) + case _: UnspecifiedDistribution => Array.empty[Expression] + } + + val queryWithDistribution = if (distribution.nonEmpty) { + val finalNumPartitions = if (numPartitions > 0) { + numPartitions + } else { + conf.numShufflePartitions + } + // the conversion to catalyst expressions above produces SortOrder expressions + // for OrderedDistribution and generic expressions for ClusteredDistribution + // this allows RepartitionByExpression to pick either range or hash partitioning + RepartitionByExpression(distribution, query, finalNumPartitions) Review comment: Unfortunately, we cannot do this due to SPARK-34230. I have a small comment at the top of this class. -- 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]
