sunchao commented on a change in pull request #35657: URL: https://github.com/apache/spark/pull/35657#discussion_r827171559
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/V2ScanPartitioning.scala ########## @@ -0,0 +1,50 @@ +/* + * 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.SQLConfHelper +import org.apache.spark.sql.catalyst.expressions.V2ExpressionUtils +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.FunctionCatalog +import org.apache.spark.sql.connector.read.SupportsReportPartitioning +import org.apache.spark.sql.connector.read.partitioning.{HashPartitioning, UnknownPartitioning} +import org.apache.spark.util.collection.Utils.sequenceToOption + +/** + * Extract [[DataSourceV2ScanRelation]] from the input logical plan, convert any V2 partitioning + * reported by data sources to their catalyst counterparts. Then, annotate the plan with the result. + */ +object V2ScanPartitioning extends Rule[LogicalPlan] with SQLConfHelper { + override def apply(plan: LogicalPlan): LogicalPlan = plan transformDown { + case d @ DataSourceV2ScanRelation(relation, scan: SupportsReportPartitioning, _, _) => + val funCatalogOpt = relation.catalog.flatMap { + case c: FunctionCatalog => Some(c) + case _ => None + } + + val catalystClustering = scan.outputPartitioning() match { + case hp: HashPartitioning => sequenceToOption(hp.clustering().map( + V2ExpressionUtils.toCatalyst(_, relation, funCatalogOpt))) + case _: UnknownPartitioning => None + case p => throw new IllegalArgumentException("Unsupported data source V2 partitioning " + + "type: " + p.getClass.getSimpleName) + } + + d.copy(clustering = catalystClustering) Review comment: Since we need a way to pass clustering expressions down to `BatchScanExec`. You can see how it is used in `DataSourceV2Strategy`. -- 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]
