aokolnychyi commented on a change in pull request #1955: URL: https://github.com/apache/iceberg/pull/1955#discussion_r546633194
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/ExtendedScanRelation.scala ########## @@ -0,0 +1,29 @@ +/* + * 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.catalyst.plans.logical + +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.execution.datasources.v2.DataSourceV2ScanRelation + +case class ExtendedScanRelation(relation: DataSourceV2ScanRelation) extends LogicalPlan { Review comment: I get the intention here now. I did a quick look and see that Spark injects the extended planner strategies before the data source V2 strategy. That got me thinking that we can get rid of this extra logical plan and just use the scan node directly and apply the new logic only if we have a scan that implements `SupportsFileFilter`. ``` case PhysicalOperation(project, filters, DataSourceV2ScanRelation(_, scan: SupportsFileFilter, output)) => // projection and filters were already pushed down in the optimizer. // this uses PhysicalOperation to get the projection and ensure that if the batch scan does // not support columnar, a projection is added to convert the rows to UnsafeRow. val batchExec = ExtendedBatchScanExec(output, scan) withProjectAndFilter(project, filters, batchExec, !batchExec.supportsColumnar) :: Nil .... private def withProjectAndFilter( project: Seq[NamedExpression], filters: Seq[Expression], scan: LeafExecNode, needsUnsafeConversion: Boolean): SparkPlan = { val filterCondition = filters.reduceLeftOption(And) val withFilter = filterCondition.map(FilterExec(_, scan)).getOrElse(scan) if (withFilter.output != project || needsUnsafeConversion) { ProjectExec(project, withFilter) } else { withFilter } } ``` This also takes care of adding a projection if 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
