rdblue commented on a change in pull request #1947: URL: https://github.com/apache/iceberg/pull/1947#discussion_r558714187
########## File path: spark3-extensions/src/main/scala/org/apache/spark/sql/catalyst/utils/PlanHelper.scala ########## @@ -0,0 +1,87 @@ +/* + * 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.utils + +import java.util.UUID +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeReference, PredicateHelper} +import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, DynamicFileFilter, LogicalPlan} +import org.apache.spark.sql.connector.catalog.Table +import org.apache.spark.sql.connector.iceberg.read.SupportsFileFilter +import org.apache.spark.sql.connector.iceberg.write.MergeBuilder +import org.apache.spark.sql.connector.write.{LogicalWriteInfo, LogicalWriteInfoImpl} +import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2ScanRelation} +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap + +trait PlanHelper extends PredicateHelper { + val FILE_NAME_COL = "_file" + val ROW_POS_COL = "_pos" + + def buildScanPlan(table: Table, + output: Seq[AttributeReference], + mergeBuilder: MergeBuilder, + prunedTargetPlan: LogicalPlan): LogicalPlan = { + + val scanBuilder = mergeBuilder.asScanBuilder + val scan = scanBuilder.build() + val scanRelation = DataSourceV2ScanRelation(table, scan, toOutputAttrs(scan.readSchema(), output)) + + scan match { + case filterable: SupportsFileFilter => + val matchingFilePlan = buildFileFilterPlan(prunedTargetPlan) + val dynamicFileFilter = DynamicFileFilter(scanRelation, matchingFilePlan, filterable) + dynamicFileFilter + case _ => + scanRelation + } + } + + private def buildFileFilterPlan(prunedTargetPlan: LogicalPlan): LogicalPlan = { Review comment: I think that this will require a reference to the target table because `_file` needs to come from the target table and not the source table. Right now it works because the target table is the only one with `_file` defined, but I think we should plan on selecting the right column if there are duplicates. If I were to define a column `_file` in the source data, it may not work. ---------------------------------------------------------------- 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]
