AnishMahto commented on code in PR #55836: URL: https://github.com/apache/spark/pull/55836#discussion_r3236107859
########## sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/ChangeArgs.scala: ########## @@ -0,0 +1,90 @@ +/* + * 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.pipelines.autocdc + +import org.apache.spark.sql.{AnalysisException, Column} +import org.apache.spark.sql.types.StructType + +sealed trait ColumnSelection +object ColumnSelection { + type ColumnList = Seq[String] + case class IncludeColumns(columns: ColumnList) extends ColumnSelection + case class ExcludeColumns(columns: ColumnList) extends ColumnSelection + + /** + * Applies [[ColumnSelection]] to a [[StructType]] and returns the filtered schema. + * Field names are matched exactly. Field order follows the original schema (filtered in place). + */ + def applyToSchema(schema: StructType, columnSelection: Option[ColumnSelection]): StructType = + columnSelection match { + case None => + // A none column selection is interpreted as a no-op. + schema + case Some(IncludeColumns(includeColumns)) => + validateColumnsExistInSchema(columns = includeColumns, schema = schema) Review Comment: Wouldn't really matter IMO, validation here needs to specifically do a contains check on the schema columns not the other way around. Regardless of whether we use set/seq for the includeColumns, we'd need to loop through all of them (even if we did a set bijection). -- 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]
