AnishMahto commented on code in PR #55836: URL: https://github.com/apache/spark/pull/55836#discussion_r3262066979
########## sql/pipelines/src/main/scala/org/apache/spark/sql/pipelines/autocdc/ChangeArgs.scala: ########## @@ -0,0 +1,180 @@ +/* + * 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 java.util.Locale + +import org.apache.spark.sql.{AnalysisException, Column} +import org.apache.spark.sql.catalyst.parser.CatalystSqlParser +import org.apache.spark.sql.catalyst.util.QuotingUtils +import org.apache.spark.sql.types.StructType + +/** + * A single, unqualified column identifier (no nested path or table/alias qualifier). Backticks + * are consumed: "`a.b`" is stored as "a.b" in [[name]]. Use [[name]] for direct schema-fieldName + * comparison and [[quoted]] for APIs that re-parse identifier strings. + */ +case class UnqualifiedColumnName private (name: String) { + def quoted: String = QuotingUtils.quoteIdentifier(name) +} + +object UnqualifiedColumnName { + def apply(input: String): UnqualifiedColumnName = { + val nameParts = CatalystSqlParser.parseMultipartIdentifier(input) + if (nameParts.length != 1) { + throw multipartColumnIdentifierError(input, nameParts) + } + new UnqualifiedColumnName(nameParts.head) + } + + private def multipartColumnIdentifierError( + columnName: String, + nameParts: Seq[String] + ): AnalysisException = + new AnalysisException( + errorClass = "AUTOCDC_MULTIPART_COLUMN_IDENTIFIER", + messageParameters = Map( + "columnName" -> columnName, + "nameParts" -> nameParts.mkString(", ") + ) + ) +} + +sealed trait ColumnSelection +object ColumnSelection { + + case class IncludeColumns(columns: Seq[UnqualifiedColumnName]) extends ColumnSelection + case class ExcludeColumns(columns: Seq[UnqualifiedColumnName]) + extends ColumnSelection + + /** + * Applies [[ColumnSelection]] to a [[StructType]] and returns the filtered schema. Field + * order follows the original schema; filtering happens in place. + */ + def applyToSchema( + schemaName: String, + schema: StructType, + columnSelection: Option[ColumnSelection], + ignoreCase: Boolean): StructType = columnSelection match { + case None => Review Comment: Already exists for `None`: https://github.com/AnishMahto/spark/blob/0126659c5203b7d512ea80d3ecb3cfa83debc0b2/sql/pipelines/src/test/scala/org/apache/spark/sql/pipelines/autocdc/ChangeArgsSuite.scala#L33-L41 I'll add explicit tests for `Some(IncludeColumns(Seq()))` and `Some(ExcludeColumns(Seq()))` too though. -- 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]
