wayneguow commented on code in PR #47539: URL: https://github.com/apache/spark/pull/47539#discussion_r1702432161
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/xml/XmlScan.scala: ########## @@ -0,0 +1,96 @@ +/* + * 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.xml + +import scala.jdk.CollectionConverters._ + +import org.apache.hadoop.fs.Path + +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.expressions.{Expression, ExprUtils} +import org.apache.spark.sql.catalyst.util.CaseInsensitiveMap +import org.apache.spark.sql.catalyst.xml.XmlOptions +import org.apache.spark.sql.connector.read.PartitionReaderFactory +import org.apache.spark.sql.errors.QueryCompilationErrors +import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex +import org.apache.spark.sql.execution.datasources.v2.TextBasedFileScan +import org.apache.spark.sql.execution.datasources.xml.XmlDataSource +import org.apache.spark.sql.sources.Filter +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.CaseInsensitiveStringMap +import org.apache.spark.util.ArrayImplicits._ +import org.apache.spark.util.SerializableConfiguration + +case class XmlScan( + sparkSession: SparkSession, + fileIndex: PartitioningAwareFileIndex, + dataSchema: StructType, + readDataSchema: StructType, + readPartitionSchema: StructType, + options: CaseInsensitiveStringMap, + pushedFilters: Array[Filter], + partitionFilters: Seq[Expression] = Seq.empty, + dataFilters: Seq[Expression] = Seq.empty) + extends TextBasedFileScan(sparkSession, options) { + + private val xmlOptions = new XmlOptions( + CaseInsensitiveMap(options.asScala.toMap), + sparkSession.sessionState.conf.sessionLocalTimeZone, + sparkSession.sessionState.conf.columnNameOfCorruptRecord, + true) + + override def isSplitable(path: Path): Boolean = { + XmlDataSource(xmlOptions).isSplitable && super.isSplitable(path) + } + + override def getFileUnSplittableReason(path: Path): String = { + assert(!isSplitable(path)) + if (!super.isSplitable(path)) { + super.getFileUnSplittableReason(path) + } else { + "the xml datasource is set multiLine mode" + } + } + + override def createReaderFactory(): PartitionReaderFactory = { + // Check a field requirement for corrupt records here to throw an exception in a driver side + ExprUtils.verifyColumnNameOfCorruptRecord(dataSchema, xmlOptions.columnNameOfCorruptRecord) + + if (readDataSchema.length == 1 && + readDataSchema.head.name == xmlOptions.columnNameOfCorruptRecord) { + throw QueryCompilationErrors.queryFromRawFilesIncludeCorruptRecordColumnError() + } + val caseSensitiveMap = options.asCaseSensitiveMap.asScala.toMap + // Hadoop Configurations are case sensitive. + val hadoopConf = sparkSession.sessionState.newHadoopConfWithOptions(caseSensitiveMap) + val broadcastedConf = sparkSession.sparkContext.broadcast( + new SerializableConfiguration(hadoopConf)) + // The partition values are already truncated in `FileScan.partitions`. + // We should use `readPartitionSchema` as the partition schema here. + XmlPartitionReaderFactory(sparkSession.sessionState.conf, broadcastedConf, + dataSchema, readDataSchema, readPartitionSchema, xmlOptions, + pushedFilters.toImmutableArraySeq) + } + + override def equals(obj: Any): Boolean = obj match { + case j: XmlScan => super.equals(j) && dataSchema == j.dataSchema && options == j.options && + equivalentFilters(pushedFilters, j.pushedFilters) + case _ => false + } + + override def hashCode(): Int = super.hashCode() +} Review Comment: Since there is no `PushedFilters`, just keep the default method of the parent class. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
