dongjoon-hyun commented on a change in pull request #24005: [SPARK-27085][SQL] Migrate CSV to File Data Source V2 URL: https://github.com/apache/spark/pull/24005#discussion_r268044726
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/csv/CSVScan.scala ########## @@ -0,0 +1,85 @@ +/* + * 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.csv + +import scala.collection.JavaConverters._ + +import org.apache.hadoop.fs.Path + +import org.apache.spark.sql.{AnalysisException, SparkSession} +import org.apache.spark.sql.catalyst.csv.CSVOptions +import org.apache.spark.sql.catalyst.expressions.ExprUtils +import org.apache.spark.sql.execution.datasources.PartitioningAwareFileIndex +import org.apache.spark.sql.execution.datasources.csv.CSVDataSource +import org.apache.spark.sql.execution.datasources.v2.TextBasedFileScan +import org.apache.spark.sql.sources.v2.reader.PartitionReaderFactory +import org.apache.spark.sql.types.{DataType, StructType} +import org.apache.spark.sql.util.CaseInsensitiveStringMap +import org.apache.spark.util.SerializableConfiguration + +case class CSVScan( + sparkSession: SparkSession, + fileIndex: PartitioningAwareFileIndex, + dataSchema: StructType, + readSchema: StructType, + options: CaseInsensitiveStringMap) + extends TextBasedFileScan(sparkSession, fileIndex, readSchema, options) { + + private val optionsAsScala = options.asScala.toMap + private lazy val parsedOptions: CSVOptions = new CSVOptions( + optionsAsScala, + columnPruning = sparkSession.sessionState.conf.csvColumnPruning, + sparkSession.sessionState.conf.sessionLocalTimeZone, + sparkSession.sessionState.conf.columnNameOfCorruptRecord) + + override def isSplitable(path: Path): Boolean = { + CSVDataSource(parsedOptions).isSplitable && super.isSplitable(path) + } + + override def createReaderFactory(): PartitionReaderFactory = { + // Check a field requirement for corrupt records here to throw an exception in a driver side + ExprUtils.verifyColumnNameOfCorruptRecord(dataSchema, parsedOptions.columnNameOfCorruptRecord) + + if (readSchema.length == 1 && + readSchema.head.name == parsedOptions.columnNameOfCorruptRecord) { + throw new AnalysisException( + "Since Spark 2.3, the queries from raw JSON/CSV files are disallowed when the\n" + + "referenced columns only include the internal corrupt record column\n" + + s"(named _corrupt_record by default). For example:\n" + Review comment: I know this is a copied one. But, shall we remove `s` from `s"`? ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
