Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/16928#discussion_r102366908 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVFileFormat.scala --- @@ -96,31 +96,44 @@ class CSVFileFormat extends TextBasedFileFormat with DataSourceRegister { filters: Seq[Filter], options: Map[String, String], hadoopConf: Configuration): (PartitionedFile) => Iterator[InternalRow] = { - val csvOptions = new CSVOptions(options, sparkSession.sessionState.conf.sessionLocalTimeZone) - + CSVUtils.verifySchema(dataSchema) val broadcastedHadoopConf = sparkSession.sparkContext.broadcast(new SerializableConfiguration(hadoopConf)) + val parsedOptions = new CSVOptions( + options, + sparkSession.sessionState.conf.sessionLocalTimeZone, + sparkSession.sessionState.conf.columnNameOfCorruptRecord) + + // Check a field requirement for corrupt records here to throw an exception in a driver side + dataSchema.getFieldIndex(parsedOptions.columnNameOfCorruptRecord).map { corruptFieldIndex => + val f = dataSchema(corruptFieldIndex) + if (f.dataType != StringType || !f.nullable) { --- End diff -- This check seems duplicated with https://github.com/apache/spark/pull/16928/files/4eed4a4bea927c6365dac2e2734c895a0a1a0026#diff-d19881aceddcaa5c60620fdcda99b4c4R51
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org