Github user HyukjinKwon commented on a diff in the pull request: https://github.com/apache/spark/pull/16928#discussion_r102645418 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/UnivocityParser.scala --- @@ -45,24 +45,41 @@ private[csv] class UnivocityParser( // A `ValueConverter` is responsible for converting the given value to a desired type. private type ValueConverter = String => Any + private val corruptFieldIndex = schema.getFieldIndex(options.columnNameOfCorruptRecord) + corruptFieldIndex.foreach { corrFieldIndex => + require(schema(corrFieldIndex).dataType == StringType) + require(schema(corrFieldIndex).nullable) + } + + private val inputSchema = StructType(schema.filter(_.name != options.columnNameOfCorruptRecord)) --- End diff -- (For example, [this code path](https://github.com/apache/spark/pull/16928/files/c86febe6b018faafa62e0bf6444f8cd4326fb021#diff-d19881aceddcaa5c60620fdcda99b4c4R213) is dependent on the length of the data schema. It drops/adds tokens after comparing the length between data schema and tokens. If we keep the corrupt column, then the schema length would be different with the tokens.)
--- 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