Github user maropu commented on a diff in the pull request: https://github.com/apache/spark/pull/16928#discussion_r102653357 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/UnivocityParser.scala --- @@ -202,21 +212,41 @@ private[csv] class UnivocityParser( } numMalformedRecords += 1 None - } else if (options.failFast && schema.length != tokens.length) { + } else if (options.failFast && dataSchema.length != tokens.length) { throw new RuntimeException(s"Malformed line in FAILFAST mode: " + s"${tokens.mkString(options.delimiter.toString)}") } else { - val checkedTokens = if (options.permissive && schema.length > tokens.length) { - tokens ++ new Array[String](schema.length - tokens.length) - } else if (options.permissive && schema.length < tokens.length) { - tokens.take(schema.length) + val checkedTokens = if (options.permissive) { + // If a length of parsed tokens is not equal to expected one, it makes the length the same + // with the expected. If the length is shorter, it adds extra tokens in the tail. + // If longer, it drops extra tokens. + val lengthSafeTokens = if (dataSchema.length > tokens.length) { + tokens ++ new Array[String](dataSchema.length - tokens.length) + } else if (dataSchema.length < tokens.length) { + tokens.take(dataSchema.length) + } else { + tokens + } + + // If we need to handle corrupt fields, it adds an extra token to skip a field for malformed --- End diff -- @HyukjinKwon This fix satisfies your intention? I slightly modified code based on your code.
--- 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