jubins commented on code in PR #56581:
URL: https://github.com/apache/spark/pull/56581#discussion_r3438645628
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala:
##########
@@ -146,9 +155,33 @@ class CSVHeaderChecker(
// be not extracted.
if (options.headerFlag && isStartOfFile) {
CSVExprUtils.extractHeader(lines, options).foreach { header =>
- checkHeaderColumnNames(tokenizer.parseLine(header))
+ val tokens = try {
+ tokenizer.parseLine(header)
+ } catch {
+ // scalastyle:off line.size.limit
+ case e: TextParsingException if
e.getCause.isInstanceOf[ArrayIndexOutOfBoundsException] =>
+ // scalastyle:on line.size.limit
+ throw malformedCsvHeaderRecord(e, header)
+ case e: ArrayIndexOutOfBoundsException =>
+ throw malformedCsvHeaderRecord(e, header)
+ }
+ checkHeaderColumnNames(tokens)
}
}
setHeaderForSingleVariantColumn.foreach(f => f(headerColumnNames))
}
+
+ // scalastyle:off line.size.limit
+ private def malformedCsvHeaderRecord(cause: Throwable, badRecord: String):
SparkRuntimeException = {
Review Comment:
done, widened `malformedCsvRecord` in `UnivocityParser to private[csv]` and
replaced all three call sites with `UnivocityParser.malformedCsvRecord(...)`
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
