jubins commented on code in PR #56581:
URL: https://github.com/apache/spark/pull/56581#discussion_r3457055261
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/csv/CSVHeaderChecker.scala:
##########
@@ -122,15 +122,26 @@ class CSVHeaderChecker(
def checkHeaderColumnNames(line: String): Unit = {
if (options.headerFlag) {
val parser = new CsvParser(options.asParserSettings)
- checkHeaderColumnNames(parser.parseLine(line))
+ checkHeaderColumnNames(UnivocityParser.parseLine(parser, line))
}
}
// This is currently only used to parse CSV with multiLine mode.
private[csv] def checkHeaderColumnNames(tokenizer:
AbstractParser[CsvParserSettings]): Unit = {
assert(options.multiLine, "This method should be executed with multiLine.")
if (options.headerFlag) {
- val firstRecord = tokenizer.parseNext()
+ val firstRecord = try {
+ tokenizer.parseNext()
+ } catch {
+ // scalastyle:off line.size.limit
+ case e: TextParsingException if
e.getCause.isInstanceOf[ArrayIndexOutOfBoundsException] =>
+ // scalastyle:on line.size.limit
+ // In the multiLine stream path the field appender is reset before
the AIOOBE propagates,
+ // so the record content is unavailable; pass an empty string as the
bad-record marker.
Review Comment:
updated the comment to "use the bounded parsed content when present, empty
string as the fallback", matching the phrasing used in `convertStream`
--
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]
