Hisoka-X commented on code in PR #42979:
URL: https://github.com/apache/spark/pull/42979#discussion_r1353811718
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/csv/CSVDataSource.scala:
##########
@@ -190,12 +191,19 @@ object MultiLineCSVDataSource extends CSVDataSource {
parsedOptions: CSVOptions): StructType = {
val csv = createBaseRdd(sparkSession, inputPaths, parsedOptions)
csv.flatMap { lines =>
- val path = new Path(lines.getPath())
- UnivocityParser.tokenizeStream(
-
CodecStreams.createInputStreamWithCloseResource(lines.getConfiguration, path),
- shouldDropHeader = false,
- new CsvParser(parsedOptions.asParserSettings),
- encoding = parsedOptions.charset)
+ try {
+ val path = new Path(lines.getPath())
+ UnivocityParser.tokenizeStream(
+
CodecStreams.createInputStreamWithCloseResource(lines.getConfiguration, path),
+ shouldDropHeader = false,
+ new CsvParser(parsedOptions.asParserSettings),
+ encoding = parsedOptions.charset)
+ } catch {
+ case e @ (_: RuntimeException | _: IOException) if
parsedOptions.ignoreCorruptFiles =>
+ logWarning(
+ s"Skipped the rest of the content in the corrupted file:
${lines.getPath()}", e)
Review Comment:
Addressed.
--
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]
