dongjoon-hyun commented on code in PR #52671:
URL: https://github.com/apache/spark/pull/52671#discussion_r2446143576
##########
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSinkSuite.scala:
##########
@@ -534,10 +535,25 @@ abstract class FileStreamSinkSuite extends StreamTest {
}
import PendingCommitFilesTrackingManifestFileCommitProtocol._
- val outputFileNames = Files.walk(outputDir.toPath).iterator().asScala
- .filter(_.toString.endsWith(".parquet"))
- .map(_.getFileName.toString)
- .toSet
+ import java.nio.file.{Path, _}
+ val outputFileNames = scala.collection.mutable.Set.empty[String]
+ Files.walkFileTree(
+ outputDir.toPath,
+ new SimpleFileVisitor[Path] {
+ override def visitFile(file: Path, attrs: BasicFileAttributes):
FileVisitResult = {
+ val fileName = file.getFileName.toString
+ if (fileName.endsWith(".parquet")) outputFileNames += fileName
+ FileVisitResult.CONTINUE
+ }
+ override def visitFileFailed(file: Path, exc: IOException):
FileVisitResult = {
+ exc match {
+ case _: NoSuchFileException =>
+ FileVisitResult.CONTINUE
Review Comment:
It's okay to ignore the deleted files because those are supposed to be
cleaned up in a success case.
--
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]
