gengliangwang commented on a change in pull request #29959:
URL: https://github.com/apache/spark/pull/29959#discussion_r556432426
##########
File path: core/src/main/scala/org/apache/spark/util/HadoopFSUtils.scala
##########
@@ -245,27 +208,18 @@ private[spark] object HadoopFSUtils extends Logging {
Array.empty[FileStatus]
}
- def doFilter(statuses: Array[FileStatus]) = filterFun match {
- case Some(shouldFilterOut) =>
- statuses.filterNot(status => shouldFilterOut(status.getPath.getName))
- case None =>
- statuses
- }
-
- val filteredStatuses = doFilter(statuses)
val allLeafStatuses = {
- val (dirs, topLevelFiles) = filteredStatuses.partition(_.isDirectory)
+ val (dirs, topLevelFiles) = statuses.partition(_.isDirectory)
Review comment:
@sunchao the `dirs` here may contain hidden directories. We still need
to filter them before listing leaf files.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
