Github user srowen commented on a diff in the pull request: https://github.com/apache/spark/pull/14731#discussion_r75944182 --- Diff: streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala --- @@ -196,29 +192,33 @@ class FileInputDStream[K, V, F <: NewInputFormat[K, V]]( logDebug(s"Getting new files for time $currentTime, " + s"ignoring files older than $modTimeIgnoreThreshold") - val newFileFilter = new PathFilter { - def accept(path: Path): Boolean = isNewFile(path, currentTime, modTimeIgnoreThreshold) - } - val directoryFilter = new PathFilter { - override def accept(path: Path): Boolean = fs.getFileStatus(path).isDirectory + val directories = if (SparkHadoopUtil.get.isGlobPath(directoryPath)) { + fs.globStatus(directoryPath) + .filter(_.isDirectory) + .map(_.getPath) + } else { + List(directoryPath).toArray --- End diff -- Just `Array(directoryPath)`?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org