Github user liancheng commented on a diff in the pull request: https://github.com/apache/spark/pull/12153#discussion_r58720668 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/sources/interfaces.scala --- @@ -620,17 +621,28 @@ class HDFSFileCatalog( if (paths.length >= sqlContext.conf.parallelPartitionDiscoveryThreshold) { HadoopFsRelation.listLeafFilesInParallel(paths, hadoopConf, sqlContext.sparkContext) } else { - val statuses = paths.flatMap { path => + val statuses: Seq[FileStatus] = paths.flatMap { path => val fs = path.getFileSystem(hadoopConf) logInfo(s"Listing $path on driver") // Dummy jobconf to get to the pathFilter defined in configuration - val jobConf = new JobConf(hadoopConf, this.getClass()) + val jobConf = new JobConf(hadoopConf, this.getClass) val pathFilter = FileInputFormat.getInputPathFilter(jobConf) - if (pathFilter != null) { + val statuses = if (pathFilter != null) { Try(fs.listStatus(path, pathFilter)).getOrElse(Array.empty) } else { Try(fs.listStatus(path)).getOrElse(Array.empty) } + + fs match { + case _: S3FileSystem => --- End diff -- Thanks, made corresponding changes and added comments.
--- 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