Github user lw-lin commented on a diff in the pull request: https://github.com/apache/spark/pull/16987#discussion_r103604050 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala --- @@ -190,32 +190,31 @@ class FileStreamSource( val startTime = System.nanoTime var allFiles: Seq[FileStatus] = null - if (sourceHasMetadata.isEmpty) { - if (FileStreamSink.hasMetadata(Seq(path), hadoopConf)) { - sourceHasMetadata = Some(true) - allFiles = allFilesUsingMetadataLogFileIndex() - } else { - allFiles = allFilesUsingInMemoryFileIndex() - if (allFiles.isEmpty) { - // we still cannot decide + sourceHasMetadata match { --- End diff -- simply switched to `sourceHasMetadata match { case... case ... case ...}` actual diff is quite small
--- 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