Github user vanzin commented on a diff in the pull request:
https://github.com/apache/spark/pull/18235#discussion_r122503215
--- Diff: core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala ---
@@ -858,19 +844,33 @@ object SparkSubmit extends CommandLineUtils {
require(path != null, "path cannot be null.")
val uri = Utils.resolveURI(path)
uri.getScheme match {
- case "file" | "local" =>
- path
-
+ case "file" | "local" => path
+ case "https" | "http" | "ftp" => path
case _ =>
val fs = FileSystem.get(uri, hadoopConf)
- val tmpFile = new File(Files.createTempDirectory("tmp").toFile,
uri.getPath)
+ val tmpFile = new File(Files.createTempDirectory("tmp").toFile,
new Path(uri).getName)
// scalastyle:off println
printStream.println(s"Downloading ${uri.toString} to
${tmpFile.getAbsolutePath}.")
// scalastyle:on println
fs.copyToLocalFile(new Path(uri), new
Path(tmpFile.getAbsolutePath))
Utils.resolveURI(tmpFile.getAbsolutePath).toString
}
}
+
+ private def resolveGlobPaths(paths: String, hadoopConf:
HadoopConfiguration): String = {
+ require(paths != null, "paths cannot be null.")
+ paths.split(",").filter(_.trim.nonEmpty).flatMap { path =>
--- End diff --
minor, but you should actually trim the strings, not just for filtering
purposes.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
