Github user jiangxb1987 commented on a diff in the pull request:
https://github.com/apache/spark/pull/18235#discussion_r124948820
--- Diff: core/src/main/scala/org/apache/spark/deploy/SparkSubmit.scala ---
@@ -841,36 +845,132 @@ object SparkSubmit extends CommandLineUtils {
* Download a list of remote files to temp local files. If the file is
local, the original file
* will be returned.
* @param fileList A comma separated file list.
+ * @param targetDir A temporary directory for which downloaded files
+ * @param sparkProperties Spark properties
* @return A comma separated local files list.
*/
private[deploy] def downloadFileList(
fileList: String,
+ targetDir: File,
+ sparkProperties: Map[String, String],
hadoopConf: HadoopConfiguration): String = {
require(fileList != null, "fileList cannot be null.")
- fileList.split(",").map(downloadFile(_, hadoopConf)).mkString(",")
+ fileList.split(",")
+ .map(downloadFile(_, targetDir, sparkProperties, hadoopConf))
+ .mkString(",")
}
/**
* Download a file from the remote to a local temporary directory. If
the input path points to
* a local path, returns it with no operation.
+ * @param path A file path from where the files will be downloaded.
+ * @param targetDir A temporary directory for which downloaded files
+ * @param sparkProperties Spark properties
+ * @return A comma separated local files list.
*/
- private[deploy] def downloadFile(path: String, hadoopConf:
HadoopConfiguration): String = {
+ private[deploy] def downloadFile(
+ path: String,
+ targetDir: File,
+ sparkProperties: Map[String, String],
+ hadoopConf: HadoopConfiguration): String = {
require(path != null, "path cannot be null.")
val uri = Utils.resolveURI(path)
uri.getScheme match {
- case "file" | "local" =>
- path
+ case "file" | "local" => path
+ case "http" | "https" | "ftp" =>
+ val uc = uri.toURL.openConnection()
+ uc match {
+ case https: HttpsURLConnection =>
+ val trustStore = sparkProperties.get("spark.ssl.fs.trustStore")
--- End diff --
Should we make this a common util?
---
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
