xuanyuanking commented on a change in pull request #32767:
URL: https://github.com/apache/spark/pull/32767#discussion_r656921453
##########
File path: core/src/main/scala/org/apache/spark/util/Utils.scala
##########
@@ -3084,6 +3085,35 @@ private[spark] object Utils extends Logging {
conf.get(config.STORAGE_BLOCKMANAGER_HEARTBEAT_TIMEOUT)
.getOrElse(Utils.timeStringAsMs(s"${conf.get(Network.NETWORK_TIMEOUT)}s"))
}
+
+ /** Decompress a zip file into a local dir. File names are read from the zip
file. */
+ def unzipFromFile(fs: FileSystem, dfsZipFile: Path, localDir: File):
Seq[File] = {
+ val files = new mutable.ArrayBuffer[File]()
+ val in = new ZipInputStream(fs.open(dfsZipFile))
+ var out: OutputStream = null
+ try {
+ var entry = in.getNextEntry()
+ while (entry != null) {
+ if (!entry.isDirectory) {
+ val fileName =
localDir.toPath.resolve(entry.getName).getFileName.toString
+ val outFile = new File(localDir, fileName)
+ files += outFile
+ out = new FileOutputStream(outFile)
+ IOUtils.copy(in, out)
+ out.close()
+ in.closeEntry()
+ }
+ entry = in.getNextEntry()
+ }
+ in.close() // so that any error in closing does not get ignored
+ logInfo(s"Unzipped from $dfsZipFile\n\t${files.mkString("\n\t")}")
+ } finally {
+ // Close everything no matter what happened
+ IOUtils.closeQuietly(in)
+ IOUtils.closeQuietly(out)
+ }
Review comment:
Yes, we rely on the caller side to address any exceptions. Javadoc added
as well.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
