Github user vanzin commented on the pull request:
https://github.com/apache/spark/pull/4881#issuecomment-77209251
I tested with this version of `fetchHcfsFile` and my tests pass:
/**
* Fetch a file or directory from a Hadoop-compatible filesystem.
*
* Visible for testing
*/
private[spark] def fetchHcfsFile(
path: Path,
targetDir: File,
fs: FileSystem,
conf: SparkConf,
hadoopConf: Configuration,
fileOverwrite: Boolean,
filename: Option[String] = None): Unit = {
if (!targetDir.exists() && !targetDir.mkdir()) {
throw new IOException(s"Failed to create directory
${targetDir.getPath}")
}
val dest = new File(targetDir, filename.getOrElse(path.getName))
if (fs.isFile(path)) {
val in = fs.open(path)
try {
downloadFile(path.toString, in, dest, fileOverwrite)
} finally {
in.close()
}
} else {
fs.listStatus(path).foreach { fileStatus =>
fetchHcfsFile(fileStatus.getPath(), dest, fs, conf, hadoopConf,
fileOverwrite)
}
}
}
---
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]
