HeartSaVioR commented on a change in pull request #22952: [SPARK-20568][SS]
Provide option to clean up completed files in streaming query
URL: https://github.com/apache/spark/pull/22952#discussion_r256248107
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/FileStreamSource.scala
##########
@@ -329,4 +350,129 @@ object FileStreamSource {
def size: Int = map.size()
}
+
+ private[sql] class FileStreamSourceCleaner(
+ fileSystem: FileSystem,
+ sourcePath: Path,
+ baseArchivePathString: Option[String]) extends Logging {
+
+ private val sourceGlobFilters: Seq[GlobFilter] =
buildSourceGlobFilters(sourcePath)
+
+ private val baseArchivePath: Option[Path] = baseArchivePathString.map(new
Path(_))
+
+ def archive(entry: FileEntry): Unit = {
+ require(baseArchivePath.isDefined)
+
+ val curPath = new Path(new URI(entry.path))
+ val curPathUri = curPath.toUri
+
+ val newPath = buildArchiveFilePath(curPathUri)
+
+ if (isArchiveFileMatchedAgainstSourcePattern(newPath)) {
+ logWarning(s"Fail to move $curPath to $newPath - destination matches "
+
+ s"to source path/pattern. Skip moving file.")
+ } else {
+ doArchive(curPath, newPath)
+ }
+ }
+
+ def remove(entry: FileEntry): Unit = {
Review comment:
Yeah sounds better for consistency. Will address.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
