[
https://issues.apache.org/jira/browse/SPARK-20568?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16717094#comment-16717094
]
ASF GitHub Bot commented on SPARK-20568:
----------------------------------------
gaborgsomogyi 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_r240561879
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
##########
@@ -1494,6 +1512,287 @@ class FileStreamSourceSuite extends
FileStreamSourceTest {
newSource.getBatch(None, FileStreamSourceOffset(1))
}
}
+
+ test("remove completed files when remove option is enabled") {
+ def assertFileIsRemoved(files: Array[String], fileName: String): Unit = {
+ assert(!files.exists(_.startsWith(fileName)))
+ }
+
+ def assertFileIsNotRemoved(files: Array[String], fileName: String): Unit =
{
+ assert(files.exists(_.startsWith(fileName)))
+ }
+
+ withTempDirs { case (src, tmp) =>
+ withSQLConf(
+ SQLConf.FILE_SOURCE_LOG_COMPACT_INTERVAL.key -> "2",
+ // Force deleting the old logs
+ SQLConf.FILE_SOURCE_LOG_CLEANUP_DELAY.key -> "1"
+ ) {
+ val option = Map("latestFirst" -> "false", "maxFilesPerTrigger" -> "1",
+ "cleanSource" -> "delete")
+
+ val fileStream = createFileStream("text", src.getCanonicalPath,
options = option)
+ val filtered = fileStream.filter($"value" contains "keep")
+
+ testStream(filtered)(
+ AddTextFileData("keep1", src, tmp, tmpFilePrefix = "keep1"),
+ CheckAnswer("keep1"),
+ AssertOnQuery("input file removed") { _: StreamExecution =>
+ // it doesn't rename any file yet
+ assertFileIsNotRemoved(src.list(), "keep1")
+ true
+ },
+ AddTextFileData("keep2", src, tmp, tmpFilePrefix = "ke ep2 %"),
+ CheckAnswer("keep1", "keep2"),
+ AssertOnQuery("input file removed") { _: StreamExecution =>
+ val files = src.list()
+
+ // it renames input file for first batch, but not for second batch
yet
+ assertFileIsRemoved(files, "keep1")
+ assertFileIsNotRemoved(files, "ke ep2 %")
+
+ true
+ },
+ AddTextFileData("keep3", src, tmp, tmpFilePrefix = "keep3"),
+ CheckAnswer("keep1", "keep2", "keep3"),
+ AssertOnQuery("input file renamed") { _: StreamExecution =>
+ val files = src.list()
+
+ // it renames input file for second batch, but not third batch yet
+ assertFileIsRemoved(files, "ke ep2 %")
+ assertFileIsNotRemoved(files, "keep3")
+
+ true
+ }
+ )
+ }
+ }
+ }
+
+ test("move completed files to archive directory when archive option is
enabled") {
+
+ withThreeTempDirs { case (src, tmp, archiveDir) =>
+ withSQLConf(
+ SQLConf.FILE_SOURCE_LOG_COMPACT_INTERVAL.key -> "2",
+ // Force deleting the old logs
+ SQLConf.FILE_SOURCE_LOG_CLEANUP_DELAY.key -> "1"
+ ) {
+ val option = Map("latestFirst" -> "false", "maxFilesPerTrigger" -> "1",
+ "cleanSource" -> "archive", "sourceArchiveDir" ->
archiveDir.getAbsolutePath)
+
+ val fileStream = createFileStream("text",
s"${src.getCanonicalPath}/*/*",
+ options = option)
+ val filtered = fileStream.filter($"value" contains "keep")
+
+ // src/k %1
+ // file: src/k1 %1/keep1
+ val dirForKeep1 = new File(src, "k %1")
+ // src/k1/k 2
+ // file: src/k1/k 2/keep2
Review comment:
Nit: I think this is `file: src/k1 %1/k 2/keep2`
----------------------------------------------------------------
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:
us...@infra.apache.org
> Delete files after processing in structured streaming
> -----------------------------------------------------
>
> Key: SPARK-20568
> URL: https://issues.apache.org/jira/browse/SPARK-20568
> Project: Spark
> Issue Type: New Feature
> Components: Structured Streaming
> Affects Versions: 2.1.0, 2.2.1
> Reporter: Saul Shanabrook
> Priority: Major
>
> It would be great to be able to delete files after processing them with
> structured streaming.
> For example, I am reading in a bunch of JSON files and converting them into
> Parquet. If the JSON files are not deleted after they are processed, it
> quickly fills up my hard drive. I originally [posted this on Stack
> Overflow|http://stackoverflow.com/q/43671757/907060] and was recommended to
> make a feature request for it.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
