Github user tdas commented on a diff in the pull request:
https://github.com/apache/spark/pull/16251#discussion_r92558907
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
---
@@ -1059,6 +1060,72 @@ class FileStreamSourceSuite extends
FileStreamSourceTest {
val str =
Source.fromFile(getClass.getResource(s"/structured-streaming/$file").toURI).mkString
SerializedOffset(str.trim)
}
+
+ test("FileStreamSource - latestFirst") {
+ withTempDir { src =>
+ // Prepare two files: 1.txt, 2.txt, and make sure they have
different modified time.
+ val f1 = stringToFile(new File(src, "1.txt"), "1")
+ val f2 = stringToFile(new File(src, "2.txt"), "2")
+ eventually(timeout(streamingTimeout)) {
+ f2.setLastModified(System.currentTimeMillis())
+ assert(f1.lastModified < f2.lastModified)
+ }
+
+ // Read oldest files first, so the first batch is "1", and the
second batch is "2".
+ val fileStream = createFileStream(
+ "text",
+ src.getCanonicalPath,
+ options = Map("latestFirst" -> "false", "maxFilesPerTrigger" ->
"1"))
+ val clock = new StreamManualClock()
+ testStream(fileStream)(
+ StartStream(trigger = ProcessingTime(10), triggerClock = clock),
+ AssertOnQuery { _ =>
--- End diff --
why do you need to wait on the manual clock? CheckLastBatch will
automatically wait for the batch to complete?
---
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
