viirya commented on a change in pull request #33763:
URL: https://github.com/apache/spark/pull/33763#discussion_r699045368
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/streaming/FileStreamSourceSuite.scala
##########
@@ -1304,6 +1304,140 @@ class FileStreamSourceSuite extends
FileStreamSourceTest {
}
}
+ test("SPARK-36533: Trigger.AvailableNow") {
+ withTempDirs { (src, target) =>
+ val checkpoint = new File(target, "chk").getCanonicalPath
+ val targetDir = new File(target, "data").getCanonicalPath
+ var lastFileModTime: Option[Long] = None
+
+ /** Create a text file with a single data item */
+ def createFile(data: Int): File = {
+ val file = stringToFile(new File(src, s"$data.txt"), data.toString)
+ if (lastFileModTime.nonEmpty) file.setLastModified(lastFileModTime.get
+ 1000)
+ lastFileModTime = Some(file.lastModified)
+ file
+ }
+
+ createFile(1)
+ createFile(2)
+ createFile(3)
+
+ // Set up a query to read text files one at a time
+ val df = spark
+ .readStream
+ .option("maxFilesPerTrigger", 1)
+ .text(src.getCanonicalPath)
+
+ def startQuery(): StreamingQuery = {
+ df.writeStream
+ .format("parquet")
+ .trigger(Trigger.AvailableNow)
+ .option("checkpointLocation", checkpoint)
+ .start(targetDir)
+ }
+ val q = startQuery()
+
+ try {
Review comment:
Shouldn't we add more offsets `createFile` here after latest offset was
fetched into the source? So we can verify that we only process all available at
the beginning of the query?
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
