HeartSaVioR commented on code in PR #44688:
URL: https://github.com/apache/spark/pull/44688#discussion_r1452013986
##########
sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingDeduplicationWithinWatermarkSuite.scala:
##########
@@ -199,4 +199,27 @@ class StreamingDeduplicationWithinWatermarkSuite extends
StateStoreMetricsTest {
)
}
}
+
+ test("SPARK-46676: canonicalization of
StreamingDeduplicateWithinWatermarkExec should work") {
+ withTempDir { checkpoint =>
+ val dedupeInputData = MemoryStream[(String, Int)]
+ val dedupe = dedupeInputData.toDS()
+ .withColumn("eventTime", timestamp_seconds($"_2"))
+ .withWatermark("eventTime", "10 second")
+ .dropDuplicatesWithinWatermark("_1")
+ .select($"_1", $"eventTime".cast("long").as[Long])
+
+ testStream(dedupe, Append)(
+ StartStream(checkpointLocation = checkpoint.getCanonicalPath),
+
Review Comment:
Good point.
--
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]
