HeartSaVioR commented on code in PR #38503:
URL: https://github.com/apache/spark/pull/38503#discussion_r1021172211
##########
sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsInPandasWithStateSuite.scala:
##########
@@ -240,25 +240,30 @@ class FlatMapGroupsInPandasWithStateSuite extends
StateStoreMetricsTest {
.groupBy("key")
.count()
- testStream(result, Complete)(
- AddData(inputData, "a"),
- CheckNewAnswer(("a", 1)),
- AddData(inputData, "a", "b"),
- // mapGroups generates ("a", "2"), ("b", "1"); so increases counts of a
and b by 1
- CheckNewAnswer(("a", 2), ("b", 1)),
- StopStream,
- StartStream(),
- AddData(inputData, "a", "b"),
- // mapGroups should remove state for "a" and generate ("a", "-1"), ("b",
"2") ;
- // so increment a and b by 1
- CheckNewAnswer(("a", 3), ("b", 2)),
- StopStream,
- StartStream(),
- AddData(inputData, "a", "c"),
- // mapGroups should recreate state for "a" and generate ("a", "1"),
("c", "1") ;
- // so increment a and c by 1
- CheckNewAnswer(("a", 4), ("b", 2), ("c", 1))
- )
+ // As of [SPARK-40940], multiple state operator with Complete mode is
disabled by default
+ val exp = intercept[AnalysisException] {
Review Comment:
(DISCLAIMER: I don't like complete mode which complicates things.)
See aggregation closely - it does not leverage event time, hence it doesn't
trigger technical limit of the output of flatMapGroupsWithState.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
