Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/16970#discussion_r102378594 --- Diff: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/analysis/UnsupportedOperationsSuite.scala --- @@ -129,6 +156,33 @@ class UnsupportedOperationsSuite extends SparkFunSuite { outputMode = Complete, expectedMsgs = Seq("(map/flatMap)GroupsWithState")) + assertSupportedInStreamingPlan( + "mapGroupsWithState - mapGroupsWithState on batch relation inside streaming relation", + MapGroupsWithState(null, att, att, Seq(att), Seq(att), att, att, Seq(att), batchRelation), + outputMode = Append + ) + + // Deduplication: Not supported after a streaming aggregation + assertSupportedInStreamingPlan( + "Deduplication - Deduplication on streaming relation before aggregation", + Aggregate( + Seq(attributeWithWatermark), + aggExprs("c"), + Deduplication(Seq(att), streamRelation, streaming = true)), + outputMode = Append) + + assertNotSupportedInStreamingPlan( + "Deduplication - Deduplication on streaming relation after aggregation", + Deduplication(Seq(att), Aggregate(Nil, aggExprs("c"), streamRelation), streaming = true), + outputMode = Complete, + expectedMsgs = Seq("dropDuplicates")) + + assertSupportedInStreamingPlan( + "Deduplication - Deduplication on batch relation inside streaming relation", --- End diff -- nit: inside a streaming query. sounds weird otherwise.
--- 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