Github user zhzhan commented on a diff in the pull request: https://github.com/apache/spark/pull/16068#discussion_r91570259 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala --- @@ -487,6 +489,26 @@ class HiveUDFSuite extends QueryTest with TestHiveSingleton with SQLTestUtils { assert(count4 == 1) sql("DROP TABLE parquet_tmp") } + + test("Hive Stateful UDF") { + withUserDefinedFunction("statefulUDF" -> true, "statelessUDF" -> true) { + sql(s"CREATE TEMPORARY FUNCTION statefulUDF AS '${classOf[StatefulUDF].getName}'") + sql(s"CREATE TEMPORARY FUNCTION statelessUDF AS '${classOf[StatelessUDF].getName}'") + val testData = spark.range(10).repartition(1) + + // Expected Max(s) is 10 as statefulUDF returns the sequence number starting from 1. + checkAnswer(testData.selectExpr("statefulUDF() as s").agg(max($"s")), Row(10)) + + // Expected Max(s) is 5 as statefulUDF returns the sequence number starting from 1, + // and the data is evenly distributed into 2 partitions. --- End diff -- case logical.Repartition(numPartitions, shuffle, child) => if (shuffle) { ShuffleExchange(RoundRobinPartitioning(numPartitions), planLater(child)) :: Nil } else { execution.CoalesceExec(numPartitions, planLater(child)) :: Nil } case logical.RepartitionByExpression(expressions, child, nPartitions) => exchange.ShuffleExchange(HashPartitioning( expressions, nPartitions.getOrElse(numPartitions)), planLater(child)) :: Nil
--- 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