Github user zhzhan commented on a diff in the pull request: https://github.com/apache/spark/pull/16068#discussion_r91026585 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUDFSuite.scala --- @@ -487,6 +488,52 @@ 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}'") + withTempView("inputTable") { + val testData = spark.sparkContext.parallelize( + (0 until 10) map (x => IntegerCaseClass(1)), 2).toDF() + testData.createOrReplaceTempView("inputTable") + // Distribute all rows to one partition (all rows have the same content), --- End diff -- @cloud-fan Thanks for the review. Because all rows only contains IntegerCaseClass(1), RepartitionByExpression will assign all rows to one partition, which has 10 records.
--- 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