Github user xuanyuanking commented on a diff in the pull request: https://github.com/apache/spark/pull/22326#discussion_r214806996 --- Diff: python/pyspark/sql/tests.py --- @@ -545,6 +545,15 @@ def test_udf_in_filter_on_top_of_join(self): right = self.spark.createDataFrame([Row(b=1)]) f = udf(lambda a, b: a == b, BooleanType()) df = left.crossJoin(right).filter(f("a", "b")) + + def test_udf_in_join_condition(self): + # regression test for SPARK-25314 + from pyspark.sql.functions import udf + left = self.spark.createDataFrame([Row(a=1)]) + right = self.spark.createDataFrame([Row(b=1)]) + f = udf(lambda a, b: a == b, BooleanType()) + df = left.crossJoin(right).filter(f("a", "b")) + self.assertEqual(df.collect(), [Row(a=1, b=1)]) self.assertEqual(df.collect(), [Row(a=1, b=1)]) --- End diff -- Yep, sorry for the mess here, another commit left on. I'll fix soon, how to cancel the test?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org