Github user xuanyuanking commented on a diff in the pull request:
https://github.com/apache/spark/pull/22326#discussion_r214807200
--- 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"))
--- End diff --
ditto, the correct test is `df = left.join(right, f("a", "b"))`.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
