Github user xuanyuanking commented on the issue:
https://github.com/apache/spark/pull/23153
Thanks for the fix from Wenchen,
```
the suites should also construct the dummy python udf from both side.
```
I fix the suite locally, they can be simply modified like:
```
diff --git
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/PullOutPythonUDFInJoinConditionSuite.scala
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/PullOutPythonUDFInJoinConditionSuite.scala
index d3867f2b6b..a0f8ae2fc7 100644
---
a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/PullOutPythonUDFInJoinConditionSuite.scala
+++
b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/PullOutPythonUDFInJoinConditionSuite.scala
@@ -40,13 +40,18 @@ class PullOutPythonUDFInJoinConditionSuite extends
PlanTest {
CheckCartesianProducts) :: Nil
}
- val testRelationLeft = LocalRelation('a.int, 'b.int)
- val testRelationRight = LocalRelation('c.int, 'd.int)
+ val attrA = 'a.int
+ val attrB = 'b.int
+ val attrC = 'c.int
+ val attrD = 'd.int
+
+ val testRelationLeft = LocalRelation(attrA, attrB)
+ val testRelationRight = LocalRelation(attrC, attrD)
// Dummy python UDF for testing. Unable to execute.
val pythonUDF = PythonUDF("pythonUDF", null,
BooleanType,
- Seq.empty,
+ Seq(attrA, attrC),
PythonEvalType.SQL_BATCHED_UDF,
udfDeterministic = true)
@@ -118,7 +123,7 @@ class PullOutPythonUDFInJoinConditionSuite extends
PlanTest {
test("pull out whole complex condition with multiple python udf") {
val pythonUDF1 = PythonUDF("pythonUDF1", null,
BooleanType,
- Seq.empty,
+ Seq(attrA, attrC),
PythonEvalType.SQL_BATCHED_UDF,
udfDeterministic = true)
val condition = (pythonUDF || 'a.attr === 'c.attr) && pythonUDF1
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
