Github user dilipbiswal commented on a diff in the pull request:
https://github.com/apache/spark/pull/22326#discussion_r220436983
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala
---
@@ -152,3 +153,56 @@ object EliminateOuterJoin extends Rule[LogicalPlan]
with PredicateHelper {
if (j.joinType == newJoinType) f else Filter(condition,
j.copy(joinType = newJoinType))
}
}
+
+/**
+ * Correctly handle PythonUDF which need access both side of join side by
changing the new join
+ * type to Cross.
+ */
+object HandlePythonUDFInJoinCondition extends Rule[LogicalPlan] with
PredicateHelper {
+ def hasPythonUDF(expression: Expression): Boolean = {
+ expression.collectFirst { case udf: PythonUDF => udf }.isDefined
+ }
+
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transformUp {
+ case j @ Join(_, _, joinType, condition)
+ if
condition.map(splitConjunctivePredicates).getOrElse(Nil).exists(hasPythonUDF) =>
--- End diff --
@xuanyuanking So here we are finding out if the join condition has a python
UDF. I am trying to understand where we are making the determination that this
python UDF is referring to attributes of both legs of the join ? Can you please
let me know. Thank you.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
