Github user mgaido91 commented on a diff in the pull request:
https://github.com/apache/spark/pull/22326#discussion_r220484279
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala
---
@@ -152,3 +153,51 @@ 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 PullOutPythonUDFInJoinCondition 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.isDefined && hasPythonUDF(condition.get) =>
+ if (!joinType.isInstanceOf[InnerLike] && joinType != LeftSemi) {
--- End diff --
can't we support `LeftAnti` too?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
