Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/22326#discussion_r220517587
--- 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) {
+ // The current strategy only support InnerLike and LeftSemi join
because for other type,
+ // it breaks SQL semantic if we run the join condition as a filter
after join. If we pass
+ // the plan here, it'll still get a an invalid PythonUDF
RuntimeException with message
+ // `requires attributes from more than one child`, we throw
firstly here for better
+ // readable information.
+ throw new AnalysisException("Using PythonUDF in join condition of
join type" +
+ s" $joinType is not supported.")
+ }
+ // if condition expression contains python udf, it will be moved out
from
+ // the new join conditions, and the join type will be changed to
CrossJoin.
+ logWarning(s"The join condition:$condition of the join plan contains
" +
--- End diff --
do we really need this warning? If it becomes cross join, users will get an
error anyway, if cross join is disabled.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
