Github user xuanyuanking commented on a diff in the pull request:
https://github.com/apache/spark/pull/22326#discussion_r220576188
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/joins.scala
---
@@ -152,3 +153,53 @@ object EliminateOuterJoin extends Rule[LogicalPlan]
with PredicateHelper {
if (j.joinType == newJoinType) f else Filter(condition,
j.copy(joinType = newJoinType))
}
}
+
+/**
+ * PythonUDF in join condition can not be evaluated, this rule will detect
the PythonUDF
+ * and pull them out from join condition. For python udf accessing
attributes from only one side,
+ * they would be pushed down by operation push down rules. If not(e.g.
user disables filter push
+ * down rules), we need to pull them out in this rule too.
+ */
+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" $joinType is not supported.")
+ }
+ // If condition expression contains python udf, it will be moved out
from
+ // the new join conditions. If join condition has python udf only,
it will be turned
+ // to cross join and the crossJoinEnable will be checked in
CheckCartesianProducts.
+ val (udf, rest) =
+
condition.map(splitConjunctivePredicates).get.partition(hasPythonUDF)
+ val newCondition = if (rest.isEmpty) {
+ logWarning(s"The join condition:$condition of the join plan
contains " +
+ "PythonUDF only, it will be moved out and the join plan will be
turned to cross " +
+ s"join. This plan shows below:\n $j")
--- End diff --
Got it, done in d2739af.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
