mihailoale-db commented on code in PR #49837:
URL: https://github.com/apache/spark/pull/49837#discussion_r1950859900
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/PullOutNondeterministic.scala:
##########
@@ -51,27 +52,12 @@ object PullOutNondeterministic extends Rule[LogicalPlan] {
// from LogicalPlan, currently we only do it for UnaryNode which has same
output
// schema with its child.
case p: UnaryNode if p.output == p.child.output &&
p.expressions.exists(!_.deterministic) =>
- val nondeterToAttr = getNondeterToAttr(p.expressions)
+ val nondeterToAttr =
+
NondeterministicExpressionCollection.getNondeterministicToAttributes(p.expressions)
val newPlan = p.transformExpressions { case e =>
nondeterToAttr.get(e).map(_.toAttribute).getOrElse(e)
}
val newChild = Project(p.child.output ++ nondeterToAttr.values, p.child)
Project(p.output, newPlan.withNewChildren(newChild :: Nil))
}
-
- private def getNondeterToAttr(exprs: Seq[Expression]): Map[Expression,
NamedExpression] = {
- exprs.filterNot(_.deterministic).flatMap { expr =>
- val leafNondeterministic = expr.collect {
- case n: Nondeterministic => n
- case udf: UserDefinedExpression if !udf.deterministic => udf
- }
- leafNondeterministic.distinct.map { e =>
- val ne = e match {
- case n: NamedExpression => n
- case _ => Alias(e, "_nondeterministic")()
- }
- e -> ne
- }
- }.toMap
Review Comment:
Done.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
