maropu commented on a change in pull request #29585:
URL: https://github.com/apache/spark/pull/29585#discussion_r484890981
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/LogicalPlan.scala
##########
@@ -203,3 +203,58 @@ abstract class BinaryNode extends LogicalPlan {
abstract class OrderPreservingUnaryNode extends UnaryNode {
override final def outputOrdering: Seq[SortOrder] = child.outputOrdering
}
+
+object LogicalPlanIntegrity {
+
+ private def canGetOutputAttrs(p: LogicalPlan): Boolean = {
+ p.resolved && !p.expressions.exists { e =>
+ e.collectFirst {
+ // We cannot call `output` in plans with a `ScalarSubquery` expr
having no column,
+ // so, we filter out them in advance.
+ case s: ScalarSubquery if s.plan.schema.fields.isEmpty => true
+ }.isDefined
+ }
+ }
+
+ /**
+ * Since some logical plans (e.g., `Union`) can build `AttributeReference`s
in their `output`,
+ * this method checks if the same `ExprId` refers to a semantically-equal
attribute
+ * in a plan output.
+ */
+ def hasUniqueExprIdsForOutput(plan: LogicalPlan): Boolean = {
+ val allOutputAttrs = plan.collect { case p if canGetOutputAttrs(p) =>
+ p.output.filter(_.resolved).map(_.canonicalized.asInstanceOf[Attribute])
+ }
+ val groupedAttrsByExprId = allOutputAttrs
+ .flatten.groupBy(_.exprId).values.map(_.distinct)
+ groupedAttrsByExprId.forall(_.length == 1)
+ }
+
+ /**
+ * This method checks if reference `ExprId`s are not reused when assigning a
new `ExprId`.
+ * For example, it returns false if plan transformers create an alias having
the same `ExprId`
+ * with one of reference attributes, e.g., `a#1 + 1 AS a#1`.
+ */
+ def checkIfSameExprIdNotReused(plan: LogicalPlan): Boolean = {
+ plan.collect { case p if p.resolved =>
+ val inputExprIds = p.inputSet.filter(_.resolved).map(_.exprId).toSet
Review comment:
Yea, I think we need it. For example, outer references in `ExistencJoin`;
https://github.com/apache/spark/blob/e7d9a245656655e7bb1df3e04df30eb3cc9e23ad/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/basicLogicalOperators.scala#L334-L335
`j.exists` has an unresolved reference.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
