milanisvet commented on code in PR #49518:
URL: https://github.com/apache/spark/pull/49518#discussion_r1928436802
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveWithCTE.scala:
##########
@@ -183,4 +185,67 @@ object ResolveWithCTE extends Rule[LogicalPlan] {
columnNames.map(UnresolvedSubqueryColumnAliases(_, ref)).getOrElse(ref)
}
}
+
+ /**
+ * Checks if there is any self-reference within subqueries and throws an
error
+ * if that is the case.
+ */
+ def checkForSelfReferenceInSubquery(plan: LogicalPlan): Unit = {
+ plan.subqueriesAll.foreach { subquery =>
+ subquery.foreach {
+ case r: CTERelationRef if r.recursive =>
+ throw new AnalysisException(
+ errorClass = "INVALID_RECURSIVE_REFERENCE.SUBQUERY",
+ messageParameters = Map.empty)
+ case _ =>
+ }
+ }
+ }
+
+ /**
+ * Counts number of self-references in a recursive CTE definition and throws
an error
+ * if that number is bigger than 1.
+ */
+ private def checkNumberOfSelfReferences(cteDef: CTERelationDef): Unit = {
+ val numOfSelfRef = cteDef.collectWithSubqueries {
+ case ref: CTERelationRef if ref.cteId == cteDef.id => ref
+ }.length
+ if (numOfSelfRef > 1) {
+ cteDef.failAnalysis(
+ errorClass = "INVALID_RECURSIVE_REFERENCE.NUMBER",
+ messageParameters = Map.empty)
+ }
+ }
+
+ /**
+ * Throws error if self-reference is placed in places which are not allowed:
+ * right side of left outer/semi/anti joins, left side of right outer joins,
+ * in full outer joins and in aggregates
+ */
+ def checkIfSelfReferenceIsPlacedCorrectly(unionLoop: UnionLoop): Unit = {
+ def unionLoopRefNotAllowedUnderCurrentNode(currentNode: LogicalPlan) :
Unit =
+ currentNode.foreach {
+ case UnionLoopRef(unionLoop.id, _, _) =>
+ throw new AnalysisException(
+ errorClass = "INVALID_RECURSIVE_REFERENCE.PLACE",
+ messageParameters = Map.empty)
+ case other =>
+ }
+ unionLoop.foreach {
Review Comment:
Makes completely sense. It should be fixed now. Thanks a lot
--
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
