[GitHub] [spark] peter-toth commented on a diff in pull request #40856: [SPARK-43199][SQL] Make InlineCTE idempotent

["peter-toth (via GitHub)" <gi...@apache.org>]

peter-toth commented on code in PR #40856:
URL: https://github.com/apache/spark/pull/40856#discussion_r1173553935


##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InlineCTE.scala:
##########
@@ -70,48 +71,69 @@ case class InlineCTE(alwaysInline: Boolean = false) extends Rule[LogicalPlan] {
 
   def buildCTEMap(
       plan: LogicalPlan,
-      cteMap: mutable.HashMap[Long, (CTERelationDef, Int)]): Unit = {
+      cteMap: mutable.Map[Long, (CTERelationDef, Int, mutable.Map[Long, Int])],
+      outerCTEId: Option[Long] = None): Unit = {
     plan match {
-      case WithCTE(_, cteDefs) =>
+      case WithCTE(child, cteDefs) =>
+        cteDefs.foreach { cteDef =>
+          cteMap(cteDef.id) = (cteDef, 0, mutable.Map.empty.withDefaultValue(0))
+        }
         cteDefs.foreach { cteDef =>
-          cteMap.put(cteDef.id, (cteDef, 0))
+          buildCTEMap(cteDef, cteMap, Some(cteDef.id))
         }
+        buildCTEMap(child, cteMap, outerCTEId)
 
       case ref: CTERelationRef =>
-        val (cteDef, refCount) = cteMap(ref.cteId)
-        cteMap.update(ref.cteId, (cteDef, refCount + 1))
+        val (cteDef, refCount, refMap) = cteMap(ref.cteId)
+        cteMap(ref.cteId) = (cteDef, refCount + 1, refMap)
+        outerCTEId.foreach { cteId =>
+          val (_, _, outerRefMap) = cteMap(cteId)
+          outerRefMap(ref.cteId) += 1
+        }
 
       case _ =>
-    }
-
-    if (plan.containsPattern(CTE)) {
-      plan.children.foreach { child =>
-        buildCTEMap(child, cteMap)
-      }
+        if (plan.containsPattern(CTE)) {
+          plan.children.foreach { child =>
+            buildCTEMap(child, cteMap, outerCTEId)
+          }
 
-      plan.expressions.foreach { expr =>
-        if (expr.containsAllPatterns(PLAN_EXPRESSION, CTE)) {
-          expr.foreach {
-            case e: SubqueryExpression =>
-              buildCTEMap(e.plan, cteMap)
-            case _ =>
+          plan.expressions.foreach { expr =>
+            if (expr.containsAllPatterns(PLAN_EXPRESSION, CTE)) {
+              expr.foreach {
+                case e: SubqueryExpression => buildCTEMap(e.plan, cteMap, outerCTEId)
+                case _ =>
+              }
+            }
           }
         }
+    }
+  }
+
+  private def cleanCTEMap(
+      cteRefMap: mutable.SortedMap[Long, (CTERelationDef, Int, mutable.Map[Long, Int])]
+    ) = {
+    cteRefMap.keys.toSeq.reverse.foreach { currentCTEId =>
+      val (_, currentRefCount, refMap) = cteRefMap(currentCTEId)

Review Comment:
   Yes. Added scaladoc in https://github.com/apache/spark/pull/40856/commits/ecbc4b879a8f1c397d200958b1b7ade0f6768ca5, let me know if it needs more detailed comments.



-- 
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-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org