[GitHub] [spark] peter-toth commented on a change in pull request #27454: [SPARK-28228][SQL] Change the default behavior for name conflict in nested WITH clause

[GitBox <gi...@apache.org>]

peter-toth commented on a change in pull request #27454: [SPARK-28228][SQL] Change the default behavior for name conflict in nested WITH clause
URL: https://github.com/apache/spark/pull/27454#discussion_r376279947
 
 

 ##########
 File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CTESubstitution.scala
 ##########
 @@ -28,10 +29,49 @@ import org.apache.spark.sql.internal.SQLConf.LEGACY_CTE_PRECEDENCE_ENABLED
  */
 object CTESubstitution extends Rule[LogicalPlan] {
   def apply(plan: LogicalPlan): LogicalPlan = {
-    if (SQLConf.get.getConf(LEGACY_CTE_PRECEDENCE_ENABLED)) {
+    val isLegacy = SQLConf.get.getConf(LEGACY_CTE_PRECEDENCE_ENABLED)
+    if (isLegacy.isEmpty) {
+      assertNoNameConflictsInCTE(plan, inTraverse = false)
+      traverseAndSubstituteCTE(plan, inTraverse = false)
+    } else if (isLegacy.get) {
       legacyTraverseAndSubstituteCTE(plan)
     } else {
-      traverseAndSubstituteCTE(plan, false)
+      traverseAndSubstituteCTE(plan, inTraverse = false)
+    }
+  }
+
+  /**
+   * Check the plan to be traversed has naming conflicts in nested CTE or not, traverse through
+   * child, innerChildren and subquery for the current plan.
+   */
+  private def assertNoNameConflictsInCTE(
+      plan: LogicalPlan,
+      inTraverse: Boolean,
+      cteNames: Set[String] = Set.empty): Unit = {
+    plan.foreach {
+      case w @ With(child, relations) =>
+        val newNames = relations.map {
+          case (cteName, _) =>
+            if (cteNames.contains(cteName)) {
+              throw new AnalysisException(s"Name $cteName is conflict in nested CTE. " +
+                s"Please set ${LEGACY_CTE_PRECEDENCE_ENABLED.key} to false so that name defined " +
+                "in inner CTE takes precedence. See more details in SPARK-28228.")
+            } else {
+              cteName
+            }
+        }.toSet
+        (w.innerChildren :+ child).foreach { p =>
 
 Review comment:
   This could be:
   ```
           child.transformExpressions {
             case e: SubqueryExpression =>
               assertNoNameConflictsInCTE(e.plan, inTraverse = true, cteNames ++ newNames)
               e
           }
           w.innerChildren.foreach { p =>
             assertNoNameConflictsInCTE(p, inTraverse = true, cteNames ++ newNames)
           }
   ```
   If you check `CTE in subquery shadows outer` test cases you will see that legacy and new results are the same. We shouldn't give `AnalysisException` in those cases.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

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