[GitHub] [spark] maropu commented on a change in pull request #31966: [SPARK-34638][SQL] Single field nested column prune on generator output

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

maropu commented on a change in pull request #31966:
URL: https://github.com/apache/spark/pull/31966#discussion_r606985124



##########
File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/NestedColumnAliasing.scala
##########
@@ -231,6 +231,27 @@ object NestedColumnAliasing {
  * of it.
  */
 object GeneratorNestedColumnAliasing {
+  // Partitions `attrToAliases` based on whether the attribute is in Generator's output.
+  private def aliasesOnGeneratorOutput(
+      attrToAliases: Map[ExprId, Seq[Alias]],
+      generatorOutput: Seq[Attribute]) = {
+    val generatorOutputExprId = generatorOutput.map(_.exprId)
+    attrToAliases.partition { k =>
+      generatorOutputExprId.contains(k._1)
+    }
+  }
+
+  // Partitions `nestedFieldToAlias` based on whether the attribute of nested field extractor
+  // is in Generator's output.
+  private def nestedFieldOnGeneratorOutput(
+      nestedFieldToAlias: Map[ExtractValue, Alias],
+      generatorOutput: Seq[Attribute]) = {
+    val generatorOutputSet = AttributeSet(generatorOutput)
+    nestedFieldToAlias.partition { pair =>
+      pair._1.references.subsetOf(generatorOutputSet)
+    }
+  }

Review comment:
       sgtm




-- 
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



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