viirya commented on a change in pull request #31966: URL: https://github.com/apache/spark/pull/31966#discussion_r602999807
########## 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: okay for me. Put it as functions not for reuse but for making the code look simpler. -- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org