Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/14988#discussion_r78330099 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/execution/HiveTableScanExec.scala --- @@ -164,4 +164,28 @@ case class HiveTableScanExec( } override def output: Seq[Attribute] = attributes + + override def sameResult(plan: SparkPlan): Boolean = plan match { + case other: HiveTableScanExec => + val thisRequestedAttributes = requestedAttributes.map(cleanExpression) + val otherRequestedAttributes = other.requestedAttributes.map(cleanExpression) + + val result = partitionPruningPred == other.partitionPruningPred && + relation.sameResult(other.relation) && + thisRequestedAttributes.zip(otherRequestedAttributes) + .forall(p => p._1.semanticEquals(p._2)) + result + case _ => false + } + + private def cleanExpression(e: Attribute): Expression = e match { + case a: AttributeReference => + // As the root of the expression, Alias will always take an arbitrary exprId, we need --- End diff -- this comment doesn't match the code. Can you explain more about why the default `cleanExpression` doesn't work?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org