Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/14241#discussion_r72016917 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/ExistingRDD.scala --- @@ -275,62 +271,152 @@ private[sql] case class RowDataSourceScanExec( |} """.stripMargin } + + // Ignore rdd when checking results + override def sameResult(plan: SparkPlan): Boolean = plan match { + case other: RowDataSourceScanExec => relation == other.relation && metadata == other.metadata + case _ => false + } } -/** Physical plan node for scanning data from a batched relation. */ -private[sql] case class BatchedDataSourceScanExec( +/** Physical plan node for scanning data from files. */ +private[sql] case class FileSourceScanExec( + @transient relation: HadoopFsRelation, output: Seq[Attribute], - rdd: RDD[InternalRow], - @transient relation: BaseRelation, - override val outputPartitioning: Partitioning, - override val metadata: Map[String, String], + outputSchema: StructType, + partitionFilters: Seq[Expression], --- End diff -- BTW in order to make this more dynamic, we'd need to make these mutable.
--- 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