Github user ericl commented on a diff in the pull request: https://github.com/apache/spark/pull/14690#discussion_r83340821 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala --- @@ -2602,7 +2602,7 @@ class Dataset[T] private[sql]( * @since 2.0.0 */ def inputFiles: Array[String] = { - val files: Seq[String] = logicalPlan.collect { + val files: Seq[String] = queryExecution.optimizedPlan.collect { --- End diff -- We only determine the partitions read after optimization, so it's necessary to read it from that instead of the logical plan.
--- 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