leovegas commented on code in PR #46678: URL: https://github.com/apache/spark/pull/46678#discussion_r1613994258
########## sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala: ########## @@ -62,10 +62,10 @@ object OrcUtils extends Logging { val CATALYST_TYPE_ATTRIBUTE_NAME = "spark.sql.catalyst.type" def listOrcFiles(pathStr: String, conf: Configuration): Seq[Path] = { + // TODO: Check if the paths coming in are already qualified and simplify. val origPath = new Path(pathStr) val fs = origPath.getFileSystem(conf) val paths = SparkHadoopUtil.get.listLeafStatuses(fs, origPath) - .filterNot(_.isDirectory) Review Comment: listFiles in listLeafStatuses provides FileStatus of the files only. -- 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. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org 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