Github user chenghao-intel commented on a diff in the pull request: https://github.com/apache/spark/pull/5059#discussion_r27782363 --- Diff: sql/hive/src/main/scala/org/apache/spark/sql/hive/TableReader.scala --- @@ -142,7 +142,46 @@ class HadoopTableReader( partitionToDeserializer: Map[HivePartition, Class[_ <: Deserializer]], filterOpt: Option[PathFilter]): RDD[Row] = { - val hivePartitionRDDs = partitionToDeserializer.map { case (partition, partDeserializer) => + + // SPARK-5068:get FileStatus and do the filtering locally when the path is not exists + def verifyPartitionPath( + partitionToDeserializer: Map[HivePartition, Class[_ <: Deserializer]]): + Map[HivePartition, Class[_ <: Deserializer]] = { + if (!sc.getConf("spark.sql.hive.verifyPartitionPath", "true").toBoolean) { + partitionToDeserializer + } else { + var existPathSet = collection.mutable.Set[String]() + var pathPatternSet = collection.mutable.Set[String]() + partitionToDeserializer.filter { + case (partition, partDeserializer) => + def updateExistPathSetByPathPattern(pathPatternStr: String) { + val pathPattern = new Path(pathPatternStr) + val fs = pathPattern.getFileSystem(sc.hiveconf) + val matches = fs.globStatus(pathPattern) + matches.map(fileStatus => existPathSet += fileStatus.getPath.toString) + } + // convert /demo/data/year/month/day to /demo/data/**/**/**/ --- End diff -- to `/demo/data/*/*/*/`?
--- 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