[GitHub] spark pull request #20611: [SPARK-23425][SQL]Support wildcard in HDFS path f...

[HyukjinKwon <gi...@git.apache.org>]

Github user HyukjinKwon commented on a diff in the pull request:

    https://github.com/apache/spark/pull/20611#discussion_r196365562
  
    --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/command/tables.scala ---
    @@ -303,94 +303,50 @@ case class LoadDataCommand(
               s"partitioned, but a partition spec was provided.")
           }
         }
    -
    -    val loadPath =
    +    val loadPath = {
           if (isLocal) {
    -        val uri = Utils.resolveURI(path)
    -        val file = new File(uri.getPath)
    -        val exists = if (file.getAbsolutePath.contains("*")) {
    -          val fileSystem = FileSystems.getDefault
    -          val dir = file.getParentFile.getAbsolutePath
    -          if (dir.contains("*")) {
    -            throw new AnalysisException(
    -              s"LOAD DATA input path allows only filename wildcard: $path")
    -          }
    -
    -          // Note that special characters such as "*" on Windows are not allowed as a path.
    -          // Calling `WindowsFileSystem.getPath` throws an exception if there are in the path.
    -          val dirPath = fileSystem.getPath(dir)
    -          val pathPattern = new File(dirPath.toAbsolutePath.toString, file.getName).toURI.getPath
    -          val safePathPattern = if (Utils.isWindows) {
    -            // On Windows, the pattern should not start with slashes for absolute file paths.
    -            pathPattern.stripPrefix("/")
    -          } else {
    -            pathPattern
    -          }
    -          val files = new File(dir).listFiles()
    -          if (files == null) {
    -            false
    -          } else {
    -            val matcher = fileSystem.getPathMatcher("glob:" + safePathPattern)
    -            files.exists(f => matcher.matches(fileSystem.getPath(f.getAbsolutePath)))
    -          }
    -        } else {
    -          new File(file.getAbsolutePath).exists()
    -        }
    -        if (!exists) {
    -          throw new AnalysisException(s"LOAD DATA input path does not exist: $path")
    -        }
    -        uri
    -      } else {
    -        val uri = new URI(path)
    -        val hdfsUri = if (uri.getScheme() != null && uri.getAuthority() != null) {
    -          uri
    +        val localFS = FileContext.getLocalFSFileContext()
    +        localFS.makeQualified(new Path(path))
    +      }
    +      else {
    --- End diff --
    
    nit: `} else {`


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org