How to list all files in a directory and its subdirectories in hadoop hdfs

Question

I have a folder in hdfs which has two subfolders each one has about 30 subfolders which,finally,each one contains xml files. I want to list all xml files giving only the mai

Answer 1

Thanks Radu Adrian Moldovan for the suggestion.

Here is an implementation using queue:

private static List listAllFilePath(Path hdfsFilePath, FileSystem fs)
throws FileNotFoundException, IOException {
  List filePathList = new ArrayList();
  Queue fileQueue = new LinkedList();
  fileQueue.add(hdfsFilePath);
  while (!fileQueue.isEmpty()) {
    Path filePath = fileQueue.remove();
    if (fs.isFile(filePath)) {
      filePathList.add(filePath.toString());
    } else {
      FileStatus[] fileStatus = fs.listStatus(filePath);
      for (FileStatus fileStat : fileStatus) {
        fileQueue.add(fileStat.getPath());
      }
    }
  }
  return filePathList;
}