关于hadoop循环获取路径以及获得分片的源代码

protected List<FileStatus> listStatus(JobContext job
                                        ) throws IOException {
    List<FileStatus> result = new ArrayList<FileStatus>();
    Path[] dirs = getInputPaths(job);//指向输入路径
    if (dirs.length == 0) {
      throw new IOException("No input paths specified in job");
    }

    List<IOException> errors = new ArrayList<IOException>();
    
    
    List<PathFilter> filters = new ArrayList<PathFilter>();
    filters.add(hiddenFileFilter);
    PathFilter jobFilter = getInputPathFilter(job);
    if (jobFilter != null) {
      filters.add(jobFilter);
    }
    PathFilter inputFilter = new MultiPathFilter(filters);
    
    for (int i=0; i < dirs.length; ++i)

 { //路径赋值给p

      Path p = dirs[i];
      FileSystem fs = p.getFileSystem(job.getConfiguration()); 
      FileStatus[] matches = fs.globStatus(p, inputFilter);//globStatus()返回了其路径匹配于所供格式的FileStatus对象数组，按路径排序
      if (matches == null) {
        errors.add(new IOException("Input path does not exist: " + p));
      } else if (matches.length == 0) {
        errors.add(new IOException("Input Pattern " + p + " matches 0 files"));
      } else {
        for (FileStatus globStat: matches) {
          if (globStat.isDir()) {
            for(FileStatus stat: fs.listStatus(globStat.getPath(),
                inputFilter)) {
              result.add(stat);
            }          
          } else {
            result.add(globStat);
          }
        }
      }
    }

    if (!errors.isEmpty()) {
      throw new InvalidInputException(errors);
    }
    LOG.info("Total input paths to process : " + result.size()); 
    return result;
  }
  

  /** 
   * Generate the list of files and make them into FileSplits.
   */ 
  public List<InputSplit> getSplits(JobContext job
                                    ) throws IOException {
    long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
    long maxSize = getMaxSplitSize(job);

    // generate splits
    List<InputSplit> splits = new ArrayList<InputSplit>();
    for (FileStatus file: listStatus(job))//每个file里是一个单独的传入文件
 {
      Path path = file.getPath();
      FileSystem fs = path.getFileSystem(job.getConfiguration());
      long length = file.getLen();//获得文件长度
      BlockLocation[] blkLocations = fs.getFileBlockLocations(file, 0, length);
      if ((length != 0) && isSplitable(job, path)) { 
        long blockSize = file.getBlockSize();
        long splitSize = computeSplitSize(blockSize, minSize, maxSize);

        long bytesRemaining = length;
        while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
          int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
          splits.add(new FileSplit(path, length-bytesRemaining, splitSize, 
                                   blkLocations[blkIndex].getHosts()));
          bytesRemaining -= splitSize;
        }
        
        if (bytesRemaining != 0) {
          splits.add(new FileSplit(path, length-bytesRemaining, bytesRemaining, 
                     blkLocations[blkLocations.length-1].getHosts()));
        }
      } else if (length != 0) {
        splits.add(new FileSplit(path, 0, length, blkLocations[0].getHosts()));
      } else { 
        //Create empty hosts array for zero length files
        splits.add(new FileSplit(path, 0, length, new String[0]));
      }
    }
    LOG.debug("Total # of splits: " + splits.size());
    return splits;
  }