InputFormat牛逼（7）抽象类FileInputFormat

@Public
@Stable

A base class for file-based InputFormats.

FileInputFormat is the base class for all file-based InputFormats. This provides a generic implementation of getSplits(JobContext). Subclasses of FileInputFormat can also override the isSplitable(JobContext, Path) method to ensure input-files are not split-up and are processed as a whole by Mappers.

类定义

public abstract class FileInputFormat<K, V> extends InputFormat<K, V> 

核心方法getSplits

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

    // generate splits
    List<InputSplit> splits = new ArrayList<InputSplit>();
    List<FileStatus> files = listStatus(job);
    for (FileStatus file: files) {
      Path path = file.getPath();
      long length = file.getLen();
      if (length != 0) {
        BlockLocation[] blkLocations;
        if (file instanceof LocatedFileStatus) {
          blkLocations = ((LocatedFileStatus) file).getBlockLocations();
        } else {
          FileSystem fs = path.getFileSystem(job.getConfiguration());
          blkLocations = fs.getFileBlockLocations(file, 0, length);
        }
        if (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(makeSplit(path, length-bytesRemaining, splitSize,
                        blkLocations[blkIndex].getHosts(),
                        blkLocations[blkIndex].getCachedHosts()));
            bytesRemaining -= splitSize;
          }

          if (bytesRemaining != 0) {
            int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
            splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining,
                       blkLocations[blkIndex].getHosts(),
                       blkLocations[blkIndex].getCachedHosts()));
          }
        } else { // not splitable
          splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts(),
                      blkLocations[0].getCachedHosts()));
        }
      } else { 
        //Create empty hosts array for zero length files
        splits.add(makeSplit(path, 0, length, new String[0]));
      }
    }
    // Save the number of input files for metrics/loadgen
    job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
    sw.stop();
    if (LOG.isDebugEnabled()) {
      LOG.debug("Total # of splits generated by getSplits: " + splits.size()
          + ", TimeTaken: " + sw.elapsedMillis());
    }
    return splits;
  }

构建FileSplit对象

  /**
   * A factory that makes the split for this class. It can be overridden
   * by sub-classes to make sub-types
   */
  protected FileSplit makeSplit(Path file, long start, long length, 
                                String[] hosts) {
    return new FileSplit(file, start, length, hosts);
  }