hadoop InputSplit

/**
 * <code>InputSplit</code> represents the data to be processed by an
 * individual {@link Mapper}.
 * InputSplit 代表可以被Mapper处理的数据
 * <p>Typically, it presents a byte-oriented view on the input and is the
 * responsibility of {@link RecordReader} of the job to process this and present
 * a record-oriented view.
 *
 * @see InputFormat
 * @see RecordReader
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public abstract class InputSplit {
  /**
   * Get the size of the split, so that the input splits can be sorted by size.
   * @return the number of bytes in the split
   * @throws IOException
   * @throws InterruptedException
   * split的长度用byte表示
   */
  public abstract long getLength() throws IOException, InterruptedException;

  /**
   * Get the list of nodes by name where the data for the split would be local.
   * The locations do not need to be serialized.
   * 获取split所在的节点
   * @return a new array of the node nodes.
   * @throws IOException
   * @throws InterruptedException
   */
  public abstract
    String[] getLocations() throws IOException, InterruptedException;

  /**
   * Gets info about which nodes the input split is stored on and how it is
   * stored at each location.
   * 返回split所在的节点信息以及在该节点上如何存储 memory
   * @return list of <code>SplitLocationInfo</code>s describing how the split
   *    data is stored at each location. A null value indicates that all the
   *    locations have the data stored on disk.
   * @throws IOException
   */
  @Evolving
  public SplitLocationInfo[] getLocationInfo() throws IOException {
    return null;
  }
}