Hadoop1.0 ObjectWritable

2019独角兽企业重金招聘Python工程师标准>>>

  Hadoop的ObjectWritable保存了一个可以在Hadoop RPC里面传输的对象和对象类型的说明信息。用于客户端与服务器间传输的Writable对象，也是对RPC传输对象的封装，因为RPC上交换的信息只能是JAVA的基础数据类型，String或者Writable类型，而ObjectWritable是对其子类的抽象封装，该类大致情况如下：

ObjectWritable会往流里写入如下信息：

对象类名，对象自己的串行化结果

其序列化和反序列化方法如下：

public void readFields(DataInput in) throws IOException {
    readObject(in, this, this.conf);
  }
  
  public void write(DataOutput out) throws IOException {
    writeObject(out, instance, declaredClass, conf);
  }

 分别调用的是writeObject(out, instance, declaredClass, conf)和readObject(in, this, this.conf)方法：

writeObject(out, instance, declaredClass, conf)方法：该方法逐一分析待xulie的数据类型并且实现序列化。

public static void writeObject(DataOutput out, Object instance,
                                 Class declaredClass, 
                                 Configuration conf) throws IOException {
	//对象为空则抽象出内嵌数据类型NullInstance
    if (instance == null) {                       // null
      instance = new NullInstance(declaredClass, conf);
      declaredClass = Writable.class;
    }
    //先写入类名
    UTF8.writeString(out, declaredClass.getName()); // always write declared
    /*
     * 封装的对象为数组类型，则逐个序列化（序列化为length+对象的序列化内容）
     * 采用了迭代
     */
    
    if (declaredClass.isArray()) {                // array
      int length = Array.getLength(instance);
      out.writeInt(length);
      for (int i = 0; i < length; i++) {
        writeObject(out, Array.get(instance, i),
                    declaredClass.getComponentType(), conf);
      }
      //为String类型直接写入
    } else if (declaredClass == String.class) {   // String
      UTF8.writeString(out, (String)instance);
      
    }//基本数据类型写入 
    else if (declaredClass.isPrimitive()) {     // primitive type

      if (declaredClass == Boolean.TYPE) {        // boolean
        out.writeBoolean(((Boolean)instance).booleanValue());
      } else if (declaredClass == Character.TYPE) { // char
        out.writeChar(((Character)instance).charValue());
      } else if (declaredClass == Byte.TYPE) {    // byte
        out.writeByte(((Byte)instance).byteValue());
      } else if (declaredClass == Short.TYPE) {   // short
        out.writeShort(((Short)instance).shortValue());
      } else if (declaredClass == Integer.TYPE) { // int
        out.writeInt(((Integer)instance).intValue());
      } else if (declaredClass == Long.TYPE) {    // long
        out.writeLong(((Long)instance).longValue());
      } else if (declaredClass == Float.TYPE) {   // float
        out.writeFloat(((Float)instance).floatValue());
      } else if (declaredClass == Double.TYPE) {  // double
        out.writeDouble(((Double)instance).doubleValue());
      } else if (declaredClass == Void.TYPE) {    // void
      } else {
        throw new IllegalArgumentException("Not a primitive: "+declaredClass);
      }
      //枚举类型写入
    } else if (declaredClass.isEnum()) {         // enum
      UTF8.writeString(out, ((Enum)instance).name());
      //hadoop的Writable类型写入
    } else if (Writable.class.isAssignableFrom(declaredClass)) { // Writable
      UTF8.writeString(out, instance.getClass().getName());
      ((Writable)instance).write(out);

    } else {
      throw new IOException("Can't write: "+instance+" as "+declaredClass);
    }
  }

对于readObject(in, this, this.conf)方法：该方法用于反序列化，在ObjectWritable对象内部封装了一个基本数据类型的注册表

通过if语句条件实现基本数据类型的反序列化，而对于实现了Writbale接口的封装数据，则是通过Conf对象获取其类声明，其反序列化的

实例化也是调用WritableFactories工程去实例化，最后在存储反序列化的值。

public static Object readObject(DataInput in, Configuration conf)
    throws IOException {
    return readObject(in, null, conf);
  }
    
  /** Read a {@link Writable}, {@link String}, primitive type, or an array of
   * the preceding. */
  @SuppressWarnings("unchecked")
  public static Object readObject(DataInput in, ObjectWritable objectWritable, Configuration conf)
    throws IOException {
	  //获取反序列化的名字
    String className = UTF8.readString(in);
    //假设为基本数据类型
    Class<?> declaredClass = PRIMITIVE_NAMES.get(className);
    /*
     * 判断是否为基本数据类型，不是则为空，则为Writable类型，
     * 对于Writable类型从Conf配置文件中读取类名，
     * 在这里只是获取类名，而并没有反序列化对象
     */
    
    if (declaredClass == null) {
      try {
        declaredClass = conf.getClassByName(className);
      } catch (ClassNotFoundException e) {
        throw new RuntimeException("readObject can't find class " + className, e);
      }
    }    
    //基本数据类型
    Object instance;
    //为基本数据类型，逐一反序列化
    if (declaredClass.isPrimitive()) {            // primitive types

      if (declaredClass == Boolean.TYPE) {             // boolean
        instance = Boolean.valueOf(in.readBoolean());
      } else if (declaredClass == Character.TYPE) {    // char
        instance = Character.valueOf(in.readChar());
      } else if (declaredClass == Byte.TYPE) {         // byte
        instance = Byte.valueOf(in.readByte());
      } else if (declaredClass == Short.TYPE) {        // short
        instance = Short.valueOf(in.readShort());
      } else if (declaredClass == Integer.TYPE) {      // int
        instance = Integer.valueOf(in.readInt());
      } else if (declaredClass == Long.TYPE) {         // long
        instance = Long.valueOf(in.readLong());
      } else if (declaredClass == Float.TYPE) {        // float
        instance = Float.valueOf(in.readFloat());
      } else if (declaredClass == Double.TYPE) {       // double
        instance = Double.valueOf(in.readDouble());
      } else if (declaredClass == Void.TYPE) {         // void
        instance = null;
      } else {
        throw new IllegalArgumentException("Not a primitive: "+declaredClass);
      }

    } else if (declaredClass.isArray()) {              // array
      int length = in.readInt();
      instance = Array.newInstance(declaredClass.getComponentType(), length);
      for (int i = 0; i < length; i++) {
        Array.set(instance, i, readObject(in, conf));
      }
      
    } else if (declaredClass == String.class) {        // String类型的反序列化
      instance = UTF8.readString(in);
    } else if (declaredClass.isEnum()) {         // enum的反序列化
      instance = Enum.valueOf((Class<? extends Enum>) declaredClass, UTF8.readString(in));
    } else {                                      // Writable
      Class instanceClass = null;
      String str = "";
      try {
    	  //剩下的从Conf对象中获取类型Class
        str = UTF8.readString(in);
        instanceClass = conf.getClassByName(str);
      } catch (ClassNotFoundException e) {
        throw new RuntimeException("readObject can't find class " + str, e);
      }
      /*
       * 带用了WritableFactories工厂去new instanceClass(实现了Writable接口)对象出来
       * 在调用实现Writable对象自身的反序列化方法
       */
     
      Writable writable = WritableFactories.newInstance(instanceClass, conf);
      writable.readFields(in);
      instance = writable;

      if (instanceClass == NullInstance.class) {  // null
        declaredClass = ((NullInstance)instance).declaredClass;
        instance = null;
      }
    }
    //最后存储反序列化后待封装的ObjectWritable对象
    if (objectWritable != null) {                 // store values
      objectWritable.declaredClass = declaredClass;
      objectWritable.instance = instance;
    }

    return instance;
      
  }

对于Null类型的封装，在ObjectWritable内部封装了一个Nullinstance

private static class NullInstance extends Configured implements Writable {
    private Class<?> declaredClass;
    public NullInstance() { super(null); }
    public NullInstance(Class declaredClass, Configuration conf) {
      super(conf);
      this.declaredClass = declaredClass;
    }

转载于:https://my.oschina.net/tuzibuluo/blog/49576