hadoop学习——IO之ObjectWritable

ObjectWritable类主要方法

public void write(DataOutput out) throws IOException {
    writeObject(out, instance, declaredClass, conf);
  }

 public void readFields(DataInput in) throws IOException {
    readObject(in, this, this.conf);
  }

 write是把ObjectWritable对象中的instance写入out，那么instance是从哪里来的呢？

一种方式是通过new时设置的：

  public ObjectWritable(Object instance) {
    set(instance);
  }

 

另一种方式可以通过readFields方法读取的。

然后看看readObject方法是怎么反序列化一个object的：

public static Object readObject(DataInput in, ObjectWritable objectWritable, Configuration conf)
    throws IOException {
    String className = UTF8.readString(in);
    Class<?> declaredClass = PRIMITIVE_NAMES.get(className);
    if (declaredClass == null) {
      try {
        declaredClass = conf.getClassByName(className);
      } catch (ClassNotFoundException e) {
        throw new RuntimeException("readObject can't find class " + className, e);
      }
    }    

    Object instance;
    
    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
      instance = UTF8.readString(in);
    } else if (declaredClass.isEnum()) {         // enum
      instance = Enum.valueOf((Class<? extends Enum>) declaredClass, UTF8.readString(in));
    } else {                                      // Writable
      Class instanceClass = null;
      String str = "";
      try {
        str = UTF8.readString(in);
        instanceClass = conf.getClassByName(str);
      } catch (ClassNotFoundException e) {
        throw new RuntimeException("readObject can't find class " + str, e);
      }
      
      Writable writable = WritableFactories.newInstance(instanceClass, conf);
      writable.readFields(in);
      instance = writable;

      if (instanceClass == NullInstance.class) {  // null
        declaredClass = ((NullInstance)instance).declaredClass;
        instance = null;
      }
    }

    if (objectWritable != null) {                 // store values
      objectWritable.declaredClass = declaredClass;
      objectWritable.instance = instance;
    }

    return instance;
      
  }

 可以看出 instance 指向的是java基本类型，或者Array，Enum，或者Writable 。而如果DataInput中传过来的是Writable 类型，则会在readObject再去调用readFields方法（writable.readFields(in)），直到DataInput中传递的是非Writable 类型，就这样递归的反序列化DataInput中的Writable对象。

再看看writeObject方法是如何序列化Writable对象的：

/** Write a {@link Writable}, {@link String}, primitive type, or an array of
   * the preceding. */
  public static void writeObject(DataOutput out, Object instance,
                                 Class declaredClass, 
                                 Configuration conf) throws IOException {

    if (instance == null) {                       // null
      instance = new NullInstance(declaredClass, conf);
      declaredClass = Writable.class;
    }

    UTF8.writeString(out, declaredClass.getName()); // always write declared

    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);
      }
      
    } else if (declaredClass == String.class) {   // String
      UTF8.writeString(out, (String)instance);
      
    } 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);
      }
    } else if (declaredClass.isEnum()) {         // enum
      UTF8.writeString(out, ((Enum)instance).name());
    } 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);
    }
  }

 在这两个方法中，向数据流中写数据都是用UTF8类，UTF8类相当于一个工具类。

参考：http://caibinbupt.iteye.com/blog/277640