hadoop serialization and deserialization

structured object를 byte stream 형태로 네트웍으로 전달하기 위해 serialization 및 deserialization 작업을 진행함 ( compact / fast / extensible / interoperable )

1. serialization code

public static byte[] serialize(Writable writable) throws IOException {

    ByteArrayOutputStream out = new ByteArrayOutputStream();

    DataOutputStream dataOut = new DataOutputStream(out);

    writable.write(dataOut); 

    dataOut.close();

    return out.toByteArray();

}

byte[] bytes = serialize(writable);

assertThat(bytes.length, is(10));

2. deserialization code

public static byte[] deserialize(Writable writable, byte[] bytes) throws IOException {

   ByteArrayInputStream in = new ByteArrayInputStream(bytes);

   DataInputStream dataIn = new DataInputStream(in);

   writable.readFields(dataIn);

   dataIn.close();

   return bytes;

}

IntWritable newWritable = new IntWritable();

deserialize(newWritable, bytes);

assertThat(newWritable.get(), is(163));