public static void main(String[] args) throws IOException {
Text text = new Text("\u0041");
ObjectWritable writable = new ObjectWritable(text);
System.out.println(StringUtils.byteToHexString(serialize(writable)));
// 00196f72672e6170616368652e6861646f6f702e696f2e5465787400196f72672e6170616368652e6861646f6f702e696f2e546578740141
// (a)0019 6f72672e6170616368652e6861646f6f702e696f2e54657874， (b)0019
// 6f72672e6170616368652e6861646f6f702e696f2e54657874，(c)0141
/*
(1)序列化 ObjectWritable 的声明部分
UTF8.writeString(out, declaredClass.getName()); ==>
0019 6f72672e6170616368652e6861646f6f702e696f2e54657874(第一部分是一个short数值，为该对象class名字的字符串长度，org.apache.hadoop.io.Text，25位=0x0019)
(2)序列化 Writable 接口对象的实现类
if (Writable.class.isAssignableFrom(declaredClass)) { // Writable接口实现类
UTF8.writeString(out, instance.getClass().getName());
((Writable)instance).write(out);
} ==>
0019 6f72672e6170616368652e6861646f6f702e696f2e54657874
0141(可变长Text的序列化值，0x01长度，0x41数值内容)
*/
ObjectWritable srcWritable = new ObjectWritable(Integer.TYPE, 188);
ObjectWritable destWritable = new ObjectWritable();
cloneInto(srcWritable, destWritable);
System.out.println(serializeToHexString(srcWritable)); // 0003696e74000000bc
System.out.println((Integer) destWritable.get()); // 188
}
/** Convert a MD5MD5CRC32FileChecksum to a Json string. */
public static String toJsonString(final MD5MD5CRC32FileChecksum checksum) {
if (checksum == null) {
return null;
}
final Map<String, Object> m = new TreeMap<String, Object>();
m.put("algorithm", checksum.getAlgorithmName());
m.put("length", checksum.getLength());
m.put("bytes", StringUtils.byteToHexString(checksum.getBytes()));
return toJsonString(MD5MD5CRC32FileChecksum.class, m);
}
public String toString() {
StringBuilder sb = new StringBuilder(1024);
sb.append("id=");
String id = StringUtils.byteToHexString(this.getIdentifier());
int idLen = id.length();
sb.append(id.substring(idLen - 6));
sb.append(";k=");
sb.append(this.getKind());
sb.append(";s=");
sb.append(this.getService());
return sb.toString();
}
/**
* Test encoding and decoding of UTF8 outside the basic multilingual plane.
*
* <p>This is a regression test for HADOOP-9103.
*/
@Test
public void testNonBasicMultilingualPlane() throws Exception {
// Test using the "CAT FACE" character (U+1F431)
// See http://www.fileformat.info/info/unicode/char/1f431/index.htm
String catFace = "\uD83D\uDC31";
// This encodes to 4 bytes in UTF-8:
byte[] encoded = catFace.getBytes("UTF-8");
assertEquals(4, encoded.length);
assertEquals("f09f90b1", StringUtils.byteToHexString(encoded));
// Decode back to String using our own decoder
String roundTrip = UTF8.fromBytes(encoded);
assertEquals(catFace, roundTrip);
}
public static void main(String[] args)
throws IOException, InstantiationException, IllegalAccessException {
Writable writable = new IntWritable();
((IntWritable) writable).set(163);
byte[] bytes = serialize(writable);
assertThat(bytes.length, is(4));
assertThat(StringUtils.byteToHexString(bytes), is("000000a3"));
System.out.println("序列化操作完成");
IntWritable newWritable = new IntWritable();
deserialize(newWritable, bytes);
assertThat(newWritable.get(), is(163));
System.out.println(newWritable.get());
System.out.println("反序列化操作完成");
}
