UCS-2和UTF-8的互相转换

我们都知道对于UNICODE来说，UCS-2是内码，而UTF-8则是它的实现方式。每一个字节都有8个位，而对于UTF-8来说，每一个字节的前两位尤为重要，按照前两位的不同，一共有四种排列组合：00xxxxxx，01xxxxxx，10xxxxxx，11xxxxxx。 

按照UTF-8标准， 

（1）所有以0开始的字节，都与原来的ASCII码兼容，也就是说，0xxxxxxx不需要额外转换，就是我们平时用的ASCII码。 

（2）所有以10开始的字节，都不是每个UNICODE的第一个字节，都是紧跟着前一位。例如：10110101，这个字节不可以单独解析，必须通过前一个字节来解析，如果前一个也是10开头，就继续前嗍。 

（3）所有以11开始的字节，都表示是UNICODE的第一个字节，而且后面紧跟着若干个以10开头的字节。如果是110xxxxx（就是最左边的0的左边有2个1），代表后面还有1个10xxxxxx；如果是1110xxxx（就是最左边的0的左边有3个1），代表后面还有2个10xxxxxx；以此类推，一直到1111110x。 

具体的表格如下： 

1字节 0xxxxxxx 
2字节 110xxxxx 10xxxxxx 
3字节 1110xxxx 10xxxxxx 10xxxxxx 
4字节 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx 
5字节 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 
6字节 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 

（很明显，以11开头的，最左边的0左边有多少个1，那这个UCS的UTF-8的表示长度就有多少个字节） 

上面是用6个字节，最多可以表示2 ^ 31个的字符，实际上，只有UCS-4才有这么多的字符，对于UCS-2，仅仅有2 ^ 16个字符，只需要三个字节就可以，也就是说，只需要用到下面的格式： 

1字节 0xxxxxxx 
2字节 110xxxxx 10xxxxxx 
3字节 1110xxxx 10xxxxxx 10xxxxxx 

大家可以试一下下面的program，来看看UTF-8的每个字节。 

package com.ray.utf8;import java.io.UnsupportedEncodingException;public class UTF8Tester {private static String toBin(int n) {StringBuilder b = new StringBuilder();if (n < 0) n += 256;for (int i = 7; i >= 0; i--) {if (1 == ((n >> i) & 1)) {b.append('1');} else {b.append('0');}}return b.toString();}private static String HEX = "0123456789ABCDEF";private static String toHex(int n) {StringBuilder b = new StringBuilder();if (n < 0) n += 256;b.append(HEX.charAt(n >> 4));b.append(HEX.charAt(n & 0x0F));return b.toString();}private static void printUTF8(char ch) throws UnsupportedEncodingException {String unicode = toHex(ch >> 8) + toHex(ch & 0xFF);String unicodeBin = toBin(ch >> 8) + ' ' + toBin(ch & 0xFF);String s = "" + ch;byte[] b = s.getBytes("UTF-8");String hex = "";for (int i = 0; i < b.length; i++) {hex += toHex((int) b[i]);hex += " ";}String bin = "";for (int i = 0; i < b.length; i++) {bin += toBin((int) b[i]);bin += " ";}String sf = String.format("U+%s %s : %-8s : %s", unicode, unicodeBin, hex.trim(), bin.trim());System.out.println(sf);}public static void main(String[] args) throws Exception {printUTF8('/u002A');printUTF8('/u012A');printUTF8('/u012B');printUTF8('/u052C');printUTF8('/u013C');printUTF8('/uAA2A');printUTF8('/uFDFD');}}

输出： 

U+002A 00000000 00101010 : 2A       : 00101010

U+012A 00000001 00101010 : C4 AA    : 11000100 10101010 

U+012B 00000001 00101011 : C4 AB    : 11000100 10101011 

U+052C 00000101 00101100 : D4 AC    : 11010100 10101100 

U+013C 00000001 00111100 : C4 BC    : 11000100 10111100 

U+AA2A 10101010 00101010 : EA A8 AA : 11101010 10101000 10101010 

U+FDFD 11111101 11111101 : EF B7 BD : 11101111 10110111 10111101 

UCS-2和UTF-8的转换，只涉及到位运算，不需要像GBK般需要查找代码表，所以转换效率很高。 

先来说说UTF-8转UCS-2： 

（1）对于以0开始的字节，直接在前面部补一个0的字节凑成2个字节（即0xxxxxxx ==> 00000000 0xxxxxxxx）； 

（2）对于以110开始（110xxxxx）的字节，把后面紧跟着的一个10xxxxxx拿过来，首先在高位字节的左边补5个零，然后把11个“x”放在右边（即110xxxxx 10yyyyyy ==> 00000xxx xxyyyyyy）； 

（3）对于以1110开始（1110xxxx）的字节，把后面紧跟着的两个10xxxxxx拿过来，数一下，一共有16个“x”，没错，就是把这16个“x”组成两个字节（即1110xxxx 10yyyyyy 10zzzzzz ==> xxxxyyyy yyzzzzzz）。 

再来说说UCS-2转UTF-8： 

（1）对于不大于0x007F（即00000000 01111111）的，直接把它转成一个字节，变成ASCII； 

（2）对于不大于0x07FF（即00000111 11111111）的，转换成两个字节，转换的时候把右边的11位分别放到110xxxxx 10yyyyyy里边，即00000aaa bbbbbbbb ==> 110aaabb 10bbbbbb 

（3）剩下的回转换成三个字节，转换的时候也是把16个位分别填写到那三个字节里面，即aaaaaaaa bbbbbbbb ==> 1110aaaa 10aaaabb 10bbcccccc 下面是转换的实现代码： 

 

package com.ray.utf8;import java.io.ByteArrayOutputStream;import java.io.UnsupportedEncodingException;public class Utf8Utils {private final static byte B_10000000 = 128 - 256;private final static byte B_11000000 = 192 - 256;private final static byte B_11100000 = 224 - 256;private final static byte B_11110000 = 240 - 256;private final static byte B_00011100 = 28;private final static byte B_00000011 = 3;private final static byte B_00111111 = 63;private final static byte B_00001111 = 15;private final static byte B_00111100 = 60;/** Convert from UTF8 bytes to UNICODE character */public static char[] toUCS2(byte[] utf8Bytes) {CharList charList = new CharList();byte b2 = 0, b3 = 0;int ub1 = 0, ub2 = 0;for (int i = 0; i < utf8Bytes.length; i++) {byte b = utf8Bytes[i];if (isNotHead(b)) {// start with 10xxxxxx, skip it.continue;} else if (b > 0) {// 1 byte, ASCIIcharList.add((char) b);} else if ((b & B_11110000) == B_11110000) {// UCS-4, here we skip itcontinue;} else if ((b & B_11100000) == B_11100000) {// 3 bytesb2 = utf8Bytes[i+1];if (!isNotHead(b2)) continue;i++;b3 = utf8Bytes[i+1];if (!isNotHead(b3)) continue;i++;ub1 = ((b & B_00001111) << 4) + ((b2 & B_00111100) >> 2);ub2 = ((b2 & B_00000011) << 6) + ((b3 & B_00111111));charList.add(makeChar(ub1, ub2));} else {// 2 bytesb2 = utf8Bytes[i+1];if (!isNotHead(b2)) continue;i++;ub1 = (b & B_00011100) >> 2;ub2 = ((b & B_00000011) << 6) + (b2 & B_00111111);charList.add(makeChar(ub1, ub2));}}return charList.toArray();}private static boolean isNotHead(byte b) {return (b & B_11000000) == B_10000000;}private static char makeChar(int b1, int b2) {return (char) ((b1 << 8) + b2);}public static byte[] fromUCS2(char[] ucs2Array) {ByteArrayOutputStream baos = new ByteArrayOutputStream();for (int i = 0; i < ucs2Array.length; i++) {char ch = ucs2Array[i];if (ch <= 0x007F) {baos.write(ch);} else if (ch <= 0x07FF) {int ub1 = ch >> 8;int ub2 = ch & 0xFF;int b1 = B_11000000 + (ub1 << 2) +  (ub2 >> 6);int b2 = B_10000000 + (ub2 & B_00111111);baos.write(b1);baos.write(b2);} else {int ub1 = ch >> 8;int ub2 = ch & 0xFF;int b1 = B_11100000 + (ub1 >> 4);int b2 = B_10000000 + ((ub1 & B_00001111) << 2) + (ub2 >> 6);int b3 = B_10000000 + (ub2 & B_00111111);baos.write(b1);baos.write(b2);baos.write(b3);}}return baos.toByteArray();}private static class CharList {private char[] data = null;private int used = 0;public void add(char c) {if (data == null) {data = new char[16];} else if (used >= data.length) {char[] temp = new char[data.length * 2];System.arraycopy(data, 0, temp, 0, used);data = temp;}data[used++] = c;}public char[] toArray() {char[] chars = new char[used];System.arraycopy(data, 0, chars, 0, used);return chars;}}private static void assert1(String s) throws UnsupportedEncodingException {byte[] b = s.getBytes("utf-8");char[] c = toUCS2(b);if (!s.equals(new String(c))) {throw new RuntimeException("Can not pass assert1 for: " + s);}}private static void assert2(String s) throws UnsupportedEncodingException {byte[] b = s.getBytes("utf-8");byte[] b2 = fromUCS2(s.toCharArray());if (b.length == b2.length) {int i;for (i = 0; i < b.length; i++) {if (b[i] != b2[i]) {break;}}if (i == b.length) {return;}}throw new RuntimeException("Can not pass assert2 for: " + s);}public static void main(String[] args) throws Exception {assert1("test");assert1("中文测试");assert1("A中V文c测d试E");assert1("/u052CA/u052CBc测");assert2("test");assert2("中文测试");assert2("A中V文c测d试E");assert2("/u052CA/u052CBc测/u007F/u07FF");System.out.println("pass");}}

 

 

http://my.oschina.net/soar/blog/2524