Java字符串找出4个字节长度的字符
不解释，直接上代码：由于Iteye代码贴四个字节的ＵＴＦ－８字符出错，特能图的方式发布几个特殊字符：
http://dl.iteye.com/upload/attachment/0075/8460/efb377f0-c112-3ba2-b1a9-d39b61b1e87e.png
public class Byte4Check {public static void main(String args[]) throws UnsupportedEncodingException {String nickName = "12葫";byte[] t = nickName.substring(0, 1).getBytes("UTF-8");for (byte tt : t) {System.out.println(tt);}System.out.println("====================");byte[] t1 = nickName.getBytes("UTF-8");for (int i = 0; i < t1.length;) {byte tt = t1;if (CharUtils.isAscii((char) tt)) {byte[] ba = new byte;ba = tt;i++;String result = new String(ba);System.out.println("1个字节的字符");System.out.println("字符为：" + result);}if ((tt & 0xE0) == 0xC0) {byte[] ba = new byte;ba = tt;ba = t1;i++;i++;String result = new String(ba);System.out.println("2个字节的字符");System.out.println("字符为：" + result);}if ((tt & 0xF0) == 0xE0) {byte[] ba = new byte;ba = tt;ba = t1;ba = t1;i++;i++;i++;String result = new String(ba);System.out.println("3个字节的字符");System.out.println("字符为：" + result);}if ((tt & 0xF8) == 0xF0) {byte[] ba = new byte;ba = tt;ba = t1;ba = t1;ba = t1;i++;i++;i++;i++;String result = new String(ba);System.out.println("4个字节的字符");System.out.println("字符为：" + result);}}}}
参考文献：
http://www.yunmx.com/archives/2011/138.htm
http://zh.wikipedia.org/wiki/UTF-8
页:
[1]