平時開發中,經常遇到中文轉換成中文轉換成Unicode編碼和Unicode編碼轉換成中文的問題,國際化的時候,也要遇到這個問題,
現在我就把中網上找的很自己學習的經驗,共享給大家了。閑話少說,步入正題,Java代碼如下:
轉貼請著名:http://www.tkk7.com/jerry-zhaoj/
- package test.com.gjob.services;
- import java.util.Properties;
- public class Test {
- public static void main(String[] args) {
- String s = "簡介";
- String tt = gbEncoding(s);
- // String tt1 = "你好,我想给你说一个事情";
- System.out.println(decodeUnicode("\\u7b80\\u4ecb"));
- // System.out.println(decodeUnicode(tt1));
- System.out.println(HTMLDecoder.decode("中国"));
- String s1 = "\u7b80\u4ecb";
- System.out.println(s.indexOf("\\"));
- }
- public static String gbEncoding(final String gbString) {
- char[] utfBytes = gbString.toCharArray();
- String unicodeBytes = "";
- for (int byteIndex = 0; byteIndex < utfBytes.length; byteIndex++) {
- String hexB = Integer.toHexString(utfBytes[byteIndex]);
- if (hexB.length() <= 2) {
- hexB = "00" + hexB;
- }
- unicodeBytes = unicodeBytes + "\\u" + hexB;
- }
- System.out.println("unicodeBytes is: " + unicodeBytes);
- return unicodeBytes;
- }
-
- public static String decodeUnicode(final String dataStr) {
- int start = 0;
- int end = 0;
- final StringBuffer buffer = new StringBuffer();
- while (start > -1) {
- end = dataStr.indexOf("\\u", start + 2);
- String charStr = "";
- if (end == -1) {
- charStr = dataStr.substring(start + 2, dataStr.length());
- } else {
- charStr = dataStr.substring(start + 2, end);
- }
- char letter = (char) Integer.parseInt(charStr, 16); // 16進制parse整形字符串。
- buffer.append(new Character(letter).toString());
- start = end;
- }
- return buffer.toString();
- }
- }