平时开发中,经常遇到中文转换成中文转换成Unicode编码和Unicode编码转换成中文的问题,国际化的时候,也要遇到这个问题,
现在我就把中网上找的很自己学习的经验,共享给大家了。闲话少说,步入正题,
Java代码如下:
[java] view plain copy
- package test.com.gjob.services;
- import java.util.Properties;
- public class Test {
- public static void main(String[] args) {
- String s = "简介";
- 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进制parse整形字符串。
- buffer.append(new Character(letter).toString());
- start = end;
- }
- return buffer.toString();
- }
- }
unicode转换成中文
[java] view plain copy
- public static String decodeUnicode(String theString) {
- char aChar;
- int len = theString.length();
- StringBuffer outBuffer = new StringBuffer(len);
- for (int x = 0; x < len;) {
- aChar = theString.charAt(x++);
- if (aChar == ‘\\‘) {
- aChar = theString.charAt(x++);
- if (aChar == ‘u‘) {
- // Read the xxxx
- int value = 0;
- for (int i = 0; i < 4; i++) {
- aChar = theString.charAt(x++);
- switch (aChar) {
- case ‘0‘:
- case ‘1‘:
- case ‘2‘:
- case ‘3‘:
- case ‘4‘:
- case ‘5‘:
- case ‘6‘:
- case ‘7‘:
- case ‘8‘:
- case ‘9‘:
- value = (value << 4) + aChar - ‘0‘;
- break;
- case ‘a‘:
- case ‘b‘:
- case ‘c‘:
- case ‘d‘:
- case ‘e‘:
- case ‘f‘:
- value = (value << 4) + 10 + aChar - ‘a‘;
- break;
- case ‘A‘:
- case ‘B‘:
- case ‘C‘:
- case ‘D‘:
- case ‘E‘:
- case ‘F‘:
- value = (value << 4) + 10 + aChar - ‘A‘;
- break;
- default:
- throw new IllegalArgumentException(
- "Malformed \\uxxxx encoding.");
- }
- }
- outBuffer.append((char) value);
- } else {
- if (aChar == ‘t‘)
- aChar = ‘\t‘;
- else if (aChar == ‘r‘)
- aChar = ‘\r‘;
- else if (aChar == ‘n‘)
- aChar = ‘\n‘;
- else if (aChar == ‘f‘)
- aChar = ‘\f‘;
- outBuffer.append(aChar);
- }
- } else
- outBuffer.append(aChar);
- }
- return outBuffer.toString();
- }
时间: 2024-10-14 08:47:44