返回顶部

收藏

UTF2GBK

更多
public class UTF2GBK {

    public String gbk2utf8(String gbk) {
        String l_temp = GBK2Unicode(gbk);
        l_temp = unicodeToUtf8(l_temp);

        return l_temp;
    }

    public String utf82gbk(String utf) {
        String l_temp = utf8ToUnicode(utf);
        l_temp = Unicode2GBK(l_temp);

        return l_temp;
    }

    /**
     * 
     * @param str
     * @return String
     */

    public static String GBK2Unicode(String str) {
        StringBuffer result = new StringBuffer();
        for (int i = 0; i < str.length(); i++) {
            char chr1 = (char) str.charAt(i);

            if (!isNeedConvert(chr1)) {
                result.append(chr1);
                continue;
            }

            result.append("\\\\u" + Integer.toHexString((int) chr1));
        }

        return result.toString();
    }

    /**
     * 
     * @param dataStr
     * @return String
     */

    public static String Unicode2GBK(String dataStr) {
        int index = 0;
        StringBuffer buffer = new StringBuffer();

        int li_len = dataStr.length();
        while (index < li_len) {
            if (index >= li_len - 1
                    || !"\\\\u".equals(dataStr.substring(index, index + 2))) {
                buffer.append(dataStr.charAt(index));

                index++;
                continue;
            }

            String charStr = "";
            charStr = dataStr.substring(index + 2, index + 6);

            char letter = (char) Integer.parseInt(charStr, 16);

            buffer.append(letter);
            index += 6;
        }

        return buffer.toString();
    }

    public static boolean isNeedConvert(char para) {
        return ((para & (0x00FF)) != para);
    }

    /**
     * utf-8 转unicode
     * 
     * @param inStr
     * @return String
     */
    public static String utf8ToUnicode(String inStr) {
        char[] myBuffer = inStr.toCharArray();

        StringBuffer sb = new StringBuffer();
        for (int i = 0; i < inStr.length(); i++) {
            UnicodeBlock ub = UnicodeBlock.of(myBuffer[i]);
            if (ub == UnicodeBlock.BASIC_LATIN) {
                sb.append(myBuffer[i]);
            } else if (ub == UnicodeBlock.HALFWIDTH_AND_FULLWIDTH_FORMS) {
                int j = (int) myBuffer[i] - 65248;
                sb.append((char) j);
            } else {
                short s = (short) myBuffer[i];
                String hexS = Integer.toHexString(s);
                String unicode = "\\\\u" + hexS;
                sb.append(unicode.toLowerCase());
            }
        }
        return sb.toString();
    }

    /**
     * 
     * @param theString
     * @return String
     */
    public static String unicodeToUtf8(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();
    }

}
//该片段来自于http://outofmemory.cn

标签:java,基础

收藏

0人收藏

支持

0

反对

0

相关聚客文章
  1. 郑 旭东 发表 2014-01-16 16:46:51 JAVA多线程和并发基础面试问答
  2. Terry Zhang 发表 2014-04-17 15:27:06 [正则] 字符类型
  3. Terry Zhang 发表 2014-04-27 10:43:29 [集合框架] 接口
  4. 逍遥冲 发表 2013-12-05 05:53:28 [引]Java NIO —- IO复用
  5. 糖果 发表 2015-08-03 21:33:22 逆向基础(十三) JAVA (四)
  6. Terry Zhang 发表 2014-04-18 05:08:52 [NIO.2] 编写一个文件拷贝应用
  7. Terry Zhang 发表 2014-04-24 08:14:18 [正则] 边界匹配器
  8. Terry Zhang 发表 2014-05-03 06:33:32 [集合框架] List 接口
  9. Terry Zhang 发表 2014-05-13 06:05:01 [集合框架] SortedSet 接口
  10. 逍遥冲 发表 2013-12-30 14:13:10 [引]编译器自举和移植
  11. 糖果 发表 2015-08-03 20:25:16 逆向基础(十三) JAVA (三)
  12. 博主 发表 2013-03-12 14:17:00 Java基础学习之Enum

发表评论