在Java中正确解码用Javascript:escape()编码的中文字符

       在做页面开发时使用了Javascript的escape()函数进行URL编码，如果url中有中文，结果在JSP或Servlet中用request.getParameter()时取不到参数，只返回一个空值。经过Baidu的搜索终于找到了问题所在及解决的办法。

        本来Javascript中的escape()是将中文按ISO-8859-1字符集进行URL编码的，那样通过 request.getParameter()是能直接获取到请求参数的，但后来的Javascript将escape()换成了Unicode字符集编 码，如此一来，在JSP和Servlet中就没法直接拿到请求参数了，具体原因我也不知道。

        解决办法：

        1、首先对中文字符进行两次escape()编码，如要传参数name，值为“你好”，则url的格式为....name=escape(escape("你好"))，这样一来，在request.getParameter()就能取到编码后的参数了。

        2、由于取到的参数是  %25u4F60%25u597D  格式的，没法用常规的URLDecoder.decode()来进行解码，还好，这世上的牛人够多，在网上直接找到了一个工具类，能实现 Javascript中escape()及unescape()式的编解码，源代码如下：
**
 * JavaScript escape/unescape 编码的 Java 实现
 * author jackyz
 * keep this copyright info while using this method by free
 */
public class Escape {
    private final static String[] hex = {
        "00","01","02","03","04","05","06","07","08","09","0A","0B","0C","0D","0E","0F",
        "10","11","12","13","14","15","16","17","18","19","1A","1B","1C","1D","1E","1F",
        "20","21","22","23","24","25","26","27","28","29","2A","2B","2C","2D","2E","2F",
        "30","31","32","33","34","35","36","37","38","39","3A","3B","3C","3D","3E","3F",
        "40","41","42","43","44","45","46","47","48","49","4A","4B","4C","4D","4E","4F",
        "50","51","52","53","54","55","56","57","58","59","5A","5B","5C","5D","5E","5F",
        "60","61","62","63","64","65","66","67","68","69","6A","6B","6C","6D","6E","6F",
        "70","71","72","73","74","75","76","77","78","79","7A","7B","7C","7D","7E","7F",
        "80","81","82","83","84","85","86","87","88","89","8A","8B","8C","8D","8E","8F",
        "90","91","92","93","94","95","96","97","98","99","9A","9B","9C","9D","9E","9F",
        "A0","A1","A2","A3","A4","A5","A6","A7","A8","A9","AA","AB","AC","AD","AE","AF",
        "B0","B1","B2","B3","B4","B5","B6","B7","B8","B9","BA","BB","BC","BD","BE","BF",
        "C0","C1","C2","C3","C4","C5","C6","C7","C8","C9","CA","CB","CC","CD","CE","CF",
        "D0","D1","D2","D3","D4","D5","D6","D7","D8","D9","DA","DB","DC","DD","DE","DF",
        "E0","E1","E2","E3","E4","E5","E6","E7","E8","E9","EA","EB","EC","ED","EE","EF",
        "F0","F1","F2","F3","F4","F5","F6","F7","F8","F9","FA","FB","FC","FD","FE","FF"
    };
    private final static byte[] val = {
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x00,0x01,0x02,0x03,0x04,0x05,0x06,0x07,0x08,0x09,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x0A,0x0B,0x0C,0x0D,0x0E,0x0F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,
        0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F,0x3F
    };
    public static String escape(String s) {
        StringBuffer sbuf = new StringBuffer();
        int len = s.length();
        for (int i = 0; i < len; i++) {
            int ch = s.charAt(i);
            if (ch == ' ') {                        // space : map to '+'
                sbuf.append('+');
            } else if ('A' <= ch && ch <= 'Z') {    // 'A'..'Z' : as it was
                sbuf.append((char)ch);
            } else if ('a' <= ch && ch <= 'z') {    // 'a'..'z' : as it was
                sbuf.append((char)ch);
            } else if ('0' <= ch && ch <= '9') {    // '0'..'9' : as it was
                sbuf.append((char)ch);
            } else if (ch == '-' || ch == '_'       // unreserved : as it was
                || ch == '.' || ch == '!'
                || ch == '~' || ch == '*'
                || ch == '\'' || ch == '('
                || ch == ')') {
                sbuf.append((char)ch);
            } else if (ch <= 0x007F) {              // other ASCII : map to %XX
                sbuf.append('%');
                sbuf.append(hex[ch]);
            } else {                                // unicode : map to %uXXXX
                sbuf.append('%');
                sbuf.append('u');
                sbuf.append(hex[(ch >>> 8)]);
                sbuf.append(hex[(0x00FF & ch)]);
            }
    &nbsp;   }
        return sbuf.toString();
    }
    public static String unescape(String s) {
        StringBuffer sbuf = new StringBuffer();
        int i = 0;
        int len = s.length();
        while (i < len) {
            int ch = s.charAt(i);
            if (ch == '+') {                        // + : map to ' '
                sbuf.append(' ');
            } else if ('A' <= ch && ch <= 'Z') {    // 'A'..'Z' : as it was
                sbuf.append((char)ch);
            } else if ('a' <= ch && ch <= 'z') {    // 'a'..'z' : as it was
                sbuf.append((char)ch);
            } else if ('0' <= ch && ch <= '9') {    // '0'..'9' : as it was
                sbuf.append((char)ch);
            } else if (ch == '-' || ch == '_'       // unreserved : as it was
                || ch == '.' || ch == '!'
                || ch == '~' || ch == '*'
                || ch == '\'' || ch == '('
                || ch == ')') {
                sbuf.append((char)ch);
            } else if (ch == '%') {
                int cint = 0;
                if ('u' != s.charAt(i+1)) {         // %XX : map to ascii(XX)
                    cint = (cint << 4) | val[s.charAt(i+1)];
                    cint = (cint << 4) | val[s.charAt(i+2)];
                    i+=2;
                } else {                            // %uXXXX : map to unicode(XXXX)
                    cint = (cint << 4) | val[s.charAt(i+2)];
                    cint = (cint << 4) | val[s.charAt(i+3)];
                    cint = (cint << 4) | val[s.charAt(i+4)];
                    cint = (cint << 4) | val[s.charAt(i+5)];
                    i+=5;
                }
                sbuf.append((char)cint);
            }
            i++;
        }
        return sbuf.toString();
    }
    public static void main(String[] args) {
        String stest = "中文1234 abcd[]()<+>,.~\\";
        System.out.println(stest);
        System.out.println(escape(stest));
        System.out.println(unescape(escape(stest)));
    }
}
有了这个工具类，直接用Escape.unescape()方法就能将获取到的参数解码成中文格式了。

评论

3 楼 hupengfeijiayou 2009-09-17  

  其实不用那个工具类那么麻烦,在客户端对将要发送的中文字符进行两次EncodeURI("中文"),然后在服务端用URLDecoder.decode()对接受到的客户端参数进行解码就可以得到正确的中文字符。
这是一种通用的解决方案,希望楼主可以试验一下。

2 楼 lianda220 2009-09-03  

很好 很强大啊   呵呵 

1 楼 mtvwang 2009-08-19  

及时雨啊  ， 解决了 我的问题啊
很好。