java中url汉字编码互相转换实例

java代码如下:

package com.gjob.common;
public class urltoutf8 {
    //转换为%e4%bd%a0形式
    public static string toutf8string(string s) {
        stringbuffer sb = new stringbuffer();
        for (int i = 0; i < s.length(); i++) {
            char c = s.charat(i);
            if (c >= 0 && c <= 255) {
                sb.append(c);
            } else {
                byte[] b;
                try {
                    b = string.valueof(c).getbytes("utf-8");
                } catch (exception ex) {
                    system.out.println(ex);
                    b = new byte[0];
                }
                for (int j = 0; j < b.length; j++) {
                    int k = b[j];
                    if (k < 0)
                        k += 256;
                    sb.append("%" + integer.tohexstring(k).touppercase());
                }
            }
        }
        return sb.tostring();
    }

    //将%e4%bd%a0转换为汉字
    public static string unescape(string s) {
        stringbuffer sbuf = new stringbuffer();
        int l = s.length();
        int ch = -1;
        int b, sumb = 0;
        for (int i = 0, more = -1; i < l; i++) {
            /* get next byte b from url segment s */
            switch (ch = s.charat(i)) {
            case '%':
                ch = s.charat(++i);
                int hb = (character.isdigit((char) ch) ? ch - '0'
                        : 10 + character.tolowercase((char) ch) - 'a') & 0xf;
                ch = s.charat(++i);
                int lb = (character.isdigit((char) ch) ? ch - '0'
                        : 10 + character.tolowercase((char) ch) - 'a') & 0xf;
                b = (hb << 4) | lb;
                break;
            case '+':
                b = ' ';
                break;
            default:
                b = ch;
            }
            /* decode byte b as utf-8, sumb collects incomplete chars */
            if ((b & 0xc0) == 0x80) { // 10xxxxxx (continuation byte)  
                sumb = (sumb << 6) | (b & 0x3f); // add 6 bits to sumb  
                if (--more == 0)
                    sbuf.append((char) sumb); // add char to sbuf  
            } else if ((b & 0x80) == 0x00) { // 0xxxxxxx (yields 7 bits)  
                sbuf.append((char) b); // store in sbuf  
            } else if ((b & 0xe0) == 0xc0) { // 110xxxxx (yields 5 bits)  
                sumb = b & 0x1f;
                more = 1; // expect 1 more byte  
            } else if ((b & 0xf0) == 0xe0) { // 1110xxxx (yields 4 bits)  
                sumb = b & 0x0f;
                more = 2; // expect 2 more bytes  
            } else if ((b & 0xf8) == 0xf0) { // 11110xxx (yields 3 bits)  
                sumb = b & 0x07;
                more = 3; // expect 3 more bytes  
            } else if ((b & 0xfc) == 0xf8) { // 111110xx (yields 2 bits)  
                sumb = b & 0x03;
                more = 4; // expect 4 more bytes  
            } else /*if ((b & 0xfe) == 0xfc)*/{ // 1111110x (yields 1 bit)  
                sumb = b & 0x01;
                more = 5; // expect 5 more bytes  
            }
            /* we don't test if the utf-8 encoding is well-formed */
        }
        return sbuf.tostring();
    }

    public static void main(string[] args){
        system.out.println(urltoutf8.toutf8string("你"));
        system.out.println(urltoutf8.unescape("%e4%bd%a0%20%e5%a5%bd"));

    }
}

############
运行结果：

%e4%bd%a0
你 好