JAVA对URL的解码【转】

前段时间做URL的中文转换,有些url是utf8的格式,有的是gb2312的格式,找了好久,发现网上的一个牛人写的转换代码:

JAVA对URL的解码【转】
package org.apache.hadoop.examples;
import java.io.UnsupportedEncodingException;
//import java.net.URLEncoder;
import java.net.URLDecoder;
/**
* <p>Title:字符编码工具类 </p>
* <p>Description:  </p>
* <p>Copyright: flashman.com.cn Copyright (c) 2005</p>
* <p>Company: flashman.com.cn </p>
* @author: jeffzhu
* @version 1.0
*/
public class CharTools {
    /**
    * 转换编码 ISO-8859-1到GB2312
    * @param text
    * @return
    */
    public String ISO2GB(String text) {
        String result = "";
        try {
        result = new String(text.getBytes("ISO-8859-1"), "GB2312");
        }
        catch (UnsupportedEncodingException ex) {
        result = ex.toString();
        }
        return result;
    }
    /**
    * 转换编码 GB2312到ISO-8859-1
    * @param text
    * @return
    */
    public String GB2ISO(String text) {
        String result = "";
        try {
        result = new String(text.getBytes("GB2312"), "ISO-8859-1");
        }
        catch (UnsupportedEncodingException ex) {
        ex.printStackTrace();
        }
        return result;
    }
    /**
    * Utf8URL编码
    * @param s
    * @return
    */
    public String Utf8URLencode(String text) {
        StringBuffer result = new StringBuffer();
        for (int i = 0; i < text.length(); i++) {
            char c = text.charAt(i);
            if (c >= 0 && c <= 255) {
            result.append(c);
            }else {
            byte[] b = new byte[0];
            try {
            b = Character.toString(c).getBytes("UTF-8");
            }catch (Exception ex) {
            }
            for (int j = 0; j < b.length; j++) {
                int k = b[j];
                if (k < 0) k += 256;
                result.append("%" + Integer.toHexString(k).toUpperCase());
            }
            }
        }
        return result.toString();
    }
    /**
    * Utf8URL解码
    * @param text
    * @return
    */
    public String Utf8URLdecode(String text) {
        String result = "";
        int p = 0;
        if (text!=null && text.length()>0){
        text = text.toLowerCase();
        p = text.indexOf("%e");
        if (p == -1) return text;
        while (p != -1) {
        result += text.substring(0, p);
        text = text.substring(p, text.length());
        if (text == "" || text.length() < 9) return result;
        result += CodeToWord(text.substring(0, 9));
        text = text.substring(9, text.length());
        p = text.indexOf("%e");
        }
        }
        return result + text;
    }
    /**
    * utf8URL编码转字符
    * @param text
    * @return
    */
    private String CodeToWord(String text) {
        String result;
        if (Utf8codeCheck(text)) {
        byte[] code = new byte[3];
        code[0] = (byte) (Integer.parseInt(text.substring(1, 3), 16) - 256);
        code[1] = (byte) (Integer.parseInt(text.substring(4, 6), 16) - 256);
        code[2] = (byte) (Integer.parseInt(text.substring(7, 9), 16) - 256);
        try {
        result = new String(code, "UTF-8");
        }catch (UnsupportedEncodingException ex) {
        result = null;
        }
        }
        else {
        result = text;
        }
        return result;
    }
    /**
    * 编码是否有效
    * @param text
    * @return
    */
    private boolean Utf8codeCheck(String text){
        String sign = "";
        if (text.startsWith("%e"))
        for (int i = 0, p = 0; p != -1; i++) {
        p = text.indexOf("%", p);
        if (p != -1)
        p++;
        sign += p;
        }
        return sign.equals("147-1");
    }
    /**
    * 是否Utf8Url编码
    * @param text
    * @return
    */
    public boolean isUtf8Url(String text) {
        text = text.toLowerCase();
        int p = text.indexOf("%");
        if (p != -1 && text.length() - p > 9) {
        text = text.substring(p, p + 9);
        }
        return Utf8codeCheck(text);
    }
    /**
    * 测试
    * @param args
    */
//            public static void main(String[] args) throws Exception{
//            CharTools charTools = new CharTools();
//            String url;
//            url = "http://www.google.com/search?hl=zh-CN&newwindow=1&q=%E4%B8%AD%E5%9B%BD%E5%A4%A7%E7%99%BE%E7%A7%91%E5%9C%A8%E7%BA%BF%E5%85%A8%E6%96%87%E6%A3%80%E7%B4%A2&btnG=%E6%90%9C%E7%B4%A2&lr=";
//            if(charTools.isUtf8Url(url)){
//            System.out.println(charTools.Utf8URLdecode(url));
//            }else{
//            System.out.println(URLDecoder.decode(url,"gb2312"));
//            }
//            url = "http://www.baidu.com/baidu?word=%D6%D0%B9%FA%B4%F3%B0%D9%BF%C6%D4%DA%CF%DF%C8%AB%CE%C4%BC%EC%CB%F7&tn=myie2dg";
//            if(charTools.isUtf8Url(url)){
//            System.out.println(charTools.Utf8URLdecode(url));
//            }else{
//            System.out.println(URLDecoder.decode(url,"gb2312"));
//            }
//            }
}
JAVA对URL的解码【转】

转:http://www.360doc.com/content/06/0829/16/6246_193641.shtml

JAVA对URL的解码【转】,布布扣,bubuko.com

JAVA对URL的解码【转】

上一篇:[009]转+修正---C++的贪吃蛇程序(未用面向对象封装)


下一篇:微信直接打开浏览器的实现方式