一、encodeURIComponent()
1.encodeURIComponent()方法的使用
语法：encodeURIComponent(URIstring)
参数：URIstring，必需。一个字符串，含有 URI 组件或其他要编码的文本。
2.encodeURIComponent()测试
测试
document.write(encodeURIComponent("https://www.sojson.com/encodeurl.html?我是个中文参数"))
document.write("
")
document.write(encodeURIComponent(",/?:@&=+$#"))
结果
http%3A%2F%2Fwww.sojson.com%2Fencodeurl.html%3F%E6%88%91%E6%98%AF%E4%B8%AA%E4%B8%AD%E6%96%87%E5%8F%82%E6%95%B0
%3Cbr%20%2F%3E
%2C%2F%3F%3A%40%26%3D%2B%24%23
二、encodeURI()测试
测试
document.write(encodeURI("https://www.sojson.com/encodeurl.html?我是个中文参数"))
document.write("
")
document.write(encodeURI(",/?:@&=+$#"))
结果
https://www.sojson.com/encodeurl.html?%E6%88%91%E6%98%AF%E4%B8%AA%E4%B8%AD%E6%96%87%E5%8F%82%E6%95%B0
%3Cbr%20/%3E
,/?:@&=+$#
三、 encodeURIComponent() 函数 与 encodeURI() 函数的区别
请注意 encodeURIComponent() 函数 与 encodeURI() 函数的区别之处，前者假定它的参数是 URI 的一部分(比如协议、主机名、路径或查询字符串)。因此 encodeURIComponent() 函数将转义用于分隔 URI 各个部分的标点符号。
广告 for Goolge

此文仅对自己工作中用到的类进行总结，方便以后的使用。

package com.cn.hnust.util;

import java.io.UnsupportedEncodingException;
import java.util.HashMap;
import java.util.Map;
/**
 * url转码、解码
 *
 * @author
 * @date 
 */
public class UrlUtil {
    private final static String ENCODE = "GBK"; 
    /**
     * URL 解码
     *
     * @return String
     * @author lifq
     * @date 2015-3-17 下午04:09:51
     */
    public static String getURLDecoderString(String str) {
        String result = "";
        if (null == str) {
            return "";
        }
        try {
            result = java.net.URLDecoder.decode(str, ENCODE);
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        return result;
    }
    /**
     * URL 转码
     *
     * @return String
     * @author lifq
     * @date 2015-3-17 下午04:10:28
     */
    public static String getURLEncoderString(String str) {
        String result = "";
        if (null == str) {
            return "";
        }
        try {
            result = java.net.URLEncoder.encode(str, ENCODE);
        } catch (UnsupportedEncodingException e) {
            e.printStackTrace();
        }
        return result;
     }
    /**  
     * 正则替换  
     * @param url  
     * @param name  
     * @param value  
     * @return  
     */  
    public static String replaceUrlParameterReg(String url, String name, String value) {  
        if (StringUtils.isNotBlank(url) && StringUtils.isNotBlank(value)) {  
            url = url.replaceAll("(" + name + "=[^&]*)", name + "=" + value);  
        }  
        return url;  
    }  
    /**  
     * 正则替换  
     * @param url  
     * @param name  
     * @param value  
     * @return  
     */  
    public static String getUrlParameterReg(String url, String name) {

        Map<String, String> mapRequest = new HashMap<String, String>();

          String[] arrSplit=null;

        String strUrlParam=TruncateUrlPage(url);
        if(strUrlParam==null)
        {
            return "";
        }
          //每个键值为一组 www.2cto.com
        arrSplit=strUrlParam.split("[&]");
        for(String strSplit:arrSplit)
        {
              String[] arrSplitEqual=null;         
              arrSplitEqual= strSplit.split("[=]");

              //解析出键值
              if(arrSplitEqual.length>1)
              {
                  //正确解析
                  mapRequest.put(arrSplitEqual[0], arrSplitEqual[1]);

              }
              else
              {
                  if(arrSplitEqual[0]!="")
                  {
                  //只有参数没有值，不加入
                  mapRequest.put(arrSplitEqual[0], "");       
                  }
              }
        }   
        return mapRequest.get(name);  
    }  
    /**
     * 去掉url中的路径，留下请求参数部分
     * @param strURL url地址
     * @return url请求参数部分
     */
    private static String TruncateUrlPage(String strURL)
    {
    String strAllParam=null;
      String[] arrSplit=null;

      strURL=strURL.trim().toLowerCase();

      arrSplit=strURL.split("[?]");
      if(strURL.length()>1)
      {
          if(arrSplit.length>1)
          {
                  if(arrSplit[1]!=null)
                  {
                  strAllParam=arrSplit[1];
                  }
          }
      }

    return strAllParam;   
    }
    public static void main(String[] args) {
        String str ="/activePage?wxto=0C29975119DE037B4F25CD119CF4CF11&activity2018topid=oz9Zj07Jg5O9IfAyVauT-GL-CSfM&activity2018topunid=o-NUA0l8fxm2_5fmK_ocpyxrP1dE&subscribe=0&timestamp=1516008942920&-NUA0l8fxm2_5fmK_ocpyxrP1dE&oaccesstoken=5_xJYY3gnUTD4pqJFc7_ltbvclb0ZRKOFBEc5BXAwi7vjZndRAN58AkPazqUJDGzBbrw-J1ag1PF0C-S39SqJflA&m=1&wxt=C9A58DA3804E46981BF4B78C8C862743&-NUA0oHjJjCcyGe-wJdEFYjwrfU&-NUA0oHjJjCcyGe-wJdEFYjwrfU&-NUA0oHjJjCcyGe-wJdEFYjwrfU";
        String m = "9j70Dj%2BpVA64qK9%2FeOjsg2dP3biHh6imIC6WFXtIRcR6nHwDkjHPNOL9zUi7fmpcbgJP3u%2Bh3VUTfDO0B2fsbKWsizlqOKdXJovkg3HZMTxAIcByvYvtHoCyd9iOgUxoDqslzoMunvnEzPS8FbYc%2Fjkd4y47zhKk%2FUTE4GGm8ZM5Ns5eYwZSFL7A8pX0U%2BXfsMR%2FGf5z2pci6a5BJaki4e0z0Pmh5sPsjytmKdjdssHQ98iZ8ge3mXJm7G%2FaSJ3e%2FHvNENLv0JRJf7q1bFu180RZEtsMRs%2BWdesTuJamtJBYtLxQEYaCMygRcmd%2F1VdSqfLnuZqcZAzT6GAmvBwZyfzCK9LffGsyZGWce%2B0g2R%2FTCKTTtNpWWCJb0e7Gs0g82DmBNV4jh3hrOAmeLNwpu0M%2B049%2FHrDxAZPvXowCb5OLb7if%2BVqBpYkphGssurkqLV2KTXx3vhjl9vIiMQnD4397oNYf81P%2BBWFPBFhPQSfGaxZGZbAlPgkluR4%2Fj75f9SeZlcWFMnl%2BYKYtopw1gw%3D%3D";
        System.out.println(getURLEncoderString(m));
        System.out.println(getURLDecoderString(m));
      //System.out.println( getUrlParameterReg(str,"wxto"));
    }
}



 

对 url 中含有的中文进行转码操作
一般情况下，将带有中文的 url 拷贝到开发工具，开发工具都会有相应的转码(自动转码)，
现在大部分的浏览器也可以对含有中文的 url 进行转码(自动转码)
情景说明
android
安卓系统，能够识别中文路径：
https://spdbimg.idoupiao.com/film/my/美国队长3
IOS
苹果系统，不能够识别中文路径：
https://spdbimg.idoupiao.com/film/my/美国队长3
必须将以上路径进行转码为下来形式才可以访问：
https://spdbimg.idoupiao.com/film/my/%E7%BE%8E%E5%9B%BD%E9%98%9F%E9%95%BF3
这和他们各自的战略定位有关系。。。
编码实现
1、先寻找有没有已经实现类似功能的成熟工具。
2、找到 JDK 提供的 URLEncoder 类的 encode 方法基本满足需求。
3、测试是否满足当下需求。
经过测试发现，JDK 提供的 URLEncoder 类的 encode 方法会将 ':' 和 '/' 等字符也进行编码。
4、查找 JDK 提供的 URLEncoder 类的 encode 方法 相关源码。
5、发现可以进行部分改造满足当前需求，重写 URLEncoder 类，并将其设置为私有静态类，多人合作时，防止他人误用。
6、改造完成进行验证型测试。
添加以下两条语句：
// 排除这两个特殊字符的编码
dontNeedEncoding.set(':');
dontNeedEncoding.set('/');
重写后的 URLEncoder 类：
/**
* Utility class for HTML form encoding. This class contains static methods
* for converting a String to the application/x-www-form-urlencoded MIME
* format. For more information about HTML form encoding, consult the HTML
* specification.
*
* 
* When encoding a String, the following rules apply:
*
* 
* 
The alphanumeric characters "{@code a}" through
*     "{@code z}", "{@code A}" through
*     "{@code Z}" and "{@code 0}"
*     through "{@code 9}" remain the same.
* 
The special characters "{@code .}",
*     "{@code -}", "{@code *}", and
*     "{@code _}" remain the same.
* 
The space character "   " is
*     converted into a plus sign "{@code +}".
* 
All other characters are unsafe and are first converted into
*     one or more bytes using some encoding scheme. Then each byte is
*     represented by the 3-character string
*     "{@code %xy}", where xy is the
*     two-digit hexadecimal representation of the byte.
*     The recommended encoding scheme to use is UTF-8. However,
*     for compatibility reasons, if an encoding is not specified,
*     then the default encoding of the platform is used.
* 
*
* 
* For example using UTF-8 as the encoding scheme the string "The
* string ü@foo-bar" would get converted to
* "The+string+%C3%BC%40foo-bar" because in UTF-8 the character
* ü is encoded as two bytes C3 (hex) and BC (hex), and the
* character @ is encoded as one byte 40 (hex).
*
* @author  Herb Jellinek
* @since   JDK1.0
*/
private static class URLEncoder {
static BitSet dontNeedEncoding;
static final int caseDiff = ('a' - 'A');
static String dfltEncName = null;
static {
/* The list of characters that are not encoded has been
* determined as follows:
*
* RFC 2396 states:
* -----
* Data characters that are allowed in a URI but do not have a
* reserved purpose are called unreserved.  These include upper
* and lower case letters, decimal digits, and a limited set of
* punctuation marks and symbols.
*
* unreserved  = alphanum | mark
*
* mark        = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
*
* Unreserved characters can be escaped without changing the
* semantics of the URI, but this should not be done unless the
* URI is being used in a context that does not allow the
* unescaped character to appear.
* -----
*
* It appears that both Netscape and Internet Explorer escape
* all special characters from this list with the exception
* of "-", "_", ".", "*". While it is not clear why they are
* escaping the other characters, perhaps it is safest to
* assume that there might be contexts in which the others
* are unsafe if not escaped. Therefore, we will use the same
* list. It is also noteworthy that this is consistent with
* O'Reilly's "HTML: The Definitive Guide" (page 164).
*
* As a last note, Intenet Explorer does not encode the "@"
* character which is clearly not unreserved according to the
* RFC. We are being consistent with the RFC in this matter,
* as is Netscape.
*
*/
dontNeedEncoding = new BitSet(256);
int i;
for (i = 'a'; i <= 'z'; i++) {
dontNeedEncoding.set(i);
}
for (i = 'A'; i <= 'Z'; i++) {
dontNeedEncoding.set(i);
}
for (i = '0'; i <= '9'; i++) {
dontNeedEncoding.set(i);
}
dontNeedEncoding.set(' '); /* encoding a space to a + is done
* in the encode() method */
dontNeedEncoding.set('-');
dontNeedEncoding.set('_');
dontNeedEncoding.set('.');
dontNeedEncoding.set('*');
// 排除这两个特殊字符的编码
dontNeedEncoding.set(':');
dontNeedEncoding.set('/');
dfltEncName = AccessController.doPrivileged(
new GetPropertyAction("file.encoding")
);
}
/**
* You can't call the constructor.
*/
private URLEncoder() { }
/**
* Translates a string into {@code x-www-form-urlencoded}
* format. This method uses the platform's default encoding
* as the encoding scheme to obtain the bytes for unsafe characters.
*
* @param   s   {@code String} to be translated.
* @deprecated The resulting string may vary depending on the platform's
*             default encoding. Instead, use the encode(String,String)
*             method to specify the encoding.
* @return  the translated {@code String}.
*/
@Deprecated
public static String encode(String s) {
String str = null;
try {
str = encode(s, dfltEncName);
} catch (UnsupportedEncodingException e) {
// The system should always have the platform default
}
return str;
}
/**
* Translates a string into {@code application/x-www-form-urlencoded}
* format using a specific encoding scheme. This method uses the
* supplied encoding scheme to obtain the bytes for unsafe
* characters.
* 
* Note: The 
* "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">
* World Wide Web Consortium Recommendation
 states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilities.
*
* @param   s   {@code String} to be translated.
* @param   enc   The name of a supported
*    character
*    encoding.
* @return  the translated {@code String}.
* @exception  UnsupportedEncodingException
*             If the named encoding is not supported
* @see URLDecoder#decode(java.lang.String, java.lang.String)
* @since 1.4
*/
public static String encode(String s, String enc)
throws UnsupportedEncodingException {
boolean needToChange = false;
StringBuffer out = new StringBuffer(s.length());
Charset charset;
CharArrayWriter charArrayWriter = new CharArrayWriter();
if (enc == null)
throw new NullPointerException("charsetName");
try {
charset = Charset.forName(enc);
} catch (IllegalCharsetNameException e) {
throw new UnsupportedEncodingException(enc);
} catch (UnsupportedCharsetException e) {
throw new UnsupportedEncodingException(enc);
}
for (int i = 0; i < s.length();) {
int c = (int) s.charAt(i);
//System.out.println("Examining character: " + c);
if (dontNeedEncoding.get(c)) {
if (c == ' ') {
c = '+';
needToChange = true;
}
//System.out.println("Storing: " + c);
out.append((char)c);
i++;
} else {
// convert to external encoding before hex conversion
do {
charArrayWriter.write(c);
/*
* If this character represents the start of a Unicode
* surrogate pair, then pass in two characters. It's not
* clear what should be done if a bytes reserved in the
* surrogate pairs range occurs outside of a legal
* surrogate pair. For now, just treat it as if it were
* any other character.
*/
if (c >= 0xD800 && c <= 0xDBFF) {
/*
System.out.println(Integer.toHexString(c)
+ " is high surrogate");
*/
if ( (i+1) < s.length()) {
int d = (int) s.charAt(i+1);
/*
System.out.println("\tExamining "
+ Integer.toHexString(d));
*/
if (d >= 0xDC00 && d <= 0xDFFF) {
/*
System.out.println("\t"
+ Integer.toHexString(d)
+ " is low surrogate");
*/
charArrayWriter.write(d);
i++;
}
}
}
i++;
} while (i < s.length() && !dontNeedEncoding.get((c = (int) s.charAt(i))));
charArrayWriter.flush();
String str = new String(charArrayWriter.toCharArray());
byte[] ba = str.getBytes(charset);
for (int j = 0; j < ba.length; j++) {
out.append('%');
char ch = Character.forDigit((ba[j] >> 4) & 0xF, 16);
// converting to use uppercase letter as part of
// the hex value if ch is a letter.
if (Character.isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
ch = Character.forDigit(ba[j] & 0xF, 16);
if (Character.isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
}
charArrayWriter.reset();
needToChange = true;
}
}
return (needToChange? out.toString() : s);
}
}
测试代码：
@Test
public void testReplace() throws UnsupportedEncodingException {
// https://ojjqzz83h.qnssl.com/film/my/美国队长3?imageView2/1/w/140/h/90/interlace/0/q/100
// https://spdbimg.idoupiao.com/film/my/%E7%BE%8E%E5%9B%BD%E9%98%9F%E9%95%BF3
String oldImgUrl = "https://spdbimg.idoupiao.com/film/my/美国队长3";
oldImgUrl = URLEncoder.encode(oldImgUrl, "UTF-8");
//        oldImgUrl = new String(Base64.getEncoder().encode(oldImgUrl.getBytes()));
String oldDomain = "spdbimg.idoupiao.com";
String newDomain = "ojjqzz83h.qnssl.com";
String suffix = "?imageView2/1/w/140/h/90/interlace/0/q/100";
String newImgUrl = StringUtils.replace(oldImgUrl, oldDomain, newDomain).concat(suffix);
System.out.println("newImgUrl === " + newImgUrl);
}
完整代码如下：
package com.github.ljmatlight.util;
import org.junit.Test;
import sun.security.action.GetPropertyAction;
import java.io.CharArrayWriter;
import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.nio.charset.Charset;
import java.nio.charset.IllegalCharsetNameException;
import java.nio.charset.UnsupportedCharsetException;
import java.security.AccessController;
import java.util.BitSet;
/**
* Description：对 url 中含有的中文进行转码操作
* 
 Author：ljmatlight
*/
public class StringTest {
@Test
public void testReplace() throws UnsupportedEncodingException {
// https://ojjqzz83h.qnssl.com/film/my/美国队长3?imageView2/1/w/140/h/90/interlace/0/q/100
// https://spdbimg.idoupiao.com/film/my/%E7%BE%8E%E5%9B%BD%E9%98%9F%E9%95%BF3
String oldImgUrl = "https://spdbimg.idoupiao.com/film/my/美国队长3";
oldImgUrl = URLEncoder.encode(oldImgUrl, "UTF-8");
//        oldImgUrl = new String(Base64.getEncoder().encode(oldImgUrl.getBytes()));
String oldDomain = "spdbimg.idoupiao.com";
String newDomain = "ojjqzz83h.qnssl.com";
String suffix = "?imageView2/1/w/140/h/90/interlace/0/q/100";
String newImgUrl = StringUtils.replace(oldImgUrl, oldDomain, newDomain).concat(suffix);
System.out.println("newImgUrl === " + newImgUrl);
}
/**
* Utility class for HTML form encoding. This class contains static methods
* for converting a String to the application/x-www-form-urlencoded MIME
* format. For more information about HTML form encoding, consult the HTML
* specification.
*
* 
* When encoding a String, the following rules apply:
*
* 
* 
The alphanumeric characters "{@code a}" through
*     "{@code z}", "{@code A}" through
*     "{@code Z}" and "{@code 0}"
*     through "{@code 9}" remain the same.
* 
The special characters "{@code .}",
*     "{@code -}", "{@code *}", and
*     "{@code _}" remain the same.
* 
The space character "   " is
*     converted into a plus sign "{@code +}".
* 
All other characters are unsafe and are first converted into
*     one or more bytes using some encoding scheme. Then each byte is
*     represented by the 3-character string
*     "{@code %xy}", where xy is the
*     two-digit hexadecimal representation of the byte.
*     The recommended encoding scheme to use is UTF-8. However,
*     for compatibility reasons, if an encoding is not specified,
*     then the default encoding of the platform is used.
* 
*
* 
* For example using UTF-8 as the encoding scheme the string "The
* string ü@foo-bar" would get converted to
* "The+string+%C3%BC%40foo-bar" because in UTF-8 the character
* ü is encoded as two bytes C3 (hex) and BC (hex), and the
* character @ is encoded as one byte 40 (hex).
*
* @author  Herb Jellinek
* @since   JDK1.0
*/
private static class URLEncoder {
static BitSet dontNeedEncoding;
static final int caseDiff = ('a' - 'A');
static String dfltEncName = null;
static {
/* The list of characters that are not encoded has been
* determined as follows:
*
* RFC 2396 states:
* -----
* Data characters that are allowed in a URI but do not have a
* reserved purpose are called unreserved.  These include upper
* and lower case letters, decimal digits, and a limited set of
* punctuation marks and symbols.
*
* unreserved  = alphanum | mark
*
* mark        = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
*
* Unreserved characters can be escaped without changing the
* semantics of the URI, but this should not be done unless the
* URI is being used in a context that does not allow the
* unescaped character to appear.
* -----
*
* It appears that both Netscape and Internet Explorer escape
* all special characters from this list with the exception
* of "-", "_", ".", "*". While it is not clear why they are
* escaping the other characters, perhaps it is safest to
* assume that there might be contexts in which the others
* are unsafe if not escaped. Therefore, we will use the same
* list. It is also noteworthy that this is consistent with
* O'Reilly's "HTML: The Definitive Guide" (page 164).
*
* As a last note, Intenet Explorer does not encode the "@"
* character which is clearly not unreserved according to the
* RFC. We are being consistent with the RFC in this matter,
* as is Netscape.
*
*/
dontNeedEncoding = new BitSet(256);
int i;
for (i = 'a'; i <= 'z'; i++) {
dontNeedEncoding.set(i);
}
for (i = 'A'; i <= 'Z'; i++) {
dontNeedEncoding.set(i);
}
for (i = '0'; i <= '9'; i++) {
dontNeedEncoding.set(i);
}
dontNeedEncoding.set(' '); /* encoding a space to a + is done
* in the encode() method */
dontNeedEncoding.set('-');
dontNeedEncoding.set('_');
dontNeedEncoding.set('.');
dontNeedEncoding.set('*');
// 排除这两个特殊字符的编码
dontNeedEncoding.set(':');
dontNeedEncoding.set('/');
dfltEncName = AccessController.doPrivileged(
new GetPropertyAction("file.encoding")
);
}
/**
* You can't call the constructor.
*/
private URLEncoder() { }
/**
* Translates a string into {@code x-www-form-urlencoded}
* format. This method uses the platform's default encoding
* as the encoding scheme to obtain the bytes for unsafe characters.
*
* @param   s   {@code String} to be translated.
* @deprecated The resulting string may vary depending on the platform's
*             default encoding. Instead, use the encode(String,String)
*             method to specify the encoding.
* @return  the translated {@code String}.
*/
@Deprecated
public static String encode(String s) {
String str = null;
try {
str = encode(s, dfltEncName);
} catch (UnsupportedEncodingException e) {
// The system should always have the platform default
}
return str;
}
/**
* Translates a string into {@code application/x-www-form-urlencoded}
* format using a specific encoding scheme. This method uses the
* supplied encoding scheme to obtain the bytes for unsafe
* characters.
* 
* Note: The 
* "http://www.w3.org/TR/html40/appendix/notes.html#non-ascii-chars">
* World Wide Web Consortium Recommendation
 states that
* UTF-8 should be used. Not doing so may introduce
* incompatibilities.
*
* @param   s   {@code String} to be translated.
* @param   enc   The name of a supported
*    character
*    encoding.
* @return  the translated {@code String}.
* @exception  UnsupportedEncodingException
*             If the named encoding is not supported
* @see URLDecoder#decode(java.lang.String, java.lang.String)
* @since 1.4
*/
public static String encode(String s, String enc)
throws UnsupportedEncodingException {
boolean needToChange = false;
StringBuffer out = new StringBuffer(s.length());
Charset charset;
CharArrayWriter charArrayWriter = new CharArrayWriter();
if (enc == null)
throw new NullPointerException("charsetName");
try {
charset = Charset.forName(enc);
} catch (IllegalCharsetNameException e) {
throw new UnsupportedEncodingException(enc);
} catch (UnsupportedCharsetException e) {
throw new UnsupportedEncodingException(enc);
}
for (int i = 0; i < s.length();) {
int c = (int) s.charAt(i);
//System.out.println("Examining character: " + c);
if (dontNeedEncoding.get(c)) {
if (c == ' ') {
c = '+';
needToChange = true;
}
//System.out.println("Storing: " + c);
out.append((char)c);
i++;
} else {
// convert to external encoding before hex conversion
do {
charArrayWriter.write(c);
/*
* If this character represents the start of a Unicode
* surrogate pair, then pass in two characters. It's not
* clear what should be done if a bytes reserved in the
* surrogate pairs range occurs outside of a legal
* surrogate pair. For now, just treat it as if it were
* any other character.
*/
if (c >= 0xD800 && c <= 0xDBFF) {
/*
System.out.println(Integer.toHexString(c)
+ " is high surrogate");
*/
if ( (i+1) < s.length()) {
int d = (int) s.charAt(i+1);
/*
System.out.println("\tExamining "
+ Integer.toHexString(d));
*/
if (d >= 0xDC00 && d <= 0xDFFF) {
/*
System.out.println("\t"
+ Integer.toHexString(d)
+ " is low surrogate");
*/
charArrayWriter.write(d);
i++;
}
}
}
i++;
} while (i < s.length() && !dontNeedEncoding.get((c = (int) s.charAt(i))));
charArrayWriter.flush();
String str = new String(charArrayWriter.toCharArray());
byte[] ba = str.getBytes(charset);
for (int j = 0; j < ba.length; j++) {
out.append('%');
char ch = Character.forDigit((ba[j] >> 4) & 0xF, 16);
// converting to use uppercase letter as part of
// the hex value if ch is a letter.
if (Character.isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
ch = Character.forDigit(ba[j] & 0xF, 16);
if (Character.isLetter(ch)) {
ch -= caseDiff;
}
out.append(ch);
}
charArrayWriter.reset();
needToChange = true;
}
}
return (needToChange? out.toString() : s);
}
}
}
作者：随风浮云
出处：http://www.cnblogs.com/ljmatlight
本文版权归作者所有，欢迎转载，但未经作者同意必须保留此段声明。
文中有不妥或者错误的地方，欢迎勘误，如果你有更好的建议，可以给我留言讨论，共同进步。
互联网技术时效性较强，引用请慎重。

package com.cn.hnust.util;
import java.io.UnsupportedEncodingException;
import java.util.HashMap;
import java.util.Map;
/**
* url转码、解码
*
* @author
* @date
*/
public class UrlUtil {
private final static String ENCODE = "GBK";
/**
* URL 解码
*
* @return String
* @author lifq
* @date 2015-3-17 下午04:09:51
*/
public static String getURLDecoderString(String str) {
String result = "";
if (null == str) {
return "";
}
try {
result = java.net.URLDecoder.decode(str, ENCODE);
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
}
return result;
}
/**
* URL 转码
*
* @return String
* @author lifq
* @date 2015-3-17 下午04:10:28
*/
public static String getURLEncoderString(String str) {
String result = "";
if (null == str) {
return "";
}
try {
result = java.net.URLEncoder.encode(str, ENCODE);
} catch (UnsupportedEncodingException e) {
e.printStackTrace();
}
return result;
}
/**
* 正则替换
* @param url
* @param name
* @param value
* @return
*/
public static String replaceUrlParameterReg(String url, String name, String value) {
if (StringUtils.isNotBlank(url) && StringUtils.isNotBlank(value)) {
url = url.replaceAll("(" + name + "=[^&]*)", name + "=" + value);
}
return url;
}
/**
* 正则替换
* @param url
* @param name
* @param value
* @return
*/
public static String getUrlParameterReg(String url, String name) {
Map mapRequest = new HashMap();
String[] arrSplit=null;
String strUrlParam=TruncateUrlPage(url);
if(strUrlParam==null)
{
return "";
}
//每个键值为一组 www.2cto.com
arrSplit=strUrlParam.split("[&]");
for(String strSplit:arrSplit)
{
String[] arrSplitEqual=null;
arrSplitEqual= strSplit.split("[=]");
//解析出键值
if(arrSplitEqual.length>1)
{
//正确解析
mapRequest.put(arrSplitEqual[0], arrSplitEqual[1]);
}
else
{
if(arrSplitEqual[0]!="")
{
//只有参数没有值，不加入
mapRequest.put(arrSplitEqual[0], "");
}
}
}
return mapRequest.get(name);
}
/**
* 去掉url中的路径，留下请求参数部分
* @param strURL url地址
* @return url请求参数部分
*/
private static String TruncateUrlPage(String strURL)
{
String strAllParam=null;
String[] arrSplit=null;
strURL=strURL.trim().toLowerCase();
arrSplit=strURL.split("[?]");
if(strURL.length()>1)
{
if(arrSplit.length>1)
{
if(arrSplit[1]!=null)
{
strAllParam=arrSplit[1];
}
}
}
return strAllParam;
}
public static void main(String[] args) {
String str ="/activePage?wxto=0C29975119DE037B4F25CD119CF4CF11&activity2018topid=oz9Zj07Jg5O9IfAyVauT-GL-CSfM&activity2018topunid=o-NUA0l8fxm2_5fmK_ocpyxrP1dE&subscribe=0&timestamp=1516008942920&-NUA0l8fxm2_5fmK_ocpyxrP1dE&oaccesstoken=5_xJYY3gnUTD4pqJFc7_ltbvclb0ZRKOFBEc5BXAwi7vjZndRAN58AkPazqUJDGzBbrw-J1ag1PF0C-S39SqJflA&m=1&wxt=C9A58DA3804E46981BF4B78C8C862743&-NUA0oHjJjCcyGe-wJdEFYjwrfU&-NUA0oHjJjCcyGe-wJdEFYjwrfU&-NUA0oHjJjCcyGe-wJdEFYjwrfU";
String m = "9j70Dj%2BpVA64qK9%2FeOjsg2dP3biHh6imIC6WFXtIRcR6nHwDkjHPNOL9zUi7fmpcbgJP3u%2Bh3VUTfDO0B2fsbKWsizlqOKdXJovkg3HZMTxAIcByvYvtHoCyd9iOgUxoDqslzoMunvnEzPS8FbYc%2Fjkd4y47zhKk%2FUTE4GGm8ZM5Ns5eYwZSFL7A8pX0U%2BXfsMR%2FGf5z2pci6a5BJaki4e0z0Pmh5sPsjytmKdjdssHQ98iZ8ge3mXJm7G%2FaSJ3e%2FHvNENLv0JRJf7q1bFu180RZEtsMRs%2BWdesTuJamtJBYtLxQEYaCMygRcmd%2F1VdSqfLnuZqcZAzT6GAmvBwZyfzCK9LffGsyZGWce%2B0g2R%2FTCKTTtNpWWCJb0e7Gs0g82DmBNV4jh3hrOAmeLNwpu0M%2B049%2FHrDxAZPvXowCb5OLb7if%2BVqBpYkphGssurkqLV2KTXx3vhjl9vIiMQnD4397oNYf81P%2BBWFPBFhPQSfGaxZGZbAlPgkluR4%2Fj75f9SeZlcWFMnl%2BYKYtopw1gw%3D%3D";
System.out.println(getURLEncoderString(m));
System.out.println(getURLDecoderString(m));
//System.out.println( getUrlParameterReg(str,"wxto"));
}
}