java实现url编码与中文的互相转换

拼搏现实的明天。 2022-06-08 11:13 1883阅读 0赞

参考：http://blog.csdn.net/u012364841/article/details/41964477

# **问题：** #

在读取查看类编译位置的时候，出现编码的问题，原因是在读取的时候，java自动转为Base64的编码形式。

# **输出编码如下：** #

/D:/JAVA%ef%bc%88%e5%b8%85%e5%b0%8f%e5%8b%87%ef%bc%89/java%e7%ab%8b%e6%95%8f%e8%80%81%e5%b8%88/java%20%e5%b7%a5%e4%bd%9c%e7%a9%ba%e9%97%b4/Warehouse/build/classes/

# **代码如下：** #

package com.lnsf.warehose.service.test2;  
import static org.junit.Assert.\*;  
import java.io.UnsupportedEncodingException;  
import org.junit.Test;  
import org.junit.runner.RunWith;  
import org.springframework.context.ApplicationContext;  
import org.springframework.context.support.ClassPathXmlApplicationContext;  
import com.lnsf.warehose.service.test.TestInterface0923;  
/\*\*  
\* @author 渴望飞的鱼   
\* @version 创建时间：2017年9月23日 下午1:49:01  
\* @introduction  
\*/  
  
public class TestSpringIoC \{  
public TestSpringIoC() throws UnsupportedEncodingException\{  
**    //查看编译位置**  
String str=TestSpringIoC.class.getClass().getResource("/").getPath();

** //没有处理过的编码形式**  
System.out.println(str);   
System.out.println("查看编译位置："+**java.net.URLDecoder.decode(str,"utf-8")**);  
\}  
@Test  
public void test() \{  
**//springioc.xml在src路径下时候**  
**//ApplicationContext context = new ClassPathXmlApplicationContext("springioc.xml");**  
ApplicationContext context = new ClassPathXmlApplicationContext("com/lnsf/warehose/service/test/springioc.xml");  
**//ApplicationContext  context=new ClassPathXmlApplicationContext("classpath:/\*.xml");**  
TestInterface0923 TestInterface0923=(com.lnsf.warehose.service.test.TestInterface0923) context.getBean("TestInterface0923");  
System.out.println(TestInterface0923.getString("嘻嘻，依赖注入啊"));  
\}  
\}

运行结果如下：

/D:/JAVA%ef%bc%88%e5%b8%85%e5%b0%8f%e5%8b%87%ef%bc%89/java%e7%ab%8b%e6%95%8f%e8%80%81%e5%b8%88/java%20%e5%b7%a5%e4%bd%9c%e7%a9%ba%e9%97%b4/Warehouse/build/classes/  
查看编译位置：/D:/JAVA（帅小勇）/java立敏老师/java 工作空间/Warehouse/build/classes/  
SLF4J: Failed to load class "org.slf4j.impl.StaticLoggerBinder".  
SLF4J: Defaulting to no-operation (NOP) logger implementation  
SLF4J: See http://www.slf4j.org/codes.html\#StaticLoggerBinder for further details.  
testInterface0923Impl  get the string is: 嘻嘻，依赖注入啊 .

# 处理方法： #

**1.可以API中方法用encode和decode方法即可实现转换并输出。**

System.out.println(java.net.URLEncoder.encode("您好","utf-8"));  
System.out.println(java.net.URLDecoder.decode("%E6%82%A8%E5%A5%BD","utf-8"));

**2.通过URLtoUTF8类中的toUtf8String和unescape两个方法，分别实现汉字转成URL编码和URL编码转成汉字的功能。在main()方法更改参数即可，完成测试转换。（此方法转自：http://www.jb51.net/article/42495.htm）**

package test;

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"));  
  
    \}  
\}

**示例结果：**

%E4%BD%A0  
你 好