解析URL编码格式到中文（直接从完整的URL地址入手）V2.0

最新推荐文章于 2024-07-30 12:22:43 发布

原创最新推荐文章于 2024-07-30 12:22:43 发布 · 823 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#URL编码 #转码 #Stack应用

Notes 专栏收录该内容

53 篇文章

订阅专栏

该程序旨在解析URL地址，解决URL编码部分，并将其转换为中文。通过使用Stack作为存储结构，过滤特殊字符，再利用Java的URLDecoder函数进行最终解析。目前能解析部分编码，如'%E6%B1%87%E7%8E%87&%E7%BE%8E%E5++%E6%AC%A7%E5%85%83BA%E6%B0%91_%E5%B8%81'，但无法解析'%3A110666'。升级版使用LinkedList替换Stack，以简化数据处理。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

思路就是把字符串按照不同分隔符分开

遇到包含的可能特殊字符，用Stack这个存储结构做个中转，为得是过滤掉哪些特殊字符

用java提供的URLDecode函数，做最后解析

未完待续：

package web.transfer;

import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.util.Iterator;
import java.util.Stack;
import java.util.Vector;

/**
* the original goal of this program:parsing URL address,resolving parts encoding in URL form,and transferring them to Chinese
* this is v2.0 of Url2Unicode.java,since i use stacks to resolve the first problem mentioned in Url2Unicode.java
* progress:can parse %E6%B1%87%E7%8E%87&
*                                %E7%BE%8E%E5++%E6%AC%A7%E5%85%83BA%E6%B0%91_%E5%B8%81
*            can not parse %3A110666
*
*
* IMPROVEMENT:using LinkedList to replace Stack,since the single direction of data to push or pop in Stack,
*                                i have to use two stacks to get the order of encoding part is right.
*                                If you use LinkedList,only one LinkedList will be needed to initialize.
*
*/

public class Url2UnicodeWithStack {

   public String StacksToOrderString(Stack<Character> source) {
       Stack<Character> temp = new Stack<Character>();
       while ( !source.empty()) {
           temp.push(source.pop());
       }
       String order = new String();

       while(!temp.empty()) {
           order = order.concat(temp.pop().toString());
           //System.out.println("order "+order);
       }
       return order;
   }

   public String CheckHeadStartPercent(String input) {
       System.out.println("CheckHeadStartPercent method: "+input);
       if(!input.startsWith("%")) {
           System.out.println("After CheckHeadStartPercent method: "+ input.substring(input.indexOf("%"),input.length()-1));
           return input.substring(input.indexOf("%"),input.length()-1);
       }
       else {
           return input;
       }
   }

   public String[] Vector2String(Vector<String> v) {
       int length= v.size();
       String [] re = new String[length];
       Iterator<String> it =(Iterator<String>)v.iterator();
       int i = 0;
       while(it.hasNext()) {
           re[i] = it.next();
           ++i;
       }
       return re;
   }

   public Vector<String> containPercent (String [] input) {
       Vector<String> results = new Vector();
       int length = input.length;
       for(int i = 0;i < length;i++) {
           if( input[i].contains("%") ) {
               //System.out.println("containPercent method: "+input[i]);
               results.add(input[i]);
           }
       }
       /*System.out.println("containPercent method~~Iterator");
       Iterator<String> itr = (Iterator<String>)results.iterator();
       while(itr.hasNext()) {
           System.out.println(itr.next());
       }*/

       return results;
   }

   public String[] containSpecialCharWithStack(String input) {
       System.out.println("Enter containSpecialChar method: ");
       char [] sp = {'_','-','+','!','`','~','#','@','$','^','*','(',')','{','}','[',']','|',':','\\',';','"','<','>','?',','};
       //String [] sp = {"_","-","\\+","!","`","~","#","@","$","\\^","\\*","(",")","{","}","[","]","|",":","\\",";","\"","<",">","?",","};
       Vector<String> results = new Vector();
       int length = input.length();
       Stack<Character> stk = new Stack<Character>();
           for(int i = 0;i < length;i++) {
               stk.push(input.charAt(i));
               for(int j = 0; j < sp.length;++j) {
                   if(Character.compare(input.charAt(i),sp[j]) == 0) {
                       stk.pop();
                       //System.out.println("Enter containSpecialChar method: if(compare char) "+i+" "+j);
                       String order = StacksToOrderString(stk);
                       results.add(order);
                   /*System.out.println("Enter containSpecialChar method: if(compare char) iterator: ");
                       Iterator<String> itr = (Iterator<String>)results.iterator();
                       while(itr.hasNext()) {
                           System.out.println(itr.next());
                           }       */
                   }
               }
               //System.out.println("Enter containSpecialChar method: first for loop: "+i+" results size() "+results.size());
           }
       results.add(StacksToOrderString(stk));
       System.out.println("Enter containSpecialChar method: if(compare char) iterator: ");
       Iterator<String> itr = (Iterator<String>)results.iterator();
       while(itr.hasNext()) {
           System.out.println(itr.next());
           }
       return Vector2String(results);
   }

       public void test() {
String input =

"http://wzdig.pbc.gov.cn:8080/dig/ui/search.action?ty=&w=false&f=&dr=true&p=2&sr=score+desc%2Cdatetime+desc&rp=&advtime=&advrange=&fq=&ext=&q=%E4%B8%AD%E5%9B%BD%E5%A4%96%E6%B1%87%E4%BA%A4%E6%98%93%E4%B8%AD%E5%BF%83%E5%8F%97%E6%9D%83%E5%85%AC%E5%B8%83%E4%BA%BA%E6%B0%91%E5%B8%81%E6%B1%87%E7%8E%87%E4%B8%AD%E9%97%B4%E4%BB%B7";
               Vector<String> UrlWords = new Vector();
                   String [] UrlWordsPre = input.split("=");
               /*for(String in:UrlWordsPre) {
                       System.out.println(in);
               }
               System.out.println("Start while method:");*/
               int i = 1;
               while( i < UrlWordsPre.length ) {
                       String [] temp = UrlWordsPre[i].split("&");
                       /*for(String in:temp) {
                           System.out.println(in);
                       }*/
                       if ( temp[0].contains("%")) {
                           System.out.println(i+"---------"+temp[0]);

                           String[] re = containSpecialCharWithStack(CheckHeadStartPercent(temp[0]));
                           for(int j =0; j < re.length; j++) {
                               try {
                                   UrlWords.add(URLDecoder.decode(re[j],"utf-8"));
                               } catch (UnsupportedEncodingException e) {
                                   // TODO Auto-generated catch block
                                   e.printStackTrace();
                               }
                           }
                       }
                   ++i;
               }

               System.out.println("Start iterator ZZZZZZZZZZZZZZ:");
               Iterator<String> itr = (Iterator<String>)UrlWords.iterator();
               while(itr.hasNext()) {
                   System.out.println(itr.next());
               }
       }

       /*public static void main(String [] args) {

           Url2UnicodeWithStack test = new Url2UnicodeWithStack();
           test.test();
       }*/

}