一个URL编码和解码的C++类

来源：互联网发布：易语言ip攻击器源码编辑：程序博客网时间：2024/05/16 06:13

[cpp] view plain copy
1. #pragma once
4. #include <iostream>
5. #include <string>
6. #include <windows.h>
7. using namespace std;
9. class strCoding
10. {
11. public:
12. strCoding(void);
13. ~strCoding(void);
15. void UTF_8ToGB2312(string &pOut, char *pText, int pLen);//utf_8转为gb2312
16. void GB2312ToUTF_8(string& pOut,char *pText, int pLen); //gb2312 转utf_8
17. string UrlGB2312(char * str); //urlgb2312编码
18. string UrlUTF8(char * str); //urlutf8 编码
19. string UrlUTF8Decode(string str); //urlutf8解码
20. string UrlGB2312Decode(string str); //urlgb2312解码
22. private:
23. void Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer);
24. void UTF_8ToUnicode(WCHAR* pOut,char *pText);
25. void UnicodeToUTF_8(char* pOut,WCHAR* pText);
26. void UnicodeToGB2312(char* pOut,WCHAR uData);
27. char CharToInt(char ch);
28. char StrToBin(char *str);
30. };
32. #include "StdAfx.h"
33. #include ".\urlcodeing.h"
34. //这是个类strCoding (strCoding.cpp文件)
36. strCoding::strCoding(void)
37. {
38. }
40. strCoding::~strCoding(void)
41. {
42. }
43. void strCoding::Gb2312ToUnicode(WCHAR* pOut,char *gbBuffer)
44. {
45. ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
46. return;
47. }
48. void strCoding::UTF_8ToUnicode(WCHAR* pOut,char *pText)
49. {
50. char* uchar = (char *)pOut;
52. uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
53. uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);
55. return;
56. }
58. void strCoding::UnicodeToUTF_8(char* pOut,WCHAR* pText)
59. {
60. // 注意 WCHAR高低字的顺序,低字节在前，高字节在后
61. char* pchar = (char *)pText;
63. pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4));
64. pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
65. pOut[2] = (0x80 | (pchar[0] & 0x3F));
67. return;
68. }
69. void strCoding::UnicodeToGB2312(char* pOut,WCHAR uData)
70. {
71. WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);
72. return;
73. }
75. //做为解Url使用
76. char strCoding:: CharToInt(char ch){
77. if(ch>='0' && ch<='9')return (char)(ch-'0');
78. if(ch>='a' && ch<='f')return (char)(ch-'a'+10);
79. if(ch>='A' && ch<='F')return (char)(ch-'A'+10);
80. return -1;
81. }
82. char strCoding::StrToBin(char *str){
83. char tempWord[2];
84. char chn;
86. tempWord[0] = CharToInt(str[0]); //make the B to 11 -- 00001011
87. tempWord[1] = CharToInt(str[1]); //make the 0 to 0 -- 00000000
89. chn = (tempWord[0] << 4) | tempWord[1]; //to change the BO to 10110000
91. return chn;
92. }
95. //UTF_8 转gb2312
96. void strCoding::UTF_8ToGB2312(string &pOut, char *pText, int pLen)
97. {
98. char buf[4];
99. char* rst = new char[pLen + (pLen >> 2) + 2];
100. memset(buf,0,4);
101. memset(rst,0,pLen + (pLen >> 2) + 2);
103. int i =0;
104. int j = 0;
106. while(i < pLen)
107. {
108. if(*(pText + i) >= 0)
109. {
111. rst[j++] = pText[i++];
112. }
113. else
114. {
115. WCHAR Wtemp;
118. UTF_8ToUnicode(&Wtemp,pText + i);
120. UnicodeToGB2312(buf,Wtemp);
122. unsigned short int tmp = 0;
123. tmp = rst[j] = buf[0];
124. tmp = rst[j+1] = buf[1];
125. tmp = rst[j+2] = buf[2];
127. //newBuf[j] = Ctemp[0];
128. //newBuf[j + 1] = Ctemp[1];
130. i += 3;
131. j += 2;
132. }
134. }
135. rst[j]='\0';
136. pOut = rst;
137. delete []rst;
138. }
140. //GB2312 转为 UTF-8
141. void strCoding::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
142. {
143. char buf[4];
144. memset(buf,0,4);
146. pOut.clear();
148. int i = 0;
149. while(i < pLen)
150. {
151. //如果是英文直接复制就可以
152. if( pText[i] >= 0)
153. {
154. char asciistr[2]={0};
155. asciistr[0] = (pText[i++]);
156. pOut.append(asciistr);
157. }
158. else
159. {
160. WCHAR pbuffer;
161. Gb2312ToUnicode(&pbuffer,pText+i);
163. UnicodeToUTF_8(buf,&pbuffer);
165. pOut.append(buf);
167. i += 2;
168. }
169. }
171. return;
172. }
173. //把str编码为网页中的 GB2312 url encode ,英文不变，汉字双字节如%3D%AE%88
174. string strCoding::UrlGB2312(char * str)
175. {
176. string dd;
177. size_t len = strlen(str);
178. for (size_t i=0;i<len;i++)
179. {
180. if(isalnum((BYTE)str[i]))
181. {
182. char tempbuff[2];
183. sprintf(tempbuff,"%c",str[i]);
184. dd.append(tempbuff);
185. }
186. else if (isspace((BYTE)str[i]))
187. {
188. dd.append("+");
189. }
190. else
191. {
192. char tempbuff[4];
193. sprintf(tempbuff,"%%%X%X",((BYTE*)str)[i] >>4,((BYTE*)str)[i] %16);
194. dd.append(tempbuff);
195. }
197. }
198. return dd;
199. }
201. //把str编码为网页中的 UTF-8 url encode ,英文不变，汉字三字节如%3D%AE%88
203. string strCoding::UrlUTF8(char * str)
204. {
205. string tt;
206. string dd;
207. GB2312ToUTF_8(tt,str,(int)strlen(str));
209. size_t len=tt.length();
210. for (size_t i=0;i<len;i++)
211. {
212. if(isalnum((BYTE)tt.at(i)))
213. {
214. char tempbuff[2]={0};
215. sprintf(tempbuff,"%c",(BYTE)tt.at(i));
216. dd.append(tempbuff);
217. }
218. else if (isspace((BYTE)tt.at(i)))
219. {
220. dd.append("+");
221. }
222. else
223. {
224. char tempbuff[4];
225. sprintf(tempbuff,"%%%X%X",((BYTE)tt.at(i)) >>4,((BYTE)tt.at(i)) %16);
226. dd.append(tempbuff);
227. }
229. }
230. return dd;
231. }
232. //把url GB2312解码
233. string strCoding::UrlGB2312Decode(string str)
234. {
235. string output="";
236. char tmp[2];
237. int i=0,idx=0,ndx,len=str.length();
239. while(i<len){
240. if(str[i]=='%'){
241. tmp[0]=str[i+1];
242. tmp[1]=str[i+2];
243. output += StrToBin(tmp);
244. i=i+3;
245. }
246. else if(str[i]=='+'){
247. output+=' ';
248. i++;
249. }
250. else{
251. output+=str[i];
252. i++;
253. }
254. }
256. return output;
257. }
258. //把url utf8解码
259. string strCoding::UrlUTF8Decode(string str)
260. {
261. string output="";
263. string temp =UrlGB2312Decode(str);//
265. UTF_8ToGB2312(output,(char *)temp.data(),strlen(temp.data()));
267. return output;
269. }

0 0