C++ UTF8 UrlEncode(宽字符)(转载)

转载:http://www.cnblogs.com/newcj/p/3645749.html

1 #include "UrlEncode.h"
  2 #include <string>
  3 #include <windows.h>
  4 #include <assert.h>
  5 
  6 using namespace std;
  7 
  8 namespace ConnectSDK
  9 {
 10     namespace Utility
 11     {
 12         const wchar_t * hexenc[] = {
 13             L"%00", L"%01", L"%02", L"%03", L"%04", L"%05", L"%06", L"%07",
 14             L"%08", L"%09", L"%0a", L"%0b", L"%0c", L"%0d", L"%0e", L"%0f",
 15             L"%10", L"%11", L"%12", L"%13", L"%14", L"%15", L"%16", L"%17",
 16             L"%18", L"%19", L"%1a", L"%1b", L"%1c", L"%1d", L"%1e", L"%1f",
 17             L"%20", L"%21", L"%22", L"%23", L"%24", L"%25", L"%26", L"%27",
 18             L"%28", L"%29", L"%2a", L"%2b", L"%2c", L"%2d", L"%2e", L"%2f",
 19             L"%30", L"%31", L"%32", L"%33", L"%34", L"%35", L"%36", L"%37",
 20             L"%38", L"%39", L"%3a", L"%3b", L"%3c", L"%3d", L"%3e", L"%3f",
 21             L"%40", L"%41", L"%42", L"%43", L"%44", L"%45", L"%46", L"%47",
 22             L"%48", L"%49", L"%4a", L"%4b", L"%4c", L"%4d", L"%4e", L"%4f",
 23             L"%50", L"%51", L"%52", L"%53", L"%54", L"%55", L"%56", L"%57",
 24             L"%58", L"%59", L"%5a", L"%5b", L"%5c", L"%5d", L"%5e", L"%5f",
 25             L"%60", L"%61", L"%62", L"%63", L"%64", L"%65", L"%66", L"%67",
 26             L"%68", L"%69", L"%6a", L"%6b", L"%6c", L"%6d", L"%6e", L"%6f",
 27             L"%70", L"%71", L"%72", L"%73", L"%74", L"%75", L"%76", L"%77",
 28             L"%78", L"%79", L"%7a", L"%7b", L"%7c", L"%7d", L"%7e", L"%7f",
 29             L"%80", L"%81", L"%82", L"%83", L"%84", L"%85", L"%86", L"%87",
 30             L"%88", L"%89", L"%8a", L"%8b", L"%8c", L"%8d", L"%8e", L"%8f",
 31             L"%90", L"%91", L"%92", L"%93", L"%94", L"%95", L"%96", L"%97",
 32             L"%98", L"%99", L"%9a", L"%9b", L"%9c", L"%9d", L"%9e", L"%9f",
 33             L"%a0", L"%a1", L"%a2", L"%a3", L"%a4", L"%a5", L"%a6", L"%a7",
 34             L"%a8", L"%a9", L"%aa", L"%ab", L"%ac", L"%ad", L"%ae", L"%af",
 35             L"%b0", L"%b1", L"%b2", L"%b3", L"%b4", L"%b5", L"%b6", L"%b7",
 36             L"%b8", L"%b9", L"%ba", L"%bb", L"%bc", L"%bd", L"%be", L"%bf",
 37             L"%c0", L"%c1", L"%c2", L"%c3", L"%c4", L"%c5", L"%c6", L"%c7",
 38             L"%c8", L"%c9", L"%ca", L"%cb", L"%cc", L"%cd", L"%ce", L"%cf",
 39             L"%d0", L"%d1", L"%d2", L"%d3", L"%d4", L"%d5", L"%d6", L"%d7",
 40             L"%d8", L"%d9", L"%da", L"%db", L"%dc", L"%dd", L"%de", L"%df",
 41             L"%e0", L"%e1", L"%e2", L"%e3", L"%e4", L"%e5", L"%e6", L"%e7",
 42             L"%e8", L"%e9", L"%ea", L"%eb", L"%ec", L"%ed", L"%ee", L"%ef",
 43             L"%f0", L"%f1", L"%f2", L"%f3", L"%f4", L"%f5", L"%f6", L"%f7",
 44             L"%f8", L"%f9", L"%fa", L"%fb", L"%fc", L"%fd", L"%fe", L"%ff"
 45         };
 46 
 47         String^ UrlEncode(String^ url)
 48         {
 49             wstring text(url->Data());
 50 
 51             size_t len = text.length();
 52             std::wstring encoded = L"";
 53             for(size_t i = 0; i < len; i++)
 54             {
 55                 wchar_t wch = text.at(i);
 56                 if ('A' <= wch && wch <= 'Z') {
 57                     encoded += wch;
 58                 } else if ('a' <= wch && wch <= 'z') {
 59                     encoded += wch;
 60                 } else if ('0' <= wch && wch <= '9') {
 61                     encoded += wch;
 62                 } else if (wch == ' ') {
 63                     encoded += hexenc[wch];
 64                 } else if (wch == '-' || wch == '_'
 65                     || wch == '.' || wch == '!'
 66                     || wch == '~' || wch == '*'
 67                     || wch == '\'' || wch == '('
 68                     || wch == ')') {
 69                         encoded += hexenc[wch];
 70                 } else if (wch <= 0x007f) {        // other ASCII
 71                     encoded += hexenc[wch];
 72                 } else if (wch <= 0x07FF) {        // non-ASCII <= 0x7FF
 73                     encoded += hexenc[0xc0 | (wch >> 6)];
 74                     encoded += hexenc[0x80 | (wch & 0x3F)];
 75                 } else {                    // 0x7FF < ch <= 0xFFFF
 76                     encoded += hexenc[0xe0 | (wch >> 12)];
 77                     encoded += hexenc[0x80 | ((wch >> 6) & 0x3F)];
 78                     encoded += hexenc[0x80 | (wch & 0x3F)];
 79                 }
 80             }
 81             return ref new String(encoded.c_str());    
 82         }
 83 
 84         String^ UrlDecode(String^ encodeUrl)
 85         {
 86             wstring text(encodeUrl->Data());
 87             std::wstring decoded = L"";
 88             wchar_t temp[] = L"0x00";
 89             size_t len = text.length();
 90             int sequence = 0;
 91             wchar_t conwch = 0;
 92             for(size_t i = 0; i < len; i++)
 93             {    
 94                 wchar_t wch = text.at(i++);
 95                 if((wch == '%') && (i+1 < len))
 96                 {            
 97                     temp[2] = text.at(i++);
 98                     temp[3] = text.at(i);
 99                     long tconwch = wcstol(temp, NULL, 16);
100                     if(tconwch <= 0x7F) {
101                         decoded += tconwch; // normal ascii char
102                     } else if(tconwch >= 0x80 && tconwch <= 0xBF) { // partial byte
103                         tconwch = tconwch & 0x3F;
104                         if(sequence-- == 2)
105                             tconwch = tconwch << 6;
106                         conwch |= tconwch;
107                         if(sequence == 0)
108                             decoded += conwch;
109                     } else if(tconwch >= 0xC0 && tconwch <= 0xDF) {
110                         conwch = (tconwch & 0x1F) << 6; // make space for partial bytes
111                         sequence = 1; // 1 more partial bytes follow
112                     } else if(tconwch >= 0xE0 && tconwch <= 0xEF) {
113                         conwch = (tconwch & 0xF) << 12; // make space for partial bytes
114                         sequence = 2; // 2 more partial bytes follow
115                     } // TODO add case fore 3 partial bytes ... very rare
116                 } else {
117                     decoded += text.at(--i);
118                 }
119             }
120             return ref new String(decoded.c_str());
121         }
122     }
123 }

上面是网上找的:

根据项目需要进行修改:

UrlEncode:

1 CString URLEncode(CString url)
 2 {
 3     std::wstring text = url;
 4 
 5     size_t len = text.length();
 6     std::wstring encoded = L"";
 7     for(size_t i = 0; i < len; i++)
 8     {
 9         wchar_t wch = text.at(i);
10         if ('A' <= wch && wch <= 'Z') {
11             encoded += wch;
12         } else if ('a' <= wch && wch <= 'z') {
13             encoded += wch;
14         } else if ('0' <= wch && wch <= '9') {
15             encoded += wch;
16         } else if (wch == ' ') {
17             encoded += hexenc[wch];
18         } else if (wch == '-' || wch == '_'
19             || wch == '.' || wch == '!'
20             || wch == '~' || wch == '*'
21             || wch == '\'' || wch == '('
22             || wch == ')') {
23                 encoded += hexenc[wch];
24         } else if (wch <= 0x007f) {        // other ASCII
25             encoded += hexenc[wch];
26         } else if (wch <= 0x07FF) {        // non-ASCII <= 0x7FF
27             encoded += hexenc[0xc0 | (wch >> 6)];
28             encoded += hexenc[0x80 | (wch & 0x3F)];
29         } else {                    // 0x7FF < ch <= 0xFFFF
30             encoded += hexenc[0xe0 | (wch >> 12)];
31             encoded += hexenc[0x80 | ((wch >> 6) & 0x3F)];
32             encoded += hexenc[0x80 | (wch & 0x3F)];
33         }
34     }
35     return encoded.c_str();    
36 }
UrlDecode:
1    CString UrlDecode(CString encodeUrl)
 2         {
 3             std::wstring text = encodeUrl;
 4             std::wstring decoded = L"";
 5             wchar_t temp[] = L"0x00";
 6             size_t len = text.length();
 7             int sequence = 0;
 8             wchar_t conwch = 0;
 9             for(size_t i = 0; i < len; i++)
10             {    
11                 wchar_t wch = text.at(i++);
12                 if((wch == '%') && (i+1 < len))
13                 {            
14                     temp[2] = text.at(i++);
15                     temp[3] = text.at(i);
16                     long tconwch = wcstol(temp, NULL, 16);
17                     if(tconwch <= 0x7F) {
18                         decoded += tconwch; // normal ascii char
19                     } else if(tconwch >= 0x80 && tconwch <= 0xBF) { // partial byte
20                         tconwch = tconwch & 0x3F;
21                         if(sequence-- == 2)
22                             tconwch = tconwch << 6;
23                         conwch |= tconwch;
24                         if(sequence == 0)
25                             decoded += conwch;
26                     } else if(tconwch >= 0xC0 && tconwch <= 0xDF) {
27                         conwch = (tconwch & 0x1F) << 6; // make space for partial bytes
28                         sequence = 1; // 1 more partial bytes follow
29                     } else if(tconwch >= 0xE0 && tconwch <= 0xEF) {
30                         conwch = (tconwch & 0xF) << 12; // make space for partial bytes
31                         sequence = 2; // 2 more partial bytes follow
32                     } // TODO add case fore 3 partial bytes ... very rare
33                 } else {
34                     decoded += text.at(--i);
35                 }
36             }
37             return decoded.c_str();
38         }

原文链接: https://www.cnblogs.com/chechen/p/5800616.html

欢迎关注

微信关注下方公众号,第一时间获取干货硬货;公众号内回复【pdf】免费获取数百本计算机经典书籍

原创文章受到原创版权保护。转载请注明出处:https://www.ccppcoding.com/archives/239215

非原创文章文中已经注明原地址,如有侵权,联系删除

关注公众号【高性能架构探索】,第一时间获取最新文章

转载文章受原作者版权保护。转载请注明原作者出处!

(0)
上一篇 2023年2月13日 下午6:05
下一篇 2023年2月13日 下午6:05

相关推荐