URL转码

class CChineseCode
{
public:
static void UTF_8ToUnicode(wchar_t* pOut,char *pText);  // 把UTF-8转换成Unicode
static void UnicodeToUTF_8(char* pOut,wchar_t* pText);  //Unicode 转换成UTF-8
static void UnicodeToGB2312(char* pOut,wchar_t uData);  // 把Unicode 转换成 GB2312
static void Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer);// GB2312 转换成　Unicode
static void GB2312ToUTF_8(string& pOut,char *pText, int pLen);//GB2312 转为 UTF-8
static void UTF_8ToGB2312(string &pOut, char *pText, int pLen);//UTF-8 转为 GB2312
};




void CChineseCode::UTF_8ToUnicode(wchar_t* pOut,char *pText)
{
char* uchar = (char *)pOut;


uchar[1] = ((pText[0] & 0x0F) << 4) + ((pText[1] >> 2) & 0x0F);
uchar[0] = ((pText[1] & 0x03) << 6) + (pText[2] & 0x3F);


return;
}


void CChineseCode::UnicodeToUTF_8(char* pOut,wchar_t* pText)
{
// 注意 WCHAR高低字的顺序,低字节在前，高字节在后
char* pchar = (char *)pText;


pOut[0] = (0xE0 | ((pchar[1] & 0xF0) >> 4));
pOut[1] = (0x80 | ((pchar[1] & 0x0F) << 2)) + ((pchar[0] & 0xC0) >> 6);
pOut[2] = (0x80 | (pchar[0] & 0x3F));


return;
}


void CChineseCode::UnicodeToGB2312(char* pOut,wchar_t uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);
return;
}    


void CChineseCode::Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return ;
}


void CChineseCode::GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4];
int nLength = pLen* 3;
char* rst = new char[nLength];


memset(buf,0,4);
memset(rst,0,nLength);


int i = 0;
int j = 0;     
while(i < pLen)
{
//如果是英文直接复制就能
if( *(pText + i) >= 0)
{
rst[j++] = pText[i++];
}
else
{
wchar_t pbuffer;
Gb2312ToUnicode(&pbuffer,pText+i);


UnicodeToUTF_8(buf,&pbuffer);


unsigned short int tmp = 0;
tmp = rst[j] = buf[0];
tmp = rst[j+1] = buf[1];
tmp = rst[j+2] = buf[2];    


j += 3;
i += 2;
}
}
rst[j] = 0;


//返回结果
pOut = rst;             
delete []rst;  


return;
}


void CChineseCode::UTF_8ToGB2312(string &pOut, char *pText, int pLen)
{
char * newBuf = new char[pLen];
char Ctemp[4];
memset(Ctemp,0,4);


int i =0;
int j = 0;


while(i < pLen)
{
if(pText > 0)
{
newBuf[j++] = pText[i++];                      
}
else                
{
WCHAR Wtemp;
UTF_8ToUnicode(&Wtemp,pText + i);


UnicodeToGB2312(Ctemp,Wtemp);


newBuf[j] = Ctemp[0];
newBuf[j + 1] = Ctemp[1];


i += 3;    
j += 2;  
}
}
newBuf[j] = 0;


pOut = newBuf;
delete []newBuf;


return;
} 




unsigned char ToHex(unsigned char x) 
{ 
return  x > 9 ? x + 55 : x + 48; 
}


unsigned char FromHex(unsigned char x) 
{ 
unsigned char y;
if (x >= 'A' && x <= 'Z') y = x - 'A' + 10;
else if (x >= 'a' && x <= 'z') y = x - 'a' + 10;
else if (x >= '0' && x <= '9') y = x - '0';
else ASSERT(0);
return y;
}


std::string UrlEncode(const std::string& str)
{
std::string strTemp = "";
size_t length = str.length();
for (size_t i = 0; i < length; i++)
{
if (isalnum((unsigned char)str[i]) || 
(str[i] == '-') ||
(str[i] == '_') || 
(str[i] == '.') || 
(str[i] == '~'))
strTemp += str[i];
else if (str[i] == ' ')
strTemp += "+";
else
{
strTemp += '%';
strTemp += ToHex((unsigned char)str[i] >> 4);
strTemp += ToHex((unsigned char)str[i] % 16);
}
}
return strTemp;
}


std::string UrlDecode(const std::string& str)
{
std::string strTemp = "";
size_t length = str.length();
for (size_t i = 0; i < length; i++)
{
if (str[i] == '+') strTemp += ' ';
else if (str[i] == '%')
{
ASSERT(i + 2 < length);
unsigned char high = FromHex((unsigned char)str[++i]);
unsigned char low = FromHex((unsigned char)str[++i]);
strTemp += high*16 + low;
}
else strTemp += str[i];
}
return strTemp;
}