CString Utf8ToStringT(LPSTR str)
{
_ASSERT(str);
USES_CONVERSION;
WCHAR *buf;
int length = MultiByteToWideChar(CP_UTF8, 0, str, -1, NULL, 0);
buf = new WCHAR[length+1];
ZeroMemory(buf, (length+1) * sizeof(WCHAR));
MultiByteToWideChar(CP_UTF8, 0, str, -1, buf, length);
return (CString(W2T(buf)));
}
/**/ /*
CString UrlDecode(LPCTSTR url)
{
_ASSERT(url);
USES_CONVERSION;
LPSTR _url = T2A(const_cast<LPTSTR>(url));
int i = 0;
int length = (int)strlen(_url);
CHAR *buf = new CHAR[length];
ZeroMemory(buf, length);
LPSTR p = buf;
while(i < length)
{
if(i <= length -3 && _url[i] == '%' && IsHexNum(_url[i+1]) && IsHexNum(_url[i+2]))
{
sscanf(_url + i + 1, "%x", p++);
i += 3;
}
else
{
*(p++) = _url[i++];
}
}
//return Utf8ToStringT(buf);
return CString(buf);
}
*/
CString UrlDecode(LPCTSTR url)
{
_ASSERT(url);
USES_CONVERSION;
LPSTR _url = T2A(const_cast<LPTSTR>(url));
int i = 0;
int length = (int)strlen(_url);
CHAR *buf = new CHAR[length];
ZeroMemory(buf, length);
LPSTR p = buf;
char tmp[4];
while(i < length)
{
if(i <= length -3 && _url[i] == '%' && IsHexNum(_url[i+1]) && IsHexNum(_url[i+2]))
{
memset(tmp, 0, sizeof(tmp));
memcpy(tmp, _url + i + 1,2);
sscanf(tmp, "%x", p++);
i += 3;
}
else
{
*(p++) = _url[i++];
}
}
return Utf8ToStringT(buf);
}
void ConvertUtf8ToGBK(CString & strUtf8)
{
int len=MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUtf8, -1, NULL,0);
unsigned short * wszGBK = new unsigned short[len+1];
memset(wszGBK, 0, len * 2 + 2);
MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUtf8, -1, wszGBK, len);
len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL);
char *szGBK=new char[len + 1];
memset(szGBK, 0, len + 1);
WideCharToMultiByte (CP_ACP, 0, wszGBK, -1, szGBK, len, NULL,NULL);
strUtf8 = szGBK;
delete[] szGBK;
delete[] wszGBK;
}
void ConvertGBKToUtf8(CString & strGBK)
{
int len=MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, NULL,0);
unsigned short * wszUtf8 = new unsigned short[len+1];
memset(wszUtf8, 0, len * 2 + 2);
MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, wszUtf8, len);
len = WideCharToMultiByte(CP_UTF8, 0, wszUtf8, -1, NULL, 0, NULL, NULL);
char *szUtf8=new char[len + 1];
memset(szUtf8, 0, len + 1);
WideCharToMultiByte (CP_UTF8, 0, wszUtf8, -1, szUtf8, len, NULL,NULL);
strGBK = szUtf8;
delete[] szUtf8;
delete[] wszUtf8;
}
void UTF_8ToUnicode(WCHAR * 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;
}
// Unicode 转换成UTF-8
void UnicodeToUTF_8( char * pOut,WCHAR * 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;
}
// 把Unicode 转换成 GB2312
void UnicodeToGB2312( char * pOut,unsigned short uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL);
return;
}
// GB2312 转换成 Unicode
void Gb2312ToUnicode(WCHAR * pOut, char * gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
return;
}
// GB2312 转为 UTF-8
void GB2312ToUTF_8(CString & pOut, char * pText, int pLen)
{
char buf[1024];
char* rst = new char[pLen + (pLen >> 2) + 2];
memset(buf,0,1024);
memset(rst,0,pLen + (pLen >> 2) + 2);
int i = 0;
int j = 0;
while(i < pLen)
{
//如果是英文直接复制就可以
if( *(pText + i) >= 0)
{
rst[j++] = pText[i++];
}
else
{
WCHAR 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;
}
}
strcpy(&rst[j],"\0");
//返回结果
pOut = rst;
delete []rst;
return;
}
// UTF-8 转为 GB2312
void UTF_8ToGB2312(CString & 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[i] > 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;
}
}
strcpy(&newBuf[j],"\0");
pOut = newBuf;
delete []newBuf;
return;
}
CString UTF8_Encode(LPTSTR strUnicode)
{
long TLen ;
CString UTF8_EncodeLong ;
TLen = CString(strUnicode).GetLength() ;
if(TLen == 0)
{
return CString(strUnicode);
}
long lngBufferSize ;
long lngResult ;
//Set buffer for longest possible string.
lngBufferSize = TLen * 3 + 1 ;
char *bytUtf8 = new char[lngBufferSize] ;
//Translate using code page 65001(UTF-8).
lngResult = WideCharToMultiByte(CP_UTF8, 0, (unsigned short*)strUnicode, TLen, bytUtf8, lngBufferSize, NULL, 0) ;
bytUtf8[lngResult] = NULL ;
return CString(bytUtf8) ;
}
/**/ /*************************************************************************/
inline BYTE toHex( const BYTE & x)
{
return x > 9 ? x + 55: x + 48;
}
CString URLEncode(CString sIn)
{
CString sOut;
const int nLen = sIn.GetLength() + 1;
register LPBYTE pOutTmp = NULL;
LPBYTE pOutBuf = NULL;
register LPBYTE pInTmp = NULL;
LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen);
BYTE b = 0;
//alloc out buffer
pOutBuf = (LPBYTE)sOut.GetBuffer(nLen*3 - 2);//new BYTE [nLen * 3];
if(pOutBuf)
{
pInTmp = pInBuf;
pOutTmp = pOutBuf;
// do encoding
while (*pInTmp)
{
if(isalnum(*pInTmp))
*pOutTmp++ = *pInTmp;
else
if(isspace(*pInTmp))
*pOutTmp++ = '+';
else
{
*pOutTmp++ = '%';
*pOutTmp++ = toHex(*pInTmp>>4);
*pOutTmp++ = toHex(*pInTmp%16);
}
pInTmp++;
}
*pOutTmp = '\0';
//sOut=pOutBuf;
//delete [] pOutBuf;
sOut.ReleaseBuffer();
}
sIn.ReleaseBuffer();
return sOut;
}
http://blog.csdn.net/leechiyang/archive/2008/02/22/2112915.aspx http://blog.csdn.net/zhengyun_ustc/archive/2002/05/20/12654.aspx URLEncode: CString URLEncode(CString sIn) //alloc out buffer if(pOutBuf) // do encoding
UrlDecode: CString Utf8ToStringT(LPSTR str) return (CString(W2T(buf))); CString UrlDecode(LPCTSTR url)
#define
IsHexNum(c) ((c >= '0' && c <= '9') || (c >= 'A' && c <= 'F') || (c >= 'a' && c <= 'f'))
CString Utf8ToStringT(LPSTR str) { _ASSERT(str); USES_CONVERSION; WCHAR *buf; int length = MultiByteToWideChar(CP_UTF8, 0, str, -1, NULL, 0); buf = new WCHAR[length+1]; ZeroMemory(buf, (length+1) * sizeof(WCHAR)); MultiByteToWideChar(CP_UTF8, 0, str, -1, buf, length); return (CString(W2T(buf))); } /**/ /* CString UrlDecode(LPCTSTR url) { _ASSERT(url); USES_CONVERSION; LPSTR _url = T2A(const_cast<LPTSTR>(url)); int i = 0; int length = (int)strlen(_url); CHAR *buf = new CHAR[length]; ZeroMemory(buf, length); LPSTR p = buf; while(i < length) { if(i <= length -3 && _url[i] == '%' && IsHexNum(_url[i+1]) && IsHexNum(_url[i+2])) { sscanf(_url + i + 1, "%x", p++); i += 3; } else { *(p++) = _url[i++]; } } //return Utf8ToStringT(buf); return CString(buf); } */ CString UrlDecode(LPCTSTR url) { _ASSERT(url); USES_CONVERSION; LPSTR _url = T2A(const_cast<LPTSTR>(url)); int i = 0; int length = (int)strlen(_url); CHAR *buf = new CHAR[length]; ZeroMemory(buf, length); LPSTR p = buf; char tmp[4]; while(i < length) { if(i <= length -3 && _url[i] == '%' && IsHexNum(_url[i+1]) && IsHexNum(_url[i+2])) { memset(tmp, 0, sizeof(tmp)); memcpy(tmp, _url + i + 1,2); sscanf(tmp, "%x", p++); i += 3; } else { *(p++) = _url[i++]; } } return Utf8ToStringT(buf); } void ConvertUtf8ToGBK(CString & strUtf8) { int len=MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUtf8, -1, NULL,0); unsigned short * wszGBK = new unsigned short[len+1]; memset(wszGBK, 0, len * 2 + 2); MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUtf8, -1, wszGBK, len); len = WideCharToMultiByte(CP_ACP, 0, wszGBK, -1, NULL, 0, NULL, NULL); char *szGBK=new char[len + 1]; memset(szGBK, 0, len + 1); WideCharToMultiByte (CP_ACP, 0, wszGBK, -1, szGBK, len, NULL,NULL); strUtf8 = szGBK; delete[] szGBK; delete[] wszGBK; } void ConvertGBKToUtf8(CString & strGBK) { int len=MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, NULL,0); unsigned short * wszUtf8 = new unsigned short[len+1]; memset(wszUtf8, 0, len * 2 + 2); MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strGBK, -1, wszUtf8, len); len = WideCharToMultiByte(CP_UTF8, 0, wszUtf8, -1, NULL, 0, NULL, NULL); char *szUtf8=new char[len + 1]; memset(szUtf8, 0, len + 1); WideCharToMultiByte (CP_UTF8, 0, wszUtf8, -1, szUtf8, len, NULL,NULL); strGBK = szUtf8; delete[] szUtf8; delete[] wszUtf8; } void UTF_8ToUnicode(WCHAR * 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; } // Unicode 转换成UTF-8 void UnicodeToUTF_8( char * pOut,WCHAR * 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; } // 把Unicode 转换成 GB2312 void UnicodeToGB2312( char * pOut,unsigned short uData) { WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(WCHAR),NULL,NULL); return; } // GB2312 转换成 Unicode void Gb2312ToUnicode(WCHAR * pOut, char * gbBuffer) { ::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1); return; } // GB2312 转为 UTF-8 void GB2312ToUTF_8(CString & pOut, char * pText, int pLen) { char buf[1024]; char* rst = new char[pLen + (pLen >> 2) + 2]; memset(buf,0,1024); memset(rst,0,pLen + (pLen >> 2) + 2); int i = 0; int j = 0; while(i < pLen) { //如果是英文直接复制就可以 if( *(pText + i) >= 0) { rst[j++] = pText[i++]; } else { WCHAR 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; } } strcpy(&rst[j],"\0"); //返回结果 pOut = rst; delete []rst; return; } // UTF-8 转为 GB2312 void UTF_8ToGB2312(CString & 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[i] > 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; } } strcpy(&newBuf[j],"\0"); pOut = newBuf; delete []newBuf; return; } CString UTF8_Encode(LPTSTR strUnicode) { long TLen ; CString UTF8_EncodeLong ; TLen = CString(strUnicode).GetLength() ; if(TLen == 0) { return CString(strUnicode); } long lngBufferSize ; long lngResult ; //Set buffer for longest possible string. lngBufferSize = TLen * 3 + 1 ; char *bytUtf8 = new char[lngBufferSize] ; //Translate using code page 65001(UTF-8). lngResult = WideCharToMultiByte(CP_UTF8, 0, (unsigned short*)strUnicode, TLen, bytUtf8, lngBufferSize, NULL, 0) ; bytUtf8[lngResult] = NULL ; return CString(bytUtf8) ; } /**/ /*************************************************************************/ inline BYTE toHex( const BYTE & x) { return x > 9 ? x + 55: x + 48; } CString URLEncode(CString sIn) { CString sOut; const int nLen = sIn.GetLength() + 1; register LPBYTE pOutTmp = NULL; LPBYTE pOutBuf = NULL; register LPBYTE pInTmp = NULL; LPBYTE pInBuf =(LPBYTE)sIn.GetBuffer(nLen); BYTE b = 0; //alloc out buffer pOutBuf = (LPBYTE)sOut.GetBuffer(nLen*3 - 2);//new BYTE [nLen * 3]; if(pOutBuf) { pInTmp = pInBuf; pOutTmp = pOutBuf; // do encoding while (*pInTmp) { if(isalnum(*pInTmp)) *pOutTmp++ = *pInTmp; else if(isspace(*pInTmp)) *pOutTmp++ = '+'; else { *pOutTmp++ = '%'; *pOutTmp++ = toHex(*pInTmp>>4); *pOutTmp++ = toHex(*pInTmp%16); } pInTmp++; } *pOutTmp = '\0'; //sOut=pOutBuf; //delete [] pOutBuf; sOut.ReleaseBuffer(); } sIn.ReleaseBuffer(); return sOut; } } |