在做关于字符识别和应用的过程中常常遇到UFT8和GB232之间的转换,至于什么是UTF8,什么是GB232这个我就不细细的说了,后续有时间在补上,在这里主要是贴上自己的转换代码,后续在使用的时候自己能清楚的知道,对其它的在使用这一块的朋友也有个帮助~!
void 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);
}
void 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));
}
void UnicodeToGB2312(char* pOut,wchar_t uData)
{
WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);
}
void Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer)
{
::MultiByteToWideChar(CP_ACP,MB_PRECOMPOSED,gbBuffer,2,pOut,1);
}
void GB2312ToUTF_8(string& pOut,char *pText, int pLen)
{
char buf[4] = {0};
int nLength = pLen* 3;
char* rst = new char[nLength];
memset(rst,0,nLength);
int i = 0 ,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_t pbuffer;
Gb2312ToUnicode(&pbuffer,pText+i);
UnicodeToUTF_8(buf,&pbuffer);
rst[j] = buf[0];
rst[j+1] = buf[1];
rst[j+2] = buf[2];
j += 3;
i += 2;
}
}
rst[j] ='\n'; //返回结果
pOut = rst;
delete []rst;
return;
}
void UTF_8ToGB2312(char*pOut, char *pText, int pLen)
{
char Ctemp[4];
memset(Ctemp,0,4);
int i =0 ,j = 0;
while(i < pLen)
{
if(pText[i] >= 0)
{
pOut[j++] = pText[i++];
}
else
{
WCHAR Wtemp;
UTF_8ToUnicode(&Wtemp,pText + i);
UnicodeToGB2312(Ctemp,Wtemp);
pOut[j] = Ctemp[0];
pOut[j + 1] = Ctemp[1];
i += 3;
j += 2;
}
}
pOut[j] ='\n';
return;
}
后续主函数调用过程如下:
char *outStr = new[n];//根据实际需要分配//
char *pText = (char *)charSymbolString.c_str();
UTF_8ToGB2312(outStr,pText,strlen(charSymbolString.c_str()));
std::string strTemp = std::string(outStr);