C++ 字符集转换留着用

来源：互联网发布：linux ntpdate命令编辑：程序博客网时间：2024/06/01 21:34

char* UnicodeToUtf8( WCHAR*  wszUtf8)
{
    int len= WideCharToMultiByte(CP_UTF8,0, wszUtf8,-1, NULL,0, NULL, NULL);
    char* szUtf8=newchar[len+1];
    memset(szUtf8,0, len+1);
    WideCharToMultiByte (CP_UTF8,0, wszUtf8,-1, szUtf8, len, NULL,NULL);
    return szUtf8;
}
WCHAR* ConvertUtf8ToGBK( char* szUtf8 )
{
    int len=MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)szUtf8 ,-1, NULL,0);
    WCHAR* wszUCD=new WCHAR[len+1];
    memset(wszUCD,0, len*2+2);
    MultiByteToWideChar(CP_UTF8,0, (LPCTSTR)strUtf8,-1, wszUCD, len);
    return wszUCD;
}

classCChineseCode{

public:

staticvoid UTF_8ToUnicode(wchar_t* pOut,char *pText); //把UTF-8转换成Unicode

staticvoid UnicodeToUTF_8(char* pOut,wchar_t* pText); //Unicode转换成UTF-8

staticvoid UnicodeToGB2312(char* pOut,wchar_t uData); //把Unicode转换成 GB2312

staticvoid Gb2312ToUnicode(wchar_t* pOut,char *gbBuffer);// GB2312转换成　Unicode

staticvoid GB2312ToUTF_8(string& pOut,char *pText, int pLen);//GB2312转为 UTF-8

staticvoid UTF_8ToGB2312(string &pOut, char *pText, int pLen);//UTF-8转为 GB2312

};

//类实现

voidCChineseCode::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;

}

voidCChineseCode::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;

}

voidCChineseCode::UnicodeToGB2312(char* pOut,wchar_t uData){

WideCharToMultiByte(CP_ACP,NULL,&uData,1,pOut,sizeof(wchar_t),NULL,NULL);

return;

}

voidCChineseCode::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){

charbuf[4];

intnLength = pLen* 3;

char*rst = new char[nLength];

memset(buf,0,4);

memset(rst,0,nLength);

inti = 0;

intj = 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_tpbuffer;

Gb2312ToUnicode(&pbuffer,pText+i);

UnicodeToUTF_8(buf,&pbuffer);

unsignedshort 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]=’’;

//返回结果

pOut= rst;

delete[]rst;

return;

}

voidCChineseCode::UTF_8ToGB2312(string &pOut, char *pText, int pLen){

char* newBuf = new char[pLen];

charCtemp[4];

memset(Ctemp,0,4);

inti =0;

intj = 0;

while(i< pLen){

if(pText> 0){

newBuf[j++] =pText[i++];

}else{

WCHARWtemp;

UTF_8ToUnicode(&Wtemp,pText+ i);

UnicodeToGB2312(Ctemp,Wtemp);

newBuf[j]= Ctemp[0];

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

i+= 3;

j+= 2;

}

newBuf[j]=’’;

pOut= newBuf;

delete[]newBuf;

return;

}

//UTF-8到GB2312的转换
char* U2G(const char* utf8)
{
int len = MultiByteToWideChar(CP_UTF8, 0, utf8, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_UTF8, 0, utf8, -1, wstr, len);
len = WideCharToMultiByte(CP_ACP, 0, wstr, -1, NULL, 0, NULL, NULL);
char* str = new char[len+1];
memset(str, 0, len+1);
WideCharToMultiByte(CP_ACP, 0, wstr, -1, str, len, NULL, NULL);
if(wstr) delete[] wstr;
return str;
}

//GB2312到UTF-8的转换
char* G2U(const char* gb2312)
{
int len = MultiByteToWideChar(CP_ACP, 0, gb2312, -1, NULL, 0);
wchar_t* wstr = new wchar_t[len+1];
memset(wstr, 0, len+1);
MultiByteToWideChar(CP_ACP, 0, gb2312, -1, wstr, len);
len = WideCharToMultiByte(CP_UTF8, 0, wstr, -1, NULL, 0, NULL, NULL);
char* str = new char[len+1];
memset(str, 0, len+1);
WideCharToMultiByte(CP_UTF8, 0, wstr, -1, str, len, NULL, NULL);
if(wstr) delete[] wstr;
return str;
}

0 0