UTF8转Unicode

int GetUtf8ByteNumForWord(char firstCh)
{
    int nRet=0;
    __asm
    {    
        movzx ecx,byte ptr[firstCh]
        and ecx,0xE0
        jz  done
        test ecx,0x80
        jnz lbm
        mov nRet,1
        jmp done
lbm:
        cmp cl,0xE0
        jz  lb3
        cmp cl,0x0C
        jz  lb2
        jmp done
lb3:
        mov nRet,3
        jmp done
lb2:
        mov nRet,2
done:
    }
    return nRet;
}
void Utf8ToUnicode(const char* utf8, int len, wchar_t *unicode)
{
    int i = 0;
    int j = 0;
    char* temp=(char*)unicode;
    //循环解析
    while (i < len)
    {   
        int nByteNum=GetUtf8ByteNumForWord(utf8[i]);
        if (nByteNum==0)
        {
            return;
        }
        switch(nByteNum)
        {
        case 1:
            temp[j] = utf8[i];
            temp[j+1]=0;
            break;
        case 2:
            temp[j] = utf8[i];
            temp[j + 1] = utf8[i + 1];
            break;
        case 3:
            //这里就开始进行UTF8->Unicode
            temp[j + 1] = ((utf8[i] & 0x0F) << 4) | ((utf8[i + 1] >> 2) & 0x0F);
            temp[j] = ((utf8[i + 1] & 0x03) << 6) + (utf8[i + 2] & 0x3F);
            break;
        default:
            break;    
        }
        j+=2;
        i+=nByteNum;
    }
    temp[j]=0;
    temp[j+1]=0;
}

测试代码如下：

std::ifstream fin("debug\\Test.txt");
const unsigned int L_MAX_LINE=1024;
char utf8[L_MAX_LINE];
wchar_t unicode[L_MAX_LINE];
while(fin.getline(utf8,L_MAX_LINE))
{
    Utf8ToUnicode(utf8,strlen(utf8),unicode);
    MessageBoxW(0,unicode,0,0);
}
fin.close();