MFC/C++用Char*（Byte*）讀取文件utf-8的文件亂碼----解碼

//utf8Str：以字節（char*或者Byte*）讀取中文的字符串（亂碼）
CString UTF8toUnicode(const char* utf8Str)
{
    UINT theLength=strlen(utf8Str);
    return UTF8toUnicode(utf8Str,theLength);
}
 
CString UTF8toUnicode(const char* utf8Str,UINT length)
{
    CString unicodeStr;
    unicodeStr=_T("");
 
    if (!utf8Str)
        return unicodeStr;
 
    if (length==0)
        return unicodeStr;
 
  
    WCHAR chr=0;//一個中文字符
    for (UINT i=0;i<length;)
    {
        //UTF8的三種中文格式
        if ((0x80&utf8Str[i])==0) //只占用一個字節
        {
            chr=utf8Str[i];
            i++;
        }
        else if((0xE0&utf8Str[i])==0xC0) //占用兩個字節
        {
            chr =(utf8Str[i+0]&0x3F)<<6;
            chr|=(utf8Str[i+1]&0x3F);
            i+=2;
        }
        else if((0xF0&utf8Str[i])==0xE0)//占用三個字節
        {
            chr =(utf8Str[i+0]&0x1F)<<12;
            chr|=(utf8Str[i+1]&0x3F)<<6;
            chr|=(utf8Str[i+2]&0x3F);
            i+=3;
        }
      
        else 
        {
            return unicodeStr;
        }
        unicodeStr.AppendChar(chr);
    }
 
    return unicodeStr;
}

UTF-8百度百科仔細研究!!!

轉自：https://blog.csdn.net/chenlu5201314/article/details/8912707?utm_medium=distribute.pc_relevant.none-task-blog-baidujs-3