UTF8 CString 互转问题和代码

最新推荐文章于 2025-05-22 12:11:07 发布

翻译最新推荐文章于 2025-05-22 12:11:07 发布 · 1.2k 阅读

C++ 专栏收录该内容

103 篇文章

订阅专栏

本文提供了将UTF8编码转换为Unicode编码及反之的方法，并详细解释了如何通过位操作解析UTF8编码的字节数，适用于不同长度的UTF8字符。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

//把utf8转成unicode，再转成cstring
void ConvertUTF8ToANSI(char* strUTF8,CString &strANSI)   //
{
   int nLen = ::MultiByteToWideChar(CP_UTF8,MB_ERR_INVALID_CHARS,(LPCTSTR)strUTF8,-1,NULL,0);   //返回需要的unicode长度
   WCHAR * wszANSI = new WCHAR[nLen+1];
   memset(wszANSI, 0, nLen * 2 + 2);
   nLen = MultiByteToWideChar(CP_UTF8, 0, (LPCTSTR)strUTF8, -1, wszANSI, nLen);   //把utf8转成unicode

   nLen = WideCharToMultiByte(CP_ACP, 0, wszANSI, -1, NULL, 0, NULL, NULL);       //得到要的ansi长度
   char *szANSI=new char[nLen + 1];
   memset(szANSI, 0, nLen + 1);
   WideCharToMultiByte (CP_ACP, 0, wszANSI, -1, szANSI, nLen, NULL,NULL);           //把unicode转成ansi
   strANSI = szANSI;
   delete wszANSI;
   delete szANSI;

}

void ConvertANSIToUTF8(CString &strANSI)
{
int nLen = ::MultiByteToWideChar(CP_ACP,MB_ERR_INVALID_CHARS,(LPCTSTR)strANSI,-1,NULL,0);
unsigned short * wszUTF_8 = new unsigned short[nLen+1];
memset(wszUTF_8, 0, nLen * 2 + 2);
nLen = MultiByteToWideChar(CP_ACP, 0, (LPCTSTR)strANSI, -1, wszUTF_8, nLen);

nLen = WideCharToMultiByte(CP_UTF8, 0, wszUTF_8, -1, NULL, 0, NULL, NULL);
    char *szUTF8=new char[nLen + 1];
    memset(szUTF8, 0, nLen + 1);
    WideCharToMultiByte (CP_UTF8, 0, wszUTF_8, -1, szUTF8, nLen, NULL,NULL);
strANSI = szUTF8;
delete wszUTF_8;
delete szUTF8;
}

short Utf8TextBytes (const unsigned char *mstr)
{
    short textbytes = 0;
    if (mstr == 0)
    {                           //Returns 0 if mstr contains a null string or if there is
        return 0;               //no valid character in mstr.
    }
    /* code checking.
   because all unicode used now is lower than 0xffff, only 1~3 bytes UTF-8 has means,
   the other length will not be dealed with in other functions */
    if (((*mstr) & 0x80) == 0)
    {
        textbytes = 1;          //0xxxxxxx, normal ASCII code
    }
    else if ((((*mstr) & 0xe0) == 0xc0) && (((*(mstr + 1)) & 0xc0) == 0x80))
    {
        if (((*mstr) & 0xfe) == 0xc0) //1100,000x is illegal data,
        {
            textbytes = 0;
        }
        else
        {
            textbytes = 2;      //110xxxxx 10xxxxxx
        }
    }
    else if ((((*mstr) & 0xf0) == 0xe0) && (((*(mstr + 1)) & 0xc0) == 0x80) && (((*(mstr + 2)) & 0xc0) == 0x80))
    {
        if ((*mstr == (char) 0xe0) && (((*(mstr + 1)) & 0xe0) == 0x80)) //1110,0000,100x,xxxx is illegal data
        {
            textbytes = 0;
        }
        else
        {
            textbytes = 3;      //1110xxxx 10xxxxxx 10xxxxxx
        }
    }
    else if ((((*mstr) & 0xf8) == 0xf0) && (((*(mstr + 1)) & 0xc0) == 0x80) && (((*(mstr + 2)) & 0xc0) == 0x80)
             && (((*(mstr + 3)) & 0xc0) == 0x80))
    {
        if (((*mstr) == (char) 0xf0) && (((*(mstr + 1)) & 0xf0) == 0x80)) // 1111,0000,1000,xxxx is illegal data
        {
            textbytes = 0;
        }
        else
        {
            textbytes = 4;      // 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
        }
    }
    else if ((((*mstr) & 0xfc) == 0xf8) && (((*(mstr + 1)) & 0xc0) == 0x80) &&
             (((*(mstr + 2)) & 0xc0) == 0x80) && (((*(mstr + 3)) & 0xc0) == 0x80) && (((*(mstr + 4)) & 0xc0) == 0x80))
    {
        if ((*mstr == (char) 0xf8) && (((*(mstr + 1)) & 0xf8) == 0x80)) //1111,1000,1000,0xxx is illegal data
        {
            textbytes = 0;
        }
        else
        {
            textbytes = 5;      //111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
        }
    }
    else if ((((*mstr) & 0xfe) == 0xfc) && (((*(mstr + 1)) & 0xc0) == 0x80) &&
             (((*(mstr + 2)) & 0xc0) == 0x80) && (((*(mstr + 3)) & 0xc0) == 0x80) && (((*(mstr + 4)) & 0xc0) == 0x80) &&
             (((*(mstr + 5)) & 0xc0) == 0x80))
    {
        if ((*mstr == (char) 0xfc) && (((*(mstr + 1)) & 0xfc) == 0x80)) //1111,1100,1000,00xx is illegal data
        {
            textbytes = 0;
        }
        else
        {
            textbytes = 6;      //1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
        }
    }
    else
    {
        textbytes = 0;          //illegal formal, return 0
    }

    return textbytes;
}

utf8Str --UTF8 source string
utf8strlen --max utf8 length
unStr -- Unicode Str dest
unMaxlen --Unicode 最大个数
return : --实际转化的长度
short FromUTF8ToUnicode (unsigned char *utf8Str, short utf8StrLen, WORD * unStr, unsigned short unMaxLen)

{
   short zen_han, len_dest;
   unsigned char *p_src;
   unsigned char utf8_len = 0;
   len_dest = 0;
   p_src = (unsigned char *) (utf8Str);

   /* limit the total bytes of the *mstr */
   if (utf8StrLen <= 0)
   {
       return (0);
   }

   /* converting at here utf8_len <= utf8StrLen 改为 utf8_len < utf8StrLen*/
   for (; (*p_src != 0x00) && (len_dest <= unMaxLen - 1) && (utf8_len < utf8StrLen);)
   {
       zen_han = Utf8TextBytes ((const unsigned char *) p_src);
       if (zen_han == 1)       //ASCII, just add 0x00 at beginning
       {
           (*unStr) = *(p_src);
           unStr++;
           p_src++;
           utf8_len++;
           len_dest += 1;
       }
       else if (zen_han == 2)
       {
           *unStr = (((((*p_src) >> 2) & (unsigned char) 0x07)) & 0x00ff) << 8;
           *unStr |= ((((*p_src) << 6) | ((*(p_src + 1)) & (unsigned char) 0x3f))) & 0x00ff;
           unStr++;
           p_src += 2;
           utf8_len += 2;
           len_dest += 1;

       }
       else if (zen_han == 3)
       {
           *(unStr) = ((((*(p_src)) << 4) | (((*(p_src + 1)) >> 2) & 0x0f)) & 0x00ff) << 8;

           *unStr |= ((((*(p_src + 1)) << 6) | ((*(p_src + 2)) & (unsigned char) 0x3f))) & 0x00ff;
           unStr++;
           p_src += 3;
           utf8_len += 3;
           len_dest += 1;
       }
       else if (zen_han == 4) //
       {
           *unStr = (*(p_src)) & 0x7;
           for (int i=1; i<4;i++)
           {
               *unStr <<= 6; // 左移6位后与后续字节的有效位值"位或"赋值
               *unStr = *unStr | ((*(p_src + i)) & 0x3f);//先与后或
           }
           unStr++;
           p_src += 4;
           utf8_len += 4;
           len_dest += 1;
       }
       else if (zen_han == 5) //
       {
           *unStr = (*(p_src)) & 0x3;
           for (int i=1; i<5;i++)
           {
               *unStr <<= 6; // 左移6位后与后续字节的有效位值"位或"赋值
               *unStr = *unStr | ((*(p_src + i)) & 0x3f);//先与后或
           }
           unStr++;
           p_src += 5;
           utf8_len += 5;
           len_dest += 1;
       }
       else if (zen_han == 6) //
       {
           *unStr = (*(p_src)) & 0x1;
           for (int i=1; i<6;i++)
           {
               *unStr <<= 6; // 左移6位后与后续字节的有效位值"位或"赋值
               *unStr = *unStr | ((*(p_src + i)) & 0x3f);//先与后或
           }
           unStr++;
           p_src += 6;
           utf8_len += 6;
           len_dest += 1;
       }
       else                    //treated as illegal character, search the next character
       {
           p_src++;
           utf8_len++;
       }
   }
   *(unStr) = 0x0000;
   return (len_dest);

}