如何在C++中使用unicode編碼

來源:互聯網
上載者:User

char * input = "大家好, World!";
int cd = iconv_open("utf8", "gb2312");
int il = strlen(input);
int bufl = il * 3 + 1;
char * output = (char *)calloc(bufl, sizeof(char));
char * p = output;
int oleft = bufl;
int ret = iconv(cd, (const char **)&input, &il, &p, &oleft);
iconv_close(cd);
int ol = bufl - oleft;
剩下的就是將output轉為unicode
unsigned short * utf2unicode(char * utf8, int utf8_length, int * pwcs_length)
{
   int i = 0;
   unsigned short * wcs;
   unsigned short a, b, c;
   char * p1 = utf8;
   char * p2;
   char * end = p1 + utf8_length;
   wcs = (unsigned short *)calloc(utf8_length+1, sizeof(benwchar_t));
   while (p1 < end)
   {
      p2 = (char *)&wcs[i++];
      if ((*p1 & 0xE0) == 0xE0)
      {
         *p2++ = ((*p1 & 0x0F) << 4) | (*(p1+1) & 0x3C) >> 2;
         *p2 = ((*(p1+1) & 0x3F) << 6) | (*(p1+2) & 0x3F);
         p1 += 3;
      }
      else if ((*p1 & 0xC0) == 0xC0)
      {
         *p2++ = (*p1 & 0x1F) >> 2;
         *p2 = ((*p1 & 0x1F) << 6 ) | (*(p1+1) & 0x3F);
         p1 += 2;
      }
      else if ((*p1 & 0x80) == 0x0)
      {
         *p2++ = 0;
         *p2 = *p1;
         p1 += 1;
      }
      else break;
   }
   *pwcs_length = i;
   return (wcs);
}
 

聯繫我們

該頁面正文內容均來源於網絡整理,並不代表阿里雲官方的觀點,該頁面所提到的產品和服務也與阿里云無關,如果該頁面內容對您造成了困擾,歡迎寫郵件給我們,收到郵件我們將在5個工作日內處理。

如果您發現本社區中有涉嫌抄襲的內容,歡迎發送郵件至: info-contact@alibabacloud.com 進行舉報並提供相關證據,工作人員會在 5 個工作天內聯絡您,一經查實,本站將立刻刪除涉嫌侵權內容。

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.