当前位置: 首页 >> 程序设计 >> Unicode与UTF8互转源代码

Unicode与UTF8互转源代码

作者：来源：http://blog.csdn.net/flying8127 发表时间：2007-05-15 浏览次数：字号：大 中 小

int UTF2Uni(const char* src, std::wstring &t)
{
if (src == NULL)
{
return -1;
}

int size_s = strlen(src);
int size_d = size_s + 10;          //?

wchar_t *des = new wchar_t[size_d];
memset(des, 0, size_d * sizeof(wchar_t));

int s = 0, d = 0;
bool toomuchbyte = true; //set true to skip error prefix.

while (s < size_s && d < size_d)
{
  unsigned char c = src[s];
  if ((c & 0x80) == 0)
  {
   des[d++] += src[s++];
  }
  else if((c & 0xE0) == 0xC0)  ///< 110x-xxxx 10xx-xxxx
  {
   WCHAR &wideChar = des[d++];
   wideChar = (src[s + 0] & 0x3F) << 6;
   wideChar |= (src[s + 1] & 0x3F);

   s += 2;
  }
  else if((c & 0xF0) == 0xE0)  ///< 1110-xxxx 10xx-xxxx 10xx-xxxx
  {
   WCHAR &wideChar = des[d++];

   wideChar = (src[s + 0] & 0x1F) << 12;
   wideChar |= (src[s + 1] & 0x3F) << 6;
   wideChar |= (src[s + 2] & 0x3F);

   s += 3;
  }
  else if((c & 0xF8) == 0xF0)  ///< 1111-0xxx 10xx-xxxx 10xx-xxxx 10xx-xxxx
  {
   WCHAR &wideChar = des[d++];

   wideChar = (src[s + 0] & 0x0F) << 18;
   wideChar = (src[s + 1] & 0x3F) << 12;
   wideChar |= (src[s + 2] & 0x3F) << 6;
   wideChar |= (src[s + 3] & 0x3F);

   s += 4;
  }
  else
  {
   WCHAR &wideChar = des[d++]; ///< 1111-10xx 10xx-xxxx 10xx-xxxx 10xx-xxxx 10xx-xxxx

   wideChar = (src[s + 0] & 0x07) << 24;
   wideChar = (src[s + 1] & 0x3F) << 18;
   wideChar = (src[s + 2] & 0x3F) << 12;
   wideChar |= (src[s + 3] & 0x3F) << 6;
   wideChar |= (src[s + 4] & 0x3F);

s += 5;
}
}

t = des;
delete[] des;
des = NULL;

return 0;
}

int Uni2UTF(wchar_t wchar, char *utf8)
{
if (utf8 == NULL) {
  return -1;
}
int len = 0;
int size_d = 8;

if (wchar < 0x80)
{  //
  //length = 1;
  utf8[len++] = (char)wchar;
}
else if(wchar < 0x800)
{
  //length = 2;

  if (len + 1 >= size_d)
   return -1;

  utf8[len++] = 0xc0 | ( wchar >> 6 );
  utf8[len++] = 0x80 | ( wchar & 0x3f );
}
else if(wchar < 0x10000 )
{
  //length = 3;
  if (len + 2 >= size_d)
   return -1;

  utf8[len++] = 0xe0 | ( wchar >> 12 );
  utf8[len++] = 0x80 | ( (wchar >> 6) & 0x3f );
  utf8[len++] = 0x80 | ( wchar & 0x3f );
}
else if( wchar < 0x200000 )
{
  //length = 4;
  if (len + 3 >= size_d)
   return -1;

  utf8[len++] = 0xf0 | ( (int)wchar >> 18 );
  utf8[len++] = 0x80 | ( (wchar >> 12) & 0x3f );
  utf8[len++] = 0x80 | ( (wchar >> 6) & 0x3f );
  utf8[len++] = 0x80 | ( wchar & 0x3f );
}
return len;
}