From: bc@freeuk.com   
      
   On 15/11/2025 05:24, Bonita Montero wrote:   
   > A little bugfix and a perfect style:   
   >   
   > #include    
   > #include    
   > #include    
   > #include    
   >   
   > using namespace std;   
   >   
   > optional utf8Width( u8string_view str )   
   > {   
   >      size_t w = 0;   
   >      for( auto it = str.begin(); it != str.end(); ++w ) [[likely]]   
   >          if( size_t head = countl_zero( (unsigned char)~*it ); head <= 4   
   > && (size_t)(str.end() - it) >= head + 1 ) [[likely]]   
   >              it += head + 1;   
   >          else   
   >              return nullopt;   
   >      return w;   
   > }   
   >   
   > int main()   
   > {   
   >      cout << *utf8Width( u8"Hello, 世界!" ) << endl;   
   > }   
   >   
      
   The trouble with this is that I haven't a clue how it works or what   
   those extras do, or how they impact on performance.   
      
   A version in C is given below. This is much more straightforward. It   
   doesn't verify anything, but then I don't know if yours does either.   
      
   As for performance: I duplicated that test string to form one 104 times   
   as long, then called that function one million times. Here are the timings:   
      
      C   gcc-O2     1.06   seconds   
      C   bcc        1.17   seconds   
      C   tcc        2.81   seconds   
      
      C++ g++-O2     4.6   seconds   
      C++ g++-O0    19     seconds   
      
   --------------------------   
      
   size_t utf8width(char* s) {   
        size_t length;   
        int c, n;   
      
        length=0;   
        while (c=*s) {   
            if ((c & 0x80) == 0) n = 1;   
            else if ((c & 0xE0) == 0xC0) n = 2;   
            else if ((c & 0xF0) == 0xE0) n = 3;   
            else n = 4;   
            s += n;   
            ++length;   
        }   
        return length;   
   }   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)