Re: [9fans] tcs bug

[arisawa@ar.aichi-u.ac.jp]

> one problem with this fix is that it assumes valid utf-8 input.
> you're better off using fullrune.
>

more simple and robust solution
that follows forsyth's suggestion


/* read until utf boundary */
int
readu(int fd, char *buf, int n)
{
         static char b[3];
         static int nb;
         int m;
         char *s, *e;
         if(nb)
                 memcpy(buf, b, nb);
         m = read(fd, buf + nb, n - nb);

         /*
         01.   x in [00000000.0bbbbbbb] → 0bbbbbbb
         10.   x in [00000bbb.bbbbbbbb] → 110bbbbb, 10bbbbbb
         11.   x in [bbbbbbbb.bbbbbbbb] → 1110bbbb, 10bbbbbb, 
10bbbbbb
         */

         e = buf + m + nb;
         for(s = e - 2; s < e; s++){
                 if((*s & 0xc0) == 0x80)
                         continue;
                 if((*s & 0xc0) == 0xc0)
                         break;
         }

         /* we have e - s bytes in s     */
         nb = e - s;
         memcpy(b, s, nb);
         return s - buf;
}

Kenji Arisawa