From mboxrd@z Thu Jan  1 00:00:00 1970
Mime-Version: 1.0 (Apple Message framework v734)
In-Reply-To: <9D17C8E2-2DE4-4E34-A95B-59A6232B132D@ar.aichi-u.ac.jp>
References: <9D17C8E2-2DE4-4E34-A95B-59A6232B132D@ar.aichi-u.ac.jp>
Content-Type: text/plain; charset=ISO-2022-JP; format=flowed
Message-Id: <37F6EFDF-3C9E-48F9-A03F-6ED617BA6166@ar.aichi-u.ac.jp>
Content-Transfer-Encoding: 7bit
From: arisawa@ar.aichi-u.ac.jp
Subject: Re: [9fans] tcs bug
Date: Wed, 31 Aug 2005 18:11:49 +0900
To: Fans of the OS Plan 9 from Bell Labs <9fans@cse.psu.edu>
Topicbox-Message-UUID: 81cedd1c-ead0-11e9-9d60-3106f5b1d025

The bellow is a first-aid bug fix

we define read function for utf-8

/* 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 = buf; s < e; s++){
         if((*s & 0x80) == 0)
             continue;
         if((*s & 0xe0) == 0xd0){
             s++;
             continue;
         }
         /* then *s is 111bbbbb */
         if(s+2 >= e)
             break;
         s += 2;
         continue;
     }
     /* we have e - s bytes in s    */
     nb = e - s;
     memcpy(b, s, nb);
     return s - buf;
}

and replace 'read' by 'readu' in utf.c

utf_in(int fd, long *notused, struct convert *out)
{

     ...
     while((n = readu(fd, buf+tot, N-tot)) >= 0){
         ...
}

Kenji Arisawa