Re: [bug-gnulib] Handling of invalid multibyte character sequences in fnmatch()

[Paul Eggert]

James Youngman <address@hidden> writes:

> Any ideas/suggestions?

Does the following untested patch fix things?  It attempts to mimic
what Bash does.

*** fnmatch.c   Fri May 13 23:03:58 2005
--- /tmp/fnmatch.c      Tue Jun  7 00:02:03 2005
*************** fnmatch (const char *pattern, const char
*** 319,372 ****
         wide characters.  */
        memset (&ps, '\0', sizeof (ps));
        patsize = mbsrtowcs (NULL, &pattern, 0, &ps) + 1;
!       if (__builtin_expect (patsize == 0, 0))
!       /* Something wrong.
!          XXX Do we have to set `errno' to something which mbsrtows hasn't
!          already done?  */
!       return -1;
!       assert (mbsinit (&ps));
!       strsize = mbsrtowcs (NULL, &string, 0, &ps) + 1;
!       if (__builtin_expect (strsize == 0, 0))
!       /* Something wrong.
!          XXX Do we have to set `errno' to something which mbsrtows hasn't
!          already done?  */
!       return -1;
!       assert (mbsinit (&ps));
!       totsize = patsize + strsize;
!       if (__builtin_expect (! (patsize <= totsize
!                              && totsize <= SIZE_MAX / sizeof (wchar_t)),
!                           0))
        {
!         errno = ENOMEM;
!         return -1;
!       }
! 
!       /* Allocate room for the wide characters.  */
!       if (__builtin_expect (totsize < ALLOCA_LIMIT, 1))
!       wpattern = (wchar_t *) alloca (totsize * sizeof (wchar_t));
!       else
!       {
!         wpattern = malloc (totsize * sizeof (wchar_t));
!         if (__builtin_expect (! wpattern, 0))
            {
!             errno = ENOMEM;
!             return -1;
            }
        }
-       wstring = wpattern + patsize;
- 
-       /* Convert the strings into wide characters.  */
-       mbsrtowcs (wpattern, &pattern, patsize, &ps);
-       assert (mbsinit (&ps));
-       mbsrtowcs (wstring, &string, strsize, &ps);
- 
-       res = internal_fnwmatch (wpattern, wstring, wstring + strsize - 1,
-                              flags & FNM_PERIOD, flags);
- 
-       if (__builtin_expect (! (totsize < ALLOCA_LIMIT), 0))
-       free (wpattern);
-       return res;
      }
  # endif /* HANDLE_MULTIBYTE */
  
    return internal_fnmatch (pattern, string, string + strlen (string),
--- 319,369 ----
         wide characters.  */
        memset (&ps, '\0', sizeof (ps));
        patsize = mbsrtowcs (NULL, &pattern, 0, &ps) + 1;
!       if (__builtin_expect (patsize != 0, 1))
        {
!         assert (mbsinit (&ps));
!         strsize = mbsrtowcs (NULL, &string, 0, &ps) + 1;
!         if (__builtin_expect (strsize != 0, 1))
            {
!             assert (mbsinit (&ps));
!             totsize = patsize + strsize;
!             if (__builtin_expect (! (patsize <= totsize
!                                      && totsize <= SIZE_MAX / sizeof 
(wchar_t)),
!                                   0))
!               {
!                 errno = ENOMEM;
!                 return -1;
!               }
! 
!             /* Allocate room for the wide characters.  */
!             if (__builtin_expect (totsize < ALLOCA_LIMIT, 1))
!               wpattern = (wchar_t *) alloca (totsize * sizeof (wchar_t));
!             else
!               {
!                 wpattern = malloc (totsize * sizeof (wchar_t));
!                 if (__builtin_expect (! wpattern, 0))
!                   {
!                     errno = ENOMEM;
!                     return -1;
!                   }
!               }
!             wstring = wpattern + patsize;
! 
!             /* Convert the strings into wide characters.  */
!             mbsrtowcs (wpattern, &pattern, patsize, &ps);
!             assert (mbsinit (&ps));
!             mbsrtowcs (wstring, &string, strsize, &ps);
! 
!             res = internal_fnwmatch (wpattern, wstring, wstring + strsize - 1,
!                                      flags & FNM_PERIOD, flags);
! 
!             if (__builtin_expect (! (totsize < ALLOCA_LIMIT), 0))
!               free (wpattern);
!             return res;
            }
        }
      }
+ 
  # endif /* HANDLE_MULTIBYTE */
  
    return internal_fnmatch (pattern, string, string + strlen (string),