GNU bug report logs - #22169
25.0.50; File name compiletion doesn't work with non-ASCII characters on OS X

Previous Next

Full log

View this message in rfc822 format

From: Anders Lindgren <andlind <at> gmail.com>
To: Eli Zaretskii <eliz <at> gnu.org>
Cc: random832 <at> fastmail.com, 22169 <at> debbugs.gnu.org
Subject: bug#22169: 25.0.50; File name compiletion doesn't work with non-ASCII characters on OS X
Date: Tue, 22 Dec 2015 23:29:16 +0100

[Message part 1 (text/plain, inline)]

Hi!

I just tried this and I can confirm that it works.

Thanks for your hard work!

I will push my patch for using the utf-8-hfs coding system (most likely)
tomorrow.

    -- Anders


On Tue, Dec 22, 2015 at 6:10 PM, Eli Zaretskii <eliz <at> gnu.org> wrote:

> > Date: Tue, 22 Dec 2015 06:42:47 +0100
> > From: Anders Lindgren <andlind <at> gmail.com>
> > Cc: random832 <at> fastmail.com, 22169 <at> debbugs.gnu.org
> >
> >     > I haven't had time to see what actually happens in the code,
> though.
> >     However,
> >     > the " if (STRING_MULTIBYTE (file))" looks suspicious as the
> decoded value
> >     needs
> >     > to be checked even for strings like "a". (However, I don't really
> know
> >     what
> >     > STRING_MULTIBYTE does.)
> >
> >     Does removing the STRING_MULTIBYTE test make it work?
> >
> > Yes, it does:
> >
> > (file-name-all-completions "a" ".")
> > ("aaosecond.txt")
>
> Then please try the final patch below (again against the current
> emacs-25 branch), I hope I didn't goof this time.
>
> Thanks.
>
> diff --git a/lisp/international/ucs-normalize.el
> b/lisp/international/ucs-normalize.el
> index 8839b00..6f2fb28 100644
> --- a/lisp/international/ucs-normalize.el
> +++ b/lisp/international/ucs-normalize.el
> @@ -627,6 +627,10 @@ 'utf-8-hfs
>    :pre-write-conversion 'ucs-normalize-hfs-nfd-pre-write-conversion
>    )
>
> +;; This is tested in dired.c:file_name_completion in order to reject
> +;; false positives due to comparison of encoded file names.
> +(coding-system-put 'utf-8-hfs 'decomposed-characters 't)
> +
>  (provide 'ucs-normalize)
>
>  ;; Local Variables:
> diff --git a/src/dired.c b/src/dired.c
> index 84bf247..89bd908 100644
> --- a/src/dired.c
> +++ b/src/dired.c
> @@ -467,6 +467,7 @@ file_name_completion (Lisp_Object file, Lisp_Object
> dirname, bool all_flag,
>       well as "." and "..".  Until shown otherwise, assume we can't exclude
>       anything.  */
>    bool includeall = 1;
> +  bool check_decoded = false;
>    ptrdiff_t count = SPECPDL_INDEX ();
>
>    elt = Qnil;
> @@ -485,6 +486,28 @@ file_name_completion (Lisp_Object file, Lisp_Object
> dirname, bool all_flag,
>       on the encoded file name.  */
>    encoded_file = ENCODE_FILE (file);
>    encoded_dir = ENCODE_FILE (Fdirectory_file_name (dirname));
> +
> +  Lisp_Object file_encoding = Vfile_name_coding_system;
> +  if (NILP (Vfile_name_coding_system))
> +    file_encoding = Vdefault_file_name_coding_system;
> +  /* If the file-name encoding decomposes characters, as we do for
> +     HFS+ filesystems, we need to make an additional comparison of
> +     decoded names in order to filter false positives, such as "a"
> +     falsely matching "a-ring".  */
> +  if (!NILP (file_encoding)
> +      && !NILP (Fplist_get (Fcoding_system_plist (file_encoding),
> +                           Qdecomposed_characters)))
> +    {
> +      check_decoded = true;
> +      if (STRING_MULTIBYTE (file))
> +       {
> +         /* Recompute FILE to make sure any decomposed characters in
> +            it are re-composed by the post-read-conversion.
> +            Otherwise, any decomposed characters will be rejected by
> +            the additional check below.  */
> +         file = DECODE_FILE (encoded_file);
> +       }
> +    }
>    int fd;
>    DIR *d = open_directory (encoded_dir, &fd);
>    record_unwind_protect_ptr (directory_files_internal_unwind, d);
> @@ -637,6 +660,21 @@ file_name_completion (Lisp_Object file, Lisp_Object
> dirname, bool all_flag,
>        if (!NILP (predicate) && NILP (call1 (predicate, name)))
>         continue;
>
> +      /* Reject entries where the encoded strings match, but the
> +         decoded don't.  For example, "a" should not match "a-ring" on
> +         file systems that store decomposed characters. */
> +      Lisp_Object zero = make_number (0);
> +      Lisp_Object compare;
> +      Lisp_Object cmp;
> +      if (check_decoded && SCHARS (file) <= SCHARS (name))
> +       {
> +         compare = make_number (SCHARS (file));
> +         cmp = Fcompare_strings (name, zero, compare, file, zero, compare,
> +                                 completion_ignore_case ? Qt : Qnil);
> +         if (!EQ (cmp, Qt))
> +           continue;
> +       }
> +
>        /* Suitably record this match.  */
>
>        matchcount += matchcount <= 1;
> @@ -650,15 +688,13 @@ file_name_completion (Lisp_Object file, Lisp_Object
> dirname, bool all_flag,
>         }
>        else
>         {
> -         Lisp_Object zero = make_number (0);
>           /* FIXME: This is a copy of the code in Ftry_completion.  */
> -         ptrdiff_t compare = min (bestmatchsize, SCHARS (name));
> -         Lisp_Object cmp
> -           = Fcompare_strings (bestmatch, zero,
> -                               make_number (compare),
> -                               name, zero,
> -                               make_number (compare),
> -                               completion_ignore_case ? Qt : Qnil);
> +         compare = min (bestmatchsize, SCHARS (name));
> +         cmp = Fcompare_strings (bestmatch, zero,
> +                                 make_number (compare),
> +                                 name, zero,
> +                                 make_number (compare),
> +                                 completion_ignore_case ? Qt : Qnil);
>           ptrdiff_t matchsize = EQ (cmp, Qt) ? compare : eabs (XINT (cmp))
> - 1;
>
>           if (completion_ignore_case)
> @@ -1007,6 +1043,7 @@ syms_of_dired (void)
>    DEFSYM (Qfile_attributes, "file-attributes");
>    DEFSYM (Qfile_attributes_lessp, "file-attributes-lessp");
>    DEFSYM (Qdefault_directory, "default-directory");
> +  DEFSYM (Qdecomposed_characters, "decomposed-characters");
>
>    defsubr (&Sdirectory_files);
>    defsubr (&Sdirectory_files_and_attributes);
>

[Message part 2 (text/html, inline)]

Previous Next

GNU bug tracking system
Copyright (C) 1999 Darren O. Benham, 1997,2003 nCipher Corporation Ltd, 1994-97 Ian Jackson.