Re: iso-8859-1 and non-latin-1 chars

[Kenichi Handa <handa@m17n.org>]

In article <E18MDdz-0005Mz-00@fencepost.gnu.org>, Richard Stallman <rms@gnu.org> writes:
>>  If you specify a coding system with C-x RET c, and it doesn't
>>  handle all the text, should Emacs warn about that?

>     I don't think so.  That would amount to a significant overhead on all
>     i/o, since C-x RET c just amounts to binding
>     coding-system-for-{read,write} around the invocation of the command.

> It could also bind a flag saying "do warn".

How about the attached change?  Shall I install it?

Notes on the change:

(1) I made a new variable coding-system-require-warning, and
universal-coding-system-argument binds it to t.

(2) If car of the arg DEFAULT-CODING-SYSTEM is t, it
indicates that select-safe-coding-system should not include
buffer-file-coding-system and most preferred coding system
in a list of coding systems tried by default.
Fwrite_region calls select-safe-coding-system in this way if
coding-system-require-warning is non-nil.

(3) Now a user can specify any coding system in
select-safe-coding-system on his risk.  At least, this is
necessary when an unsafe coding sysetm is specified by C-x
RET c.

---
Ken'ichi HANDA
handa@m17n.org


Index: lisp/ChangeLog
===================================================================
RCS file: /cvs/emacs/lisp/ChangeLog,v
retrieving revision 1.4625
diff -u -c -b -r1.4625 ChangeLog
*** lisp/ChangeLog	13 Dec 2002 00:40:52 -0000	1.4625
--- lisp/ChangeLog	13 Dec 2002 02:51:25 -0000
***************
*** 1,3 ****
--- 1,12 ----
+ 2002-12-13  Kenichi Handa  <handa@m17n.org>
+ 
+ 	* international/mule-cmds.el (universal-coding-system-argument):
+ 	Bind coding-system-require-warning to t.
+ 	(select-safe-coding-system): Handle t in the arg
+ 	DEFAULT-CODING-SYSTEM specially.  Use read-coding-system to read a
+ 	coding-system to allow users to specify unsafe coding system on
+ 	their risk.
+ 
  2002-12-13  Nick Roberts  <nick@nick.uklinux.net>
  
  	* gdb-ui.el: Improve documentation strings.
Index: lisp/international/mule-cmds.el
===================================================================
RCS file: /cvs/emacs/lisp/international/mule-cmds.el,v
retrieving revision 1.211
diff -u -c -b -r1.211 mule-cmds.el
*** lisp/international/mule-cmds.el	12 Dec 2002 00:51:31 -0000	1.211
--- lisp/international/mule-cmds.el	13 Dec 2002 02:51:30 -0000
***************
*** 305,310 ****
--- 305,311 ----
  
      (let ((coding-system-for-read coding-system)
  	  (coding-system-for-write coding-system)
+ 	  (coding-system-require-warning t)
  	  (current-prefix-arg prefix))
        (message "")
        (call-interactively cmd))))
***************
*** 604,610 ****
  
  Optional 3rd arg DEFAULT-CODING-SYSTEM specifies a coding system or a
  list of coding systems to be prepended to the default coding system
! list.
  
  Optional 4th arg ACCEPT-DEFAULT-P, if non-nil, is a function to
  determine the acceptability of the silently selected coding system.
--- 605,614 ----
  
  Optional 3rd arg DEFAULT-CODING-SYSTEM specifies a coding system or a
  list of coding systems to be prepended to the default coding system
! list.  However, if DEFAULT-CODING-SYSTEM is a list and the first
! element is t, the cdr part is used as the defualt coding system list,
! i.e. `buffer-file-coding-system' and the most prepended coding system
! is not used.
  
  Optional 4th arg ACCEPT-DEFAULT-P, if non-nil, is a function to
  determine the acceptability of the silently selected coding system.
***************
*** 624,634 ****
--- 628,644 ----
  	   (not (listp default-coding-system)))
        (setq default-coding-system (list default-coding-system)))
  
+   (let ((no-other-defaults nil))
+     (if (eq (car default-coding-system) t)
+ 	(setq no-other-defaults t
+ 	      default-coding-system (cdr default-coding-system)))
+ 
      ;; Change elements of the list to (coding . base-coding).
      (setq default-coding-system
  	  (mapcar (function (lambda (x) (cons x (coding-system-base x))))
  		  default-coding-system))
  
+     (unless no-other-defaults
        ;; If buffer-file-coding-system is not nil nor undecided, append it
        ;; to the defaults.
        (if buffer-file-coding-system
***************
*** 653,659 ****
  	 (not (assq preferred default-coding-system))
  	 (not (rassq base default-coding-system))
  	 (setq default-coding-system
! 	       (append default-coding-system (list (cons preferred base))))))
  
    (if select-safe-coding-system-accept-default-p
        (setq accept-default-p select-safe-coding-system-accept-default-p))
--- 663,670 ----
  	     (not (assq preferred default-coding-system))
  	     (not (rassq base default-coding-system))
  	     (setq default-coding-system
! 		   (append default-coding-system
! 			   (list (cons preferred base))))))))
  
    (if select-safe-coding-system-accept-default-p
        (setq accept-default-p select-safe-coding-system-accept-default-p))
***************
*** 821,840 ****
  		(mapcar (function (lambda (x) (princ "  ") (princ x)))
  			codings)
  		(insert "\n")
! 		(fill-region-as-paragraph pos (point)))))
  
  	  ;; Read a coding system.
! 	  (if safe
! 	      (setq codings (append safe codings)))
! 	  (let* ((safe-names (mapcar (lambda (x) (list (symbol-name x)))
! 				     codings))
! 		 (name (completing-read
  			(format "Select coding system (default %s): "
! 				(car codings))
! 			safe-names nil t nil nil
! 			(car (car safe-names)))))
! 	    (setq last-coding-system-specified (intern name)
! 		  coding-system last-coding-system-specified)))
  	(kill-buffer "*Warning*")
  	(set-window-configuration window-configuration)))
  
--- 832,850 ----
  		(mapcar (function (lambda (x) (princ "  ") (princ x)))
  			codings)
  		(insert "\n")
! 		(fill-region-as-paragraph pos (point)))
! 	      (insert "Or specify any other coding system
! on your risk of loosing the problematic characters.\n")))
  
  	  ;; Read a coding system.
! 	  (setq default-coding-system (or (car safe) (car codings)))
! 	  (setq coding-system
! 		(read-coding-system 
  		 (format "Select coding system (default %s): "
! 			 default-coding-system)
! 		 default-coding-system))
! 	  (setq last-coding-system-specified coding-system))
! 
  	(kill-buffer "*Warning*")
  	(set-window-configuration window-configuration)))
  
Index: src/ChangeLog
===================================================================
RCS file: /cvs/emacs/src/ChangeLog,v
retrieving revision 1.2994
diff -u -c -b -r1.2994 ChangeLog
*** src/ChangeLog	13 Dec 2002 02:35:34 -0000	1.2994
--- src/ChangeLog	13 Dec 2002 02:51:31 -0000
***************
*** 1,5 ****
--- 1,17 ----
  2002-12-13  Kenichi Handa  <handa@m17n.org>
  
+ 	* coding.c (coding_system_require_warning): New variable.
+ 	(syms_of_coding): DEFVAR it.
+ 
+ 	* coding.h (coding_system_require_warning): Extern it.
+ 
+ 	* fileio.c (choose_write_coding_system): Even if
+ 	Vcoding_system_for_write is non-nil, if
+ 	coding_system_require_warning is nonzero, call
+ 	Vselect_safe_coding_system_function.
+ 
+ 2002-12-13  Kenichi Handa  <handa@m17n.org>
+ 
  	* coding.c (Funencodable_char_position): Set pend correctly.
  
  2002-12-12  Jason Rumney  <jasonr@gnu.org>
Index: src/coding.c
===================================================================
RCS file: /cvs/emacs/src/coding.c,v
retrieving revision 1.265
diff -u -c -b -r1.265 coding.c
*** src/coding.c	13 Dec 2002 02:35:51 -0000	1.265
--- src/coding.c	13 Dec 2002 02:51:33 -0000
***************
*** 367,372 ****
--- 367,374 ----
  
  Lisp_Object Vselect_safe_coding_system_function;
  
+ int coding_system_require_warning;
+ 
  /* Mnemonic string for each format of end-of-line.  */
  Lisp_Object eol_mnemonic_unix, eol_mnemonic_dos, eol_mnemonic_mac;
  /* Mnemonic string to indicate format of end-of-line is not yet
***************
*** 7530,7535 ****
--- 7532,7546 ----
  
  The default value is `select-safe-coding-system' (which see).  */);
    Vselect_safe_coding_system_function = Qnil;
+ 
+   DEFVAR_BOOL ("coding-system-require-warning",
+ 	       &coding_system_require_warning,
+ 	       doc: /* Internal use only.
+ If non-nil, on writing a file, select-safe-coding-system-function is
+ called even if coding-system-for-write is non-nil.  The command
+ universal-coding-system-argument binds this variable to t temporarily.  */);
+   coding_system_require_warning = 0;
+ 
  
    DEFVAR_LISP ("char-coding-system-table", &Vchar_coding_system_table,
  	       doc: /* Char-table containing safe coding systems of each characters.
Index: src/coding.h
===================================================================
RCS file: /cvs/emacs/src/coding.h,v
retrieving revision 1.64
diff -u -c -b -r1.64 coding.h
*** src/coding.h	19 Jul 2002 14:27:01 -0000	1.64
--- src/coding.h	13 Dec 2002 02:51:33 -0000
***************
*** 705,710 ****
--- 705,714 ----
     system.  */
  extern Lisp_Object Vselect_safe_coding_system_function;
  
+ /* If nonzero, on writing a file, Vselect_safe_coding_system_function
+    is called even if Vcoding_system_for_write is non-nil.  */
+ extern int coding_system_require_warning;
+ 
  /* Coding system for file names, or nil if none.  */
  extern Lisp_Object Vfile_name_coding_system;
  
Index: src/fileio.c
===================================================================
RCS file: /cvs/emacs/src/fileio.c,v
retrieving revision 1.467
diff -u -c -b -r1.467 fileio.c
*** src/fileio.c	7 Dec 2002 21:39:50 -0000	1.467
--- src/fileio.c	13 Dec 2002 02:51:34 -0000
***************
*** 4624,4630 ****
--- 4624,4638 ----
    if (auto_saving)
      val = Qnil;
    else if (!NILP (Vcoding_system_for_write))
+     {
        val = Vcoding_system_for_write;
+       if (coding_system_require_warning
+ 	  && !NILP (Ffboundp (Vselect_safe_coding_system_function)))
+ 	/* Confirm that VAL can surely encode the current region.  */
+ 	val = call5 (Vselect_safe_coding_system_function,
+ 		     start, end, Fcons (Qt, Fcons (val, Qnil)),
+ 		     Qnil, filename);
+     }
    else
      {
        /* If the variable `buffer-file-coding-system' is set locally,