buffer-charset

[Francesco Potorti`]

Some time ago I advocated the use of buffer-charset.el (appended) to
ease users' problems when meeting strange characters in their buffers.
I was answered that this was not the right solution.  However, unless
something better has come up in the meantme, I found it very useful in
the last month or so.

I'll give an example.

I take the file in 
 <ftp://alpha.gnu.org/gnu/emacs/pretest/emacs-21.2.91.announce>

and save it into `ann'.  Then 
emacs -q
C-x m
C-c TAB ann RET
C-c C-c

I get a pop-up window proposing a bunch of "safe" coding systems.
Obviously I have no idea why ever I should change my coding system,
given that the file I included is apparently text only.  So I do:

M-x load-library RET buffer-charset RET
M-x highlight-charset-characters RET
TAB

and I get a completion window with these possible charset to higlight:

ascii                              latin-iso8859-1
mule-unicode-0100-24ff

Obviously the last one is strange.  So I select that to highlight, look
in the buffer and discover that there are two such characters, which I
can change or leave alone, if I know what I do (I don't).

In summary, I find this to be a really useful and comfortable user
interface for dealing with these problems, until a better one is
introduced.


===File ~/elisp/buffer-charset.el===========================
;;; buffer-charsets.el --- show usage of charsets in a buffer

;; Copyright (C) 2002 Joanna Pluta<address@hidden>.

;; Keywords: mule, hi-lock

;; This file is [not yet] part of GNU Emacs.

;; This program is free software; you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
;; the Free Software Foundation; either version 2, or (at your option)
;; any later version.

;; This program is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.

;; A copy of the GNU General Public License can be obtained from this
;; program's author (send electronic mail to <address@hidden>) or
;; from the Free Software Foundation, Inc., 675 Mass Ave, Cambridge,
;; MA 02139, USA.

;;; Commentary:

;;   - display-buffer-charsets
;;     Displays list of charsets used in current buffer.

;;   - show-buffer-charset-characters C-x w c

;;     Uses hi-lock-mode to highlight in current buffer characters
;;     from chosen charset.
;;     Creates and adds to local history (hi-lock-interactive-patterns)
;;     regexpx matching characters from a given charset.
;;     Characters from different charsets can be highlighted by
;;     different colors according to chosen face.

;;   - unhighlight-charset  C-x w u
;;     unhighlights characters from given charset
;;



;;; Code:

;;;

(require 'hi-lock)

(defun charset-chars-regexp (charset)
 (let ((dim (charset-dimension charset))
        (chars (charset-chars charset))
        (plane (charset-iso-graphic-plane charset))
        min
        max)
      (cond ((eq charset 'eight-bit-control)
           (setq min 128 max 159))
          ((eq charset 'eight-bit-graphic)
           (setq min 160 max 255))
          (t
           (if (= chars 94)
               (setq min 33 max 126)
             (setq min 32 max 127))
           (or (= plane 0)
               (setq min (+ min 128) max (+ max 128)))))
    (if (= dim 1)
        (format "[%c-%c]" (make-char charset min) (make-char charset max))
     (format "[%c-%c]"
             (make-char charset min min) (make-char charset max max)))))

(defun buffer-charsets ()
 (find-charset-region (point-min) (point-max)))

(defun display-buffer-charsets ()
  "Displays list of charsets used in current buffer"
  (interactive)
  (let ((charsets (buffer-charsets))
        (curr-buf-name (current-buffer)))
    (with-output-to-temp-buffer "*Buffer Charsets*"
      (save-excursion
        (set-buffer standard-output)
        (insert
         (format "Buffer %s uses the following charsets:\n" curr-buf-name))
        (while charsets
          (insert (symbol-name (car charsets)))
          (insert "\n")
          (setq charsets (cdr charsets)))))))

(defun charset-alist (charset-list)
 (let ((l (charset-list))
       charset-alist)
  (while l
    (setq charset-alist (cons (list (symbol-name (car l))) charset-alist))
    (setq l (cdr l)))
  charset-alist))


(defalias 'highlight-charset-characters 'show-buffer-charset-characters)
(defun show-buffer-charset-characters (charset face)
 "Uses hi-lock-mode to highlight by face characters of charset."
  (interactive
   (let ((completion-ignore-case t))
   (list
    (completing-read "Charset:"
                     (charset-alist (buffer-charsets))  nil t nil nil)
    (hi-lock-read-face-name))))
    (highlight-regexp (charset-chars-regexp (intern charset)) face))

(defun unhighlight-charset (charset)
 (interactive
  (let ((completion-ignore-case t))
   (list
    (completing-read "Charset:"
                     (charset-alist (buffer-charsets))  nil t nil nil))))
    (unhighlight-regexp (charset-chars-regexp  (intern charset))))

(define-key hi-lock-map "\C-xwc" 'show-buffer-charset-characters)
(define-key hi-lock-map "\C-xwu" 'unhighlight-charset)

;;; mule-utils.el ends here
============================================================