;; -*- lexical-binding: nil; -*-
;; This file:
;;   http://angg.twu.net/elisp/derawify.el.html
;;   http://angg.twu.net/elisp/derawify.el
;;           (find-angg "elisp/derawify.el")
;; Author: Eduardo Ochs <eduardoochs@gmail.com>
;; Date: 2022feb12
;; Public domain.
;;
;; I still have many files that use the "raw-text-unix" encoding, that
;; is explained here:
;;
;;   (find-elnode "Coding System Basics")
;;
;; When I copy text with chars in the range 128-255 (0x80-0xff) from
;; these files to files in the "utf-8-unix" encoding these chars are
;; converted to the range 0x3fff80-0x3fffff, and when I try to save
;; the utf-8 file with those characters Emacs creates a temporary
;; buffer called "*Warning*" with a message like this one:
;;
;;   These default coding systems were tried to encode the following
;;   problematic characters in the buffer `ooo':
;;     Coding System           Pos  Codepoint  Char
;;     utf-8                    11  #x3FFFE9   é
;;                              34  #x3FFFED   í
;;                             119  #x3FFFE3   ã
;;                             193  #x3FFFED   í
;;                             264  #x3FFFED   í
;;                             ...             
;;   
;;   However, each of them encountered characters it couldn't encode:
;;     utf-8 cannot encode these: é í ã í í í
;;   
;;   Click on a character (or switch to this window by `M-o'
;;   and select the characters by RET) to jump to the place it appears,
;;   where `C-u C-x =' will give information about it.
;;   
;;   Select one of the safe coding systems listed below,
;;   or cancel the writing with C-g and edit the buffer
;;      to remove or modify the problematic characters,
;;   or specify any other coding system (and risk losing
;;      the problematic characters).
;;   
;;     raw-text no-conversion
;;
;; I never found the "right" way to make Emacs convert the chars in
;; the range 0x3fff80-0x3fffff (the "bad" range) to the range
;; 0x80-0xff (the "good" range), so I wrote this hack. If we run `M-x
;; derawify' in a buffer it will find all the "bad" characters in that
;; buffer - or, more precisely: the "bad" characters in the accessible
;; portion of the current buffer - and it will change each of them to
;; the corresponding "good" character and mark each one of the
;; converted characters with the face `derawify-face'.

;; Todo: use rx.
;;
;;   (find-epp (rx (in 2000 4000)))
;;   (rx (in 32 64))
;;   (rx (in #x3fff80 #x3fffff))
;;   (insert "\x3fff80-\x3fffff")

(make-face           'derawify-face)
(set-face-foreground 'derawify-face nil)
(set-face-background 'derawify-face "OliveDrab")

(defun derawify-here ()
  (interactive)
  (let* ((pos (point))
	 (str1 (delete-and-extract-region pos (1+ pos)))
	 (str2 (char-to-string (logand 255 (string-to-char str1))))
	 (str3 (propertize str2 'face 'derawify-face)))
    (insert str3)))

(defun derawify ()
  "Convert all characters in the range 0x3fff80-0x3fffff to the range 0x80-0xff.
All the \"bad\" characters in accessible portion of the current
buffer are converted to corresponding \"good\" characters and
marked with the face `derawify-face'."
  (interactive)
  (save-excursion
    (goto-char (point-min))
    (while (search-forward-regexp "[\x3fff80-\x3fffff]" nil t)
      (goto-char (match-beginning 0))
      (derawify-here))))


;; ;; Old version:
;; ;;
;; ;; (find-efunctiondescr 'search-forward-regexp)
;; ;; (replace-match NEWTEXT &optional FIXEDCASE LITERAL STRING SUBEXP)
;; 
;; (defun derawify-here-p (pos)
;;   (<= #x3fff80 (char-after pos) #x3fffff))
;; 
;; (defun derawify-here-find-first (b e)
;;   (cl-loop for pos from b to e
;;            do (if (derawify-here-p pos)
;;                   (cl-return pos))))
;; 
;; (defun derawify-here-find-first (b e)
;;   (goto-char b)
;;   (search-forward-regexp "[\x3fff80-\x3fffff]" e t))
;; 
;; (defun derawify-here-goto-first (b e)
;;   (interactive "r")
;;   (goto-char (derawify-here-find-first b e)))
;; 
;; (defun derawify-next (e)
;;   (let ((pos (derawify-here-find-first b e)))
;;     (if pos
;;         (progn (goto-char pos)
;;                (derawify-here)
;;                t))))
;; 
;; (defun derawify-region (b e)
;;   "This is like `derawify' but operates only in the region from B to E."
;;   (interactive "r")
;;   (save-excursion
;;     (goto-char b)
;;     (while (derawify-next e))))
;; 
;; (defun derawify ()
;;   "Convert all characters in the range 0x3fff80-0x3fffff to the range 0x80-0xff.
;; All the \"bad\" characters in accessible portion of the current
;; buffer are converted to corresponding \"good\" characters and
;; marked with the face `derawify-face'."
;;   (interactive)
;;   (derawify-region (point-min) (1- (point-max))))




;; (defun e () (interactive) (find-angg "elisp/derawify.el"))

;; Local Variables:
;; coding:  utf-8-unix
;; End: