my-lisp/my-replace-zen-to-ascii.el

;;; my-replace-zen-to-ascii.el --- Convert fullwidth/superscript/subscript chars to ASCII -*- lexical-binding: t; -*-

;; This library converts selected fullwidth ASCII-like characters,
;; Unicode superscript/subscript digits, and common typographic symbols
;; into plain ASCII characters.
;;
;; Main commands:
;;
;;   M-x replace-zen-to-ascii-region
;;   M-x replace-zen-to-ascii-buffer
;;   M-x replace-zen-to-ascii-region-copy
;;   M-x replace-zen-to-ascii-buffer-copy
;;
;; The original command name `replace-zen-to-ascii-region' is kept
;; for compatibility with existing init.el settings.

(require 'subr-x)

(defgroup my-replace-zen-to-ascii nil
  "Convert selected fullwidth and Unicode compatibility characters to ASCII."
  :group 'editing
  :prefix "my-replace-zen-to-ascii-")

(defcustom my-replace-zen-to-ascii-convert-scientific-symbols nil
  "If non-nil, also convert selected scientific symbols to ASCII.
For example, μ/µ -> u, Å/Å -> A, × -> x, ° -> deg.
This is disabled by default because these symbols may be meaningful
in manuscripts."
  :type 'boolean
  :group 'my-replace-zen-to-ascii)

(defconst my-replace-zen-to-ascii--basic-table
  '(("　" . " ")

    ;; Fullwidth digits
    ("０" . "0") ("１" . "1") ("２" . "2") ("３" . "3") ("４" . "4")
    ("５" . "5") ("６" . "6") ("７" . "7") ("８" . "8") ("９" . "9")

    ;; Fullwidth uppercase letters
    ("Ａ" . "A") ("Ｂ" . "B") ("Ｃ" . "C") ("Ｄ" . "D") ("Ｅ" . "E")
    ("Ｆ" . "F") ("Ｇ" . "G") ("Ｈ" . "H") ("Ｉ" . "I") ("Ｊ" . "J")
    ("Ｋ" . "K") ("Ｌ" . "L") ("Ｍ" . "M") ("Ｎ" . "N") ("Ｏ" . "O")
    ("Ｐ" . "P") ("Ｑ" . "Q") ("Ｒ" . "R") ("Ｓ" . "S") ("Ｔ" . "T")
    ("Ｕ" . "U") ("Ｖ" . "V") ("Ｗ" . "W") ("Ｘ" . "X") ("Ｙ" . "Y")
    ("Ｚ" . "Z")

    ;; Fullwidth lowercase letters
    ("ａ" . "a") ("ｂ" . "b") ("ｃ" . "c") ("ｄ" . "d") ("ｅ" . "e")
    ("ｆ" . "f") ("ｇ" . "g") ("ｈ" . "h") ("ｉ" . "i") ("ｊ" . "j")
    ("ｋ" . "k") ("ｌ" . "l") ("ｍ" . "m") ("ｎ" . "n") ("ｏ" . "o")
    ("ｐ" . "p") ("ｑ" . "q") ("ｒ" . "r") ("ｓ" . "s") ("ｔ" . "t")
    ("ｕ" . "u") ("ｖ" . "v") ("ｗ" . "w") ("ｘ" . "x") ("ｙ" . "y")
    ("ｚ" . "z")

    ;; Fullwidth ASCII punctuation
    ("！" . "!") ("＂" . "\"") ("＃" . "#") ("＄" . "$")
    ("％" . "%") ("＆" . "&") ("＇" . "'") ("（" . "(")
    ("）" . ")") ("＊" . "*") ("＋" . "+") ("，" . ",")
    ("－" . "-") ("．" . ".") ("／" . "/") ("：" . ":")
    ("；" . ";") ("＜" . "<") ("＝" . "=") ("＞" . ">")
    ("？" . "?") ("＠" . "@") ("［" . "[") ("＼" . "\\")
    ("］" . "]") ("＾" . "^") ("＿" . "_") ("｀" . "`")
    ("｛" . "{") ("｜" . "|") ("｝" . "}") ("～" . "~")

    ;; Curly quotes and common dash/minus variants
    ("“" . "\"") ("”" . "\"")
    ("„" . "\"") ("‟" . "\"")
    ("‘" . "'") ("’" . "'")
    ("‚" . "'") ("‛" . "'")
    ("−" . "-") ("–" . "-") ("—" . "-") ("―" . "-")

    ;; Superscript digits
    ("⁰" . "0") ("¹" . "1") ("²" . "2") ("³" . "3") ("⁴" . "4")
    ("⁵" . "5") ("⁶" . "6") ("⁷" . "7") ("⁸" . "8") ("⁹" . "9")

    ;; Subscript digits
    ("₀" . "0") ("₁" . "1") ("₂" . "2") ("₃" . "3") ("₄" . "4")
    ("₅" . "5") ("₆" . "6") ("₇" . "7") ("₈" . "8") ("₉" . "9")

    ;; Superscript signs and parentheses
    ("⁺" . "+") ("⁻" . "-") ("⁼" . "=")
    ("⁽" . "(") ("⁾" . ")")

    ;; Subscript signs and parentheses
    ("₊" . "+") ("₋" . "-") ("₌" . "=")
    ("₍" . "(") ("₎" . ")"))
  "Basic conversion table.")

(defconst my-replace-zen-to-ascii--scientific-table
  '(("μ" . "u")
    ("µ" . "u")
    ("Å" . "A")
    ("Å" . "A")
    ("×" . "x")
    ("°" . " deg"))
  "Optional scientific-symbol conversion table.")

(defun my-replace-zen-to-ascii--table ()
  "Return active conversion table."
  (if my-replace-zen-to-ascii-convert-scientific-symbols
      (append my-replace-zen-to-ascii--basic-table
              my-replace-zen-to-ascii--scientific-table)
    my-replace-zen-to-ascii--basic-table))

(defun my-replace-zen-to-ascii--regexp ()
  "Return regexp for active conversion table."
  (regexp-opt (mapcar #'car (my-replace-zen-to-ascii--table))))

(defun my-replace-zen-to-ascii--replace-region (start end)
  "Convert selected characters in region START END."
  (let* ((table (my-replace-zen-to-ascii--table))
         (regexp (regexp-opt (mapcar #'car table))))
    (save-excursion
      (goto-char start)
      (while (re-search-forward regexp end t)
        (let* ((from (match-string 0))
               (to (cdr (assoc from table))))
          (when to
            (replace-match to t t)))))))

;;;###autoload
(defun replace-zen-to-ascii-region (start end)
  "Convert fullwidth ASCII-like and super/subscript characters in region to ASCII."
  (interactive "r")
  (my-replace-zen-to-ascii--replace-region start end)
  (message "Converted selected characters to ASCII."))

;;;###autoload
(defun replace-zen-to-ascii-buffer ()
  "Convert fullwidth ASCII-like and super/subscript characters in the whole buffer."
  (interactive)
  (replace-zen-to-ascii-region (point-min) (point-max)))

;;;###autoload
(defun replace-zen-to-ascii-region-copy (start end)
  "Copy converted region to kill-ring without modifying current buffer."
  (interactive "r")
  (let ((text (buffer-substring-no-properties start end))
        (buf (generate-new-buffer " *replace-zen-to-ascii-copy*")))
    (unwind-protect
        (with-current-buffer buf
          (insert text)
          (replace-zen-to-ascii-region (point-min) (point-max))
          (kill-new (buffer-string)))
      (kill-buffer buf))
    (message "Converted text copied to kill-ring.")))

;;;###autoload
(defun replace-zen-to-ascii-buffer-copy ()
  "Copy converted whole buffer to kill-ring without modifying current buffer."
  (interactive)
  (replace-zen-to-ascii-region-copy (point-min) (point-max)))

;;;###autoload
(defun replace-zen-to-ascii-toggle-scientific-symbols ()
  "Toggle optional scientific-symbol conversion."
  (interactive)
  (setq my-replace-zen-to-ascii-convert-scientific-symbols
        (not my-replace-zen-to-ascii-convert-scientific-symbols))
  (message "Scientific-symbol conversion: %s"
           (if my-replace-zen-to-ascii-convert-scientific-symbols
               "ON"
             "OFF")))

(provide 'my-replace-zen-to-ascii)
;;; my-replace-zen-to-ascii.el ends here