-;;; thai-util.el --- utilities for Thai
+;;; thai-util.el --- utilities for Thai -*- coding: iso-2022-7bit; -*-
-;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
-;; Licensed to the Free Software Foundation.
+;; Copyright (C) 1995, 1997, 1998, 1999, 2000, 2001, 2005
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H14PRO021
;; Keywords: mule, multilingual, thai
;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
;; Boston, MA 02111-1307, USA.
-;;; Code:
+;;; Commentary:
-;;;###autoload
-(defun setup-thai-environment ()
- "Setup multilingual environment (MULE) for Thai."
- (interactive)
- (setup-8-bit-environment "Thai" 'thai-tis620 "thai-kesmanee"))
+;;; Code:
;; Setting information of Thai characters.
+(defconst thai-category-table (make-category-table))
+(define-category ?c "Thai consonant" thai-category-table)
+(define-category ?v "Thai upper/lower vowel" thai-category-table)
+(define-category ?t "Thai tone mark" thai-category-table)
+(define-category ?u "Thai tone mark and upper sign" thai-category-table)
+(define-category ?I "THAI CHARACTER SARA I" thai-category-table)
+(define-category ?U "THAI CHARACTER THANTHAKHAT" thai-category-table)
+
+;; The general composing rules are as follows:
+;;
+;; T
+;; V U V U
+;; CV -> C, CU -> C, CVT -> C, Cv -> C, CvU -> C
+;; v v
+;;
+;; where C: consonant, V: vowel upper, v: vowel lower,
+;; T: tone mark, U: tone mark and upper sign.
+;; Special rule: The sign `\e,Tl\e(B' can be put on the vowel `\e,TT\e(B'.
+
+
+(defvar thai-composition-pattern
+ "\\cc\\(\\cu\\|\\cI\\cU\\|\\cv\\ct?\\)\\|\\cv\\ct\\|\\cI\\cU"
+ "Regular expression matching a Thai composite sequence.")
+
+(defun thai-self-insert-command (&optional n)
+ "Insert the Thai character you type.
+The character will be composed with the surrounding Thai character
+if necessary."
+ (interactive "*p")
+ (let ((pos (point))
+ category-set ch)
+ (self-insert-command n)
+ (or thai-auto-composition-mode
+ (thai-auto-composition (1- (point)) (point) 0))))
+
(let ((l '((?\e,T!\e(B consonant "LETTER KO KAI") ; 0xA1
(?\e,T"\e(B consonant "LETTER KHO KHAI") ; 0xA2
(?\e,T#\e(B consonant "LETTER KHO KHUAT") ; 0xA3
(?\e,Td\e(B vowel-base "VOWEL SIGN SARA MAI MALAI") ; 0xE4
(?\e,Te\e(B vowel-base "LAK KHANG YAO") ; 0xE5
(?\e,Tf\e(B special "MAI YAMOK (repetion)") ; 0xE6
- (?\e,Tg\e(B vowel-upper "VOWEL SIGN MAI TAI KHU N/S-T") ; 0xE7
+ (?\e,Tg\e(B sign-upper "VOWEL SIGN MAI TAI KHU N/S-T") ; 0xE7
(?\e,Th\e(B tone "TONE MAI EK N/S-T") ; 0xE8
(?\e,Ti\e(B tone "TONE MAI THO N/S-T") ; 0xE9
(?\e,Tj\e(B tone "TONE MAI TRI N/S-T") ; 0xEA
(?\e,Tk\e(B tone "TONE MAI CHATTAWA N/S-T") ; 0xEB
- (?\e,Tl\e(B tone "THANTHAKHAT N/S-T (cancellation mark)") ; 0xEC
- (?\e,Tm\e(B tone "NIKKHAHIT N/S-T (final nasal)") ; 0xED
- (?\e,Tn\e(B vowel-upper "YAMAKKAN N/S-T") ; 0xEE
+ (?\e,Tl\e(B sign-upper "THANTHAKHAT N/S-T (cancellation mark)") ; 0xEC
+ (?\e,Tm\e(B sign-upper "NIKKHAHIT N/S-T (final nasal)") ; 0xED
+ (?\e,Tn\e(B sign-upper "YAMAKKAN N/S-T") ; 0xEE
(?\e,To\e(B special "FONRMAN") ; 0xEF
(?\e,Tp\e(B special "DIGIT ZERO") ; 0xF0
(?\e,Tq\e(B special "DIGIT ONE") ; 0xF1
(?\e,T|\e(B invalid nil) ; 0xFC
(?\e,T}\e(B invalid nil) ; 0xFD
(?\e,T~\e(B invalid nil) ; 0xFE
+
+ ;; Unicode equivalents
+ (?\e$,1Ba\e(B consonant "LETTER KO KAI")
+ (?\e$,1Bb\e(B consonant "LETTER KHO KHAI")
+ (?\e$,1Bc\e(B consonant "LETTER KHO KHUAT")
+ (?\e$,1Bd\e(B consonant "LETTER KHO KHWAI")
+ (?\e$,1Be\e(B consonant "LETTER KHO KHON")
+ (?\e$,1Bf\e(B consonant "LETTER KHO RAKHANG")
+ (?\e$,1Bg\e(B consonant "LETTER NGO NGU")
+ (?\e$,1Bh\e(B consonant "LETTER CHO CHAN")
+ (?\e$,1Bi\e(B consonant "LETTER CHO CHING")
+ (?\e$,1Bj\e(B consonant "LETTER CHO CHANG")
+ (?\e$,1Bk\e(B consonant "LETTER SO SO")
+ (?\e$,1Bl\e(B consonant "LETTER CHO CHOE")
+ (?\e$,1Bm\e(B consonant "LETTER YO YING")
+ (?\e$,1Bn\e(B consonant "LETTER DO CHADA")
+ (?\e$,1Bo\e(B consonant "LETTER TO PATAK")
+ (?\e$,1Bp\e(B consonant "LETTER THO THAN")
+ (?\e$,1Bq\e(B consonant "LETTER THO NANGMONTHO")
+ (?\e$,1Br\e(B consonant "LETTER THO PHUTHAO")
+ (?\e$,1Bs\e(B consonant "LETTER NO NEN")
+ (?\e$,1Bt\e(B consonant "LETTER DO DEK")
+ (?\e$,1Bu\e(B consonant "LETTER TO TAO")
+ (?\e$,1Bv\e(B consonant "LETTER THO THUNG")
+ (?\e$,1Bw\e(B consonant "LETTER THO THAHAN")
+ (?\e$,1Bx\e(B consonant "LETTER THO THONG")
+ (?\e$,1By\e(B consonant "LETTER NO NU")
+ (?\e$,1Bz\e(B consonant "LETTER BO BAIMAI")
+ (?\e$,1B{\e(B consonant "LETTER PO PLA")
+ (?\e$,1B|\e(B consonant "LETTER PHO PHUNG")
+ (?\e$,1B}\e(B consonant "LETTER FO FA")
+ (?\e$,1B~\e(B consonant "LETTER PHO PHAN")
+ (?\e$,1B\7f\e(B consonant "LETTER FO FAN")
+ (?\e$,1C \e(B consonant "LETTER PHO SAMPHAO")
+ (?\e$,1C!\e(B consonant "LETTER MO MA")
+ (?\e$,1C"\e(B consonant "LETTER YO YAK")
+ (?\e$,1C#\e(B consonant "LETTER RO RUA")
+ (?\e$,1C$\e(B vowel-base "LETTER RU (Pali vowel letter)")
+ (?\e$,1C%\e(B consonant "LETTER LO LING")
+ (?\e$,1C&\e(B vowel-base "LETTER LU (Pali vowel letter)")
+ (?\e$,1C'\e(B consonant "LETTER WO WAEN")
+ (?\e$,1C(\e(B consonant "LETTER SO SALA")
+ (?\e$,1C)\e(B consonant "LETTER SO RUSI")
+ (?\e$,1C*\e(B consonant "LETTER SO SUA")
+ (?\e$,1C+\e(B consonant "LETTER HO HIP")
+ (?\e$,1C,\e(B consonant "LETTER LO CHULA")
+ (?\e$,1C-\e(B consonant "LETTER O ANG")
+ (?\e$,1C.\e(B consonant "LETTER HO NOK HUK")
+ (?\e$,1C/\e(B special "PAI YAN NOI (abbreviation)")
+ (?\e$,1C0\e(B vowel-base "VOWEL SIGN SARA A")
+ (?\e$,1C1\e(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T")
+ (?\e$,1C2\e(B vowel-base "VOWEL SIGN SARA AA")
+ (?\e$,1C3\e(B vowel-base "VOWEL SIGN SARA AM")
+ (?\e$,1C4\e(B vowel-upper "VOWEL SIGN SARA I N/S-T")
+ (?\e$,1C5\e(B vowel-upper "VOWEL SIGN SARA II N/S-T")
+ (?\e$,1C6\e(B vowel-upper "VOWEL SIGN SARA UE N/S-T")
+ (?\e$,1C7\e(B vowel-upper "VOWEL SIGN SARA UEE N/S-T")
+ (?\e$,1C8\e(B vowel-lower "VOWEL SIGN SARA U N/S-B")
+ (?\e$,1C9\e(B vowel-lower "VOWEL SIGN SARA UU N/S-B")
+ (?\e$,1C:\e(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)")
+ (?\e$,1C?\e(B special "BAHT SIGN (currency symbol)")
+ (?\e$,1C@\e(B vowel-base "VOWEL SIGN SARA E")
+ (?\e$,1CA\e(B vowel-base "VOWEL SIGN SARA AE")
+ (?\e$,1CB\e(B vowel-base "VOWEL SIGN SARA O")
+ (?\e$,1CC\e(B vowel-base "VOWEL SIGN SARA MAI MUAN")
+ (?\e$,1CD\e(B vowel-base "VOWEL SIGN SARA MAI MALAI")
+ (?\e$,1CE\e(B vowel-base "LAK KHANG YAO")
+ (?\e$,1CF\e(B special "MAI YAMOK (repetion)")
+ (?\e$,1CG\e(B sign-upper "VOWEL SIGN MAI TAI KHU N/S-T")
+ (?\e$,1CH\e(B tone "TONE MAI EK N/S-T")
+ (?\e$,1CI\e(B tone "TONE MAI THO N/S-T")
+ (?\e$,1CJ\e(B tone "TONE MAI TRI N/S-T")
+ (?\e$,1CK\e(B tone "TONE MAI CHATTAWA N/S-T")
+ (?\e$,1CL\e(B sign-upper "THANTHAKHAT N/S-T (cancellation mark)")
+ (?\e$,1CM\e(B sign-upper "NIKKHAHIT N/S-T (final nasal)")
+ (?\e$,1CN\e(B sign-upper "YAMAKKAN N/S-T")
+ (?\e$,1CO\e(B special "FONRMAN")
+ (?\e$,1CP\e(B special "DIGIT ZERO")
+ (?\e$,1CQ\e(B special "DIGIT ONE")
+ (?\e$,1CR\e(B special "DIGIT TWO")
+ (?\e$,1CS\e(B special "DIGIT THREE")
+ (?\e$,1CT\e(B special "DIGIT FOUR")
+ (?\e$,1CU\e(B special "DIGIT FIVE")
+ (?\e$,1CV\e(B special "DIGIT SIX")
+ (?\e$,1CW\e(B special "DIGIT SEVEN")
+ (?\e$,1CX\e(B special "DIGIT EIGHT")
+ (?\e$,1CY\e(B special "DIGIT NINE")
+ (?\e$,1CZ\e(B special "ANGKHANKHU (ellipsis)")
+ (?\e$,1C[\e(B special "KHOMUT (beginning of religious texts)")
))
elm)
(while l
- (setq elm (car l))
- (put-char-code-property (car elm) 'phonetic-type (car (cdr elm)))
- (put-char-code-property (car elm) 'name (nth 2 elm))
- (setq l (cdr l))))
+ (setq elm (car l) l (cdr l))
+ (let ((char (car elm))
+ (ptype (nth 1 elm)))
+ (put-char-code-property char 'phonetic-type ptype)
+ (cond ((eq ptype 'consonant)
+ (modify-category-entry char ?c thai-category-table)
+ (global-set-key (vector char) 'thai-self-insert-command))
+ ((memq ptype '(vowel-upper vowel-lower))
+ (modify-category-entry char ?v thai-category-table)
+ (if (or (= char ?\e,TT\e(B) (= char ?\e$,1C4\e(B))
+ ;; Give category `I' to "SARA I".
+ (modify-category-entry char ?I thai-category-table))
+ (global-set-key (vector char) 'thai-self-insert-command))
+ ((eq ptype 'tone)
+ (modify-category-entry char ?t thai-category-table)
+ (modify-category-entry char ?u thai-category-table)
+ (global-set-key (vector char) 'thai-self-insert-command))
+ ((eq ptype 'sign-upper)
+ (modify-category-entry char ?u thai-category-table)
+ (if (or (= char ?\e,Tl\e(B) (= char ?\e$,1CL\e(B))
+ ;; Give category `U' to "THANTHAKHAT".
+ (modify-category-entry char ?U thai-category-table))
+ (global-set-key (vector char) 'thai-self-insert-command)))
+ (put-char-code-property char 'name (nth 2 elm)))))
+
+(defun thai-compose-syllable (beg end &optional category-set string)
+ (or category-set
+ (setq category-set
+ (char-category-set (if string (aref string beg) (char-after beg)))))
+ (if (aref category-set ?c)
+ ;; Starting with a consonant. We do relative composition.
+ (if string
+ (compose-string string beg end)
+ (compose-region beg end))
+ ;; Vowel tone sequence.
+ (if string
+ (compose-string string beg end (list (aref string beg) '(Bc . Bc)
+ (aref string (1+ beg))))
+ (compose-region beg end (list (char-after beg) '(Bc . Bc)
+ (char-after (1+ beg))))))
+ (- end beg))
;;;###autoload
(defun thai-compose-region (beg end)
When called from a program, expects two arguments,
positions (integers or markers) specifying the region."
(interactive "r")
- (save-restriction
- (narrow-to-region beg end)
- (decompose-region (point-min) (point-max))
- (goto-char (point-min))
- (while (re-search-forward "\\c0\\(\\c2\\|\\c3\\|\\c4\\)+" nil t)
- (if (aref (char-category-set (char-after (match-beginning 0))) ?t)
- (compose-region (match-beginning 0) (match-end 0))))))
+ (let ((pos (point)))
+ (save-restriction
+ (narrow-to-region beg end)
+ (goto-char (point-min))
+ (with-category-table thai-category-table
+ (while (re-search-forward thai-composition-pattern nil t)
+ (setq beg (match-beginning 0) end (match-end 0))
+ (if (and (> pos beg) (< pos end))
+ (setq pos end))
+ (thai-compose-syllable beg end
+ (char-category-set (char-after beg))))))
+ (goto-char pos)))
+
+;;;###autoload
+(defun thai-compose-string (string)
+ "Compose Thai characters in STRING and return the resulting string."
+ (with-category-table thai-category-table
+ (let ((idx 0))
+ (while (setq idx (string-match thai-composition-pattern string idx))
+ (thai-compose-syllable idx (match-end 0) nil string)
+ (setq idx (match-end 0)))))
+ string)
;;;###autoload
(defun thai-compose-buffer ()
;;;###autoload
(defun thai-post-read-conversion (len)
- (save-excursion
- (save-restriction
- (let ((buffer-modified-p (buffer-modified-p)))
- (narrow-to-region (point) (+ (point) len))
- (thai-compose-region (point-min) (point-max))
- (set-buffer-modified-p buffer-modified-p)
- (- (point-max) (point-min))))))
+ (thai-compose-region (point) (+ (point) len))
+ len)
;;;###autoload
-(defun thai-pre-write-conversion (from to)
- (let ((old-buf (current-buffer))
- (work-buf (get-buffer-create " *thai-work*")))
- (set-buffer work-buf)
- (erase-buffer)
- (if (stringp from)
- (insert from)
- (insert-buffer-substring old-buf from to))
- (decompose-region (point-min) (point-max))
- ;; Should return nil as annotations.
- nil))
+(defun thai-composition-function (from to pattern &optional string)
+ "Compose Thai text in the region FROM and TO.
+The text matches the regular expression PATTERN.
+Optional 4th argument STRING, if non-nil, is a string containing text
+to compose.
+
+The return value is number of composed characters."
+ (when (and (not thai-auto-composition-mode)
+ (< (1+ from) to))
+ (with-category-table thai-category-table
+ (if string
+ (if (eq (string-match thai-composition-pattern string from) from)
+ (thai-compose-syllable from (match-end 0) nil string))
+ (if (save-excursion
+ (goto-char from)
+ (and (looking-at thai-composition-pattern)
+ (setq to (match-end 0))))
+ (thai-compose-syllable from to))))))
+
+(defun thai-auto-composition (beg end len)
+ (with-category-table thai-category-table
+ (let (category-set)
+ (while (and (> beg (point-min))
+ (setq category-set (char-category-set (char-after (1- beg))))
+ (or (aref category-set ?v) (aref category-set ?u)))
+ (setq beg (1- beg)))
+ (if (and (> beg (point-min))
+ (aref (char-category-set (char-after (1- beg))) ?c))
+ (setq beg (1- beg)))
+ (while (and (< end (point-max))
+ (setq category-set (char-category-set (char-after end)))
+ (or (aref category-set ?v) (aref category-set ?u)))
+ (setq end (1+ end)))
+ (if (< beg end)
+ (thai-compose-region beg end)))))
+
+(put 'thai-auto-composition-mode 'permanent-local t)
+
+;;;###autoload
+(define-minor-mode thai-auto-composition-mode
+ "Minor mode for automatically correct Thai character composition."
+ nil nil nil
+ (cond ((null thai-auto-composition-mode)
+ (remove-hook 'after-change-functions 'thai-auto-composition))
+ (t
+ (add-hook 'after-change-functions 'thai-auto-composition))))
+
+;; Thai-word-mode requires functions in the feature `thai-word'.
+(require 'thai-word)
+
+(defvar thai-word-mode-map
+ (let ((map (make-sparse-keymap)))
+ (define-key map [remap forward-word] 'thai-forward-word)
+ (define-key map [remap backward-word] 'thai-backward-word)
+ (define-key map [remap kill-word] 'thai-kill-word)
+ (define-key map [remap backward-kill-word] 'thai-backward-kill-word)
+ (define-key map [remap transpose-words] 'thai-transpose-words)
+ map)
+ "Keymap for `thai-word-mode'.")
+
+(define-minor-mode thai-word-mode
+ "Minor mode to make word-oriented commands aware of Thai words.
+The commands affected are \\[forward-word], \\[backward-word], \\[kill-word], \\[backward-kill-word], \\[transpose-words], and \\[fill-paragraph]."
+ :global t
+ (cond (thai-word-mode
+ ;; This enables linebreak between Thai characters.
+ (modify-category-entry (make-char 'thai-tis620) ?|)
+ ;; This enables linebreak at a Thai word boundary.
+ (put-charset-property 'thai-tis620 'fill-find-break-point-function
+ 'thai-fill-find-break-point))
+ (t
+ (modify-category-entry (make-char 'thai-tis620) ?| nil t)
+ (put-charset-property 'thai-tis620 'fill-find-break-point-function
+ nil))))
+
+;; Function to call on entering the Thai language environment.
+(defun setup-thai-language-environment-internal ()
+ (thai-word-mode 1))
+
+;; Function to call on exiting the Thai language environment.
+(defun exit-thai-language-environment-internal ()
+ (thai-word-mode -1))
;;
(provide 'thai-util)
+;;; arch-tag: 59425d6a-8cf9-4e06-a6ab-8ab7dc7a7a97
;;; thai-util.el ends here