1 ;;; thai-util.el --- utilities for Thai -*- coding: iso-2022-7bit; -*-
3 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
5 ;; National Institute of Advanced Industrial Science and Technology (AIST)
6 ;; Registration Number H13PRO009
7 ;; Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007
8 ;; Free Software Foundation, Inc.
10 ;; Keywords: mule, multilingual, Thai, i18n
12 ;; This file is part of GNU Emacs.
14 ;; GNU Emacs is free software; you can redistribute it and/or modify
15 ;; it under the terms of the GNU General Public License as published by
16 ;; the Free Software Foundation; either version 2, or (at your option)
19 ;; GNU Emacs is distributed in the hope that it will be useful,
20 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
21 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
22 ;; GNU General Public License for more details.
24 ;; You should have received a copy of the GNU General Public License
25 ;; along with GNU Emacs; see the file COPYING. If not, write to the
26 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
27 ;; Boston, MA 02110-1301, USA.
33 (defvar thai-auto-composition-mode)
35 ;; Setting information of Thai characters.
37 (defconst thai-category-table (make-category-table))
38 (define-category ?c "Thai consonant" thai-category-table)
39 (define-category ?v "Thai upper/lower vowel" thai-category-table)
40 (define-category ?t "Thai tone mark" thai-category-table)
41 (define-category ?u "Thai tone mark and upper sign" thai-category-table)
42 (define-category ?I "THAI CHARACTER SARA I" thai-category-table)
43 (define-category ?U "THAI CHARACTER THANTHAKHAT" thai-category-table)
45 ;; The general composing rules are as follows:
49 ;; CV -> C, CU -> C, CVT -> C, Cv -> C, CvU -> C
52 ;; where C: consonant, V: vowel upper, v: vowel lower,
53 ;; T: tone mark, U: tone mark and upper sign.
54 ;; Special rule: The sign `
\e,Tl
\e(B' can be put on the vowel `
\e,TT
\e(B'.
57 (defvar thai-composition-pattern
58 "\\cc\\(\\cu\\|\\cI\\cU\\|\\cv\\ct?\\)\\|\\cv\\ct\\|\\cI\\cU"
59 "Regular expression matching a Thai composite sequence.")
61 (let ((l '((?
\e,T!
\e(B consonant "LETTER KO KAI") ; 0xA1
62 (?
\e,T"
\e(B consonant "LETTER KHO KHAI") ; 0xA2
63 (?
\e,T#
\e(B consonant "LETTER KHO KHUAT") ; 0xA3
64 (?
\e,T$
\e(B consonant "LETTER KHO KHWAI") ; 0xA4
65 (?
\e,T%
\e(B consonant "LETTER KHO KHON") ; 0xA5
66 (?
\e,T&
\e(B consonant "LETTER KHO RAKHANG") ; 0xA6
67 (?
\e,T'
\e(B consonant "LETTER NGO NGU") ; 0xA7
68 (?
\e,T(
\e(B consonant "LETTER CHO CHAN") ; 0xA8
69 (?
\e,T)
\e(B consonant "LETTER CHO CHING") ; 0xA9
70 (?
\e,T*
\e(B consonant "LETTER CHO CHANG") ; 0xAA
71 (?
\e,T+
\e(B consonant "LETTER SO SO") ; 0xAB
72 (?
\e,T,
\e(B consonant "LETTER CHO CHOE") ; 0xAC
73 (?
\e,T-
\e(B consonant "LETTER YO YING") ; 0xAD
74 (?
\e,T.
\e(B consonant "LETTER DO CHADA") ; 0xAE
75 (?
\e,T/
\e(B consonant "LETTER TO PATAK") ; 0xAF
76 (?
\e,T0
\e(B consonant "LETTER THO THAN") ; 0xB0
77 (?
\e,T1
\e(B consonant "LETTER THO NANGMONTHO") ; 0xB1
78 (?
\e,T2
\e(B consonant "LETTER THO PHUTHAO") ; 0xB2
79 (?
\e,T3
\e(B consonant "LETTER NO NEN") ; 0xB3
80 (?
\e,T4
\e(B consonant "LETTER DO DEK") ; 0xB4
81 (?
\e,T5
\e(B consonant "LETTER TO TAO") ; 0xB5
82 (?
\e,T6
\e(B consonant "LETTER THO THUNG") ; 0xB6
83 (?
\e,T7
\e(B consonant "LETTER THO THAHAN") ; 0xB7
84 (?
\e,T8
\e(B consonant "LETTER THO THONG") ; 0xB8
85 (?
\e,T9
\e(B consonant "LETTER NO NU") ; 0xB9
86 (?
\e,T:
\e(B consonant "LETTER BO BAIMAI") ; 0xBA
87 (?
\e,T;
\e(B consonant "LETTER PO PLA") ; 0xBB
88 (?
\e,T<
\e(B consonant "LETTER PHO PHUNG") ; 0xBC
89 (?
\e,T=
\e(B consonant "LETTER FO FA") ; 0xBD
90 (?
\e,T>
\e(B consonant "LETTER PHO PHAN") ; 0xBE
91 (?
\e,T?
\e(B consonant "LETTER FO FAN") ; 0xBF
92 (?
\e,T@
\e(B consonant "LETTER PHO SAMPHAO") ; 0xC0
93 (?
\e,TA
\e(B consonant "LETTER MO MA") ; 0xC1
94 (?
\e,TB
\e(B consonant "LETTER YO YAK") ; 0xC2
95 (?
\e,TC
\e(B consonant "LETTER RO RUA") ; 0xC3
96 (?
\e,TD
\e(B vowel-base "LETTER RU (Pali vowel letter)") ; 0xC4
97 (?
\e,TE
\e(B consonant "LETTER LO LING") ; 0xC5
98 (?
\e,TF
\e(B vowel-base "LETTER LU (Pali vowel letter)") ; 0xC6
99 (?
\e,TG
\e(B consonant "LETTER WO WAEN") ; 0xC7
100 (?
\e,TH
\e(B consonant "LETTER SO SALA") ; 0xC8
101 (?
\e,TI
\e(B consonant "LETTER SO RUSI") ; 0xC9
102 (?
\e,TJ
\e(B consonant "LETTER SO SUA") ; 0xCA
103 (?
\e,TK
\e(B consonant "LETTER HO HIP") ; 0xCB
104 (?
\e,TL
\e(B consonant "LETTER LO CHULA") ; 0xCC
105 (?
\e,TM
\e(B consonant "LETTER O ANG") ; 0xCD
106 (?
\e,TN
\e(B consonant "LETTER HO NOK HUK") ; 0xCE
107 (?
\e,TO
\e(B special "PAI YAN NOI (abbreviation)") ; 0xCF
108 (?
\e,TP
\e(B vowel-base "VOWEL SIGN SARA A") ; 0xD0
109 (?
\e,TQ
\e(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T") ; 0xD1
110 (?
\e,TR
\e(B vowel-base "VOWEL SIGN SARA AA") ; 0xD2
111 (?
\e,TS
\e(B vowel-base "VOWEL SIGN SARA AM") ; 0xD3
112 (?
\e,TT
\e(B vowel-upper "VOWEL SIGN SARA I N/S-T") ; 0xD4
113 (?
\e,TU
\e(B vowel-upper "VOWEL SIGN SARA II N/S-T") ; 0xD5
114 (?
\e,TV
\e(B vowel-upper "VOWEL SIGN SARA UE N/S-T") ; 0xD6
115 (?
\e,TW
\e(B vowel-upper "VOWEL SIGN SARA UEE N/S-T") ; 0xD7
116 (?
\e,TX
\e(B vowel-lower "VOWEL SIGN SARA U N/S-B") ; 0xD8
117 (?
\e,TY
\e(B vowel-lower "VOWEL SIGN SARA UU N/S-B") ; 0xD9
118 (?
\e,TZ
\e(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)") ; 0xDA
119 (?
\e,T[
\e(B invalid nil) ; 0xDA
120 (?
\e,T\
\e(B invalid nil) ; 0xDC
121 (?
\e,T]
\e(B invalid nil) ; 0xDC
122 (?
\e,T^
\e(B invalid nil) ; 0xDC
123 (?
\e,T_
\e(B special "BAHT SIGN (currency symbol)") ; 0xDF
124 (?
\e,T`
\e(B vowel-base "VOWEL SIGN SARA E") ; 0xE0
125 (?
\e,Ta
\e(B vowel-base "VOWEL SIGN SARA AE") ; 0xE1
126 (?
\e,Tb
\e(B vowel-base "VOWEL SIGN SARA O") ; 0xE2
127 (?
\e,Tc
\e(B vowel-base "VOWEL SIGN SARA MAI MUAN") ; 0xE3
128 (?
\e,Td
\e(B vowel-base "VOWEL SIGN SARA MAI MALAI") ; 0xE4
129 (?
\e,Te
\e(B vowel-base "LAK KHANG YAO") ; 0xE5
130 (?
\e,Tf
\e(B special "MAI YAMOK (repetion)") ; 0xE6
131 (?
\e,Tg
\e(B sign-upper "VOWEL SIGN MAI TAI KHU N/S-T") ; 0xE7
132 (?
\e,Th
\e(B tone "TONE MAI EK N/S-T") ; 0xE8
133 (?
\e,Ti
\e(B tone "TONE MAI THO N/S-T") ; 0xE9
134 (?
\e,Tj
\e(B tone "TONE MAI TRI N/S-T") ; 0xEA
135 (?
\e,Tk
\e(B tone "TONE MAI CHATTAWA N/S-T") ; 0xEB
136 (?
\e,Tl
\e(B sign-upper "THANTHAKHAT N/S-T (cancellation mark)") ; 0xEC
137 (?
\e,Tm
\e(B sign-upper "NIKKHAHIT N/S-T (final nasal)") ; 0xED
138 (?
\e,Tn
\e(B sign-upper "YAMAKKAN N/S-T") ; 0xEE
139 (?
\e,To
\e(B special "FONRMAN") ; 0xEF
140 (?
\e,Tp
\e(B special "DIGIT ZERO") ; 0xF0
141 (?
\e,Tq
\e(B special "DIGIT ONE") ; 0xF1
142 (?
\e,Tr
\e(B special "DIGIT TWO") ; 0xF2
143 (?
\e,Ts
\e(B special "DIGIT THREE") ; 0xF3
144 (?
\e,Tt
\e(B special "DIGIT FOUR") ; 0xF4
145 (?
\e,Tu
\e(B special "DIGIT FIVE") ; 0xF5
146 (?
\e,Tv
\e(B special "DIGIT SIX") ; 0xF6
147 (?
\e,Tw
\e(B special "DIGIT SEVEN") ; 0xF7
148 (?
\e,Tx
\e(B special "DIGIT EIGHT") ; 0xF8
149 (?
\e,Ty
\e(B special "DIGIT NINE") ; 0xF9
150 (?
\e,Tz
\e(B special "ANGKHANKHU (ellipsis)") ; 0xFA
151 (?
\e,T{
\e(B special "KHOMUT (beginning of religious texts)") ; 0xFB
152 (?
\e,T|
\e(B invalid nil) ; 0xFC
153 (?
\e,T}
\e(B invalid nil) ; 0xFD
154 (?
\e,T~
\e(B invalid nil) ; 0xFE
158 (setq elm (car l) l (cdr l))
159 (let ((char (car elm))
161 (put-char-code-property char 'phonetic-type ptype)
162 (cond ((eq ptype 'consonant)
163 (modify-category-entry char ?c thai-category-table))
164 ((memq ptype '(vowel-upper vowel-lower))
165 (modify-category-entry char ?v thai-category-table)
166 (if (= char ?
\e,TT
\e(B)
167 ;; Give category `I' to "SARA I".
168 (modify-category-entry char ?I thai-category-table)))
170 (modify-category-entry char ?t thai-category-table)
171 (modify-category-entry char ?u thai-category-table))
172 ((eq ptype 'sign-upper)
173 (modify-category-entry char ?u thai-category-table)
174 (if (= char ?
\e,Tl
\e(B)
175 ;; Give category `U' to "THANTHAKHAT".
176 (modify-category-entry char ?U thai-category-table))))
177 (put-char-code-property char 'name (nth 2 elm)))))
179 (defun thai-compose-syllable (beg end &optional category-set string)
182 (char-category-set (if string (aref string beg) (char-after beg)))))
183 (if (aref category-set ?c)
184 ;; Starting with a consonant. We do relative composition.
186 (compose-string string beg end)
187 (compose-region beg end))
188 ;; Vowel tone sequence.
190 (compose-string string beg end (list (aref string beg) '(Bc . Bc)
191 (aref string (1+ beg))))
192 (compose-region beg end (list (char-after beg) '(Bc . Bc)
193 (char-after (1+ beg))))))
197 (defun thai-compose-region (beg end)
198 "Compose Thai characters in the region.
199 When called from a program, expects two arguments,
200 positions (integers or markers) specifying the region."
204 (narrow-to-region beg end)
205 (goto-char (point-min))
206 (with-category-table thai-category-table
207 (while (re-search-forward thai-composition-pattern nil t)
208 (setq beg (match-beginning 0) end (match-end 0))
209 (if (and (> pos beg) (< pos end))
211 (thai-compose-syllable beg end
212 (char-category-set (char-after beg))))))
216 (defun thai-compose-string (string)
217 "Compose Thai characters in STRING and return the resulting string."
218 (with-category-table thai-category-table
220 (while (setq idx (string-match thai-composition-pattern string idx))
221 (thai-compose-syllable idx (match-end 0) nil string)
222 (setq idx (match-end 0)))))
226 (defun thai-compose-buffer ()
227 "Compose Thai characters in the current buffer."
229 (thai-compose-region (point-min) (point-max)))
232 (defun thai-composition-function (pos &optional string)
234 (with-category-table thai-category-table
237 (eq (string-match thai-composition-pattern string pos) pos))
239 (thai-compose-syllable pos (match-end 0) nil string)))
240 (if (>= pos (point-min))
243 (if (looking-at thai-composition-pattern)
245 (thai-compose-syllable pos (match-end 0)))))))))
247 ;; Thai-word-mode requires functions in the feature `thai-word'.
250 (defvar thai-word-mode-map
251 (let ((map (make-sparse-keymap)))
252 (define-key map [remap forward-word] 'thai-forward-word)
253 (define-key map [remap backward-word] 'thai-backward-word)
254 (define-key map [remap kill-word] 'thai-kill-word)
255 (define-key map [remap backward-kill-word] 'thai-backward-kill-word)
256 (define-key map [remap transpose-words] 'thai-transpose-words)
258 "Keymap for `thai-word-mode'.")
260 (define-minor-mode thai-word-mode
261 "Minor mode to make word-oriented commands aware of Thai words.
262 The commands affected are \\[forward-word], \\[backward-word], \\[kill-word], \\[backward-kill-word], \\[transpose-words], and \\[fill-paragraph]."
263 :global t :group 'mule
264 (cond (thai-word-mode
265 ;; This enables linebreak between Thai characters.
266 (modify-category-entry (make-char 'thai-tis620) ?|)
267 ;; This enables linebreak at a Thai word boundary.
268 (put-charset-property 'thai-tis620 'fill-find-break-point-function
269 'thai-fill-find-break-point))
271 (modify-category-entry (make-char 'thai-tis620) ?| nil t)
272 (put-charset-property 'thai-tis620 'fill-find-break-point-function
275 ;; Function to call on entering the Thai language environment.
276 (defun setup-thai-language-environment-internal ()
279 ;; Function to call on exiting the Thai language environment.
280 (defun exit-thai-language-environment-internal ()
286 ;;; arch-tag: 59425d6a-8cf9-4e06-a6ab-8ab7dc7a7a97
287 ;;; thai-util.el ends here