1;;; thai-util.el --- utilities for Thai -*- coding: iso-2022-7bit; -*- 2 3;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 4;; 2005, 2006, 2007 5;; National Institute of Advanced Industrial Science and Technology (AIST) 6;; Registration Number H14PRO021 7;; Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007 8;; Free Software Foundation, Inc. 9 10;; Keywords: mule, multilingual, thai 11 12;; This file is part of GNU Emacs. 13 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) 17;; any later version. 18 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. 23 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. 28 29;;; Commentary: 30 31;;; Code: 32 33(defvar thai-auto-composition-mode) 34 35;; Setting information of Thai characters. 36 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) 44 45;; The general composing rules are as follows: 46;; 47;; T 48;; V U V U 49;; CV -> C, CU -> C, CVT -> C, Cv -> C, CvU -> C 50;; v v 51;; 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 `,Tl(B' can be put on the vowel `,TT(B'. 55 56 57(defvar thai-composition-pattern 58 "\\cc\\(\\cu\\|\\cI\\cU\\|\\cv\\ct?\\)\\|\\cv\\ct\\|\\cI\\cU" 59 "Regular expression matching a Thai composite sequence.") 60 61(defun thai-self-insert-command (&optional n) 62 "Insert the Thai character you type. 63The character will be composed with the surrounding Thai character 64if necessary." 65 (interactive "*p") 66 (let ((pos (point)) 67 category-set ch) 68 (self-insert-command n) 69 (or thai-auto-composition-mode 70 (thai-auto-composition (1- (point)) (point) 0)))) 71 72(let ((l '((?,T!(B consonant "LETTER KO KAI") ; 0xA1 73 (?,T"(B consonant "LETTER KHO KHAI") ; 0xA2 74 (?,T#(B consonant "LETTER KHO KHUAT") ; 0xA3 75 (?,T$(B consonant "LETTER KHO KHWAI") ; 0xA4 76 (?,T%(B consonant "LETTER KHO KHON") ; 0xA5 77 (?,T&(B consonant "LETTER KHO RAKHANG") ; 0xA6 78 (?,T'(B consonant "LETTER NGO NGU") ; 0xA7 79 (?,T((B consonant "LETTER CHO CHAN") ; 0xA8 80 (?,T)(B consonant "LETTER CHO CHING") ; 0xA9 81 (?,T*(B consonant "LETTER CHO CHANG") ; 0xAA 82 (?,T+(B consonant "LETTER SO SO") ; 0xAB 83 (?,T,(B consonant "LETTER CHO CHOE") ; 0xAC 84 (?,T-(B consonant "LETTER YO YING") ; 0xAD 85 (?,T.(B consonant "LETTER DO CHADA") ; 0xAE 86 (?,T/(B consonant "LETTER TO PATAK") ; 0xAF 87 (?,T0(B consonant "LETTER THO THAN") ; 0xB0 88 (?,T1(B consonant "LETTER THO NANGMONTHO") ; 0xB1 89 (?,T2(B consonant "LETTER THO PHUTHAO") ; 0xB2 90 (?,T3(B consonant "LETTER NO NEN") ; 0xB3 91 (?,T4(B consonant "LETTER DO DEK") ; 0xB4 92 (?,T5(B consonant "LETTER TO TAO") ; 0xB5 93 (?,T6(B consonant "LETTER THO THUNG") ; 0xB6 94 (?,T7(B consonant "LETTER THO THAHAN") ; 0xB7 95 (?,T8(B consonant "LETTER THO THONG") ; 0xB8 96 (?,T9(B consonant "LETTER NO NU") ; 0xB9 97 (?,T:(B consonant "LETTER BO BAIMAI") ; 0xBA 98 (?,T;(B consonant "LETTER PO PLA") ; 0xBB 99 (?,T<(B consonant "LETTER PHO PHUNG") ; 0xBC 100 (?,T=(B consonant "LETTER FO FA") ; 0xBD 101 (?,T>(B consonant "LETTER PHO PHAN") ; 0xBE 102 (?,T?(B consonant "LETTER FO FAN") ; 0xBF 103 (?,T@(B consonant "LETTER PHO SAMPHAO") ; 0xC0 104 (?,TA(B consonant "LETTER MO MA") ; 0xC1 105 (?,TB(B consonant "LETTER YO YAK") ; 0xC2 106 (?,TC(B consonant "LETTER RO RUA") ; 0xC3 107 (?,TD(B vowel-base "LETTER RU (Pali vowel letter)") ; 0xC4 108 (?,TE(B consonant "LETTER LO LING") ; 0xC5 109 (?,TF(B vowel-base "LETTER LU (Pali vowel letter)") ; 0xC6 110 (?,TG(B consonant "LETTER WO WAEN") ; 0xC7 111 (?,TH(B consonant "LETTER SO SALA") ; 0xC8 112 (?,TI(B consonant "LETTER SO RUSI") ; 0xC9 113 (?,TJ(B consonant "LETTER SO SUA") ; 0xCA 114 (?,TK(B consonant "LETTER HO HIP") ; 0xCB 115 (?,TL(B consonant "LETTER LO CHULA") ; 0xCC 116 (?,TM(B consonant "LETTER O ANG") ; 0xCD 117 (?,TN(B consonant "LETTER HO NOK HUK") ; 0xCE 118 (?,TO(B special "PAI YAN NOI (abbreviation)") ; 0xCF 119 (?,TP(B vowel-base "VOWEL SIGN SARA A") ; 0xD0 120 (?,TQ(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T") ; 0xD1 121 (?,TR(B vowel-base "VOWEL SIGN SARA AA") ; 0xD2 122 (?,TS(B vowel-base "VOWEL SIGN SARA AM") ; 0xD3 123 (?,TT(B vowel-upper "VOWEL SIGN SARA I N/S-T") ; 0xD4 124 (?,TU(B vowel-upper "VOWEL SIGN SARA II N/S-T") ; 0xD5 125 (?,TV(B vowel-upper "VOWEL SIGN SARA UE N/S-T") ; 0xD6 126 (?,TW(B vowel-upper "VOWEL SIGN SARA UEE N/S-T") ; 0xD7 127 (?,TX(B vowel-lower "VOWEL SIGN SARA U N/S-B") ; 0xD8 128 (?,TY(B vowel-lower "VOWEL SIGN SARA UU N/S-B") ; 0xD9 129 (?,TZ(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)") ; 0xDA 130 (?,T[(B invalid nil) ; 0xDA 131 (?,T\(B invalid nil) ; 0xDC 132 (?,T](B invalid nil) ; 0xDC 133 (?,T^(B invalid nil) ; 0xDC 134 (?,T_(B special "BAHT SIGN (currency symbol)") ; 0xDF 135 (?,T`(B vowel-base "VOWEL SIGN SARA E") ; 0xE0 136 (?,Ta(B vowel-base "VOWEL SIGN SARA AE") ; 0xE1 137 (?,Tb(B vowel-base "VOWEL SIGN SARA O") ; 0xE2 138 (?,Tc(B vowel-base "VOWEL SIGN SARA MAI MUAN") ; 0xE3 139 (?,Td(B vowel-base "VOWEL SIGN SARA MAI MALAI") ; 0xE4 140 (?,Te(B vowel-base "LAK KHANG YAO") ; 0xE5 141 (?,Tf(B special "MAI YAMOK (repetion)") ; 0xE6 142 (?,Tg(B sign-upper "VOWEL SIGN MAI TAI KHU N/S-T") ; 0xE7 143 (?,Th(B tone "TONE MAI EK N/S-T") ; 0xE8 144 (?,Ti(B tone "TONE MAI THO N/S-T") ; 0xE9 145 (?,Tj(B tone "TONE MAI TRI N/S-T") ; 0xEA 146 (?,Tk(B tone "TONE MAI CHATTAWA N/S-T") ; 0xEB 147 (?,Tl(B sign-upper "THANTHAKHAT N/S-T (cancellation mark)") ; 0xEC 148 (?,Tm(B sign-upper "NIKKHAHIT N/S-T (final nasal)") ; 0xED 149 (?,Tn(B sign-upper "YAMAKKAN N/S-T") ; 0xEE 150 (?,To(B special "FONRMAN") ; 0xEF 151 (?,Tp(B special "DIGIT ZERO") ; 0xF0 152 (?,Tq(B special "DIGIT ONE") ; 0xF1 153 (?,Tr(B special "DIGIT TWO") ; 0xF2 154 (?,Ts(B special "DIGIT THREE") ; 0xF3 155 (?,Tt(B special "DIGIT FOUR") ; 0xF4 156 (?,Tu(B special "DIGIT FIVE") ; 0xF5 157 (?,Tv(B special "DIGIT SIX") ; 0xF6 158 (?,Tw(B special "DIGIT SEVEN") ; 0xF7 159 (?,Tx(B special "DIGIT EIGHT") ; 0xF8 160 (?,Ty(B special "DIGIT NINE") ; 0xF9 161 (?,Tz(B special "ANGKHANKHU (ellipsis)") ; 0xFA 162 (?,T{(B special "KHOMUT (beginning of religious texts)") ; 0xFB 163 (?,T|(B invalid nil) ; 0xFC 164 (?,T}(B invalid nil) ; 0xFD 165 (?,T~(B invalid nil) ; 0xFE 166 167 ;; Unicode equivalents 168 (?$,1Ba(B consonant "LETTER KO KAI") 169 (?$,1Bb(B consonant "LETTER KHO KHAI") 170 (?$,1Bc(B consonant "LETTER KHO KHUAT") 171 (?$,1Bd(B consonant "LETTER KHO KHWAI") 172 (?$,1Be(B consonant "LETTER KHO KHON") 173 (?$,1Bf(B consonant "LETTER KHO RAKHANG") 174 (?$,1Bg(B consonant "LETTER NGO NGU") 175 (?$,1Bh(B consonant "LETTER CHO CHAN") 176 (?$,1Bi(B consonant "LETTER CHO CHING") 177 (?$,1Bj(B consonant "LETTER CHO CHANG") 178 (?$,1Bk(B consonant "LETTER SO SO") 179 (?$,1Bl(B consonant "LETTER CHO CHOE") 180 (?$,1Bm(B consonant "LETTER YO YING") 181 (?$,1Bn(B consonant "LETTER DO CHADA") 182 (?$,1Bo(B consonant "LETTER TO PATAK") 183 (?$,1Bp(B consonant "LETTER THO THAN") 184 (?$,1Bq(B consonant "LETTER THO NANGMONTHO") 185 (?$,1Br(B consonant "LETTER THO PHUTHAO") 186 (?$,1Bs(B consonant "LETTER NO NEN") 187 (?$,1Bt(B consonant "LETTER DO DEK") 188 (?$,1Bu(B consonant "LETTER TO TAO") 189 (?$,1Bv(B consonant "LETTER THO THUNG") 190 (?$,1Bw(B consonant "LETTER THO THAHAN") 191 (?$,1Bx(B consonant "LETTER THO THONG") 192 (?$,1By(B consonant "LETTER NO NU") 193 (?$,1Bz(B consonant "LETTER BO BAIMAI") 194 (?$,1B{(B consonant "LETTER PO PLA") 195 (?$,1B|(B consonant "LETTER PHO PHUNG") 196 (?$,1B}(B consonant "LETTER FO FA") 197 (?$,1B~(B consonant "LETTER PHO PHAN") 198 (?$,1B(B consonant "LETTER FO FAN") 199 (?$,1C (B consonant "LETTER PHO SAMPHAO") 200 (?$,1C!(B consonant "LETTER MO MA") 201 (?$,1C"(B consonant "LETTER YO YAK") 202 (?$,1C#(B consonant "LETTER RO RUA") 203 (?$,1C$(B vowel-base "LETTER RU (Pali vowel letter)") 204 (?$,1C%(B consonant "LETTER LO LING") 205 (?$,1C&(B vowel-base "LETTER LU (Pali vowel letter)") 206 (?$,1C'(B consonant "LETTER WO WAEN") 207 (?$,1C((B consonant "LETTER SO SALA") 208 (?$,1C)(B consonant "LETTER SO RUSI") 209 (?$,1C*(B consonant "LETTER SO SUA") 210 (?$,1C+(B consonant "LETTER HO HIP") 211 (?$,1C,(B consonant "LETTER LO CHULA") 212 (?$,1C-(B consonant "LETTER O ANG") 213 (?$,1C.(B consonant "LETTER HO NOK HUK") 214 (?$,1C/(B special "PAI YAN NOI (abbreviation)") 215 (?$,1C0(B vowel-base "VOWEL SIGN SARA A") 216 (?$,1C1(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T") 217 (?$,1C2(B vowel-base "VOWEL SIGN SARA AA") 218 (?$,1C3(B vowel-base "VOWEL SIGN SARA AM") 219 (?$,1C4(B vowel-upper "VOWEL SIGN SARA I N/S-T") 220 (?$,1C5(B vowel-upper "VOWEL SIGN SARA II N/S-T") 221 (?$,1C6(B vowel-upper "VOWEL SIGN SARA UE N/S-T") 222 (?$,1C7(B vowel-upper "VOWEL SIGN SARA UEE N/S-T") 223 (?$,1C8(B vowel-lower "VOWEL SIGN SARA U N/S-B") 224 (?$,1C9(B vowel-lower "VOWEL SIGN SARA UU N/S-B") 225 (?$,1C:(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)") 226 (?$,1C?(B special "BAHT SIGN (currency symbol)") 227 (?$,1C@(B vowel-base "VOWEL SIGN SARA E") 228 (?$,1CA(B vowel-base "VOWEL SIGN SARA AE") 229 (?$,1CB(B vowel-base "VOWEL SIGN SARA O") 230 (?$,1CC(B vowel-base "VOWEL SIGN SARA MAI MUAN") 231 (?$,1CD(B vowel-base "VOWEL SIGN SARA MAI MALAI") 232 (?$,1CE(B vowel-base "LAK KHANG YAO") 233 (?$,1CF(B special "MAI YAMOK (repetion)") 234 (?$,1CG(B sign-upper "VOWEL SIGN MAI TAI KHU N/S-T") 235 (?$,1CH(B tone "TONE MAI EK N/S-T") 236 (?$,1CI(B tone "TONE MAI THO N/S-T") 237 (?$,1CJ(B tone "TONE MAI TRI N/S-T") 238 (?$,1CK(B tone "TONE MAI CHATTAWA N/S-T") 239 (?$,1CL(B sign-upper "THANTHAKHAT N/S-T (cancellation mark)") 240 (?$,1CM(B sign-upper "NIKKHAHIT N/S-T (final nasal)") 241 (?$,1CN(B sign-upper "YAMAKKAN N/S-T") 242 (?$,1CO(B special "FONRMAN") 243 (?$,1CP(B special "DIGIT ZERO") 244 (?$,1CQ(B special "DIGIT ONE") 245 (?$,1CR(B special "DIGIT TWO") 246 (?$,1CS(B special "DIGIT THREE") 247 (?$,1CT(B special "DIGIT FOUR") 248 (?$,1CU(B special "DIGIT FIVE") 249 (?$,1CV(B special "DIGIT SIX") 250 (?$,1CW(B special "DIGIT SEVEN") 251 (?$,1CX(B special "DIGIT EIGHT") 252 (?$,1CY(B special "DIGIT NINE") 253 (?$,1CZ(B special "ANGKHANKHU (ellipsis)") 254 (?$,1C[(B special "KHOMUT (beginning of religious texts)") 255 )) 256 elm) 257 (while l 258 (setq elm (car l) l (cdr l)) 259 (let ((char (car elm)) 260 (ptype (nth 1 elm))) 261 (put-char-code-property char 'phonetic-type ptype) 262 (cond ((eq ptype 'consonant) 263 (modify-category-entry char ?c thai-category-table) 264 (global-set-key (vector char) 'thai-self-insert-command)) 265 ((memq ptype '(vowel-upper vowel-lower)) 266 (modify-category-entry char ?v thai-category-table) 267 (if (or (= char ?,TT(B) (= char ?$,1C4(B)) 268 ;; Give category `I' to "SARA I". 269 (modify-category-entry char ?I thai-category-table)) 270 (global-set-key (vector char) 'thai-self-insert-command)) 271 ((eq ptype 'tone) 272 (modify-category-entry char ?t thai-category-table) 273 (modify-category-entry char ?u thai-category-table) 274 (global-set-key (vector char) 'thai-self-insert-command)) 275 ((eq ptype 'sign-upper) 276 (modify-category-entry char ?u thai-category-table) 277 (if (or (= char ?,Tl(B) (= char ?$,1CL(B)) 278 ;; Give category `U' to "THANTHAKHAT". 279 (modify-category-entry char ?U thai-category-table)) 280 (global-set-key (vector char) 'thai-self-insert-command))) 281 (put-char-code-property char 'name (nth 2 elm))))) 282 283(defun thai-compose-syllable (beg end &optional category-set string) 284 (or category-set 285 (setq category-set 286 (char-category-set (if string (aref string beg) (char-after beg))))) 287 (if (aref category-set ?c) 288 ;; Starting with a consonant. We do relative composition. 289 (if string 290 (compose-string string beg end) 291 (compose-region beg end)) 292 ;; Vowel tone sequence. 293 (if string 294 (compose-string string beg end (list (aref string beg) '(Bc . Bc) 295 (aref string (1+ beg)))) 296 (compose-region beg end (list (char-after beg) '(Bc . Bc) 297 (char-after (1+ beg)))))) 298 (- end beg)) 299 300;;;###autoload 301(defun thai-compose-region (beg end) 302 "Compose Thai characters in the region. 303When called from a program, expects two arguments, 304positions (integers or markers) specifying the region." 305 (interactive "r") 306 (let ((pos (point))) 307 (save-restriction 308 (narrow-to-region beg end) 309 (goto-char (point-min)) 310 (with-category-table thai-category-table 311 (while (re-search-forward thai-composition-pattern nil t) 312 (setq beg (match-beginning 0) end (match-end 0)) 313 (if (and (> pos beg) (< pos end)) 314 (setq pos end)) 315 (thai-compose-syllable beg end 316 (char-category-set (char-after beg)))))) 317 (goto-char pos))) 318 319;;;###autoload 320(defun thai-compose-string (string) 321 "Compose Thai characters in STRING and return the resulting string." 322 (with-category-table thai-category-table 323 (let ((idx 0)) 324 (while (setq idx (string-match thai-composition-pattern string idx)) 325 (thai-compose-syllable idx (match-end 0) nil string) 326 (setq idx (match-end 0))))) 327 string) 328 329;;;###autoload 330(defun thai-compose-buffer () 331 "Compose Thai characters in the current buffer." 332 (interactive) 333 (thai-compose-region (point-min) (point-max))) 334 335;;;###autoload 336(defun thai-post-read-conversion (len) 337 (thai-compose-region (point) (+ (point) len)) 338 len) 339 340;;;###autoload 341(defun thai-composition-function (from to pattern &optional string) 342 "Compose Thai text in the region FROM and TO. 343The text matches the regular expression PATTERN. 344Optional 4th argument STRING, if non-nil, is a string containing text 345to compose. 346 347The return value is number of composed characters." 348 (when (and (not thai-auto-composition-mode) 349 (< (1+ from) to)) 350 (with-category-table thai-category-table 351 (if string 352 (if (eq (string-match thai-composition-pattern string from) from) 353 (thai-compose-syllable from (match-end 0) nil string)) 354 (if (save-excursion 355 (goto-char from) 356 (and (looking-at thai-composition-pattern) 357 (setq to (match-end 0)))) 358 (thai-compose-syllable from to)))))) 359 360(defun thai-auto-composition (beg end len) 361 (with-category-table thai-category-table 362 (let (category-set) 363 (while (and (> beg (point-min)) 364 (setq category-set (char-category-set (char-after (1- beg)))) 365 (or (aref category-set ?v) (aref category-set ?u))) 366 (setq beg (1- beg))) 367 (if (and (> beg (point-min)) 368 (aref (char-category-set (char-after (1- beg))) ?c)) 369 (setq beg (1- beg))) 370 (while (and (< end (point-max)) 371 (setq category-set (char-category-set (char-after end))) 372 (or (aref category-set ?v) (aref category-set ?u))) 373 (setq end (1+ end))) 374 (if (< beg end) 375 (thai-compose-region beg end))))) 376 377(put 'thai-auto-composition-mode 'permanent-local t) 378 379;;;###autoload 380(define-minor-mode thai-auto-composition-mode 381 "Minor mode for automatically correct Thai character composition." 382 :group 'mule 383 (cond ((null thai-auto-composition-mode) 384 (remove-hook 'after-change-functions 'thai-auto-composition)) 385 (t 386 (add-hook 'after-change-functions 'thai-auto-composition)))) 387 388;; Thai-word-mode requires functions in the feature `thai-word'. 389(require 'thai-word) 390 391(defvar thai-word-mode-map 392 (let ((map (make-sparse-keymap))) 393 (define-key map [remap forward-word] 'thai-forward-word) 394 (define-key map [remap backward-word] 'thai-backward-word) 395 (define-key map [remap kill-word] 'thai-kill-word) 396 (define-key map [remap backward-kill-word] 'thai-backward-kill-word) 397 (define-key map [remap transpose-words] 'thai-transpose-words) 398 map) 399 "Keymap for `thai-word-mode'.") 400 401(define-minor-mode thai-word-mode 402 "Minor mode to make word-oriented commands aware of Thai words. 403The commands affected are \\[forward-word], \\[backward-word], \\[kill-word], \\[backward-kill-word], \\[transpose-words], and \\[fill-paragraph]." 404 :global t :group 'mule 405 (cond (thai-word-mode 406 ;; This enables linebreak between Thai characters. 407 (modify-category-entry (make-char 'thai-tis620) ?|) 408 ;; This enables linebreak at a Thai word boundary. 409 (put-charset-property 'thai-tis620 'fill-find-break-point-function 410 'thai-fill-find-break-point)) 411 (t 412 (modify-category-entry (make-char 'thai-tis620) ?| nil t) 413 (put-charset-property 'thai-tis620 'fill-find-break-point-function 414 nil)))) 415 416;; Function to call on entering the Thai language environment. 417(defun setup-thai-language-environment-internal () 418 (thai-word-mode 1)) 419 420;; Function to call on exiting the Thai language environment. 421(defun exit-thai-language-environment-internal () 422 (thai-word-mode -1)) 423 424;; 425(provide 'thai-util) 426 427;;; arch-tag: 59425d6a-8cf9-4e06-a6ab-8ab7dc7a7a97 428;;; thai-util.el ends here 429