| | 1 | ;;; tibetan.el --- support for Tibetan language -*- coding: utf-8-emacs; -*- |
| | 2 | |
| | 3 | ;; Copyright (C) 1997, 2001-2014 Free Software Foundation, Inc. |
| | 4 | ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, |
| | 5 | ;; 2006, 2007, 2008, 2009, 2010, 2011 |
| | 6 | ;; National Institute of Advanced Industrial Science and Technology (AIST) |
| | 7 | ;; Registration Number H14PRO021 |
| | 8 | ;; Copyright (C) 2003 |
| | 9 | ;; National Institute of Advanced Industrial Science and Technology (AIST) |
| | 10 | ;; Registration Number H13PRO009 |
| | 11 | |
| | 12 | ;; Author: Toru TOMABECHI <Toru.Tomabechi@orient.unil.ch> |
| | 13 | ;; Created: Feb. 17. 1997 |
| | 14 | ;; Keywords: multilingual, Tibetan, i18n |
| | 15 | |
| | 16 | ;; This file is part of GNU Emacs. |
| | 17 | |
| | 18 | ;; GNU Emacs is free software: you can redistribute it and/or modify |
| | 19 | ;; it under the terms of the GNU General Public License as published by |
| | 20 | ;; the Free Software Foundation, either version 3 of the License, or |
| | 21 | ;; (at your option) any later version. |
| | 22 | |
| | 23 | ;; GNU Emacs is distributed in the hope that it will be useful, |
| | 24 | ;; but WITHOUT ANY WARRANTY; without even the implied warranty of |
| | 25 | ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| | 26 | ;; GNU General Public License for more details. |
| | 27 | |
| | 28 | ;; You should have received a copy of the GNU General Public License |
| | 29 | ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. |
| | 30 | |
| | 31 | ;;; History: |
| | 32 | |
| | 33 | ;; 1997.03.13 Modification for special signs and punctuation. |
| | 34 | |
| | 35 | ;;; Commentary: |
| | 36 | |
| | 37 | ;;; Code: |
| | 38 | |
| | 39 | ;;; Tibetan Character set. |
| | 40 | ;;; \x2130 -- \x234a is a subset of Unicode v.2 \x0f00 - \x0fb9 |
| | 41 | ;;; with a slight modification. And there are some subjoined |
| | 42 | ;;; consonants which are not specified in Unicode. |
| | 43 | ;;; I hope I can add missing characters later. |
| | 44 | ;;; |
| | 45 | ;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F |
| | 46 | ;;;2120 // ; obsolete glyphs (2123-5) |
| | 47 | ;;;2130 ༀ ༁ ༂ ༃ ༄ ༅ ༆ ༇ ༈ ༉ ༊ ་ ༌ ། ༎ ༏ ; Punctuation, |
| | 48 | ;;;2140 ༐ ༑ ༒ ༓ ༔ ༕ ༖ ༗ ༘ ༙ ༚ ༛ ༜ ༝ ༞ ༟ ; Digits and |
| | 49 | ;;;2150 ༠ ༡ ༢ ༣ ༤ ༥ ༦ ༧ ༨ ༩ ༪ ༫ ༬ ༭ ༮ ༯ ; Special signs. |
| | 50 | ;;;2160 ༰ ༱ ༲ ༳ ༴ ༵ ༶ ༷ ༸ ༹ ༺ ༻ ༼ ༽ ༾ ༿ ; |
| | 51 | ;;;2170 // ; |
| | 52 | ;;; |
| | 53 | ;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F |
| | 54 | ;;;2220 // ཀ ཁ ག གྷ ང ཅ ཆ ཇ ཉ ཊ ཋ ཌ ཌྷ ཎ ; Base consonants |
| | 55 | ;;;2230 ཏ ཐ ད དྷ ན པ ཕ བ བྷ མ ཙ ཚ ཛ ཛྷ ཝ ཞ ; and |
| | 56 | ;;;2240 ཟ འ ཡ ར ལ ཤ ཥ ས ཧ ཨ ཀྵ ཪ ; Vowel signs. |
| | 57 | ;;;2250 ཱ ི ཱི ུ ཱུ ྲྀ ཷ ླྀ ཹ ེ ཻ ོ ཽ ཾ ; (\x2251 = vowel a) |
| | 58 | ;;;2260 ཿ ྀ ཱྀ ྂ ྃ ྄ ྅ ྆ ྇ ྈ ྉ ྊ ྋ ; Long vowels and |
| | 59 | ;;;2270 // ; vocalic r, l ARE |
| | 60 | ;;; ; atomically |
| | 61 | ;;; ; encoded. |
| | 62 | ;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F |
| | 63 | ;;;2320 // ྐ ྑ ྒ ྒྷ ྔ ྕ ྖ ྗ ྙ ྚ ྛ ྜ ྜྷ ྞ ; Subjoined consonants |
| | 64 | ;;;2330 ྟ ྠ ྡ ྡྷ ྣ ྤ ྥ ྦ ྦྷ ྨ ྩ ྪ ྫ ྫྷ ྭ ྮ ; |
| | 65 | ;;;2340 ྯ ྰ ྱ ྲ ླ ྴ ྵ ྶ ྷ ྸ ྐྵ ྺ ྻ ྼ ྾ ; |
| | 66 | ;;;2350 ྿ ࿀ ࿁ ࿂ ࿃ ࿄ ࿅ ࿆ ࿇ ࿈ ࿉ ࿊ ࿋ ࿌ ; Hereafter, the chars |
| | 67 | ;;;2360 ࿏ ; are not specified |
| | 68 | ;;;2370 // ; in Unicode. |
| | 69 | ;;; |
| | 70 | ;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F |
| | 71 | ;;;2420 // ; Precomposed |
| | 72 | ;;;2430 ; consonants for |
| | 73 | ;;;2440 ; ordinary Tibetan. |
| | 74 | ;;;2450 ; They are decomposed |
| | 75 | ;;;2460 ; into base and |
| | 76 | ;;;2470 // ; subjoined consonants |
| | 77 | ;;; ; when written on a |
| | 78 | ;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F ; file in Tibetan |
| | 79 | ;;;2520 // ; coding system. |
| | 80 | ;;;2530 ; |
| | 81 | ;;;2540 ; |
| | 82 | ;;;2550 ; |
| | 83 | ;;;2560 ; |
| | 84 | ;;;2570 // ; |
| | 85 | ;;; |
| | 86 | |
| | 87 | |
| | 88 | (define-coding-system 'tibetan-iso-8bit |
| | 89 | "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)." |
| | 90 | :coding-type 'iso-2022 |
| | 91 | :mnemonic ?Q |
| | 92 | :designation [ascii tibetan nil nil] |
| | 93 | :charset-list '(ascii tibetan)) |
| | 94 | |
| | 95 | (define-coding-system-alias 'tibetan 'tibetan-iso-8bit) |
| | 96 | |
| | 97 | (set-language-info-alist |
| | 98 | "Tibetan" '((charset tibetan tibetan-1-column) |
| | 99 | (coding-system tibetan-iso-8bit) |
| | 100 | (coding-priority iso-2022-7bit tibetan-iso-8bit) |
| | 101 | (input-method . "tibetan-wylie") |
| | 102 | (features tibet-util) |
| | 103 | (documentation . t) |
| | 104 | (sample-text . "Tibetan (བོད་སྐད་) ༄༅༅༎བཀྲ་ཤིས་བདེ་ལེགས༎ཨོཾ་མ་ཎི་པདྨེ་ཧའུྂ༎"))) |
| | 105 | |
| | 106 | ;; `འ' is included in the pattern for subjoined consonants because we |
| | 107 | ;; treat it specially in tibetan-add-components. |
| | 108 | ;; modified by Tomabechi 1999/12/10 |
| | 109 | ;; modified by Tomabechi 2000/06/08 |
| | 110 | ;; To allow infinite addition of vowels/modifiers |
| | 111 | ;; as specified in Unicode v.3 |
| | 112 | ;; འ is removed from the class of subjoined. Tomabechi 2000/06/08 |
| | 113 | ;; (for Unicode support) |
| | 114 | (defconst tibetan-composable-pattern |
| | 115 | "[ཀ-ཀྵཪ][ྐ-ྐྵྺྻྼ]*[ཱི-྄ཱཽྀྀ]*[ཾྂྃ྆-ྋ༙༵༷]*" |
| | 116 | "Regexp matching a composable sequence of Tibetan characters.") |
| | 117 | |
| | 118 | ;;; |
| | 119 | ;;; Definitions of conversion data. |
| | 120 | ;;; |
| | 121 | |
| | 122 | |
| | 123 | ;;; alists for tibetan char <-> transcription conversion |
| | 124 | ;;; longer transcription should come first |
| | 125 | (defconst tibetan-consonant-transcription-alist |
| | 126 | '(("tsh" . "ཚ") |
| | 127 | ("dzh" . "ཛྷ") |
| | 128 | ("kSH" . "ཀྵ") |
| | 129 | ("kh" . "ཁ") |
| | 130 | ("gh" . "གྷ") |
| | 131 | ("ng" . "ང") |
| | 132 | ("ch" . "ཆ") |
| | 133 | ("ny" . "ཉ") |
| | 134 | ("TH" . "ཋ") |
| | 135 | ("DH" . "ཌྷ") |
| | 136 | ("th" . "ཐ") |
| | 137 | ("dh" . "དྷ") |
| | 138 | ("ph" . "ཕ") |
| | 139 | ("bh" . "བྷ") |
| | 140 | ("ts" . "ཙ") |
| | 141 | ("dz" . "ཛ") |
| | 142 | ("zh" . "ཞ") |
| | 143 | ("sh" . "ཤ") |
| | 144 | ("SH" . "ཥ") |
| | 145 | ("k" . "ཀ") |
| | 146 | ("g" . "ག") |
| | 147 | ("c" . "ཅ") |
| | 148 | ("j" . "ཇ") |
| | 149 | ("T" . "ཊ") |
| | 150 | ("D" . "ཌ") |
| | 151 | ("N" . "ཎ") |
| | 152 | ("t" . "ཏ") |
| | 153 | ("d" . "ད") |
| | 154 | ("n" . "ན") |
| | 155 | ("p" . "པ") |
| | 156 | ("b" . "བ") |
| | 157 | ("m" . "མ") |
| | 158 | ("w" . "ཝ") |
| | 159 | ("z" . "ཟ") |
| | 160 | ("'" . "འ") |
| | 161 | ("y" . "ཡ") |
| | 162 | ("r" . "ར") |
| | 163 | ("l" . "ལ") |
| | 164 | ("s" . "ས") |
| | 165 | ("h" . "ཧ") |
| | 166 | ("H" . "ཧ") |
| | 167 | ("A" . "ཨ") |
| | 168 | ;; Added by Tomabechi 1999/12/10 |
| | 169 | ("R" . "ཪ") ;; fixed form RA |
| | 170 | )) |
| | 171 | |
| | 172 | |
| | 173 | (defconst tibetan-vowel-transcription-alist |
| | 174 | '( |
| | 175 | ;; Composite Vowels |
| | 176 | ;; Added by Tomabechi 2000/06/08 |
| | 177 | ("frr" . "ཷ") |
| | 178 | ("fll" . "ཹ") |
| | 179 | ("fa" . "ཱ") |
| | 180 | ("fi" . "ཱི") |
| | 181 | ("fu" . "ཱུ") |
| | 182 | ("fr" . "ྲྀ") |
| | 183 | ("fl" . "ླྀ") |
| | 184 | ("fI" . "ཱྀ") |
| | 185 | ;; Normal Vowels |
| | 186 | ("ai" . "ཻ") |
| | 187 | ("au" . "ཽ") |
| | 188 | ("ee" . "ཻ") |
| | 189 | ("oo" . "ཽ") |
| | 190 | ("a" . "") ; invisible vowel sign (\x2251) |
| | 191 | ("i" . "ི") |
| | 192 | ("u" . "ུ") |
| | 193 | ("e" . "ེ") |
| | 194 | ("o" . "ོ") |
| | 195 | ("E" . "ཻ") |
| | 196 | ("O" . "ཽ") |
| | 197 | ("I" . "ྀ") |
| | 198 | ("," . "྄") ; idem. |
| | 199 | )) |
| | 200 | |
| | 201 | (defconst tibetan-modifier-transcription-alist |
| | 202 | '(("M" . "ཾ") |
| | 203 | ("~" . "ྂ") |
| | 204 | ("`" . "ྃ") |
| | 205 | ("x" . "ྈ") |
| | 206 | ("X" . "ྉ") |
| | 207 | ("v" . "྆") |
| | 208 | ("V" . "྇") |
| | 209 | ("q" . "ྊ") |
| | 210 | ("Q" . "ྋ") |
| | 211 | ("_/" . "༙") |
| | 212 | ("_o" . "༷") |
| | 213 | ("_O" . "༵"))) |
| | 214 | |
| | 215 | (defconst tibetan-precomposed-transcription-alist |
| | 216 | '(("phyw" . "") |
| | 217 | ("tshw" . "") |
| | 218 | ("rtsw" . "") |
| | 219 | ("khw" . "") |
| | 220 | ("nyw" . "") |
| | 221 | ("tsw" . "") |
| | 222 | ("zhw" . "") |
| | 223 | ("shw" . "") |
| | 224 | ("khy" . "") |
| | 225 | ("phy" . "") |
| | 226 | ("khr" . "") |
| | 227 | ("thr" . "") |
| | 228 | ("phr" . "") |
| | 229 | ("shr" . "") |
| | 230 | ("dzr" . "") |
| | 231 | ("grw" . "") |
| | 232 | ("rng" . "") |
| | 233 | ("rny" . "") |
| | 234 | ("rts" . "") |
| | 235 | ("rdz" . "") |
| | 236 | ("rgw" . "") |
| | 237 | ("rky" . "") |
| | 238 | ("rgy" . "") |
| | 239 | ("rmy" . "") |
| | 240 | ("lng" . "") |
| | 241 | ("sng" . "") |
| | 242 | ("sny" . "") |
| | 243 | ("sts" . "") |
| | 244 | ("sky" . "") |
| | 245 | ("sgy" . "") |
| | 246 | ("spy" . "") |
| | 247 | ("sby" . "") |
| | 248 | ("smy" . "") |
| | 249 | ("skr" . "") |
| | 250 | ("sgr" . "") |
| | 251 | ("snr" . "") |
| | 252 | ("spr" . "") |
| | 253 | ("sbr" . "") |
| | 254 | ("smr" . "") |
| | 255 | ("kw" . "") |
| | 256 | ("gw" . "") |
| | 257 | ("cw" . "") |
| | 258 | ("tw" . "") |
| | 259 | ("dw" . "") |
| | 260 | ("zw" . "") |
| | 261 | ("rw" . "") |
| | 262 | ("lw" . "") |
| | 263 | ("sw" . "") |
| | 264 | ("hw" . "") |
| | 265 | ("ky" . "") |
| | 266 | ("gy" . "") |
| | 267 | ("py" . "") |
| | 268 | ("by" . "") |
| | 269 | ("my" . "") |
| | 270 | ("kr" . "") |
| | 271 | ("gr" . "") |
| | 272 | ("tr" . "") |
| | 273 | ("dr" . "") |
| | 274 | ("pr" . "") |
| | 275 | ("brk" . "བ") |
| | 276 | ("brg" . "བ") |
| | 277 | ("brng" . "བ") |
| | 278 | ("brj" . "བ") |
| | 279 | ("brny" . "བ") |
| | 280 | ("brt" . "བ") |
| | 281 | ("brd" . "བ") |
| | 282 | ("brn" . "བ") |
| | 283 | ("brts" . "བ") |
| | 284 | ("brdz" . "བ") |
| | 285 | ("brl" . "བ") |
| | 286 | ("br" . "") |
| | 287 | ("mr" . "") |
| | 288 | ("sr" . "") |
| | 289 | ("hr" . "") |
| | 290 | ("jr" . "") |
| | 291 | ("kl" . "") |
| | 292 | ("gl" . "") |
| | 293 | ("blt" . "བ") |
| | 294 | ("bld" . "བ") |
| | 295 | ("bl" . "") |
| | 296 | ("zl" . "") |
| | 297 | ("rl" . "") |
| | 298 | ("sl" . "") |
| | 299 | ("rk" . "") |
| | 300 | ("rg" . "") |
| | 301 | ("rj" . "") |
| | 302 | ("rt" . "") |
| | 303 | ("rd" . "") |
| | 304 | ("rn" . "") |
| | 305 | ("rb" . "") |
| | 306 | ("rm" . "") |
| | 307 | ("lk" . "") |
| | 308 | ("lg" . "") |
| | 309 | ("lc" . "") |
| | 310 | ("lj" . "") |
| | 311 | ("lt" . "") |
| | 312 | ("ld" . "") |
| | 313 | ("ln" . "") ; dummy \x2121 |
| | 314 | ("lp" . "") |
| | 315 | ("lb" . "") |
| | 316 | ("lh" . "") |
| | 317 | ("sk" . "") |
| | 318 | ("sg" . "") |
| | 319 | ("st" . "") |
| | 320 | ("sd" . "") |
| | 321 | ("sn" . "") |
| | 322 | ("sp" . "") |
| | 323 | ("sb" . "") |
| | 324 | ("sm" . "")) |
| | 325 | ) |
| | 326 | |
| | 327 | |
| | 328 | (defconst tibetan-subjoined-transcription-alist |
| | 329 | (sort '(("+k" . "ྐ") |
| | 330 | ("+kh" . "ྑ") |
| | 331 | ("+g" . "ྒ") |
| | 332 | ("+gh" . "ྒྷ") |
| | 333 | ("+ng" . "ྔ") |
| | 334 | ("+c" . "ྕ") |
| | 335 | ("+ch" . "ྖ") |
| | 336 | ("+j" . "ྗ") |
| | 337 | ("+ny" . "ྙ") |
| | 338 | ("+T" . "ྚ") |
| | 339 | ("+TH" . "ྛ") |
| | 340 | ("+D" . "ྜ") |
| | 341 | ("+DH" . "ྜྷ") |
| | 342 | ("+N" . "ྞ") |
| | 343 | ("+t" . "ྟ") |
| | 344 | ("+th" . "ྠ") |
| | 345 | ("+d" . "ྡ") |
| | 346 | ("+dh" . "ྡྷ") |
| | 347 | ("+n" . "ྣ") |
| | 348 | ("+p" . "ྤ") |
| | 349 | ("+ph" . "ྥ") |
| | 350 | ("+b" . "ྦ") |
| | 351 | ("+bh" . "ྦྷ") |
| | 352 | ("+m" . "ྨ") |
| | 353 | ("+ts" . "ྩ") |
| | 354 | ("+tsh" . "ྪ") |
| | 355 | ("+dz" . "ྫ") |
| | 356 | ("+dzh" . "ྫྷ") |
| | 357 | ("+w" . "ྭ") |
| | 358 | ("+zh" . "ྮ") |
| | 359 | ("+z" . "ྯ") |
| | 360 | ("+'" . "ྰ") |
| | 361 | ("+y" . "ྱ") |
| | 362 | ("+r" . "ྲ") |
| | 363 | ("+l" . "ླ") |
| | 364 | ("+sh" . "ྴ") |
| | 365 | ("+SH" . "ྵ") |
| | 366 | ("+s" . "ྶ") |
| | 367 | ("+h" . "ྷ") |
| | 368 | ("+A" . "ྸ") |
| | 369 | ("+kSH" . "ྐྵ") |
| | 370 | ;; Added by Tomabechi 1999/12/10 |
| | 371 | ("+W" . "ྺ") ;; fixed form subscribed WA |
| | 372 | ("+Y" . "ྻ") ;; fixed form subscribed YA |
| | 373 | ("+R" . "ྼ") ;; fixed form subscribed RA |
| | 374 | ) |
| | 375 | (lambda (x y) (> (length (car x)) (length (car y)))))) |
| | 376 | |
| | 377 | ;;; |
| | 378 | ;;; alist for Tibetan base consonant <-> subjoined consonant conversion. |
| | 379 | ;;; |
| | 380 | (defconst tibetan-base-to-subjoined-alist |
| | 381 | '(("ཀ" . "ྐ") |
| | 382 | ("ཁ" . "ྑ") |
| | 383 | ("ག" . "ྒ") |
| | 384 | ("གྷ" . "ྒྷ") |
| | 385 | ("ང" . "ྔ") |
| | 386 | ("ཅ" . "ྕ") |
| | 387 | ("ཆ" . "ྖ") |
| | 388 | ("ཇ" . "ྗ") |
| | 389 | ("ཉ" . "ྙ") |
| | 390 | ("ཊ" . "ྚ") |
| | 391 | ("ཋ" . "ྛ") |
| | 392 | ("ཌ" . "ྜ") |
| | 393 | ("ཌྷ" . "ྜྷ") |
| | 394 | ("ཎ" . "ྞ") |
| | 395 | ("ཏ" . "ྟ") |
| | 396 | ("ཐ" . "ྠ") |
| | 397 | ("ད" . "ྡ") |
| | 398 | ("དྷ" . "ྡྷ") |
| | 399 | ("ན" . "ྣ") |
| | 400 | ("པ" . "ྤ") |
| | 401 | ("ཕ" . "ྥ") |
| | 402 | ("བ" . "ྦ") |
| | 403 | ("བྷ" . "ྦྷ") |
| | 404 | ("མ" . "ྨ") |
| | 405 | ("ཙ" . "ྩ") |
| | 406 | ("ཚ" . "ྪ") |
| | 407 | ("ཛ" . "ྫ") |
| | 408 | ("ཛྷ" . "ྫྷ") |
| | 409 | ("ཝ" . "ྭ") |
| | 410 | ("ཞ" . "ྮ") |
| | 411 | ("ཟ" . "ྯ") |
| | 412 | ("འ" . "ྰ") |
| | 413 | ("ཡ" . "ྱ") |
| | 414 | ("ར" . "ྲ") |
| | 415 | ("ལ" . "ླ") |
| | 416 | ("ཤ" . "ྴ") |
| | 417 | ("ཥ" . "ྵ") |
| | 418 | ("ས" . "ྶ") |
| | 419 | ("ཧ" . "ྷ") |
| | 420 | ("ཨ" . "ྸ") |
| | 421 | ("ཀྵ" . "ྐྵ") |
| | 422 | ;; Added by Tomabechi 1999/12/10 |
| | 423 | ("ཪ" . "ྼ") ;; Fixed form RA (224B->234D) |
| | 424 | )) |
| | 425 | |
| | 426 | ;;; alist for Tibetan composite vowels (long i, vocalic r, etc.) |
| | 427 | ;;; New variable. created by Tomabechi 2000/06/08 |
| | 428 | (defconst tibetan-composite-vowel-alist |
| | 429 | '(;; LONG A |
| | 430 | ;; ("ཱ" . ((bc . tc) ?ཱ)) |
| | 431 | ;; LONG I |
| | 432 | ("ཱི" . (?ཱ (tc . bc) ?ི)) |
| | 433 | ;; LONG U |
| | 434 | ("ཱུ" . (?ཱ (bc . tc) ?ུ)) |
| | 435 | ;; VOCALIC R |
| | 436 | ("ྲྀ" . (?ྲ (tc . bc) ?ྀ)) |
| | 437 | ;; LONG VOCALIC R |
| | 438 | ("ཷ" . (?ྲ (bc . tc) ?ཱ (tc . bc) ?ྀ)) |
| | 439 | ;; VOCALIC L |
| | 440 | ("ླྀ" . (?ླ (tc . bc) ?ྀ)) |
| | 441 | ;;་LONG VOCALIC L |
| | 442 | ("ཹ" . (?ླ (bc . tc) ?ཱ (tc . bc) ?ྀ)) |
| | 443 | ;; LONG REVERSE I |
| | 444 | ("ཱྀ" . (?ཱ (tc . bc) ?ྀ)) |
| | 445 | )) |
| | 446 | |
| | 447 | |
| | 448 | |
| | 449 | ;;; |
| | 450 | ;;; alist for Tibetan consonantic components <-> precomposed glyph conversion. |
| | 451 | ;;; (includes some punctuation conversion rules) |
| | 452 | ;;; |
| | 453 | (defconst tibetan-precomposition-rule-alist |
| | 454 | `(("ཕྱྭ" . "") |
| | 455 | ("གྲྭ" . "") |
| | 456 | ("ཚྭ" . "") |
| | 457 | ("རྩྭ" . "") |
| | 458 | ("རྒྭ" . "") |
| | 459 | ("རྐྱ" . "") |
| | 460 | ("རྒྱ" . "") |
| | 461 | ("རྨྱ" . "") |
| | 462 | ("སྐྱ" . "") |
| | 463 | ("སྒྱ" . "") |
| | 464 | ("སྤྱ" . "") |
| | 465 | ("སྦྱ" . "") |
| | 466 | ("སྨྱ" . "") |
| | 467 | ("སྐྲ" . "") |
| | 468 | ("སྒྲ" . "") |
| | 469 | ("སྣྲ" . "") |
| | 470 | ("སྤྲ" . "") |
| | 471 | ("སྦྲ" . "") |
| | 472 | ("སྨྲ" . "") |
| | 473 | ("ཁྭ" . "") |
| | 474 | ("ཉྭ" . "") |
| | 475 | ("ཙྭ" . "") |
| | 476 | ("ཞྭ" . "") |
| | 477 | ("ཤྭ" . "") |
| | 478 | ("ཁྱ" . "") |
| | 479 | ("ཕྱ" . "") |
| | 480 | ("ཁྲ" . "") |
| | 481 | ("ཐྲ" . "") |
| | 482 | ("ཕྲ" . "") |
| | 483 | ("ཤྲ" . "") |
| | 484 | ("ཛྲ" . "") |
| | 485 | ("རྔ" . "") |
| | 486 | ("རྙ" . "") |
| | 487 | ("རྩ" . "") |
| | 488 | ("རྫ" . "") |
| | 489 | ("ལྔ" . "") |
| | 490 | ("སྔ" . "") |
| | 491 | ("སྙ" . "") |
| | 492 | ("སྩ" . "") |
| | 493 | ("ཀྭ" . "") |
| | 494 | ("གྭ" . "") |
| | 495 | ("ཅྭ" . "") |
| | 496 | ("ཏྭ" . "") |
| | 497 | ("དྭ" . "") |
| | 498 | ("ཟྭ" . "") |
| | 499 | ("རྭ" . "") |
| | 500 | ("ལྭ" . "") |
| | 501 | ("སྭ" . "") |
| | 502 | ("ཧྭ" . "") |
| | 503 | ("ཀྱ" . "") |
| | 504 | ("གྱ" . "") |
| | 505 | ("པྱ" . "") |
| | 506 | ("བྱ" . "") |
| | 507 | ("མྱ" . "") |
| | 508 | ("ཀྲ" . "") |
| | 509 | ("གྲ" . "") |
| | 510 | ("ཏྲ" . "") |
| | 511 | ("དྲ" . "") |
| | 512 | ("པྲ" . "") |
| | 513 | ("བྲ" . "") |
| | 514 | ("མྲ" . "") |
| | 515 | ("སྲ" . "") |
| | 516 | ("ཧྲ" . "") |
| | 517 | ("ཇྲ" . "") |
| | 518 | ("ཀླ" . "") |
| | 519 | ("གླ" . "") |
| | 520 | ("བླ" . "") |
| | 521 | ("ཟླ" . "") |
| | 522 | ("རླ" . "") |
| | 523 | ("སླ" . "") |
| | 524 | ("རྐ" . "") |
| | 525 | ("རྒ" . "") |
| | 526 | ("རྗ" . "") |
| | 527 | ("རྟ" . "") |
| | 528 | ("རྡ" . "") |
| | 529 | ("རྣ" . "") |
| | 530 | ("རྦ" . "") |
| | 531 | ("རྨ" . "") |
| | 532 | ("ལྐ" . "") |
| | 533 | ("ལྒ" . "") |
| | 534 | ("ལྣ" . "") ; dummy 0x2121 added 2000/06/08 for transition l -> lng |
| | 535 | ("ལྕ" . "") |
| | 536 | ("ལྗ" . "") |
| | 537 | ("ལྟ" . "") |
| | 538 | ("ལྡ" . "") |
| | 539 | ("ལྤ" . "") |
| | 540 | ("ལྦ" . "") |
| | 541 | ("ལྷ" . "") |
| | 542 | ("སྐ" . "") |
| | 543 | ("སྒ" . "") |
| | 544 | ("སྟ" . "") |
| | 545 | ("སྡ" . "") |
| | 546 | ("སྣ" . "") |
| | 547 | ("སྤ" . "") |
| | 548 | ("སྦ" . "") |
| | 549 | ("སྨ" . ""))) |
| | 550 | |
| | 551 | (defconst tibetan-regexp |
| | 552 | (let ((l (list tibetan-precomposed-transcription-alist |
| | 553 | tibetan-consonant-transcription-alist |
| | 554 | tibetan-vowel-transcription-alist |
| | 555 | tibetan-modifier-transcription-alist |
| | 556 | tibetan-subjoined-transcription-alist)) |
| | 557 | (separator "\\|") |
| | 558 | tail pattern) |
| | 559 | (while l |
| | 560 | (setq tail (car l) l (cdr l)) |
| | 561 | (while tail |
| | 562 | (setq pattern (cons separator (cons (car (car tail)) pattern)) |
| | 563 | tail (cdr tail)))) |
| | 564 | (apply 'concat (nreverse (cdr pattern)))) |
| | 565 | "Regexp matching a Tibetan transcription of a composable Tibetan sequence. |
| | 566 | The result of matching is to be used for indexing alists at conversion |
| | 567 | from a roman transcription to the corresponding Tibetan character.") |
| | 568 | |
| | 569 | (defvar tibetan-precomposed-regexp |
| | 570 | (purecopy |
| | 571 | (let ((l tibetan-precomposed-transcription-alist) |
| | 572 | temp) |
| | 573 | (setq temp "^\\(") |
| | 574 | (setq temp |
| | 575 | (concat temp (car (car l)))) |
| | 576 | (setq l (cdr l)) |
| | 577 | (while l |
| | 578 | (setq temp |
| | 579 | (concat temp "\\|" (car (car l)))) |
| | 580 | (setq l (cdr l))) |
| | 581 | (concat temp "\\)"))) |
| | 582 | "Regexp string to match a romanized Tibetan complex consonant. |
| | 583 | The result of matching is to be used for indexing alists when the input key |
| | 584 | from an input method is converted to the corresponding precomposed glyph.") |
| | 585 | |
| | 586 | (defvar tibetan-precomposition-rule-regexp |
| | 587 | (purecopy |
| | 588 | (let ((l tibetan-precomposition-rule-alist) |
| | 589 | temp) |
| | 590 | (setq temp "\\(") |
| | 591 | (setq temp (concat temp (car (car l)))) |
| | 592 | (setq l (cdr l)) |
| | 593 | (while l |
| | 594 | (setq temp (concat temp "\\|" (car (car l)))) |
| | 595 | (setq l (cdr l))) |
| | 596 | (concat temp "\\)"))) |
| | 597 | "Regexp string to match a sequence of Tibetan consonantic components, i.e., |
| | 598 | one base consonant and one or more subjoined consonants. |
| | 599 | The result of matching is to be used for indexing alist when the component |
| | 600 | sequence is converted to the corresponding precomposed glyph. |
| | 601 | This also matches some punctuation characters which need conversion.") |
| | 602 | |
| | 603 | (defvar tibetan-decomposed nil) |
| | 604 | (defvar tibetan-decomposed-temp nil) |
| | 605 | |
| | 606 | ;; For automatic composition. |
| | 607 | (set-char-table-range |
| | 608 | composition-function-table '(#xF00 . #xFD1) |
| | 609 | (list (vector tibetan-composable-pattern 0 'font-shape-gstring))) |
| | 610 | |
| | 611 | (provide 'tibetan) |
| | 612 | |
| | 613 | ;;; tibetan.el ends here |
HCoop / bpt / emacs.git / blame_incremental