aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorKenichi Handa1997-04-05 02:44:02 +0000
committerKenichi Handa1997-04-05 02:44:02 +0000
commit80d75b56bda0ed49084e89550e0f310fedc76e5d (patch)
tree2a4c1d870fa33a7f1b0f5380b3c763999858b518
parent37cdc7adb331acefcdd51eada85049c2fda3e63f (diff)
downloademacs-80d75b56bda0ed49084e89550e0f310fedc76e5d.tar.gz
emacs-80d75b56bda0ed49084e89550e0f310fedc76e5d.zip
Initial revision
Diffstat
-rw-r--r--lisp/language/english.el74
-rw-r--r--lisp/language/tibet-util.el453
-rw-r--r--lisp/language/tibetan.el620
3 files changed, 1147 insertions, 0 deletions
diff --git a/lisp/language/english.el b/lisp/language/english.el
new file mode 100644
index 00000000000..e4ff06861ad
--- /dev/null
+++ b/lisp/language/english.el
@@ -0,0 +1,74 @@
1;;; english.el --- English support
2
3;; Copyright (C) 1997 Free Software Foundation, Inc.
4;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
5
6;; Keywords: multibyte character, character set, syntax, category
7
8;; This file is part of GNU Emacs.
9
10;; GNU Emacs is free software; you can redistribute it and/or modify
11;; it under the terms of the GNU General Public License as published by
12;; the Free Software Foundation; either version 2, or (at your option)
13;; any later version.
14
15;; GNU Emacs is distributed in the hope that it will be useful,
16;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18;; GNU General Public License for more details.
19
20;; You should have received a copy of the GNU General Public License
21;; along with GNU Emacs; see the file COPYING. If not, write to the
22;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23;; Boston, MA 02111-1307, USA.
24
25;;; Commentary:
26
27;; We need nothing special to support English on Emacs. Selecting
28;; English as a language environment is one of the ways to reset
29;; various multilingual environment to the original settting.
30
31;;; Code
32
33(defun setup-english-environment ()
34 "Reset MULE (multilingual environment) to the default status."
35 (interactive)
36 (setq-default enable-multibyte-characters t)
37 (if (local-variable-p 'enable-multibyte-characters)
38 (setq enable-multibyte-characters t))
39
40 (setq coding-category-internal 'internal
41 coding-category-iso-7 'iso-2022-7
42 coding-category-iso-8-1 'iso-8859-1
43 coding-category-iso-8-2 'iso-8859-1
44 coding-category-iso-else 'iso-8859-1
45 coding-category-sjis 'sjis
46 coding-category-big5 'big5
47 coding-category-binary 'no-conversion)
48
49 (set-coding-priority
50 '(coding-category-iso-7
51 coding-category-iso-8-2
52 coding-category-iso-8-1
53 coding-category-iso-else
54 coding-category-internal
55 coding-category-binary
56 coding-category-sjis
57 coding-category-big5))
58
59 (setq-default buffer-file-coding-system 'iso-8859-1)
60 (set-terminal-coding-system 'iso-8859-1)
61 (set-keyboard-coding-system 'iso-8859-1)
62 )
63
64(set-language-info-alist
65 "English" '((setup-function . setup-english-environment)
66 (tutorial . "TUTORIAL")
67 (charset . (ascii))
68 (documentation . t)
69 (sample-text . "Hello!, Hi!, How are you?")))
70
71(register-input-method "English"
72 '("quail-dvorak" quail-use-package "quail/latin"))
73
74;;; english.el ends here
diff --git a/lisp/language/tibet-util.el b/lisp/language/tibet-util.el
new file mode 100644
index 00000000000..cc4624e4014
--- /dev/null
+++ b/lisp/language/tibet-util.el
@@ -0,0 +1,453 @@
1;;; language/tibet-util.el -- Support for inputting Tibetan characters
2
3;; Copyright (C) 1995 Free Software Foundation, Inc.
4;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
5
6;; Keywords: multilingual, Tibetan
7
8;; This file is part of GNU Emacs.
9
10;; GNU Emacs is free software; you can redistribute it and/or modify
11;; it under the terms of the GNU General Public License as published by
12;; the Free Software Foundation; either version 2, or (at your option)
13;; any later version.
14
15;; GNU Emacs is distributed in the hope that it will be useful,
16;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18;; GNU General Public License for more details.
19
20;; You should have received a copy of the GNU General Public License
21;; along with GNU Emacs; see the file COPYING. If not, write to the
22;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23;; Boston, MA 02111-1307, USA.
24
25;; Author: Toru TOMABECHI, <Toru.Tomabechi@orient.unil.ch>
26
27;; Created: Feb. 17. 1997
28
29;; History:
30;; 1997.03.13 Modification in treatment of text properties;
31;; Support for some special signs and punctuations.
32
33;;; Code:
34
35;;; This function makes a transcription string for
36;;; re-composing a character.
37
38;;;###autoload
39(defun tibetan-tibetan-to-transcription (ch)
40 "Return a transcription string of Tibetan character CH"
41 (let ((char ch)
42 (l (append tibetan-consonant-transcription-alist
43 tibetan-vowel-transcription-alist
44 tibetan-precomposed-transcription-alist
45 tibetan-subjoined-transcription-alist))
46 decomp-l t-char trans str result)
47 (if (eq (char-charset char) 'composition)
48 (setq decomp-l (decompose-composite-char char 'list nil))
49 (setq decomp-l (cons char nil)))
50 (setq str "")
51 (while decomp-l
52 (setq t-char (char-to-string (car decomp-l)))
53 (setq trans (car (rassoc t-char l)))
54 (setq str (concat str trans))
55 (setq decomp-l (cdr decomp-l)))
56 (setq result str)))
57
58;;; This function translates transcription string into a string of
59;;; Tibetan characters.
60
61;;;###autoload
62(defun tibetan-transcription-to-tibetan (transcription)
63 "Translate Roman transcription into a sequence of Tibetan components."
64 (let ((trans transcription)
65 (lp tibetan-precomposed-transcription-alist)
66 (l (append tibetan-consonant-transcription-alist
67 tibetan-vowel-transcription-alist
68 tibetan-subjoined-transcription-alist))
69 (case-fold-search nil)
70 substr t-char p-str t-str result)
71 (setq substr "")
72 (setq p-str "")
73 (setq t-str "")
74 (cond ((string-match tibetan-precomposed-regexp trans)
75 (setq substr (substring trans (match-beginning 0) (match-end 0)))
76 (setq trans (substring trans (match-end 0)))
77 (setq t-char (cdr (assoc substr lp)))
78 (setq p-str t-char)))
79 (while (string-match tibetan-regexp trans)
80 (setq substr (substring trans (match-beginning 0) (match-end 0)))
81 (setq trans (substring trans 0 (match-beginning 0)))
82 (setq t-char
83 (cdr (assoc substr l)))
84 (setq t-str (concat t-char t-str)))
85 (setq result (concat p-str t-str))))
86
87
88;;;
89;;; Functions for composing Tibetan character.
90;;;
91;;; A Tibetan syllable is typically structured as follows:
92;;;
93;;; [Prefix] C [C+] V [M] [Suffix [Post suffix]]
94;;;
95;;; where C's are all vertically stacked, V appears below or above
96;;; consonant cluster and M is always put above the C[C+]V combination.
97;;; (Sanskrit visarga, though it is a vowel modifier, is considered
98;;; to be a punctuation.)
99;;;
100;;; Here are examples of the words "bsgrubs" and "h'uM"
101;;;
102;;; $(7"72%q`"U1"7"G(B 2$(7"H`#A`"U0"_1(B
103;;;
104;;; M
105;;; b s b s h
106;;; g '
107;;; r u
108;;; u
109;;;
110;;; Consonants ''', 'w', 'y', 'r' take special forms when they are used
111;;; as subjoined consonant. Consonant 'r' takes another special form
112;;; when used as superjoined as in "rka", and so on, while it does not
113;;; change its form when conjoined with subjoined ''', 'w' or 'y'
114;;; as in "rwa", "rya".
115;;;
116;;;
117;;; As a Tibetan input method should avoid using conversion key,
118;;; we use a "Tibetan glyph -> transcription -> Tibetan glyph"
119;;; translation at each key input.
120;;;
121;;; 1st stage - Check the preceding char.
122;;; If the preceding char is Tibetan and composable, then
123;;;
124;;; 2nd stage - Translate the preceding char into transcription
125;;;
126;;; 3rd stage - Concatenate the transcription of preceding char
127;;; and the current input key.
128;;;
129;;; 4th stage - Re-translate the concatenated transcription into
130;;; a sequence of Tibetan letters.
131;;;
132;;; 5th stage - Convert leading consonants into one single precomposed char
133;;; if possible.
134;;;
135;;; 6th stage - Compose the consonants into one composite glyph.
136;;;
137;;; (If the current input is a vowel sign or a vowel modifier,
138;;; then it is composed with preceding char without checking
139;;; except when the preceding char is a punctuation or a digit.)
140;;;
141;;;
142
143;;; This function is used to avoid composition
144;;; between Tibetan and non-Tibetan chars.
145
146;;;###autoload
147(defun tibetan-char-examin (ch)
148 "Check if char CH is Tibetan character.
149Returns non-nil if CH is Tibetan. Otherwise, returns nil."
150 (let ((chr ch))
151 (if (eq (char-charset chr) 'composition)
152 (string-match "\\cq+" (decompose-composite-char chr))
153 (string-match "\\cq" (char-to-string chr)))))
154
155;;; This is used to avoid composition between digits, signs, punctuations
156;;; and word constituents.
157
158;;;###autoload
159(defun tibetan-composable-examin (ch)
160 "Check if Tibetan char CH is composable.
161Returns t if CH is a composable char \(i.e. neither punctuation nor digit)."
162 (let ((chr ch)
163 chstr)
164 (if (eq (char-charset chr) 'composition)
165 (setq chstr (decompose-composite-char chr))
166 (setq chstr (char-to-string chr)))
167 (not (string-match "[$(7!1(B-$(7!o"f$(8!;!=!?!@!A!D"`(B]" chstr))))
168
169
170;;; This checks if a character to be composed contains already
171;;; one or more vowels / vowel modifiers. If the character contains
172;;; them, then no more consonant should be added.
173
174;;;###autoload
175(defun tibetan-complete-char-examin (ch)
176 "Check if composite char CH contains one or more vowel/vowel modifiers.
177Returns non-nil, if CH contains vowel/vowel modifiers."
178 (let ((chr ch)
179 chstr)
180 (if (eq (char-charset chr) 'composition)
181 (setq chstr (decompose-composite-char chr))
182 (setq chstr (char-to-string chr)))
183 (string-match "[$(7!g!e"Q(B-$(7"^"_(B-$(7"l(B]" chstr)))
184
185;;; This function makes a composite character consisting of two characters
186;;; vertically stacked.
187
188;;;###autoload
189(defun tibetan-vertical-stacking (first second upward)
190 "Return a vertically stacked composite char consisting of FIRST and SECOND.
191If UPWARD is non-nil, then SECOND is put above FIRST."
192 (if upward
193 (compose-chars first '(tc . bc) second)
194 (compose-chars first '(bc . tc) second)))
195
196;;; This function makes a composite char from a string.
197;;; Note that this function returns a string, not a char.
198
199;;;###autoload
200(defun tibetan-compose-string (str)
201 "Compose a sequence of Tibetan character components into a composite character.
202Returns a string containing a composite character."
203 (let ((t-str str)
204 f-str s-str f-ch s-ch rest composed result)
205 ;;Make sure no redundant vowel sign is present.
206 (if (string-match
207 "^\\(.+\\)\\($(7"Q(B\\)\\([$(7!I!g!e"Q(B-$(7"^"_(B-$(7"l(B]\\)" t-str)
208 (setq t-str (concat
209 (match-string 1 t-str)
210 (match-string 3 t-str))))
211 (if (string-match
212 "^\\(.+\\)\\([$(7!I!g!e"Q(B-$(7"^"_(B-$(7"l(B]\\)\\($(7"Q(B\\)" t-str)
213 (setq t-str (concat
214 (match-string 1 t-str)
215 (match-string 2 t-str))))
216 ;;Start conversion.
217 (setq result "")
218 ;; Consecutive base/precomposed consonants are reduced to the last one.
219 (while (string-match "^\\([$(7"!(B-$(7"J$!(B-$(7%u(B]\\)\\([$(7"!(B-$(7"@"B(B-$(7"J$!(B-$(7%u(B].*\\)" t-str)
220 (setq result (concat result (match-string 1 t-str)))
221 (setq t-str (match-string 2 t-str)))
222 ;; Vowel/vowel modifier, subjoined consonants are added one by one
223 ;; to the preceding element.
224 (while
225 (string-match "^\\(.\\)\\([$(7"A#!(B-$(7#J!I!g!e"Q(B-$(7"^"_(B-$(7"l(B]\\)\\(.*\\)" t-str)
226 (setq f-str (match-string 1 t-str))
227 (setq f-ch (string-to-char f-str))
228 (setq s-str (match-string 2 t-str))
229 ;;Special treatment for 'a chung.
230 ;;If 'a follows a consonant, then turned into its subjoined form.
231 (if (and (string-match "$(7"A(B" s-str)
232 (not (tibetan-complete-char-examin f-ch)))
233 (setq s-str "$(7#A(B"))
234 (setq s-ch (string-to-char s-str))
235 (setq rest (match-string 3 t-str))
236 (cond ((string-match "\\c2" s-str);; upper vowel sign
237 (setq composed
238 (tibetan-vertical-stacking f-ch s-ch t)))
239 ((string-match "\\c3" s-str);; lower vowel sign
240 (setq composed
241 (tibetan-vertical-stacking f-ch s-ch nil)))
242 ;;Automatic conversion of ra-mgo (superscribed r).
243 ;;'r' is converted if followed by a subjoined consonant
244 ;;other than w, ', y, r.
245 ((and (string-match "$(7"C(B" f-str)
246 (not (string-match "[$(7#>#A#B#C(B]" s-str)))
247 (setq f-ch ?$(7#P(B)
248 (setq composed
249 (tibetan-vertical-stacking f-ch s-ch nil)))
250 ((not (tibetan-complete-char-examin f-ch))
251 ;;Initial base consonant is tranformed, if followed by
252 ;;a subjoined consonant, except when it is followed
253 ;;by a subscribed 'a.
254 (if (and (string-match "[$(7"!(B-$(7"="?"@"D(B-$(7"J(B]" f-str)
255 (not (string-match "$(7#A(B" s-str)))
256 (setq f-ch
257 (string-to-char
258 (cdr (assoc f-str tibetan-base-to-subjoined-alist)))))
259 (setq composed
260 (tibetan-vertical-stacking f-ch s-ch nil)))
261 (t
262 (setq composed s-str)
263 (setq result (concat result f-str))))
264 (setq t-str (concat composed rest)))
265 (setq result (concat result t-str))))
266
267;;; quail <-> conversion interface.
268
269(defun tibetan-composition (pc key)
270 "Interface to quail input method.
271Takes two arguments: char PC and string KEY, where PC is the preceding
272character to be composed with current input KEY.
273Returns a string which is the result of composition."
274 (let (trans cur-ch t-str result)
275 ;; Make a tibetan character corresponding to current input key.
276 (setq cur-ch (tibetan-transcription-to-tibetan key))
277 ;; Check if the preceding character is Tibetan and composable.
278 (cond ((and (tibetan-char-examin pc)
279 (tibetan-composable-examin pc))
280 ;;If Tibetan char corresponding to the current input key exists,
281 (cond (cur-ch
282 ;; Then,
283 ;; Convert the preceding character into transcription,
284 ;; and concatenate it with the current input key,
285 (setq trans (tibetan-tibetan-to-transcription pc))
286 (setq trans (concat trans key))
287 ;; Concatenated transcription is converted to
288 ;; a sequence of Tibetan characters,
289 (setq t-str (tibetan-transcription-to-tibetan trans))
290 ;; And it is composed into a composite character.
291 (setq result (tibetan-compose-string t-str)))
292 ;; Else,
293 (t
294 ;; Simply concatenate the preceding character and
295 ;; the current input key.
296 (setq result (char-to-string pc))
297 (setq result (concat result key)))))
298 ;; If the preceding char is not Tibetan or not composable,
299 (t
300 ;; pc = 0 means the point is at the beginning of buffer.
301 (if (not (eq pc 0))
302 (setq result (char-to-string pc)))
303 (if cur-ch
304 (setq result (concat result cur-ch))
305 (setq result (concat result key))))
306 )))
307
308
309;;;###autoload
310(defun tibetan-decompose-region (beg end)
311 "Decompose Tibetan characters in the region BEG END into their components.
312Components are: base and subjoined consonants, vowel signs, vowel modifiers.
313One column punctuations are converted to their 2 column equivalents."
314 (interactive "r")
315 (let (ch-str ch-beg ch-end)
316 (save-excursion
317 (save-restriction
318 (narrow-to-region beg end)
319 (goto-char (point-min))
320 ;; \\cq = Tibetan character
321 (while (re-search-forward "\\cq" nil t)
322 (setq ch-str (buffer-substring-no-properties
323 (match-beginning 0) (match-end 0)))
324 ;; Save the points. Maybe, using save-match-data is preferable.
325 ;; But in order not to lose the trace(because the body is too long),
326 ;; we save the points in variables.
327 (setq ch-beg (match-beginning 0))
328 (setq ch-end (match-end 0))
329 ;; Here starts the decomposition.
330 (cond
331 ;; 1 column punctuations -> 2 column equivalent
332 ((string-match "[$(8!D!;!=!?!@!A"`(B]" ch-str)
333 (setq ch-str
334 (car (rassoc ch-str tibetan-precomposition-rule-alist))))
335 ;; Decomposition of composite character.
336 ((eq (char-charset (string-to-char ch-str)) 'composition)
337 ;; Make a string which consists of a sequence of
338 ;; components.
339 (setq ch-str (decompose-composite-char (string-to-char ch-str)))
340 ;; Converts nyi zla into base elements.
341 (cond ((string= ch-str "$(7#R#S#S#S(B")
342 (setq ch-str "$(7!4!5!5(B"))
343 ((string= ch-str "$(7#R#S#S(B")
344 (setq ch-str "$(7!4!5(B"))
345 ((string= ch-str "$(7#R#S!I(B")
346 (setq ch-str "$(7!6(B"))
347 ((string= ch-str "$(7#R#S(B")
348 (setq ch-str "$(7!4(B")))))
349 ;; If the sequence of components starts with a subjoined consonants,
350 (if (string-match "^\\([$(7#!(B-$(7#J(B]\\)\\(.*\\)$" ch-str)
351 ;; then the first components is converted to its base form.
352 (setq ch-str
353 (concat (car (rassoc (match-string 1 ch-str)
354 tibetan-base-to-subjoined-alist))
355 (match-string 2 ch-str))))
356 ;; If the sequence of components starts with a precomposed character,
357 (if (string-match "^\\([$(7$!(B-$(7%u(B]\\)\\(.*\\)$" ch-str)
358 ;; then it is converted into a sequence of components.
359 (setq ch-str
360 (concat (car (rassoc (match-string 1 ch-str)
361 tibetan-precomposition-rule-alist))
362 (match-string 2 ch-str))))
363 ;; Special treatment for superscribed r.
364 (if (string-match "^$(7#P(B\\(.*\\)$" ch-str)
365 (setq ch-str (concat "$(7"C(B" (match-string 1 ch-str))))
366 ;; Finally, the result of decomposition is inserted, and
367 ;; the composite character is deleted.
368 (insert-and-inherit ch-str)
369 (delete-region ch-beg ch-end))))))
370
371;;;###autoload
372(defun tibetan-compose-region (beg end)
373 "Make composite chars from Tibetan character components in the region BEG END.
374Two column punctuations are converted to their 1 column equivalents."
375 (interactive "r")
376 (let (str result)
377 (save-excursion
378 (save-restriction
379 (narrow-to-region beg end)
380 (goto-char (point-min))
381 ;; First, sequence of components which has a precomposed equivalent
382 ;; is converted.
383 (while (re-search-forward
384 tibetan-precomposition-rule-regexp nil t)
385 (setq str (buffer-substring-no-properties
386 (match-beginning 0) (match-end 0)))
387 (save-match-data
388 (insert-and-inherit
389 (cdr (assoc str tibetan-precomposition-rule-alist))))
390 (delete-region (match-beginning 0) (match-end 0)))
391 (goto-char (point-min))
392 ;; Then, composable elements are put into a composite character.
393 (while (re-search-forward
394 "[$(7"!(B-$(7"J$!(B-$(7%u(B]+[$(7#!(B-$(7#J!I!g!e"Q(B-$(7"^"_(B-$(7"l(B]+"
395 nil t)
396 (setq str (buffer-substring-no-properties
397 (match-beginning 0) (match-end 0)))
398 (save-match-data
399 (setq result (tibetan-compose-string str))
400 (insert-and-inherit result))
401 (delete-region (match-beginning 0) (match-end 0)))))))
402
403;;;
404;;; This variable is used to avoid repeated decomposition.
405;;;
406(setq-default tibetan-decomposed nil)
407
408;;;###autoload
409(defun tibetan-decompose-buffer ()
410 "Decomposes Tibetan characters in the buffer into their components.
411See also docstring of the function tibetan-decompose-region."
412 (interactive)
413 (make-local-variable 'tibetan-decomposed)
414 (cond ((not tibetan-decomposed)
415 (tibetan-decompose-region (point-min) (point-max))
416 (setq tibetan-decomposed t))))
417
418;;;###autoload
419(defun tibetan-compose-buffer ()
420 "Composes Tibetan character components in the buffer.
421See also docstring of the function tibetan-compose-region."
422 (interactive)
423 (make-local-variable 'tibetan-decomposed)
424 (tibetan-compose-region (point-min) (point-max))
425 (setq tibetan-decomposed nil))
426
427;;;###autoload
428(defun tibetan-post-read-conversion (len)
429 (save-excursion
430 (save-restriction
431 (let ((buffer-modified-p (buffer-modified-p)))
432 (narrow-to-region (point) (+ (point) len))
433 (tibetan-compose-region (point-min) (point-max))
434 (set-buffer-modified-p buffer-modified-p)
435 (point-max))))
436 (make-local-variable 'tibetan-decomposed)
437 (setq tibetan-decomposed nil))
438
439
440;;;###autoload
441(defun tibetan-pre-write-conversion (from to)
442 (setq tibetan-decomposed-temp tibetan-decomposed)
443 (let ((old-buf (current-buffer))
444 (work-buf (get-buffer-create " *tibetan-work*")))
445 (set-buffer work-buf)
446 (erase-buffer)
447 (insert-buffer-substring old-buf from to)
448 (if (not tibetan-decomposed-temp)
449 (tibetan-decompose-region (point-min) (point-max)))))
450
451(provide 'language/tibet-util)
452
453;;; language/tibet-util.el ends here.
diff --git a/lisp/language/tibetan.el b/lisp/language/tibetan.el
new file mode 100644
index 00000000000..d54689119c6
--- /dev/null
+++ b/lisp/language/tibetan.el
@@ -0,0 +1,620 @@
1;;; tibetan.el --- Support for Tibetan language
2
3;; Copyright (C) 1997 Free Software Foundation, Inc.
4;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
5
6;; Keywords: multilingual, Tibetan
7
8;; This file is part of GNU Emacs.
9
10;; GNU Emacs is free software; you can redistribute it and/or modify
11;; it under the terms of the GNU General Public License as published by
12;; the Free Software Foundation; either version 2, or (at your option)
13;; any later version.
14
15;; GNU Emacs is distributed in the hope that it will be useful,
16;; but WITHOUT ANY WARRANTY; without even the implied warranty of
17;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
18;; GNU General Public License for more details.
19
20;; You should have received a copy of the GNU General Public License
21;; along with GNU Emacs; see the file COPYING. If not, write to the
22;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
23;; Boston, MA 02111-1307, USA.
24
25;; Author: Toru TOMABECHI, <Toru.Tomabechi@orient.unil.ch>
26
27;; Created: Feb. 17. 1997
28
29;; History:
30;; 1997.03.13 Modification for special signs and punctuations.
31
32;;; Code:
33
34(define-category ?q "Tibetan")
35(modify-category-entry (make-char 'tibetan) ?q)
36(modify-category-entry (make-char 'tibetan-1-column) ?q)
37
38(let ((row 33))
39 (while (< row 38)
40 (modify-category-entry (make-char 'tibetan row) ?q)
41 (setq row (1+ row))))
42
43(modify-category-entry (make-char 'tibetan-1-column 33) ?q)
44
45(let ((deflist '(;; chars syntax category
46 ("$(7"!(B-$(7"J(B" "w" ?0) ; consonant
47 ("$(7#!(B-$(7#J#P#Q(B" "w" ?0) ;
48 ("$(7$!(B-$(7$e(B" "w" ?0) ;
49 ("$(7%!(B-$(7%u(B" "w" ?0) ;
50 ("$(7"S"["\"]"^"a(B" "w" ?2) ; upper vowel
51 ("$(7"_"c"d"g"h"i"j"k"l(B" "w" ?2) ; upper modifier
52 ("$(7!I"Q"U"e!e!g(B" "w" ?3) ; lowel vowel/modifier
53 ("$(7!P(B-$(7!Y!Z(B-$(7!c(B" "w" ?6) ; digit
54 ("$(7!;!=(B-$(7!B!D"`(B" "." ?|) ; line-break char
55 ("$(8!;!=!?!@!A!D"`(B" "." ?|) ;
56 ("$(7!8!;!=(B-$(7!B!D"`!m!d(B" "." ?>) ; prohibition
57 ("$(8!;!=!?!@!A!D"`(B" "." ?>) ;
58 ("$(7!0(B-$(7!:!l#R#S"f(B" "." ?<) ; prohibition
59 ("$(7!C!E(B-$(7!H!J(B-$(7!O!f!h(B-$(7!k!n!o(B" "." ?q) ; others
60 ))
61 elm chars len syntax category to ch i)
62 (while deflist
63 (setq elm (car deflist))
64 (setq chars (car elm)
65 len (length chars)
66 syntax (nth 1 elm)
67 category (nth 2 elm)
68 i 0)
69 (while (< i len)
70 (if (= (aref chars i) ?-)
71 (setq i (1+ i)
72 to (sref chars i))
73 (setq ch (sref chars i)
74 to ch))
75 (while (<= ch to)
76 (modify-syntax-entry ch syntax)
77 (modify-category-entry ch category)
78 (setq ch (1+ ch)))
79 (setq i (+ i (char-bytes to))))
80 (setq deflist (cdr deflist))))
81
82
83;;; Tibetan Character set.
84;;; \x2130 -- \x234a is a subset of Unicode v.2 \x0f00 - \x0fb9
85;;; with a slight modification. And there are some subjoined
86;;; consonants which are not specified in Unicode.
87;;; I hope I can add missing characters later.
88;;;
89;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
90;;;2120 // $(7!!(B $(7!"(B $(7!#(B $(7!$(B $(7!%(B $(7!&(B $(7!'(B $(7!((B $(7!)(B $(7!*(B $(7!+(B $(7!,(B $(7!-(B $(7!.(B $(7!/(B ;
91;;;2130 $(7!0(B $(7!1(B $(7!2(B $(7!3(B $(7!4(B $(7!5(B $(7!6(B $(7!7(B $(7!8(B $(7!9(B $(7!:(B $(7!;(B $(7!<(B $(7!=(B $(7!>(B $(7!?(B ; Punctuations,
92;;;2140 $(7!@(B $(7!A(B $(7!B(B $(7!C(B $(7!D(B $(7!E(B $(7!F(B $(7!G(B $(7!H(B $(7!I(B $(7!J(B $(7!K(B $(7!L(B $(7!M(B $(7!N(B $(7!O(B ; Digits and
93;;;2150 $(7!P(B $(7!Q(B $(7!R(B $(7!S(B $(7!T(B $(7!U(B $(7!V(B $(7!W(B $(7!X(B $(7!Y(B $(7!Z(B $(7![(B $(7!\(B $(7!](B $(7!^(B $(7!_(B ; Special signs.
94;;;2160 $(7!`(B $(7!a(B $(7!b(B $(7!c(B $(7!d(B $(7!e(B $(7!f(B $(7!g(B $(7!h(B $(7!i(B $(7!j(B $(7!k(B $(7!l(B $(7!m(B $(7!n(B $(7!o(B ;
95;;;2170 $(7!p(B $(7!q(B $(7!r(B $(7!s(B $(7!t(B $(7!u(B $(7!v(B $(7!w(B $(7!x(B $(7!y(B $(7!z(B $(7!{(B $(7!|(B $(7!}(B $(7!~(B // ;
96;;;
97;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
98;;;2220 // $(7"!(B $(7""(B $(7"#(B $(7"$(B $(7"%(B $(7"&(B $(7"'(B $(7"((B $(7")(B $(7"*(B $(7"+(B $(7",(B $(7"-(B $(7".(B $(7"/(B ; Base consonants
99;;;2230 $(7"0(B $(7"1(B $(7"2(B $(7"3(B $(7"4(B $(7"5(B $(7"6(B $(7"7(B $(7"8(B $(7"9(B $(7":(B $(7";(B $(7"<(B $(7"=(B $(7">(B $(7"?(B ; and
100;;;2240 $(7"@(B $(7"A(B $(7"B(B $(7"C(B $(7"D(B $(7"E(B $(7"F(B $(7"G(B $(7"H(B $(7"I(B $(7"J(B $(7"K(B $(7"L(B $(7"M(B $(7"N(B $(7"O(B ; Vowel signs.
101;;;2250 $(7"P(B $(7"Q(B $(7"R(B $(7"S(B $(7"T(B $(7"U(B $(7"V(B $(7"W(B $(7"X(B $(7"Y(B $(7"Z(B $(7"[(B $(7"\(B $(7"](B $(7"^(B $(7"_(B ; (\x2251 = vowel a)
102;;;2260 $(7"`(B $(7"a(B $(7"b(B $(7"c(B $(7"d(B $(7"e(B $(7"f(B $(7"g(B $(7"h(B $(7"i(B $(7"j(B $(7"k(B $(7"l(B $(7"m(B $(7"n(B $(7"o(B ; Long vowels and
103;;;2270 $(7"p(B $(7"q(B $(7"r(B $(7"s(B $(7"t(B $(7"u(B $(7"v(B $(7"w(B $(7"x(B $(7"y(B $(7"z(B $(7"{(B $(7"|(B $(7"}(B $(7"~(B // ; vocalic r, l are
104;;; ; not atomically
105;;; ; encoded.
106;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
107;;;2320 // $(7#!(B $(7#"(B $(7##(B $(7#$(B $(7#%(B $(7#&(B $(7#'(B $(7#((B $(7#)(B $(7#*(B $(7#+(B $(7#,(B $(7#-(B $(7#.(B $(7#/(B ; Subjoined consonants
108;;;2330 $(7#0(B $(7#1(B $(7#2(B $(7#3(B $(7#4(B $(7#5(B $(7#6(B $(7#7(B $(7#8(B $(7#9(B $(7#:(B $(7#;(B $(7#<(B $(7#=(B $(7#>(B $(7#?(B ;
109;;;2340 $(7#@(B $(7#A(B $(7#B(B $(7#C(B $(7#D(B $(7#E(B $(7#F(B $(7#G(B $(7#H(B $(7#I(B $(7#J(B $(7#K(B $(7#L(B $(7#M(B $(7#N(B $(7#O(B ; 'a chung (\x2341)is
110;;; ; here,
111;;; ; while in Unicode
112;;; ; it is classified
113;;; ; as a vowel sign
114;;; ; (\x0f71).
115;;;
116;;;2350 $(7#P(B $(7#Q(B $(7#R(B $(7#S(B $(7#T(B $(7#U(B $(7#V(B $(7#W(B $(7#X(B $(7#Y(B $(7#Z(B $(7#[(B $(7#\(B $(7#](B $(7#^(B $(7#_(B ; Hereafter, the chars
117;;;2360 $(7#`(B $(7#a(B $(7#b(B $(7#c(B $(7#d(B $(7#e(B $(7#f(B $(7#g(B $(7#h(B $(7#i(B $(7#j(B $(7#k(B $(7#l(B $(7#m(B $(7#n(B $(7#o(B ; are not specified
118;;;2370 $(7#p(B $(7#q(B $(7#r(B $(7#s(B $(7#t(B $(7#u(B $(7#v(B $(7#w(B $(7#x(B $(7#y(B $(7#z(B $(7#{(B $(7#|(B $(7#}(B $(7#~(B // ; in Unicode.
119;;; ; The character \x2351
120;;; ; is not used in our
121;;; ; implementation.
122;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
123;;;2420 // $(7$!(B $(7$"(B $(7$#(B $(7$$(B $(7$%(B $(7$&(B $(7$'(B $(7$((B $(7$)(B $(7$*(B $(7$+(B $(7$,(B $(7$-(B $(7$.(B $(7$/(B ; Precomposed
124;;;2430 $(7$0(B $(7$1(B $(7$2(B $(7$3(B $(7$4(B $(7$5(B $(7$6(B $(7$7(B $(7$8(B $(7$9(B $(7$:(B $(7$;(B $(7$<(B $(7$=(B $(7$>(B $(7$?(B ; consonants for
125;;;2440 $(7$@(B $(7$A(B $(7$B(B $(7$C(B $(7$D(B $(7$E(B $(7$F(B $(7$G(B $(7$H(B $(7$I(B $(7$J(B $(7$K(B $(7$L(B $(7$M(B $(7$N(B $(7$O(B ; ordinary Tibetan.
126;;;2450 $(7$P(B $(7$Q(B $(7$R(B $(7$S(B $(7$T(B $(7$U(B $(7$V(B $(7$W(B $(7$X(B $(7$Y(B $(7$Z(B $(7$[(B $(7$\(B $(7$](B $(7$^(B $(7$_(B ; They are decomposed
127;;;2460 $(7$`(B $(7$a(B $(7$b(B $(7$c(B $(7$d(B $(7$e(B $(7$f(B $(7$g(B $(7$h(B $(7$i(B $(7$j(B $(7$k(B $(7$l(B $(7$m(B $(7$n(B $(7$o(B ; into base and
128;;;2470 $(7$p(B $(7$q(B $(7$r(B $(7$s(B $(7$t(B $(7$u(B $(7$v(B $(7$w(B $(7$x(B $(7$y(B $(7$z(B $(7${(B $(7$|(B $(7$}(B $(7$~(B // ; subjoined consonants
129;;; ; when written on a
130;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F ; file in Tibetan
131;;;2520 // $(7%!(B $(7%"(B $(7%#(B $(7%$(B $(7%%(B $(7%&(B $(7%'(B $(7%((B $(7%)(B $(7%*(B $(7%+(B $(7%,(B $(7%-(B $(7%.(B $(7%/(B ; coding system.
132;;;2530 $(7%0(B $(7%1(B $(7%2(B $(7%3(B $(7%4(B $(7%5(B $(7%6(B $(7%7(B $(7%8(B $(7%9(B $(7%:(B $(7%;(B $(7%<(B $(7%=(B $(7%>(B $(7%?(B ;
133;;;2540 $(7%@(B $(7%A(B $(7%B(B $(7%C(B $(7%D(B $(7%E(B $(7%F(B $(7%G(B $(7%H(B $(7%I(B $(7%J(B $(7%K(B $(7%L(B $(7%M(B $(7%N(B $(7%O(B ;
134;;;2550 $(7%P(B $(7%Q(B $(7%R(B $(7%S(B $(7%T(B $(7%U(B $(7%V(B $(7%W(B $(7%X(B $(7%Y(B $(7%Z(B $(7%[(B $(7%\(B $(7%](B $(7%^(B $(7%_(B ;
135;;;2560 $(7%`(B $(7%a(B $(7%b(B $(7%c(B $(7%d(B $(7%e(B $(7%f(B $(7%g(B $(7%h(B $(7%i(B $(7%j(B $(7%k(B $(7%l(B $(7%m(B $(7%n(B $(7%o(B ;
136;;;2570 $(7%p(B $(7%q(B $(7%r(B $(7%s(B $(7%t(B $(7%u(B $(7%v(B $(7%w(B $(7%x(B $(7%y(B $(7%z(B $(7%{(B $(7%|(B $(7%}(B $(7%~(B // ;
137;;;
138
139
140(make-coding-system
141 'tibetan 2 ?Q
142 "Coding-system used for ASCII(MSB=0) & TIBETAN(MSB=1)."
143 '((ascii t) (tibetan t) nil nil
144 nil ascii-eol))
145
146(put 'tibetan 'post-read-conversion 'tibetan-post-read-conversion)
147(put 'tibetan 'pre-write-conversion 'tibetan-pre-write-conversion)
148
149(register-input-method
150 "Tibetan" '("quail-tibetan-wylie" quail-use-package "quail/tibetan"))
151(register-input-method
152 "Tibetan" '("quail-tibetan-tibkey" quail-use-package "quail/tibetan"))
153
154(defun setup-tibetan-environment ()
155 (setq coding-category-iso-7 'tibetan)
156
157 (set-coding-priority
158 '(coding-category-iso-7
159 coding-category-iso-8-1))
160
161 (setq-default buffer-file-coding-system 'iso-2022-7)
162
163 (setq default-input-method '("Tibetan" . "quail-tibetan-wylie")))
164
165(set-language-info-alist
166 "Tibetan" '((setup-function . setup-tibetan-environment)
167 (charset . (tibetan tibetan-1-column))
168 (coding-system . (tibetan))
169 (documentation . t)
170 (sample-text .
171"Tibetan (2$(7"70"]1"2$(8!;2$(7%P`"Q1"2$(8!;(B) 2$(7#RP#SP#S1!>"72$P`"Q1$(8!;2$(7"E0"S1"G$(8!;$(7"72"20"[1$(8!;2$(7"D0"[1"#"G!>2"I0"]0"_1$(8!;2$(7"9`"Q1$(8!;2$(7"/0"S1$(8!;2$(7"5`"Q12#2`#90"[1$(8!;2$(7"H`#A`"U0"c1!>(B")))
172
173
174;;;
175;;; Definitions of conversion data.
176;;;
177
178
179;;; alists for tibetan char <-> transcription conversion
180;;; longer transcription should come first
181(defconst tibetan-consonant-transcription-alist
182 '(("tsh" . "$(7";(B")
183 ("dzh" . "$(7"=(B")
184 ("kSH" . "$(7"J(B")
185 ("kh" . "$(7""(B")
186 ("gh" . "$(7"$(B")
187 ("ng" . "$(7"%(B")
188 ("ch" . "$(7"'(B")
189 ("ny" . "$(7"*(B")
190 ("TH" . "$(7",(B")
191 ("DH" . "$(7".(B")
192 ("th" . "$(7"1(B")
193 ("dh" . "$(7"3(B")
194 ("ph" . "$(7"6(B")
195 ("bh" . "$(7"8(B")
196 ("ts" . "$(7":(B")
197 ("dz" . "$(7"<(B")
198 ("zh" . "$(7"?(B")
199 ("sh" . "$(7"E(B")
200 ("SH" . "$(7"F(B")
201 ("k" . "$(7"!(B")
202 ("g" . "$(7"#(B")
203 ("c" . "$(7"&(B")
204 ("j" . "$(7"((B")
205 ("T" . "$(7"+(B")
206 ("D" . "$(7"-(B")
207 ("N" . "$(7"/(B")
208 ("t" . "$(7"0(B")
209 ("d" . "$(7"2(B")
210 ("n" . "$(7"4(B")
211 ("p" . "$(7"5(B")
212 ("b" . "$(7"7(B")
213 ("m" . "$(7"9(B")
214 ("w" . "$(7">(B")
215 ("z" . "$(7"@(B")
216 ("'" . "$(7"A(B")
217 ("y" . "$(7"B(B")
218 ("r" . "$(7"C(B")
219 ("l" . "$(7"D(B")
220 ("s" . "$(7"G(B")
221 ("h" . "$(7"H(B")
222 ("H" . "$(7"H(B")
223 ("A" . "$(7"I(B")))
224
225
226(defconst tibetan-vowel-transcription-alist
227 '(("ai" . "$(7"\(B")
228 ("au" . "$(7"^(B")
229 ("ee" . "$(7"\(B")
230 ("oo" . "$(7"^(B")
231 ("a" . "$(7"Q(B") ; invisible vowel sign (\x2251)
232 ("i" . "$(7"S(B")
233 ("u" . "$(7"U(B")
234 ("e" . "$(7"[(B")
235 ("o" . "$(7"](B")
236 ("E" . "$(7"\(B")
237 ("O" . "$(7"^(B")
238 ("I" . "$(7"a(B")
239 ("M" . "$(7"_(B")
240 ("~" . "$(7"c(B") ; not specified in Ext.wylie
241 ("`" . "$(7"d(B") ; idem.
242 ("," . "$(7"e(B") ; idem.
243 ("v" . "$(7"g(B") ; idem.
244 ("V" . "$(7"h(B") ; idem.
245 ("x" . "$(7"i(B") ; idem.
246 ("X" . "$(7"j(B") ; idem.
247 ("q" . "$(7"k(B") ; idem.
248 ("Q" . "$(7"l(B") ; idem.
249 ("_o" . "$(7!g(B") ; idem.
250 ("_O" . "$(7!e(B") ; idem.
251 ("_/" . "$(7!I(B") ; idem.
252 ))
253
254(defconst tibetan-precomposed-transcription-alist
255 '(("phyw" . "$(7$G(B")
256 ("tshw" . "$(7$)(B")
257 ("rtsw" . "$(7%.(B")
258 ("khw" . "$(7$"(B")
259 ("nyw" . "$(7$%(B")
260 ("tsw" . "$(7$((B")
261 ("zhw" . "$(7$*(B")
262 ("shw" . "$(7$.(B")
263 ("khy" . "$(7$A(B")
264 ("phy" . "$(7$D(B")
265 ("khr" . "$(7$Q(B")
266 ("thr" . "$(7$T(B")
267 ("phr" . "$(7$W(B")
268 ("shr" . "$(7$Z(B")
269 ("dzr" . "$(7$^(B")
270 ("grw" . "$(7$_(B")
271 ("rng" . "$(7%#(B")
272 ("rny" . "$(7%%(B")
273 ("rts" . "$(7%+(B")
274 ("rdz" . "$(7%,(B")
275 ("rgw" . "$(7%-(B")
276 ("rky" . "$(7%0(B")
277 ("rgy" . "$(7%1(B")
278 ("rmy" . "$(7%2(B")
279 ("lng" . "$(7%B(B")
280 ("sng" . "$(7%R(B")
281 ("sny" . "$(7%S(B")
282 ("sts" . "$(7%Z(B")
283 ("sky" . "$(7%`(B")
284 ("sgy" . "$(7%a(B")
285 ("spy" . "$(7%b(B")
286 ("sby" . "$(7%c(B")
287 ("smy" . "$(7%d(B")
288 ("skr" . "$(7%p(B")
289 ("sgr" . "$(7%q(B")
290 ("snr" . "$(7%r(B")
291 ("spr" . "$(7%s(B")
292 ("sbr" . "$(7%t(B")
293 ("smr" . "$(7%u(B")
294 ("kw" . "$(7$!(B")
295 ("gw" . "$(7$#(B")
296 ("cw" . "$(7$$(B")
297 ("tw" . "$(7$&(B")
298 ("dw" . "$(7$'(B")
299 ("zw" . "$(7$+(B")
300 ("rw" . "$(7$,(B")
301 ("lw" . "$(7$-(B")
302 ("sw" . "$(7$/(B")
303 ("hw" . "$(7$0(B")
304 ("ky" . "$(7$@(B")
305 ("gy" . "$(7$B(B")
306 ("py" . "$(7$C(B")
307 ("by" . "$(7$E(B")
308 ("my" . "$(7$F(B")
309 ("kr" . "$(7$P(B")
310 ("gr" . "$(7$R(B")
311 ("tr" . "$(7$S(B")
312 ("dr" . "$(7$U(B")
313 ("pr" . "$(7$V(B")
314 ("brk" . "$(7"7%!(B")
315 ("brg" . "$(7"7%"(B")
316 ("brng" . "$(7"7%#(B")
317 ("brj" . "$(7"7%$(B")
318 ("brny" . "$(7"7%%(B")
319 ("brt" . "$(7"7%&(B")
320 ("brd" . "$(7"7%'(B")
321 ("brn" . "$(7"7%((B")
322 ("brts" . "$(7"7%+(B")
323 ("brdz" . "$(7"7%,(B")
324 ("brl" . "$(7"7$d(B")
325 ("br" . "$(7$X(B")
326 ("mr" . "$(7$Y(B")
327 ("sr" . "$(7$[(B")
328 ("hr" . "$(7$\(B")
329 ("jr" . "$(7$](B")
330 ("kl" . "$(7$`(B")
331 ("gl" . "$(7$a(B")
332 ("blt" . "$(7"7%E(B")
333 ("bld" . "$(7"7%F(B")
334 ("bl" . "$(7$b(B")
335 ("zl" . "$(7$c(B")
336 ("rl" . "$(7$d(B")
337 ("sl" . "$(7$e(B")
338 ("rk" . "$(7%!(B")
339 ("rg" . "$(7%"(B")
340 ("rj" . "$(7%$(B")
341 ("rt" . "$(7%&(B")
342 ("rd" . "$(7%'(B")
343 ("rn" . "$(7%((B")
344 ("rb" . "$(7%)(B")
345 ("rm" . "$(7%*(B")
346 ("lk" . "$(7%@(B")
347 ("lg" . "$(7%A(B")
348 ("lc" . "$(7%C(B")
349 ("lj" . "$(7%D(B")
350 ("lt" . "$(7%E(B")
351 ("ld" . "$(7%F(B")
352 ("ln" . "$(7!!(B") ; dummy \x2121
353 ("lp" . "$(7%G(B")
354 ("lb" . "$(7%H(B")
355 ("lh" . "$(7%I(B")
356 ("sk" . "$(7%P(B")
357 ("sg" . "$(7%Q(B")
358 ("st" . "$(7%T(B")
359 ("sd" . "$(7%U(B")
360 ("sn" . "$(7%V(B")
361 ("sp" . "$(7%W(B")
362 ("sb" . "$(7%X(B")
363 ("sm" . "$(7%Y(B")))
364
365(defconst tibetan-subjoined-transcription-alist
366 '(("+k" . "$(7#!(B")
367 ("+kh" . "$(7#"(B")
368 ("+g" . "$(7##(B")
369 ("+gh" . "$(7#$(B")
370 ("+ng" . "$(7#%(B")
371 ("+c" . "$(7#&(B")
372 ("+ch" . "$(7#'(B")
373 ("+j" . "$(7#((B")
374 ("+ny" . "$(7#*(B")
375 ("+T" . "$(7#+(B")
376 ("+TH" . "$(7#,(B")
377 ("+D" . "$(7#-(B")
378 ("+DH" . "$(7#.(B")
379 ("+N" . "$(7#/(B")
380 ("+t" . "$(7#0(B")
381 ("+th" . "$(7#1(B")
382 ("+d" . "$(7#2(B")
383 ("+dh" . "$(7#3(B")
384 ("+n" . "$(7#4(B")
385 ("+p" . "$(7#5(B")
386 ("+ph" . "$(7#6(B")
387 ("+b" . "$(7#7(B")
388 ("+bh" . "$(7#8(B")
389 ("+m" . "$(7#9(B")
390 ("+ts" . "$(7#:(B")
391 ("+tsh" . "$(7#;(B")
392 ("+dz" . "$(7#<(B")
393 ("+dzh" . "$(7#=(B")
394 ("+w" . "$(7#>(B")
395 ("+zh" . "$(7#?(B")
396 ("+z" . "$(7#@(B")
397 ("+'" . "$(7#A(B")
398 ("+y" . "$(7#B(B")
399 ("+r" . "$(7#C(B")
400 ("+l" . "$(7#D(B")
401 ("+sh" . "$(7#E(B")
402 ("+SH" . "$(7#F(B")
403 ("+s" . "$(7#G(B")
404 ("+h" . "$(7#H(B")
405 ("+A" . "$(7#I(B")
406 ("+kSH" . "$(7#J(B")
407 ("R" . "$(7#P(B")))
408
409;;;
410;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
411;;;
412(defconst tibetan-base-to-subjoined-alist
413 '(("$(7"!(B" . "$(7#!(B")
414 ("$(7""(B" . "$(7#"(B")
415 ("$(7"#(B" . "$(7##(B")
416 ("$(7"$(B" . "$(7#$(B")
417 ("$(7"%(B" . "$(7#%(B")
418 ("$(7"&(B" . "$(7#&(B")
419 ("$(7"'(B" . "$(7#'(B")
420 ("$(7"((B" . "$(7#((B")
421 ("$(7"*(B" . "$(7#*(B")
422 ("$(7"+(B" . "$(7#+(B")
423 ("$(7",(B" . "$(7#,(B")
424 ("$(7"-(B" . "$(7#-(B")
425 ("$(7".(B" . "$(7#.(B")
426 ("$(7"/(B" . "$(7#/(B")
427 ("$(7"0(B" . "$(7#0(B")
428 ("$(7"1(B" . "$(7#1(B")
429 ("$(7"2(B" . "$(7#2(B")
430 ("$(7"3(B" . "$(7#3(B")
431 ("$(7"4(B" . "$(7#4(B")
432 ("$(7"5(B" . "$(7#5(B")
433 ("$(7"6(B" . "$(7#6(B")
434 ("$(7"7(B" . "$(7#7(B")
435 ("$(7"8(B" . "$(7#8(B")
436 ("$(7"9(B" . "$(7#9(B")
437 ("$(7":(B" . "$(7#:(B")
438 ("$(7";(B" . "$(7#;(B")
439 ("$(7"<(B" . "$(7#<(B")
440 ("$(7"=(B" . "$(7#=(B")
441 ("$(7">(B" . "$(7#>(B")
442 ("$(7"?(B" . "$(7#?(B")
443 ("$(7"@(B" . "$(7#@(B")
444 ("$(7"A(B" . "$(7#A(B")
445 ("$(7"B(B" . "$(7#B(B")
446 ("$(7"C(B" . "$(7#C(B")
447 ("$(7"D(B" . "$(7#D(B")
448 ("$(7"E(B" . "$(7#E(B")
449 ("$(7"F(B" . "$(7#F(B")
450 ("$(7"G(B" . "$(7#G(B")
451 ("$(7"H(B" . "$(7#H(B")
452 ("$(7"I(B" . "$(7#I(B")
453 ("$(7"J(B" . "$(7#J(B")))
454
455;;;
456;;; alist for Tibetan consonantic components <-> precomposed glyph conversion.
457;;; (includes some punctuation conversion rules)
458;;;
459(defconst tibetan-precomposition-rule-alist
460 '(("$(7"6#B#>(B" . "$(7$G(B")
461 ("$(7"##C#>(B" . "$(7$_(B")
462 ("$(7";#>(B" . "$(7$)(B")
463 ("$(7"C#:#>(B" . "$(7%.(B")
464 ("$(7"C###>(B" . "$(7%-(B")
465 ("$(7"C#!#B(B" . "$(7%0(B")
466 ("$(7"C###B(B" . "$(7%1(B")
467 ("$(7"C#9#B(B" . "$(7%2(B")
468 ("$(7"G#!#B(B" . "$(7%`(B")
469 ("$(7"G###B(B" . "$(7%a(B")
470 ("$(7"G#5#B(B" . "$(7%b(B")
471 ("$(7"G#7#B(B" . "$(7%c(B")
472 ("$(7"G#9#B(B" . "$(7%d(B")
473 ("$(7"G#!#C(B" . "$(7%p(B")
474 ("$(7"G###C(B" . "$(7%q(B")
475 ("$(7"G#4#C(B" . "$(7%r(B")
476 ("$(7"G#5#C(B" . "$(7%s(B")
477 ("$(7"G#7#C(B" . "$(7%t(B")
478 ("$(7"G#9#C(B" . "$(7%u(B")
479 ("$(7""#>(B" . "$(7$"(B")
480 ("$(7"*#>(B" . "$(7$%(B")
481 ("$(7":#>(B" . "$(7$((B")
482 ("$(7"?#>(B" . "$(7$*(B")
483 ("$(7"E#>(B" . "$(7$.(B")
484 ("$(7""#B(B" . "$(7$A(B")
485 ("$(7"6#B(B" . "$(7$D(B")
486 ("$(7""#C(B" . "$(7$Q(B")
487 ("$(7"1#C(B" . "$(7$T(B")
488 ("$(7"6#C(B" . "$(7$W(B")
489 ("$(7"E#C(B" . "$(7$Z(B")
490 ("$(7"<#C(B" . "$(7$^(B")
491 ("$(7"C#%(B" . "$(7%#(B")
492 ("$(7"C#*(B" . "$(7%%(B")
493 ("$(7"C#:(B" . "$(7%+(B")
494 ("$(7"C#<(B" . "$(7%,(B")
495 ("$(7"D#%(B" . "$(7%B(B")
496 ("$(7"G#%(B" . "$(7%R(B")
497 ("$(7"G#*(B" . "$(7%S(B")
498 ("$(7"G#:(B" . "$(7%Z(B")
499 ("$(7"!#>(B" . "$(7$!(B")
500 ("$(7"##>(B" . "$(7$#(B")
501 ("$(7"&#>(B" . "$(7$$(B")
502 ("$(7"0#>(B" . "$(7$&(B")
503 ("$(7"2#>(B" . "$(7$'(B")
504 ("$(7"@#>(B" . "$(7$+(B")
505 ("$(7"C#>(B" . "$(7$,(B")
506 ("$(7"D#>(B" . "$(7$-(B")
507 ("$(7"G#>(B" . "$(7$/(B")
508 ("$(7"H#>(B" . "$(7$0(B")
509 ("$(7"!#B(B" . "$(7$@(B")
510 ("$(7"##B(B" . "$(7$B(B")
511 ("$(7"5#B(B" . "$(7$C(B")
512 ("$(7"7#B(B" . "$(7$E(B")
513 ("$(7"9#B(B" . "$(7$F(B")
514 ("$(7"!#C(B" . "$(7$P(B")
515 ("$(7"##C(B" . "$(7$R(B")
516 ("$(7"0#C(B" . "$(7$S(B")
517 ("$(7"2#C(B" . "$(7$U(B")
518 ("$(7"5#C(B" . "$(7$V(B")
519 ("$(7"7#C(B" . "$(7$X(B")
520 ("$(7"9#C(B" . "$(7$Y(B")
521 ("$(7"G#C(B" . "$(7$[(B")
522 ("$(7"H#C(B" . "$(7$\(B")
523 ("$(7"(#C(B" . "$(7$](B")
524 ("$(7"!#D(B" . "$(7$`(B")
525 ("$(7"##D(B" . "$(7$a(B")
526 ("$(7"7#D(B" . "$(7$b(B")
527 ("$(7"@#D(B" . "$(7$c(B")
528 ("$(7"C#D(B" . "$(7$d(B")
529 ("$(7"G#D(B" . "$(7$e(B")
530 ("$(7"C#!(B" . "$(7%!(B")
531 ("$(7"C##(B" . "$(7%"(B")
532 ("$(7"C#((B" . "$(7%$(B")
533 ("$(7"C#0(B" . "$(7%&(B")
534 ("$(7"C#2(B" . "$(7%'(B")
535 ("$(7"C#4(B" . "$(7%((B")
536 ("$(7"C#7(B" . "$(7%)(B")
537 ("$(7"C#9(B" . "$(7%*(B")
538 ("$(7"D#!(B" . "$(7%@(B")
539 ("$(7"D##(B" . "$(7%A(B")
540 ("$(7"D#&(B" . "$(7%C(B")
541 ("$(7"D#((B" . "$(7%D(B")
542 ("$(7"D#0(B" . "$(7%E(B")
543 ("$(7"D#2(B" . "$(7%F(B")
544 ("$(7"D#5(B" . "$(7%G(B")
545 ("$(7"D#7(B" . "$(7%H(B")
546 ("$(7"D#H(B" . "$(7%I(B")
547 ("$(7"G#!(B" . "$(7%P(B")
548 ("$(7"G##(B" . "$(7%Q(B")
549 ("$(7"G#0(B" . "$(7%T(B")
550 ("$(7"G#2(B" . "$(7%U(B")
551 ("$(7"G#4(B" . "$(7%V(B")
552 ("$(7"G#5(B" . "$(7%W(B")
553 ("$(7"G#7(B" . "$(7%X(B")
554 ("$(7"G#9(B" . "$(7%Y(B")
555 ("$(7!=(B" . "$(8!=(B") ; 2 col <-> 1 col
556 ("$(7!?(B" . "$(8!?(B")
557 ("$(7!@(B" . "$(8!@(B")
558 ("$(7!A(B" . "$(8!A(B")
559 ("$(7"`(B" . "$(8"`(B")
560 ("$(7!;(B" . "$(8!;(B")
561 ("$(7!D(B" . "$(8!D(B")
562 ("$(7!>(B $(7!>(B" . "2$(7!>P(B P$(7!>1(B") ; Yes this is dirty. But ...
563 ("$(7!4!5!5(B" . "2$(7#RP#SP#SP#S1(B")
564 ("$(7!4!5(B" . "2$(7#RP#SP#S1(B")
565 ("$(7!6(B" . "2$(7#RP#S_!I1(B")
566 ("$(7!4(B" . "2$(7#RP#S1(B")))
567
568(defvar tibetan-regexp
569 (let ((l (append tibetan-consonant-transcription-alist
570 tibetan-vowel-transcription-alist
571 tibetan-subjoined-transcription-alist))
572 temp)
573 (setq temp "\\(")
574 (setq temp (concat temp (car (car l))))
575 (setq l (cdr l))
576 (while l
577 (setq temp (concat temp "\\|" (car (car l))))
578 (setq l (cdr l)))
579 (concat temp "\\)$"))
580 "Regexp string to match a romanized Tibetan character component, i.e.,
581base and subjoined consonant, vowel and vowel modifier. The result of matching
582is to be used for indexing alists at conversion from a roman transcription to
583the corresponding Tibetan character.")
584
585(defvar tibetan-precomposed-regexp
586 (let ((l tibetan-precomposed-transcription-alist)
587 temp)
588 (setq temp "^\\(")
589 (setq temp
590 (concat temp (car (car l))))
591 (setq l (cdr l))
592 (while l
593 (setq temp
594 (concat temp "\\|" (car (car l))))
595 (setq l (cdr l)))
596 (concat temp "\\)"))
597 "Regexp string to match a romanized Tibetan complex consonant.
598The result of matching is to be used for indexing alists when the input key
599from an input method is converted to the corresponding precomposed glyph.")
600
601(defvar tibetan-precomposition-rule-regexp
602 (let ((l tibetan-precomposition-rule-alist)
603 temp)
604 (setq temp "\\(")
605 (setq temp (concat temp (car (car l))))
606 (setq l (cdr l))
607 (while l
608 (setq temp (concat temp "\\|" (car (car l))))
609 (setq l (cdr l)))
610 (concat temp "\\)"))
611 "Regexp string to match a sequence of Tibetan consonantic components, i.e.,
612one base consonant and one or more subjoined consonants.
613The result of matching is to be used for indexing alist when the component
614sequence is converted to the corresponding precomposed glyph.
615This also matches some punctuation characters which need conversion.")
616
617(defvar tibetan-decomposed nil)
618(defvar tibetan-decomposed-temp nil)
619
620;;; language/tibetan.el ends here
generated by cgit v1.2.1 (git 2.18.0) at 2026-01-19 17:39:47 +0000