| blob | 91c9c4d2dd940a2176d1bbf6e174332f84ab9895 |
1 ;;; tibetan.el --- support for Tibetan language -*- coding: utf-8-emacs; -*-
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
12 ;; Author: Toru TOMABECHI <Toru.Tomabechi@orient.unil.ch>
13 ;; Created: Feb. 17. 1997
14 ;; Keywords: multilingual, Tibetan, i18n
16 ;; This file is part of GNU Emacs.
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.
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.
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/>.
31 ;;; History:
33 ;; 1997.03.13 Modification for special signs and punctuation.
35 ;;; Commentary:
37 ;;; Code:
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 ;;;
89 "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)."
91 :mnemonic ?Q
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)
115 "[ཀ-ཀྵཪ][ྐ-ྐྵྺྻྼ]*[ཱི-྄ཱཽྀྀ]*[ཾྂྃ྆-ྋ༙༵༷]*"
118 ;;;
119 ;;; Definitions of conversion data.
120 ;;;
123 ;;; alists for tibetan char <-> transcription conversion
124 ;;; longer transcription should come first
168 ;; Added by Tomabechi 1999/12/10
170 ))
174 '(
175 ;; Composite Vowels
176 ;; Added by Tomabechi 2000/06/08
185 ;; Normal Vowels
199 ))
325 )
370 ;; Added by Tomabechi 1999/12/10
374 )
377 ;;;
378 ;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
379 ;;;
422 ;; Added by Tomabechi 1999/12/10
424 ))
426 ;;; alist for Tibetan composite vowels (long i, vocalic r, etc.)
427 ;;; New variable. created by Tomabechi 2000/06/08
430 ;; ("ཱ" . ((bc . tc) ?ཱ))
431 ;; LONG I
433 ;; LONG U
435 ;; VOCALIC R
437 ;; LONG VOCALIC R
439 ;; VOCALIC L
441 ;;་LONG VOCALIC L
443 ;; LONG REVERSE I
445 ))
449 ;;;
450 ;;; alist for Tibetan consonantic components <-> precomposed glyph conversion.
451 ;;; (includes some punctuation conversion rules)
452 ;;;
553 tibetan-consonant-transcription-alist
554 tibetan-vowel-transcription-alist
555 tibetan-modifier-transcription-alist
556 tibetan-subjoined-transcription-alist))
558 tail 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
572 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
589 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.
606 ;; For automatic composition.
613 ;;; tibetan.el ends here