-;;; tibetan.el --- support for Tibetan language -*- coding: iso-2022-7bit; -*-
-
-;; Copyright (C) 1997, 2001-2013 Free Software Foundation, Inc.
-;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005,
-;; 2006, 2007, 2008, 2009, 2010, 2011
-;; National Institute of Advanced Industrial Science and Technology (AIST)
-;; Registration Number H14PRO021
-;; Copyright (C) 2003
-;; National Institute of Advanced Industrial Science and Technology (AIST)
-;; Registration Number H13PRO009
-
-;; Author: Toru TOMABECHI <Toru.Tomabechi@orient.unil.ch>
-;; Created: Feb. 17. 1997
-;; Keywords: multilingual, Tibetan, i18n
-
-;; This file is part of GNU Emacs.
-
-;; GNU Emacs is free software: you can redistribute it and/or modify
-;; it under the terms of the GNU General Public License as published by
-;; the Free Software Foundation, either version 3 of the License, or
-;; (at your option) any later version.
-
-;; GNU Emacs is distributed in the hope that it will be useful,
-;; but WITHOUT ANY WARRANTY; without even the implied warranty of
-;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-;; GNU General Public License for more details.
-
-;; You should have received a copy of the GNU General Public License
-;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
-
-;;; History:
-
-;; 1997.03.13 Modification for special signs and punctuation.
-
-;;; Commentary:
-
-;;; Code:
-
-;;; Tibetan Character set.
-;;; \x2130 -- \x234a is a subset of Unicode v.2 \x0f00 - \x0fb9
-;;; with a slight modification. And there are some subjoined
-;;; consonants which are not specified in Unicode.
-;;; I hope I can add missing characters later.
-;;;
-;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
-;;;2120 // \e$(7!!\e(B \e$(7!"\e(B \e$(7!#\e(B \e$(7!$\e(B \e$(7!%\e(B \e$(7!&\e(B \e$(7!'\e(B \e$(7!(\e(B \e$(7!)\e(B \e$(7!*\e(B \e$(7!+\e(B \e$(7!,\e(B \e$(7!-\e(B \e$(7!.\e(B \e$(7!/\e(B ; obsolete glyphs (2123-5)
-;;;2130 \e$(7!0\e(B \e$(7!1\e(B \e$(7!2\e(B \e$(7!3\e(B \e$(7!4\e(B \e$(7!5\e(B \e$(7!6\e(B \e$(7!7\e(B \e$(7!8\e(B \e$(7!9\e(B \e$(7!:\e(B \e$(7!;\e(B \e$(7!<\e(B \e$(7!=\e(B \e$(7!>\e(B \e$(7!?\e(B ; Punctuation,
-;;;2140 \e$(7!@\e(B \e$(7!A\e(B \e$(7!B\e(B \e$(7!C\e(B \e$(7!D\e(B \e$(7!E\e(B \e$(7!F\e(B \e$(7!G\e(B \e$(7!H\e(B \e$(7!I\e(B \e$(7!J\e(B \e$(7!K\e(B \e$(7!L\e(B \e$(7!M\e(B \e$(7!N\e(B \e$(7!O\e(B ; Digits and
-;;;2150 \e$(7!P\e(B \e$(7!Q\e(B \e$(7!R\e(B \e$(7!S\e(B \e$(7!T\e(B \e$(7!U\e(B \e$(7!V\e(B \e$(7!W\e(B \e$(7!X\e(B \e$(7!Y\e(B \e$(7!Z\e(B \e$(7![\e(B \e$(7!\\e(B \e$(7!]\e(B \e$(7!^\e(B \e$(7!_\e(B ; Special signs.
-;;;2160 \e$(7!`\e(B \e$(7!a\e(B \e$(7!b\e(B \e$(7!c\e(B \e$(7!d\e(B \e$(7!e\e(B \e$(7!f\e(B \e$(7!g\e(B \e$(7!h\e(B \e$(7!i\e(B \e$(7!j\e(B \e$(7!k\e(B \e$(7!l\e(B \e$(7!m\e(B \e$(7!n\e(B \e$(7!o\e(B ;
-;;;2170 \e$(7!p\e(B \e$(7!q\e(B \e$(7!r\e(B \e$(7!s\e(B \e$(7!t\e(B \e$(7!u\e(B \e$(7!v\e(B \e$(7!w\e(B \e$(7!x\e(B \e$(7!y\e(B \e$(7!z\e(B \e$(7!{\e(B \e$(7!|\e(B \e$(7!}\e(B \e$(7!~\e(B // ;
-;;;
-;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
-;;;2220 // \e$(7"!\e(B \e$(7""\e(B \e$(7"#\e(B \e$(7"$\e(B \e$(7"%\e(B \e$(7"&\e(B \e$(7"'\e(B \e$(7"(\e(B \e$(7")\e(B \e$(7"*\e(B \e$(7"+\e(B \e$(7",\e(B \e$(7"-\e(B \e$(7".\e(B \e$(7"/\e(B ; Base consonants
-;;;2230 \e$(7"0\e(B \e$(7"1\e(B \e$(7"2\e(B \e$(7"3\e(B \e$(7"4\e(B \e$(7"5\e(B \e$(7"6\e(B \e$(7"7\e(B \e$(7"8\e(B \e$(7"9\e(B \e$(7":\e(B \e$(7";\e(B \e$(7"<\e(B \e$(7"=\e(B \e$(7">\e(B \e$(7"?\e(B ; and
-;;;2240 \e$(7"@\e(B \e$(7"A\e(B \e$(7"B\e(B \e$(7"C\e(B \e$(7"D\e(B \e$(7"E\e(B \e$(7"F\e(B \e$(7"G\e(B \e$(7"H\e(B \e$(7"I\e(B \e$(7"J\e(B \e$(7"K\e(B \e$(7"L\e(B \e$(7"M\e(B \e$(7"N\e(B \e$(7"O\e(B ; Vowel signs.
-;;;2250 \e$(7"P\e(B \e$(7"Q\e(B \e$(7"R\e(B \e$(7"S\e(B \e$(7"T\e(B \e$(7"U\e(B \e$(7"V\e(B \e$(7"W\e(B \e$(7"X\e(B \e$(7"Y\e(B \e$(7"Z\e(B \e$(7"[\e(B \e$(7"\\e(B \e$(7"]\e(B \e$(7"^\e(B \e$(7"_\e(B ; (\x2251 = vowel a)
-;;;2260 \e$(7"`\e(B \e$(7"a\e(B \e$(7"b\e(B \e$(7"c\e(B \e$(7"d\e(B \e$(7"e\e(B \e$(7"f\e(B \e$(7"g\e(B \e$(7"h\e(B \e$(7"i\e(B \e$(7"j\e(B \e$(7"k\e(B \e$(7"l\e(B \e$(7"m\e(B \e$(7"n\e(B \e$(7"o\e(B ; Long vowels and
-;;;2270 \e$(7"p\e(B \e$(7"q\e(B \e$(7"r\e(B \e$(7"s\e(B \e$(7"t\e(B \e$(7"u\e(B \e$(7"v\e(B \e$(7"w\e(B \e$(7"x\e(B \e$(7"y\e(B \e$(7"z\e(B \e$(7"{\e(B \e$(7"|\e(B \e$(7"}\e(B \e$(7"~\e(B // ; vocalic r, l ARE
-;;; ; atomically
-;;; ; encoded.
-;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
-;;;2320 // \e$(7#!\e(B \e$(7#"\e(B \e$(7##\e(B \e$(7#$\e(B \e$(7#%\e(B \e$(7#&\e(B \e$(7#'\e(B \e$(7#(\e(B \e$(7#)\e(B \e$(7#*\e(B \e$(7#+\e(B \e$(7#,\e(B \e$(7#-\e(B \e$(7#.\e(B \e$(7#/\e(B ; Subjoined consonants
-;;;2330 \e$(7#0\e(B \e$(7#1\e(B \e$(7#2\e(B \e$(7#3\e(B \e$(7#4\e(B \e$(7#5\e(B \e$(7#6\e(B \e$(7#7\e(B \e$(7#8\e(B \e$(7#9\e(B \e$(7#:\e(B \e$(7#;\e(B \e$(7#<\e(B \e$(7#=\e(B \e$(7#>\e(B \e$(7#?\e(B ;
-;;;2340 \e$(7#@\e(B \e$(7#A\e(B \e$(7#B\e(B \e$(7#C\e(B \e$(7#D\e(B \e$(7#E\e(B \e$(7#F\e(B \e$(7#G\e(B \e$(7#H\e(B \e$(7#I\e(B \e$(7#J\e(B \e$(7#K\e(B \e$(7#L\e(B \e$(7#M\e(B \e$(7#N\e(B \e$(7#O\e(B ;
-;;;2350 \e$(7#P\e(B \e$(7#Q\e(B \e$(7#R\e(B \e$(7#S\e(B \e$(7#T\e(B \e$(7#U\e(B \e$(7#V\e(B \e$(7#W\e(B \e$(7#X\e(B \e$(7#Y\e(B \e$(7#Z\e(B \e$(7#[\e(B \e$(7#\\e(B \e$(7#]\e(B \e$(7#^\e(B \e$(7#_\e(B ; Hereafter, the chars
-;;;2360 \e$(7#`\e(B \e$(7#a\e(B \e$(7#b\e(B \e$(7#c\e(B \e$(7#d\e(B \e$(7#e\e(B \e$(7#f\e(B \e$(7#g\e(B \e$(7#h\e(B \e$(7#i\e(B \e$(7#j\e(B \e$(7#k\e(B \e$(7#l\e(B \e$(7#m\e(B \e$(7#n\e(B \e$(7#o\e(B ; are not specified
-;;;2370 \e$(7#p\e(B \e$(7#q\e(B \e$(7#r\e(B \e$(7#s\e(B \e$(7#t\e(B \e$(7#u\e(B \e$(7#v\e(B \e$(7#w\e(B \e$(7#x\e(B \e$(7#y\e(B \e$(7#z\e(B \e$(7#{\e(B \e$(7#|\e(B \e$(7#}\e(B \e$(7#~\e(B // ; in Unicode.
-;;;
-;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
-;;;2420 // \e$(7$!\e(B \e$(7$"\e(B \e$(7$#\e(B \e$(7$$\e(B \e$(7$%\e(B \e$(7$&\e(B \e$(7$'\e(B \e$(7$(\e(B \e$(7$)\e(B \e$(7$*\e(B \e$(7$+\e(B \e$(7$,\e(B \e$(7$-\e(B \e$(7$.\e(B \e$(7$/\e(B ; Precomposed
-;;;2430 \e$(7$0\e(B \e$(7$1\e(B \e$(7$2\e(B \e$(7$3\e(B \e$(7$4\e(B \e$(7$5\e(B \e$(7$6\e(B \e$(7$7\e(B \e$(7$8\e(B \e$(7$9\e(B \e$(7$:\e(B \e$(7$;\e(B \e$(7$<\e(B \e$(7$=\e(B \e$(7$>\e(B \e$(7$?\e(B ; consonants for
-;;;2440 \e$(7$@\e(B \e$(7$A\e(B \e$(7$B\e(B \e$(7$C\e(B \e$(7$D\e(B \e$(7$E\e(B \e$(7$F\e(B \e$(7$G\e(B \e$(7$H\e(B \e$(7$I\e(B \e$(7$J\e(B \e$(7$K\e(B \e$(7$L\e(B \e$(7$M\e(B \e$(7$N\e(B \e$(7$O\e(B ; ordinary Tibetan.
-;;;2450 \e$(7$P\e(B \e$(7$Q\e(B \e$(7$R\e(B \e$(7$S\e(B \e$(7$T\e(B \e$(7$U\e(B \e$(7$V\e(B \e$(7$W\e(B \e$(7$X\e(B \e$(7$Y\e(B \e$(7$Z\e(B \e$(7$[\e(B \e$(7$\\e(B \e$(7$]\e(B \e$(7$^\e(B \e$(7$_\e(B ; They are decomposed
-;;;2460 \e$(7$`\e(B \e$(7$a\e(B \e$(7$b\e(B \e$(7$c\e(B \e$(7$d\e(B \e$(7$e\e(B \e$(7$f\e(B \e$(7$g\e(B \e$(7$h\e(B \e$(7$i\e(B \e$(7$j\e(B \e$(7$k\e(B \e$(7$l\e(B \e$(7$m\e(B \e$(7$n\e(B \e$(7$o\e(B ; into base and
-;;;2470 \e$(7$p\e(B \e$(7$q\e(B \e$(7$r\e(B \e$(7$s\e(B \e$(7$t\e(B \e$(7$u\e(B \e$(7$v\e(B \e$(7$w\e(B \e$(7$x\e(B \e$(7$y\e(B \e$(7$z\e(B \e$(7${\e(B \e$(7$|\e(B \e$(7$}\e(B \e$(7$~\e(B // ; subjoined consonants
-;;; ; when written on a
-;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F ; file in Tibetan
-;;;2520 // \e$(7%!\e(B \e$(7%"\e(B \e$(7%#\e(B \e$(7%$\e(B \e$(7%%\e(B \e$(7%&\e(B \e$(7%'\e(B \e$(7%(\e(B \e$(7%)\e(B \e$(7%*\e(B \e$(7%+\e(B \e$(7%,\e(B \e$(7%-\e(B \e$(7%.\e(B \e$(7%/\e(B ; coding system.
-;;;2530 \e$(7%0\e(B \e$(7%1\e(B \e$(7%2\e(B \e$(7%3\e(B \e$(7%4\e(B \e$(7%5\e(B \e$(7%6\e(B \e$(7%7\e(B \e$(7%8\e(B \e$(7%9\e(B \e$(7%:\e(B \e$(7%;\e(B \e$(7%<\e(B \e$(7%=\e(B \e$(7%>\e(B \e$(7%?\e(B ;
-;;;2540 \e$(7%@\e(B \e$(7%A\e(B \e$(7%B\e(B \e$(7%C\e(B \e$(7%D\e(B \e$(7%E\e(B \e$(7%F\e(B \e$(7%G\e(B \e$(7%H\e(B \e$(7%I\e(B \e$(7%J\e(B \e$(7%K\e(B \e$(7%L\e(B \e$(7%M\e(B \e$(7%N\e(B \e$(7%O\e(B ;
-;;;2550 \e$(7%P\e(B \e$(7%Q\e(B \e$(7%R\e(B \e$(7%S\e(B \e$(7%T\e(B \e$(7%U\e(B \e$(7%V\e(B \e$(7%W\e(B \e$(7%X\e(B \e$(7%Y\e(B \e$(7%Z\e(B \e$(7%[\e(B \e$(7%\\e(B \e$(7%]\e(B \e$(7%^\e(B \e$(7%_\e(B ;
-;;;2560 \e$(7%`\e(B \e$(7%a\e(B \e$(7%b\e(B \e$(7%c\e(B \e$(7%d\e(B \e$(7%e\e(B \e$(7%f\e(B \e$(7%g\e(B \e$(7%h\e(B \e$(7%i\e(B \e$(7%j\e(B \e$(7%k\e(B \e$(7%l\e(B \e$(7%m\e(B \e$(7%n\e(B \e$(7%o\e(B ;
-;;;2570 \e$(7%p\e(B \e$(7%q\e(B \e$(7%r\e(B \e$(7%s\e(B \e$(7%t\e(B \e$(7%u\e(B \e$(7%v\e(B \e$(7%w\e(B \e$(7%x\e(B \e$(7%y\e(B \e$(7%z\e(B \e$(7%{\e(B \e$(7%|\e(B \e$(7%}\e(B \e$(7%~\e(B // ;
-;;;
-
-
-(define-coding-system 'tibetan-iso-8bit
- "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)."
- :coding-type 'iso-2022
- :mnemonic ?Q
- :designation [ascii tibetan nil nil]
- :charset-list '(ascii tibetan))
-
-(define-coding-system-alias 'tibetan 'tibetan-iso-8bit)
-
-(set-language-info-alist
- "Tibetan" '((charset tibetan tibetan-1-column)
- (coding-system tibetan-iso-8bit)
- (coding-priority iso-2022-7bit tibetan-iso-8bit)
- (input-method . "tibetan-wylie")
- (features tibet-util)
- (documentation . t)
- (sample-text . "Tibetan (\e$(7"7"]"2!;"G#!"Q"2!;\e(B) \e$(7!4!5!5!>"7"!#C"Q!;"E"S"G!;"7"2"[!;"D"["#"G!>"I"]"_!;"9"Q!;"/"S!;"5"Q"2#9"[!;"H"A"U"c!>\e(B")))
-
-;; `\e$(7"A\e(B' is included in the pattern for subjoined consonants because we
-;; treat it specially in tibetan-add-components.
-;; modified by Tomabechi 1999/12/10
-;; modified by Tomabechi 2000/06/08
-;; To allow infinite addition of vowels/modifiers
-;; as specified in Unicode v.3
-;; \e$(7"A\e(B is removed from the class of subjoined. Tomabechi 2000/06/08
-;; (for Unicode support)
-(defconst tibetan-composable-pattern
- "[\e$(7"!\e(B-\e$(7"J"K\e(B][\e$(7#!\e(B-\e$(7#J#K#L#M\e(B]*[\e$,1FP\e$(7"Q"R"S\e(B-\e$(7"^"a"b"e\e(B]*[\e$(7"_"c"d"g\e(B-\e$(7"l!I!e!g\e(B]*"
- "Regexp matching a composable sequence of Tibetan characters.")
-
-;;;
-;;; Definitions of conversion data.
-;;;
-
-
-;;; alists for tibetan char <-> transcription conversion
-;;; longer transcription should come first
-(defconst tibetan-consonant-transcription-alist
- '(("tsh" . "\e$(7";\e(B")
- ("dzh" . "\e$(7"=\e(B")
- ("kSH" . "\e$(7"J\e(B")
- ("kh" . "\e$(7""\e(B")
- ("gh" . "\e$(7"$\e(B")
- ("ng" . "\e$(7"%\e(B")
- ("ch" . "\e$(7"'\e(B")
- ("ny" . "\e$(7"*\e(B")
- ("TH" . "\e$(7",\e(B")
- ("DH" . "\e$(7".\e(B")
- ("th" . "\e$(7"1\e(B")
- ("dh" . "\e$(7"3\e(B")
- ("ph" . "\e$(7"6\e(B")
- ("bh" . "\e$(7"8\e(B")
- ("ts" . "\e$(7":\e(B")
- ("dz" . "\e$(7"<\e(B")
- ("zh" . "\e$(7"?\e(B")
- ("sh" . "\e$(7"E\e(B")
- ("SH" . "\e$(7"F\e(B")
- ("k" . "\e$(7"!\e(B")
- ("g" . "\e$(7"#\e(B")
- ("c" . "\e$(7"&\e(B")
- ("j" . "\e$(7"(\e(B")
- ("T" . "\e$(7"+\e(B")
- ("D" . "\e$(7"-\e(B")
- ("N" . "\e$(7"/\e(B")
- ("t" . "\e$(7"0\e(B")
- ("d" . "\e$(7"2\e(B")
- ("n" . "\e$(7"4\e(B")
- ("p" . "\e$(7"5\e(B")
- ("b" . "\e$(7"7\e(B")
- ("m" . "\e$(7"9\e(B")
- ("w" . "\e$(7">\e(B")
- ("z" . "\e$(7"@\e(B")
- ("'" . "\e$(7"A\e(B")
- ("y" . "\e$(7"B\e(B")
- ("r" . "\e$(7"C\e(B")
- ("l" . "\e$(7"D\e(B")
- ("s" . "\e$(7"G\e(B")
- ("h" . "\e$(7"H\e(B")
- ("H" . "\e$(7"H\e(B")
- ("A" . "\e$(7"I\e(B")
- ;; Added by Tomabechi 1999/12/10
- ("R" . "\e$(7"K\e(B") ;; fixed form RA
- ))
-
-
-(defconst tibetan-vowel-transcription-alist
- '(
- ;; Composite Vowels
- ;; Added by Tomabechi 2000/06/08
- ("frr" . "\e$(7"X\e(B")
- ("fll" . "\e$(7"Z\e(B")
- ("fa" . "\e$(7"R\e(B")
- ("fi" . "\e$(7"T\e(B")
- ("fu" . "\e$(7"V\e(B")
- ("fr" . "\e$(7"W\e(B")
- ("fl" . "\e$(7"Y\e(B")
- ("fI" . "\e$(7"b\e(B")
- ;; Normal Vowels
- ("ai" . "\e$(7"\\e(B")
- ("au" . "\e$(7"^\e(B")
- ("ee" . "\e$(7"\\e(B")
- ("oo" . "\e$(7"^\e(B")
- ("a" . "\e$(7"Q\e(B") ; invisible vowel sign (\x2251)
- ("i" . "\e$(7"S\e(B")
- ("u" . "\e$(7"U\e(B")
- ("e" . "\e$(7"[\e(B")
- ("o" . "\e$(7"]\e(B")
- ("E" . "\e$(7"\\e(B")
- ("O" . "\e$(7"^\e(B")
- ("I" . "\e$(7"a\e(B")
- ("," . "\e$(7"e\e(B") ; idem.
- ))
-
-(defconst tibetan-modifier-transcription-alist
- '(("M" . "\e$(7"_\e(B")
- ("~" . "\e$(7"c\e(B")
- ("`" . "\e$(7"d\e(B")
- ("x" . "\e$(7"i\e(B")
- ("X" . "\e$(7"j\e(B")
- ("v" . "\e$(7"g\e(B")
- ("V" . "\e$(7"h\e(B")
- ("q" . "\e$(7"k\e(B")
- ("Q" . "\e$(7"l\e(B")
- ("_/" . "\e$(7!I\e(B")
- ("_o" . "\e$(7!g\e(B")
- ("_O" . "\e$(7!e\e(B")))
-
-(defconst tibetan-precomposed-transcription-alist
- '(("phyw" . "\e$(7$G\e(B")
- ("tshw" . "\e$(7$)\e(B")
- ("rtsw" . "\e$(7%.\e(B")
- ("khw" . "\e$(7$"\e(B")
- ("nyw" . "\e$(7$%\e(B")
- ("tsw" . "\e$(7$(\e(B")
- ("zhw" . "\e$(7$*\e(B")
- ("shw" . "\e$(7$.\e(B")
- ("khy" . "\e$(7$A\e(B")
- ("phy" . "\e$(7$D\e(B")
- ("khr" . "\e$(7$Q\e(B")
- ("thr" . "\e$(7$T\e(B")
- ("phr" . "\e$(7$W\e(B")
- ("shr" . "\e$(7$Z\e(B")
- ("dzr" . "\e$(7$^\e(B")
- ("grw" . "\e$(7$_\e(B")
- ("rng" . "\e$(7%#\e(B")
- ("rny" . "\e$(7%%\e(B")
- ("rts" . "\e$(7%+\e(B")
- ("rdz" . "\e$(7%,\e(B")
- ("rgw" . "\e$(7%-\e(B")
- ("rky" . "\e$(7%0\e(B")
- ("rgy" . "\e$(7%1\e(B")
- ("rmy" . "\e$(7%2\e(B")
- ("lng" . "\e$(7%B\e(B")
- ("sng" . "\e$(7%R\e(B")
- ("sny" . "\e$(7%S\e(B")
- ("sts" . "\e$(7%Z\e(B")
- ("sky" . "\e$(7%`\e(B")
- ("sgy" . "\e$(7%a\e(B")
- ("spy" . "\e$(7%b\e(B")
- ("sby" . "\e$(7%c\e(B")
- ("smy" . "\e$(7%d\e(B")
- ("skr" . "\e$(7%p\e(B")
- ("sgr" . "\e$(7%q\e(B")
- ("snr" . "\e$(7%r\e(B")
- ("spr" . "\e$(7%s\e(B")
- ("sbr" . "\e$(7%t\e(B")
- ("smr" . "\e$(7%u\e(B")
- ("kw" . "\e$(7$!\e(B")
- ("gw" . "\e$(7$#\e(B")
- ("cw" . "\e$(7$$\e(B")
- ("tw" . "\e$(7$&\e(B")
- ("dw" . "\e$(7$'\e(B")
- ("zw" . "\e$(7$+\e(B")
- ("rw" . "\e$(7$,\e(B")
- ("lw" . "\e$(7$-\e(B")
- ("sw" . "\e$(7$/\e(B")
- ("hw" . "\e$(7$0\e(B")
- ("ky" . "\e$(7$@\e(B")
- ("gy" . "\e$(7$B\e(B")
- ("py" . "\e$(7$C\e(B")
- ("by" . "\e$(7$E\e(B")
- ("my" . "\e$(7$F\e(B")
- ("kr" . "\e$(7$P\e(B")
- ("gr" . "\e$(7$R\e(B")
- ("tr" . "\e$(7$S\e(B")
- ("dr" . "\e$(7$U\e(B")
- ("pr" . "\e$(7$V\e(B")
- ("brk" . "\e$(7"7%!\e(B")
- ("brg" . "\e$(7"7%"\e(B")
- ("brng" . "\e$(7"7%#\e(B")
- ("brj" . "\e$(7"7%$\e(B")
- ("brny" . "\e$(7"7%%\e(B")
- ("brt" . "\e$(7"7%&\e(B")
- ("brd" . "\e$(7"7%'\e(B")
- ("brn" . "\e$(7"7%(\e(B")
- ("brts" . "\e$(7"7%+\e(B")
- ("brdz" . "\e$(7"7%,\e(B")
- ("brl" . "\e$(7"7$d\e(B")
- ("br" . "\e$(7$X\e(B")
- ("mr" . "\e$(7$Y\e(B")
- ("sr" . "\e$(7$[\e(B")
- ("hr" . "\e$(7$\\e(B")
- ("jr" . "\e$(7$]\e(B")
- ("kl" . "\e$(7$`\e(B")
- ("gl" . "\e$(7$a\e(B")
- ("blt" . "\e$(7"7%E\e(B")
- ("bld" . "\e$(7"7%F\e(B")
- ("bl" . "\e$(7$b\e(B")
- ("zl" . "\e$(7$c\e(B")
- ("rl" . "\e$(7$d\e(B")
- ("sl" . "\e$(7$e\e(B")
- ("rk" . "\e$(7%!\e(B")
- ("rg" . "\e$(7%"\e(B")
- ("rj" . "\e$(7%$\e(B")
- ("rt" . "\e$(7%&\e(B")
- ("rd" . "\e$(7%'\e(B")
- ("rn" . "\e$(7%(\e(B")
- ("rb" . "\e$(7%)\e(B")
- ("rm" . "\e$(7%*\e(B")
- ("lk" . "\e$(7%@\e(B")
- ("lg" . "\e$(7%A\e(B")
- ("lc" . "\e$(7%C\e(B")
- ("lj" . "\e$(7%D\e(B")
- ("lt" . "\e$(7%E\e(B")
- ("ld" . "\e$(7%F\e(B")
- ("ln" . "\e$(7!!\e(B") ; dummy \x2121
- ("lp" . "\e$(7%G\e(B")
- ("lb" . "\e$(7%H\e(B")
- ("lh" . "\e$(7%I\e(B")
- ("sk" . "\e$(7%P\e(B")
- ("sg" . "\e$(7%Q\e(B")
- ("st" . "\e$(7%T\e(B")
- ("sd" . "\e$(7%U\e(B")
- ("sn" . "\e$(7%V\e(B")
- ("sp" . "\e$(7%W\e(B")
- ("sb" . "\e$(7%X\e(B")
- ("sm" . "\e$(7%Y\e(B"))
- )
-
-
-(defconst tibetan-subjoined-transcription-alist
- (sort '(("+k" . "\e$(7#!\e(B")
- ("+kh" . "\e$(7#"\e(B")
- ("+g" . "\e$(7##\e(B")
- ("+gh" . "\e$(7#$\e(B")
- ("+ng" . "\e$(7#%\e(B")
- ("+c" . "\e$(7#&\e(B")
- ("+ch" . "\e$(7#'\e(B")
- ("+j" . "\e$(7#(\e(B")
- ("+ny" . "\e$(7#*\e(B")
- ("+T" . "\e$(7#+\e(B")
- ("+TH" . "\e$(7#,\e(B")
- ("+D" . "\e$(7#-\e(B")
- ("+DH" . "\e$(7#.\e(B")
- ("+N" . "\e$(7#/\e(B")
- ("+t" . "\e$(7#0\e(B")
- ("+th" . "\e$(7#1\e(B")
- ("+d" . "\e$(7#2\e(B")
- ("+dh" . "\e$(7#3\e(B")
- ("+n" . "\e$(7#4\e(B")
- ("+p" . "\e$(7#5\e(B")
- ("+ph" . "\e$(7#6\e(B")
- ("+b" . "\e$(7#7\e(B")
- ("+bh" . "\e$(7#8\e(B")
- ("+m" . "\e$(7#9\e(B")
- ("+ts" . "\e$(7#:\e(B")
- ("+tsh" . "\e$(7#;\e(B")
- ("+dz" . "\e$(7#<\e(B")
- ("+dzh" . "\e$(7#=\e(B")
- ("+w" . "\e$(7#>\e(B")
- ("+zh" . "\e$(7#?\e(B")
- ("+z" . "\e$(7#@\e(B")
- ("+'" . "\e$(7#A\e(B")
- ("+y" . "\e$(7#B\e(B")
- ("+r" . "\e$(7#C\e(B")
- ("+l" . "\e$(7#D\e(B")
- ("+sh" . "\e$(7#E\e(B")
- ("+SH" . "\e$(7#F\e(B")
- ("+s" . "\e$(7#G\e(B")
- ("+h" . "\e$(7#H\e(B")
- ("+A" . "\e$(7#I\e(B")
- ("+kSH" . "\e$(7#J\e(B")
- ;; Added by Tomabechi 1999/12/10
- ("+W" . "\e$(7#K\e(B") ;; fixed form subscribed WA
- ("+Y" . "\e$(7#L\e(B") ;; fixed form subscribed YA
- ("+R" . "\e$(7#M\e(B") ;; fixed form subscribed RA
- )
- (lambda (x y) (> (length (car x)) (length (car y))))))
-
-;;;
-;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
-;;;
-(defconst tibetan-base-to-subjoined-alist
- '(("\e$(7"!\e(B" . "\e$(7#!\e(B")
- ("\e$(7""\e(B" . "\e$(7#"\e(B")
- ("\e$(7"#\e(B" . "\e$(7##\e(B")
- ("\e$(7"$\e(B" . "\e$(7#$\e(B")
- ("\e$(7"%\e(B" . "\e$(7#%\e(B")
- ("\e$(7"&\e(B" . "\e$(7#&\e(B")
- ("\e$(7"'\e(B" . "\e$(7#'\e(B")
- ("\e$(7"(\e(B" . "\e$(7#(\e(B")
- ("\e$(7"*\e(B" . "\e$(7#*\e(B")
- ("\e$(7"+\e(B" . "\e$(7#+\e(B")
- ("\e$(7",\e(B" . "\e$(7#,\e(B")
- ("\e$(7"-\e(B" . "\e$(7#-\e(B")
- ("\e$(7".\e(B" . "\e$(7#.\e(B")
- ("\e$(7"/\e(B" . "\e$(7#/\e(B")
- ("\e$(7"0\e(B" . "\e$(7#0\e(B")
- ("\e$(7"1\e(B" . "\e$(7#1\e(B")
- ("\e$(7"2\e(B" . "\e$(7#2\e(B")
- ("\e$(7"3\e(B" . "\e$(7#3\e(B")
- ("\e$(7"4\e(B" . "\e$(7#4\e(B")
- ("\e$(7"5\e(B" . "\e$(7#5\e(B")
- ("\e$(7"6\e(B" . "\e$(7#6\e(B")
- ("\e$(7"7\e(B" . "\e$(7#7\e(B")
- ("\e$(7"8\e(B" . "\e$(7#8\e(B")
- ("\e$(7"9\e(B" . "\e$(7#9\e(B")
- ("\e$(7":\e(B" . "\e$(7#:\e(B")
- ("\e$(7";\e(B" . "\e$(7#;\e(B")
- ("\e$(7"<\e(B" . "\e$(7#<\e(B")
- ("\e$(7"=\e(B" . "\e$(7#=\e(B")
- ("\e$(7">\e(B" . "\e$(7#>\e(B")
- ("\e$(7"?\e(B" . "\e$(7#?\e(B")
- ("\e$(7"@\e(B" . "\e$(7#@\e(B")
- ("\e$(7"A\e(B" . "\e$(7#A\e(B")
- ("\e$(7"B\e(B" . "\e$(7#B\e(B")
- ("\e$(7"C\e(B" . "\e$(7#C\e(B")
- ("\e$(7"D\e(B" . "\e$(7#D\e(B")
- ("\e$(7"E\e(B" . "\e$(7#E\e(B")
- ("\e$(7"F\e(B" . "\e$(7#F\e(B")
- ("\e$(7"G\e(B" . "\e$(7#G\e(B")
- ("\e$(7"H\e(B" . "\e$(7#H\e(B")
- ("\e$(7"I\e(B" . "\e$(7#I\e(B")
- ("\e$(7"J\e(B" . "\e$(7#J\e(B")
- ;; Added by Tomabechi 1999/12/10
- ("\e$(7"K\e(B" . "\e$(7#M\e(B") ;; Fixed form RA (224B->234D)
- ))
-
-;;; alist for Tibetan composite vowels (long i, vocalic r, etc.)
-;;; New variable. created by Tomabechi 2000/06/08
-(defconst tibetan-composite-vowel-alist
- '(;; LONG A
- ;; ("\e$(7"R\e(B" . ((bc . tc) ?\e$(7"R\e(B))
- ;; LONG I
- ("\e$(7"T\e(B" . (?\e$(7"R\e(B (tc . bc) ?\e$(7"S\e(B))
- ;; LONG U
- ("\e$(7"V\e(B" . (?\e$(7"R\e(B (bc . tc) ?\e$(7"U\e(B))
- ;; VOCALIC R
- ("\e$(7"W\e(B" . (?\e$(7#C\e(B (tc . bc) ?\e$(7"a\e(B))
- ;; LONG VOCALIC R
- ("\e$(7"X\e(B" . (?\e$(7#C\e(B (bc . tc) ?\e$(7"R\e(B (tc . bc) ?\e$(7"a\e(B))
- ;; VOCALIC L
- ("\e$(7"Y\e(B" . (?\e$(7#D\e(B (tc . bc) ?\e$(7"a\e(B))
- ;;\e$(7!;\e(BLONG VOCALIC L
- ("\e$(7"Z\e(B" . (?\e$(7#D\e(B (bc . tc) ?\e$(7"R\e(B (tc . bc) ?\e$(7"a\e(B))
- ;; LONG REVERSE I
- ("\e$(7"b\e(B" . (?\e$(7"R\e(B (tc . bc) ?\e$(7"a\e(B))
- ))
-
-
-
-;;;
-;;; alist for Tibetan consonantic components <-> precomposed glyph conversion.
-;;; (includes some punctuation conversion rules)
-;;;
-(defconst tibetan-precomposition-rule-alist
- `(("\e$(7"6#B#>\e(B" . "\e$(7$G\e(B")
- ("\e$(7"##C#>\e(B" . "\e$(7$_\e(B")
- ("\e$(7";#>\e(B" . "\e$(7$)\e(B")
- ("\e$(7"C#:#>\e(B" . "\e$(7%.\e(B")
- ("\e$(7"C###>\e(B" . "\e$(7%-\e(B")
- ("\e$(7"C#!#B\e(B" . "\e$(7%0\e(B")
- ("\e$(7"C###B\e(B" . "\e$(7%1\e(B")
- ("\e$(7"C#9#B\e(B" . "\e$(7%2\e(B")
- ("\e$(7"G#!#B\e(B" . "\e$(7%`\e(B")
- ("\e$(7"G###B\e(B" . "\e$(7%a\e(B")
- ("\e$(7"G#5#B\e(B" . "\e$(7%b\e(B")
- ("\e$(7"G#7#B\e(B" . "\e$(7%c\e(B")
- ("\e$(7"G#9#B\e(B" . "\e$(7%d\e(B")
- ("\e$(7"G#!#C\e(B" . "\e$(7%p\e(B")
- ("\e$(7"G###C\e(B" . "\e$(7%q\e(B")
- ("\e$(7"G#4#C\e(B" . "\e$(7%r\e(B")
- ("\e$(7"G#5#C\e(B" . "\e$(7%s\e(B")
- ("\e$(7"G#7#C\e(B" . "\e$(7%t\e(B")
- ("\e$(7"G#9#C\e(B" . "\e$(7%u\e(B")
- ("\e$(7""#>\e(B" . "\e$(7$"\e(B")
- ("\e$(7"*#>\e(B" . "\e$(7$%\e(B")
- ("\e$(7":#>\e(B" . "\e$(7$(\e(B")
- ("\e$(7"?#>\e(B" . "\e$(7$*\e(B")
- ("\e$(7"E#>\e(B" . "\e$(7$.\e(B")
- ("\e$(7""#B\e(B" . "\e$(7$A\e(B")
- ("\e$(7"6#B\e(B" . "\e$(7$D\e(B")
- ("\e$(7""#C\e(B" . "\e$(7$Q\e(B")
- ("\e$(7"1#C\e(B" . "\e$(7$T\e(B")
- ("\e$(7"6#C\e(B" . "\e$(7$W\e(B")
- ("\e$(7"E#C\e(B" . "\e$(7$Z\e(B")
- ("\e$(7"<#C\e(B" . "\e$(7$^\e(B")
- ("\e$(7"C#%\e(B" . "\e$(7%#\e(B")
- ("\e$(7"C#*\e(B" . "\e$(7%%\e(B")
- ("\e$(7"C#:\e(B" . "\e$(7%+\e(B")
- ("\e$(7"C#<\e(B" . "\e$(7%,\e(B")
- ("\e$(7"D#%\e(B" . "\e$(7%B\e(B")
- ("\e$(7"G#%\e(B" . "\e$(7%R\e(B")
- ("\e$(7"G#*\e(B" . "\e$(7%S\e(B")
- ("\e$(7"G#:\e(B" . "\e$(7%Z\e(B")
- ("\e$(7"!#>\e(B" . "\e$(7$!\e(B")
- ("\e$(7"##>\e(B" . "\e$(7$#\e(B")
- ("\e$(7"&#>\e(B" . "\e$(7$$\e(B")
- ("\e$(7"0#>\e(B" . "\e$(7$&\e(B")
- ("\e$(7"2#>\e(B" . "\e$(7$'\e(B")
- ("\e$(7"@#>\e(B" . "\e$(7$+\e(B")
- ("\e$(7"C#>\e(B" . "\e$(7$,\e(B")
- ("\e$(7"D#>\e(B" . "\e$(7$-\e(B")
- ("\e$(7"G#>\e(B" . "\e$(7$/\e(B")
- ("\e$(7"H#>\e(B" . "\e$(7$0\e(B")
- ("\e$(7"!#B\e(B" . "\e$(7$@\e(B")
- ("\e$(7"##B\e(B" . "\e$(7$B\e(B")
- ("\e$(7"5#B\e(B" . "\e$(7$C\e(B")
- ("\e$(7"7#B\e(B" . "\e$(7$E\e(B")
- ("\e$(7"9#B\e(B" . "\e$(7$F\e(B")
- ("\e$(7"!#C\e(B" . "\e$(7$P\e(B")
- ("\e$(7"##C\e(B" . "\e$(7$R\e(B")
- ("\e$(7"0#C\e(B" . "\e$(7$S\e(B")
- ("\e$(7"2#C\e(B" . "\e$(7$U\e(B")
- ("\e$(7"5#C\e(B" . "\e$(7$V\e(B")
- ("\e$(7"7#C\e(B" . "\e$(7$X\e(B")
- ("\e$(7"9#C\e(B" . "\e$(7$Y\e(B")
- ("\e$(7"G#C\e(B" . "\e$(7$[\e(B")
- ("\e$(7"H#C\e(B" . "\e$(7$\\e(B")
- ("\e$(7"(#C\e(B" . "\e$(7$]\e(B")
- ("\e$(7"!#D\e(B" . "\e$(7$`\e(B")
- ("\e$(7"##D\e(B" . "\e$(7$a\e(B")
- ("\e$(7"7#D\e(B" . "\e$(7$b\e(B")
- ("\e$(7"@#D\e(B" . "\e$(7$c\e(B")
- ("\e$(7"C#D\e(B" . "\e$(7$d\e(B")
- ("\e$(7"G#D\e(B" . "\e$(7$e\e(B")
- ("\e$(7"C#!\e(B" . "\e$(7%!\e(B")
- ("\e$(7"C##\e(B" . "\e$(7%"\e(B")
- ("\e$(7"C#(\e(B" . "\e$(7%$\e(B")
- ("\e$(7"C#0\e(B" . "\e$(7%&\e(B")
- ("\e$(7"C#2\e(B" . "\e$(7%'\e(B")
- ("\e$(7"C#4\e(B" . "\e$(7%(\e(B")
- ("\e$(7"C#7\e(B" . "\e$(7%)\e(B")
- ("\e$(7"C#9\e(B" . "\e$(7%*\e(B")
- ("\e$(7"D#!\e(B" . "\e$(7%@\e(B")
- ("\e$(7"D##\e(B" . "\e$(7%A\e(B")
- ("\e$(7"D#4\e(B" . "\e$(7!!\e(B") ; dummy 0x2121 added 2000/06/08 for transition l -> lng
- ("\e$(7"D#&\e(B" . "\e$(7%C\e(B")
- ("\e$(7"D#(\e(B" . "\e$(7%D\e(B")
- ("\e$(7"D#0\e(B" . "\e$(7%E\e(B")
- ("\e$(7"D#2\e(B" . "\e$(7%F\e(B")
- ("\e$(7"D#5\e(B" . "\e$(7%G\e(B")
- ("\e$(7"D#7\e(B" . "\e$(7%H\e(B")
- ("\e$(7"D#H\e(B" . "\e$(7%I\e(B")
- ("\e$(7"G#!\e(B" . "\e$(7%P\e(B")
- ("\e$(7"G##\e(B" . "\e$(7%Q\e(B")
- ("\e$(7"G#0\e(B" . "\e$(7%T\e(B")
- ("\e$(7"G#2\e(B" . "\e$(7%U\e(B")
- ("\e$(7"G#4\e(B" . "\e$(7%V\e(B")
- ("\e$(7"G#5\e(B" . "\e$(7%W\e(B")
- ("\e$(7"G#7\e(B" . "\e$(7%X\e(B")
- ("\e$(7"G#9\e(B" . "\e$(7%Y\e(B")))
-
-(defconst tibetan-regexp
- (let ((l (list tibetan-precomposed-transcription-alist
- tibetan-consonant-transcription-alist
- tibetan-vowel-transcription-alist
- tibetan-modifier-transcription-alist
- tibetan-subjoined-transcription-alist))
- (separator "\\|")
- tail pattern)
- (while l
- (setq tail (car l) l (cdr l))
- (while tail
- (setq pattern (cons separator (cons (car (car tail)) pattern))
- tail (cdr tail))))
- (apply 'concat (nreverse (cdr pattern))))
- "Regexp matching a Tibetan transcription of a composable Tibetan sequence.
-The result of matching is to be used for indexing alists at conversion
-from a roman transcription to the corresponding Tibetan character.")
-
-(defvar tibetan-precomposed-regexp
- (purecopy
- (let ((l tibetan-precomposed-transcription-alist)
- temp)
- (setq temp "^\\(")
- (setq temp
- (concat temp (car (car l))))
- (setq l (cdr l))
- (while l
- (setq temp
- (concat temp "\\|" (car (car l))))
- (setq l (cdr l)))
- (concat temp "\\)")))
- "Regexp string to match a romanized Tibetan complex consonant.
-The result of matching is to be used for indexing alists when the input key
-from an input method is converted to the corresponding precomposed glyph.")
-
-(defvar tibetan-precomposition-rule-regexp
- (purecopy
- (let ((l tibetan-precomposition-rule-alist)
- temp)
- (setq temp "\\(")
- (setq temp (concat temp (car (car l))))
- (setq l (cdr l))
- (while l
- (setq temp (concat temp "\\|" (car (car l))))
- (setq l (cdr l)))
- (concat temp "\\)")))
- "Regexp string to match a sequence of Tibetan consonantic components, i.e.,
-one base consonant and one or more subjoined consonants.
-The result of matching is to be used for indexing alist when the component
-sequence is converted to the corresponding precomposed glyph.
-This also matches some punctuation characters which need conversion.")
-
-(defvar tibetan-decomposed nil)
-(defvar tibetan-decomposed-temp nil)
-
-;; For automatic composition.
-(set-char-table-range
- composition-function-table '(#xF00 . #xFD1)
- (list (vector tibetan-composable-pattern 0 'font-shape-gstring)))
-
-(provide 'tibetan)
-
-;;; tibetan.el ends here
+;;; tibetan.el --- support for Tibetan language -*- coding: utf-8-emacs; -*-
+
+;; Copyright (C) 1997, 2001-2013 Free Software Foundation, Inc.
+;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005,
+;; 2006, 2007, 2008, 2009, 2010, 2011
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H14PRO021
+;; Copyright (C) 2003
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H13PRO009
+
+;; Author: Toru TOMABECHI <Toru.Tomabechi@orient.unil.ch>
+;; Created: Feb. 17. 1997
+;; Keywords: multilingual, Tibetan, i18n
+
+;; This file is part of GNU Emacs.
+
+;; GNU Emacs is free software: you can redistribute it and/or modify
+;; it under the terms of the GNU General Public License as published by
+;; the Free Software Foundation, either version 3 of the License, or
+;; (at your option) any later version.
+
+;; GNU Emacs is distributed in the hope that it will be useful,
+;; but WITHOUT ANY WARRANTY; without even the implied warranty of
+;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+;; GNU General Public License for more details.
+
+;; You should have received a copy of the GNU General Public License
+;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>.
+
+;;; History:
+
+;; 1997.03.13 Modification for special signs and punctuation.
+
+;;; Commentary:
+
+;;; Code:
+
+;;; Tibetan Character set.
+;;; \x2130 -- \x234a is a subset of Unicode v.2 \x0f00 - \x0fb9
+;;; with a slight modification. And there are some subjoined
+;;; consonants which are not specified in Unicode.
+;;; I hope I can add missing characters later.
+;;;
+;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
+;;;2120 // ; obsolete glyphs (2123-5)
+;;;2130 ༀ ༁ ༂ ༃ ༄ ༅ ༆ ༇ ༈ ༉ ༊ ་ ༌ ། ༎ ༏ ; Punctuation,
+;;;2140 ༐ ༑ ༒ ༓ ༔ ༕ ༖ ༗ ༘ ༙ ༚ ༛ ༜ ༝ ༞ ༟ ; Digits and
+;;;2150 ༠ ༡ ༢ ༣ ༤ ༥ ༦ ༧ ༨ ༩ ༪ ༫ ༬ ༭ ༮ ༯ ; Special signs.
+;;;2160 ༰ ༱ ༲ ༳ ༴ ༵ ༶ ༷ ༸ ༹ ༺ ༻ ༼ ༽ ༾ ༿ ;
+;;;2170 // ;
+;;;
+;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
+;;;2220 // ཀ ཁ ག གྷ ང ཅ ཆ ཇ ཉ ཊ ཋ ཌ ཌྷ ཎ ; Base consonants
+;;;2230 ཏ ཐ ད དྷ ན པ ཕ བ བྷ མ ཙ ཚ ཛ ཛྷ ཝ ཞ ; and
+;;;2240 ཟ འ ཡ ར ལ ཤ ཥ ས ཧ ཨ ཀྵ ཪ ; Vowel signs.
+;;;2250 ཱ ི ཱི ུ ཱུ ྲྀ ཷ ླྀ ཹ ེ ཻ ོ ཽ ཾ ; (\x2251 = vowel a)
+;;;2260 ཿ ྀ ཱྀ ྂ ྃ ྄ ྅ ྆ ྇ ྈ ྉ ྊ ྋ ; Long vowels and
+;;;2270 // ; vocalic r, l ARE
+;;; ; atomically
+;;; ; encoded.
+;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
+;;;2320 // ྐ ྑ ྒ ྒྷ ྔ ྕ ྖ ྗ ྙ ྚ ྛ ྜ ྜྷ ྞ ; Subjoined consonants
+;;;2330 ྟ ྠ ྡ ྡྷ ྣ ྤ ྥ ྦ ྦྷ ྨ ྩ ྪ ྫ ྫྷ ྭ ྮ ;
+;;;2340 ྯ ྰ ྱ ྲ ླ ྴ ྵ ྶ ྷ ྸ ྐྵ ྺ ྻ ྼ ྾ ;
+;;;2350 ྿ ࿀ ࿁ ࿂ ࿃ ࿄ ࿅ ࿆ ࿇ ࿈ ࿉ ࿊ ࿋ ࿌ ; Hereafter, the chars
+;;;2360 ࿏ ; are not specified
+;;;2370 // ; in Unicode.
+;;;
+;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
+;;;2420 // ; Precomposed
+;;;2430 ; consonants for
+;;;2440 ; ordinary Tibetan.
+;;;2450 ; They are decomposed
+;;;2460 ; into base and
+;;;2470 // ; subjoined consonants
+;;; ; when written on a
+;;; 00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F ; file in Tibetan
+;;;2520 // ; coding system.
+;;;2530 ;
+;;;2540 ;
+;;;2550 ;
+;;;2560 ;
+;;;2570 // ;
+;;;
+
+
+(define-coding-system 'tibetan-iso-8bit
+ "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)."
+ :coding-type 'iso-2022
+ :mnemonic ?Q
+ :designation [ascii tibetan nil nil]
+ :charset-list '(ascii tibetan))
+
+(define-coding-system-alias 'tibetan 'tibetan-iso-8bit)
+
+(set-language-info-alist
+ "Tibetan" '((charset tibetan tibetan-1-column)
+ (coding-system tibetan-iso-8bit)
+ (coding-priority iso-2022-7bit tibetan-iso-8bit)
+ (input-method . "tibetan-wylie")
+ (features tibet-util)
+ (documentation . t)
+ (sample-text . "Tibetan (བོད་སྐད་) ༄༅༅༎བཀྲ་ཤིས་བདེ་ལེགས༎ཨོཾ་མ་ཎི་པདྨེ་ཧའུྂ༎")))
+
+;; `འ' is included in the pattern for subjoined consonants because we
+;; treat it specially in tibetan-add-components.
+;; modified by Tomabechi 1999/12/10
+;; modified by Tomabechi 2000/06/08
+;; To allow infinite addition of vowels/modifiers
+;; as specified in Unicode v.3
+;; འ is removed from the class of subjoined. Tomabechi 2000/06/08
+;; (for Unicode support)
+(defconst tibetan-composable-pattern
+ "[ཀ-ཀྵཪ][ྐ-ྐྵྺྻྼ]*[ཱི-྄ཱཽྀྀ]*[ཾྂྃ྆-ྋ༙༵༷]*"
+ "Regexp matching a composable sequence of Tibetan characters.")
+
+;;;
+;;; Definitions of conversion data.
+;;;
+
+
+;;; alists for tibetan char <-> transcription conversion
+;;; longer transcription should come first
+(defconst tibetan-consonant-transcription-alist
+ '(("tsh" . "ཚ")
+ ("dzh" . "ཛྷ")
+ ("kSH" . "ཀྵ")
+ ("kh" . "ཁ")
+ ("gh" . "གྷ")
+ ("ng" . "ང")
+ ("ch" . "ཆ")
+ ("ny" . "ཉ")
+ ("TH" . "ཋ")
+ ("DH" . "ཌྷ")
+ ("th" . "ཐ")
+ ("dh" . "དྷ")
+ ("ph" . "ཕ")
+ ("bh" . "བྷ")
+ ("ts" . "ཙ")
+ ("dz" . "ཛ")
+ ("zh" . "ཞ")
+ ("sh" . "ཤ")
+ ("SH" . "ཥ")
+ ("k" . "ཀ")
+ ("g" . "ག")
+ ("c" . "ཅ")
+ ("j" . "ཇ")
+ ("T" . "ཊ")
+ ("D" . "ཌ")
+ ("N" . "ཎ")
+ ("t" . "ཏ")
+ ("d" . "ད")
+ ("n" . "ན")
+ ("p" . "པ")
+ ("b" . "བ")
+ ("m" . "མ")
+ ("w" . "ཝ")
+ ("z" . "ཟ")
+ ("'" . "འ")
+ ("y" . "ཡ")
+ ("r" . "ར")
+ ("l" . "ལ")
+ ("s" . "ས")
+ ("h" . "ཧ")
+ ("H" . "ཧ")
+ ("A" . "ཨ")
+ ;; Added by Tomabechi 1999/12/10
+ ("R" . "ཪ") ;; fixed form RA
+ ))
+
+
+(defconst tibetan-vowel-transcription-alist
+ '(
+ ;; Composite Vowels
+ ;; Added by Tomabechi 2000/06/08
+ ("frr" . "ཷ")
+ ("fll" . "ཹ")
+ ("fa" . "ཱ")
+ ("fi" . "ཱི")
+ ("fu" . "ཱུ")
+ ("fr" . "ྲྀ")
+ ("fl" . "ླྀ")
+ ("fI" . "ཱྀ")
+ ;; Normal Vowels
+ ("ai" . "ཻ")
+ ("au" . "ཽ")
+ ("ee" . "ཻ")
+ ("oo" . "ཽ")
+ ("a" . "") ; invisible vowel sign (\x2251)
+ ("i" . "ི")
+ ("u" . "ུ")
+ ("e" . "ེ")
+ ("o" . "ོ")
+ ("E" . "ཻ")
+ ("O" . "ཽ")
+ ("I" . "ྀ")
+ ("," . "྄") ; idem.
+ ))
+
+(defconst tibetan-modifier-transcription-alist
+ '(("M" . "ཾ")
+ ("~" . "ྂ")
+ ("`" . "ྃ")
+ ("x" . "ྈ")
+ ("X" . "ྉ")
+ ("v" . "྆")
+ ("V" . "྇")
+ ("q" . "ྊ")
+ ("Q" . "ྋ")
+ ("_/" . "༙")
+ ("_o" . "༷")
+ ("_O" . "༵")))
+
+(defconst tibetan-precomposed-transcription-alist
+ '(("phyw" . "")
+ ("tshw" . "")
+ ("rtsw" . "")
+ ("khw" . "")
+ ("nyw" . "")
+ ("tsw" . "")
+ ("zhw" . "")
+ ("shw" . "")
+ ("khy" . "")
+ ("phy" . "")
+ ("khr" . "")
+ ("thr" . "")
+ ("phr" . "")
+ ("shr" . "")
+ ("dzr" . "")
+ ("grw" . "")
+ ("rng" . "")
+ ("rny" . "")
+ ("rts" . "")
+ ("rdz" . "")
+ ("rgw" . "")
+ ("rky" . "")
+ ("rgy" . "")
+ ("rmy" . "")
+ ("lng" . "")
+ ("sng" . "")
+ ("sny" . "")
+ ("sts" . "")
+ ("sky" . "")
+ ("sgy" . "")
+ ("spy" . "")
+ ("sby" . "")
+ ("smy" . "")
+ ("skr" . "")
+ ("sgr" . "")
+ ("snr" . "")
+ ("spr" . "")
+ ("sbr" . "")
+ ("smr" . "")
+ ("kw" . "")
+ ("gw" . "")
+ ("cw" . "")
+ ("tw" . "")
+ ("dw" . "")
+ ("zw" . "")
+ ("rw" . "")
+ ("lw" . "")
+ ("sw" . "")
+ ("hw" . "")
+ ("ky" . "")
+ ("gy" . "")
+ ("py" . "")
+ ("by" . "")
+ ("my" . "")
+ ("kr" . "")
+ ("gr" . "")
+ ("tr" . "")
+ ("dr" . "")
+ ("pr" . "")
+ ("brk" . "བ")
+ ("brg" . "བ")
+ ("brng" . "བ")
+ ("brj" . "བ")
+ ("brny" . "བ")
+ ("brt" . "བ")
+ ("brd" . "བ")
+ ("brn" . "བ")
+ ("brts" . "བ")
+ ("brdz" . "བ")
+ ("brl" . "བ")
+ ("br" . "")
+ ("mr" . "")
+ ("sr" . "")
+ ("hr" . "")
+ ("jr" . "")
+ ("kl" . "")
+ ("gl" . "")
+ ("blt" . "བ")
+ ("bld" . "བ")
+ ("bl" . "")
+ ("zl" . "")
+ ("rl" . "")
+ ("sl" . "")
+ ("rk" . "")
+ ("rg" . "")
+ ("rj" . "")
+ ("rt" . "")
+ ("rd" . "")
+ ("rn" . "")
+ ("rb" . "")
+ ("rm" . "")
+ ("lk" . "")
+ ("lg" . "")
+ ("lc" . "")
+ ("lj" . "")
+ ("lt" . "")
+ ("ld" . "")
+ ("ln" . "") ; dummy \x2121
+ ("lp" . "")
+ ("lb" . "")
+ ("lh" . "")
+ ("sk" . "")
+ ("sg" . "")
+ ("st" . "")
+ ("sd" . "")
+ ("sn" . "")
+ ("sp" . "")
+ ("sb" . "")
+ ("sm" . ""))
+ )
+
+
+(defconst tibetan-subjoined-transcription-alist
+ (sort '(("+k" . "ྐ")
+ ("+kh" . "ྑ")
+ ("+g" . "ྒ")
+ ("+gh" . "ྒྷ")
+ ("+ng" . "ྔ")
+ ("+c" . "ྕ")
+ ("+ch" . "ྖ")
+ ("+j" . "ྗ")
+ ("+ny" . "ྙ")
+ ("+T" . "ྚ")
+ ("+TH" . "ྛ")
+ ("+D" . "ྜ")
+ ("+DH" . "ྜྷ")
+ ("+N" . "ྞ")
+ ("+t" . "ྟ")
+ ("+th" . "ྠ")
+ ("+d" . "ྡ")
+ ("+dh" . "ྡྷ")
+ ("+n" . "ྣ")
+ ("+p" . "ྤ")
+ ("+ph" . "ྥ")
+ ("+b" . "ྦ")
+ ("+bh" . "ྦྷ")
+ ("+m" . "ྨ")
+ ("+ts" . "ྩ")
+ ("+tsh" . "ྪ")
+ ("+dz" . "ྫ")
+ ("+dzh" . "ྫྷ")
+ ("+w" . "ྭ")
+ ("+zh" . "ྮ")
+ ("+z" . "ྯ")
+ ("+'" . "ྰ")
+ ("+y" . "ྱ")
+ ("+r" . "ྲ")
+ ("+l" . "ླ")
+ ("+sh" . "ྴ")
+ ("+SH" . "ྵ")
+ ("+s" . "ྶ")
+ ("+h" . "ྷ")
+ ("+A" . "ྸ")
+ ("+kSH" . "ྐྵ")
+ ;; Added by Tomabechi 1999/12/10
+ ("+W" . "ྺ") ;; fixed form subscribed WA
+ ("+Y" . "ྻ") ;; fixed form subscribed YA
+ ("+R" . "ྼ") ;; fixed form subscribed RA
+ )
+ (lambda (x y) (> (length (car x)) (length (car y))))))
+
+;;;
+;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
+;;;
+(defconst tibetan-base-to-subjoined-alist
+ '(("ཀ" . "ྐ")
+ ("ཁ" . "ྑ")
+ ("ག" . "ྒ")
+ ("གྷ" . "ྒྷ")
+ ("ང" . "ྔ")
+ ("ཅ" . "ྕ")
+ ("ཆ" . "ྖ")
+ ("ཇ" . "ྗ")
+ ("ཉ" . "ྙ")
+ ("ཊ" . "ྚ")
+ ("ཋ" . "ྛ")
+ ("ཌ" . "ྜ")
+ ("ཌྷ" . "ྜྷ")
+ ("ཎ" . "ྞ")
+ ("ཏ" . "ྟ")
+ ("ཐ" . "ྠ")
+ ("ད" . "ྡ")
+ ("དྷ" . "ྡྷ")
+ ("ན" . "ྣ")
+ ("པ" . "ྤ")
+ ("ཕ" . "ྥ")
+ ("བ" . "ྦ")
+ ("བྷ" . "ྦྷ")
+ ("མ" . "ྨ")
+ ("ཙ" . "ྩ")
+ ("ཚ" . "ྪ")
+ ("ཛ" . "ྫ")
+ ("ཛྷ" . "ྫྷ")
+ ("ཝ" . "ྭ")
+ ("ཞ" . "ྮ")
+ ("ཟ" . "ྯ")
+ ("འ" . "ྰ")
+ ("ཡ" . "ྱ")
+ ("ར" . "ྲ")
+ ("ལ" . "ླ")
+ ("ཤ" . "ྴ")
+ ("ཥ" . "ྵ")
+ ("ས" . "ྶ")
+ ("ཧ" . "ྷ")
+ ("ཨ" . "ྸ")
+ ("ཀྵ" . "ྐྵ")
+ ;; Added by Tomabechi 1999/12/10
+ ("ཪ" . "ྼ") ;; Fixed form RA (224B->234D)
+ ))
+
+;;; alist for Tibetan composite vowels (long i, vocalic r, etc.)
+;;; New variable. created by Tomabechi 2000/06/08
+(defconst tibetan-composite-vowel-alist
+ '(;; LONG A
+ ;; ("ཱ" . ((bc . tc) ?ཱ))
+ ;; LONG I
+ ("ཱི" . (?ཱ (tc . bc) ?ི))
+ ;; LONG U
+ ("ཱུ" . (?ཱ (bc . tc) ?ུ))
+ ;; VOCALIC R
+ ("ྲྀ" . (?ྲ (tc . bc) ?ྀ))
+ ;; LONG VOCALIC R
+ ("ཷ" . (?ྲ (bc . tc) ?ཱ (tc . bc) ?ྀ))
+ ;; VOCALIC L
+ ("ླྀ" . (?ླ (tc . bc) ?ྀ))
+ ;;་LONG VOCALIC L
+ ("ཹ" . (?ླ (bc . tc) ?ཱ (tc . bc) ?ྀ))
+ ;; LONG REVERSE I
+ ("ཱྀ" . (?ཱ (tc . bc) ?ྀ))
+ ))
+
+
+
+;;;
+;;; alist for Tibetan consonantic components <-> precomposed glyph conversion.
+;;; (includes some punctuation conversion rules)
+;;;
+(defconst tibetan-precomposition-rule-alist
+ `(("ཕྱྭ" . "")
+ ("གྲྭ" . "")
+ ("ཚྭ" . "")
+ ("རྩྭ" . "")
+ ("རྒྭ" . "")
+ ("རྐྱ" . "")
+ ("རྒྱ" . "")
+ ("རྨྱ" . "")
+ ("སྐྱ" . "")
+ ("སྒྱ" . "")
+ ("སྤྱ" . "")
+ ("སྦྱ" . "")
+ ("སྨྱ" . "")
+ ("སྐྲ" . "")
+ ("སྒྲ" . "")
+ ("སྣྲ" . "")
+ ("སྤྲ" . "")
+ ("སྦྲ" . "")
+ ("སྨྲ" . "")
+ ("ཁྭ" . "")
+ ("ཉྭ" . "")
+ ("ཙྭ" . "")
+ ("ཞྭ" . "")
+ ("ཤྭ" . "")
+ ("ཁྱ" . "")
+ ("ཕྱ" . "")
+ ("ཁྲ" . "")
+ ("ཐྲ" . "")
+ ("ཕྲ" . "")
+ ("ཤྲ" . "")
+ ("ཛྲ" . "")
+ ("རྔ" . "")
+ ("རྙ" . "")
+ ("རྩ" . "")
+ ("རྫ" . "")
+ ("ལྔ" . "")
+ ("སྔ" . "")
+ ("སྙ" . "")
+ ("སྩ" . "")
+ ("ཀྭ" . "")
+ ("གྭ" . "")
+ ("ཅྭ" . "")
+ ("ཏྭ" . "")
+ ("དྭ" . "")
+ ("ཟྭ" . "")
+ ("རྭ" . "")
+ ("ལྭ" . "")
+ ("སྭ" . "")
+ ("ཧྭ" . "")
+ ("ཀྱ" . "")
+ ("གྱ" . "")
+ ("པྱ" . "")
+ ("བྱ" . "")
+ ("མྱ" . "")
+ ("ཀྲ" . "")
+ ("གྲ" . "")
+ ("ཏྲ" . "")
+ ("དྲ" . "")
+ ("པྲ" . "")
+ ("བྲ" . "")
+ ("མྲ" . "")
+ ("སྲ" . "")
+ ("ཧྲ" . "")
+ ("ཇྲ" . "")
+ ("ཀླ" . "")
+ ("གླ" . "")
+ ("བླ" . "")
+ ("ཟླ" . "")
+ ("རླ" . "")
+ ("སླ" . "")
+ ("རྐ" . "")
+ ("རྒ" . "")
+ ("རྗ" . "")
+ ("རྟ" . "")
+ ("རྡ" . "")
+ ("རྣ" . "")
+ ("རྦ" . "")
+ ("རྨ" . "")
+ ("ལྐ" . "")
+ ("ལྒ" . "")
+ ("ལྣ" . "") ; dummy 0x2121 added 2000/06/08 for transition l -> lng
+ ("ལྕ" . "")
+ ("ལྗ" . "")
+ ("ལྟ" . "")
+ ("ལྡ" . "")
+ ("ལྤ" . "")
+ ("ལྦ" . "")
+ ("ལྷ" . "")
+ ("སྐ" . "")
+ ("སྒ" . "")
+ ("སྟ" . "")
+ ("སྡ" . "")
+ ("སྣ" . "")
+ ("སྤ" . "")
+ ("སྦ" . "")
+ ("སྨ" . "")))
+
+(defconst tibetan-regexp
+ (let ((l (list tibetan-precomposed-transcription-alist
+ tibetan-consonant-transcription-alist
+ tibetan-vowel-transcription-alist
+ tibetan-modifier-transcription-alist
+ tibetan-subjoined-transcription-alist))
+ (separator "\\|")
+ tail pattern)
+ (while l
+ (setq tail (car l) l (cdr l))
+ (while tail
+ (setq pattern (cons separator (cons (car (car tail)) pattern))
+ tail (cdr tail))))
+ (apply 'concat (nreverse (cdr pattern))))
+ "Regexp matching a Tibetan transcription of a composable Tibetan sequence.
+The result of matching is to be used for indexing alists at conversion
+from a roman transcription to the corresponding Tibetan character.")
+
+(defvar tibetan-precomposed-regexp
+ (purecopy
+ (let ((l tibetan-precomposed-transcription-alist)
+ temp)
+ (setq temp "^\\(")
+ (setq temp
+ (concat temp (car (car l))))
+ (setq l (cdr l))
+ (while l
+ (setq temp
+ (concat temp "\\|" (car (car l))))
+ (setq l (cdr l)))
+ (concat temp "\\)")))
+ "Regexp string to match a romanized Tibetan complex consonant.
+The result of matching is to be used for indexing alists when the input key
+from an input method is converted to the corresponding precomposed glyph.")
+
+(defvar tibetan-precomposition-rule-regexp
+ (purecopy
+ (let ((l tibetan-precomposition-rule-alist)
+ temp)
+ (setq temp "\\(")
+ (setq temp (concat temp (car (car l))))
+ (setq l (cdr l))
+ (while l
+ (setq temp (concat temp "\\|" (car (car l))))
+ (setq l (cdr l)))
+ (concat temp "\\)")))
+ "Regexp string to match a sequence of Tibetan consonantic components, i.e.,
+one base consonant and one or more subjoined consonants.
+The result of matching is to be used for indexing alist when the component
+sequence is converted to the corresponding precomposed glyph.
+This also matches some punctuation characters which need conversion.")
+
+(defvar tibetan-decomposed nil)
+(defvar tibetan-decomposed-temp nil)
+
+;; For automatic composition.
+(set-char-table-range
+ composition-function-table '(#xF00 . #xFD1)
+ (list (vector tibetan-composable-pattern 0 'font-shape-gstring)))
+
+(provide 'tibetan)
+
+;;; tibetan.el ends here
HCoop / bpt / emacs.git / blobdiff