1 ;;; thai-util.el --- utilities for Thai -*- coding: iso-2022-7bit; -*-
3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
4 ;; Licensed to the Free Software Foundation.
6 ;; National Institute of Advanced Industrial Science and Technology (AIST)
7 ;; Registration Number H13PRO009
9 ;; Keywords: mule, multilingual, Thai, i18n
11 ;; This file is part of GNU Emacs.
13 ;; GNU Emacs is free software; you can redistribute it and/or modify
14 ;; it under the terms of the GNU General Public License as published by
15 ;; the Free Software Foundation; either version 2, or (at your option)
18 ;; GNU Emacs is distributed in the hope that it will be useful,
19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
21 ;; GNU General Public License for more details.
23 ;; You should have received a copy of the GNU General Public License
24 ;; along with GNU Emacs; see the file COPYING. If not, write to the
25 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
26 ;; Boston, MA 02111-1307, USA.
32 ;; Setting information of Thai characters.
34 (defconst thai-category-table (make-category-table))
35 (define-category ?c "Thai consonant" thai-category-table)
36 (define-category ?v "Thai upper/lower vowel" thai-category-table)
37 (define-category ?t "Thai tone" thai-category-table)
39 ;; The general composing rules are as follows:
43 ;; CV -> C, CT -> C, CVT -> C, Cv -> C, CvT -> C
46 ;; where C: consonant, V: vowel upper, v: vowel lower, T: tone mark.
48 (defvar thai-composition-pattern "\\cc\\(\\ct\\|\\cv\\ct?\\)"
49 "Regular expression matching a Thai composite sequence.")
51 (let ((l '((?
\e,T!
\e(B consonant "LETTER KO KAI") ; 0xA1
52 (?
\e,T"
\e(B consonant "LETTER KHO KHAI") ; 0xA2
53 (?
\e,T#
\e(B consonant "LETTER KHO KHUAT") ; 0xA3
54 (?
\e,T$
\e(B consonant "LETTER KHO KHWAI") ; 0xA4
55 (?
\e,T%
\e(B consonant "LETTER KHO KHON") ; 0xA5
56 (?
\e,T&
\e(B consonant "LETTER KHO RAKHANG") ; 0xA6
57 (?
\e,T'
\e(B consonant "LETTER NGO NGU") ; 0xA7
58 (?
\e,T(
\e(B consonant "LETTER CHO CHAN") ; 0xA8
59 (?
\e,T)
\e(B consonant "LETTER CHO CHING") ; 0xA9
60 (?
\e,T*
\e(B consonant "LETTER CHO CHANG") ; 0xAA
61 (?
\e,T+
\e(B consonant "LETTER SO SO") ; 0xAB
62 (?
\e,T,
\e(B consonant "LETTER CHO CHOE") ; 0xAC
63 (?
\e,T-
\e(B consonant "LETTER YO YING") ; 0xAD
64 (?
\e,T.
\e(B consonant "LETTER DO CHADA") ; 0xAE
65 (?
\e,T/
\e(B consonant "LETTER TO PATAK") ; 0xAF
66 (?
\e,T0
\e(B consonant "LETTER THO THAN") ; 0xB0
67 (?
\e,T1
\e(B consonant "LETTER THO NANGMONTHO") ; 0xB1
68 (?
\e,T2
\e(B consonant "LETTER THO PHUTHAO") ; 0xB2
69 (?
\e,T3
\e(B consonant "LETTER NO NEN") ; 0xB3
70 (?
\e,T4
\e(B consonant "LETTER DO DEK") ; 0xB4
71 (?
\e,T5
\e(B consonant "LETTER TO TAO") ; 0xB5
72 (?
\e,T6
\e(B consonant "LETTER THO THUNG") ; 0xB6
73 (?
\e,T7
\e(B consonant "LETTER THO THAHAN") ; 0xB7
74 (?
\e,T8
\e(B consonant "LETTER THO THONG") ; 0xB8
75 (?
\e,T9
\e(B consonant "LETTER NO NU") ; 0xB9
76 (?
\e,T:
\e(B consonant "LETTER BO BAIMAI") ; 0xBA
77 (?
\e,T;
\e(B consonant "LETTER PO PLA") ; 0xBB
78 (?
\e,T<
\e(B consonant "LETTER PHO PHUNG") ; 0xBC
79 (?
\e,T=
\e(B consonant "LETTER FO FA") ; 0xBD
80 (?
\e,T>
\e(B consonant "LETTER PHO PHAN") ; 0xBE
81 (?
\e,T?
\e(B consonant "LETTER FO FAN") ; 0xBF
82 (?
\e,T@
\e(B consonant "LETTER PHO SAMPHAO") ; 0xC0
83 (?
\e,TA
\e(B consonant "LETTER MO MA") ; 0xC1
84 (?
\e,TB
\e(B consonant "LETTER YO YAK") ; 0xC2
85 (?
\e,TC
\e(B consonant "LETTER RO RUA") ; 0xC3
86 (?
\e,TD
\e(B vowel-base "LETTER RU (Pali vowel letter)") ; 0xC4
87 (?
\e,TE
\e(B consonant "LETTER LO LING") ; 0xC5
88 (?
\e,TF
\e(B vowel-base "LETTER LU (Pali vowel letter)") ; 0xC6
89 (?
\e,TG
\e(B consonant "LETTER WO WAEN") ; 0xC7
90 (?
\e,TH
\e(B consonant "LETTER SO SALA") ; 0xC8
91 (?
\e,TI
\e(B consonant "LETTER SO RUSI") ; 0xC9
92 (?
\e,TJ
\e(B consonant "LETTER SO SUA") ; 0xCA
93 (?
\e,TK
\e(B consonant "LETTER HO HIP") ; 0xCB
94 (?
\e,TL
\e(B consonant "LETTER LO CHULA") ; 0xCC
95 (?
\e,TM
\e(B consonant "LETTER O ANG") ; 0xCD
96 (?
\e,TN
\e(B consonant "LETTER HO NOK HUK") ; 0xCE
97 (?
\e,TO
\e(B special "PAI YAN NOI (abbreviation)") ; 0xCF
98 (?
\e,TP
\e(B vowel-base "VOWEL SIGN SARA A") ; 0xD0
99 (?
\e,TQ
\e(B vowel-upper "VOWEL SIGN MAI HAN-AKAT N/S-T") ; 0xD1
100 (?
\e,TR
\e(B vowel-base "VOWEL SIGN SARA AA") ; 0xD2
101 (?
\e,TS
\e(B vowel-base "VOWEL SIGN SARA AM") ; 0xD3
102 (?
\e,TT
\e(B vowel-upper "VOWEL SIGN SARA I N/S-T") ; 0xD4
103 (?
\e,TU
\e(B vowel-upper "VOWEL SIGN SARA II N/S-T") ; 0xD5
104 (?
\e,TV
\e(B vowel-upper "VOWEL SIGN SARA UE N/S-T") ; 0xD6
105 (?
\e,TW
\e(B vowel-upper "VOWEL SIGN SARA UEE N/S-T") ; 0xD7
106 (?
\e,TX
\e(B vowel-lower "VOWEL SIGN SARA U N/S-B") ; 0xD8
107 (?
\e,TY
\e(B vowel-lower "VOWEL SIGN SARA UU N/S-B") ; 0xD9
108 (?
\e,TZ
\e(B vowel-lower "VOWEL SIGN PHINTHU N/S-B (Pali virama)") ; 0xDA
109 (?
\e,T[
\e(B invalid nil) ; 0xDA
110 (?
\e,T\
\e(B invalid nil) ; 0xDC
111 (?
\e,T]
\e(B invalid nil) ; 0xDC
112 (?
\e,T^
\e(B invalid nil) ; 0xDC
113 (?
\e,T_
\e(B special "BAHT SIGN (currency symbol)") ; 0xDF
114 (?
\e,T`
\e(B vowel-base "VOWEL SIGN SARA E") ; 0xE0
115 (?
\e,Ta
\e(B vowel-base "VOWEL SIGN SARA AE") ; 0xE1
116 (?
\e,Tb
\e(B vowel-base "VOWEL SIGN SARA O") ; 0xE2
117 (?
\e,Tc
\e(B vowel-base "VOWEL SIGN SARA MAI MUAN") ; 0xE3
118 (?
\e,Td
\e(B vowel-base "VOWEL SIGN SARA MAI MALAI") ; 0xE4
119 (?
\e,Te
\e(B vowel-base "LAK KHANG YAO") ; 0xE5
120 (?
\e,Tf
\e(B special "MAI YAMOK (repetion)") ; 0xE6
121 (?
\e,Tg
\e(B vowel-upper "VOWEL SIGN MAI TAI KHU N/S-T") ; 0xE7
122 (?
\e,Th
\e(B tone "TONE MAI EK N/S-T") ; 0xE8
123 (?
\e,Ti
\e(B tone "TONE MAI THO N/S-T") ; 0xE9
124 (?
\e,Tj
\e(B tone "TONE MAI TRI N/S-T") ; 0xEA
125 (?
\e,Tk
\e(B tone "TONE MAI CHATTAWA N/S-T") ; 0xEB
126 (?
\e,Tl
\e(B tone "THANTHAKHAT N/S-T (cancellation mark)") ; 0xEC
127 (?
\e,Tm
\e(B tone "NIKKHAHIT N/S-T (final nasal)") ; 0xED
128 (?
\e,Tn
\e(B vowel-upper "YAMAKKAN N/S-T") ; 0xEE
129 (?
\e,To
\e(B special "FONRMAN") ; 0xEF
130 (?
\e,Tp
\e(B special "DIGIT ZERO") ; 0xF0
131 (?
\e,Tq
\e(B special "DIGIT ONE") ; 0xF1
132 (?
\e,Tr
\e(B special "DIGIT TWO") ; 0xF2
133 (?
\e,Ts
\e(B special "DIGIT THREE") ; 0xF3
134 (?
\e,Tt
\e(B special "DIGIT FOUR") ; 0xF4
135 (?
\e,Tu
\e(B special "DIGIT FIVE") ; 0xF5
136 (?
\e,Tv
\e(B special "DIGIT SIX") ; 0xF6
137 (?
\e,Tw
\e(B special "DIGIT SEVEN") ; 0xF7
138 (?
\e,Tx
\e(B special "DIGIT EIGHT") ; 0xF8
139 (?
\e,Ty
\e(B special "DIGIT NINE") ; 0xF9
140 (?
\e,Tz
\e(B special "ANGKHANKHU (ellipsis)") ; 0xFA
141 (?
\e,T{
\e(B special "KHOMUT (beginning of religious texts)") ; 0xFB
142 (?
\e,T|
\e(B invalid nil) ; 0xFC
143 (?
\e,T}
\e(B invalid nil) ; 0xFD
144 (?
\e,T~
\e(B invalid nil) ; 0xFE
148 (setq elm (car l) l (cdr l))
149 (let ((char (car elm))
151 (put-char-code-property char 'phonetic-type ptype)
152 (cond ((eq ptype 'consonant)
153 (modify-category-entry char ?c thai-category-table))
154 ((memq ptype '(vowel-upper vowel-lower))
155 (modify-category-entry char ?v thai-category-table))
157 (modify-category-entry char ?t thai-category-table)))
158 (put-char-code-property char 'name (nth 2 elm)))))
161 (defun thai-compose-region (beg end)
162 "Compose Thai characters in the region.
163 When called from a program, expects two arguments,
164 positions (integers or markers) specifying the region."
167 (narrow-to-region beg end)
168 (goto-char (point-min))
169 (with-category-table thai-category-table
170 (while (re-search-forward thai-composition-pattern nil t)
171 (compose-region (match-beginning 0) (match-end 0))))))
174 (defun thai-compose-string (string)
175 "Compose Thai characters in STRING and return the resulting string."
176 (with-category-table thai-category-table
178 (while (setq idx (string-match thai-composition-pattern string idx))
179 (compose-string string idx (match-end 0))
180 (setq idx (match-end 0)))))
184 (defun thai-compose-buffer ()
185 "Compose Thai characters in the current buffer."
187 (thai-compose-region (point-min) (point-max)))
190 (defun thai-composition-function (pos &optional string)
192 (let ((pattern "[
\e,T!
\e(B-
\e,TCEG
\e(B-
\e,TN!
\e(B-
\e,TCEG
\e(B-
\e,TN
\e(B][
\e,TQT
\e(B-
\e,TWgnX
\e(B-
\e,TZQT
\e(B-
\e,TWgnX
\e(B-
\e,TZ
\e(B]?[
\e,Th
\e(B-
\e,Tmh
\e(B-
\e,Tm
\e(B]?"))
195 (eq (string-match pattern string pos) pos))
197 (compose-string string pos (match-end 0))))
198 (if (>= pos (point-min))
201 (if (looking-at pattern)
203 (compose-region pos (match-end 0)))))))))
208 ;;; arch-tag: 59425d6a-8cf9-4e06-a6ab-8ab7dc7a7a97
209 ;;; thai-util.el ends here