1;;; tml-util.el --- support for composing tamil characters -*-coding: iso-2022-7bit;-*- 2 3;; Copyright (C) 2001, 2003, 2004, 2005, 2006, 2007 Free Software Foundation, Inc. 4 5;; Maintainer: KAWABATA, Taichi <kawabata@m17n.org> 6;; Keywords: multilingual, Indian, Tamil 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., 51 Franklin Street, Fifth Floor, 23;; Boston, MA 02110-1301, USA. 24 25;; Created: Nov. 08. 2002 26 27;;; Commentary: 28 29;; This file provides character(Unicode) to glyph(CDAC) conversion and 30;; composition of Tamil script characters. 31 32;;; Code: 33 34;; Tamil Composable Pattern 35;; C .. Consonants 36;; V .. Vowel 37;; H .. Pulli 38;; M .. Matra 39;; V .. Vowel 40;; A .. Anuswar 41;; D .. Chandrabindu 42;; 1. vowel 43;; V 44;; 2. syllable : only ligature-formed pattern forms composition. 45;; (CkHCs|C)(H|M)? 46;; 3. sri special 47;; (CsHCrVi) 48 49;; oririnal 50;; ((CH)?(CH)?(CH)?CH)?C(H|M?(A|D)?)? 51 52(defconst tamil-consonant 53 "[$,1<5(B-$,1<Y(B]") 54 55(defconst tamil-composable-pattern 56 (concat 57 "\\([$,1<%(B-$,1<4(B]\\)\\|" 58 "[$,1<"<#(B]\\|" ;; vowel modifier considered independent 59 "\\(\\(?:\\(?:$,1<5(B\\)\\|[$,1<5(B-$,1 (B]\\)[$,1 ^(B-$,1 (B]?\\)\\|" 60 "\\($,1 `(B\\)") 61 "Regexp matching a composable sequence of Tamil characters.") 62 63;;;###autoload 64(defun tamil-compose-region (from to) 65 (interactive "r") 66 (save-excursion 67 (save-restriction 68 (narrow-to-region from to) 69 (goto-char (point-min)) 70 (while (re-search-forward tamil-composable-pattern nil t) 71 (tamil-compose-syllable-region (match-beginning 0) 72 (match-end 0)))))) 73(defun tamil-compose-string (string) 74 (with-temp-buffer 75 (insert (decompose-string string)) 76 (tamil-compose-region (point-min) (point-max)) 77 (buffer-string))) 78 79;;;###autoload 80(defun tamil-post-read-conversion (len) 81 (save-excursion 82 (save-restriction 83 (let ((buffer-modified-p (buffer-modified-p))) 84 (narrow-to-region (point) (+ (point) len)) 85 (tamil-compose-region (point-min) (point-max)) 86 (set-buffer-modified-p buffer-modified-p) 87 (- (point-max) (point-min)))))) 88 89(defun tamil-range (from to) 90 "Make the list of the integers of range FROM to TO." 91 (let (result) 92 (while (<= from to) (setq result (cons to result) to (1- to))) result)) 93 94(defun tamil-regexp-of-hashtbl-keys (hashtbl) 95 "Return a regular expression that matches all keys in hashtable HASHTBL." 96 (let ((max-specpdl-size 1000)) 97 (regexp-opt 98 (sort 99 (let (dummy) 100 (maphash (function (lambda (key val) (setq dummy (cons key dummy)))) hashtbl) 101 dummy) 102 (function (lambda (x y) (> (length x) (length y)))))))) 103 104 105;;;###autoload 106(defun tamil-composition-function (from to pattern &optional string) 107 "Compose Tamil characters in REGION, or STRING if specified. 108Assume that the REGION or STRING must fully match the composable 109PATTERN regexp." 110 (if string (tamil-compose-syllable-string string) 111 (tamil-compose-syllable-region from to)) 112 (- to from)) 113 114;; Register a function to compose Tamil characters. 115(mapc 116 (function (lambda (ucs) 117 (aset composition-function-table (decode-char 'ucs ucs) 118 (list (cons tamil-composable-pattern 119 'tamil-composition-function))))) 120 (nconc '(#x0b82 #x0b83) (tamil-range #x0b85 #x0bb9))) 121 122;; Notes on conversion steps. 123 124;; 1. chars to glyphs 125;; Simple replacement of characters to glyphs is done. 126 127;; 2. glyphs reordering. 128;; following "$,4)j(B", "$,4)k(B", "$,4)l(B" goes to the front. 129 130;; 3. glyphs to glyphs 131;; reordered vowels are ligatured to consonants. 132 133;; 4. Composition. 134;; left modifiers will be attached at the left. 135;; others will be attached right. 136 137(defvar tml-char-glyph 138 '(;; various signs 139 ;;("$,1<"(B" . "") 140 ("$,1<#(B" . "$,4*G(B") 141 ;; Independent Vowels 142 ("$,1<%(B" . "$,4*<(B") 143 ("$,1<&(B" . "$,4*=(B") 144 ("$,1<'(B" . "$,4*>(B") 145 ("$,1<((B" . "$,4*?(B") 146 ("$,1<)(B" . "$,4*@(B") 147 ("$,1<*(B" . "$,4*A(B") 148 ("$,1<.(B" . "$,4*B(B") 149 ("$,1</(B" . "$,4*C(B") 150 ("$,1<0(B" . "$,4*D(B") 151 ("$,1<2(B" . "$,4*E(B") 152 ("$,1<3(B" . "$,4*F(B") 153 ("$,1<4(B" . "$,4*E*W(B") 154 ;; Consonants 155 ("$,1<5<m<W<m(B" . "$,4):(B") ; ks. 156 ("$,1<5<m<W(B" . "$,4*^(B") ; ks 157 ("$,1<5(B" . "$,4*H(B") 158 159 ("$,1<9(B" . "$,4*I(B") 160 ("$,1<:(B" . "$,4*J(B") 161 ("$,1<<(B" . "$,4*\(B") 162 ("$,1<<<m(B" . "$,4)8(B") 163 ("$,1<>(B" . "$,4*K(B") 164 ("$,1<?(B" . "$,4*L(B") 165 ("$,1<C(B" . "$,4*M(B") 166 ("$,1<D(B" . "$,4*N(B") 167 ("$,1<H(B" . "$,4*O(B") 168 ("$,1<I(B" . "$,4*Y(B") 169 ("$,1<I<m(B" . "$,4)a(B") 170 ("$,1<J(B" . "$,4*P(B") 171 ("$,1<N(B" . "$,4*Q(B") 172 ("$,1<O(B" . "$,4*R(B") 173 ("$,1<P(B" . "$,4*S(B") 174 ("$,1<Q(B" . "$,4*X(B") 175 ("$,1<R(B" . "$,4*T(B") 176 ("$,1<S(B" . "$,4*W(B") 177 ("$,1<T(B" . "$,4*V(B") 178 ("$,1<U(B" . "$,4*U(B") 179 ("$,1<W(B" . "$,4*[(B") 180 ("$,1<W<m(B" . "$,4)7(B") 181 ("$,1<W<m<P<`(B" . "$,4*_(B") 182 ("$,1<X(B" . "$,4*Z(B") 183 ("$,1<X<m(B" . "$,4)6(B") 184 ("$,1<Y(B" . "$,4*](B") 185 ("$,1<Y<m(B" . "$,4)9(B") 186 187 ;; Dependent vowel signs 188 ("$,1<^(B" . "$,4)c(B") 189 ("$,1<_(B" . "$,4)d(B") 190 ("$,1<`(B" . "$,4)f(B") 191 ("$,1<a(B" . "$,4)g(B") 192 ("$,1<b(B" . "$,4)h(B") 193 ("$,1<f(B" . "$,4)j(B") 194 ("$,1<g(B" . "$,4)k(B") 195 ("$,1<h(B" . "$,4)l(B") 196 ("$,1<j(B" . "$,4)j)c(B") 197 ("$,1<k(B" . "$,4)k)c(B") 198 ("$,1<l(B" . "$,4)j*W(B") 199 200 ;; Various signs 201 ("$,1<m(B" . "$,4)b(B") 202 ("$,1<w(B" . "nil") ;; not supported? 203 )) 204 205(defvar tml-char-glyph-hash 206 (let* ((hash (make-hash-table :test 'equal))) 207 (mapc (function (lambda (x) (puthash (car x) (cdr x) hash))) 208 tml-char-glyph) 209 hash)) 210 211(defvar tml-char-glyph-regexp 212 (tamil-regexp-of-hashtbl-keys tml-char-glyph-hash)) 213 214;; Tamil languages needed to be reordered. 215 216(defvar tml-consonants-regexp 217 "[$,4*H*^*I*J*\*K*L*M*N*O*Y*P*Q*R*S*X*T*W*V*U*[*Z*](B]") 218 219(defvar tml-glyph-reorder-key-glyphs "[$,4)j)k)l(B]") 220 221(defvar tml-glyph-reordering-regexp-list 222 (cons 223 (concat "\\(" tml-consonants-regexp "\\)\\([$,4)j)k)l(B]\\)") "\\2\\1")) 224 225;; Tamil vowel modifiers to be ligatured. 226(defvar tml-glyph-glyph 227 '( 228 ("$,4*H)d(B" . "$,4(a(B") ; ki 229 ("$,4*^)d(B" . "$,4(v(B") ; ksi 230 ("$,4*^)f(B" . "$,4)2(B") ; ksi~ 231 ("$,4*I)d(B" . "$,4(b(B") ; n^i 232 ("$,4*J)d(B" . "$,4(c(B") ; ci 233 ("$,4*K)d(B" . "$,4(d(B") ; n~i 234 ("$,4*L)d(B" . "$,4)n(B") ; t.i 235 ("$,4*M)d(B" . "$,4(e(B") ; n.i 236 ("$,4*N)d(B" . "$,4(f(B") ; ti 237 ("$,4*O)d(B" . "$,4(g(B") ; ni 238 ("$,4*P)d(B" . "$,4(h(B") ; pi 239 ("$,4*Q)d(B" . "$,4(i(B") ; mi 240 ("$,4*R)d(B" . "$,4(j(B") ; yi 241 ("$,4*S)d(B" . "$,4(k(B") ; ri 242 ("$,4*T)d(B" . "$,4(l(B") ; li 243 ("$,4*U)d(B" . "$,4(m(B") ; vi 244 ("$,4*V)d(B" . "$,4(n(B") ; l_i 245 ("$,4*W)d(B" . "$,4(o(B") ; l.i 246 ("$,4*X)d(B" . "$,4(p(B") ; r_i 247 ("$,4*Y)d(B" . "$,4(q(B") ; n_i 248 ("$,4*Z)d(B" . "$,4(r(B") ; si 249 ("$,4*[)d(B" . "$,4(s(B") ; s'i 250 ("$,4*\)d(B" . "$,4(t(B") ; ji 251 ("$,4*])d(B" . "$,4(u(B") ; hi 252 253 ("$,4*H)f(B" . "$,4(w(B") ; ki~ 254 ("$,4*I)f(B" . "$,4(x(B") ; n^i~ 255 ("$,4*J)f(B" . "$,4(y(B") ; ci~ 256 ("$,4*K)f(B" . "$,4(z(B") ; n~i~ 257 ("$,4*L)f(B" . "$,4)o(B") ; t.i~ 258 ("$,4*M)f(B" . "$,4)!(B") ; n.i~ 259 ("$,4*N)f(B" . "$,4)"(B") ; ti~ 260 ("$,4*O)f(B" . "$,4)#(B") ; ni~ 261 ("$,4*P)f(B" . "$,4)$(B") ; pi~ 262 ("$,4*Q)f(B" . "$,4)%(B") ; mi~ 263 ("$,4*R)f(B" . "$,4)&(B") ; yi~ 264 ("$,4*S)f(B" . "$,4)'(B") ; ri~ 265 ("$,4*T)f(B" . "$,4)((B") ; li~ 266 ("$,4*U)f(B" . "$,4))(B") ; vi~ 267 ("$,4*V)f(B" . "$,4)*(B") ; l_i~ 268 ("$,4*W)f(B" . "$,4)+(B") ; l.i~ 269 ("$,4*X)f(B" . "$,4),(B") ; r_i~ 270 ("$,4*Y)f(B" . "$,4)-(B") ; n_i~ 271 ("$,4*Z)f(B" . "$,4).(B") ; si~ 272 ("$,4*[)f(B" . "$,4)/(B") ; s'i~ 273 ("$,4*\)f(B" . "$,4)0(B") ; ji~ 274 ("$,4*])f(B" . "$,4)1(B") ; hi~ 275 276 ("$,4*H)g(B" . "$,4)p(B") ; ku 277 ("$,4*I)g(B" . "$,4)q(B") ; n^u 278 ("$,4*J)g(B" . "$,4)r(B") ; cu 279 ("$,4*K)g(B" . "$,4)s(B") ; n~u 280 ("$,4*L)g(B" . "$,4)t(B") ; t.u 281 ("$,4*M)g(B" . "$,4)u(B") ; n.u 282 ("$,4*N)g(B" . "$,4)v(B") ; tu 283 ("$,4*O)g(B" . "$,4)x(B") ; nu 284 ("$,4*P)g(B" . "$,4)y(B") ; pu 285 ("$,4*Q)g(B" . "$,4)z(B") ; mu 286 ("$,4*R)g(B" . "$,4){(B") ; yu 287 ("$,4*S)g(B" . "$,4)|(B") ; ru 288 ("$,4*T)g(B" . "$,4)}(B") ; lu 289 ("$,4*U)g(B" . "$,4)~(B") ; vu 290 ("$,4*V)g(B" . "$,4)(B") ; l_u 291 ("$,4*W)g(B" . "$,4* (B") ; l.u 292 ("$,4*X)g(B" . "$,4*!(B") ; r_u 293 ("$,4*Y)g(B" . "$,4*"(B") ; n_u 294 295 ("$,4*H)h(B" . "$,4*#(B") ; ku~ 296 ("$,4*I)h(B" . "$,4*$(B") ; n^u~ 297 ("$,4*J)h(B" . "$,4*%(B") ; cu~ 298 ("$,4*K)h(B" . "$,4*&(B") ; n~u~ 299 ("$,4*L)h(B" . "$,4*'(B") ; t.u~ 300 ("$,4*M)h(B" . "$,4*((B") ; n.u~ 301 ("$,4*N)h(B" . "$,4*)(B") ; tu~ 302 ("$,4*O)h(B" . "$,4*+(B") ; nu~ 303 ("$,4*P)h(B" . "$,4*,(B") ; pu~ 304 ("$,4*Q)h(B" . "$,4*-(B") ; mu~ 305 ("$,4*R)h(B" . "$,4*.(B") ; yu~ 306 ("$,4*S)h(B" . "$,4*/(B") ; ru~ 307 ("$,4*T)h(B" . "$,4*6(B") ; lu~ 308 ("$,4*U)h(B" . "$,4*7(B") ; vu~ 309 ("$,4*V)h(B" . "$,4*8(B") ; l_u~ 310 ("$,4*W)h(B" . "$,4*9(B") ; l.u~ 311 ("$,4*X)h(B" . "$,4*:(B") ; r_u~ 312 ("$,4*Y)h(B" . "$,4*;(B") ; n_u~ 313 )) 314 315(defvar tml-glyph-glyph-hash 316 (let* ((hash (make-hash-table :test 'equal))) 317 (mapc (function (lambda (x) (puthash (car x) (cdr x) hash))) 318 tml-glyph-glyph) 319 hash)) 320 321(defvar tml-glyph-glyph-regexp 322 (tamil-regexp-of-hashtbl-keys tml-glyph-glyph-hash)) 323 324(defun tamil-compose-syllable-string (string) 325 (with-temp-buffer 326 (insert (decompose-string string)) 327 (tamil-compose-syllable-region (point-min) (point-max)) 328 (buffer-string))) 329 330(defun tamil-compose-syllable-region (from to) 331 "Compose tamil syllable in region FROM to TO." 332 (let (glyph-str match-str glyph-reorder-regexps) 333 (save-excursion 334 (save-restriction 335 (narrow-to-region from to) 336 (goto-char (point-min)) 337 ;; char-glyph-conversion 338 (while (re-search-forward tml-char-glyph-regexp nil t) 339 (setq match-str (match-string 0)) 340 (setq glyph-str 341 (concat glyph-str (gethash match-str tml-char-glyph-hash)))) 342 ;; glyph reordering 343 (when (string-match tml-glyph-reorder-key-glyphs glyph-str) 344 (if (string-match (car tml-glyph-reordering-regexp-list) 345 glyph-str) 346 (setq glyph-str 347 (replace-match (cdr tml-glyph-reordering-regexp-list) 348 nil nil glyph-str)))) 349 ;; glyph-glyph-conversion 350 (when (string-match tml-glyph-glyph-regexp glyph-str) 351 (setq match-str (match-string 0 glyph-str)) 352 (setq glyph-str 353 (replace-match (gethash match-str tml-glyph-glyph-hash) 354 nil nil glyph-str))) 355 ;; concatenate and attach reference-points. 356 (setq glyph-str 357 (cdr 358 (apply 359 'nconc 360 (mapcar 361 (function 362 (lambda (x) (list '(5 . 3) x))) ;; default ref. point. 363 glyph-str)))) 364 (compose-region from to glyph-str))))) 365 366(provide 'tml-util) 367 368;;; arch-tag: 4d1c9737-e7b1-44cf-a040-4f64c50e773e 369;;; tml-util.el ends here 370