1;;; lao-util.el --- utilities for Lao -*- coding: iso-2022-7bit; -*- 2 3;; Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007 4;; Free Software Foundation, Inc. 5;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007 6;; National Institute of Advanced Industrial Science and Technology (AIST) 7;; Registration Number H14PRO021 8 9;; Keywords: multilingual, Lao 10 11;; This file is part of GNU Emacs. 12 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) 16;; any later version. 17 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. 22 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., 51 Franklin Street, Fifth Floor, 26;; Boston, MA 02110-1301, USA. 27 28;;; Commentary: 29 30;;; Code: 31 32;; Setting information of Thai characters. 33 34(defconst lao-category-table (make-category-table)) 35(define-category ?c "Lao consonant" lao-category-table) 36(define-category ?s "Lao semi-vowel" lao-category-table) 37(define-category ?v "Lao upper/lower vowel" lao-category-table) 38(define-category ?t "Lao tone" lao-category-table) 39 40(let ((l '((?(1!(B consonant "LETTER KOR KAI'" "CHICKEN") 41 (?(1"(B consonant "LETTER KHOR KHAI'" "EGG") 42 (?(1#(B invalid nil) 43 (?(1$(B consonant "LETTER QHOR QHWARGN" "BUFFALO") 44 (?(1%(B invalid nil) 45 (? invalid nil) 46 (?(1'(B consonant "LETTER NGOR NGUU" "SNAKE") 47 (?(1((B consonant "LETTER JOR JUA" "BUDDHIST NOVICE") 48 (?(1)(B invalid nil) 49 (?(1*(B consonant "LETTER XOR X\"ARNG" "ELEPHANT") 50 (?(1+(B invalid nil) 51 (?(1,(B invalid nil) 52 (?(1-(B consonant "LETTER YOR YUNG" "MOSQUITO") 53 (?(1.(B invalid nil) 54 (?(1.(B invalid nil) 55 (?(1.(B invalid nil) 56 (?(1.(B invalid nil) 57 (?(1.(B invalid nil) 58 (?(1.(B invalid nil) 59 (?(14(B consonant "LETTER DOR DANG" "NOSE") 60 (?(15(B consonant "LETTER TOR TAR" "EYE") 61 (?(16(B consonant "LETTER THOR THUNG" "TO ASK,QUESTION") 62 (?(17(B consonant "LETTER DHOR DHARM" "FLAG") 63 (?(18(B invalid nil) 64 (?(19(B consonant "LETTER NOR NOK" "BIRD") 65 (?(1:(B consonant "LETTER BOR BED" "FISHHOOK") 66 (?(1;(B consonant "LETTER POR PAR" "FISH") 67 (?(1<(B consonant "LETTER HPOR HPER\"" "BEE") 68 (?(1=(B consonant "LETTER FHOR FHAR" "WALL") 69 (?(1>(B consonant "LETTER PHOR PHUU" "MOUNTAIN") 70 (?(1?(B consonant "LETTER FOR FAI" "FIRE") 71 (?(1@(B invalid nil) 72 (?(1A(B consonant "LETTER MOR MAR\"" "HORSE") 73 (?(1B(B consonant "LETTER GNOR GNAR" "MEDICINE") 74 (?(1C(B consonant "LETTER ROR ROD" "CAR") 75 (?(1D(B invalid nil) 76 (?(1E(B consonant "LETTER LOR LIING" "MONKEY") 77 (?(1F(B invalid nil) 78 (?(1G(B consonant "LETTER WOR WII" "HAND FAN") 79 (?(1H(B invalid nil) 80 (?(1I(B invalid nil) 81 (?(1J(B consonant "LETTER SOR SEA" "TIGER") 82 (?(1K(B consonant "LETTER HHOR HHAI" "JAR") 83 (?(1L(B invalid nil) 84 (?(1M(B consonant "LETTER OR OOW" "TAKE") 85 (?(1N(B consonant "LETTER HOR HEA" "BOAT") 86 (?(1O(B special "ELLIPSIS") 87 (?(1P(B vowel-base "VOWEL SIGN SARA A") 88 (?(1Q(B vowel-upper "VOWEL SIGN MAI KAN") 89 (?(1R(B vowel-base "VOWEL SIGN SARA AR") 90 (?(1S(B vowel-base "VOWEL SIGN SARA AM") 91 (?(1T(B vowel-upper "VOWEL SIGN SARA I") 92 (?(1U(B vowel-upper "VOWEL SIGN SARA II") 93 (?(1V(B vowel-upper "VOWEL SIGN SARA EU") 94 (?(1W(B vowel-upper "VOWEL SIGN SARA UR") 95 (?(1X(B vowel-lower "VOWEL SIGN SARA U") 96 (?(1Y(B vowel-lower "VOWEL SIGN SARA UU") 97 (?(1Z(B invalid nil) 98 (?(1[(B vowel-upper "VOWEL SIGN MAI KONG") 99 (?(1\(B semivowel-lower "SEMIVOWEL SIGN LO") 100 (?(1](B vowel-base "SEMIVOWEL SIGN SARA IA") 101 (?(1^(B invalid nil) 102 (?(1_(B invalid nil) 103 (?(1`(B vowel-base "VOWEL SIGN SARA EE") 104 (?(1a(B vowel-base "VOWEL SIGN SARA AA") 105 (?(1b(B vowel-base "VOWEL SIGN SARA OO") 106 (?(1c(B vowel-base "VOWEL SIGN SARA EI MAI MUAN\"") 107 (?(1d(B vowel-base "VOWEL SIGN SARA AI MAI MAY") 108 (?(1e(B invalid nil) 109 (?(1f(B special "KO LA (REPETITION)") 110 (?(1g(B invalid nil) 111 (?(1h(B tone "TONE MAI EK") 112 (?(1i(B tone "TONE MAI THO") 113 (?(1j(B tone "TONE MAI TI") 114 (?(1k(B tone "TONE MAI JADTAWAR") 115 (?(1l(B tone "CANCELLATION MARK") 116 (?(1m(B vowel-upper "VOWEL SIGN SARA OR") 117 (?(1n(B invalid nil) 118 (?(1o(B invalid nil) 119 (?(1p(B special "DIGIT ZERO") 120 (?(1q(B special "DIGIT ONE") 121 (?(1r(B special "DIGIT TWO") 122 (?(1s(B special "DIGIT THREE") 123 (?(1t(B special "DIGIT FOUR") 124 (?(1u(B special "DIGIT FIVE") 125 (?(1v(B special "DIGIT SIX") 126 (?(1w(B special "DIGIT SEVEN") 127 (?(1x(B special "DIGIT EIGHT") 128 (?(1y(B special "DIGIT NINE") 129 (?(1z(B invalid nil) 130 (?(1{(B invalid nil) 131 (?(1|(B consonant "LETTER NHOR NHUU" "MOUSE") 132 (?(1}(B consonant "LETTER MHOR MHAR" "DOG") 133 (?(1~(B invalid nil) 134 ;; Unicode equivalents 135 (?$,1D!(B consonant "LETTER KOR KAI'" "CHICKEN") 136 (?$,1D"(B consonant "LETTER KHOR KHAI'" "EGG") 137 (?$,1D$(B consonant "LETTER QHOR QHWARGN" "BUFFALO") 138 (?$,1D'(B consonant "LETTER NGOR NGUU" "SNAKE") 139 (?$,1D((B consonant "LETTER JOR JUA" "BUDDHIST NOVICE") 140 (?$,1D*(B consonant "LETTER XOR X\"ARNG" "ELEPHANT") 141 (?$,1D-(B consonant "LETTER YOR YUNG" "MOSQUITO") 142 (?$,1D4(B consonant "LETTER DOR DANG" "NOSE") 143 (?$,1D5(B consonant "LETTER TOR TAR" "EYE") 144 (?$,1D6(B consonant "LETTER THOR THUNG" "TO ASK,QUESTION") 145 (?$,1D7(B consonant "LETTER DHOR DHARM" "FLAG") 146 (?$,1D9(B consonant "LETTER NOR NOK" "BIRD") 147 (?$,1D:(B consonant "LETTER BOR BED" "FISHHOOK") 148 (?$,1D;(B consonant "LETTER POR PAR" "FISH") 149 (?$,1D<(B consonant "LETTER HPOR HPER\"" "BEE") 150 (?$,1D=(B consonant "LETTER FHOR FHAR" "WALL") 151 (?$,1D>(B consonant "LETTER PHOR PHUU" "MOUNTAIN") 152 (?$,1D?(B consonant "LETTER FOR FAI" "FIRE") 153 (?$,1DA(B consonant "LETTER MOR MAR\"" "HORSE") 154 (?$,1DB(B consonant "LETTER GNOR GNAR" "MEDICINE") 155 (?$,1DC(B consonant "LETTER ROR ROD" "CAR") 156 (?$,1DE(B consonant "LETTER LOR LIING" "MONKEY") 157 (?$,1DG(B consonant "LETTER WOR WII" "HAND FAN") 158 (?$,1DJ(B consonant "LETTER SOR SEA" "TIGER") 159 (?$,1DK(B consonant "LETTER HHOR HHAI" "JAR") 160 (?$,1DM(B consonant "LETTER OR OOW" "TAKE") 161 (?$,1DN(B consonant "LETTER HOR HEA" "BOAT") 162 (?$,1DO(B special "ELLIPSIS") 163 (?$,1DP(B vowel-base "VOWEL SIGN SARA A") 164 (?$,1DQ(B vowel-upper "VOWEL SIGN MAI KAN") 165 (?$,1DR(B vowel-base "VOWEL SIGN SARA AR") 166 (?$,1DS(B vowel-base "VOWEL SIGN SARA AM") 167 (?$,1DT(B vowel-upper "VOWEL SIGN SARA I") 168 (?$,1DU(B vowel-upper "VOWEL SIGN SARA II") 169 (?$,1DV(B vowel-upper "VOWEL SIGN SARA EU") 170 (?$,1DW(B vowel-upper "VOWEL SIGN SARA UR") 171 (?$,1DX(B vowel-lower "VOWEL SIGN SARA U") 172 (?$,1DY(B vowel-lower "VOWEL SIGN SARA UU") 173 (?$,1D[(B vowel-upper "VOWEL SIGN MAI KONG") 174 (?$,1D\(B semivowel-lower "SEMIVOWEL SIGN LO") 175 (?$,1D](B vowel-base "SEMIVOWEL SIGN SARA IA") 176 (?$,1D`(B vowel-base "VOWEL SIGN SARA EE") 177 (?$,1Da(B vowel-base "VOWEL SIGN SARA AA") 178 (?$,1Db(B vowel-base "VOWEL SIGN SARA OO") 179 (?$,1Dc(B vowel-base "VOWEL SIGN SARA EI MAI MUAN\"") 180 (?$,1Dd(B vowel-base "VOWEL SIGN SARA AI MAI MAY") 181 (?$,1Df(B special "KO LA (REPETITION)") 182 (?$,1Dh(B tone "TONE MAI EK") 183 (?$,1Di(B tone "TONE MAI THO") 184 (?$,1Dj(B tone "TONE MAI TI") 185 (?$,1Dk(B tone "TONE MAI JADTAWAR") 186 (?$,1Dl(B tone "CANCELLATION MARK") 187 (?$,1Dm(B vowel-upper "VOWEL SIGN SARA OR") 188 (?$,1Dp(B special "DIGIT ZERO") 189 (?$,1Dq(B special "DIGIT ONE") 190 (?$,1Dr(B special "DIGIT TWO") 191 (?$,1Ds(B special "DIGIT THREE") 192 (?$,1Dt(B special "DIGIT FOUR") 193 (?$,1Du(B special "DIGIT FIVE") 194 (?$,1Dv(B special "DIGIT SIX") 195 (?$,1Dw(B special "DIGIT SEVEN") 196 (?$,1Dx(B special "DIGIT EIGHT") 197 (?$,1Dy(B special "DIGIT NINE") 198 (?$,1D|(B consonant "LETTER NHOR NHUU" "MOUSE") 199 (?$,1D}(B consonant "LETTER MHOR MHAR" "DOG"))) 200 elm) 201 (while l 202 (setq elm (car l) l (cdr l)) 203 (let ((char (car elm)) 204 (ptype (nth 1 elm))) 205 (cond ((eq ptype 'consonant) 206 (modify-category-entry char ?c lao-category-table)) 207 ((memq ptype '(vowel-upper vowel-lower)) 208 (modify-category-entry char ?v lao-category-table)) 209 ((eq ptype 'semivowel-lower) 210 (modify-category-entry char ?s lao-category-table)) 211 ((eq ptype 'tone) 212 (modify-category-entry char ?t lao-category-table))) 213 (put-char-code-property char 'phonetic-type ptype) 214 (put-char-code-property char 'name (nth 2 elm)) 215 (put-char-code-property char 'meaning (nth 3 elm))))) 216 217;; The general composing rules are as follows: 218;; 219;; T 220;; V T V T 221;; CV -> C, CT -> C, CVT -> C, Cv -> C, CvT -> C 222;; v v 223;; T 224;; V T V T 225;; CsV -> C, CsT -> C, CsVT -> C, Csv -> C, CvT -> C 226;; s s s s s 227;; v v 228 229 230;; where C: consonant, V: vowel upper, v: vowel lower, 231;; T: tone mark, s: semivowel lower 232 233(defvar lao-composition-pattern 234 "\\cc\\(\\ct\\|\\cv\\ct?\\|\\cs\\(\\ct\\|\\cv\\ct?\\)?\\)" 235 "Regular expression matching a Lao composite sequence.") 236 237;;;###autoload 238(defun lao-compose-string (str) 239 (with-category-table lao-category-table 240 (let ((idx 0)) 241 (while (setq idx (string-match lao-composition-pattern str idx)) 242 (compose-string str idx (match-end 0)) 243 (setq idx (match-end 0)))) 244 str)) 245 246;;; LRT: Lao <-> Roman Transcription 247 248;; Upper vowels and tone-marks are put on the letter. 249;; Semi-vowel-sign-lo and lower vowels are put under the letter. 250 251(defconst lao-transcription-consonant-alist 252 (sort '(;; single consonants 253 ("k" . "(1!(B") 254 ("kh" . "(1"(B") 255 ("qh" . "(1$(B") 256 ("ng" . "(1'(B") 257 ("j" . "(1((B") 258 ("s" . "(1J(B") 259 ("x" . "(1*(B") 260 ("y" . "(1-(B") 261 ("d" . "(14(B") 262 ("t" . "(15(B") 263 ("th" . "(16(B") 264 ("dh" . "(17(B") 265 ("n" . "(19(B") 266 ("b" . "(1:(B") 267 ("p" . "(1;(B") 268 ("hp" . "(1<(B") 269 ("fh" . "(1=(B") 270 ("ph" . "(1>(B") 271 ("f" . "(1?(B") 272 ("m" . "(1A(B") 273 ("gn" . "(1B(B") 274 ("l" . "(1E(B") 275 ("r" . "(1C(B") 276 ("v" . "(1G(B") 277 ("w" . "(1G(B") 278 ("hh" . "(1K(B") 279 ("O" . "(1M(B") 280 ("h" . "(1N(B") 281 ("nh" . "(1|(B") 282 ("mh" . "(1}(B") 283 ("lh" . ["(1K\(B"]) 284 ;; double consonants 285 ("ngh" . ["(1K'(B"]) 286 ("yh" . ["(1K](B"]) 287 ("wh" . ["(1KG(B"]) 288 ("hl" . ["(1KE(B"]) 289 ("hy" . ["(1K-(B"]) 290 ("hn" . ["(1K9(B"]) 291 ("hm" . ["(1KA(B"]) 292 ) 293 (function (lambda (x y) (> (length (car x)) (length (car y))))))) 294 295(defconst lao-transcription-semi-vowel-alist 296 '(("r" . "(1\(B"))) 297 298(defconst lao-transcription-vowel-alist 299 (sort '(("a" . "(1P(B") 300 ("ar" . "(1R(B") 301 ("i" . "(1T(B") 302 ("ii" . "(1U(B") 303 ("eu" . "(1V(B") 304 ("ur" . "(1W(B") 305 ("u" . "(1X(B") 306 ("uu" . "(1Y(B") 307 ("e" . ["(1`P(B"]) 308 ("ee" . "(1`(B") 309 ("ae" . ["(1aP(B"]) 310 ("aa" . "(1a(B") 311 ("o" . ["(1bP(B"]) 312 ("oo" . "(1b(B") 313 ("oe" . ["(1`RP(B"]) 314 ("or" . "(1m(B") 315 ("er" . ["(1`T(B"]) 316 ("ir" . ["(1`U(B"]) 317 ("ua" . ["(1[GP(B"]) 318 ("uaa" . ["(1[G(B"]) 319 ("ie" . ["(1`Q]P(B"]) 320 ("ia" . ["(1`Q](B"]) 321 ("ea" . ["(1`VM(B"]) 322 ("eaa" . ["(1`WM(B"]) 323 ("ai" . "(1d(B") 324 ("ei" . "(1c(B") 325 ("ao" . ["(1`[R(B"]) 326 ("aM" . "(1S(B")) 327 (function (lambda (x y) (> (length (car x)) (length (car y))))))) 328 329;; Maa-sakod is put at the tail. 330(defconst lao-transcription-maa-sakod-alist 331 '(("k" . "(1!(B") 332 ("g" . "(1'(B") 333 ("y" . "(1-(B") 334 ("d" . "(14(B") 335 ("n" . "(19(B") 336 ("b" . "(1:(B") 337 ("m" . "(1A(B") 338 ("v" . "(1G(B") 339 ("w" . "(1G(B") 340 )) 341 342(defconst lao-transcription-tone-alist 343 '(("'" . "(1h(B") 344 ("\"" . "(1i(B") 345 ("^" . "(1j(B") 346 ("+" . "(1k(B") 347 ("~" . "(1l(B"))) 348 349(defconst lao-transcription-punctuation-alist 350 '(("\\0" . "(1p(B") 351 ("\\1" . "(1q(B") 352 ("\\2" . "(1r(B") 353 ("\\3" . "(1s(B") 354 ("\\4" . "(1t(B") 355 ("\\5" . "(1u(B") 356 ("\\6" . "(1v(B") 357 ("\\7" . "(1w(B") 358 ("\\8" . "(1x(B") 359 ("\\9" . "(1y(B") 360 ("\\\\" . "(1f(B") 361 ("\\$" . "(1O(B"))) 362 363(defconst lao-transcription-pattern 364 (concat 365 "\\(" 366 (mapconcat 'car lao-transcription-consonant-alist "\\|") 367 "\\)\\(" 368 (mapconcat 'car lao-transcription-semi-vowel-alist "\\|") 369 "\\)?\\(\\(" 370 (mapconcat 'car lao-transcription-vowel-alist "\\|") 371 "\\)\\(" 372 (mapconcat 'car lao-transcription-maa-sakod-alist "\\|") 373 "\\)?\\(" 374 (mapconcat (lambda (x) (regexp-quote (car x))) 375 lao-transcription-tone-alist "\\|") 376 "\\)?\\)?\\|" 377 (mapconcat (lambda (x) (regexp-quote (car x))) 378 lao-transcription-punctuation-alist "\\|") 379 ) 380 "Regexp of Roman transcription pattern for one Lao syllable.") 381 382(defconst lao-transcription-pattern 383 (concat 384 "\\(" 385 (regexp-opt (mapcar 'car lao-transcription-consonant-alist)) 386 "\\)\\(" 387 (regexp-opt (mapcar 'car lao-transcription-semi-vowel-alist)) 388 "\\)?\\(\\(" 389 (regexp-opt (mapcar 'car lao-transcription-vowel-alist)) 390 "\\)\\(" 391 (regexp-opt (mapcar 'car lao-transcription-maa-sakod-alist)) 392 "\\)?\\(" 393 (regexp-opt (mapcar 'car lao-transcription-tone-alist)) 394 "\\)?\\)?\\|" 395 (regexp-opt (mapcar 'car lao-transcription-punctuation-alist)) 396 ) 397 "Regexp of Roman transcription pattern for one Lao syllable.") 398 399(defconst lao-vowel-reordering-rule 400 '(("(1P(B" (0 ?(1P(B) (0 ?(1Q(B)) 401 ("(1R(B" (0 ?(1R(B)) 402 ("(1T(B" (0 ?(1U(B)) 403 ("(1U(B" (0 ?(1U(B)) 404 ("(1V(B" (0 ?(1V(B)) 405 ("(1W(B" (0 ?(1W(B)) 406 ("(1X(B" (0 ?(1X(B)) 407 ("(1Y(B" (0 ?(1Y(B)) 408 ("(1`P(B" (?(1`(B 0 ?(1P(B) (?(1`(B 0 ?(1Q(B)) 409 ("(1`(B" (?(1`(B 0)) 410 ("(1aP(B" (?(1a(B 0 ?(1P(B) (?(1a(B 0 ?(1Q(B)) 411 ("(1a(B" (?(1a(B 0)) 412 ("(1bP(B" (?(1b(B 0 ?(1P(B) (0 ?(1[(B) (?(1-(B ?(1b(B 0 ?(1Q(B) (?(1G(B ?(1b(B 0 ?(1Q(B)) 413 ("(1b(B" (?(1b(B 0)) 414 ("(1`RP(B" (?(1`(B 0 ?(1R(B ?(1P(B) (0 ?(1Q(B ?(1M(B)) 415 ("(1m(B" (0 ?(1m(B) (0 ?(1M(B)) 416 ("(1`T(B" (?(1`(B 0 ?(1T(B)) 417 ("(1`U(B" (?(1`(B 0 ?(1U(B)) 418 ("(1[GP(B" (0 ?(1[(B ?(1G(B ?(1P(B) (0 ?(1Q(B ?(1G(B)) 419 ("(1[G(B" (0 ?(1[(B ?(1G(B) (0 ?(1G(B)) 420 ("(1`Q]P(B" (?(1`(B 0 ?(1Q(B ?(1](B ?(1P(B) (0 ?(1Q(B ?(1](B)) 421 ("(1`Q](B" (?(1`(B 0 ?(1Q(B ?(1](B) (0 ?(1](B)) 422 ("(1`VM(B" (?(1`(B 0 ?(1V(B ?(1M(B)) 423 ("(1`WM(B" (?(1`(B 0 ?(1W(B ?(1M(B)) 424 ("(1d(B" (?(1d(B 0)) 425 ("(1c(B" (?(1c(B 0)) 426 ("(1`[R(B" (?(1`(B 0 ?(1[(B ?(1R(B)) 427 ("(1S(B" (0 ?(1S(B)) 428 429 ;; Unicode equivalents 430 ("$,1DP(B" (0 ?$,1DP(B) (0 ?$,1DQ(B)) 431 ("$,1DR(B" (0 ?$,1DR(B)) 432 ("$,1DT(B" (0 ?$,1DU(B)) 433 ("$,1DU(B" (0 ?$,1DU(B)) 434 ("$,1DV(B" (0 ?$,1DV(B)) 435 ("$,1DW(B" (0 ?$,1DW(B)) 436 ("$,1DX(B" (0 ?$,1DX(B)) 437 ("$,1DY(B" (0 ?$,1DY(B)) 438 ("$,1D`DP(B" (?$,1D`(B 0 ?$,1DP(B) (?$,1D`(B 0 ?$,1DQ(B)) 439 ("$,1D`(B" (?$,1D`(B 0)) 440 ("$,1DaDP(B" (?$,1Da(B 0 ?$,1DP(B) (?$,1Da(B 0 ?$,1DQ(B)) 441 ("$,1Da(B" (?$,1Da(B 0)) 442 ("$,1DbDP(B" (?$,1Db(B 0 ?$,1DP(B) (0 ?$,1D[(B) (?$,1D-(B ?$,1Db(B 0 ?$,1DQ(B) (?$,1DG(B ?$,1Db(B 0 ?$,1DQ(B)) 443 ("$,1Db(B" (?$,1Db(B 0)) 444 ("$,1D`DRDP(B" (?$,1D`(B 0 ?$,1DR(B ?$,1DP(B) (0 ?$,1DQ(B ?$,1DM(B)) 445 ("$,1Dm(B" (0 ?$,1Dm(B) (0 ?$,1DM(B)) 446 ("$,1D`DT(B" (?$,1D`(B 0 ?$,1DT(B)) 447 ("$,1D`DU(B" (?$,1D`(B 0 ?$,1DU(B)) 448 ("$,1D[DGDP(B" (0 ?$,1D[(B ?$,1DG(B ?$,1DP(B) (0 ?$,1DQ(B ?$,1DG(B)) 449 ("$,1D[DG(B" (0 ?$,1D[(B ?$,1DG(B) (0 ?$,1DG(B)) 450 ("$,1D`DQD]DP(B" (?$,1D`(B 0 ?$,1DQ(B ?$,1D](B ?$,1DP(B) (0 ?$,1DQ(B ?$,1D](B)) 451 ("$,1D`DQD](B" (?$,1D`(B 0 ?$,1DQ(B ?$,1D](B) (0 ?$,1D](B)) 452 ("$,1D`DVDM(B" (?$,1D`(B 0 ?$,1DV(B ?$,1DM(B)) 453 ("$,1D`DWDM(B" (?$,1D`(B 0 ?$,1DW(B ?$,1DM(B)) 454 ("$,1Dd(B" (?$,1Dd(B 0)) 455 ("$,1Dc(B" (?$,1Dc(B 0)) 456 ("$,1D`D[DR(B" (?$,1D`(B 0 ?$,1D[(B ?$,1DR(B)) 457 ("$,1DS(B" (0 ?$,1DS(B))) 458 "Alist of Lao vowel string vs the corresponding re-ordering rule. 459Each element has this form: 460 (VOWEL NO-MAA-SAKOD-RULE WITH-MAA-SAKOD-RULE (MAA-SAKOD-0 RULE-0) ...) 461 462VOWEL is a vowel string (e.g. \"(1`Q]P(B\"). 463 464NO-MAA-SAKOD-RULE is a rule to re-order and modify VOWEL following a 465consonant. It is a list vowel characters or 0. The element 0 466indicate the place to embed a consonant. 467 468Optional WITH-MAA-SAKOD-RULE is a rule to re-order and modify VOWEL 469follwoing a consonant and preceding a maa-sakod character. If it is 470nil, NO-MAA-SAKOD-RULE is used. The maa-sakod character is alwasy 471appended at the tail. 472 473For instance, rule `(\"(1`WM(B\" (?(1`(B t ?(1W(B ?(1M(B))' tells that this vowel 474string following a consonant `(1!(B' should be re-ordered as \"(1`!WM(B\". 475 476Optional (MAA-SAKOD-n RULE-n) are rules specially applied to maa-sakod 477character MAA-SAKOD-n.") 478 479;;;###autoload 480(defun lao-transcribe-single-roman-syllable-to-lao (from to &optional str) 481 "Transcribe a Romanized Lao syllable in the region FROM and TO to Lao string. 482Only the first syllable is transcribed. 483The value has the form: (START END LAO-STRING), where 484START and END are the beggining and end positions of the Roman Lao syllable, 485LAO-STRING is the Lao character transcription of it. 486 487Optional 3rd arg STR, if non-nil, is a string to search for Roman Lao 488syllable. In that case, FROM and TO are indexes to STR." 489 (if str 490 (if (setq from (string-match lao-transcription-pattern str from)) 491 (progn 492 (if (>= from to) 493 (setq from nil) 494 (setq to (match-end 0))))) 495 (save-excursion 496 (goto-char from) 497 (if (setq to (re-search-forward lao-transcription-pattern to t)) 498 (setq from (match-beginning 0)) 499 (setq from nil)))) 500 (if from 501 (let* ((consonant (match-string 1 str)) 502 (semivowel (match-string 3 str)) 503 (vowel (match-string 5 str)) 504 (maa-sakod (match-string 8 str)) 505 (tone (match-string 9 str)) 506 lao-consonant lao-semivowel lao-vowel lao-maa-sakod lao-tone 507 clen cidx) 508 (setq to (match-end 0)) 509 (if (not consonant) 510 (setq str (cdr (assoc (match-string 0 str) 511 lao-transcription-punctuation-alist))) 512 (setq lao-consonant 513 (cdr (assoc consonant lao-transcription-consonant-alist))) 514 (if (vectorp lao-consonant) 515 (setq lao-consonant (aref lao-consonant 0))) 516 (setq clen (length lao-consonant)) 517 (if semivowel 518 ;; Include semivowel in STR. 519 (setq lao-semivowel 520 (cdr (assoc semivowel lao-transcription-semi-vowel-alist)) 521 str (if (= clen 1) 522 (concat lao-consonant lao-semivowel) 523 (concat (substring lao-consonant 0 1) lao-semivowel 524 (substring lao-consonant 1)))) 525 (setq str lao-consonant)) 526 (if vowel 527 (let (rule) 528 (setq lao-vowel 529 (cdr (assoc vowel lao-transcription-vowel-alist))) 530 (if (vectorp lao-vowel) 531 (setq lao-vowel (aref lao-vowel 0))) 532 (setq rule (assoc lao-vowel lao-vowel-reordering-rule)) 533 (if (null maa-sakod) 534 (setq rule (nth 1 rule)) 535 (setq lao-maa-sakod 536 (cdr (assoc maa-sakod lao-transcription-maa-sakod-alist)) 537 rule 538 (or (cdr (assq (aref lao-maa-sakod 0) (nthcdr 2 rule))) 539 (nth 2 rule) 540 (nth 1 rule)))) 541 (or rule 542 (error "Lao vowel %S has no re-ordering rule" lao-vowel)) 543 (setq lao-consonant str str "") 544 (while rule 545 (if (= (car rule) 0) 546 (setq str (concat str lao-consonant) 547 cidx (length str)) 548 (setq str (concat str (list (car rule))))) 549 (setq rule (cdr rule))) 550 (or cidx 551 (error "Lao vowel %S has malformed re-ordering rule" vowel)) 552 ;; Set CIDX to after upper or lower vowel if any. 553 (let ((len (length str))) 554 (while (and (< cidx len) 555 (memq (get-char-code-property (aref str cidx) 556 'phonetic-type) 557 '(vowel-lower vowel-upper))) 558 (setq cidx (1+ cidx)))) 559 (if lao-maa-sakod 560 (setq str (concat str lao-maa-sakod))) 561 (if tone 562 (setq lao-tone 563 (cdr (assoc tone lao-transcription-tone-alist)) 564 str (concat (substring str 0 cidx) lao-tone 565 (substring str cidx))))))) 566 (list from to (lao-compose-string str))))) 567 568;;;###autoload 569(defun lao-transcribe-roman-to-lao-string (str) 570 "Transcribe Romanized Lao string STR to Lao character string." 571 (let ((from 0) 572 (to (length str)) 573 (lao-str "") 574 val) 575 (while (setq val (lao-transcribe-single-roman-syllable-to-lao from to str)) 576 (let ((start (car val)) 577 (end (nth 1 val)) 578 (lao (nth 2 val))) 579 (if (> start from) 580 (setq lao-str (concat lao-str (substring str from start) lao)) 581 (setq lao-str (concat lao-str lao))) 582 (setq from end))) 583 (if (< from to) 584 (concat lao-str (substring str from to)) 585 lao-str))) 586 587;;;###autoload 588(defun lao-post-read-conversion (len) 589 (lao-compose-region (point) (+ (point) len)) 590 len) 591 592;;;###autoload 593(defun lao-composition-function (from to pattern &optional string) 594 "Compose Lao text in the region FROM and TO. 595The text matches the regular expression PATTERN. 596Optional 4th argument STRING, if non-nil, is a string containing text 597to compose. 598 599The return value is number of composed characters." 600 (if (< (1+ from) to) 601 (progn 602 (if string 603 (compose-string string from to) 604 (compose-region from to)) 605 (- to from)))) 606 607;;;###autoload 608(defun lao-compose-region (from to) 609 (interactive "r") 610 (save-restriction 611 (narrow-to-region from to) 612 (goto-char (point-min)) 613 (with-category-table lao-category-table 614 (while (re-search-forward lao-composition-pattern nil t) 615 (compose-region (match-beginning 0) (point)))))) 616 617;; 618(provide 'lao-util) 619 620;;; arch-tag: 1f828781-3cb8-4695-88af-8f33222338ce 621;;; lao-util.el ends here 622