lisp/language/indian.el

   1 ;;; indian.el --- Indian languages support -*- coding: utf-8; -*-
   2
   3 ;; Copyright (C) 1997, 1999, 2001-2012  Free Software Foundation, Inc.
   4 ;; Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   5 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   6 ;;   Registration Number H14PRO021
   7
   8 ;; Maintainer:  Kenichi Handa <handa@m17n.org>
   9 ;;              KAWABATA, Taichi <kawabata@m17n.org>
  10 ;; Keywords:    multilingual, i18n, Indian
  11
  12 ;; This file is part of GNU Emacs.
  13
  14 ;; GNU Emacs is free software: you can redistribute it and/or modify
  15 ;; it under the terms of the GNU General Public License as published by
  16 ;; the Free Software Foundation, either version 3 of the License, or
  17 ;; (at your option) any later version.
  18
  19 ;; GNU Emacs is distributed in the hope that it will be useful,
  20 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  21 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  22 ;; GNU General Public License for more details.
  23
  24 ;; You should have received a copy of the GNU General Public License
  25 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  26
  27 ;;; Commentary:
  28
  29 ;; This file contains definitions of Indian language environments, and
  30 ;; setups for displaying the scrtipts used there.
  31
  32 ;;; Code:
  33
  34 (define-coding-system 'in-is13194-devanagari
  35   "8-bit encoding for ASCII (MSB=0) and IS13194-Devanagari (MSB=1)."
  36   :coding-type 'iso-2022
  37   :mnemonic ?D
  38   :designation [ascii indian-is13194 nil nil]
  39   :charset-list '(ascii indian-is13194)
  40   :post-read-conversion 'in-is13194-post-read-conversion
  41   :pre-write-conversion 'in-is13194-pre-write-conversion)
  42
  43 (define-coding-system-alias 'devanagari 'in-is13194-devanagari)
  44
  45 (set-language-info-alist
  46  "Devanagari" '((charset unicode)
  47                 (coding-system utf-8)
  48                 (coding-priority utf-8)
  49                 (input-method . "devanagari-aiba")
  50                 (documentation . "\
  51 Such languages using Devanagari script as Hindi and Marathi
  52 are supported in this language environment."))
  53  '("Indian"))
  54
  55 (set-language-info-alist
  56  "Bengali" '((charset unicode)
  57              (coding-system utf-8)
  58              (coding-priority utf-8)
  59              (input-method . "bengali-itrans")
  60              (documentation . "\
  61 Such languages using Bengali script as Bengali and Assamese
  62 are supported in this language environment."))
  63  '("Indian"))
  64
  65 (set-language-info-alist
  66  "Punjabi" '((charset unicode)
  67               (coding-system utf-8)
  68               (coding-priority utf-8)
  69               (input-method . "punjabi-itrans")
  70               (documentation . "\
  71 North Indian language Punjabi is supported in this language environment."))
  72  '("Indian"))
  73
  74 (set-language-info-alist
  75  "Gujarati" '((charset unicode)
  76               (coding-system utf-8)
  77               (coding-priority utf-8)
  78               (input-method . "gujarati-itrans")
  79               (documentation . "\
  80 North Indian language Gujarati is supported in this language environment."))
  81  '("Indian"))
  82
  83 (set-language-info-alist
  84  "Oriya" '((charset unicode)
  85               (coding-system utf-8)
  86               (coding-priority utf-8)
  87               (input-method . "oriya-itrans")
  88               (documentation . "\
  89 Such languages using Oriya script as Oriya, Khonti, and Santali
  90 are supported in this language environment."))
  91  '("Indian"))
  92
  93 (set-language-info-alist
  94  "Tamil" '((charset unicode)
  95            (coding-system utf-8)
  96            (coding-priority utf-8)
  97            (input-method . "tamil-itrans")
  98            (documentation . "\
  99 South Indian Language Tamil is supported in this language environment."))
 100  '("Indian"))
 101
 102 (set-language-info-alist
 103  "Telugu" '((charset unicode)
 104             (coding-system utf-8)
 105             (coding-priority utf-8)
 106             (input-method . "telugu-itrans")
 107             (documentation . "\
 108 South Indian Language Telugu is supported in this language environment."))
 109  '("Indian"))
 110
 111 (set-language-info-alist
 112  "Kannada" '((charset unicode)
 113              (coding-system mule-utf-8)
 114              (coding-priority mule-utf-8)
 115              (input-method . "kannada-itrans")
 116              (sample-text . "Kannada (ಕನ್ನಡ)  ನಮಸ್ಕಾರ")
 117              (documentation . "\
 118 Kannada language and script is supported in this language
 119 environment."))
 120  '("Indian"))
 121
 122 (set-language-info-alist
 123  "Malayalam" '((charset unicode)
 124                (coding-system utf-8)
 125                (coding-priority utf-8)
 126                (input-method . "malayalam-itrans")
 127                (documentation . "\
 128 South Indian language Malayalam is supported in this language environment."))
 129  '("Indian"))
 130
 131 ;; Replace mnemonic characters in REGEXP according to TABLE.  TABLE is
 132 ;; an alist of (MNEMONIC-STRING . REPLACEMENT-STRING).
 133
 134 (defun indian-compose-regexp (regexp table)
 135   (let ((case-fold-search nil))
 136     (dolist (elt table)
 137       (setq regexp (replace-regexp-in-string (car elt) (cdr elt) regexp t t)))
 138     regexp))
 139
 140 (defconst devanagari-composable-pattern
 141   (let ((table
 142          '(("a" . "[\u0900-\u0902]")    ; vowel modifier (above)
 143            ("A" . "\u0903")             ; vowel modifier (post)
 144            ("V" . "[\u0904-\u0914\u0960-\u0961\u0972]") ; independent vowel
 145            ("C" . "[\u0915-\u0939\u0958-\u095F\u0979-\u097F]") ; consonant
 146            ("R" . "\u0930")             ; RA
 147            ("n" . "\u093C")             ; NUKTA
 148            ("v" . "[\u093E-\u094C\u094E\u0955\u0962-\u0963]") ; vowel sign
 149            ("H" . "\u094D")             ; HALANT
 150            ("s" . "[\u0951-\u0952]")    ; stress sign
 151            ("t" . "[\u0953-\u0954]")    ; accent
 152            ("N" . "\u200C")             ; ZWNJ
 153            ("J" . "\u200D")             ; ZWJ
 154            ("X" . "[\u0900-\u097F]")))) ; all coverage
 155     (indian-compose-regexp
 156      (concat
 157       ;; syllables with an independent vowel, or
 158       "\\(?:RH\\)?Vn?\\(?:J?HR\\)?v*n?a?s?t?A?\\|"
 159       ;; consonant-based syllables, or
 160       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*n?a?s?t?A?\\)\\|"
 161       ;; special consonant form, or
 162       "JHR\\|"
 163       ;; any other singleton characters
 164       "X")
 165      table))
 166   "Regexp matching a composable sequence of Devanagari characters.")
 167
 168 (defconst bengali-composable-pattern
 169   (let ((table
 170          '(("a" . "\u0981")             ; SIGN CANDRABINDU
 171            ("A" . "[\u0982-\u0983]")    ; SIGN ANUSVARA .. VISARGA
 172            ("V" . "[\u0985-\u0994\u09E0-\u09E1]") ; independent vowel
 173            ("C" . "[\u0995-\u09B9\u09DC-\u09DF\u09F1]") ; consonant
 174            ("B" . "[\u09AC\u09AF-\u09B0\u09F0]")                ; BA, YA, RA
 175            ("R" . "[\u09B0\u09F0]")             ; RA
 176            ("n" . "\u09BC")             ; NUKTA
 177            ("v" . "[\u09BE-\u09CC\u09D7\u09E2-\u09E3]") ; vowel sign
 178            ("H" . "\u09CD")             ; HALANT
 179            ("T" . "\u09CE")             ; KHANDA TA
 180            ("N" . "\u200C")             ; ZWNJ
 181            ("J" . "\u200D")             ; ZWJ
 182            ("X" . "[\u0980-\u09FF]")))) ; all coverage
 183     (indian-compose-regexp
 184      (concat
 185       ;; syllables with an independent vowel, or
 186       "\\(?:RH\\)?Vn?\\(?:J?HB\\)?v*n?a?A?\\|"
 187       ;; consonant-based syllables, or
 188       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*[NJ]?v?a?A?\\)\\|"
 189       ;; another syllables with an independent vowel, or
 190       "\\(?:RH\\)?T\\|"
 191       ;; special consonant form, or
 192       "JHB\\|"
 193       ;; any other singleton characters
 194       "X")
 195      table))
 196   "Regexp matching a composable sequence of Bengali characters.")
 197
 198 (defconst gurmukhi-composable-pattern
 199   (let ((table
 200          '(("a" . "[\u0A01-\u0A02\u0A70]") ; SIGN ADAK BINDI .. BINDI, TIPPI
 201            ("A" . "\u0A03")             ; SIGN VISARGA
 202            ("V" . "[\u0A05-\u0A14]")    ; independent vowel
 203            ("C" . "[\u0A15-\u0A39\u0A59-\u0A5E]")       ; consonant
 204            ("Y" . "[\u0A2F-u0A30\u0A35\u0A39]") ; YA, RA, VA, HA
 205            ("n" . "\u0A3C")             ; NUKTA
 206            ("v" . "[\u0A3E-\u0A4C]")    ; vowel sign
 207            ("H" . "\u0A4D")             ; VIRAMA
 208            ("N" . "\u200C")             ; ZWNJ
 209            ("J" . "\u200D")             ; ZWJ
 210            ("X" . "[\u0A00-\u0A7F]")))) ; all coverage
 211     (indian-compose-regexp
 212      (concat
 213       ;; consonant-based syllables, or
 214       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*n?a?A?\\)\\|"
 215       ;; syllables with an independent vowel, or
 216       "Vn?\\(?:J?HY\\)?v*n?a?A?\\|"
 217       ;; special consonant form, or
 218       "JHY\\|"
 219       ;; any other singleton characters
 220       "X")
 221      table))
 222   "Regexp matching a composable sequence of Gurmukhi characters.")
 223
 224 (defconst gujarati-composable-pattern
 225   (let ((table
 226          '(("a" . "[\u0A81-\u0A82]")    ; SIGN CANDRABINDU .. ANUSVARA
 227            ("A" . "\u0A83")             ; SIGN VISARGA
 228            ("V" . "[\u0A85-\u0A94\u0AE0-\u0AE1]") ; independent vowel
 229            ("C" . "[\u0A95-\u0AB9]")    ; consonant
 230            ("R" . "\u0AB0")             ; RA
 231            ("n" . "\u0ABC")             ; NUKTA
 232            ("v" . "[\u0ABE-\u0ACC\u0AE2-\u0AE3]") ; vowel sign
 233            ("H" . "\u0ACD")             ; VIRAMA
 234            ("N" . "\u200C")             ; ZWNJ
 235            ("J" . "\u200D")             ; ZWJ
 236            ("X" . "[\u0A80-\u0AFF]")))) ; all coverage
 237     (indian-compose-regexp
 238      (concat
 239       ;; syllables with an independent vowel, or
 240       "\\(?:RH\\)?Vn?\\(?:J?HR\\)?v*n?a?A?\\|"
 241       ;; consonant-based syllables, or
 242       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*n?a?A?\\)\\|"
 243       ;; special consonant form, or
 244       "JHR\\|"
 245       ;; any other singleton characters
 246       "X")
 247      table))
 248   "Regexp matching a composable sequence of Gujarati characters.")
 249
 250 (defconst oriya-composable-pattern
 251   (let ((table
 252          '(("a" . "\u0B01")             ; SIGN CANDRABINDU
 253            ("A" . "[\u0B02-\u0B03]")    ; SIGN ANUSVARA .. VISARGA
 254            ("V" . "[\u0B05-\u0B14\u0B60-\u0B61]") ; independent vowel
 255            ("C" . "[\u0B15-\u0B39\u0B5C-\u0B5D\u0B71]") ; consonant
 256            ("B" . "[\u0B15-\u0B17\u0B1B-\u0B1D\u0B1F-\u0B21\u0B23-\u0B24\u0B27-\u0B30\u0B32-\u0B35\u0B38-\u0B39]") ; consonant with below form
 257            ("R" . "\u0B30")             ; RA
 258            ("n" . "\u0B3C")             ; NUKTA
 259            ("v" . "[\u0B3E-\u0B4C\u0B56-\u0B57\u0B62-\u0B63]") ; vowel sign
 260            ("H" . "\u0B4D")             ; VIRAMA
 261            ("N" . "\u200C")             ; ZWNJ
 262            ("J" . "\u200D")             ; ZWJ
 263            ("X" . "[\u0B00-\u0B7F]")))) ; all coverage
 264     (indian-compose-regexp
 265      (concat
 266       ;; syllables with an independent vowel, or
 267       "\\(?:RH\\)?Vn?\\(?:J?HB\\)?v*n?a?A?\\|"
 268       ;; consonant-based syllables, or
 269       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*n?a?A?\\)\\|"
 270       ;; special consonant form, or
 271       "JHB\\|"
 272       ;; any other singleton characters
 273       "X")
 274      table))
 275   "Regexp matching a composable sequence of Oriya characters.")
 276
 277 (defconst tamil-composable-pattern
 278   (let ((table
 279          '(("a" . "\u0B82")             ; SIGN ANUSVARA
 280            ("V" . "[\u0B85-\u0B94]")    ; independent vowel
 281            ("C" . "[\u0B95-\u0BB9]")    ; consonant
 282            ("v" . "[\u0BBE-\u0BCC\u0BD7]") ; vowel sign
 283            ("H" . "\u0BCD")             ; VIRAMA
 284            ("N" . "\u200C")             ; ZWNJ
 285            ("J" . "\u200D")             ; ZWJ
 286            ("X" . "[\u0B80-\u0BFF]")))) ; all coverage
 287     (indian-compose-regexp
 288      (concat
 289       ;; consonant-based syllables, or
 290       "C\\(?:J?HJ?C\\)*\\(?:H[NJ]?\\|v*a?\\)\\|"
 291       ;; syllables with an independent vowel, or
 292       "Vv*a?\\|"
 293       ;; any other singleton characters
 294       "X")
 295      table))
 296   "Regexp matching a composable sequence of Tamil characters.")
 297
 298 (defconst telugu-composable-pattern
 299   (let ((table
 300          '(("a" . "[\u0C01-\u0C03]")    ; SIGN CANDRABINDU .. VISARGA
 301            ("V" . "[\u0C05-\u0C14\u0C60-\u0C61]") ; independent vowel
 302            ("C" . "[\u0C15-\u0C39\u0C58-\u0C59]") ; consonant
 303            ("v" . "[\u0C3E-\u0C4C\u0C55-\u0C56\u0C62-\u0C63]")  ; vowel sign
 304            ("H" . "\u0C4D")             ; VIRAMA
 305            ("N" . "\u200C")             ; ZWNJ
 306            ("J" . "\u200D")             ; ZWJ
 307            ("X" . "[\u0C00-\u0C7F]")))) ; all coverage
 308     (indian-compose-regexp
 309      (concat
 310       ;; consonant-based syllables, or
 311       "C\\(?:J?HJ?C\\)*\\(?:H[NJ]?\\|v*a?\\)\\|"
 312       ;; syllables with an independent vowel, or
 313       "V\\(?:J?HC\\)?v*a?\\|"
 314       ;; special consonant form, or
 315       "JHC\\|"
 316       ;; any other singleton characters
 317       "X")
 318      table))
 319   "Regexp matching a composable sequence of Telugu characters.")
 320
 321 (defconst kannada-composable-pattern
 322   (let ((table
 323          '(("A" . "[\u0C82-\u0C83]")    ; SIGN ANUSVARA .. VISARGA
 324            ("V" . "[\u0C85-\u0C94\u0CE0-\u0CE1]") ; independent vowel
 325            ("C" . "[\u0C95-\u0CB9\u0CDE]")        ; consonant
 326            ("R" . "\u0CB0")             ; RA
 327            ("n" . "\u0CBC")             ; NUKTA
 328            ("v" . "[\u0CBE-\u0CCC\u0CD5-\u0CD6\u0CE2-\u0CE3]") ; vowel sign
 329            ("H" . "\u0CCD")             ; VIRAMA
 330            ("N" . "\u200C")             ; ZWNJ
 331            ("J" . "\u200D")             ; ZWJ
 332            ("X" . "[\u0C80-\u0CFF]")))) ; all coverage
 333     (indian-compose-regexp
 334      (concat
 335       ;; syllables with an independent vowel, or
 336       "\\(?:RH\\)?Vn?\\(?:J?HC\\)?v?A?\\|"
 337       ;; consonant-based syllables, or
 338       "Cn?\\(?:J?HJ?Cn?\\)*\\(?:H[NJ]?\\|v*n?A?\\)\\|"
 339       ;; special consonant form, or
 340       "JHC\\|"
 341       ;; any other singleton characters
 342       "X")
 343      table))
 344   "Regexp matching a composable sequence of Kannada characters.")
 345
 346 (defconst malayalam-composable-pattern
 347   (let ((table
 348          '(("A" . "[\u0D02-\u0D03]")    ; SIGN ANUSVARA .. VISARGA
 349            ("V" . "[\u0D05-\u0D14\u0D60-\u0D61]") ; independent vowel
 350            ("C" . "[\u0D15-\u0D39]")              ; consonant
 351            ("Y" . "[\u0D2F-\u0D30\u0D32\u0D35]")  ; YA, RA, LA, VA
 352            ("v" . "[\u0D3E-\u0D4C\u0D57\u0D62-\u0D63]") ; postbase matra
 353            ("H" . "\u0D4D")                       ; SIGN VIRAMA
 354            ("N" . "\u200C")                       ; ZWNJ
 355            ("J" . "\u200D")                       ; ZWJ
 356            ("X" . "[\u0D00-\u0D7F]"))))           ; all coverage
 357     (indian-compose-regexp
 358      (concat
 359       ;; consonant-based syllables, or
 360       "C\\(?:J?HJ?C\\)*\\(?:H[NJ]?\\|v?A?\\)\\|"
 361       ;; syllables with an independent vowel, or
 362       "V\\(?:J?HY\\)?v*?A?\\|"
 363       ;; special consonant form, or
 364       "JHY\\|"
 365       ;; any other singleton characters
 366       "X")
 367      table))
 368   "Regexp matching a composable sequence of Malayalam characters.")
 369
 370 (let ((script-regexp-alist
 371        `((devanagari . ,devanagari-composable-pattern)
 372          (bengali . ,bengali-composable-pattern)
 373          (gurmukhi . ,gurmukhi-composable-pattern)
 374          (gujarati . ,gujarati-composable-pattern)
 375          (oriya . ,oriya-composable-pattern)
 376          (tamil . ,tamil-composable-pattern)
 377          (telugu . ,telugu-composable-pattern)
 378          (kannada . ,kannada-composable-pattern)
 379          (malayalam . ,malayalam-composable-pattern))))
 380   (map-char-table
 381    #'(lambda (key val)
 382        (let ((slot (assq val script-regexp-alist)))
 383          (if slot
 384              (set-char-table-range
 385               composition-function-table key
 386               (list (vector (cdr slot) 0 'font-shape-gstring))))))
 387    char-script-table))
 388
 389 (provide 'indian)
 390
 391 ;;; indian.el ends here