lisp/language/indian.el

   1 ;;; indian.el --- Indian languages support -*- coding: utf-8; -*-
   2
   3 ;; Copyright (C) 1997, 1999, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
   4 ;;   Free Software Foundation, Inc.
   5 ;; Copyright (C) 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8
   9 ;; Maintainer:  Kenichi Handa <handa@m17n.org>
  10 ;;              KAWABATA, Taichi <kawabata@m17n.org>
  11 ;; Keywords:    multilingual, i18n, Indian
  12
  13 ;; This file is part of GNU Emacs.
  14
  15 ;; GNU Emacs is free software: you can redistribute it and/or modify
  16 ;; it under the terms of the GNU General Public License as published by
  17 ;; the Free Software Foundation, either version 3 of the License, or
  18 ;; (at your option) any later version.
  19
  20 ;; GNU Emacs is distributed in the hope that it will be useful,
  21 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  22 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  23 ;; GNU General Public License for more details.
  24
  25 ;; You should have received a copy of the GNU General Public License
  26 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  27
  28 ;;; Commentary:
  29
  30 ;; This file contains definitions of Indian language environments, and
  31 ;; setups for displaying the scrtipts used there.
  32
  33 ;;; Code:
  34
  35 (define-coding-system 'in-is13194-devanagari
  36   "8-bit encoding for ASCII (MSB=0) and IS13194-Devanagari (MSB=1)."
  37   :coding-type 'iso-2022
  38   :mnemonic ?D
  39   :designation [ascii indian-is13194 nil nil]
  40   :charset-list '(ascii indian-is13194)
  41   :post-read-conversion 'in-is13194-post-read-conversion
  42   :pre-write-conversion 'in-is13194-pre-write-conversion)
  43
  44 (define-coding-system-alias 'devanagari 'in-is13194-devanagari)
  45
  46 (set-language-info-alist
  47  "Devanagari" '((charset unicode)
  48                 (coding-system utf-8)
  49                 (coding-priority utf-8)
  50                 (input-method . "dev-aiba")
  51                 (documentation . "\
  52 Such languages using Devanagari script as Hindi and Marathi
  53 are supported in this language environment."))
  54  '("Indian"))
  55
  56 (set-language-info-alist
  57  "Bengali" '((charset unicode)
  58              (coding-system utf-8)
  59              (coding-priority utf-8)
  60              (input-method . "bengali-itrans")
  61              (documentation . "\
  62 Such languages using Bengali script as Bengali and Assamese
  63 are supported in this language environment."))
  64  '("Indian"))
  65
  66 (set-language-info-alist
  67  "Punjabi" '((charset unicode)
  68               (coding-system utf-8)
  69               (coding-priority utf-8)
  70               (input-method . "punjabi-itrans")
  71               (documentation . "\
  72 North Indian language Punjabi is supported in this language environment."))
  73  '("Indian"))
  74
  75 (set-language-info-alist
  76  "Gujarati" '((charset unicode)
  77               (coding-system utf-8)
  78               (coding-priority utf-8)
  79               (input-method . "gujarati-itrans")
  80               (documentation . "\
  81 North Indian language Gujarati is supported in this language environment."))
  82  '("Indian"))
  83
  84 (set-language-info-alist
  85  "Oriya" '((charset unicode)
  86               (coding-system utf-8)
  87               (coding-priority utf-8)
  88               (input-method . "oriya-itrans")
  89               (documentation . "\
  90 Such languages using Oriya script as Oriya, Khonti, and Santali
  91 are supported in this language environment."))
  92  '("Indian"))
  93
  94 (set-language-info-alist
  95  "Tamil" '((charset unicode)
  96            (coding-system utf-8)
  97            (coding-priority utf-8)
  98            (input-method . "tamil-itrans")
  99            (documentation . "\
 100 South Indian Language Tamil is supported in this language environment."))
 101  '("Indian"))
 102
 103 (set-language-info-alist
 104  "Telugu" '((charset unicode)
 105             (coding-system utf-8)
 106             (coding-priority utf-8)
 107             (input-method . "telugu-itrans")
 108             (documentation . "\
 109 South Indian Language Telugu is supported in this language environment."))
 110  '("Indian"))
 111
 112 (set-language-info-alist
 113  "Kannada" '((charset unicode)
 114              (coding-system mule-utf-8)
 115              (coding-priority mule-utf-8)
 116              (input-method . "kannada-itrans")
 117              (sample-text . "Kannada (ಕನ್ನಡ)  ನಮಸ್ಕಾರ")
 118              (documentation . "\
 119 Kannada language and script is supported in this language
 120 environment."))
 121  '("Indian"))
 122
 123 (set-language-info-alist
 124  "Malayalam" '((charset unicode)
 125                (coding-system utf-8)
 126                (coding-priority utf-8)
 127                (input-method . "malayalam-itrans")
 128                (documentation . "\
 129 South Indian language Malayalam is supported in this language environment."))
 130  '("Indian"))
 131
 132 ;; Replace mnemonic characters in REGEXP according to TABLE.  TABLE is
 133 ;; an alist of (MNEMONIC-STRING . REPLACEMENT-STRING).
 134
 135 (defun indian-compose-regexp (regexp table)
 136   (let ((case-fold-search nil))
 137     (dolist (elt table)
 138       (setq regexp (replace-regexp-in-string (car elt) (cdr elt) regexp t t)))
 139     regexp))
 140
 141 (defconst devanagari-composable-pattern
 142   (concat
 143    "\\([अ-औॠॡ][ँं]?\\)\\|[ः।]"
 144    "\\|\\("
 145    "\\(?:\\(?:[क-हक़-य़]्\\)?\\(?:[क-हक़-य़]्\\)?\\(?:[क-हक़-य़]्\\)?[क-हक़-य़]्\\)?"
 146    "[क-हक़-य़]\\(?:्\\|[ा-्ॢॣ]?[ंँ]?\\)?"
 147    "\\)")
 148   "Regexp matching a composable sequence of Devanagari characters.")
 149
 150 (defconst tamil-composable-pattern
 151   (concat
 152    "\\([அ-ஔ]\\)\\|"
 153    "[ஂஃ]\\|" ;; vowel modifier considered independent
 154    "\\(\\(?:\\(?:க்ஷ\\)\\|[க-ஹ]\\)[்ா-ௌ]?\\)\\|"
 155    "\\(ஷ்ரீ\\)")
 156   "Regexp matching a composable sequence of Tamil characters.")
 157
 158 (defconst kannada-composable-pattern
 159   (concat
 160    "\\([ಂ-ಔೠಌ]\\)\\|[ಃ]"
 161    "\\|\\("
 162    "\\(?:\\(?:[ಕ-ಹ]್\\)?\\(?:[ಕ-ಹ]್\\)?\\(?:[ಕ-ಹ]್\\)?[ಕ-ಹ]್\\)?"
 163    "[ಕ-ಹ]\\(?:್\\|[ಾ-್ೕೃ]?\\)?"
 164    "\\)")
 165   "Regexp matching a composable sequence of Kannada characters.")
 166
 167 (defconst malayalam-composable-pattern
 168   (let ((table '(("V" . "[\u0D05-\u0D14\u0D60-\u0D61]") ; independent vowel
 169                  ("C" . "[\u0D15-\u0D39]")              ; consonant
 170                  ("m" . "[\u0D46-\u0D48\u0D4A-\u0D4C]") ; prebase matra
 171                  ("p" . "[\u0D3E-\u0D44\u0D57]") ; postname matra
 172                  ("b" . "[\u0D62-\u0D63]")       ; belowbase matra
 173                  ("a" . "[\u0D02-\u0D03]")       ; abovebase sign
 174                  ("H" . "്")                   ; virama sign
 175                  ("N" . "\u200D")                ; ZWJ
 176                  ("J" . "\u200C")                ; ZWNJ
 177                  ("X" . "[\u0D00-\u0D7F]")))) ; all coverage
 178     (indian-compose-regexp
 179      (concat
 180       ;; consonant-based syllables
 181       "\\(CJ?HJ?\\)*C\\(H[NJ]?\\|m?b?p?a?\\)\\|"
 182       ;; syllables with an independent vowel
 183       "V\\(J?HC\\)?m?b?p?n?a?\\|"
 184       ;; special consonant form
 185       "JHC\\|"
 186       ;; any other singleton characters
 187       "X")
 188      table))
 189   "Regexp matching a composable sequence of Malayalam characters.")
 190
 191 (let ((script-regexp-alist
 192        `((devanagari . "[\x900-\x97F\x200C\x200D]+")
 193          (bengali . "[\x980-\x9FF\x200C\x200D]+")
 194          (gurmukhi . "[\xA00-\xA7F\x200C\x200D]+")
 195          (gujarati . "[\xA80-\xAFF\x200C\x200D]+")
 196          (oriya . "[\xB00-\xB7F\x200C\x200D]+")
 197          (tamil . "[\xB80-\xBFF\x200C\x200D]+")
 198          (telugu . "[\xC00-\xC7F\x200C\x200D]+")
 199          (kannada . "[\xC80-\xCFF\x200C\x200D]+")
 200          (malayalam . ,malayalam-composable-pattern))))
 201   (map-char-table
 202    #'(lambda (key val)
 203        (let ((slot (assq val script-regexp-alist)))
 204          (if slot
 205              (set-char-table-range
 206               composition-function-table key
 207               (list (vector (cdr slot) 0 'font-shape-gstring))))))
 208    char-script-table))
 209
 210 (provide 'indian)
 211
 212 ;; arch-tag: 83aa8fc7-7ee2-4364-a6e5-498f5e3b8c2f
 213 ;;; indian.el ends here