lisp/language/chinese.el

   1 ;;; chinese.el --- support for Chinese -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
   4 ;;   Free Software Foundation, Inc.
   5 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
   6 ;;   2005, 2006, 2007, 2008
   7 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   8 ;;   Registration Number H14PRO021
   9 ;; Copyright (C) 2003
  10 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  11 ;;   Registration Number H13PRO009
  12
  13 ;; Keywords: multilingual, Chinese
  14
  15 ;; This file is part of GNU Emacs.
  16
  17 ;; GNU Emacs is free software; you can redistribute it and/or modify
  18 ;; it under the terms of the GNU General Public License as published by
  19 ;; the Free Software Foundation; either version 3, or (at your option)
  20 ;; any later version.
  21
  22 ;; GNU Emacs is distributed in the hope that it will be useful,
  23 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  24 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  25 ;; GNU General Public License for more details.
  26
  27 ;; You should have received a copy of the GNU General Public License
  28 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  29 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  30 ;; Boston, MA 02110-1301, USA.
  31
  32 ;;; Commentary:
  33
  34 ;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
  35 ;; supported.
  36
  37 ;;; Code:
  38
  39 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  40 ;;; Chinese (general)
  41 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  42
  43
  44 (define-coding-system 'iso-2022-cn
  45   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)."
  46   :coding-type 'iso-2022
  47   :mnemonic ?C
  48   :charset-list '(ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
  49   :designation [ascii
  50                 (nil chinese-gb2312 chinese-cns11643-1)
  51                 (nil chinese-cns11643-2)
  52                 nil]
  53   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  54                         designation locking-shift single-shift init-at-bol)
  55   :mime-charset 'iso-2022-cn
  56   :suitable-for-keyboard t)
  57
  58 (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
  59
  60 (define-coding-system 'iso-2022-cn-ext
  61   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)."
  62   :coding-type 'iso-2022
  63   :mnemonic ?C
  64   :charset-list '(ascii
  65                   chinese-gb2312 chinese-cns11643-1
  66                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
  67                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
  68   :designation '[ascii
  69                  (nil chinese-gb2312 chinese-cns11643-1)
  70                  (nil chinese-cns11643-2)
  71                  (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
  72                       chinese-cns11643-6 chinese-cns11643-7)]
  73   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  74                         designation locking-shift single-shift init-at-bol)
  75   :mime-charset 'iso-2022-cn-ext
  76   :suitable-for-keyboard t)
  77
  78 \f
  79 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  80 ;;; Chinese GB2312 (simplified)
  81 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  82
  83 (define-coding-system 'chinese-iso-8bit
  84   "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:GB2312)."
  85   :coding-type 'iso-2022
  86   :mnemonic ?c
  87   :charset-list '(ascii chinese-gb2312)
  88   :designation [ascii chinese-gb2312 nil nil]
  89   :mime-charset 'gb2312)
  90
  91 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
  92 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
  93 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
  94 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
  95 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
  96
  97 (define-coding-system 'chinese-hz
  98   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
  99   :coding-type 'utf-8
 100   :mnemonic ?z
 101   :charset-list '(ascii chinese-gb2312)
 102   :mime-charset 'hz-gb-2312
 103   :post-read-conversion 'post-read-decode-hz
 104   :pre-write-conversion 'pre-write-encode-hz)
 105
 106 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 107 (define-coding-system-alias 'hz 'chinese-hz)
 108
 109 (set-language-info-alist
 110  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
 111                 (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
 112                 (coding-priority chinese-iso-8bit chinese-big5 iso-2022-cn)
 113                 (input-method . "chinese-py-punct")
 114                 (features china-util)
 115                 (sample-text . "Chinese (\e$AVPND\e(B,\e$AFUM(;0\e(B,\e$A::So\e(B)    \e$ADc:C\e(B")
 116                 (documentation . "Support for Chinese GB2312 character set.")
 117                 (tutorial . "TUTORIAL.cn"))
 118  '("Chinese"))
 119
 120 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 121 ;; Chinese BIG5 (traditional)
 122 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 123
 124 (define-coding-system 'chinese-big5
 125   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 126   :coding-type 'charset
 127   :mnemonic ?B
 128   :charset-list '(ascii big5)
 129   :mime-charset 'big5)
 130
 131 (define-coding-system-alias 'big5 'chinese-big5)
 132 (define-coding-system-alias 'cn-big5 'chinese-big5)
 133 (define-coding-system-alias 'cp950 'chinese-big5)
 134
 135 (set-language-info-alist
 136  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 137                   (coding-system chinese-big5 chinese-iso-7bit)
 138                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
 139                   (input-method . "chinese-py-punct-b5")
 140                   (ctext-non-standard-encodings "big5-0")
 141                   (features china-util)
 142                   (sample-text . "Cantonese (\e$(Gemk#\e(B,\e$(Gl]N)fc\e(B) \e$ATg3?\e(B, \e$ADc:C\e(B")
 143                   (documentation . "Support for Chinese Big5 character set.")
 144                   (tutorial . "TUTORIAL.zh"))
 145  '("Chinese"))
 146
 147 (define-coding-system 'chinese-big5-hkscs
 148   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 149   :coding-type 'charset
 150   :mnemonic ?B
 151   :charset-list '(ascii big5-hkscs)
 152   :mime-charset 'big5-hkscs)
 153 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 154 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 155
 156 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 157 ;; Chinese CNS11643 (traditional)
 158 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 159
 160 (define-coding-system 'euc-tw
 161   "ISO 2022 based EUC encoding for Chinese CNS11643."
 162   :coding-type 'iso-2022
 163   :mnemonic ?Z
 164   :charset-list '(ascii
 165                   chinese-cns11643-1
 166                   chinese-cns11643-2
 167                   chinese-cns11643-3
 168                   chinese-cns11643-4
 169                   chinese-cns11643-5
 170                   chinese-cns11643-6
 171                   chinese-cns11643-7)
 172   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 173                                           chinese-cns11643-2
 174                                           chinese-cns11643-3
 175                                           chinese-cns11643-4
 176                                           chinese-cns11643-5
 177                                           chinese-cns11643-6
 178                                           chinese-cns11643-7) nil]
 179   :mime-charset 'euc-tw)
 180
 181 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 182
 183 (set-language-info-alist
 184  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 185                           chinese-cns11643-3 chinese-cns11643-4
 186                           chinese-cns11643-5 chinese-cns11643-6
 187                           chinese-cns11643-7)
 188                  (coding-system iso-2022-cn euc-tw)
 189                  (coding-priority iso-2022-cn euc-tw chinese-big5
 190                                   chinese-iso-8bit)
 191                  (features china-util)
 192                  (input-method . "chinese-cns-quick")
 193                  ;; Fixme: presumably it won't accept big5 now.
 194                  (documentation . "\
 195 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 196 accepts Big5 for input also (which is then converted to CNS)."))
 197  '("Chinese"))
 198
 199 (set-language-info-alist
 200  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 201                              chinese-cns11643-3 chinese-cns11643-4
 202                              chinese-cns11643-5 chinese-cns11643-6
 203                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 204                     (coding-system euc-tw iso-2022-cn)
 205                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 206                                      chinese-iso-8bit)
 207                     (features china-util)
 208                     (input-method . "chinese-cns-quick")
 209                     (documentation . "\
 210 Support for Chinese, prefering the EUC-TW character set.  Note that
 211 the EUC-TW coding system accepts Big5 for input also (which is then
 212 converted to CNS)."))
 213  '("Chinese"))
 214
 215
 216 ;;; Chinese GBK
 217
 218 (define-coding-system 'chinese-gbk
 219   "GBK encoding for Chinese (MIME:GBK)."
 220   :coding-type 'charset
 221   :mnemonic ?c
 222   :charset-list '(ascii chinese-gbk)
 223   :mime-charset 'gbk)
 224 (define-coding-system-alias 'gbk 'chinese-gbk)
 225 (define-coding-system-alias 'cp936 'chinese-gbk)
 226 (define-coding-system-alias 'windows-936 'chinese-gbk)
 227
 228 (set-language-info-alist
 229  "Chinese-GBK" '((charset chinese-gbk)
 230                  (coding-system chinese-gbk)
 231                  (coding-priority gbk iso-2022-cn chinese-big5
 232                                   chinese-iso-8bit) ; fixme?
 233                  (ctext-non-standard-encodings "gbk-0")
 234                  (input-method . "chinese-py-punct") ; fixme?
 235                  (sample-text . "Chinese (\e$BCfJ8\e(B,\e$BIaDL\e$A;0\e(B,\e$A::So\e(B) \e$(D95\e$B9%\e(B")
 236                  (features china-util)
 237                  (documentation . "Support for Chinese GBK character set.")
 238                  (tutorial . "TUTORIAL.cn"))
 239  '("Chinese"))
 240
 241 ;;; Chinese GB18030
 242
 243 (define-coding-system 'chinese-gb18030
 244   "GB18030 encoding for Chinese (MIME:GB18030)."
 245   :coding-type 'charset
 246   :mnemonic ?c
 247   :charset-list '(ascii gb18030-2-byte
 248                         gb18030-4-byte-bmp gb18030-4-byte-smp
 249                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 250   :mime-charset 'gb18030)
 251
 252 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 253
 254 (set-language-info-alist
 255  "Chinese-GB18030" '((charset gb18030)
 256                      (coding-system chinese-gb18030)
 257                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 258                                       chinese-iso-8bit) ; fixme?
 259                      (input-method . "chinese-py-punct") ; fixme?
 260                      (sample-text . "Chinese (\e$BCfJ8\e(B,\e$BIaDL\e$A;0\e(B,\e$A::So\e(B) \e$(D0_\e$B9%\e(B")
 261                      (features china-util)
 262                      (documentation
 263                       . "Support for Chinese GB18030 character set.")
 264                      (tutorial . "TUTORIAL.cn"))
 265  '("Chinese"))
 266
 267 ;; Fixme: add HKSCS
 268
 269 (provide 'chinese)
 270
 271 ;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f
 272 ;;; chinese.el ends here