code.delx.au - gnu-emacs/blob - 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 of the License, or
  20 ;; (at your option) 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.  If not, see <http://www.gnu.org/licenses/>.
  29
  30 ;;; Commentary:
  31
  32 ;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
  33 ;; supported.
  34
  35 ;;; Code:
  36
  37 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  38 ;;; Chinese (general)
  39 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  40
  41
  42 (define-coding-system 'iso-2022-cn
  43   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)."
  44   :coding-type 'iso-2022
  45   :mnemonic ?C
  46   :charset-list '(ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
  47   :designation [ascii
  48                 (nil chinese-gb2312 chinese-cns11643-1)
  49                 (nil chinese-cns11643-2)
  50                 nil]
  51   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  52                         designation locking-shift single-shift init-at-bol)
  53   :mime-charset 'iso-2022-cn
  54   :suitable-for-keyboard t)
  55
  56 (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
  57
  58 (define-coding-system 'iso-2022-cn-ext
  59   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)."
  60   :coding-type 'iso-2022
  61   :mnemonic ?C
  62   :charset-list '(ascii
  63                   chinese-gb2312 chinese-cns11643-1
  64                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
  65                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
  66   :designation '[ascii
  67                  (nil chinese-gb2312 chinese-cns11643-1)
  68                  (nil chinese-cns11643-2)
  69                  (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
  70                       chinese-cns11643-6 chinese-cns11643-7)]
  71   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  72                         designation locking-shift single-shift init-at-bol)
  73   :mime-charset 'iso-2022-cn-ext
  74   :suitable-for-keyboard t)
  75
  76 \f
  77 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  78 ;;; Chinese GB2312 (simplified)
  79 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  80
  81 (define-coding-system 'chinese-iso-8bit
  82   "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:GB2312)."
  83   :coding-type 'iso-2022
  84   :mnemonic ?c
  85   :charset-list '(ascii chinese-gb2312)
  86   :designation [ascii chinese-gb2312 nil nil]
  87   :mime-charset 'gb2312)
  88
  89 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
  90 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
  91 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
  92 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
  93 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
  94
  95 (define-coding-system 'chinese-hz
  96   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
  97   :coding-type 'utf-8
  98   :mnemonic ?z
  99   :charset-list '(ascii chinese-gb2312)
 100   :mime-charset 'hz-gb-2312
 101   :post-read-conversion 'post-read-decode-hz
 102   :pre-write-conversion 'pre-write-encode-hz)
 103
 104 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 105 (define-coding-system-alias 'hz 'chinese-hz)
 106
 107 (set-language-info-alist
 108  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
 109                 (iso639-language . zh)
 110                 (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
 111                 (coding-priority chinese-iso-8bit chinese-big5 iso-2022-cn)
 112                 (input-method . "chinese-py-punct")
 113                 (features china-util)
 114                 (sample-text . "Chinese (\e$AVPND\e(B,\e$AFUM(;0\e(B,\e$A::So\e(B)    \e$ADc:C\e(B")
 115                 (documentation . "Support for Chinese GB2312 character set.")
 116                 (tutorial . "TUTORIAL.cn"))
 117  '("Chinese"))
 118
 119 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 120 ;; Chinese BIG5 (traditional)
 121 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 122
 123 (define-coding-system 'chinese-big5
 124   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 125   :coding-type 'charset
 126   :mnemonic ?B
 127   :charset-list '(ascii big5)
 128   :mime-charset 'big5)
 129
 130 (define-coding-system-alias 'big5 'chinese-big5)
 131 (define-coding-system-alias 'cn-big5 'chinese-big5)
 132 (define-coding-system-alias 'cp950 'chinese-big5)
 133
 134 (set-language-info-alist
 135  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 136                   (iso639-language . zh)
 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$(0GnM$\e(B,\e$(0N]0*Hd\e(B) \e$(0*/=(\e(B, \e$(0+$)p\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                  (iso639-language . zh)
 189                  (coding-system iso-2022-cn euc-tw)
 190                  (coding-priority iso-2022-cn euc-tw chinese-big5
 191                                   chinese-iso-8bit)
 192                  (features china-util)
 193                  (input-method . "chinese-cns-quick")
 194                  ;; Fixme: presumably it won't accept big5 now.
 195                  (documentation . "\
 196 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 197 accepts Big5 for input also (which is then converted to CNS)."))
 198  '("Chinese"))
 199
 200 (set-language-info-alist
 201  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 202                              chinese-cns11643-3 chinese-cns11643-4
 203                              chinese-cns11643-5 chinese-cns11643-6
 204                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 205                     (iso639-language . zh)
 206                     (coding-system euc-tw iso-2022-cn)
 207                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 208                                      chinese-iso-8bit)
 209                     (features china-util)
 210                     (input-method . "chinese-cns-quick")
 211                     (documentation . "\
 212 Support for Chinese, prefering the EUC-TW character set.  Note that
 213 the EUC-TW coding system accepts Big5 for input also (which is then
 214 converted to CNS)."))
 215  '("Chinese"))
 216
 217
 218 ;;; Chinese GBK
 219
 220 (define-coding-system 'chinese-gbk
 221   "GBK encoding for Chinese (MIME:GBK)."
 222   :coding-type 'charset
 223   :mnemonic ?c
 224   :charset-list '(ascii chinese-gbk)
 225   :mime-charset 'gbk)
 226 (define-coding-system-alias 'gbk 'chinese-gbk)
 227 (define-coding-system-alias 'cp936 'chinese-gbk)
 228 (define-coding-system-alias 'windows-936 'chinese-gbk)
 229
 230 (set-language-info-alist
 231  "Chinese-GBK" '((charset chinese-gbk)
 232                  (iso639-language . zh)
 233                  (coding-system chinese-gbk)
 234                  (coding-priority gbk iso-2022-cn chinese-big5
 235                                   chinese-iso-8bit) ; fixme?
 236                  (ctext-non-standard-encodings "gbk-0")
 237                  (input-method . "chinese-py-punct") ; fixme?
 238                  (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")
 239                  (features china-util)
 240                  (documentation . "Support for Chinese GBK character set.")
 241                  (tutorial . "TUTORIAL.cn"))
 242  '("Chinese"))
 243
 244 ;;; Chinese GB18030
 245
 246 (define-coding-system 'chinese-gb18030
 247   "GB18030 encoding for Chinese (MIME:GB18030)."
 248   :coding-type 'charset
 249   :mnemonic ?c
 250   :charset-list '(ascii gb18030-2-byte
 251                         gb18030-4-byte-bmp gb18030-4-byte-smp
 252                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 253   :mime-charset 'gb18030)
 254
 255 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 256
 257 (set-language-info-alist
 258  "Chinese-GB18030" '((charset gb18030)
 259                      (iso639-language . zh)
 260                      (coding-system chinese-gb18030)
 261                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 262                                       chinese-iso-8bit) ; fixme?
 263                      (input-method . "chinese-py-punct") ; fixme?
 264                      (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")
 265                      (features china-util)
 266                      (documentation
 267                       . "Support for Chinese GB18030 character set.")
 268                      (tutorial . "TUTORIAL.cn"))
 269  '("Chinese"))
 270
 271 ;; Fixme: add HKSCS
 272
 273 (provide 'chinese)
 274
 275 ;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f
 276 ;;; chinese.el ends here