lisp/language/chinese.el

   1 ;;; chinese.el --- support for Chinese -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 2001, 2003  Free Software Foundation, Inc.
   4 ;; Copyright (C) 1995, 1997, 1998
   5 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   6 ;;   Registration Number H14PRO021
   7 ;; Copyright (C) 2003
   8 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   9 ;;   Registration Number H13PRO009
  10
  11 ;; Keywords: multilingual, Chinese
  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 2, or (at your option)
  18 ;; 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; see the file COPYING.  If not, write to the
  27 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  28 ;; Boston, MA 02110-1301, USA.
  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 (define-coding-system-alias 'cp936 'chinese-iso-8bit)
  95
  96 (define-coding-system 'chinese-hz
  97   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
  98   :coding-type 'utf-8
  99   :mnemonic ?z
 100   :charset-list '(ascii chinese-gb2312)
 101   :mime-charset 'hz-gb-2312
 102   :post-read-conversion 'post-read-decode-hz
 103   :pre-write-conversion 'pre-write-encode-hz)
 104
 105 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 106 (define-coding-system-alias 'hz 'chinese-hz)
 107
 108 (set-language-info-alist
 109  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
 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                   (coding-system chinese-big5 chinese-iso-7bit)
 137                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
 138                   (input-method . "chinese-py-punct-b5")
 139                   (ctext-non-standard-encodings "big5-0")
 140                   (features china-util)
 141                   (sample-text . "Cantonese (\e$(Gemk#\e(B,\e$(Gl]N)fc\e(B) \e$ATg3?\e(B, \e$ADc:C\e(B")
 142                   (documentation . "Support for Chinese Big5 character set.")
 143                   (tutorial . "TUTORIAL.zh"))
 144  '("Chinese"))
 145
 146 (define-coding-system 'chinese-big5-hkscs
 147   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 148   :coding-type 'charset
 149   :mnemonic ?B
 150   :charset-list '(ascii big5-hkscs)
 151   :mime-charset 'big5-hkscs)
 152 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 153 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 154
 155 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 156 ;; Chinese CNS11643 (traditional)
 157 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 158
 159 (define-coding-system 'euc-tw
 160   "ISO 2022 based EUC encoding for Chinese CNS11643."
 161   :coding-type 'iso-2022
 162   :mnemonic ?Z
 163   :charset-list '(ascii
 164                   chinese-cns11643-1
 165                   chinese-cns11643-2
 166                   chinese-cns11643-3
 167                   chinese-cns11643-4
 168                   chinese-cns11643-5
 169                   chinese-cns11643-6
 170                   chinese-cns11643-7)
 171   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 172                                           chinese-cns11643-2
 173                                           chinese-cns11643-3
 174                                           chinese-cns11643-4
 175                                           chinese-cns11643-5
 176                                           chinese-cns11643-6
 177                                           chinese-cns11643-7) nil]
 178   :mime-charset 'euc-tw)
 179
 180 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 181
 182 (set-language-info-alist
 183  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 184                           chinese-cns11643-3 chinese-cns11643-4
 185                           chinese-cns11643-5 chinese-cns11643-6
 186                           chinese-cns11643-7)
 187                  (coding-system iso-2022-cn euc-tw)
 188                  (coding-priority iso-2022-cn euc-tw chinese-big5
 189                                   chinese-iso-8bit)
 190                  (features china-util)
 191                  (input-method . "chinese-cns-quick")
 192                  ;; Fixme: presumably it won't accept big5 now.
 193                  (documentation . "\
 194 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 195 accepts Big5 for input also (which is then converted to CNS)."))
 196  '("Chinese"))
 197
 198 (set-language-info-alist
 199  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 200                              chinese-cns11643-3 chinese-cns11643-4
 201                              chinese-cns11643-5 chinese-cns11643-6
 202                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 203                     (coding-system euc-tw iso-2022-cn)
 204                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 205                                      chinese-iso-8bit)
 206                     (features china-util)
 207                     (input-method . "chinese-cns-quick")
 208                     (documentation . "\
 209 Support for Chinese, prefering the EUC-TW character set.  Note that
 210 the EUC-TW coding system accepts Big5 for input also (which is then
 211 converted to CNS)."))
 212  '("Chinese"))
 213
 214
 215 ;;; Chinese GBK
 216
 217 (define-coding-system 'chinese-gbk
 218   "GBK encoding for Chinese (MIME:GBK)."
 219   :coding-type 'charset
 220   :mnemonic ?c
 221   :charset-list '(ascii chinese-gbk)
 222   :mime-charset 'gbk)
 223 (define-coding-system-alias 'gbk 'chinese-gbk)
 224 (define-coding-system-alias 'cp936 'chinese-gbk)
 225 (define-coding-system-alias 'windows-936 'chinese-gbk)
 226
 227 (set-language-info-alist
 228  "Chinese-GBK" '((charset chinese-gbk)
 229                  (coding-system chinese-gbk)
 230                  (coding-priority gbk iso-2022-cn chinese-big5
 231                                   chinese-iso-8bit) ; fixme?
 232                  (ctext-non-standard-encodings "gbk-0")
 233                  (input-method . "chinese-py-punct") ; fixme?
 234                  (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")
 235                  (features china-util)
 236                  (documentation . "Support for Chinese GBK character set."))
 237  '("Chinese"))
 238
 239 ;;; Chinese GB18030
 240
 241 (define-coding-system 'chinese-gb18030
 242   "GB18030 encoding for Chinese (MIME:GB18030)."
 243   :coding-type 'charset
 244   :mnemonic ?c
 245   :charset-list '(ascii gb18030-2-byte
 246                         gb18030-4-byte-bmp gb18030-4-byte-smp
 247                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 248   :mime-charset 'gb18030)
 249
 250 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 251
 252 (set-language-info-alist
 253  "Chinese-GB18030" '((charset gb18030)
 254                      (coding-system chinese-gb18030)
 255                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 256                                       chinese-iso-8bit) ; fixme?
 257                      (input-method . "chinese-py-punct") ; fixme?
 258                      (features china-util)
 259                      (documentation
 260                       . "Support for Chinese GB18030 character set."))
 261  '("Chinese"))
 262
 263 ;; Fixme: add HKSCS
 264
 265 (provide 'chinese)
 266
 267 ;;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f
 268 ;;; chinese.el ends here