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., 59 Temple Place - Suite 330,
  28 ;; Boston, MA 02111-1307, 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
  55 (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
  56
  57 (define-coding-system 'iso-2022-cn-ext
  58   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)."
  59   :coding-type 'iso-2022
  60   :mnemonic ?C
  61   :charset-list '(ascii
  62                   chinese-gb2312 chinese-cns11643-1
  63                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
  64                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
  65   :designation '[ascii
  66                  (nil chinese-gb2312 chinese-cns11643-1)
  67                  (nil chinese-cns11643-2)
  68                  (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
  69                       chinese-cns11643-6 chinese-cns11643-7)]
  70   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  71                         designation locking-shift single-shift init-at-bol)
  72   :mime-charset 'iso-2022-cn-ext)
  73
  74 \f
  75 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  76 ;;; Chinese GB2312 (simplified)
  77 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  78
  79 (define-coding-system 'chinese-iso-8bit
  80   "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:GB2312)."
  81   :coding-type 'iso-2022
  82   :mnemonic ?c
  83   :charset-list '(ascii chinese-gb2312)
  84   :designation [ascii chinese-gb2312 nil nil]
  85   :mime-charset 'gb2312)
  86
  87 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
  88 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
  89 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
  90 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
  91 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
  92 (define-coding-system-alias 'cp936 'chinese-iso-8bit)
  93
  94 (define-coding-system 'chinese-hz
  95   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
  96   :coding-type 'utf-8
  97   :mnemonic ?z
  98   :charset-list '(ascii chinese-gb2312)
  99   :mime-charset 'hz-gb-2312
 100   :post-read-conversion 'post-read-decode-hz
 101   :pre-write-conversion 'pre-write-encode-hz)
 102
 103 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 104 (define-coding-system-alias 'hz 'chinese-hz)
 105
 106 (set-language-info-alist
 107  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
 108                 (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
 109                 (coding-priority chinese-iso-8bit chinese-big5 iso-2022-cn)
 110                 (input-method . "chinese-py-punct")
 111                 (features china-util)
 112                 (sample-text . "Chinese (\e$AVPND\e(B,\e$AFUM(;0\e(B,\e$A::So\e(B)    \e$ADc:C\e(B")
 113                 (documentation . "Support for Chinese GB2312 character set.")
 114                 (tutorial . "TUTORIAL.cn"))
 115  '("Chinese"))
 116
 117 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 118 ;; Chinese BIG5 (traditional)
 119 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 120
 121 (define-coding-system 'chinese-big5
 122   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 123   :coding-type 'charset
 124   :mnemonic ?B
 125   :charset-list '(ascii big5)
 126   :mime-charset 'big5)
 127
 128 (define-coding-system-alias 'big5 'chinese-big5)
 129 (define-coding-system-alias 'cn-big5 'chinese-big5)
 130 (define-coding-system-alias 'cp950 'chinese-big5)
 131
 132 (set-language-info-alist
 133  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 134                   (coding-system chinese-big5 chinese-iso-7bit)
 135                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
 136                   (input-method . "chinese-py-punct-b5")
 137                   (features china-util)
 138                   (sample-text . "Cantonese (\e$(Gemk#\e(B,\e$(Gl]N)fc\e(B) \e$ATg3?\e(B, \e$ADc:C\e(B")
 139                   (documentation . "Support for Chinese Big5 character set.")
 140                   (tutorial . "TUTORIAL.zh"))
 141  '("Chinese"))
 142
 143 (define-coding-system 'chinese-big5-hkscs
 144   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 145   :coding-type 'charset
 146   :mnemonic ?B
 147   :charset-list '(ascii big5-hkscs)
 148   :mime-charset 'big5-hkscs)
 149 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 150 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 151
 152 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 153 ;; Chinese CNS11643 (traditional)
 154 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 155
 156 (define-coding-system 'euc-tw
 157   "ISO 2022 based EUC encoding for Chinese CNS11643."
 158   :coding-type 'iso-2022
 159   :mnemonic ?Z
 160   :charset-list '(ascii
 161                   chinese-cns11643-1
 162                   chinese-cns11643-2
 163                   chinese-cns11643-3
 164                   chinese-cns11643-4
 165                   chinese-cns11643-5
 166                   chinese-cns11643-6
 167                   chinese-cns11643-7)
 168   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 169                                           chinese-cns11643-2
 170                                           chinese-cns11643-3
 171                                           chinese-cns11643-4
 172                                           chinese-cns11643-5
 173                                           chinese-cns11643-6
 174                                           chinese-cns11643-7) nil]
 175   :mime-charset 'euc-tw)
 176
 177 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 178
 179 (set-language-info-alist
 180  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 181                           chinese-cns11643-3 chinese-cns11643-4
 182                           chinese-cns11643-5 chinese-cns11643-6
 183                           chinese-cns11643-7)
 184                  (coding-system iso-2022-cn euc-tw)
 185                  (coding-priority iso-2022-cn euc-tw chinese-big5
 186                                   chinese-iso-8bit)
 187                  (features china-util)
 188                  (input-method . "chinese-cns-quick")
 189                  ;; Fixme: presumably it won't accept big5 now.
 190                  (documentation . "\
 191 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 192 accepts Big5 for input also (which is then converted to CNS)."))
 193  '("Chinese"))
 194
 195 (set-language-info-alist
 196  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 197                              chinese-cns11643-3 chinese-cns11643-4
 198                              chinese-cns11643-5 chinese-cns11643-6
 199                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 200                     (coding-system euc-tw iso-2022-cn)
 201                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 202                                      chinese-iso-8bit)
 203                     (features china-util)
 204                     (input-method . "chinese-cns-quick")
 205                     (documentation . "\
 206 Support for Chinese, prefering the EUC-TW character set.  Note that
 207 the EUC-TW coding system accepts Big5 for input also (which is then
 208 converted to CNS)."))
 209  '("Chinese"))
 210
 211
 212 ;;; Chinese GBK
 213
 214 (define-coding-system 'chinese-gbk
 215   "GBK encoding for Chinese (MIME:GBK)."
 216   :coding-type 'charset
 217   :mnemonic ?c
 218   :charset-list '(ascii chinese-gbk)
 219   :mime-charset 'gbk)
 220 (define-coding-system-alias 'gbk 'chinese-gbk)
 221 (define-coding-system-alias 'cp936 'chinese-gbk)
 222 (define-coding-system-alias 'windows-936 'chinese-gbk)
 223
 224 (set-language-info-alist
 225  "Chinese-GBK" '((charset chinese-gbk)
 226                  (coding-system chinese-gbk)
 227                  (coding-priority gbk iso-2022-cn chinese-big5
 228                                   chinese-iso-8bit) ; fixme?
 229                  (input-method . "chinese-py-punct") ; fixme?
 230                  (features china-util)
 231                  (documentation . "Support for Chinese GBK character set."))
 232  '("Chinese"))
 233
 234 ;;; Chinese GB18030
 235
 236 (define-coding-system 'chinese-gb18030
 237   "GB18030 encoding for Chinese (MIME:GB18030)."
 238   :coding-type 'charset
 239   :mnemonic ?c
 240   :charset-list '(ascii gb18030-2-byte
 241                         gb18030-4-byte-bmp gb18030-4-byte-smp
 242                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 243   :mime-charset 'gb18030)
 244
 245 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 246
 247 (set-language-info-alist
 248  "Chinese-GB18030" '((charset gb18030)
 249                      (coding-system chinese-gb18030)
 250                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 251                                       chinese-iso-8bit) ; fixme?
 252                      (input-method . "chinese-py-punct") ; fixme?
 253                      (features china-util)
 254                      (documentation
 255                       . "Support for Chinese GB18030 character set."))
 256  '("Chinese"))
 257
 258 ;; Fixme: add HKSCS
 259
 260 (provide 'chinese)
 261
 262 ;;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f
 263 ;;; chinese.el ends here