lisp/language/chinese.el

   1 ;;; chinese.el --- support for Chinese -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
   4 ;;   Licensed to the Free Software Foundation.
   5 ;; Copyright (C) 2003
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H13PRO009
   8
   9 ;; Keywords: multilingual, Chinese
  10
  11 ;; This file is part of GNU Emacs.
  12
  13 ;; GNU Emacs is free software; you can redistribute it and/or modify
  14 ;; it under the terms of the GNU General Public License as published by
  15 ;; the Free Software Foundation; either version 2, or (at your option)
  16 ;; any later version.
  17
  18 ;; GNU Emacs is distributed in the hope that it will be useful,
  19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21 ;; GNU General Public License for more details.
  22
  23 ;; You should have received a copy of the GNU General Public License
  24 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  25 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  26 ;; Boston, MA 02111-1307, USA.
  27
  28 ;;; Commentary:
  29
  30 ;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
  31 ;; supported.
  32
  33 ;;; Code:
  34
  35 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  36 ;;; Chinese (general)
  37 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  38
  39
  40 (define-coding-system 'iso-2022-cn
  41   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)."
  42   :coding-type 'iso-2022
  43   :mnemonic ?C
  44   :charset-list '(ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
  45   :designation [ascii
  46                 (nil chinese-gb2312 chinese-cns11643-1)
  47                 (nil chinese-cns11643-2)
  48                 nil]
  49   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  50                         designation locking-shift single-shift init-at-bol)
  51   :mime-charset 'iso-2022-cn)
  52
  53 (define-coding-system-alias 'chinese-iso-7bit 'iso-2022-cn)
  54
  55 (define-coding-system 'iso-2022-cn-ext
  56   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN-EXT)."
  57   :coding-type 'iso-2022
  58   :mnemonic ?C
  59   :charset-list '(ascii
  60                   chinese-gb2312 chinese-cns11643-1
  61                   chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
  62                   chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
  63   :designation '[ascii
  64                  (nil chinese-gb2312 chinese-cns11643-1)
  65                  (nil chinese-cns11643-2)
  66                  (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
  67                       chinese-cns11643-6 chinese-cns11643-7)]
  68   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  69                         designation locking-shift single-shift init-at-bol)
  70   :mime-charset 'iso-2022-cn-ext)
  71
  72 \f
  73 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  74 ;;; Chinese GB2312 (simplified)
  75 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  76
  77 (define-coding-system 'chinese-iso-8bit
  78   "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:CN-GB)."
  79   :coding-type 'iso-2022
  80   :mnemonic ?c
  81   :charset-list '(ascii chinese-gb2312)
  82   :designation [ascii chinese-gb2312 nil nil]
  83   :mime-charset 'cn-gb)
  84
  85 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
  86 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
  87 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
  88 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
  89 (define-coding-system-alias 'gb2312 'chinese-iso-8bit)
  90 (define-coding-system-alias 'cp936 'chinese-iso-8bit)
  91
  92 (define-coding-system 'chinese-hz
  93   "Hz/ZW 7-bit encoding for Chinese GB2312 (MIME:HZ-GB-2312)."
  94   :coding-type 'utf-8
  95   :mnemonic ?z
  96   :charset-list '(ascii chinese-gb2312)
  97   :mime-charset 'hz-gb-2312
  98   :post-read-conversion 'post-read-decode-hz
  99   :pre-write-conversion 'pre-write-encode-hz)
 100
 101 (define-coding-system-alias 'hz-gb-2312 'chinese-hz)
 102 (define-coding-system-alias 'hz 'chinese-hz)
 103
 104 (set-language-info-alist
 105  "Chinese-GB" '((charset chinese-gb2312 chinese-sisheng)
 106                 (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
 107                 (coding-priority chinese-iso-8bit chinese-big5 iso-2022-cn)
 108                 (input-method . "chinese-py-punct")
 109                 (features china-util)
 110                 (sample-text . "Chinese (\e$AVPND\e(B,\e$AFUM(;0\e(B,\e$A::So\e(B)    \e$ADc:C\e(B")
 111                 (documentation . "Support for Chinese GB2312 character set.")
 112                 (tutorial . "TUTORIAL.cn"))
 113  '("Chinese"))
 114
 115 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 116 ;; Chinese BIG5 (traditional)
 117 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 118
 119 (define-coding-system 'chinese-big5
 120   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 121   :coding-type 'charset
 122   :mnemonic ?B
 123   :charset-list '(ascii big5)
 124   :mime-charset 'big5)
 125
 126 (define-coding-system-alias 'big5 'chinese-big5)
 127 (define-coding-system-alias 'cn-big5 'chinese-big5)
 128 (define-coding-system-alias 'cp950 'chinese-big5)
 129
 130 (set-language-info-alist
 131  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 132                   (coding-system chinese-big5 chinese-iso-7bit)
 133                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
 134                   (input-method . "chinese-py-punct-b5")
 135                   (features china-util)
 136                   (sample-text . "Cantonese (\e$(0GnM$\e(B,\e$(0N]0*Hd\e(B) \e$(0*/=(\e(B, \e$(0+$)p\e(B")
 137                   (documentation . "Support for Chinese Big5 character set.")
 138                   (tutorial . "TUTORIAL.zh"))
 139  '("Chinese"))
 140
 141 (define-coding-system 'chinese-big5-hkscs
 142   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 143   :coding-type 'charset
 144   :mnemonic ?B
 145   :charset-list '(ascii big5-hkscs)
 146   :mime-charset 'big5-hkscs)
 147 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 148 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 149
 150 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 151 ;; Chinese CNS11643 (traditional)
 152 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 153
 154 (define-coding-system 'euc-tw
 155   "ISO 2022 based EUC encoding for Chinese CNS11643."
 156   :coding-type 'iso-2022
 157   :mnemonic ?Z
 158   :charset-list '(ascii
 159                   chinese-cns11643-1
 160                   chinese-cns11643-2
 161                   chinese-cns11643-3
 162                   chinese-cns11643-4
 163                   chinese-cns11643-5
 164                   chinese-cns11643-6
 165                   chinese-cns11643-7)
 166   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 167                                           chinese-cns11643-2
 168                                           chinese-cns11643-3
 169                                           chinese-cns11643-4
 170                                           chinese-cns11643-5
 171                                           chinese-cns11643-6
 172                                           chinese-cns11643-7) nil]
 173   :mime-charset 'euc-tw)
 174
 175 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 176
 177 (set-language-info-alist
 178  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 179                           chinese-cns11643-3 chinese-cns11643-4
 180                           chinese-cns11643-5 chinese-cns11643-6
 181                           chinese-cns11643-7)
 182                  (coding-system iso-2022-cn euc-tw)
 183                  (coding-priority iso-2022-cn euc-tw chinese-big5
 184                                   chinese-iso-8bit)
 185                  (features china-util)
 186                  (input-method . "chinese-cns-quick")
 187                  ;; Fixme: presumably it won't accept big5 now.
 188                  (documentation . "\
 189 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 190 accepts Big5 for input also (which is then converted to CNS)."))
 191  '("Chinese"))
 192
 193 (set-language-info-alist
 194  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 195                              chinese-cns11643-3 chinese-cns11643-4
 196                              chinese-cns11643-5 chinese-cns11643-6
 197                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 198                     (coding-system euc-tw iso-2022-cn)
 199                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 200                                      chinese-iso-8bit)
 201                     (features china-util)
 202                     (input-method . "chinese-cns-quick")
 203                     (documentation . "\
 204 Support for Chinese, prefering the EUC-TW character set.  Note that
 205 the EUC-TW coding system accepts Big5 for input also (which is then
 206 converted to CNS)."))
 207  '("Chinese"))
 208
 209
 210 ;;; Chinese GBK
 211
 212 (define-coding-system 'chinese-gbk
 213   "GBK encoding for Chinese (MIME:GBK)."
 214   :coding-type 'charset
 215   :mnemonic ?c
 216   :charset-list '(chinese-gbk)
 217   :mime-charset 'gbk)
 218 (define-coding-system-alias 'gbk 'chinese-gbk)
 219 (define-coding-system-alias 'cp936 'chinese-gbk)
 220 (define-coding-system-alias 'windows-936 'chinese-gbk)
 221
 222 (set-language-info-alist
 223  "Chinese-GBK" '((charset chinese-gbk)
 224                  (coding-system chinese-gbk)
 225                  (coding-priority gbk iso-2022-cn chinese-big5
 226                                   chinese-iso-8bit) ; fixme?
 227                  (input-method . "chinese-py-punct") ; fixme?
 228                  (features china-util)
 229                  (documentation . "Support for Chinese GBK character set."))
 230  '("Chinese"))
 231
 232 ;;; Chinese GB18030
 233
 234 (define-coding-system 'chinese-gb18030
 235   "GB18030 encoding for Chinese (MIME:GB18030)."
 236   :coding-type 'charset
 237   :mnemonic ?c
 238   :charset-list '(ascii gb18030-2-byte
 239                         gb18030-4-byte-bmp gb18030-4-byte-smp
 240                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 241   :mime-charset 'gb18030)
 242
 243 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 244
 245 (set-language-info-alist
 246  "Chinese-GB18030" '((charset gb18030)
 247                      (coding-system chinese-gb18030)
 248                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 249                                       chinese-iso-8bit) ; fixme?
 250                      (input-method . "chinese-py-punct") ; fixme?
 251                      (features china-util)
 252                      (documentation
 253                       . "Support for Chinese GB18030 character set."))
 254  '("Chinese"))
 255
 256 ;; Fixme: add HKSCS
 257
 258 (provide 'chinese)
 259
 260 ;;; arch-tag: b82fcf7a-84f6-4e0b-b38c-1742dac0e09f
 261 ;;; chinese.el ends here