lisp/language/chinese.el

   1 ;;; chinese.el --- support for Chinese -*- coding: iso-2022-7bit; -*-
   2
   3 ;; Copyright (C) 2001-2011  Free Software Foundation, Inc.
   4 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
   5 ;;   2005, 2006, 2007, 2008, 2009, 2010, 2011
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8 ;; Copyright (C) 2003
   9 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  10 ;;   Registration Number H13PRO009
  11
  12 ;; Keywords: multilingual, Chinese
  13
  14 ;; This file is part of GNU Emacs.
  15
  16 ;; GNU Emacs is free software: you can redistribute it and/or modify
  17 ;; it under the terms of the GNU General Public License as published by
  18 ;; the Free Software Foundation, either version 3 of the License, or
  19 ;; (at your option) any later version.
  20
  21 ;; GNU Emacs is distributed in the hope that it will be useful,
  22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  24 ;; GNU General Public License for more details.
  25
  26 ;; You should have received a copy of the GNU General Public License
  27 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  28
  29 ;;; Commentary:
  30
  31 ;; For Chinese, three character sets GB2312, BIG5, and CNS11643 are
  32 ;; supported.
  33
  34 ;;; Code:
  35
  36 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  37 ;;; Chinese (general)
  38 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  39
  40
  41 (define-coding-system 'iso-2022-cn
  42   "ISO 2022 based 7bit encoding for Chinese GB and CNS (MIME:ISO-2022-CN)."
  43   :coding-type 'iso-2022
  44   :mnemonic ?C
  45   :charset-list '(ascii chinese-gb2312 chinese-cns11643-1 chinese-cns11643-2)
  46   :designation [ascii
  47                 (nil chinese-gb2312 chinese-cns11643-1)
  48                 (nil chinese-cns11643-2)
  49                 nil]
  50   :flags '(ascii-at-eol ascii-at-cntl 7-bit
  51                         designation locking-shift single-shift init-at-bol)
  52   :mime-charset 'iso-2022-cn
  53   :suitable-for-keyboard t)
  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   :suitable-for-keyboard t)
  74
  75 \f
  76 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  77 ;;; Chinese GB2312 (simplified)
  78 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
  79
  80 (define-coding-system 'chinese-iso-8bit
  81   "ISO 2022 based EUC encoding for Chinese GB2312 (MIME:GB2312)."
  82   :coding-type 'iso-2022
  83   :mnemonic ?c
  84   :charset-list '(ascii chinese-gb2312)
  85   :designation [ascii chinese-gb2312 nil nil]
  86   :mime-charset 'gb2312)
  87
  88 (define-coding-system-alias 'cn-gb-2312 'chinese-iso-8bit)
  89 (define-coding-system-alias 'euc-china 'chinese-iso-8bit)
  90 (define-coding-system-alias 'euc-cn 'chinese-iso-8bit)
  91 (define-coding-system-alias 'cn-gb 'chinese-iso-8bit)
  92 (define-coding-system-alias 'gb2312 '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                 (iso639-language . zh)
 109                 (setup-function . (lambda ()
 110                                     (use-cjk-char-width-table 'zh_CN)))
 111                 (exit-function . use-default-char-width-table)
 112                 (coding-system chinese-iso-8bit iso-2022-cn chinese-hz)
 113                 (coding-priority chinese-iso-8bit chinese-big5 iso-2022-cn)
 114                 (input-method . "chinese-py-punct")
 115                 (features china-util)
 116                 (sample-text . "Chinese (\e$AVPND\e(B,\e$AFUM(;0\e(B,\e$A::So\e(B)    \e$ADc:C\e(B")
 117                 (documentation . "Support for Chinese GB2312 character set.")
 118                 (tutorial . "TUTORIAL.cn"))
 119  '("Chinese"))
 120
 121 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 122 ;; Chinese BIG5 (traditional)
 123 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 124
 125 (define-coding-system 'chinese-big5
 126   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 127   :coding-type 'big5
 128   :mnemonic ?B
 129   :charset-list '(ascii big5)
 130   :mime-charset 'big5)
 131
 132 (define-coding-system-alias 'big5 'chinese-big5)
 133 (define-coding-system-alias 'cn-big5 'chinese-big5)
 134 (define-coding-system-alias 'cp950 'chinese-big5)
 135
 136 (set-language-info-alist
 137  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 138                   (iso639-language . zh)
 139                   (setup-function . (lambda ()
 140                                       (use-cjk-char-width-table 'zh_HK)))
 141                   (exit-function . use-default-char-width-table)
 142                   (coding-system chinese-big5 chinese-iso-7bit)
 143                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit)
 144                   (input-method . "chinese-py-punct-b5")
 145                   (ctext-non-standard-encodings "big5-0")
 146                   (features china-util)
 147                   (sample-text . "Cantonese (\e$(0GnM$\e(B,\e$(0N]0*Hd\e(B) \e$(0*/=(\e(B, \e$(0+$)p\e(B")
 148                   (documentation . "Support for Chinese Big5 character set.")
 149                   (tutorial . "TUTORIAL.zh"))
 150  '("Chinese"))
 151
 152 (define-coding-system 'chinese-big5-hkscs
 153   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 154   :coding-type 'charset
 155   :mnemonic ?B
 156   :charset-list '(ascii big5-hkscs)
 157   :mime-charset 'big5-hkscs)
 158 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 159 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 160
 161 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 162 ;; Chinese CNS11643 (traditional)
 163 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 164
 165 (define-coding-system 'euc-tw
 166   "ISO 2022 based EUC encoding for Chinese CNS11643."
 167   :coding-type 'iso-2022
 168   :mnemonic ?Z
 169   :charset-list '(ascii
 170                   chinese-cns11643-1
 171                   chinese-cns11643-2
 172                   chinese-cns11643-3
 173                   chinese-cns11643-4
 174                   chinese-cns11643-5
 175                   chinese-cns11643-6
 176                   chinese-cns11643-7)
 177   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 178                                           chinese-cns11643-2
 179                                           chinese-cns11643-3
 180                                           chinese-cns11643-4
 181                                           chinese-cns11643-5
 182                                           chinese-cns11643-6
 183                                           chinese-cns11643-7) nil]
 184   :mime-charset 'euc-tw)
 185
 186 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 187
 188 (set-language-info-alist
 189  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 190                           chinese-cns11643-3 chinese-cns11643-4
 191                           chinese-cns11643-5 chinese-cns11643-6
 192                           chinese-cns11643-7)
 193                  (iso639-language . zh)
 194                  (setup-function . (lambda ()
 195                                      (use-cjk-char-width-table 'zh_TW)))
 196                  (exit-function . use-default-char-width-table)
 197                  (coding-system iso-2022-cn euc-tw)
 198                  (coding-priority iso-2022-cn euc-tw chinese-big5
 199                                   chinese-iso-8bit)
 200                  (features china-util)
 201                  (input-method . "chinese-cns-quick")
 202                  ;; Fixme: presumably it won't accept big5 now.
 203                  (documentation . "\
 204 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 205 accepts Big5 for input also (which is then converted to CNS)."))
 206  '("Chinese"))
 207
 208 (set-language-info-alist
 209  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 210                              chinese-cns11643-3 chinese-cns11643-4
 211                              chinese-cns11643-5 chinese-cns11643-6
 212                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 213                     (iso639-language . zh)
 214                     (setup-function . (lambda ()
 215                                         (use-cjk-char-width-table 'zh_TW)))
 216                     (exit-function . use-default-char-width-table)
 217                     (coding-system euc-tw iso-2022-cn)
 218                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 219                                      chinese-iso-8bit)
 220                     (features china-util)
 221                     (input-method . "chinese-cns-quick")
 222                     (documentation . "\
 223 Support for Chinese, preferring the EUC-TW character set.  Note that
 224 the EUC-TW coding system accepts Big5 for input also (which is then
 225 converted to CNS)."))
 226  '("Chinese"))
 227
 228
 229 ;;; Chinese GBK
 230
 231 (define-coding-system 'chinese-gbk
 232   "GBK encoding for Chinese (MIME:GBK)."
 233   :coding-type 'charset
 234   :mnemonic ?c
 235   :charset-list '(ascii chinese-gbk)
 236   :mime-charset 'gbk)
 237 (define-coding-system-alias 'gbk 'chinese-gbk)
 238 (define-coding-system-alias 'cp936 'chinese-gbk)
 239 (define-coding-system-alias 'windows-936 'chinese-gbk)
 240
 241 (set-language-info-alist
 242  "Chinese-GBK" '((charset chinese-gbk)
 243                  (iso639-language . zh)
 244                  (setup-function . (lambda ()
 245                                      (use-cjk-char-width-table 'zh_CN)))
 246                  (exit-function . use-default-char-width-table)
 247                  (coding-system chinese-gbk)
 248                  (coding-priority gbk iso-2022-cn chinese-big5
 249                                   chinese-iso-8bit) ; fixme?
 250                  (ctext-non-standard-encodings "gbk-0")
 251                  (input-method . "chinese-py-punct") ; fixme?
 252                  (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")
 253                  (features china-util)
 254                  (documentation . "Support for Chinese GBK character set.")
 255                  (tutorial . "TUTORIAL.cn"))
 256  '("Chinese"))
 257
 258 ;;; Chinese GB18030
 259
 260 (define-coding-system 'chinese-gb18030
 261   "GB18030 encoding for Chinese (MIME:GB18030)."
 262   :coding-type 'charset
 263   :mnemonic ?c
 264   :charset-list '(ascii gb18030-2-byte
 265                         gb18030-4-byte-bmp gb18030-4-byte-smp
 266                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 267   :mime-charset 'gb18030)
 268
 269 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 270
 271 (set-language-info-alist
 272  "Chinese-GB18030" '((charset gb18030)
 273                      (iso639-language . zh)
 274                      (coding-system chinese-gb18030)
 275                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 276                                       chinese-iso-8bit) ; fixme?
 277                      (input-method . "chinese-py-punct") ; fixme?
 278                      (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")
 279                      (features china-util)
 280                      (documentation
 281                       . "Support for Chinese GB18030 character set.")
 282                      (tutorial . "TUTORIAL.cn"))
 283  '("Chinese"))
 284
 285 ;; Fixme: add HKSCS
 286
 287 (provide 'chinese)
 288
 289 ;;; chinese.el ends here