lisp/language/chinese.el

   1 ;;; chinese.el --- support for Chinese -*- coding: utf-8; -*-
   2
   3 ;; Copyright (C) 2001-2014 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-gbk chinese-big5
 114                                  iso-2022-cn)
 115                 (input-method . "chinese-py-punct")
 116                 (features china-util)
 117                 (sample-text . "Chinese (中文,普通话,汉语)       你好")
 118                 (documentation . "Support for Chinese GB2312 character set.")
 119                 (tutorial . "TUTORIAL.cn"))
 120  '("Chinese"))
 121
 122 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 123 ;; Chinese BIG5 (traditional)
 124 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 125
 126 (define-coding-system 'chinese-big5
 127   "BIG5 8-bit encoding for Chinese (MIME:Big5)"
 128   :coding-type 'big5
 129   :mnemonic ?B
 130   :charset-list '(ascii big5)
 131   :mime-charset 'big5)
 132
 133 (define-coding-system-alias 'big5 'chinese-big5)
 134 (define-coding-system-alias 'cn-big5 'chinese-big5)
 135 (define-coding-system-alias 'cp950 'chinese-big5)
 136
 137 (set-language-info-alist
 138  "Chinese-BIG5" '((charset chinese-big5-1 chinese-big5-2)
 139                   (iso639-language . zh)
 140                   (setup-function . (lambda ()
 141                                       (use-cjk-char-width-table 'zh_HK)))
 142                   (exit-function . use-default-char-width-table)
 143                   (coding-system chinese-big5 chinese-iso-7bit)
 144                   (coding-priority chinese-big5 iso-2022-cn chinese-iso-8bit
 145                                    chinese-gbk)
 146                   (input-method . "chinese-py-punct-b5")
 147                   (ctext-non-standard-encodings "big5-0")
 148                   (features china-util)
 149                   (sample-text . "Cantonese (粵語,廣東話)  早晨, 你好")
 150                   (documentation . "Support for Chinese Big5 character set.")
 151                   (tutorial . "TUTORIAL.zh"))
 152  '("Chinese"))
 153
 154 (define-coding-system 'chinese-big5-hkscs
 155   "BIG5-HKSCS 8-bit encoding for Chinese, Hong Kong supplement (MIME:Big5-HKSCS)"
 156   :coding-type 'charset
 157   :mnemonic ?B
 158   :charset-list '(ascii big5-hkscs)
 159   :mime-charset 'big5-hkscs)
 160 (define-coding-system-alias 'big5-hkscs 'chinese-big5-hkscs)
 161 (define-coding-system-alias 'cn-big5-hkscs 'chinese-big5-hkscs)
 162
 163 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 164 ;; Chinese CNS11643 (traditional)
 165 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 166
 167 (define-coding-system 'euc-tw
 168   "ISO 2022 based EUC encoding for Chinese CNS11643."
 169   :coding-type 'iso-2022
 170   :mnemonic ?Z
 171   :charset-list '(ascii
 172                   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)
 179   :designation [ascii chinese-cns11643-1 (chinese-cns11643-1
 180                                           chinese-cns11643-2
 181                                           chinese-cns11643-3
 182                                           chinese-cns11643-4
 183                                           chinese-cns11643-5
 184                                           chinese-cns11643-6
 185                                           chinese-cns11643-7) nil]
 186   :mime-charset 'euc-tw)
 187
 188 (define-coding-system-alias 'euc-taiwan 'euc-tw)
 189
 190 (set-language-info-alist
 191  "Chinese-CNS" '((charset chinese-cns11643-1 chinese-cns11643-2
 192                           chinese-cns11643-3 chinese-cns11643-4
 193                           chinese-cns11643-5 chinese-cns11643-6
 194                           chinese-cns11643-7)
 195                  (iso639-language . zh)
 196                  (setup-function . (lambda ()
 197                                      (use-cjk-char-width-table 'zh_TW)))
 198                  (exit-function . use-default-char-width-table)
 199                  (coding-system iso-2022-cn euc-tw)
 200                  (coding-priority iso-2022-cn euc-tw chinese-big5
 201                                   chinese-iso-8bit chinese-gbk)
 202                  (features china-util)
 203                  (input-method . "chinese-cns-quick")
 204                  ;; Fixme: presumably it won't accept big5 now.
 205                  (documentation . "\
 206 Support for Chinese CNS character sets.  Note that the EUC-TW coding system
 207 accepts Big5 for input also (which is then converted to CNS)."))
 208  '("Chinese"))
 209
 210 (set-language-info-alist
 211  "Chinese-EUC-TW" '((charset chinese-cns11643-1 chinese-cns11643-2
 212                              chinese-cns11643-3 chinese-cns11643-4
 213                              chinese-cns11643-5 chinese-cns11643-6
 214                              chinese-cns11643-7 chinese-big5-1 chinese-big5-2)
 215                     (iso639-language . zh)
 216                     (setup-function . (lambda ()
 217                                         (use-cjk-char-width-table 'zh_TW)))
 218                     (exit-function . use-default-char-width-table)
 219                     (coding-system euc-tw iso-2022-cn)
 220                     (coding-priority euc-tw chinese-big5 iso-2022-cn
 221                                      chinese-iso-8bit chinese-gbk)
 222                     (features china-util)
 223                     (input-method . "chinese-cns-quick")
 224                     (documentation . "\
 225 Support for Chinese, preferring the EUC-TW character set.  Note that
 226 the EUC-TW coding system accepts Big5 for input also (which is then
 227 converted to CNS)."))
 228  '("Chinese"))
 229
 230
 231 ;;; Chinese GBK
 232
 233 (define-coding-system 'chinese-gbk
 234   "GBK encoding for Chinese (MIME:GBK)."
 235   :coding-type 'charset
 236   :mnemonic ?c
 237   :charset-list '(ascii chinese-gbk)
 238   :mime-charset 'gbk)
 239 (define-coding-system-alias 'gbk 'chinese-gbk)
 240 (define-coding-system-alias 'cp936 'chinese-gbk)
 241 (define-coding-system-alias 'windows-936 'chinese-gbk)
 242
 243 (set-language-info-alist
 244  "Chinese-GBK" '((charset chinese-gbk)
 245                  (iso639-language . zh)
 246                  (setup-function . (lambda ()
 247                                      (use-cjk-char-width-table 'zh_CN)))
 248                  (exit-function . use-default-char-width-table)
 249                  (coding-system chinese-gbk)
 250                  (coding-priority gbk iso-2022-cn chinese-big5
 251                                   chinese-iso-8bit) ; fixme?
 252                  (ctext-non-standard-encodings "gbk-0")
 253                  (input-method . "chinese-py-punct") ; fixme?
 254                  (sample-text . "Chinese (中文,普通话,汉语) 妳好")
 255                  (features china-util)
 256                  (documentation . "Support for Chinese GBK character set.")
 257                  (tutorial . "TUTORIAL.cn"))
 258  '("Chinese"))
 259
 260 ;;; Chinese GB18030
 261
 262 (define-coding-system 'chinese-gb18030
 263   "GB18030 encoding for Chinese (MIME:GB18030)."
 264   :coding-type 'charset
 265   :mnemonic ?c
 266   :charset-list '(ascii gb18030-2-byte
 267                         gb18030-4-byte-bmp gb18030-4-byte-smp
 268                         gb18030-4-byte-ext-1 gb18030-4-byte-ext-2)
 269   :mime-charset 'gb18030)
 270
 271 (define-coding-system-alias 'gb18030 'chinese-gb18030)
 272
 273 (set-language-info-alist
 274  "Chinese-GB18030" '((charset gb18030)
 275                      (iso639-language . zh)
 276                      (coding-system chinese-gb18030)
 277                      (coding-priority gb18030 gbk iso-2022-cn chinese-big5
 278                                       chinese-iso-8bit) ; fixme?
 279                      (input-method . "chinese-py-punct") ; fixme?
 280                      (sample-text . "Chinese (中文,普通话,汉语) 你好")
 281                      (features china-util)
 282                      (documentation
 283                       . "Support for Chinese GB18030 character set.")
 284                      (tutorial . "TUTORIAL.cn"))
 285  '("Chinese"))
 286
 287 ;; Fixme: add HKSCS
 288
 289 (provide 'chinese)
 290
 291 ;;; chinese.el ends here