lisp/international/mule-conf.el

   1 ;;; mule-conf.el --- configure multilingual environment
   2
   3 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003,
   4 ;;   2004, 2005, 2006, 2007, 2008  Free Software Foundation, Inc.
   5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
   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: i18n, mule, multilingual, character set, coding system
  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, or (at your option)
  19 ;; 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; see the file COPYING.  If not, write to the
  28 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  29 ;; Boston, MA 02110-1301, USA.
  30
  31 ;;; Commentary:
  32
  33 ;; This file defines the Emacs charsets and some basic coding systems.
  34 ;; Other coding systems are defined in the files in directory
  35 ;; lisp/language.
  36
  37 ;;; Code:
  38
  39 ;;; Remarks
  40
  41 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/.
  42 ;; Standards docs equivalent to iso-2022 and iso-8859 are at
  43 ;; http://www.ecma.ch/.
  44
  45 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for
  46 ;; MS Windows, which are presumably the only charsets we really need
  47 ;; to worry about on such systems:
  48 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866
  49 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257,
  50 ;;                      1258, 874, 932, 936, 949, 950
  51
  52 ;;; Definitions of character sets.
  53
  54 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined
  55 ;; in charset.c as below:
  56 ;;
  57 ;; (define-charset 'ascii
  58 ;;   ""
  59 ;;   :dimension 1
  60 ;;   :code-space [0 127]
  61 ;;   :iso-final-char ?B
  62 ;;   :ascii-compatible-p t
  63 ;;   :emacs-mule-id 0
  64 ;;   :code-offset 0)
  65 ;;
  66 ;; (define-charset 'unicode
  67 ;;   ""
  68 ;;   :dimension 3
  69 ;;   :code-space [0 255 0 255 0 16]
  70 ;;   :ascii-compatible-p t
  71 ;;   :code-offset 0)
  72 ;;
  73 ;; (define-charset 'eight-bit
  74 ;;   ""
  75 ;;   :dimension 1
  76 ;;   :code-space [128 255]
  77 ;;   :code-offset #x3FFF80)
  78 ;;
  79 ;; We now set :docstring, :short-name, and :long-name properties.
  80
  81 (put-charset-property
  82  'ascii :docstring "ASCII (ISO646 IRV)")
  83 (put-charset-property
  84  'ascii :short-name "ASCII")
  85 (put-charset-property
  86  'ascii :long-name "ASCII (ISO646 IRV)")
  87 (put-charset-property
  88  'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)")
  89 (put-charset-property
  90  'iso-8859-1 :short-name "Latin-1")
  91 (put-charset-property
  92  'iso-8859-1 :long-name "Latin-1")
  93 (put-charset-property
  94  'unicode :docstring "Unicode (ISO10646)")
  95 (put-charset-property
  96  'unicode :short-name "Unicode")
  97 (put-charset-property
  98  'unicode :long-name "Unicode (ISO10646)")
  99 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255")
 100 (put-charset-property 'eight-bit :short-name "Raw bytes")
 101
 102 (define-charset-alias 'ucs 'unicode)
 103
 104 (define-charset 'emacs
 105   "Full Emacs characters"
 106   :ascii-compatible-p t
 107   :code-space [ 0 255 0 255 0 63 ]
 108   :code-offset 0
 109   :supplementary-p t)
 110
 111 (define-charset 'latin-iso8859-1
 112   "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 113   :short-name "RHP of Latin-1"
 114   :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 115   :iso-final-char ?A
 116   :emacs-mule-id 129
 117   :code-space [32 127]
 118   :code-offset 160)
 119
 120 ;; Name perhaps not ideal, but is XEmacs-compatible.
 121 (define-charset 'control-1
 122   "8-bit control code (0x80..0x9F)"
 123   :short-name "8-bit control code"
 124   :code-space [128 159]
 125   :code-offset 128)
 126
 127 (define-charset 'eight-bit-control
 128   "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
 129   :short-name "Raw bytes 0x80..0x9F"
 130   :supplementary-p t
 131   :code-space [128 159]
 132   :code-offset #x3FFF80)                ; see character.h
 133
 134 (define-charset 'eight-bit-graphic
 135   "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
 136   :short-name "Raw bytes 0xA0..0xFF"
 137   :supplementary-p t
 138   :code-space [160 255]
 139   :code-offset #x3FFFA0)                ; see character.h
 140
 141 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname
 142                                                  iso-ir iso-final
 143                                                  emacs-mule-id map)
 144   `(progn
 145      (define-charset ,symbol
 146        ,name
 147        :short-name ,nickname
 148        :long-name ,name
 149        :ascii-compatible-p t
 150        :code-space [0 255]
 151        :map ,map)
 152      (if ,iso-symbol
 153          (define-charset ,iso-symbol
 154            (if ,iso-ir
 155                (format "Right-Hand Part of %s (%s): ISO-IR-%d"
 156                        ,name ,nickname ,iso-ir)
 157              (format "Right-Hand Part of %s (%s)" ,name ,nickname))
 158            :short-name (format "RHP of %s" ,name)
 159            :long-name (format "RHP of %s (%s)" ,name ,nickname)
 160            :iso-final-char ,iso-final
 161            :emacs-mule-id ,emacs-mule-id
 162            :code-space [32 127]
 163            :subset (list ,symbol 160 255 -128)))))
 164
 165 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2
 166   "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2")
 167
 168 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3
 169   "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3")
 170
 171 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4
 172   "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4")
 173
 174 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5
 175   "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5")
 176
 177 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6
 178   "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6")
 179
 180 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7
 181   "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7")
 182
 183 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8
 184   "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8")
 185
 186 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9
 187   "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9")
 188
 189 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10
 190   "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10")
 191
 192 ;; http://www.nectec.or.th/it-standards/iso8859-11/
 193 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620
 194 ;; plus nbsp
 195 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11
 196   "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11")
 197
 198 ;; 8859-12 doesn't (yet?) exist.
 199
 200 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13
 201   "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13")
 202
 203 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14
 204   "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14")
 205
 206 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15
 207   "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15")
 208
 209 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16
 210   "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16")
 211
 212 ;; No point in keeping it around.
 213 (fmakunbound 'define-iso-single-byte-charset)
 214
 215 ;; Can this be shared with 8859-11?
 216 ;; N.b. not all of these are defined unicodes.
 217 (define-charset 'thai-tis620
 218   "TIS620.2533"
 219   :short-name "TIS620.2533"
 220   :iso-final-char ?T
 221   :emacs-mule-id 133
 222   :code-space [32 127]
 223   :code-offset #x0E00)
 224
 225 ;; Fixme: doc for this, c.f. above
 226 (define-charset 'tis620-2533
 227   "TIS620.2533"
 228   :short-name "TIS620.2533"
 229   :ascii-compatible-p t
 230   :code-space [0 255]
 231   :superset '(ascii eight-bit-control (thai-tis620 . 128)))
 232
 233 (define-charset 'jisx0201
 234   "JISX0201"
 235   :short-name "JISX0201"
 236   :code-space [0 #xDF]
 237   :map "JISX0201")
 238
 239 (define-charset 'latin-jisx0201
 240   "Roman Part of JISX0201.1976"
 241   :short-name "JISX0201 Roman"
 242   :long-name "Japanese Roman (JISX0201.1976)"
 243   :iso-final-char ?J
 244   :emacs-mule-id  138
 245   :supplementary-p t
 246   :code-space [33 126]
 247   :subset '(jisx0201 33 126 0))
 248
 249 (define-charset 'katakana-jisx0201
 250   "Katakana Part of JISX0201.1976"
 251   :short-name "JISX0201 Katakana"
 252   :long-name "Japanese Katakana (JISX0201.1976)"
 253   :iso-final-char ?I
 254   :emacs-mule-id  137
 255   :supplementary-p t
 256   :code-space [33 126]
 257   :subset '(jisx0201 161 254 -128))
 258
 259 (define-charset 'chinese-gb2312
 260   "GB2312 Chinese simplified: ISO-IR-58"
 261   :short-name "GB2312"
 262   :long-name "GB2312: ISO-IR-58"
 263   :iso-final-char ?A
 264   :emacs-mule-id 145
 265   :code-space [33 126 33 126]
 266   :code-offset #x110000
 267   :unify-map "GB2312")
 268
 269 (define-charset 'chinese-gbk
 270   "GBK Chinese simplified."
 271   :short-name "GBK"
 272   :code-space [#x40 #xFE #x81 #xFE]
 273   :code-offset #x160000
 274   :unify-map "GBK")
 275 (define-charset-alias 'cp936 'chinese-gbk)
 276 (define-charset-alias 'windows-936 'chinese-gbk)
 277
 278 (define-charset 'chinese-cns11643-1
 279   "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
 280   :short-name "CNS11643-1"
 281   :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
 282   :iso-final-char ?G
 283   :emacs-mule-id  149
 284   :code-space [33 126 33 126]
 285   :code-offset #x114000
 286   :unify-map "CNS-1")
 287
 288 (define-charset 'chinese-cns11643-2
 289   "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
 290   :short-name "CNS11643-2"
 291   :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
 292   :iso-final-char ?H
 293   :emacs-mule-id  150
 294   :code-space [33 126 33 126]
 295   :code-offset #x118000
 296   :unify-map "CNS-2")
 297
 298 (define-charset 'chinese-cns11643-3
 299   "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
 300   :short-name  "CNS11643-3"
 301   :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
 302   :iso-final-char ?I
 303   :code-space [33 126 33 126]
 304   :emacs-mule-id  246
 305   :code-offset #x11C000
 306   :unify-map "CNS-3")
 307
 308 (define-charset 'chinese-cns11643-4
 309   "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
 310   :short-name  "CNS11643-4"
 311   :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
 312   :iso-final-char ?J
 313   :emacs-mule-id  247
 314   :code-space [33 126 33 126]
 315   :code-offset #x120000
 316   :unify-map "CNS-4")
 317
 318 (define-charset 'chinese-cns11643-5
 319   "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
 320   :short-name  "CNS11643-5"
 321   :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
 322   :iso-final-char ?K
 323   :emacs-mule-id  248
 324   :code-space [33 126 33 126]
 325   :code-offset #x124000
 326   :unify-map "CNS-5")
 327
 328 (define-charset 'chinese-cns11643-6
 329   "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
 330   :short-name  "CNS11643-6"
 331   :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
 332   :iso-final-char ?L
 333   :emacs-mule-id 249
 334   :code-space [33 126 33 126]
 335   :code-offset #x128000
 336   :unify-map "CNS-6")
 337
 338 (define-charset 'chinese-cns11643-7
 339   "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
 340   :short-name  "CNS11643-7"
 341   :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
 342   :iso-final-char ?M
 343   :emacs-mule-id 250
 344   :code-space [33 126 33 126]
 345   :code-offset #x12C000
 346   :unify-map "CNS-7")
 347
 348 (define-charset 'big5
 349   "Big5 (Chinese traditional)"
 350   :short-name "Big5"
 351   :code-space [#x40 #xFE #xA1 #xFE]
 352   :code-offset #x130000
 353   :unify-map "BIG5")
 354 ;; Fixme: AKA cp950 according to
 355 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>.  Is
 356 ;; that correct?
 357
 358 (define-charset 'chinese-big5-1
 359   "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
 360   :short-name "Big5 (Level-1)"
 361   :long-name "Big5 (Level-1) A141-C67F"
 362   :iso-final-char ?0
 363   :emacs-mule-id 152
 364   :supplementary-p t
 365   :code-space [#x21 #x7E #x21 #x7E]
 366   :code-offset #x135000
 367   :unify-map "BIG5-1")
 368
 369 (define-charset 'chinese-big5-2
 370   "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
 371   :short-name "Big5 (Level-2)"
 372   :long-name "Big5 (Level-2) C940-FEFE"
 373   :iso-final-char ?1
 374   :emacs-mule-id  153
 375   :supplementary-p t
 376   :code-space [#x21 #x7E #x21 #x7E]
 377   :code-offset #x137800
 378   :unify-map "BIG5-2")
 379
 380 (define-charset 'japanese-jisx0208
 381   "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
 382   :short-name "JISX0208"
 383   :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
 384   :iso-final-char ?B
 385   :emacs-mule-id 146
 386   :code-space [33 126 33 126]
 387   :code-offset #x140000
 388   :unify-map "JISX0208")
 389
 390 (define-charset 'japanese-jisx0208-1978
 391   "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
 392   :short-name "JISX0208.1978"
 393   :long-name  "JISX0208.1978 (JISC6226.1978): ISO-IR-42"
 394   :iso-final-char ?@
 395   :emacs-mule-id  144
 396   :code-space [33 126 33 126]
 397   :code-offset #x144000
 398   :unify-map "JISC6226")
 399
 400 (define-charset 'japanese-jisx0212
 401   "JISX0212 Japanese supplement: ISO-IR-159"
 402   :short-name "JISX0212"
 403   :long-name "JISX0212 (Japanese): ISO-IR-159"
 404   :iso-final-char ?D
 405   :emacs-mule-id 148
 406   :code-space [33 126 33 126]
 407   :code-offset #x148000
 408   :unify-map "JISX0212")
 409
 410 ;; Note that jisx0213 contains characters not in Unicode (3.2?).  It's
 411 ;; arguable whether it should have a unify-map.
 412 (define-charset 'japanese-jisx0213-1
 413   "JISX0213.2000 Plane 1 (Japanese)"
 414   :short-name "JISX0213-1"
 415   :iso-final-char ?O
 416   :emacs-mule-id  151
 417   :unify-map "JISX2131"
 418   :code-space [33 126 33 126]
 419   :code-offset #x14C000)
 420
 421 (define-charset 'japanese-jisx0213-2
 422   "JISX0213.2000 Plane 2 (Japanese)"
 423   :short-name "JISX0213-2"
 424   :iso-final-char ?P
 425   :emacs-mule-id 254
 426   :unify-map "JISX2132"
 427   :code-space [33 126 33 126]
 428   :code-offset #x150000)
 429
 430 (define-charset 'japanese-jisx0213-a
 431   "JISX0213.2004 adds these characters to JISX0213.2000."
 432   :short-name "JISX0213A"
 433   :dimension 2
 434   :code-space [33 126 33 126]
 435   :supplementary-p t
 436   :map "JISX213A")
 437
 438 (define-charset 'japanese-jisx0213.2004-1
 439   "JISX0213.2004 Plane1 (Japanese)"
 440   :short-name "JISX0213.2004-1"
 441   :dimension 2
 442   :code-space [33 126 33 126]
 443   :iso-final-char ?Q
 444   :superset '(japanese-jisx0213-a japanese-jisx0213-1))
 445
 446 (define-charset 'katakana-sjis
 447   "Katakana part of Shift-JIS"
 448   :dimension 1
 449   :code-space [#xA1 #xDF]
 450   :subset '(jisx0201 #xA1 #xDF 0)
 451   :supplementary-p t)
 452
 453 (define-charset 'cp932-2-byte
 454   "2-byte part of CP932"
 455   :dimension 2
 456   :map "CP932-2BYTE"
 457   :code-space [#x40 #xFC #x81 #xFC]
 458   :supplementary-p t)
 459
 460 (define-charset 'cp932
 461   "CP932 (Microsoft shift-jis)"
 462   :code-space [#x00 #xFF #x00 #xFE]
 463   :short-name "CP932"
 464   :superset '(ascii katakana-sjis cp932-2-byte))
 465
 466 (define-charset 'korean-ksc5601
 467   "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
 468   :short-name "KSC5601"
 469   :long-name "KSC5601 (Korean): ISO-IR-149"
 470   :iso-final-char ?C
 471   :emacs-mule-id 147
 472   :code-space [33 126 33 126]
 473   :code-offset #x279f94                 ; ... #x27c217
 474   :unify-map "KSC5601")
 475
 476 (define-charset 'big5-hkscs
 477   "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
 478   :short-name "Big5"
 479   :code-space [#x40 #xFE #xA1 #xFE]
 480   :code-offset #x27c218                 ; ... #x280839
 481   :unify-map "BIG5-HKSCS")
 482
 483 ;; Fixme: Korean cp949/UHC
 484
 485 (define-charset 'chinese-sisheng
 486   "SiSheng characters for PinYin/ZhuYin"
 487   :short-name "SiSheng"
 488   :long-name "SiSheng (PinYin/ZhuYin)"
 489   :iso-final-char ?0
 490   :emacs-mule-id 160
 491   :code-space [33 126]
 492   :unify-map "MULE-sisheng"
 493   :supplementary-p t
 494   :code-offset #x200000)
 495
 496 ;; A subset of the 1989 version of IPA.  It consists of the consonant
 497 ;; signs used in English, French, German and Italian, and all vowels
 498 ;; signs in the table.  [says old MULE doc]
 499 (define-charset 'ipa
 500   "IPA (International Phonetic Association)"
 501   :short-name "IPA"
 502   :iso-final-char ?0
 503   :emacs-mule-id  161
 504   :unify-map "MULE-ipa"
 505   :code-space [32 127]
 506   :supplementary-p t
 507   :code-offset #x200080)
 508
 509 (define-charset 'viscii
 510   "VISCII1.1"
 511   :short-name "VISCII"
 512   :long-name "VISCII 1.1"
 513   :code-space [0 255]
 514   :map "VISCII")
 515
 516 (define-charset 'vietnamese-viscii-lower
 517   "VISCII1.1 lower-case"
 518   :short-name "VISCII lower"
 519   :long-name "VISCII lower-case"
 520   :iso-final-char ?1
 521   :emacs-mule-id  162
 522   :code-space [32 127]
 523   :code-offset #x200200
 524   :supplementary-p t
 525   :unify-map "MULE-lviscii")
 526
 527 (define-charset 'vietnamese-viscii-upper
 528   "VISCII1.1 upper-case"
 529   :short-name "VISCII upper"
 530   :long-name "VISCII upper-case"
 531   :iso-final-char ?2
 532   :emacs-mule-id  163
 533   :code-space [32 127]
 534   :code-offset #x200280
 535   :supplementary-p t
 536   :unify-map "MULE-uviscii")
 537
 538 (define-charset 'vscii
 539   "VSCII1.1 (TCVN-5712 VN1)"
 540   :short-name "VSCII"
 541   :code-space [0 255]
 542   :map "VSCII")
 543
 544 (define-charset-alias 'tcvn-5712 'vscii)
 545
 546 ;; Fixme: see note in tcvn.map about combining characters
 547 (define-charset 'vscii-2
 548   "VSCII-2 (TCVN-5712 VN2)"
 549   :code-space [0 255]
 550   :map "VSCII-2")
 551
 552 (define-charset 'koi8-r
 553   "KOI8-R"
 554   :short-name "KOI8-R"
 555   :ascii-compatible-p t
 556   :code-space [0 255]
 557   :map "KOI8-R")
 558
 559 (define-charset-alias 'koi8 'koi8-r)
 560
 561 (define-charset 'alternativnyj
 562   "ALTERNATIVNYJ"
 563   :short-name "alternativnyj"
 564   :ascii-compatible-p t
 565   :code-space [0 255]
 566   :map "ALTERNATIVNYJ")
 567
 568 (define-charset 'cp866
 569   "CP866"
 570   :short-name "cp866"
 571   :ascii-compatible-p t
 572   :code-space [0 255]
 573   :map "IBM866")
 574 (define-charset-alias 'ibm866 'cp866)
 575
 576 (define-charset 'koi8-u
 577   "KOI8-U"
 578   :short-name "KOI8-U"
 579   :ascii-compatible-p t
 580   :code-space [0 255]
 581   :map "KOI8-U")
 582
 583 (define-charset 'koi8-t
 584   "KOI8-T"
 585   :short-name "KOI8-T"
 586   :ascii-compatible-p t
 587   :code-space [0 255]
 588   :map "KOI8-T")
 589
 590 (define-charset 'georgian-ps
 591   "GEORGIAN-PS"
 592   :short-name "GEORGIAN-PS"
 593   :ascii-compatible-p t
 594   :code-space [0 255]
 595   :map "KA-PS")
 596
 597 (define-charset 'georgian-academy
 598   "GEORGIAN-ACADEMY"
 599   :short-name "GEORGIAN-ACADEMY"
 600   :ascii-compatible-p t
 601   :code-space [0 255]
 602   :map "KA-ACADEMY")
 603
 604 (define-charset 'windows-1250
 605   "WINDOWS-1250 (Central Europe)"
 606   :short-name "WINDOWS-1250"
 607   :ascii-compatible-p t
 608   :code-space [0 255]
 609   :map "CP1250")
 610 (define-charset-alias 'cp1250 'windows-1250)
 611
 612 (define-charset 'windows-1251
 613   "WINDOWS-1251 (Cyrillic)"
 614   :short-name "WINDOWS-1251"
 615   :ascii-compatible-p t
 616   :code-space [0 255]
 617   :map "CP1251")
 618 (define-charset-alias 'cp1251 'windows-1251)
 619
 620 (define-charset 'windows-1252
 621   "WINDOWS-1252 (Latin I)"
 622   :short-name "WINDOWS-1252"
 623   :ascii-compatible-p t
 624   :code-space [0 255]
 625   :map "CP1252")
 626 (define-charset-alias 'cp1252 'windows-1252)
 627
 628 (define-charset 'windows-1253
 629   "WINDOWS-1253 (Greek)"
 630   :short-name "WINDOWS-1253"
 631   :ascii-compatible-p t
 632   :code-space [0 255]
 633   :map "CP1253")
 634 (define-charset-alias 'cp1253 'windows-1253)
 635
 636 (define-charset 'windows-1254
 637   "WINDOWS-1254 (Turkish)"
 638   :short-name "WINDOWS-1254"
 639   :ascii-compatible-p t
 640   :code-space [0 255]
 641   :map "CP1254")
 642 (define-charset-alias 'cp1254 'windows-1254)
 643
 644 (define-charset 'windows-1255
 645   "WINDOWS-1255 (Hebrew)"
 646   :short-name "WINDOWS-1255"
 647   :ascii-compatible-p t
 648   :code-space [0 255]
 649   :map "CP1255")
 650 (define-charset-alias 'cp1255 'windows-1255)
 651
 652 (define-charset 'windows-1256
 653   "WINDOWS-1256 (Arabic)"
 654   :short-name "WINDOWS-1256"
 655   :ascii-compatible-p t
 656   :code-space [0 255]
 657   :map "CP1256")
 658 (define-charset-alias 'cp1256 'windows-1256)
 659
 660 (define-charset 'windows-1257
 661   "WINDOWS-1257 (Baltic)"
 662   :short-name "WINDOWS-1257"
 663   :ascii-compatible-p t
 664   :code-space [0 255]
 665   :map "CP1257")
 666 (define-charset-alias 'cp1257 'windows-1257)
 667
 668 (define-charset 'windows-1258
 669   "WINDOWS-1258 (Viet Nam)"
 670   :short-name "WINDOWS-1258"
 671   :ascii-compatible-p t
 672   :code-space [0 255]
 673   :map "CP1258")
 674 (define-charset-alias 'cp1258 'windows-1258)
 675
 676 (define-charset 'next
 677   "NEXT"
 678   :short-name "NEXT"
 679   :ascii-compatible-p t
 680   :code-space [0 255]
 681   :map "NEXTSTEP")
 682
 683 (define-charset 'cp1125
 684   "CP1125"
 685   :short-name "CP1125"
 686   :code-space [0 255]
 687   :ascii-compatible-p t
 688   :map "CP1125")
 689 (define-charset-alias 'ruscii 'cp1125)
 690 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
 691 (define-charset-alias 'cp866u 'cp1125)
 692
 693 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
 694 ;; shows this as not ASCII comptaible, with various graphics in
 695 ;; 0x01-0x1F.
 696 (define-charset 'cp437
 697   "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
 698   :short-name "CP437"
 699   :code-space [0 255]
 700   :ascii-compatible-p t
 701   :map "IBM437")
 702
 703 (define-charset 'cp720
 704   "CP720 (Arabic)"
 705   :short-name "CP720"
 706   :code-space [0 255]
 707   :ascii-compatible-p t
 708   :map "CP720")
 709
 710 (define-charset 'cp737
 711   "CP737 (PC Greek)"
 712   :short-name "CP737"
 713   :code-space [0 255]
 714   :ascii-compatible-p t
 715   :map "CP737")
 716
 717 (define-charset 'cp775
 718   "CP775 (PC Baltic)"
 719   :short-name "CP775"
 720   :code-space [0 255]
 721   :ascii-compatible-p t
 722   :map "CP775")
 723
 724 (define-charset 'cp851
 725   "CP851 (Greek)"
 726   :short-name "CP851"
 727   :code-space [0 255]
 728   :ascii-compatible-p t
 729   :map "IBM851")
 730
 731 (define-charset 'cp852
 732   "CP852 (MS-DOS Latin-2)"
 733   :short-name "CP852"
 734   :code-space [0 255]
 735   :ascii-compatible-p t
 736   :map "IBM852")
 737
 738 (define-charset 'cp855
 739   "CP855 (IBM Cyrillic)"
 740   :short-name "CP855"
 741   :code-space [0 255]
 742   :ascii-compatible-p t
 743   :map "IBM855")
 744
 745 (define-charset 'cp857
 746   "CP857 (IBM Turkish)"
 747   :short-name "CP857"
 748   :code-space [0 255]
 749   :ascii-compatible-p t
 750   :map "IBM857")
 751
 752 (define-charset 'cp858
 753   "CP858 (Multilingual Latin I + Euro)"
 754   :short-name "CP858"
 755   :code-space [0 255]
 756   :ascii-compatible-p t
 757   :map "CP858")
 758 (define-charset-alias 'cp00858 'cp858)  ; IANA has IBM00858/CP00858
 759
 760 (define-charset 'cp860
 761   "CP860 (MS-DOS Portuguese)"
 762   :short-name "CP860"
 763   :code-space [0 255]
 764   :ascii-compatible-p t
 765   :map "IBM860")
 766
 767 (define-charset 'cp861
 768   "CP861 (MS-DOS Icelandic)"
 769   :short-name "CP861"
 770   :code-space [0 255]
 771   :ascii-compatible-p t
 772   :map "IBM861")
 773
 774 (define-charset 'cp862
 775   "CP862 (PC Hebrew)"
 776   :short-name "CP862"
 777   :code-space [0 255]
 778   :ascii-compatible-p t
 779   :map "IBM862")
 780
 781 (define-charset 'cp863
 782   "CP863 (MS-DOS Canadian French)"
 783   :short-name "CP863"
 784   :code-space [0 255]
 785   :ascii-compatible-p t
 786   :map "IBM863")
 787
 788 (define-charset 'cp864
 789   "CP864 (PC Arabic)"
 790   :short-name "CP864"
 791   :code-space [0 255]
 792   :ascii-compatible-p t
 793   :map "IBM864")
 794
 795 (define-charset 'cp865
 796   "CP865 (MS-DOS Nordic)"
 797   :short-name "CP865"
 798   :code-space [0 255]
 799   :ascii-compatible-p t
 800   :map "IBM865")
 801
 802 (define-charset 'cp869
 803   "CP869 (IBM Modern Greek)"
 804   :short-name "CP869"
 805   :code-space [0 255]
 806   :ascii-compatible-p t
 807   :map "IBM869")
 808
 809 (define-charset 'cp874
 810   "CP874 (IBM Thai)"
 811   :short-name "CP874"
 812   :code-space [0 255]
 813   :ascii-compatible-p t
 814   :map "IBM874")
 815
 816 ;; For Arabic, we need three different types of character sets.
 817 ;; Digits are of direction left-to-right and of width 1-column.
 818 ;; Others are of direction right-to-left and of width 1-column or
 819 ;; 2-column.
 820 (define-charset 'arabic-digit
 821   "Arabic digit"
 822   :short-name "Arabic digit"
 823   :iso-final-char ?2
 824   :emacs-mule-id 164
 825   :supplementary-p t
 826   :code-space [34 42]
 827   :code-offset #x0600)
 828
 829 (define-charset 'arabic-1-column
 830   "Arabic 1-column"
 831   :short-name "Arabic 1-col"
 832   :long-name "Arabic 1-column"
 833   :iso-final-char ?3
 834   :emacs-mule-id 165
 835   :supplementary-p t
 836   :code-space [33 126]
 837   :code-offset #x200100)
 838
 839 (define-charset 'arabic-2-column
 840   "Arabic 2-column"
 841   :short-name "Arabic 2-col"
 842   :long-name "Arabic 2-column"
 843   :iso-final-char ?4
 844   :emacs-mule-id 224
 845   :supplementary-p t
 846   :code-space [33 126]
 847   :code-offset #x200180)
 848
 849 ;; Lao script.
 850 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
 851 ;; Not all of them are defined unicodes.
 852 (define-charset 'lao
 853   "Lao characters (ISO10646 0E81..0EDF)"
 854   :short-name "Lao"
 855   :iso-final-char ?1
 856   :emacs-mule-id 167
 857   :supplementary-p t
 858   :code-space [33 126]
 859   :code-offset #x0E81)
 860
 861 (define-charset 'mule-lao
 862   "Lao characters (ISO10646 0E81..0EDF)"
 863   :short-name "Lao"
 864   :code-space [0 255]
 865   :supplementary-p t
 866   :superset '(ascii eight-bit-control (lao . 128)))
 867
 868
 869 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 870 ;; not assigned.  They are automatically converted to each Indian
 871 ;; script which IS-13194 supports.
 872
 873 (define-charset 'indian-is13194
 874   "Generic Indian charset for data exchange with IS 13194"
 875   :short-name "IS 13194"
 876   :long-name "Indian IS 13194"
 877   :iso-final-char ?5
 878   :emacs-mule-id 225
 879   :supplementary-p t
 880   :code-space [33 126]
 881   :code-offset #x180000)
 882
 883 (let ((code-offset #x180100))
 884   (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
 885                                oriya kannada malayalam gujarati punjabi))
 886     (define-charset (intern (format "%s-cdac" script))
 887       (format "Glyphs of %s script for CDAC font.  Subset of `indian-glyph'."
 888               (capitalize (symbol-name script)))
 889       :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script)))
 890       :supplementary-p t
 891       :code-space [0 255]
 892       :code-offset code-offset)
 893     (setq code-offset (+ code-offset #x100)))
 894
 895   (dolist (script '(devanagari bengali punjabi gujarati
 896                                oriya tamil telugu kannada malayalam))
 897     (define-charset (intern (format "%s-akruti" script))
 898       (format "Glyphs of %s script for AKRUTI font.  Subset of `indian-glyph'."
 899               (capitalize (symbol-name script)))
 900       :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script)))
 901       :supplementary-p t
 902       :code-space [0 255]
 903       :code-offset code-offset)
 904     (setq code-offset (+ code-offset #x100))))
 905
 906 (define-charset 'indian-glyph
 907   "Glyphs for Indian characters."
 908   :short-name "Indian glyph"
 909   :iso-final-char ?4
 910   :emacs-mule-id 240
 911   :supplementary-p t
 912   :code-space [32 127 32 127]
 913   :code-offset #x180100)
 914
 915 ;; Actual Glyph for 1-column width.
 916 (define-charset 'indian-1-column
 917   "Indian charset for 1-column width glyphs."
 918   :short-name "Indian 1-col"
 919   :long-name "Indian 1 Column"
 920   :iso-final-char ?6
 921   :emacs-mule-id  251
 922   :supplementary-p t
 923   :code-space [33 126 33 126]
 924   :code-offset #x184000)
 925
 926 ;; Actual Glyph for 2-column width.
 927 (define-charset 'indian-2-column
 928   "Indian charset for 2-column width glyphs."
 929   :short-name "Indian 2-col"
 930   :long-name "Indian 2 Column"
 931   :iso-final-char ?5
 932   :emacs-mule-id  251
 933   :supplementary-p t
 934   :code-space [33 126 33 126]
 935   :code-offset #x184000)
 936
 937 (define-charset 'tibetan
 938   "Tibetan characters"
 939   :iso-final-char ?7
 940   :short-name "Tibetan 2-col"
 941   :long-name "Tibetan 2 column"
 942   :iso-final-char ?7
 943   :emacs-mule-id 252
 944   :unify-map "MULE-tibetan"
 945   :supplementary-p t
 946   :code-space [33 126 33 37]
 947   :code-offset #x190000)
 948
 949 (define-charset 'tibetan-1-column
 950   "Tibetan 1 column glyph"
 951   :short-name "Tibetan 1-col"
 952   :long-name "Tibetan 1 column"
 953   :iso-final-char ?8
 954   :emacs-mule-id 241
 955   :supplementary-p t
 956   :code-space [33 126 33 37]
 957   :code-offset #x190000)
 958
 959 ;; Subsets of Unicode.
 960 (define-charset 'mule-unicode-2500-33ff
 961   "Unicode characters of the range U+2500..U+33FF."
 962   :short-name "Unicode subset 2"
 963   :long-name "Unicode subset (U+2500..U+33FF)"
 964   :iso-final-char ?2
 965   :emacs-mule-id 242
 966   :supplementary-p t
 967   :code-space [#x20 #x7f #x20 #x47]
 968   :code-offset #x2500)
 969
 970 (define-charset 'mule-unicode-e000-ffff
 971   "Unicode characters of the range U+E000..U+FFFF."
 972   :short-name "Unicode subset 3"
 973   :long-name "Unicode subset (U+E000+FFFF)"
 974   :iso-final-char ?3
 975   :emacs-mule-id 243
 976   :supplementary-p t
 977   :code-space [#x20 #x7F #x20 #x75]
 978   :code-offset #xE000
 979   :max-code 30015)                      ; U+FFFF
 980
 981 (define-charset 'mule-unicode-0100-24ff
 982   "Unicode characters of the range U+0100..U+24FF."
 983   :short-name "Unicode subset"
 984   :long-name "Unicode subset (U+0100..U+24FF)"
 985   :iso-final-char ?1
 986   :emacs-mule-id 244
 987   :supplementary-p t
 988   :code-space [#x20 #x7F #x20 #x7F]
 989   :code-offset #x100)
 990
 991 (define-charset 'unicode-bmp
 992   "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
 993   :short-name "Unicode BMP"
 994   :code-space [0 255 0 255]
 995   :code-offset 0)
 996
 997 (define-charset 'unicode-smp
 998   "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
 999   :short-name "Unicode SMP "
1000   :code-space [0 255 0 255]
1001   :code-offset #x10000)
1002
1003 (define-charset 'unicode-sip
1004   "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
1005   :short-name "Unicode SIP"
1006   :code-space [0 255 0 255]
1007   :code-offset #x20000)
1008
1009 (define-charset 'unicode-ssp
1010   "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
1011   :short-name "Unicode SSP"
1012   :code-space [0 255 0 255]
1013   :code-offset #xE0000)
1014
1015 (define-charset 'ethiopic
1016   "Ethiopic characters for Amharic and Tigrigna."
1017   :short-name "Ethiopic"
1018   :long-name "Ethiopic characters"
1019   :iso-final-char ?3
1020   :emacs-mule-id  245
1021   :supplementary-p t
1022   :unify-map "MULE-ethiopic"
1023   :code-space [33 126 33 126]
1024   :code-offset #x1A0000)
1025
1026 (define-charset 'mac-roman
1027   "Mac Roman charset"
1028   :short-name "Mac Roman"
1029   :ascii-compatible-p t
1030   :code-space [0 255]
1031   :map "MACINTOSH")
1032
1033 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1034 (define-charset 'ebcdic-us
1035   "US version of EBCDIC"
1036   :short-name "EBCDIC-US"
1037   :code-space [0 255]
1038   :mime-charset 'ebcdic-us
1039   :map "EBCDICUS")
1040
1041 (define-charset 'ebcdic-uk
1042   "UK version of EBCDIC"
1043   :short-name "EBCDIC-UK"
1044   :code-space [0 255]
1045   :mime-charset 'ebcdic-uk
1046   :map "EBCDICUK")
1047
1048 (define-charset 'ibm1047
1049   ;; Says groff:
1050   "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1051   :short-name "IBM1047"
1052   :code-space [0 255]
1053   :mime-charset 'ibm1047
1054   :map "IBM1047")
1055 (define-charset-alias 'cp1047 'ibm1047)
1056
1057 (define-charset 'hp-roman8
1058   "Encoding used by Hewlet-Packard printer software"
1059   :short-name "HP-ROMAN8"
1060   :ascii-compatible-p t
1061   :code-space [0 255]
1062   :map "HP-ROMAN8")
1063
1064 ;; To make a coding system with this, a pre-write-conversion should
1065 ;; account for the commented-out multi-valued code points in
1066 ;; stdenc.map.
1067 (define-charset 'adobe-standard-encoding
1068   "Adobe `standard encoding' used in PostScript"
1069   :short-name "ADOBE-STANDARD-ENCODING"
1070   :code-space [#x20 255]
1071   :map "stdenc")
1072
1073 (define-charset 'symbol
1074   "Adobe symbol encoding used in PostScript"
1075   :short-name "ADOBE-SYMBOL"
1076   :code-space [#x20 255]
1077   :map "symbol")
1078
1079 (define-charset 'ibm850
1080   "DOS codepage 850 (Latin-1)"
1081   :short-name "IBM850"
1082   :ascii-compatible-p t
1083   :code-space [0 255]
1084   :map "IBM850")
1085 (define-charset-alias 'cp850 'ibm850)
1086
1087 (define-charset 'mik
1088   "Bulgarian DOS codepage"
1089   :short-name "MIK"
1090   :ascii-compatible-p t
1091   :code-space [0 255]
1092   :map "MIK")
1093
1094 (define-charset 'ptcp154
1095   "`Paratype' codepage (Asian Cyrillic)"
1096   :short-name "PT154"
1097   :ascii-compatible-p t
1098   :code-space [0 255]
1099   :mime-charset 'pt154
1100   :map "PTCP154")
1101 (define-charset-alias 'pt154 'ptcp154)
1102 (define-charset-alias 'cp154 'ptcp154)
1103
1104 (define-charset 'gb18030-2-byte
1105   "GB18030 2-byte (0x814E..0xFEFE)"
1106   :code-space [#x40 #xFE #x81 #xFE]
1107   :supplementary-p t
1108   :map "GB180302")
1109
1110 (define-charset 'gb18030-4-byte-bmp
1111   "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1112   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84]
1113   :supplementary-p t
1114   :map "GB180304")
1115
1116 (define-charset 'gb18030-4-byte-smp
1117   "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1118   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3]
1119   :min-code '(#x9030 . #x8130)
1120   :max-code '(#xE332 . #x9A35)
1121   :supplementary-p t
1122   :code-offset #x10000)
1123
1124 (define-charset 'gb18030-4-byte-ext-1
1125   "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1126   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F]
1127   :min-code '(#x8431 . #xA530)
1128   :max-code '(#x8F39 . #xFE39)
1129   :supplementary-p t
1130   :code-offset #x200000                 ; ... #x22484B
1131   )
1132
1133 (define-charset 'gb18030-4-byte-ext-2
1134   "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1135   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE]
1136   :min-code '(#xE332 . #x9A36)
1137   :max-code '(#xFE39 . #xFE39)
1138   :supplementary-p t
1139   :code-offset #x22484C                 ; ... #x279f93
1140   )
1141
1142 (define-charset 'gb18030
1143   "GB18030"
1144   :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE]
1145   :min-code 0
1146   :max-code '(#xFE39 . #xFE39)
1147   :superset '(ascii gb18030-2-byte
1148                     gb18030-4-byte-bmp gb18030-4-byte-smp
1149                     gb18030-4-byte-ext-1 gb18030-4-byte-ext-2))
1150
1151 (define-charset 'chinese-cns11643-15
1152   "CNS11643 Plane 15 Chinese Traditional"
1153   :short-name  "CNS11643-15"
1154   :long-name "CNS11643-15 (Chinese traditional)"
1155   :code-space [33 126 33 126]
1156   :code-offset #x27A000)
1157
1158 (unify-charset 'chinese-gb2312)
1159 (unify-charset 'chinese-gbk)
1160 (unify-charset 'chinese-cns11643-1)
1161 (unify-charset 'chinese-cns11643-2)
1162 (unify-charset 'chinese-cns11643-3)
1163 (unify-charset 'chinese-cns11643-4)
1164 (unify-charset 'chinese-cns11643-5)
1165 (unify-charset 'chinese-cns11643-6)
1166 (unify-charset 'chinese-cns11643-7)
1167 (unify-charset 'big5)
1168 (unify-charset 'chinese-big5-1)
1169 (unify-charset 'chinese-big5-2)
1170 (unify-charset 'big5-hkscs)
1171 (unify-charset 'korean-ksc5601)
1172 (unify-charset 'vietnamese-viscii-lower)
1173 (unify-charset 'vietnamese-viscii-upper)
1174 (unify-charset 'chinese-sisheng)
1175 (unify-charset 'ipa)
1176 (unify-charset 'tibetan)
1177 (unify-charset 'ethiopic)
1178 (unify-charset 'japanese-jisx0208-1978)
1179 (unify-charset 'japanese-jisx0208)
1180 (unify-charset 'japanese-jisx0212)
1181 (unify-charset 'japanese-jisx0213-1)
1182 (unify-charset 'japanese-jisx0213-2)
1183
1184 \f
1185 ;; These are tables for translating characters on decoding and
1186 ;; encoding.
1187 ;; Fixme: these aren't used now -- should they be?
1188 (setq standard-translation-table-for-decode nil)
1189
1190 (setq standard-translation-table-for-encode nil)
1191 \f
1192 ;;; Make fundamental coding systems.
1193
1194 ;; The coding system `no-conversion' and `undecided' are already
1195 ;; defined in coding.c as below:
1196 ;;
1197 ;; (define-coding-system 'no-conversion
1198 ;;   "..."
1199 ;;   :coding-type 'raw-text
1200 ;;   ...)
1201 ;; (define-coding-system 'undecided
1202 ;;   "..."
1203 ;;   :coding-type 'undecided
1204 ;;   ...)
1205
1206 (define-coding-system-alias 'binary 'no-conversion)
1207 (define-coding-system-alias 'unix 'undecided-unix)
1208 (define-coding-system-alias 'dos 'undecided-dos)
1209 (define-coding-system-alias 'mac 'undecided-mac)
1210
1211 (define-coding-system 'raw-text
1212   "Raw text, which means text contains random 8-bit codes.
1213 Encoding text with this coding system produces the actual byte
1214 sequence of the text in buffers and strings.  An exception is made for
1215 eight-bit-control characters.  Each of them is encoded into a single
1216 byte.
1217
1218 When you visit a file with this coding, the file is read into a
1219 unibyte buffer as is (except for EOL format), thus each byte of a file
1220 is treated as a character."
1221   :coding-type 'raw-text
1222   :for-unibyte t
1223   :mnemonic ?t)
1224
1225 (define-coding-system 'no-conversion-multibyte
1226   "Like `no-conversion' but don't read a file into a unibyte buffer."
1227   :coding-type 'raw-text
1228   :eol-type 'unix
1229   :mnemonic ?=)
1230
1231 (define-coding-system 'iso-latin-1
1232   "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1233   :coding-type 'charset
1234   :mnemonic ?1
1235   :charset-list '(iso-8859-1)
1236   :mime-charset 'iso-8859-1)
1237
1238 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
1239 (define-coding-system-alias 'latin-1 'iso-latin-1)
1240
1241 ;; Coding systems not specific to each language environment.
1242
1243 (define-coding-system 'emacs-mule
1244  "Emacs 21 internal format used in buffer and string."
1245  :coding-type 'emacs-mule
1246  :charset-list 'emacs-mule
1247  :mnemonic ?M)
1248
1249 (define-coding-system 'utf-8
1250   "UTF-8."
1251   :coding-type 'utf-8
1252   :mnemonic ?U
1253   :charset-list '(unicode)
1254   :mime-charset 'utf-8)
1255
1256 (define-coding-system-alias 'mule-utf-8 'utf-8)
1257
1258 (define-coding-system 'utf-8-emacs
1259   "Support for all Emacs characters (including non-Unicode characters)."
1260   :coding-type 'utf-8
1261   :mnemonic ?U
1262   :charset-list '(emacs))
1263
1264 (define-coding-system 'utf-16le
1265   "UTF-16LE (little endian, no signature (BOM))."
1266   :coding-type 'utf-16
1267   :mnemonic ?U
1268   :charset-list '(unicode)
1269   :endian 'little
1270   :mime-text-unsuitable t
1271   :mime-charset 'utf-16le)
1272
1273 (define-coding-system 'utf-16be
1274   "UTF-16BE (big endian, no signature (BOM))."
1275   :coding-type 'utf-16
1276   :mnemonic ?U
1277   :charset-list '(unicode)
1278   :endian 'big
1279   :mime-text-unsuitable t
1280   :mime-charset 'utf-16be)
1281
1282 (define-coding-system 'utf-16le-with-signature
1283   "UTF-16 (little endian, with signature (BOM))."
1284   :coding-type 'utf-16
1285   :mnemonic ?U
1286   :charset-list '(unicode)
1287   :bom t
1288   :endian 'little
1289   :mime-text-unsuitable t
1290   :mime-charset 'utf-16)
1291
1292 (define-coding-system 'utf-16be-with-signature
1293   "UTF-16 (big endian, with signature)."
1294   :coding-type 'utf-16
1295   :mnemonic ?U
1296   :charset-list '(unicode)
1297   :bom t
1298   :endian 'big
1299   :mime-text-unsuitable t
1300   :mime-charset 'utf-16)
1301
1302 (define-coding-system 'utf-16
1303   "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1304   :coding-type 'utf-16
1305   :mnemonic ?U
1306   :charset-list '(unicode)
1307   :bom '(utf-16le-with-signature . utf-16be-with-signature)
1308   :endian 'big
1309   :mime-text-unsuitable t
1310   :mime-charset 'utf-16)
1311
1312 ;; Backwards compatibility (old names, also used by Mule-UCS).  We
1313 ;; prefer the MIME names.
1314 (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature)
1315 (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature)
1316
1317
1318 (define-coding-system 'iso-2022-7bit
1319   "ISO 2022 based 7-bit encoding using only G0."
1320   :coding-type 'iso-2022
1321   :mnemonic ?J
1322   :charset-list 'iso-2022
1323   :designation [(ascii t) nil nil nil]
1324   :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition))
1325
1326 (define-coding-system 'iso-2022-7bit-ss2
1327   "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1328   :coding-type 'iso-2022
1329   :mnemonic ?$
1330   :charset-list 'iso-2022
1331   :designation [(ascii 94) nil (nil 96) nil]
1332   :flags '(short ascii-at-eol ascii-at-cntl 7-bit
1333                  designation single-shift composition))
1334
1335 (define-coding-system 'iso-2022-7bit-lock
1336   "ISO-2022 coding system using Locking-Shift for 96-charset."
1337   :coding-type 'iso-2022
1338   :mnemonic ?&
1339   :charset-list 'iso-2022
1340   :designation [(ascii 94) (nil 96) nil nil]
1341   :flags '(ascii-at-eol ascii-at-cntl 7-bit
1342                         designation locking-shift composition))
1343
1344 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
1345
1346 (define-coding-system 'iso-2022-7bit-lock-ss2
1347   "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1348   :coding-type 'iso-2022
1349   :mnemonic ?i
1350   :charset-list '(ascii
1351                   japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1352                   korean-ksc5601
1353                   chinese-gb2312
1354                   chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1355                   chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1356                   chinese-cns11643-7)
1357   :designation [(ascii 94)
1358                 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96)
1359                 (nil chinese-cns11643-2)
1360                 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1361                      chinese-cns11643-6 chinese-cns11643-7)]
1362   :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift
1363                  single-shift init-bol))
1364
1365 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
1366
1367 (define-coding-system 'iso-2022-8bit-ss2
1368   "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1369   :coding-type 'iso-2022
1370   :mnemonic ?@
1371   :charset-list 'iso-2022
1372   :designation [(ascii 94) nil (nil 96) nil]
1373   :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
1374
1375 (define-coding-system 'compound-text
1376   "Compound text based generic encoding for decoding unknown messages.
1377
1378 This coding system does not support extended segments of CTEXT."
1379   :coding-type 'iso-2022
1380   :mnemonic ?x
1381   :charset-list 'iso-2022
1382   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1383   :flags '(ascii-at-eol ascii-at-cntl long-form
1384                         designation locking-shift single-shift composition)
1385   ;; Fixme: this isn't a valid MIME charset and has to be
1386   ;; special-cased elsewhere  -- fx
1387   :mime-charset 'x-ctext)
1388
1389 (define-coding-system-alias  'x-ctext 'compound-text)
1390 (define-coding-system-alias  'ctext 'compound-text)
1391
1392 ;; Same as compound-text, but doesn't produce composition escape
1393 ;; sequences.  Used in post-read and pre-write conversions of
1394 ;; compound-text-with-extensions, see mule.el.  Note that this should
1395 ;; not have a mime-charset property, to prevent it from showing up
1396 ;; close to the beginning of coding systems ordered by priority.
1397 (define-coding-system 'ctext-no-compositions
1398  "Compound text based generic encoding for decoding unknown messages.
1399
1400 Like `compound-text', but does not produce escape sequences for compositions."
1401   :coding-type 'iso-2022
1402   :mnemonic ?x
1403   :charset-list 'iso-2022
1404   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1405   :flags '(ascii-at-eol ascii-at-cntl
1406                         designation locking-shift single-shift))
1407
1408 (define-coding-system 'compound-text-with-extensions
1409  "Compound text encoding with ICCCM Extended Segment extensions.
1410
1411 See the variable `ctext-non-standard-encodings-alist' for the
1412 detail about how extended segments are handled.
1413
1414 This coding system should be used only for X selections.  It is inappropriate
1415 for decoding and encoding files, process I/O, etc."
1416   :coding-type 'iso-2022
1417   :mnemonic ?x
1418   :charset-list 'iso-2022
1419   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1420   :flags '(ascii-at-eol ascii-at-cntl long-form
1421                         designation locking-shift single-shift)
1422   :post-read-conversion 'ctext-post-read-conversion
1423   :pre-write-conversion 'ctext-pre-write-conversion)
1424
1425 (define-coding-system-alias
1426   'x-ctext-with-extensions 'compound-text-with-extensions)
1427 (define-coding-system-alias
1428   'ctext-with-extensions 'compound-text-with-extensions)
1429
1430 (define-coding-system 'us-ascii
1431   "Encode ASCII as-is and encode non-ASCII characters to `?'."
1432   :coding-type 'charset
1433   :mnemonic ?-
1434   :charset-list '(ascii)
1435   :default-char ??
1436   :mime-charset 'us-ascii)
1437
1438 (define-coding-system-alias 'iso-safe 'us-ascii)
1439
1440 (define-coding-system 'utf-7
1441   "UTF-7 encoding of Unicode (RFC 2152)."
1442   :coding-type 'utf-8
1443   :mnemonic ?U
1444   :mime-charset 'utf-7
1445   :charset-list '(unicode)
1446   :pre-write-conversion 'utf-7-pre-write-conversion
1447   :post-read-conversion 'utf-7-post-read-conversion)
1448
1449 (define-coding-system 'utf-7-imap
1450   "UTF-7 encoding of Unicode, IMAP version (RFC 2060)"
1451   :coding-type 'utf-8
1452   :mnemonic ?u
1453   :charset-list '(unicode)
1454   :pre-write-conversion 'utf-7-imap-pre-write-conversion
1455   :post-read-conversion 'utf-7-imap-post-read-conversion)
1456
1457 ;; Use us-ascii for terminal output if some other coding system is not
1458 ;; specified explicitly.
1459 (set-safe-terminal-coding-system-internal 'us-ascii)
1460
1461 ;; The other coding-systems are defined in each language specific
1462 ;; files under lisp/language.
1463
1464 ;; Normally, set coding system to `undecided' before reading a file.
1465 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1466 ;; but we regard them as containing multibyte characters.
1467 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1468
1469 (setq file-coding-system-alist
1470       '(("\\.elc\\'" . utf-8-emacs)
1471         ("\\.utf\\(-8\\)?\\'" . utf-8)
1472         ("\\.xml\\'" . xml-find-file-coding-system)
1473         ;; We use raw-text for reading loaddefs.el so that if it
1474         ;; happens to have DOS or Mac EOLs, they are converted to
1475         ;; newlines.  This is required to make the special treatment
1476         ;; of the "\ newline" combination in loaddefs.el, which marks
1477         ;; the beginning of a doc string, work.
1478         ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
1479         ("\\.tar\\'" . (no-conversion . no-conversion))
1480         ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
1481         ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
1482         ("" . (undecided . nil))))
1483
1484 \f
1485 ;;; Setting coding categories and their priorities.
1486
1487 ;; This setting is just to read an Emacs Lisp source files which
1488 ;; contain multilingual text while dumping Emacs.  More appropriate
1489 ;; values are set by the command `set-language-environment' for each
1490 ;; language environment.
1491
1492 (set-coding-system-priority
1493  'iso-latin-1
1494  'utf-8
1495  'iso-2022-7bit
1496  )
1497
1498 \f
1499 ;;; Miscellaneous settings.
1500
1501 ;; Make all multibyte characters self-insert.
1502 (set-char-table-range (nth 1 global-map)
1503                       (cons 128 (max-char))
1504                       'self-insert-command)
1505
1506 (aset latin-extra-code-table ?\221 t)
1507 (aset latin-extra-code-table ?\222 t)
1508 (aset latin-extra-code-table ?\223 t)
1509 (aset latin-extra-code-table ?\224 t)
1510 (aset latin-extra-code-table ?\225 t)
1511 (aset latin-extra-code-table ?\226 t)
1512
1513 ;; The old code-pages library is obsoleted by coding systems based on
1514 ;; the charsets defined in this file but might be required by user
1515 ;; code.
1516 (provide 'code-pages)
1517
1518 ;; Local variables:
1519 ;; no-byte-compile: t
1520 ;; End:
1521
1522 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
1523 ;;; mule-conf.el ends here