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