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, 2009, 2010, 2011  Free Software Foundation, Inc.
   5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8 ;; Copyright (C) 2003
   9 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  10 ;;   Registration Number H13PRO009
  11
  12 ;; Keywords: 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 of the License, or
  19 ;; (at your option) any later version.
  20
  21 ;; GNU Emacs is distributed in the hope that it will be useful,
  22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  24 ;; GNU General Public License for more details.
  25
  26 ;; You should have received a copy of the GNU General Public License
  27 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  28
  29 ;;; Commentary:
  30
  31 ;; This file defines the Emacs charsets and some basic coding systems.
  32 ;; Other coding systems are defined in the files in directory
  33 ;; lisp/language.
  34
  35 ;;; Code:
  36
  37 ;;; Remarks
  38
  39 ;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/.
  40 ;; Standards docs equivalent to iso-2022 and iso-8859 are at
  41 ;; http://www.ecma.ch/.
  42
  43 ;; FWIW, http://www.microsoft.com/globaldev/ lists the following for
  44 ;; MS Windows, which are presumably the only charsets we really need
  45 ;; to worry about on such systems:
  46 ;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866
  47 ;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257,
  48 ;;                      1258, 874, 932, 936, 949, 950
  49
  50 ;;; Definitions of character sets.
  51
  52 ;; The charsets `ascii', `unicode' and `eight-bit' are already defined
  53 ;; in charset.c as below:
  54 ;;
  55 ;; (define-charset 'ascii
  56 ;;   ""
  57 ;;   :dimension 1
  58 ;;   :code-space [0 127]
  59 ;;   :iso-final-char ?B
  60 ;;   :ascii-compatible-p t
  61 ;;   :emacs-mule-id 0
  62 ;;   :code-offset 0)
  63 ;;
  64 ;; (define-charset 'unicode
  65 ;;   ""
  66 ;;   :dimension 3
  67 ;;   :code-space [0 255 0 255 0 16]
  68 ;;   :ascii-compatible-p t
  69 ;;   :code-offset 0)
  70 ;;
  71 ;; (define-charset 'emacs
  72 ;;   ""
  73 ;;   :dimension 3
  74 ;;   :code-space [0 255 0 255 0 63]
  75 ;;   :ascii-compatible-p t
  76 ;;   :supplementary-p t
  77 ;;   :code-offset 0)
  78 ;;
  79 ;; (define-charset 'eight-bit
  80 ;;   ""
  81 ;;   :dimension 1
  82 ;;   :code-space [128 255]
  83 ;;   :code-offset #x3FFF80)
  84 ;;
  85 ;; We now set :docstring, :short-name, and :long-name properties.
  86
  87 (put-charset-property
  88  'ascii :docstring "ASCII (ISO646 IRV)")
  89 (put-charset-property
  90  'ascii :short-name "ASCII")
  91 (put-charset-property
  92  'ascii :long-name "ASCII (ISO646 IRV)")
  93 (put-charset-property
  94  'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)")
  95 (put-charset-property
  96  'iso-8859-1 :short-name "Latin-1")
  97 (put-charset-property
  98  'iso-8859-1 :long-name "Latin-1")
  99 (put-charset-property
 100  'unicode :docstring "Unicode (ISO10646)")
 101 (put-charset-property
 102  'unicode :short-name "Unicode")
 103 (put-charset-property
 104  'unicode :long-name "Unicode (ISO10646)")
 105 (put-charset-property
 106  'emacs :docstring "Full Emacs charset (excluding eight bit chars)")
 107 (put-charset-property
 108  'emacs :short-name "Emacs")
 109 (put-charset-property
 110  'emacs :long-name "Emacs")
 111
 112 (put-charset-property 'eight-bit :docstring "Raw bytes 128-255")
 113 (put-charset-property 'eight-bit :short-name "Raw bytes")
 114
 115 (define-charset-alias 'ucs 'unicode)
 116
 117 (define-charset 'latin-iso8859-1
 118   "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 119   :short-name "RHP of Latin-1"
 120   :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 121   :iso-final-char ?A
 122   :emacs-mule-id 129
 123   :code-space [32 127]
 124   :code-offset 160)
 125
 126 ;; Name perhaps not ideal, but is XEmacs-compatible.
 127 (define-charset 'control-1
 128   "8-bit control code (0x80..0x9F)"
 129   :short-name "8-bit control code"
 130   :code-space [128 159]
 131   :code-offset 128)
 132
 133 (define-charset 'eight-bit-control
 134   "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
 135   :short-name "Raw bytes 0x80..0x9F"
 136   :supplementary-p t
 137   :code-space [128 159]
 138   :code-offset #x3FFF80)                ; see character.h
 139
 140 (define-charset 'eight-bit-graphic
 141   "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
 142   :short-name "Raw bytes 0xA0..0xFF"
 143   :supplementary-p t
 144   :code-space [160 255]
 145   :code-offset #x3FFFA0)                ; see character.h
 146
 147 (defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname
 148                                                  iso-ir iso-final
 149                                                  emacs-mule-id map)
 150   `(progn
 151      (define-charset ,symbol
 152        ,name
 153        :short-name ,nickname
 154        :long-name ,name
 155        :ascii-compatible-p t
 156        :code-space [0 255]
 157        :map ,map)
 158      (if ,iso-symbol
 159          (define-charset ,iso-symbol
 160            (if ,iso-ir
 161                (format "Right-Hand Part of %s (%s): ISO-IR-%d"
 162                        ,name ,nickname ,iso-ir)
 163              (format "Right-Hand Part of %s (%s)" ,name ,nickname))
 164            :short-name (format "RHP of %s" ,name)
 165            :long-name (format "RHP of %s (%s)" ,name ,nickname)
 166            :iso-final-char ,iso-final
 167            :emacs-mule-id ,emacs-mule-id
 168            :code-space [32 127]
 169            :subset (list ,symbol 160 255 -128)))))
 170
 171 (define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2
 172   "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2")
 173
 174 (define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3
 175   "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3")
 176
 177 (define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4
 178   "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4")
 179
 180 (define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5
 181   "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5")
 182
 183 (define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6
 184   "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6")
 185
 186 (define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7
 187   "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7")
 188
 189 (define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8
 190   "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8")
 191
 192 (define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9
 193   "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9")
 194
 195 (define-iso-single-byte-charset 'iso-8859-10 'latin-iso8859-10
 196   "ISO/IEC 8859/10" "Latin-6" 157 ?V nil "8859-10")
 197
 198 ;; http://www.nectec.or.th/it-standards/iso8859-11/
 199 ;; http://www.cwi.nl/~dik/english/codes/8859.html says this is tis-620
 200 ;; plus nbsp
 201 (define-iso-single-byte-charset 'iso-8859-11 'thai-iso8859-11
 202   "ISO/IEC 8859/11" "Latin/Thai" 166 ?T nil "8859-11")
 203
 204 ;; 8859-12 doesn't (yet?) exist.
 205
 206 (define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13
 207   "ISO/IEC 8859/13" "Latin-7" 179 ?Y nil "8859-13")
 208
 209 (define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14
 210   "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14")
 211
 212 (define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15
 213   "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15")
 214
 215 (define-iso-single-byte-charset 'iso-8859-16 'latin-iso8859-16
 216   "ISO/IEC 8859/16" "Latin-10" 226 ?f nil "8859-16")
 217
 218 ;; No point in keeping it around.
 219 (fmakunbound 'define-iso-single-byte-charset)
 220
 221 ;; Can this be shared with 8859-11?
 222 ;; N.b. not all of these are defined unicodes.
 223 (define-charset 'thai-tis620
 224   "TIS620.2533"
 225   :short-name "TIS620.2533"
 226   :iso-final-char ?T
 227   :emacs-mule-id 133
 228   :code-space [32 127]
 229   :code-offset #x0E00)
 230
 231 ;; Fixme: doc for this, c.f. above
 232 (define-charset 'tis620-2533
 233   "TIS620.2533"
 234   :short-name "TIS620.2533"
 235   :ascii-compatible-p t
 236   :code-space [0 255]
 237   :superset '(ascii eight-bit-control (thai-tis620 . 128)))
 238
 239 (define-charset 'jisx0201
 240   "JISX0201"
 241   :short-name "JISX0201"
 242   :code-space [0 #xDF]
 243   :map "JISX0201")
 244
 245 (define-charset 'latin-jisx0201
 246   "Roman Part of JISX0201.1976"
 247   :short-name "JISX0201 Roman"
 248   :long-name "Japanese Roman (JISX0201.1976)"
 249   :iso-final-char ?J
 250   :emacs-mule-id  138
 251   :supplementary-p t
 252   :code-space [33 126]
 253   :subset '(jisx0201 33 126 0))
 254
 255 (define-charset 'katakana-jisx0201
 256   "Katakana Part of JISX0201.1976"
 257   :short-name "JISX0201 Katakana"
 258   :long-name "Japanese Katakana (JISX0201.1976)"
 259   :iso-final-char ?I
 260   :emacs-mule-id  137
 261   :supplementary-p t
 262   :code-space [33 126]
 263   :subset '(jisx0201 161 254 -128))
 264
 265 (define-charset 'chinese-gb2312
 266   "GB2312 Chinese simplified: ISO-IR-58"
 267   :short-name "GB2312"
 268   :long-name "GB2312: ISO-IR-58"
 269   :iso-final-char ?A
 270   :emacs-mule-id 145
 271   :code-space [33 126 33 126]
 272   :code-offset #x110000
 273   :unify-map "GB2312")
 274
 275 (define-charset 'chinese-gbk
 276   "GBK Chinese simplified."
 277   :short-name "GBK"
 278   :code-space [#x40 #xFE #x81 #xFE]
 279   :code-offset #x160000
 280   :unify-map "GBK")
 281 (define-charset-alias 'cp936 'chinese-gbk)
 282 (define-charset-alias 'windows-936 'chinese-gbk)
 283
 284 (define-charset 'chinese-cns11643-1
 285   "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
 286   :short-name "CNS11643-1"
 287   :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
 288   :iso-final-char ?G
 289   :emacs-mule-id  149
 290   :code-space [33 126 33 126]
 291   :code-offset #x114000
 292   :unify-map "CNS-1")
 293
 294 (define-charset 'chinese-cns11643-2
 295   "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
 296   :short-name "CNS11643-2"
 297   :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
 298   :iso-final-char ?H
 299   :emacs-mule-id  150
 300   :code-space [33 126 33 126]
 301   :code-offset #x118000
 302   :unify-map "CNS-2")
 303
 304 (define-charset 'chinese-cns11643-3
 305   "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
 306   :short-name  "CNS11643-3"
 307   :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
 308   :iso-final-char ?I
 309   :code-space [33 126 33 126]
 310   :emacs-mule-id  246
 311   :code-offset #x11C000
 312   :unify-map "CNS-3")
 313
 314 (define-charset 'chinese-cns11643-4
 315   "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
 316   :short-name  "CNS11643-4"
 317   :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
 318   :iso-final-char ?J
 319   :emacs-mule-id  247
 320   :code-space [33 126 33 126]
 321   :code-offset #x120000
 322   :unify-map "CNS-4")
 323
 324 (define-charset 'chinese-cns11643-5
 325   "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
 326   :short-name  "CNS11643-5"
 327   :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
 328   :iso-final-char ?K
 329   :emacs-mule-id  248
 330   :code-space [33 126 33 126]
 331   :code-offset #x124000
 332   :unify-map "CNS-5")
 333
 334 (define-charset 'chinese-cns11643-6
 335   "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
 336   :short-name  "CNS11643-6"
 337   :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
 338   :iso-final-char ?L
 339   :emacs-mule-id 249
 340   :code-space [33 126 33 126]
 341   :code-offset #x128000
 342   :unify-map "CNS-6")
 343
 344 (define-charset 'chinese-cns11643-7
 345   "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
 346   :short-name  "CNS11643-7"
 347   :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
 348   :iso-final-char ?M
 349   :emacs-mule-id 250
 350   :code-space [33 126 33 126]
 351   :code-offset #x12C000
 352   :unify-map "CNS-7")
 353
 354 (define-charset 'big5
 355   "Big5 (Chinese traditional)"
 356   :short-name "Big5"
 357   :code-space [#x40 #xFE #xA1 #xFE]
 358   :code-offset #x130000
 359   :unify-map "BIG5")
 360 ;; Fixme: AKA cp950 according to
 361 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>.  Is
 362 ;; that correct?
 363
 364 (define-charset 'chinese-big5-1
 365   "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
 366   :short-name "Big5 (Level-1)"
 367   :long-name "Big5 (Level-1) A141-C67F"
 368   :iso-final-char ?0
 369   :emacs-mule-id 152
 370   :supplementary-p t
 371   :code-space [#x21 #x7E #x21 #x7E]
 372   :code-offset #x135000
 373   :unify-map "BIG5-1")
 374
 375 (define-charset 'chinese-big5-2
 376   "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
 377   :short-name "Big5 (Level-2)"
 378   :long-name "Big5 (Level-2) C940-FEFE"
 379   :iso-final-char ?1
 380   :emacs-mule-id  153
 381   :supplementary-p t
 382   :code-space [#x21 #x7E #x21 #x7E]
 383   :code-offset #x137800
 384   :unify-map "BIG5-2")
 385
 386 (define-charset 'japanese-jisx0208
 387   "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
 388   :short-name "JISX0208"
 389   :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
 390   :iso-final-char ?B
 391   :emacs-mule-id 146
 392   :code-space [33 126 33 126]
 393   :code-offset #x140000
 394   :unify-map "JISX0208")
 395
 396 (define-charset 'japanese-jisx0208-1978
 397   "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
 398   :short-name "JISX0208.1978"
 399   :long-name  "JISX0208.1978 (JISC6226.1978): ISO-IR-42"
 400   :iso-final-char ?@
 401   :emacs-mule-id  144
 402   :code-space [33 126 33 126]
 403   :code-offset #x144000
 404   :unify-map "JISC6226")
 405
 406 (define-charset 'japanese-jisx0212
 407   "JISX0212 Japanese supplement: ISO-IR-159"
 408   :short-name "JISX0212"
 409   :long-name "JISX0212 (Japanese): ISO-IR-159"
 410   :iso-final-char ?D
 411   :emacs-mule-id 148
 412   :code-space [33 126 33 126]
 413   :code-offset #x148000
 414   :unify-map "JISX0212")
 415
 416 ;; Note that jisx0213 contains characters not in Unicode (3.2?).  It's
 417 ;; arguable whether it should have a unify-map.
 418 (define-charset 'japanese-jisx0213-1
 419   "JISX0213.2000 Plane 1 (Japanese)"
 420   :short-name "JISX0213-1"
 421   :iso-final-char ?O
 422   :emacs-mule-id  151
 423   :unify-map "JISX2131"
 424   :code-space [33 126 33 126]
 425   :code-offset #x14C000)
 426
 427 (define-charset 'japanese-jisx0213-2
 428   "JISX0213.2000 Plane 2 (Japanese)"
 429   :short-name "JISX0213-2"
 430   :iso-final-char ?P
 431   :emacs-mule-id 254
 432   :unify-map "JISX2132"
 433   :code-space [33 126 33 126]
 434   :code-offset #x150000)
 435
 436 (define-charset 'japanese-jisx0213-a
 437   "JISX0213.2004 adds these characters to JISX0213.2000."
 438   :short-name "JISX0213A"
 439   :dimension 2
 440   :code-space [33 126 33 126]
 441   :supplementary-p t
 442   :map "JISX213A")
 443
 444 (define-charset 'japanese-jisx0213.2004-1
 445   "JISX0213.2004 Plane1 (Japanese)"
 446   :short-name "JISX0213.2004-1"
 447   :dimension 2
 448   :code-space [33 126 33 126]
 449   :iso-final-char ?Q
 450   :superset '(japanese-jisx0213-a japanese-jisx0213-1))
 451
 452 (define-charset 'katakana-sjis
 453   "Katakana part of Shift-JIS"
 454   :dimension 1
 455   :code-space [#xA1 #xDF]
 456   :subset '(jisx0201 #xA1 #xDF 0)
 457   :supplementary-p t)
 458
 459 (define-charset 'cp932-2-byte
 460   "2-byte part of CP932"
 461   :dimension 2
 462   :map "CP932-2BYTE"
 463   :code-space [#x40 #xFC #x81 #xFC]
 464   :supplementary-p t)
 465
 466 (define-charset 'cp932
 467   "CP932 (Microsoft shift-jis)"
 468   :code-space [#x00 #xFF #x00 #xFE]
 469   :short-name "CP932"
 470   :superset '(ascii katakana-sjis cp932-2-byte))
 471
 472 (define-charset 'korean-ksc5601
 473   "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
 474   :short-name "KSC5601"
 475   :long-name "KSC5601 (Korean): ISO-IR-149"
 476   :iso-final-char ?C
 477   :emacs-mule-id 147
 478   :code-space [33 126 33 126]
 479   :code-offset #x279f94                 ; ... #x27c217
 480   :unify-map "KSC5601")
 481
 482 (define-charset 'big5-hkscs
 483   "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
 484   :short-name "Big5"
 485   :code-space [#x40 #xFE #xA1 #xFE]
 486   :code-offset #x27c218                 ; ... #x280839
 487   :unify-map "BIG5-HKSCS")
 488
 489 (define-charset 'cp949-2-byte
 490   "2-byte part of CP949"
 491   :dimension 2
 492   :map "CP949-2BYTE"
 493   :code-space [#x41 #xFE #x81 #xFD]
 494   :supplementary-p t)
 495
 496 (define-charset 'cp949
 497   "CP949 (Korean)"
 498   :short-name "CP949"
 499   :long-name  "CP949 (Korean)"
 500   :code-space [#x00 #xFE #x00 #xFD]
 501   :superset '(ascii cp949-2-byte))
 502
 503 (define-charset 'chinese-sisheng
 504   "SiSheng characters for PinYin/ZhuYin"
 505   :short-name "SiSheng"
 506   :long-name "SiSheng (PinYin/ZhuYin)"
 507   :iso-final-char ?0
 508   :emacs-mule-id 160
 509   :code-space [33 126]
 510   :unify-map "MULE-sisheng"
 511   :supplementary-p t
 512   :code-offset #x200000)
 513
 514 ;; A subset of the 1989 version of IPA.  It consists of the consonant
 515 ;; signs used in English, French, German and Italian, and all vowels
 516 ;; signs in the table.  [says old MULE doc]
 517 (define-charset 'ipa
 518   "IPA (International Phonetic Association)"
 519   :short-name "IPA"
 520   :iso-final-char ?0
 521   :emacs-mule-id  161
 522   :unify-map "MULE-ipa"
 523   :code-space [32 127]
 524   :supplementary-p t
 525   :code-offset #x200080)
 526
 527 (define-charset 'viscii
 528   "VISCII1.1"
 529   :short-name "VISCII"
 530   :long-name "VISCII 1.1"
 531   :code-space [0 255]
 532   :map "VISCII")
 533
 534 (define-charset 'vietnamese-viscii-lower
 535   "VISCII1.1 lower-case"
 536   :short-name "VISCII lower"
 537   :long-name "VISCII lower-case"
 538   :iso-final-char ?1
 539   :emacs-mule-id  162
 540   :code-space [32 127]
 541   :code-offset #x200200
 542   :supplementary-p t
 543   :unify-map "MULE-lviscii")
 544
 545 (define-charset 'vietnamese-viscii-upper
 546   "VISCII1.1 upper-case"
 547   :short-name "VISCII upper"
 548   :long-name "VISCII upper-case"
 549   :iso-final-char ?2
 550   :emacs-mule-id  163
 551   :code-space [32 127]
 552   :code-offset #x200280
 553   :supplementary-p t
 554   :unify-map "MULE-uviscii")
 555
 556 (define-charset 'vscii
 557   "VSCII1.1 (TCVN-5712 VN1)"
 558   :short-name "VSCII"
 559   :code-space [0 255]
 560   :map "VSCII")
 561
 562 (define-charset-alias 'tcvn-5712 'vscii)
 563
 564 ;; Fixme: see note in tcvn.map about combining characters
 565 (define-charset 'vscii-2
 566   "VSCII-2 (TCVN-5712 VN2)"
 567   :code-space [0 255]
 568   :map "VSCII-2")
 569
 570 (define-charset 'koi8-r
 571   "KOI8-R"
 572   :short-name "KOI8-R"
 573   :ascii-compatible-p t
 574   :code-space [0 255]
 575   :map "KOI8-R")
 576
 577 (define-charset-alias 'koi8 'koi8-r)
 578
 579 (define-charset 'alternativnyj
 580   "ALTERNATIVNYJ"
 581   :short-name "alternativnyj"
 582   :ascii-compatible-p t
 583   :code-space [0 255]
 584   :map "ALTERNATIVNYJ")
 585
 586 (define-charset 'cp866
 587   "CP866"
 588   :short-name "cp866"
 589   :ascii-compatible-p t
 590   :code-space [0 255]
 591   :map "IBM866")
 592 (define-charset-alias 'ibm866 'cp866)
 593
 594 (define-charset 'koi8-u
 595   "KOI8-U"
 596   :short-name "KOI8-U"
 597   :ascii-compatible-p t
 598   :code-space [0 255]
 599   :map "KOI8-U")
 600
 601 (define-charset 'koi8-t
 602   "KOI8-T"
 603   :short-name "KOI8-T"
 604   :ascii-compatible-p t
 605   :code-space [0 255]
 606   :map "KOI8-T")
 607
 608 (define-charset 'georgian-ps
 609   "GEORGIAN-PS"
 610   :short-name "GEORGIAN-PS"
 611   :ascii-compatible-p t
 612   :code-space [0 255]
 613   :map "KA-PS")
 614
 615 (define-charset 'georgian-academy
 616   "GEORGIAN-ACADEMY"
 617   :short-name "GEORGIAN-ACADEMY"
 618   :ascii-compatible-p t
 619   :code-space [0 255]
 620   :map "KA-ACADEMY")
 621
 622 (define-charset 'windows-1250
 623   "WINDOWS-1250 (Central Europe)"
 624   :short-name "WINDOWS-1250"
 625   :ascii-compatible-p t
 626   :code-space [0 255]
 627   :map "CP1250")
 628 (define-charset-alias 'cp1250 'windows-1250)
 629
 630 (define-charset 'windows-1251
 631   "WINDOWS-1251 (Cyrillic)"
 632   :short-name "WINDOWS-1251"
 633   :ascii-compatible-p t
 634   :code-space [0 255]
 635   :map "CP1251")
 636 (define-charset-alias 'cp1251 'windows-1251)
 637
 638 (define-charset 'windows-1252
 639   "WINDOWS-1252 (Latin I)"
 640   :short-name "WINDOWS-1252"
 641   :ascii-compatible-p t
 642   :code-space [0 255]
 643   :map "CP1252")
 644 (define-charset-alias 'cp1252 'windows-1252)
 645
 646 (define-charset 'windows-1253
 647   "WINDOWS-1253 (Greek)"
 648   :short-name "WINDOWS-1253"
 649   :ascii-compatible-p t
 650   :code-space [0 255]
 651   :map "CP1253")
 652 (define-charset-alias 'cp1253 'windows-1253)
 653
 654 (define-charset 'windows-1254
 655   "WINDOWS-1254 (Turkish)"
 656   :short-name "WINDOWS-1254"
 657   :ascii-compatible-p t
 658   :code-space [0 255]
 659   :map "CP1254")
 660 (define-charset-alias 'cp1254 'windows-1254)
 661
 662 (define-charset 'windows-1255
 663   "WINDOWS-1255 (Hebrew)"
 664   :short-name "WINDOWS-1255"
 665   :ascii-compatible-p t
 666   :code-space [0 255]
 667   :map "CP1255")
 668 (define-charset-alias 'cp1255 'windows-1255)
 669
 670 (define-charset 'windows-1256
 671   "WINDOWS-1256 (Arabic)"
 672   :short-name "WINDOWS-1256"
 673   :ascii-compatible-p t
 674   :code-space [0 255]
 675   :map "CP1256")
 676 (define-charset-alias 'cp1256 'windows-1256)
 677
 678 (define-charset 'windows-1257
 679   "WINDOWS-1257 (Baltic)"
 680   :short-name "WINDOWS-1257"
 681   :ascii-compatible-p t
 682   :code-space [0 255]
 683   :map "CP1257")
 684 (define-charset-alias 'cp1257 'windows-1257)
 685
 686 (define-charset 'windows-1258
 687   "WINDOWS-1258 (Viet Nam)"
 688   :short-name "WINDOWS-1258"
 689   :ascii-compatible-p t
 690   :code-space [0 255]
 691   :map "CP1258")
 692 (define-charset-alias 'cp1258 'windows-1258)
 693
 694 (define-charset 'next
 695   "NEXT"
 696   :short-name "NEXT"
 697   :ascii-compatible-p t
 698   :code-space [0 255]
 699   :map "NEXTSTEP")
 700
 701 (define-charset 'cp1125
 702   "CP1125"
 703   :short-name "CP1125"
 704   :code-space [0 255]
 705   :ascii-compatible-p t
 706   :map "CP1125")
 707 (define-charset-alias 'ruscii 'cp1125)
 708 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
 709 (define-charset-alias 'cp866u 'cp1125)
 710
 711 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
 712 ;; shows this as not ASCII comptaible, with various graphics in
 713 ;; 0x01-0x1F.
 714 (define-charset 'cp437
 715   "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
 716   :short-name "CP437"
 717   :code-space [0 255]
 718   :ascii-compatible-p t
 719   :map "IBM437")
 720
 721 (define-charset 'cp720
 722   "CP720 (Arabic)"
 723   :short-name "CP720"
 724   :code-space [0 255]
 725   :ascii-compatible-p t
 726   :map "CP720")
 727
 728 (define-charset 'cp737
 729   "CP737 (PC Greek)"
 730   :short-name "CP737"
 731   :code-space [0 255]
 732   :ascii-compatible-p t
 733   :map "CP737")
 734
 735 (define-charset 'cp775
 736   "CP775 (PC Baltic)"
 737   :short-name "CP775"
 738   :code-space [0 255]
 739   :ascii-compatible-p t
 740   :map "CP775")
 741
 742 (define-charset 'cp851
 743   "CP851 (Greek)"
 744   :short-name "CP851"
 745   :code-space [0 255]
 746   :ascii-compatible-p t
 747   :map "IBM851")
 748
 749 (define-charset 'cp852
 750   "CP852 (MS-DOS Latin-2)"
 751   :short-name "CP852"
 752   :code-space [0 255]
 753   :ascii-compatible-p t
 754   :map "IBM852")
 755
 756 (define-charset 'cp855
 757   "CP855 (IBM Cyrillic)"
 758   :short-name "CP855"
 759   :code-space [0 255]
 760   :ascii-compatible-p t
 761   :map "IBM855")
 762
 763 (define-charset 'cp857
 764   "CP857 (IBM Turkish)"
 765   :short-name "CP857"
 766   :code-space [0 255]
 767   :ascii-compatible-p t
 768   :map "IBM857")
 769
 770 (define-charset 'cp858
 771   "CP858 (Multilingual Latin I + Euro)"
 772   :short-name "CP858"
 773   :code-space [0 255]
 774   :ascii-compatible-p t
 775   :map "CP858")
 776 (define-charset-alias 'cp00858 'cp858)  ; IANA has IBM00858/CP00858
 777
 778 (define-charset 'cp860
 779   "CP860 (MS-DOS Portuguese)"
 780   :short-name "CP860"
 781   :code-space [0 255]
 782   :ascii-compatible-p t
 783   :map "IBM860")
 784
 785 (define-charset 'cp861
 786   "CP861 (MS-DOS Icelandic)"
 787   :short-name "CP861"
 788   :code-space [0 255]
 789   :ascii-compatible-p t
 790   :map "IBM861")
 791
 792 (define-charset 'cp862
 793   "CP862 (PC Hebrew)"
 794   :short-name "CP862"
 795   :code-space [0 255]
 796   :ascii-compatible-p t
 797   :map "IBM862")
 798
 799 (define-charset 'cp863
 800   "CP863 (MS-DOS Canadian French)"
 801   :short-name "CP863"
 802   :code-space [0 255]
 803   :ascii-compatible-p t
 804   :map "IBM863")
 805
 806 (define-charset 'cp864
 807   "CP864 (PC Arabic)"
 808   :short-name "CP864"
 809   :code-space [0 255]
 810   :ascii-compatible-p t
 811   :map "IBM864")
 812
 813 (define-charset 'cp865
 814   "CP865 (MS-DOS Nordic)"
 815   :short-name "CP865"
 816   :code-space [0 255]
 817   :ascii-compatible-p t
 818   :map "IBM865")
 819
 820 (define-charset 'cp869
 821   "CP869 (IBM Modern Greek)"
 822   :short-name "CP869"
 823   :code-space [0 255]
 824   :ascii-compatible-p t
 825   :map "IBM869")
 826
 827 (define-charset 'cp874
 828   "CP874 (IBM Thai)"
 829   :short-name "CP874"
 830   :code-space [0 255]
 831   :ascii-compatible-p t
 832   :map "IBM874")
 833
 834 ;; For Arabic, we need three different types of character sets.
 835 ;; Digits are of direction left-to-right and of width 1-column.
 836 ;; Others are of direction right-to-left and of width 1-column or
 837 ;; 2-column.
 838 (define-charset 'arabic-digit
 839   "Arabic digit"
 840   :short-name "Arabic digit"
 841   :iso-final-char ?2
 842   :emacs-mule-id 164
 843   :supplementary-p t
 844   :code-space [34 42]
 845   :code-offset #x0600)
 846
 847 (define-charset 'arabic-1-column
 848   "Arabic 1-column"
 849   :short-name "Arabic 1-col"
 850   :long-name "Arabic 1-column"
 851   :iso-final-char ?3
 852   :emacs-mule-id 165
 853   :supplementary-p t
 854   :code-space [33 126]
 855   :code-offset #x200100)
 856
 857 (define-charset 'arabic-2-column
 858   "Arabic 2-column"
 859   :short-name "Arabic 2-col"
 860   :long-name "Arabic 2-column"
 861   :iso-final-char ?4
 862   :emacs-mule-id 224
 863   :supplementary-p t
 864   :code-space [33 126]
 865   :code-offset #x200180)
 866
 867 ;; Lao script.
 868 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
 869 ;; Not all of them are defined unicodes.
 870 (define-charset 'lao
 871   "Lao characters (ISO10646 0E81..0EDF)"
 872   :short-name "Lao"
 873   :iso-final-char ?1
 874   :emacs-mule-id 167
 875   :supplementary-p t
 876   :code-space [33 126]
 877   :code-offset #x0E81)
 878
 879 (define-charset 'mule-lao
 880   "Lao characters (ISO10646 0E81..0EDF)"
 881   :short-name "Lao"
 882   :code-space [0 255]
 883   :supplementary-p t
 884   :superset '(ascii eight-bit-control (lao . 128)))
 885
 886
 887 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 888 ;; not assigned.  They are automatically converted to each Indian
 889 ;; script which IS-13194 supports.
 890
 891 (define-charset 'indian-is13194
 892   "Generic Indian charset for data exchange with IS 13194"
 893   :short-name "IS 13194"
 894   :long-name "Indian IS 13194"
 895   :iso-final-char ?5
 896   :emacs-mule-id 225
 897   :supplementary-p t
 898   :code-space [33 126]
 899   :code-offset #x180000)
 900
 901 (let ((code-offset #x180100))
 902   (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
 903                                oriya kannada malayalam gujarati punjabi))
 904     (define-charset (intern (format "%s-cdac" script))
 905       (format "Glyphs of %s script for CDAC font.  Subset of `indian-glyph'."
 906               (capitalize (symbol-name script)))
 907       :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script)))
 908       :supplementary-p t
 909       :code-space [0 255]
 910       :code-offset code-offset)
 911     (setq code-offset (+ code-offset #x100)))
 912
 913   (dolist (script '(devanagari bengali punjabi gujarati
 914                                oriya tamil telugu kannada malayalam))
 915     (define-charset (intern (format "%s-akruti" script))
 916       (format "Glyphs of %s script for AKRUTI font.  Subset of `indian-glyph'."
 917               (capitalize (symbol-name script)))
 918       :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script)))
 919       :supplementary-p t
 920       :code-space [0 255]
 921       :code-offset code-offset)
 922     (setq code-offset (+ code-offset #x100))))
 923
 924 (define-charset 'indian-glyph
 925   "Glyphs for Indian characters."
 926   :short-name "Indian glyph"
 927   :iso-final-char ?4
 928   :emacs-mule-id 240
 929   :supplementary-p t
 930   :code-space [32 127 32 127]
 931   :code-offset #x180100)
 932
 933 ;; Actual Glyph for 1-column width.
 934 (define-charset 'indian-1-column
 935   "Indian charset for 1-column width glyphs."
 936   :short-name "Indian 1-col"
 937   :long-name "Indian 1 Column"
 938   :iso-final-char ?6
 939   :emacs-mule-id  251
 940   :supplementary-p t
 941   :code-space [33 126 33 126]
 942   :code-offset #x184000)
 943
 944 ;; Actual Glyph for 2-column width.
 945 (define-charset 'indian-2-column
 946   "Indian charset for 2-column width glyphs."
 947   :short-name "Indian 2-col"
 948   :long-name "Indian 2 Column"
 949   :iso-final-char ?5
 950   :emacs-mule-id  251
 951   :supplementary-p t
 952   :code-space [33 126 33 126]
 953   :code-offset #x184000)
 954
 955 (define-charset 'tibetan
 956   "Tibetan characters"
 957   :iso-final-char ?7
 958   :short-name "Tibetan 2-col"
 959   :long-name "Tibetan 2 column"
 960   :iso-final-char ?7
 961   :emacs-mule-id 252
 962   :unify-map "MULE-tibetan"
 963   :supplementary-p t
 964   :code-space [33 126 33 37]
 965   :code-offset #x190000)
 966
 967 (define-charset 'tibetan-1-column
 968   "Tibetan 1 column glyph"
 969   :short-name "Tibetan 1-col"
 970   :long-name "Tibetan 1 column"
 971   :iso-final-char ?8
 972   :emacs-mule-id 241
 973   :supplementary-p t
 974   :code-space [33 126 33 37]
 975   :code-offset #x190000)
 976
 977 ;; Subsets of Unicode.
 978 (define-charset 'mule-unicode-2500-33ff
 979   "Unicode characters of the range U+2500..U+33FF."
 980   :short-name "Unicode subset 2"
 981   :long-name "Unicode subset (U+2500..U+33FF)"
 982   :iso-final-char ?2
 983   :emacs-mule-id 242
 984   :supplementary-p t
 985   :code-space [#x20 #x7f #x20 #x47]
 986   :code-offset #x2500)
 987
 988 (define-charset 'mule-unicode-e000-ffff
 989   "Unicode characters of the range U+E000..U+FFFF."
 990   :short-name "Unicode subset 3"
 991   :long-name "Unicode subset (U+E000+FFFF)"
 992   :iso-final-char ?3
 993   :emacs-mule-id 243
 994   :supplementary-p t
 995   :code-space [#x20 #x7F #x20 #x75]
 996   :code-offset #xE000
 997   :max-code 30015)                      ; U+FFFF
 998
 999 (define-charset 'mule-unicode-0100-24ff
1000   "Unicode characters of the range U+0100..U+24FF."
1001   :short-name "Unicode subset"
1002   :long-name "Unicode subset (U+0100..U+24FF)"
1003   :iso-final-char ?1
1004   :emacs-mule-id 244
1005   :supplementary-p t
1006   :code-space [#x20 #x7F #x20 #x7F]
1007   :code-offset #x100)
1008
1009 (define-charset 'unicode-bmp
1010   "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
1011   :short-name "Unicode BMP"
1012   :code-space [0 255 0 255]
1013   :code-offset 0)
1014
1015 (define-charset 'unicode-smp
1016   "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
1017   :short-name "Unicode SMP "
1018   :code-space [0 255 0 255]
1019   :code-offset #x10000)
1020
1021 (define-charset 'unicode-sip
1022   "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
1023   :short-name "Unicode SIP"
1024   :code-space [0 255 0 255]
1025   :code-offset #x20000)
1026
1027 (define-charset 'unicode-ssp
1028   "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
1029   :short-name "Unicode SSP"
1030   :code-space [0 255 0 255]
1031   :code-offset #xE0000)
1032
1033 (define-charset 'ethiopic
1034   "Ethiopic characters for Amharic and Tigrigna."
1035   :short-name "Ethiopic"
1036   :long-name "Ethiopic characters"
1037   :iso-final-char ?3
1038   :emacs-mule-id  245
1039   :supplementary-p t
1040   :unify-map "MULE-ethiopic"
1041   :code-space [33 126 33 126]
1042   :code-offset #x1A0000)
1043
1044 (define-charset 'mac-roman
1045   "Mac Roman charset"
1046   :short-name "Mac Roman"
1047   :ascii-compatible-p t
1048   :code-space [0 255]
1049   :map "MACINTOSH")
1050
1051 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1052 (define-charset 'ebcdic-us
1053   "US version of EBCDIC"
1054   :short-name "EBCDIC-US"
1055   :code-space [0 255]
1056   :mime-charset 'ebcdic-us
1057   :map "EBCDICUS")
1058
1059 (define-charset 'ebcdic-uk
1060   "UK version of EBCDIC"
1061   :short-name "EBCDIC-UK"
1062   :code-space [0 255]
1063   :mime-charset 'ebcdic-uk
1064   :map "EBCDICUK")
1065
1066 (define-charset 'ibm1047
1067   ;; Says groff:
1068   "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1069   :short-name "IBM1047"
1070   :code-space [0 255]
1071   :mime-charset 'ibm1047
1072   :map "IBM1047")
1073 (define-charset-alias 'cp1047 'ibm1047)
1074
1075 (define-charset 'hp-roman8
1076   "Encoding used by Hewlet-Packard printer software"
1077   :short-name "HP-ROMAN8"
1078   :ascii-compatible-p t
1079   :code-space [0 255]
1080   :map "HP-ROMAN8")
1081
1082 ;; To make a coding system with this, a pre-write-conversion should
1083 ;; account for the commented-out multi-valued code points in
1084 ;; stdenc.map.
1085 (define-charset 'adobe-standard-encoding
1086   "Adobe `standard encoding' used in PostScript"
1087   :short-name "ADOBE-STANDARD-ENCODING"
1088   :code-space [#x20 255]
1089   :map "stdenc")
1090
1091 (define-charset 'symbol
1092   "Adobe symbol encoding used in PostScript"
1093   :short-name "ADOBE-SYMBOL"
1094   :code-space [#x20 255]
1095   :map "symbol")
1096
1097 (define-charset 'ibm850
1098   "DOS codepage 850 (Latin-1)"
1099   :short-name "IBM850"
1100   :ascii-compatible-p t
1101   :code-space [0 255]
1102   :map "IBM850")
1103 (define-charset-alias 'cp850 'ibm850)
1104
1105 (define-charset 'mik
1106   "Bulgarian DOS codepage"
1107   :short-name "MIK"
1108   :ascii-compatible-p t
1109   :code-space [0 255]
1110   :map "MIK")
1111
1112 (define-charset 'ptcp154
1113   "`Paratype' codepage (Asian Cyrillic)"
1114   :short-name "PT154"
1115   :ascii-compatible-p t
1116   :code-space [0 255]
1117   :mime-charset 'pt154
1118   :map "PTCP154")
1119 (define-charset-alias 'pt154 'ptcp154)
1120 (define-charset-alias 'cp154 'ptcp154)
1121
1122 (define-charset 'gb18030-2-byte
1123   "GB18030 2-byte (0x814E..0xFEFE)"
1124   :code-space [#x40 #xFE #x81 #xFE]
1125   :supplementary-p t
1126   :map "GB180302")
1127
1128 (define-charset 'gb18030-4-byte-bmp
1129   "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1130   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84]
1131   :supplementary-p t
1132   :map "GB180304")
1133
1134 (define-charset 'gb18030-4-byte-smp
1135   "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1136   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3]
1137   :min-code '(#x9030 . #x8130)
1138   :max-code '(#xE332 . #x9A35)
1139   :supplementary-p t
1140   :code-offset #x10000)
1141
1142 (define-charset 'gb18030-4-byte-ext-1
1143   "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1144   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F]
1145   :min-code '(#x8431 . #xA530)
1146   :max-code '(#x8F39 . #xFE39)
1147   :supplementary-p t
1148   :code-offset #x200000                 ; ... #x22484B
1149   )
1150
1151 (define-charset 'gb18030-4-byte-ext-2
1152   "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1153   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE]
1154   :min-code '(#xE332 . #x9A36)
1155   :max-code '(#xFE39 . #xFE39)
1156   :supplementary-p t
1157   :code-offset #x22484C                 ; ... #x279f93
1158   )
1159
1160 (define-charset 'gb18030
1161   "GB18030"
1162   :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE]
1163   :min-code 0
1164   :max-code '(#xFE39 . #xFE39)
1165   :superset '(ascii gb18030-2-byte
1166                     gb18030-4-byte-bmp gb18030-4-byte-smp
1167                     gb18030-4-byte-ext-1 gb18030-4-byte-ext-2))
1168
1169 (define-charset 'chinese-cns11643-15
1170   "CNS11643 Plane 15 Chinese Traditional"
1171   :short-name  "CNS11643-15"
1172   :long-name "CNS11643-15 (Chinese traditional)"
1173   :code-space [33 126 33 126]
1174   :code-offset #x27A000)
1175
1176 (unify-charset 'chinese-gb2312)
1177 (unify-charset 'chinese-gbk)
1178 (unify-charset 'chinese-cns11643-1)
1179 (unify-charset 'chinese-cns11643-2)
1180 (unify-charset 'chinese-cns11643-3)
1181 (unify-charset 'chinese-cns11643-4)
1182 (unify-charset 'chinese-cns11643-5)
1183 (unify-charset 'chinese-cns11643-6)
1184 (unify-charset 'chinese-cns11643-7)
1185 (unify-charset 'big5)
1186 (unify-charset 'chinese-big5-1)
1187 (unify-charset 'chinese-big5-2)
1188 (unify-charset 'big5-hkscs)
1189 (unify-charset 'korean-ksc5601)
1190 (unify-charset 'vietnamese-viscii-lower)
1191 (unify-charset 'vietnamese-viscii-upper)
1192 (unify-charset 'chinese-sisheng)
1193 (unify-charset 'ipa)
1194 (unify-charset 'tibetan)
1195 (unify-charset 'ethiopic)
1196 (unify-charset 'japanese-jisx0208-1978)
1197 (unify-charset 'japanese-jisx0208)
1198 (unify-charset 'japanese-jisx0212)
1199 (unify-charset 'japanese-jisx0213-1)
1200 (unify-charset 'japanese-jisx0213-2)
1201
1202 \f
1203 ;; These are tables for translating characters on decoding and
1204 ;; encoding.
1205 ;; Fixme: these aren't used now -- should they be?
1206 (setq standard-translation-table-for-decode nil)
1207
1208 (setq standard-translation-table-for-encode nil)
1209 \f
1210 ;;; Make fundamental coding systems.
1211
1212 ;; The coding system `no-conversion' and `undecided' are already
1213 ;; defined in coding.c as below:
1214 ;;
1215 ;; (define-coding-system 'no-conversion
1216 ;;   "..."
1217 ;;   :coding-type 'raw-text
1218 ;;   ...)
1219 ;; (define-coding-system 'undecided
1220 ;;   "..."
1221 ;;   :coding-type 'undecided
1222 ;;   ...)
1223
1224 (define-coding-system-alias 'binary 'no-conversion)
1225 (define-coding-system-alias 'unix 'undecided-unix)
1226 (define-coding-system-alias 'dos 'undecided-dos)
1227 (define-coding-system-alias 'mac 'undecided-mac)
1228
1229 (define-coding-system 'raw-text
1230   "Raw text, which means text contains random 8-bit codes.
1231 Encoding text with this coding system produces the actual byte
1232 sequence of the text in buffers and strings.  An exception is made for
1233 characters from the `eight-bit' character set.  Each of them is encoded
1234 into a single byte.
1235
1236 When you visit a file with this coding, the file is read into a
1237 unibyte buffer as is (except for EOL format), thus each byte of a file
1238 is treated as a character."
1239   :coding-type 'raw-text
1240   :for-unibyte t
1241   :mnemonic ?t)
1242
1243 (define-coding-system 'no-conversion-multibyte
1244   "Like `no-conversion' but don't read a file into a unibyte buffer."
1245   :coding-type 'raw-text
1246   :eol-type 'unix
1247   :mnemonic ?=)
1248
1249 (define-coding-system 'iso-latin-1
1250   "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1251   :coding-type 'charset
1252   :mnemonic ?1
1253   :charset-list '(iso-8859-1)
1254   :mime-charset 'iso-8859-1)
1255
1256 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
1257 (define-coding-system-alias 'latin-1 'iso-latin-1)
1258
1259 ;; Coding systems not specific to each language environment.
1260
1261 (define-coding-system 'emacs-mule
1262  "Emacs 21 internal format used in buffer and string."
1263  :coding-type 'emacs-mule
1264  :charset-list 'emacs-mule
1265  :mnemonic ?M)
1266
1267 (define-coding-system 'utf-8
1268   "UTF-8 (no signature (BOM))"
1269   :coding-type 'utf-8
1270   :mnemonic ?U
1271   :charset-list '(unicode)
1272   :mime-charset 'utf-8)
1273
1274 (define-coding-system 'utf-8-with-signature
1275   "UTF-8 (with signature (BOM))"
1276   :coding-type 'utf-8
1277   :mnemonic ?U
1278   :charset-list '(unicode)
1279   :bom t)
1280
1281 (define-coding-system 'utf-8-auto
1282   "UTF-8 (auto-detect signature (BOM))"
1283   :coding-type 'utf-8
1284   :mnemonic ?U
1285   :charset-list '(unicode)
1286   :bom '(utf-8-with-signature . utf-8))
1287
1288 (define-coding-system-alias 'mule-utf-8 'utf-8)
1289
1290 (define-coding-system 'utf-8-emacs
1291   "Support for all Emacs characters (including non-Unicode characters)."
1292   :coding-type 'utf-8
1293   :mnemonic ?U
1294   :charset-list '(emacs))
1295
1296 ;; The encoding used internally.  This encoding is meant to be able to save
1297 ;; any multibyte buffer without losing information.  It can change between
1298 ;; Emacs releases, tho, so should only be used for internal files.
1299 (define-coding-system-alias 'emacs-internal 'utf-8-emacs-unix)
1300
1301 (define-coding-system 'utf-16le
1302   "UTF-16LE (little endian, no signature (BOM))."
1303   :coding-type 'utf-16
1304   :mnemonic ?U
1305   :charset-list '(unicode)
1306   :endian 'little
1307   :mime-text-unsuitable t
1308   :mime-charset 'utf-16le)
1309
1310 (define-coding-system 'utf-16be
1311   "UTF-16BE (big endian, no signature (BOM))."
1312   :coding-type 'utf-16
1313   :mnemonic ?U
1314   :charset-list '(unicode)
1315   :endian 'big
1316   :mime-text-unsuitable t
1317   :mime-charset 'utf-16be)
1318
1319 (define-coding-system 'utf-16le-with-signature
1320   "UTF-16 (little endian, with signature (BOM))."
1321   :coding-type 'utf-16
1322   :mnemonic ?U
1323   :charset-list '(unicode)
1324   :bom t
1325   :endian 'little
1326   :mime-text-unsuitable t
1327   :mime-charset 'utf-16)
1328
1329 (define-coding-system 'utf-16be-with-signature
1330   "UTF-16 (big endian, with signature (BOM))."
1331   :coding-type 'utf-16
1332   :mnemonic ?U
1333   :charset-list '(unicode)
1334   :bom t
1335   :endian 'big
1336   :mime-text-unsuitable t
1337   :mime-charset 'utf-16)
1338
1339 (define-coding-system 'utf-16
1340   "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1341   :coding-type 'utf-16
1342   :mnemonic ?U
1343   :charset-list '(unicode)
1344   :bom '(utf-16le-with-signature . utf-16be-with-signature)
1345   :endian 'big
1346   :mime-text-unsuitable t
1347   :mime-charset 'utf-16)
1348
1349 ;; Backwards compatibility (old names, also used by Mule-UCS).  We
1350 ;; prefer the MIME names.
1351 (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature)
1352 (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature)
1353
1354
1355 (define-coding-system 'iso-2022-7bit
1356   "ISO 2022 based 7-bit encoding using only G0."
1357   :coding-type 'iso-2022
1358   :mnemonic ?J
1359   :charset-list 'iso-2022
1360   :designation [(ascii t) nil nil nil]
1361   :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition))
1362
1363 (define-coding-system 'iso-2022-7bit-ss2
1364   "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1365   :coding-type 'iso-2022
1366   :mnemonic ?$
1367   :charset-list 'iso-2022
1368   :designation [(ascii 94) nil (nil 96) nil]
1369   :flags '(short ascii-at-eol ascii-at-cntl 7-bit
1370                  designation single-shift composition))
1371
1372 (define-coding-system 'iso-2022-7bit-lock
1373   "ISO-2022 coding system using Locking-Shift for 96-charset."
1374   :coding-type 'iso-2022
1375   :mnemonic ?&
1376   :charset-list 'iso-2022
1377   :designation [(ascii 94) (nil 96) nil nil]
1378   :flags '(ascii-at-eol ascii-at-cntl 7-bit
1379                         designation locking-shift composition))
1380
1381 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
1382
1383 (define-coding-system 'iso-2022-7bit-lock-ss2
1384   "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1385   :coding-type 'iso-2022
1386   :mnemonic ?i
1387   :charset-list '(ascii
1388                   japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1389                   korean-ksc5601
1390                   chinese-gb2312
1391                   chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1392                   chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1393                   chinese-cns11643-7)
1394   :designation [(ascii 94)
1395                 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96)
1396                 (nil chinese-cns11643-2)
1397                 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1398                      chinese-cns11643-6 chinese-cns11643-7)]
1399   :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift
1400                  single-shift init-bol))
1401
1402 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
1403
1404 (define-coding-system 'iso-2022-8bit-ss2
1405   "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1406   :coding-type 'iso-2022
1407   :mnemonic ?@
1408   :charset-list 'iso-2022
1409   :designation [(ascii 94) nil (nil 96) nil]
1410   :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
1411
1412 (define-coding-system 'compound-text
1413   "Compound text based generic encoding.
1414 This coding system is an extension of X's \"Compound Text Encoding\".
1415 It encodes many characters using the normal ISO-2022 designation sequences,
1416 but it doesn't support extended segments of CTEXT."
1417   :coding-type 'iso-2022
1418   :mnemonic ?x
1419   :charset-list 'iso-2022
1420   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1421   :flags '(ascii-at-eol ascii-at-cntl long-form
1422                         designation locking-shift single-shift composition)
1423   ;; Fixme: this isn't a valid MIME charset and has to be
1424   ;; special-cased elsewhere  -- fx
1425   :mime-charset 'x-ctext)
1426
1427 (define-coding-system-alias  'x-ctext 'compound-text)
1428 (define-coding-system-alias  'ctext 'compound-text)
1429
1430 ;; Same as compound-text, but doesn't produce composition escape
1431 ;; sequences.  Used in post-read and pre-write conversions of
1432 ;; compound-text-with-extensions, see mule.el.  Note that this should
1433 ;; not have a mime-charset property, to prevent it from showing up
1434 ;; close to the beginning of coding systems ordered by priority.
1435 (define-coding-system 'ctext-no-compositions
1436  "Compound text based generic encoding.
1437
1438 Like `compound-text', but does not produce escape sequences for compositions."
1439   :coding-type 'iso-2022
1440   :mnemonic ?x
1441   :charset-list 'iso-2022
1442   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1443   :flags '(ascii-at-eol ascii-at-cntl
1444                         designation locking-shift single-shift))
1445
1446 (define-coding-system 'compound-text-with-extensions
1447  "Compound text encoding with ICCCM Extended Segment extensions.
1448
1449 See the variables `ctext-standard-encodings' and
1450 `ctext-non-standard-encodings-alist' for the detail about how
1451 extended segments are handled.
1452
1453 This coding system should be used only for X selections.  It is inappropriate
1454 for decoding and encoding files, process I/O, etc."
1455   :coding-type 'iso-2022
1456   :mnemonic ?x
1457   :charset-list 'iso-2022
1458   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1459   :flags '(ascii-at-eol ascii-at-cntl long-form
1460                         designation locking-shift single-shift)
1461   :post-read-conversion 'ctext-post-read-conversion
1462   :pre-write-conversion 'ctext-pre-write-conversion)
1463
1464 (define-coding-system-alias
1465   'x-ctext-with-extensions 'compound-text-with-extensions)
1466 (define-coding-system-alias
1467   'ctext-with-extensions 'compound-text-with-extensions)
1468
1469 (define-coding-system 'us-ascii
1470   "Encode ASCII as-is and encode non-ASCII characters to `?'."
1471   :coding-type 'charset
1472   :mnemonic ?-
1473   :charset-list '(ascii)
1474   :default-char ??
1475   :mime-charset 'us-ascii)
1476
1477 (define-coding-system-alias 'iso-safe 'us-ascii)
1478
1479 (define-coding-system 'utf-7
1480   "UTF-7 encoding of Unicode (RFC 2152)."
1481   :coding-type 'utf-8
1482   :mnemonic ?U
1483   :mime-charset 'utf-7
1484   :charset-list '(unicode)
1485   :pre-write-conversion 'utf-7-pre-write-conversion
1486   :post-read-conversion 'utf-7-post-read-conversion)
1487
1488 (define-coding-system 'utf-7-imap
1489   "UTF-7 encoding of Unicode, IMAP version (RFC 2060)"
1490   :coding-type 'utf-8
1491   :mnemonic ?u
1492   :charset-list '(unicode)
1493   :pre-write-conversion 'utf-7-imap-pre-write-conversion
1494   :post-read-conversion 'utf-7-imap-post-read-conversion)
1495
1496 ;; Use us-ascii for terminal output if some other coding system is not
1497 ;; specified explicitly.
1498 (set-safe-terminal-coding-system-internal 'us-ascii)
1499
1500 ;; The other coding-systems are defined in each language specific
1501 ;; files under lisp/language.
1502
1503 ;; Normally, set coding system to `undecided' before reading a file.
1504 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1505 ;; but we regard them as containing multibyte characters.
1506 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1507
1508 (setq file-coding-system-alist
1509       (mapcar (lambda (arg) (cons (purecopy (car arg)) (cdr arg)))
1510       '(("\\.elc\\'" . utf-8-emacs)
1511         ("\\.utf\\(-8\\)?\\'" . utf-8)
1512         ("\\.xml\\'" . xml-find-file-coding-system)
1513         ;; We use raw-text for reading loaddefs.el so that if it
1514         ;; happens to have DOS or Mac EOLs, they are converted to
1515         ;; newlines.  This is required to make the special treatment
1516         ;; of the "\ newline" combination in loaddefs.el, which marks
1517         ;; the beginning of a doc string, work.
1518         ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
1519         ("\\.tar\\'" . (no-conversion . no-conversion))
1520         ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
1521         ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
1522         ("" . (undecided . nil)))))
1523
1524 \f
1525 ;;; Setting coding categories and their priorities.
1526
1527 ;; This setting is just to read an Emacs Lisp source files which
1528 ;; contain multilingual text while dumping Emacs.  More appropriate
1529 ;; values are set by the command `set-language-environment' for each
1530 ;; language environment.
1531
1532 (set-coding-system-priority
1533  'iso-latin-1
1534  'utf-8
1535  'iso-2022-7bit
1536  )
1537
1538 \f
1539 ;;; Miscellaneous settings.
1540
1541 ;; Make all multibyte characters self-insert.
1542 (set-char-table-range (nth 1 global-map)
1543                       (cons 128 (max-char))
1544                       'self-insert-command)
1545
1546 (aset latin-extra-code-table ?\221 t)
1547 (aset latin-extra-code-table ?\222 t)
1548 (aset latin-extra-code-table ?\223 t)
1549 (aset latin-extra-code-table ?\224 t)
1550 (aset latin-extra-code-table ?\225 t)
1551 (aset latin-extra-code-table ?\226 t)
1552
1553 ;; The old code-pages library is obsoleted by coding systems based on
1554 ;; the charsets defined in this file but might be required by user
1555 ;; code.
1556 (provide 'code-pages)
1557
1558 ;;; mule-conf.el ends here