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, 2008  Free Software Foundation, Inc.
   5 ;; Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8 ;; Copyright (C) 2003
   9 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  10 ;;   Registration Number H13PRO009
  11
  12 ;; Keywords: i18n, mule, multilingual, character set, coding system
  13
  14 ;; This file is part of GNU Emacs.
  15
  16 ;; GNU Emacs is free software: you can redistribute it and/or modify
  17 ;; it under the terms of the GNU General Public License as published by
  18 ;; the Free Software Foundation, either version 3 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 'eight-bit
  72 ;;   ""
  73 ;;   :dimension 1
  74 ;;   :code-space [128 255]
  75 ;;   :code-offset #x3FFF80)
  76 ;;
  77 ;; We now set :docstring, :short-name, and :long-name properties.
  78
  79 (put-charset-property
  80  'ascii :docstring "ASCII (ISO646 IRV)")
  81 (put-charset-property
  82  'ascii :short-name "ASCII")
  83 (put-charset-property
  84  'ascii :long-name "ASCII (ISO646 IRV)")
  85 (put-charset-property
  86  'iso-8859-1 :docstring "Latin-1 (ISO/IEC 8859-1)")
  87 (put-charset-property
  88  'iso-8859-1 :short-name "Latin-1")
  89 (put-charset-property
  90  'iso-8859-1 :long-name "Latin-1")
  91 (put-charset-property
  92  'unicode :docstring "Unicode (ISO10646)")
  93 (put-charset-property
  94  'unicode :short-name "Unicode")
  95 (put-charset-property
  96  'unicode :long-name "Unicode (ISO10646)")
  97 (put-charset-property 'eight-bit :docstring "Raw bytes 0-255")
  98 (put-charset-property 'eight-bit :short-name "Raw bytes")
  99
 100 (define-charset-alias 'ucs 'unicode)
 101
 102 (define-charset 'emacs
 103   "Full Emacs characters"
 104   :ascii-compatible-p t
 105   :code-space [ 0 255 0 255 0 63 ]
 106   :code-offset 0
 107   :supplementary-p t)
 108
 109 (define-charset 'latin-iso8859-1
 110   "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 111   :short-name "RHP of Latin-1"
 112   :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
 113   :iso-final-char ?A
 114   :emacs-mule-id 129
 115   :code-space [32 127]
 116   :code-offset 160)
 117
 118 ;; Name perhaps not ideal, but is XEmacs-compatible.
 119 (define-charset 'control-1
 120   "8-bit control code (0x80..0x9F)"
 121   :short-name "8-bit control code"
 122   :code-space [128 159]
 123   :code-offset 128)
 124
 125 (define-charset 'eight-bit-control
 126   "Raw bytes in the range 0x80..0x9F (usually produced from invalid encodings)"
 127   :short-name "Raw bytes 0x80..0x9F"
 128   :supplementary-p t
 129   :code-space [128 159]
 130   :code-offset #x3FFF80)                ; see character.h
 131
 132 (define-charset 'eight-bit-graphic
 133   "Raw bytes in the range 0xA0..0xFF (usually produced from invalid encodings)"
 134   :short-name "Raw bytes 0xA0..0xFF"
 135   :supplementary-p t
 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   :supplementary-p t
 244   :code-space [33 126]
 245   :subset '(jisx0201 33 126 0))
 246
 247 (define-charset 'katakana-jisx0201
 248   "Katakana Part of JISX0201.1976"
 249   :short-name "JISX0201 Katakana"
 250   :long-name "Japanese Katakana (JISX0201.1976)"
 251   :iso-final-char ?I
 252   :emacs-mule-id  137
 253   :supplementary-p t
 254   :code-space [33 126]
 255   :subset '(jisx0201 161 254 -128))
 256
 257 (define-charset 'chinese-gb2312
 258   "GB2312 Chinese simplified: ISO-IR-58"
 259   :short-name "GB2312"
 260   :long-name "GB2312: ISO-IR-58"
 261   :iso-final-char ?A
 262   :emacs-mule-id 145
 263   :code-space [33 126 33 126]
 264   :code-offset #x110000
 265   :unify-map "GB2312")
 266
 267 (define-charset 'chinese-gbk
 268   "GBK Chinese simplified."
 269   :short-name "GBK"
 270   :code-space [#x40 #xFE #x81 #xFE]
 271   :code-offset #x160000
 272   :unify-map "GBK")
 273 (define-charset-alias 'cp936 'chinese-gbk)
 274 (define-charset-alias 'windows-936 'chinese-gbk)
 275
 276 (define-charset 'chinese-cns11643-1
 277   "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
 278   :short-name "CNS11643-1"
 279   :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
 280   :iso-final-char ?G
 281   :emacs-mule-id  149
 282   :code-space [33 126 33 126]
 283   :code-offset #x114000
 284   :unify-map "CNS-1")
 285
 286 (define-charset 'chinese-cns11643-2
 287   "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
 288   :short-name "CNS11643-2"
 289   :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
 290   :iso-final-char ?H
 291   :emacs-mule-id  150
 292   :code-space [33 126 33 126]
 293   :code-offset #x118000
 294   :unify-map "CNS-2")
 295
 296 (define-charset 'chinese-cns11643-3
 297   "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
 298   :short-name  "CNS11643-3"
 299   :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
 300   :iso-final-char ?I
 301   :code-space [33 126 33 126]
 302   :emacs-mule-id  246
 303   :code-offset #x11C000
 304   :unify-map "CNS-3")
 305
 306 (define-charset 'chinese-cns11643-4
 307   "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
 308   :short-name  "CNS11643-4"
 309   :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
 310   :iso-final-char ?J
 311   :emacs-mule-id  247
 312   :code-space [33 126 33 126]
 313   :code-offset #x120000
 314   :unify-map "CNS-4")
 315
 316 (define-charset 'chinese-cns11643-5
 317   "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
 318   :short-name  "CNS11643-5"
 319   :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
 320   :iso-final-char ?K
 321   :emacs-mule-id  248
 322   :code-space [33 126 33 126]
 323   :code-offset #x124000
 324   :unify-map "CNS-5")
 325
 326 (define-charset 'chinese-cns11643-6
 327   "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
 328   :short-name  "CNS11643-6"
 329   :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
 330   :iso-final-char ?L
 331   :emacs-mule-id 249
 332   :code-space [33 126 33 126]
 333   :code-offset #x128000
 334   :unify-map "CNS-6")
 335
 336 (define-charset 'chinese-cns11643-7
 337   "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
 338   :short-name  "CNS11643-7"
 339   :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
 340   :iso-final-char ?M
 341   :emacs-mule-id 250
 342   :code-space [33 126 33 126]
 343   :code-offset #x12C000
 344   :unify-map "CNS-7")
 345
 346 (define-charset 'big5
 347   "Big5 (Chinese traditional)"
 348   :short-name "Big5"
 349   :code-space [#x40 #xFE #xA1 #xFE]
 350   :code-offset #x130000
 351   :unify-map "BIG5")
 352 ;; Fixme: AKA cp950 according to
 353 ;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>.  Is
 354 ;; that correct?
 355
 356 (define-charset 'chinese-big5-1
 357   "Frequently used part (A141-C67E) of Big5 (Chinese traditional)"
 358   :short-name "Big5 (Level-1)"
 359   :long-name "Big5 (Level-1) A141-C67F"
 360   :iso-final-char ?0
 361   :emacs-mule-id 152
 362   :supplementary-p t
 363   :code-space [#x21 #x7E #x21 #x7E]
 364   :code-offset #x135000
 365   :unify-map "BIG5-1")
 366
 367 (define-charset 'chinese-big5-2
 368   "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)"
 369   :short-name "Big5 (Level-2)"
 370   :long-name "Big5 (Level-2) C940-FEFE"
 371   :iso-final-char ?1
 372   :emacs-mule-id  153
 373   :supplementary-p t
 374   :code-space [#x21 #x7E #x21 #x7E]
 375   :code-offset #x137800
 376   :unify-map "BIG5-2")
 377
 378 (define-charset 'japanese-jisx0208
 379   "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
 380   :short-name "JISX0208"
 381   :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
 382   :iso-final-char ?B
 383   :emacs-mule-id 146
 384   :code-space [33 126 33 126]
 385   :code-offset #x140000
 386   :unify-map "JISX0208")
 387
 388 (define-charset 'japanese-jisx0208-1978
 389   "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
 390   :short-name "JISX0208.1978"
 391   :long-name  "JISX0208.1978 (JISC6226.1978): ISO-IR-42"
 392   :iso-final-char ?@
 393   :emacs-mule-id  144
 394   :code-space [33 126 33 126]
 395   :code-offset #x144000
 396   :unify-map "JISC6226")
 397
 398 (define-charset 'japanese-jisx0212
 399   "JISX0212 Japanese supplement: ISO-IR-159"
 400   :short-name "JISX0212"
 401   :long-name "JISX0212 (Japanese): ISO-IR-159"
 402   :iso-final-char ?D
 403   :emacs-mule-id 148
 404   :code-space [33 126 33 126]
 405   :code-offset #x148000
 406   :unify-map "JISX0212")
 407
 408 ;; Note that jisx0213 contains characters not in Unicode (3.2?).  It's
 409 ;; arguable whether it should have a unify-map.
 410 (define-charset 'japanese-jisx0213-1
 411   "JISX0213.2000 Plane 1 (Japanese)"
 412   :short-name "JISX0213-1"
 413   :iso-final-char ?O
 414   :emacs-mule-id  151
 415   :unify-map "JISX2131"
 416   :code-space [33 126 33 126]
 417   :code-offset #x14C000)
 418
 419 (define-charset 'japanese-jisx0213-2
 420   "JISX0213.2000 Plane 2 (Japanese)"
 421   :short-name "JISX0213-2"
 422   :iso-final-char ?P
 423   :emacs-mule-id 254
 424   :unify-map "JISX2132"
 425   :code-space [33 126 33 126]
 426   :code-offset #x150000)
 427
 428 (define-charset 'japanese-jisx0213-a
 429   "JISX0213.2004 adds these characters to JISX0213.2000."
 430   :short-name "JISX0213A"
 431   :dimension 2
 432   :code-space [33 126 33 126]
 433   :supplementary-p t
 434   :map "JISX213A")
 435
 436 (define-charset 'japanese-jisx0213.2004-1
 437   "JISX0213.2004 Plane1 (Japanese)"
 438   :short-name "JISX0213.2004-1"
 439   :dimension 2
 440   :code-space [33 126 33 126]
 441   :iso-final-char ?Q
 442   :superset '(japanese-jisx0213-a japanese-jisx0213-1))
 443
 444 (define-charset 'katakana-sjis
 445   "Katakana part of Shift-JIS"
 446   :dimension 1
 447   :code-space [#xA1 #xDF]
 448   :subset '(jisx0201 #xA1 #xDF 0)
 449   :supplementary-p t)
 450
 451 (define-charset 'cp932-2-byte
 452   "2-byte part of CP932"
 453   :dimension 2
 454   :map "CP932-2BYTE"
 455   :code-space [#x40 #xFC #x81 #xFC]
 456   :supplementary-p t)
 457
 458 (define-charset 'cp932
 459   "CP932 (Microsoft shift-jis)"
 460   :code-space [#x00 #xFF #x00 #xFE]
 461   :short-name "CP932"
 462   :superset '(ascii katakana-sjis cp932-2-byte))
 463
 464 (define-charset 'korean-ksc5601
 465   "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
 466   :short-name "KSC5601"
 467   :long-name "KSC5601 (Korean): ISO-IR-149"
 468   :iso-final-char ?C
 469   :emacs-mule-id 147
 470   :code-space [33 126 33 126]
 471   :code-offset #x279f94                 ; ... #x27c217
 472   :unify-map "KSC5601")
 473
 474 (define-charset 'big5-hkscs
 475   "Big5-HKSCS (Chinese traditional, Hong Kong supplement)"
 476   :short-name "Big5"
 477   :code-space [#x40 #xFE #xA1 #xFE]
 478   :code-offset #x27c218                 ; ... #x280839
 479   :unify-map "BIG5-HKSCS")
 480
 481 ;; Fixme: Korean cp949/UHC
 482
 483 (define-charset 'chinese-sisheng
 484   "SiSheng characters for PinYin/ZhuYin"
 485   :short-name "SiSheng"
 486   :long-name "SiSheng (PinYin/ZhuYin)"
 487   :iso-final-char ?0
 488   :emacs-mule-id 160
 489   :code-space [33 126]
 490   :unify-map "MULE-sisheng"
 491   :supplementary-p t
 492   :code-offset #x200000)
 493
 494 ;; A subset of the 1989 version of IPA.  It consists of the consonant
 495 ;; signs used in English, French, German and Italian, and all vowels
 496 ;; signs in the table.  [says old MULE doc]
 497 (define-charset 'ipa
 498   "IPA (International Phonetic Association)"
 499   :short-name "IPA"
 500   :iso-final-char ?0
 501   :emacs-mule-id  161
 502   :unify-map "MULE-ipa"
 503   :code-space [32 127]
 504   :supplementary-p t
 505   :code-offset #x200080)
 506
 507 (define-charset 'viscii
 508   "VISCII1.1"
 509   :short-name "VISCII"
 510   :long-name "VISCII 1.1"
 511   :code-space [0 255]
 512   :map "VISCII")
 513
 514 (define-charset 'vietnamese-viscii-lower
 515   "VISCII1.1 lower-case"
 516   :short-name "VISCII lower"
 517   :long-name "VISCII lower-case"
 518   :iso-final-char ?1
 519   :emacs-mule-id  162
 520   :code-space [32 127]
 521   :code-offset #x200200
 522   :supplementary-p t
 523   :unify-map "MULE-lviscii")
 524
 525 (define-charset 'vietnamese-viscii-upper
 526   "VISCII1.1 upper-case"
 527   :short-name "VISCII upper"
 528   :long-name "VISCII upper-case"
 529   :iso-final-char ?2
 530   :emacs-mule-id  163
 531   :code-space [32 127]
 532   :code-offset #x200280
 533   :supplementary-p t
 534   :unify-map "MULE-uviscii")
 535
 536 (define-charset 'vscii
 537   "VSCII1.1 (TCVN-5712 VN1)"
 538   :short-name "VSCII"
 539   :code-space [0 255]
 540   :map "VSCII")
 541
 542 (define-charset-alias 'tcvn-5712 'vscii)
 543
 544 ;; Fixme: see note in tcvn.map about combining characters
 545 (define-charset 'vscii-2
 546   "VSCII-2 (TCVN-5712 VN2)"
 547   :code-space [0 255]
 548   :map "VSCII-2")
 549
 550 (define-charset 'koi8-r
 551   "KOI8-R"
 552   :short-name "KOI8-R"
 553   :ascii-compatible-p t
 554   :code-space [0 255]
 555   :map "KOI8-R")
 556
 557 (define-charset-alias 'koi8 'koi8-r)
 558
 559 (define-charset 'alternativnyj
 560   "ALTERNATIVNYJ"
 561   :short-name "alternativnyj"
 562   :ascii-compatible-p t
 563   :code-space [0 255]
 564   :map "ALTERNATIVNYJ")
 565
 566 (define-charset 'cp866
 567   "CP866"
 568   :short-name "cp866"
 569   :ascii-compatible-p t
 570   :code-space [0 255]
 571   :map "IBM866")
 572 (define-charset-alias 'ibm866 'cp866)
 573
 574 (define-charset 'koi8-u
 575   "KOI8-U"
 576   :short-name "KOI8-U"
 577   :ascii-compatible-p t
 578   :code-space [0 255]
 579   :map "KOI8-U")
 580
 581 (define-charset 'koi8-t
 582   "KOI8-T"
 583   :short-name "KOI8-T"
 584   :ascii-compatible-p t
 585   :code-space [0 255]
 586   :map "KOI8-T")
 587
 588 (define-charset 'georgian-ps
 589   "GEORGIAN-PS"
 590   :short-name "GEORGIAN-PS"
 591   :ascii-compatible-p t
 592   :code-space [0 255]
 593   :map "KA-PS")
 594
 595 (define-charset 'georgian-academy
 596   "GEORGIAN-ACADEMY"
 597   :short-name "GEORGIAN-ACADEMY"
 598   :ascii-compatible-p t
 599   :code-space [0 255]
 600   :map "KA-ACADEMY")
 601
 602 (define-charset 'windows-1250
 603   "WINDOWS-1250 (Central Europe)"
 604   :short-name "WINDOWS-1250"
 605   :ascii-compatible-p t
 606   :code-space [0 255]
 607   :map "CP1250")
 608 (define-charset-alias 'cp1250 'windows-1250)
 609
 610 (define-charset 'windows-1251
 611   "WINDOWS-1251 (Cyrillic)"
 612   :short-name "WINDOWS-1251"
 613   :ascii-compatible-p t
 614   :code-space [0 255]
 615   :map "CP1251")
 616 (define-charset-alias 'cp1251 'windows-1251)
 617
 618 (define-charset 'windows-1252
 619   "WINDOWS-1252 (Latin I)"
 620   :short-name "WINDOWS-1252"
 621   :ascii-compatible-p t
 622   :code-space [0 255]
 623   :map "CP1252")
 624 (define-charset-alias 'cp1252 'windows-1252)
 625
 626 (define-charset 'windows-1253
 627   "WINDOWS-1253 (Greek)"
 628   :short-name "WINDOWS-1253"
 629   :ascii-compatible-p t
 630   :code-space [0 255]
 631   :map "CP1253")
 632 (define-charset-alias 'cp1253 'windows-1253)
 633
 634 (define-charset 'windows-1254
 635   "WINDOWS-1254 (Turkish)"
 636   :short-name "WINDOWS-1254"
 637   :ascii-compatible-p t
 638   :code-space [0 255]
 639   :map "CP1254")
 640 (define-charset-alias 'cp1254 'windows-1254)
 641
 642 (define-charset 'windows-1255
 643   "WINDOWS-1255 (Hebrew)"
 644   :short-name "WINDOWS-1255"
 645   :ascii-compatible-p t
 646   :code-space [0 255]
 647   :map "CP1255")
 648 (define-charset-alias 'cp1255 'windows-1255)
 649
 650 (define-charset 'windows-1256
 651   "WINDOWS-1256 (Arabic)"
 652   :short-name "WINDOWS-1256"
 653   :ascii-compatible-p t
 654   :code-space [0 255]
 655   :map "CP1256")
 656 (define-charset-alias 'cp1256 'windows-1256)
 657
 658 (define-charset 'windows-1257
 659   "WINDOWS-1257 (Baltic)"
 660   :short-name "WINDOWS-1257"
 661   :ascii-compatible-p t
 662   :code-space [0 255]
 663   :map "CP1257")
 664 (define-charset-alias 'cp1257 'windows-1257)
 665
 666 (define-charset 'windows-1258
 667   "WINDOWS-1258 (Viet Nam)"
 668   :short-name "WINDOWS-1258"
 669   :ascii-compatible-p t
 670   :code-space [0 255]
 671   :map "CP1258")
 672 (define-charset-alias 'cp1258 'windows-1258)
 673
 674 (define-charset 'next
 675   "NEXT"
 676   :short-name "NEXT"
 677   :ascii-compatible-p t
 678   :code-space [0 255]
 679   :map "NEXTSTEP")
 680
 681 (define-charset 'cp1125
 682   "CP1125"
 683   :short-name "CP1125"
 684   :code-space [0 255]
 685   :ascii-compatible-p t
 686   :map "CP1125")
 687 (define-charset-alias 'ruscii 'cp1125)
 688 ;; Original name for cp1125, says Serhii Hlodin <hlodin@lutsk.bank.gov.ua>
 689 (define-charset-alias 'cp866u 'cp1125)
 690
 691 ;; Fixme: C.f. iconv, http://czyborra.com/charsets/codepages.html
 692 ;; shows this as not ASCII comptaible, with various graphics in
 693 ;; 0x01-0x1F.
 694 (define-charset 'cp437
 695   "CP437 (MS-DOS United States, Australia, New Zealand, South Africa)"
 696   :short-name "CP437"
 697   :code-space [0 255]
 698   :ascii-compatible-p t
 699   :map "IBM437")
 700
 701 (define-charset 'cp720
 702   "CP720 (Arabic)"
 703   :short-name "CP720"
 704   :code-space [0 255]
 705   :ascii-compatible-p t
 706   :map "CP720")
 707
 708 (define-charset 'cp737
 709   "CP737 (PC Greek)"
 710   :short-name "CP737"
 711   :code-space [0 255]
 712   :ascii-compatible-p t
 713   :map "CP737")
 714
 715 (define-charset 'cp775
 716   "CP775 (PC Baltic)"
 717   :short-name "CP775"
 718   :code-space [0 255]
 719   :ascii-compatible-p t
 720   :map "CP775")
 721
 722 (define-charset 'cp851
 723   "CP851 (Greek)"
 724   :short-name "CP851"
 725   :code-space [0 255]
 726   :ascii-compatible-p t
 727   :map "IBM851")
 728
 729 (define-charset 'cp852
 730   "CP852 (MS-DOS Latin-2)"
 731   :short-name "CP852"
 732   :code-space [0 255]
 733   :ascii-compatible-p t
 734   :map "IBM852")
 735
 736 (define-charset 'cp855
 737   "CP855 (IBM Cyrillic)"
 738   :short-name "CP855"
 739   :code-space [0 255]
 740   :ascii-compatible-p t
 741   :map "IBM855")
 742
 743 (define-charset 'cp857
 744   "CP857 (IBM Turkish)"
 745   :short-name "CP857"
 746   :code-space [0 255]
 747   :ascii-compatible-p t
 748   :map "IBM857")
 749
 750 (define-charset 'cp858
 751   "CP858 (Multilingual Latin I + Euro)"
 752   :short-name "CP858"
 753   :code-space [0 255]
 754   :ascii-compatible-p t
 755   :map "CP858")
 756 (define-charset-alias 'cp00858 'cp858)  ; IANA has IBM00858/CP00858
 757
 758 (define-charset 'cp860
 759   "CP860 (MS-DOS Portuguese)"
 760   :short-name "CP860"
 761   :code-space [0 255]
 762   :ascii-compatible-p t
 763   :map "IBM860")
 764
 765 (define-charset 'cp861
 766   "CP861 (MS-DOS Icelandic)"
 767   :short-name "CP861"
 768   :code-space [0 255]
 769   :ascii-compatible-p t
 770   :map "IBM861")
 771
 772 (define-charset 'cp862
 773   "CP862 (PC Hebrew)"
 774   :short-name "CP862"
 775   :code-space [0 255]
 776   :ascii-compatible-p t
 777   :map "IBM862")
 778
 779 (define-charset 'cp863
 780   "CP863 (MS-DOS Canadian French)"
 781   :short-name "CP863"
 782   :code-space [0 255]
 783   :ascii-compatible-p t
 784   :map "IBM863")
 785
 786 (define-charset 'cp864
 787   "CP864 (PC Arabic)"
 788   :short-name "CP864"
 789   :code-space [0 255]
 790   :ascii-compatible-p t
 791   :map "IBM864")
 792
 793 (define-charset 'cp865
 794   "CP865 (MS-DOS Nordic)"
 795   :short-name "CP865"
 796   :code-space [0 255]
 797   :ascii-compatible-p t
 798   :map "IBM865")
 799
 800 (define-charset 'cp869
 801   "CP869 (IBM Modern Greek)"
 802   :short-name "CP869"
 803   :code-space [0 255]
 804   :ascii-compatible-p t
 805   :map "IBM869")
 806
 807 (define-charset 'cp874
 808   "CP874 (IBM Thai)"
 809   :short-name "CP874"
 810   :code-space [0 255]
 811   :ascii-compatible-p t
 812   :map "IBM874")
 813
 814 ;; For Arabic, we need three different types of character sets.
 815 ;; Digits are of direction left-to-right and of width 1-column.
 816 ;; Others are of direction right-to-left and of width 1-column or
 817 ;; 2-column.
 818 (define-charset 'arabic-digit
 819   "Arabic digit"
 820   :short-name "Arabic digit"
 821   :iso-final-char ?2
 822   :emacs-mule-id 164
 823   :supplementary-p t
 824   :code-space [34 42]
 825   :code-offset #x0600)
 826
 827 (define-charset 'arabic-1-column
 828   "Arabic 1-column"
 829   :short-name "Arabic 1-col"
 830   :long-name "Arabic 1-column"
 831   :iso-final-char ?3
 832   :emacs-mule-id 165
 833   :supplementary-p t
 834   :code-space [33 126]
 835   :code-offset #x200100)
 836
 837 (define-charset 'arabic-2-column
 838   "Arabic 2-column"
 839   :short-name "Arabic 2-col"
 840   :long-name "Arabic 2-column"
 841   :iso-final-char ?4
 842   :emacs-mule-id 224
 843   :supplementary-p t
 844   :code-space [33 126]
 845   :code-offset #x200180)
 846
 847 ;; Lao script.
 848 ;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
 849 ;; Not all of them are defined unicodes.
 850 (define-charset 'lao
 851   "Lao characters (ISO10646 0E81..0EDF)"
 852   :short-name "Lao"
 853   :iso-final-char ?1
 854   :emacs-mule-id 167
 855   :supplementary-p t
 856   :code-space [33 126]
 857   :code-offset #x0E81)
 858
 859 (define-charset 'mule-lao
 860   "Lao characters (ISO10646 0E81..0EDF)"
 861   :short-name "Lao"
 862   :code-space [0 255]
 863   :supplementary-p t
 864   :superset '(ascii eight-bit-control (lao . 128)))
 865
 866
 867 ;; Indian scripts.  Symbolic charset for data exchange.  Glyphs are
 868 ;; not assigned.  They are automatically converted to each Indian
 869 ;; script which IS-13194 supports.
 870
 871 (define-charset 'indian-is13194
 872   "Generic Indian charset for data exchange with IS 13194"
 873   :short-name "IS 13194"
 874   :long-name "Indian IS 13194"
 875   :iso-final-char ?5
 876   :emacs-mule-id 225
 877   :supplementary-p t
 878   :code-space [33 126]
 879   :code-offset #x180000)
 880
 881 (let ((code-offset #x180100))
 882   (dolist (script '(devanagari sanskrit bengali tamil telugu assamese
 883                                oriya kannada malayalam gujarati punjabi))
 884     (define-charset (intern (format "%s-cdac" script))
 885       (format "Glyphs of %s script for CDAC font.  Subset of `indian-glyph'."
 886               (capitalize (symbol-name script)))
 887       :short-name (format "CDAC %s glyphs" (capitalize (symbol-name script)))
 888       :supplementary-p t
 889       :code-space [0 255]
 890       :code-offset code-offset)
 891     (setq code-offset (+ code-offset #x100)))
 892
 893   (dolist (script '(devanagari bengali punjabi gujarati
 894                                oriya tamil telugu kannada malayalam))
 895     (define-charset (intern (format "%s-akruti" script))
 896       (format "Glyphs of %s script for AKRUTI font.  Subset of `indian-glyph'."
 897               (capitalize (symbol-name script)))
 898       :short-name (format "AKRUTI %s glyphs" (capitalize (symbol-name script)))
 899       :supplementary-p t
 900       :code-space [0 255]
 901       :code-offset code-offset)
 902     (setq code-offset (+ code-offset #x100))))
 903
 904 (define-charset 'indian-glyph
 905   "Glyphs for Indian characters."
 906   :short-name "Indian glyph"
 907   :iso-final-char ?4
 908   :emacs-mule-id 240
 909   :supplementary-p t
 910   :code-space [32 127 32 127]
 911   :code-offset #x180100)
 912
 913 ;; Actual Glyph for 1-column width.
 914 (define-charset 'indian-1-column
 915   "Indian charset for 1-column width glyphs."
 916   :short-name "Indian 1-col"
 917   :long-name "Indian 1 Column"
 918   :iso-final-char ?6
 919   :emacs-mule-id  251
 920   :supplementary-p t
 921   :code-space [33 126 33 126]
 922   :code-offset #x184000)
 923
 924 ;; Actual Glyph for 2-column width.
 925 (define-charset 'indian-2-column
 926   "Indian charset for 2-column width glyphs."
 927   :short-name "Indian 2-col"
 928   :long-name "Indian 2 Column"
 929   :iso-final-char ?5
 930   :emacs-mule-id  251
 931   :supplementary-p t
 932   :code-space [33 126 33 126]
 933   :code-offset #x184000)
 934
 935 (define-charset 'tibetan
 936   "Tibetan characters"
 937   :iso-final-char ?7
 938   :short-name "Tibetan 2-col"
 939   :long-name "Tibetan 2 column"
 940   :iso-final-char ?7
 941   :emacs-mule-id 252
 942   :unify-map "MULE-tibetan"
 943   :supplementary-p t
 944   :code-space [33 126 33 37]
 945   :code-offset #x190000)
 946
 947 (define-charset 'tibetan-1-column
 948   "Tibetan 1 column glyph"
 949   :short-name "Tibetan 1-col"
 950   :long-name "Tibetan 1 column"
 951   :iso-final-char ?8
 952   :emacs-mule-id 241
 953   :supplementary-p t
 954   :code-space [33 126 33 37]
 955   :code-offset #x190000)
 956
 957 ;; Subsets of Unicode.
 958 (define-charset 'mule-unicode-2500-33ff
 959   "Unicode characters of the range U+2500..U+33FF."
 960   :short-name "Unicode subset 2"
 961   :long-name "Unicode subset (U+2500..U+33FF)"
 962   :iso-final-char ?2
 963   :emacs-mule-id 242
 964   :supplementary-p t
 965   :code-space [#x20 #x7f #x20 #x47]
 966   :code-offset #x2500)
 967
 968 (define-charset 'mule-unicode-e000-ffff
 969   "Unicode characters of the range U+E000..U+FFFF."
 970   :short-name "Unicode subset 3"
 971   :long-name "Unicode subset (U+E000+FFFF)"
 972   :iso-final-char ?3
 973   :emacs-mule-id 243
 974   :supplementary-p t
 975   :code-space [#x20 #x7F #x20 #x75]
 976   :code-offset #xE000
 977   :max-code 30015)                      ; U+FFFF
 978
 979 (define-charset 'mule-unicode-0100-24ff
 980   "Unicode characters of the range U+0100..U+24FF."
 981   :short-name "Unicode subset"
 982   :long-name "Unicode subset (U+0100..U+24FF)"
 983   :iso-final-char ?1
 984   :emacs-mule-id 244
 985   :supplementary-p t
 986   :code-space [#x20 #x7F #x20 #x7F]
 987   :code-offset #x100)
 988
 989 (define-charset 'unicode-bmp
 990   "Unicode Basic Multilingual Plane (U+0000..U+FFFF)"
 991   :short-name "Unicode BMP"
 992   :code-space [0 255 0 255]
 993   :code-offset 0)
 994
 995 (define-charset 'unicode-smp
 996   "Unicode Supplementary Multilingual Plane (U+10000..U+1FFFF)"
 997   :short-name "Unicode SMP "
 998   :code-space [0 255 0 255]
 999   :code-offset #x10000)
1000
1001 (define-charset 'unicode-sip
1002   "Unicode Supplementary Ideographic Plane (U+20000..U+2FFFF)"
1003   :short-name "Unicode SIP"
1004   :code-space [0 255 0 255]
1005   :code-offset #x20000)
1006
1007 (define-charset 'unicode-ssp
1008   "Unicode Supplementary Special-purpose Plane (U+E0000..U+EFFFF)"
1009   :short-name "Unicode SSP"
1010   :code-space [0 255 0 255]
1011   :code-offset #xE0000)
1012
1013 (define-charset 'ethiopic
1014   "Ethiopic characters for Amharic and Tigrigna."
1015   :short-name "Ethiopic"
1016   :long-name "Ethiopic characters"
1017   :iso-final-char ?3
1018   :emacs-mule-id  245
1019   :supplementary-p t
1020   :unify-map "MULE-ethiopic"
1021   :code-space [33 126 33 126]
1022   :code-offset #x1A0000)
1023
1024 (define-charset 'mac-roman
1025   "Mac Roman charset"
1026   :short-name "Mac Roman"
1027   :ascii-compatible-p t
1028   :code-space [0 255]
1029   :map "MACINTOSH")
1030
1031 ;; Fixme: modern EBCDIC variants, e.g. IBM00924?
1032 (define-charset 'ebcdic-us
1033   "US version of EBCDIC"
1034   :short-name "EBCDIC-US"
1035   :code-space [0 255]
1036   :mime-charset 'ebcdic-us
1037   :map "EBCDICUS")
1038
1039 (define-charset 'ebcdic-uk
1040   "UK version of EBCDIC"
1041   :short-name "EBCDIC-UK"
1042   :code-space [0 255]
1043   :mime-charset 'ebcdic-uk
1044   :map "EBCDICUK")
1045
1046 (define-charset 'ibm1047
1047   ;; Says groff:
1048   "IBM1047, `EBCDIC Latin 1/Open Systems' used by OS/390 Unix."
1049   :short-name "IBM1047"
1050   :code-space [0 255]
1051   :mime-charset 'ibm1047
1052   :map "IBM1047")
1053 (define-charset-alias 'cp1047 'ibm1047)
1054
1055 (define-charset 'hp-roman8
1056   "Encoding used by Hewlet-Packard printer software"
1057   :short-name "HP-ROMAN8"
1058   :ascii-compatible-p t
1059   :code-space [0 255]
1060   :map "HP-ROMAN8")
1061
1062 ;; To make a coding system with this, a pre-write-conversion should
1063 ;; account for the commented-out multi-valued code points in
1064 ;; stdenc.map.
1065 (define-charset 'adobe-standard-encoding
1066   "Adobe `standard encoding' used in PostScript"
1067   :short-name "ADOBE-STANDARD-ENCODING"
1068   :code-space [#x20 255]
1069   :map "stdenc")
1070
1071 (define-charset 'symbol
1072   "Adobe symbol encoding used in PostScript"
1073   :short-name "ADOBE-SYMBOL"
1074   :code-space [#x20 255]
1075   :map "symbol")
1076
1077 (define-charset 'ibm850
1078   "DOS codepage 850 (Latin-1)"
1079   :short-name "IBM850"
1080   :ascii-compatible-p t
1081   :code-space [0 255]
1082   :map "IBM850")
1083 (define-charset-alias 'cp850 'ibm850)
1084
1085 (define-charset 'mik
1086   "Bulgarian DOS codepage"
1087   :short-name "MIK"
1088   :ascii-compatible-p t
1089   :code-space [0 255]
1090   :map "MIK")
1091
1092 (define-charset 'ptcp154
1093   "`Paratype' codepage (Asian Cyrillic)"
1094   :short-name "PT154"
1095   :ascii-compatible-p t
1096   :code-space [0 255]
1097   :mime-charset 'pt154
1098   :map "PTCP154")
1099 (define-charset-alias 'pt154 'ptcp154)
1100 (define-charset-alias 'cp154 'ptcp154)
1101
1102 (define-charset 'gb18030-2-byte
1103   "GB18030 2-byte (0x814E..0xFEFE)"
1104   :code-space [#x40 #xFE #x81 #xFE]
1105   :supplementary-p t
1106   :map "GB180302")
1107
1108 (define-charset 'gb18030-4-byte-bmp
1109   "GB18030 4-byte for BMP (0x81308130-0x8431A439)"
1110   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x81 #x84]
1111   :supplementary-p t
1112   :map "GB180304")
1113
1114 (define-charset 'gb18030-4-byte-smp
1115   "GB18030 4-byte for SMP (0x90308130-0xE3329A35)"
1116   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x90 #xE3]
1117   :min-code '(#x9030 . #x8130)
1118   :max-code '(#xE332 . #x9A35)
1119   :supplementary-p t
1120   :code-offset #x10000)
1121
1122 (define-charset 'gb18030-4-byte-ext-1
1123   "GB18030 4-byte (0x8431A530-0x8F39FE39)"
1124   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #x84 #x8F]
1125   :min-code '(#x8431 . #xA530)
1126   :max-code '(#x8F39 . #xFE39)
1127   :supplementary-p t
1128   :code-offset #x200000                 ; ... #x22484B
1129   )
1130
1131 (define-charset 'gb18030-4-byte-ext-2
1132   "GB18030 4-byte (0xE3329A36-0xFE39FE39)"
1133   :code-space [#x30 #x39 #x81 #xFE #x30 #x39 #xE3 #xFE]
1134   :min-code '(#xE332 . #x9A36)
1135   :max-code '(#xFE39 . #xFE39)
1136   :supplementary-p t
1137   :code-offset #x22484C                 ; ... #x279f93
1138   )
1139
1140 (define-charset 'gb18030
1141   "GB18030"
1142   :code-space [#x00 #xFF #x00 #xFE #x00 #xFE #x00 #xFE]
1143   :min-code 0
1144   :max-code '(#xFE39 . #xFE39)
1145   :superset '(ascii gb18030-2-byte
1146                     gb18030-4-byte-bmp gb18030-4-byte-smp
1147                     gb18030-4-byte-ext-1 gb18030-4-byte-ext-2))
1148
1149 (define-charset 'chinese-cns11643-15
1150   "CNS11643 Plane 15 Chinese Traditional"
1151   :short-name  "CNS11643-15"
1152   :long-name "CNS11643-15 (Chinese traditional)"
1153   :code-space [33 126 33 126]
1154   :code-offset #x27A000)
1155
1156 (unify-charset 'chinese-gb2312)
1157 (unify-charset 'chinese-gbk)
1158 (unify-charset 'chinese-cns11643-1)
1159 (unify-charset 'chinese-cns11643-2)
1160 (unify-charset 'chinese-cns11643-3)
1161 (unify-charset 'chinese-cns11643-4)
1162 (unify-charset 'chinese-cns11643-5)
1163 (unify-charset 'chinese-cns11643-6)
1164 (unify-charset 'chinese-cns11643-7)
1165 (unify-charset 'big5)
1166 (unify-charset 'chinese-big5-1)
1167 (unify-charset 'chinese-big5-2)
1168 (unify-charset 'big5-hkscs)
1169 (unify-charset 'korean-ksc5601)
1170 (unify-charset 'vietnamese-viscii-lower)
1171 (unify-charset 'vietnamese-viscii-upper)
1172 (unify-charset 'chinese-sisheng)
1173 (unify-charset 'ipa)
1174 (unify-charset 'tibetan)
1175 (unify-charset 'ethiopic)
1176 (unify-charset 'japanese-jisx0208-1978)
1177 (unify-charset 'japanese-jisx0208)
1178 (unify-charset 'japanese-jisx0212)
1179 (unify-charset 'japanese-jisx0213-1)
1180 (unify-charset 'japanese-jisx0213-2)
1181
1182 \f
1183 ;; These are tables for translating characters on decoding and
1184 ;; encoding.
1185 ;; Fixme: these aren't used now -- should they be?
1186 (setq standard-translation-table-for-decode nil)
1187
1188 (setq standard-translation-table-for-encode nil)
1189 \f
1190 ;;; Make fundamental coding systems.
1191
1192 ;; The coding system `no-conversion' and `undecided' are already
1193 ;; defined in coding.c as below:
1194 ;;
1195 ;; (define-coding-system 'no-conversion
1196 ;;   "..."
1197 ;;   :coding-type 'raw-text
1198 ;;   ...)
1199 ;; (define-coding-system 'undecided
1200 ;;   "..."
1201 ;;   :coding-type 'undecided
1202 ;;   ...)
1203
1204 (define-coding-system-alias 'binary 'no-conversion)
1205 (define-coding-system-alias 'unix 'undecided-unix)
1206 (define-coding-system-alias 'dos 'undecided-dos)
1207 (define-coding-system-alias 'mac 'undecided-mac)
1208
1209 (define-coding-system 'raw-text
1210   "Raw text, which means text contains random 8-bit codes.
1211 Encoding text with this coding system produces the actual byte
1212 sequence of the text in buffers and strings.  An exception is made for
1213 eight-bit-control characters.  Each of them is encoded into a single
1214 byte.
1215
1216 When you visit a file with this coding, the file is read into a
1217 unibyte buffer as is (except for EOL format), thus each byte of a file
1218 is treated as a character."
1219   :coding-type 'raw-text
1220   :for-unibyte t
1221   :mnemonic ?t)
1222
1223 (define-coding-system 'no-conversion-multibyte
1224   "Like `no-conversion' but don't read a file into a unibyte buffer."
1225   :coding-type 'raw-text
1226   :eol-type 'unix
1227   :mnemonic ?=)
1228
1229 (define-coding-system 'iso-latin-1
1230   "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
1231   :coding-type 'charset
1232   :mnemonic ?1
1233   :charset-list '(iso-8859-1)
1234   :mime-charset 'iso-8859-1)
1235
1236 (define-coding-system-alias 'iso-8859-1 'iso-latin-1)
1237 (define-coding-system-alias 'latin-1 'iso-latin-1)
1238
1239 ;; Coding systems not specific to each language environment.
1240
1241 (define-coding-system 'emacs-mule
1242  "Emacs 21 internal format used in buffer and string."
1243  :coding-type 'emacs-mule
1244  :charset-list 'emacs-mule
1245  :mnemonic ?M)
1246
1247 (define-coding-system 'utf-8
1248   "UTF-8."
1249   :coding-type 'utf-8
1250   :mnemonic ?U
1251   :charset-list '(unicode)
1252   :mime-charset 'utf-8)
1253
1254 (define-coding-system-alias 'mule-utf-8 'utf-8)
1255
1256 (define-coding-system 'utf-8-emacs
1257   "Support for all Emacs characters (including non-Unicode characters)."
1258   :coding-type 'utf-8
1259   :mnemonic ?U
1260   :charset-list '(emacs))
1261
1262 (define-coding-system 'utf-16le
1263   "UTF-16LE (little endian, no signature (BOM))."
1264   :coding-type 'utf-16
1265   :mnemonic ?U
1266   :charset-list '(unicode)
1267   :endian 'little
1268   :mime-text-unsuitable t
1269   :mime-charset 'utf-16le)
1270
1271 (define-coding-system 'utf-16be
1272   "UTF-16BE (big endian, no signature (BOM))."
1273   :coding-type 'utf-16
1274   :mnemonic ?U
1275   :charset-list '(unicode)
1276   :endian 'big
1277   :mime-text-unsuitable t
1278   :mime-charset 'utf-16be)
1279
1280 (define-coding-system 'utf-16le-with-signature
1281   "UTF-16 (little endian, with signature (BOM))."
1282   :coding-type 'utf-16
1283   :mnemonic ?U
1284   :charset-list '(unicode)
1285   :bom t
1286   :endian 'little
1287   :mime-text-unsuitable t
1288   :mime-charset 'utf-16)
1289
1290 (define-coding-system 'utf-16be-with-signature
1291   "UTF-16 (big endian, with signature)."
1292   :coding-type 'utf-16
1293   :mnemonic ?U
1294   :charset-list '(unicode)
1295   :bom t
1296   :endian 'big
1297   :mime-text-unsuitable t
1298   :mime-charset 'utf-16)
1299
1300 (define-coding-system 'utf-16
1301   "UTF-16 (detect endian on decoding, use big endian on encoding with BOM)."
1302   :coding-type 'utf-16
1303   :mnemonic ?U
1304   :charset-list '(unicode)
1305   :bom '(utf-16le-with-signature . utf-16be-with-signature)
1306   :endian 'big
1307   :mime-text-unsuitable t
1308   :mime-charset 'utf-16)
1309
1310 ;; Backwards compatibility (old names, also used by Mule-UCS).  We
1311 ;; prefer the MIME names.
1312 (define-coding-system-alias 'utf-16-le 'utf-16le-with-signature)
1313 (define-coding-system-alias 'utf-16-be 'utf-16be-with-signature)
1314
1315
1316 (define-coding-system 'iso-2022-7bit
1317   "ISO 2022 based 7-bit encoding using only G0."
1318   :coding-type 'iso-2022
1319   :mnemonic ?J
1320   :charset-list 'iso-2022
1321   :designation [(ascii t) nil nil nil]
1322   :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition))
1323
1324 (define-coding-system 'iso-2022-7bit-ss2
1325   "ISO 2022 based 7-bit encoding using SS2 for 96-charset."
1326   :coding-type 'iso-2022
1327   :mnemonic ?$
1328   :charset-list 'iso-2022
1329   :designation [(ascii 94) nil (nil 96) nil]
1330   :flags '(short ascii-at-eol ascii-at-cntl 7-bit
1331                  designation single-shift composition))
1332
1333 (define-coding-system 'iso-2022-7bit-lock
1334   "ISO-2022 coding system using Locking-Shift for 96-charset."
1335   :coding-type 'iso-2022
1336   :mnemonic ?&
1337   :charset-list 'iso-2022
1338   :designation [(ascii 94) (nil 96) nil nil]
1339   :flags '(ascii-at-eol ascii-at-cntl 7-bit
1340                         designation locking-shift composition))
1341
1342 (define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
1343
1344 (define-coding-system 'iso-2022-7bit-lock-ss2
1345   "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN."
1346   :coding-type 'iso-2022
1347   :mnemonic ?i
1348   :charset-list '(ascii
1349                   japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
1350                   korean-ksc5601
1351                   chinese-gb2312
1352                   chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
1353                   chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
1354                   chinese-cns11643-7)
1355   :designation [(ascii 94)
1356                 (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96)
1357                 (nil chinese-cns11643-2)
1358                 (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
1359                      chinese-cns11643-6 chinese-cns11643-7)]
1360   :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift
1361                  single-shift init-bol))
1362
1363 (define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
1364
1365 (define-coding-system 'iso-2022-8bit-ss2
1366   "ISO 2022 based 8-bit encoding using SS2 for 96-charset."
1367   :coding-type 'iso-2022
1368   :mnemonic ?@
1369   :charset-list 'iso-2022
1370   :designation [(ascii 94) nil (nil 96) nil]
1371   :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
1372
1373 (define-coding-system 'compound-text
1374   "Compound text based generic encoding for decoding unknown messages.
1375
1376 This coding system does not support extended segments of CTEXT."
1377   :coding-type 'iso-2022
1378   :mnemonic ?x
1379   :charset-list 'iso-2022
1380   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1381   :flags '(ascii-at-eol ascii-at-cntl long-form
1382                         designation locking-shift single-shift composition)
1383   ;; Fixme: this isn't a valid MIME charset and has to be
1384   ;; special-cased elsewhere  -- fx
1385   :mime-charset 'x-ctext)
1386
1387 (define-coding-system-alias  'x-ctext 'compound-text)
1388 (define-coding-system-alias  'ctext 'compound-text)
1389
1390 ;; Same as compound-text, but doesn't produce composition escape
1391 ;; sequences.  Used in post-read and pre-write conversions of
1392 ;; compound-text-with-extensions, see mule.el.  Note that this should
1393 ;; not have a mime-charset property, to prevent it from showing up
1394 ;; close to the beginning of coding systems ordered by priority.
1395 (define-coding-system 'ctext-no-compositions
1396  "Compound text based generic encoding for decoding unknown messages.
1397
1398 Like `compound-text', but does not produce escape sequences for compositions."
1399   :coding-type 'iso-2022
1400   :mnemonic ?x
1401   :charset-list 'iso-2022
1402   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1403   :flags '(ascii-at-eol ascii-at-cntl
1404                         designation locking-shift single-shift))
1405
1406 (define-coding-system 'compound-text-with-extensions
1407  "Compound text encoding with ICCCM Extended Segment extensions.
1408
1409 See the variable `ctext-non-standard-encodings-alist' for the
1410 detail about how extended segments are handled.
1411
1412 This coding system should be used only for X selections.  It is inappropriate
1413 for decoding and encoding files, process I/O, etc."
1414   :coding-type 'iso-2022
1415   :mnemonic ?x
1416   :charset-list 'iso-2022
1417   :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
1418   :flags '(ascii-at-eol ascii-at-cntl long-form
1419                         designation locking-shift single-shift)
1420   :post-read-conversion 'ctext-post-read-conversion
1421   :pre-write-conversion 'ctext-pre-write-conversion)
1422
1423 (define-coding-system-alias
1424   'x-ctext-with-extensions 'compound-text-with-extensions)
1425 (define-coding-system-alias
1426   'ctext-with-extensions 'compound-text-with-extensions)
1427
1428 (define-coding-system 'us-ascii
1429   "Encode ASCII as-is and encode non-ASCII characters to `?'."
1430   :coding-type 'charset
1431   :mnemonic ?-
1432   :charset-list '(ascii)
1433   :default-char ??
1434   :mime-charset 'us-ascii)
1435
1436 (define-coding-system-alias 'iso-safe 'us-ascii)
1437
1438 (define-coding-system 'utf-7
1439   "UTF-7 encoding of Unicode (RFC 2152)."
1440   :coding-type 'utf-8
1441   :mnemonic ?U
1442   :mime-charset 'utf-7
1443   :charset-list '(unicode)
1444   :pre-write-conversion 'utf-7-pre-write-conversion
1445   :post-read-conversion 'utf-7-post-read-conversion)
1446
1447 (define-coding-system 'utf-7-imap
1448   "UTF-7 encoding of Unicode, IMAP version (RFC 2060)"
1449   :coding-type 'utf-8
1450   :mnemonic ?u
1451   :charset-list '(unicode)
1452   :pre-write-conversion 'utf-7-imap-pre-write-conversion
1453   :post-read-conversion 'utf-7-imap-post-read-conversion)
1454
1455 ;; Use us-ascii for terminal output if some other coding system is not
1456 ;; specified explicitly.
1457 (set-safe-terminal-coding-system-internal 'us-ascii)
1458
1459 ;; The other coding-systems are defined in each language specific
1460 ;; files under lisp/language.
1461
1462 ;; Normally, set coding system to `undecided' before reading a file.
1463 ;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
1464 ;; but we regard them as containing multibyte characters.
1465 ;; Tar files are not decoded at all, but we treat them as raw bytes.
1466
1467 (setq file-coding-system-alist
1468       '(("\\.elc\\'" . utf-8-emacs)
1469         ("\\.utf\\(-8\\)?\\'" . utf-8)
1470         ("\\.xml\\'" . xml-find-file-coding-system)
1471         ;; We use raw-text for reading loaddefs.el so that if it
1472         ;; happens to have DOS or Mac EOLs, they are converted to
1473         ;; newlines.  This is required to make the special treatment
1474         ;; of the "\ newline" combination in loaddefs.el, which marks
1475         ;; the beginning of a doc string, work.
1476         ("\\(\\`\\|/\\)loaddefs.el\\'" . (raw-text . raw-text-unix))
1477         ("\\.tar\\'" . (no-conversion . no-conversion))
1478         ( "\\.po[tx]?\\'\\|\\.po\\." . po-find-file-coding-system)
1479         ("\\.\\(tex\\|ltx\\|dtx\\|drv\\)\\'" . latexenc-find-file-coding-system)
1480         ("" . (undecided . nil))))
1481
1482 \f
1483 ;;; Setting coding categories and their priorities.
1484
1485 ;; This setting is just to read an Emacs Lisp source files which
1486 ;; contain multilingual text while dumping Emacs.  More appropriate
1487 ;; values are set by the command `set-language-environment' for each
1488 ;; language environment.
1489
1490 (set-coding-system-priority
1491  'iso-latin-1
1492  'utf-8
1493  'iso-2022-7bit
1494  )
1495
1496 \f
1497 ;;; Miscellaneous settings.
1498
1499 ;; Make all multibyte characters self-insert.
1500 (set-char-table-range (nth 1 global-map)
1501                       (cons 128 (max-char))
1502                       'self-insert-command)
1503
1504 (aset latin-extra-code-table ?\221 t)
1505 (aset latin-extra-code-table ?\222 t)
1506 (aset latin-extra-code-table ?\223 t)
1507 (aset latin-extra-code-table ?\224 t)
1508 (aset latin-extra-code-table ?\225 t)
1509 (aset latin-extra-code-table ?\226 t)
1510
1511 ;; The old code-pages library is obsoleted by coding systems based on
1512 ;; the charsets defined in this file but might be required by user
1513 ;; code.
1514 (provide 'code-pages)
1515
1516 ;; Local variables:
1517 ;; no-byte-compile: t
1518 ;; End:
1519
1520 ;; arch-tag: 7d5fed55-b6df-42f6-8d3d-0011190551f5
1521 ;;; mule-conf.el ends here