;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
+;; Copyright (C) 2001, 2002
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H13PRO009
;; Keywords: mule, multilingual, character set, coding system
;;; Definitions of character sets.
-;; Basic (official) character sets. These character sets are treated
-;; efficiently with respect to buffer memory.
-
-;; Syntax:
-;; (define-charset CHARSET-ID CHARSET
-;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
-;; SHORT-NAME LONG-NAME DESCRIPTION ])
-;; ASCII charset is defined in src/charset.c as below.
-;; (define-charset 0 ascii
-;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"])
-
-;; 1-byte charsets. Valid range of CHARSET-ID is 128..143.
-
-;; CHARSET-ID 128 is not used.
-
-(define-charset 129 'latin-iso8859-1
- [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100"
- "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100."])
-(define-charset 130 'latin-iso8859-2
- [1 96 1 0 ?B 1 "RHP of Latin-2" "RHP of Latin-2 (ISO 8859-2): ISO-IR-101"
- "Right-Hand Part of Latin Alphabet 2 (ISO/IEC 8859-2): ISO-IR-101."])
-(define-charset 131 'latin-iso8859-3
- [1 96 1 0 ?C 1 "RHP of Latin-3" "RHP of Latin-3 (ISO 8859-3): ISO-IR-109"
- "Right-Hand Part of Latin Alphabet 3 (ISO/IEC 8859-3): ISO-IR-109."])
-(define-charset 132 'latin-iso8859-4
- [1 96 1 0 ?D 1 "RHP of Latin-4" "RHP of Latin-4 (ISO 8859-4): ISO-IR-110"
- "Right-Hand Part of Latin Alphabet 4 (ISO/IEC 8859-4): ISO-IR-110."])
-(define-charset 133 'thai-tis620
- [1 96 1 0 ?T 1 "RHP of TIS620" "RHP of Thai (TIS620): ISO-IR-166"
- "Right-Hand Part of TIS620.2533 (Thai): ISO-IR-166."])
-(define-charset 134 'greek-iso8859-7
- [1 96 1 0 ?F 1 "RHP of ISO8859/7" "RHP of Greek (ISO 8859-7): ISO-IR-126"
- "Right-Hand Part of Latin/Greek Alphabet (ISO/IEC 8859-7): ISO-IR-126."])
-(define-charset 135 'arabic-iso8859-6
- [1 96 1 1 ?G 1 "RHP of ISO8859/6" "RHP of Arabic (ISO 8859-6): ISO-IR-127"
- "Right-Hand Part of Latin/Arabic Alphabet (ISO/IEC 8859-6): ISO-IR-127."])
-(define-charset 136 'hebrew-iso8859-8
- [1 96 1 1 ?H 1 "RHP of ISO8859/8" "RHP of Hebrew (ISO 8859-8): ISO-IR-138"
- "Right-Hand Part of Latin/Hebrew Alphabet (ISO/IEC 8859-8): ISO-IR-138."])
-(define-charset 137 'katakana-jisx0201
- [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)"
- "Katakana Part of JISX0201.1976."])
-(define-charset 138 'latin-jisx0201
- [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)"
- "Roman Part of JISX0201.1976."])
-
-;; CHARSET-ID is not used 139.
-
-(define-charset 140 'cyrillic-iso8859-5
- [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144"
- "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144."])
-(define-charset 141 'latin-iso8859-9
- [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148"
- "Right-Hand Part of Latin Alphabet 5 (ISO/IEC 8859-9): ISO-IR-148."])
-(define-charset 142 'latin-iso8859-15
- [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203"
- "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203."])
-(define-charset 143 'latin-iso8859-14
- [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14): ISO-IR-199"
- "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14): ISO-IR-199."])
-
-;; 2-byte charsets. Valid range of CHARSET-ID is 144..153.
-
-(define-charset 144 'japanese-jisx0208-1978
- [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42"
- "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42."])
-(define-charset 145 'chinese-gb2312
- [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58"
- "GB2312 Chinese simplified: ISO-IR-58."])
-(define-charset 146 'japanese-jisx0208
- [2 94 2 0 ?B 0 "JISX0208" "JISX0208.1983/1990 (Japanese): ISO-IR-87"
- "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87."])
-(define-charset 147 'korean-ksc5601
- [2 94 2 0 ?C 0 "KSC5601" "KSC5601 (Korean): ISO-IR-149"
- "KSC5601 Korean Hangul and Hanja: ISO-IR-149."])
-(define-charset 148 'japanese-jisx0212
- [2 94 2 0 ?D 0 "JISX0212" "JISX0212 (Japanese): ISO-IR-159"
- "JISX0212 Japanese supplement: ISO-IR-159."])
-(define-charset 149 'chinese-cns11643-1
- [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171"
- "CNS11643 Plane 1 Chinese traditional: ISO-IR-171."])
-(define-charset 150 'chinese-cns11643-2
- [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172"
- "CNS11643 Plane 2 Chinese traditional: ISO-IR-172."])
-(define-charset 151 'japanese-jisx0213-1
- [2 94 2 0 ?O 0 "JISX0213-1" "JISX0213-1" "JISX0213 Plane 1 (Japanese)"])
-(define-charset 152 'chinese-big5-1
- [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F"
- "Frequently used part (A141-C67F) of Big5 (Chinese traditional)."])
-(define-charset 153 'chinese-big5-2
- [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE"
- "Less frequently used part (C940-FEFE) of Big5 (Chinese traditional)."])
-
-;; Additional (private) character sets. These character sets are
-;; treated less space-efficiently in the buffer.
-
-;; Syntax:
-;; (define-charset CHARSET-ID CHARSET
-;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE
-;; SHORT-NAME LONG-NAME DESCRIPTION ])
-
-;; ISO-2022 allows a use of character sets not registered in ISO with
-;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs
-;; reserves `0' through `9' to support several private character sets.
-;; The remaining final characters `:' through `?' are for users.
-
-;; 1-byte 1-column charsets. Valid range of CHARSET-ID is 160..223.
-
-(define-charset 160 'chinese-sisheng
- [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)"
- "Sisheng characters (vowels with tone marks) for Pinyin/Zhuyin."])
-
-;; IPA characters for phonetic symbols.
-(define-charset 161 'ipa
- [1 96 1 0 ?0 1 "IPA" "IPA"
- "IPA (International Phonetic Association) characters."])
-
-;; Vietnamese VISCII. VISCII is 1-byte character set which contains
-;; more than 96 characters. Since Emacs can't handle it as one
-;; character set, it is divided into two: lower case letters and upper
-;; case letters.
-(define-charset 162 'vietnamese-viscii-lower
- [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case"
- "Vietnamese VISCII1.1 lower-case characters."])
-(define-charset 163 'vietnamese-viscii-upper
- [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case"
- "Vietnamese VISCII1.1 upper-case characters."])
+;; The charsets `ascii' and `unicoe' are aleady defined in charset.c
+;; as below:
+;;
+;; (define-charset 'ascii
+;; ""
+;; :dimension 1
+;; :code-space [0 127]
+;; :iso-final-char ?A
+;; :ascii-compatible-p t
+;; :emacs-mule-id 0
+;; :code-offset 0)
+;;
+;; (define-charset 'unicode
+;; ""
+;; :dimension 3
+;; :code-space [0 255 0 255 0 16]
+;; :ascii-compatible-p t
+;; :code-offset 0)
+;;
+;; We now set :docstring, :short-name, and :long-name properties.
+
+(put-charset-property
+ 'ascii :docstring "ASCII (ISO646 IRV)")
+(put-charset-property
+ 'ascii :short-name "ASCII")
+(put-charset-property
+ 'ascii :long-name "ASCII (ISO646 IRV)")
+(put-charset-property
+ 'unicode :docstring "Unicode (ISO10646)")
+(put-charset-property
+ 'unicode :short-name "Unicode")
+(put-charset-property
+ 'unicode :long-name "Unicode (ISO10646)")
+
+(define-charset-alias 'ucs 'unicode)
+
+(define-charset 'emacs
+ "Full Emacs characters."
+ :ascii-compatible-p t
+ :code-space [ 0 255 0 255 0 63 ]
+ :code-offset 0
+ :supplementary-p t)
+
+(define-charset 'iso-8859-1
+ "Laint-1 (ISO/IEC 8859-1)"
+ :short-name "Latin-1"
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :code-offset 0)
+
+(define-charset 'latin-iso8859-1
+ "Right-Hand Part of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
+ :short-name "RHP of Latin-1"
+ :long-name "RHP of ISO/IEC 8859/1 (Latin-1): ISO-IR-100"
+ :iso-final-char ?A
+ :emacs-mule-id 129
+ :code-space [32 127]
+ :code-offset 160)
+
+(define-charset 'eight-bit-control
+ "8-bit control code (0x80..0x9F)"
+ :short-name "8-bit control code"
+ :code-space [128 159]
+ :code-offset 128)
+
+(define-charset 'eight-bit-graphic
+ "8-bit graphic code (0xA0..0xFF)"
+ :short-name "8-bit graphic code"
+ :code-space [160 255]
+ :code-offset 160)
+
+(defmacro define-iso-single-byte-charset (symbol iso-symbol name nickname
+ iso-ir iso-final
+ emacs-mule-id map)
+ "For internal use only."
+ `(progn
+ (define-charset ,symbol
+ ,name
+ :short-name ,nickname
+ :long-name ,name
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :map ,map)
+ (if ,iso-symbol
+ (define-charset ,iso-symbol
+ (if ,iso-ir
+ (format "Right-Hand Part of %s (%s): ISO-IR-%d"
+ ,name ,nickname ,iso-ir)
+ (format "Right-Hand Part of %s (%s)" ,name ,nickname))
+ :short-name (format "RHP of %s" ,name)
+ :long-name (format "RHP of %s (%s)" ,name ,nickname)
+ :iso-final-char ,iso-final
+ :emacs-mule-id ,emacs-mule-id
+ :code-space [32 127]
+ :parents (list (cons ,symbol 128))))))
+
+(define-iso-single-byte-charset 'iso-8859-2 'latin-iso8859-2
+ "ISO/IEC 8859/2" "Latin-2" 101 ?B 130 "8859-2")
+
+(define-iso-single-byte-charset 'iso-8859-3 'latin-iso8859-3
+ "ISO/IEC 8859/3" "Latin-3" 109 ?C 131 "8859-3")
+
+(define-iso-single-byte-charset 'iso-8859-4 'latin-iso8859-4
+ "ISO/IEC 8859/4" "Latin-4" 110 ?D 132 "8859-4")
+
+(define-iso-single-byte-charset 'iso-8859-5 'cyrillic-iso8859-5
+ "ISO/IEC 8859/5" "Latin/Cyrillic" 144 ?L 140 "8859-5")
+
+(define-iso-single-byte-charset 'iso-8859-6 'arabic-iso8859-6
+ "ISO/IEC 8859/6" "Latin/Arabic" 127 ?G 135 "8859-6")
+
+(define-iso-single-byte-charset 'iso-8859-7 'greek-iso8859-7
+ "ISO/IEC 8859/7" "Latin/Greek" 126 ?F 134 "8859-7")
+
+(define-iso-single-byte-charset 'iso-8859-8 'hebrew-iso8859-8
+ "ISO/IEC 8859/8" "Latin/Hebrew" 138 ?H 136 "8859-8")
+
+(define-iso-single-byte-charset 'iso-8859-9 'latin-iso8859-9
+ "ISO/IEC 8859/9" "Latin-5" 148 ?M 141 "8859-9")
+
+(define-iso-single-byte-charset 'iso-8859-13 'latin-iso8859-13
+ "ISO/IEC 8859/13" "Latin-7" nil nil nil "8859-13")
+
+(define-iso-single-byte-charset 'iso-8859-14 'latin-iso8859-14
+ "ISO/IEC 8859/14" "Latin-8" 199 ?_ 143 "8859-14")
+
+(define-iso-single-byte-charset 'iso-8859-15 'latin-iso8859-15
+ "ISO/IEC 8859/15" "Latin-9" 203 ?b 142 "8859-15")
+
+(define-charset 'thai-tis620
+ "TIS620.2533"
+ :short-name "TIS620.2533"
+ :iso-final-char ?T
+ :emacs-mule-id 133
+ :code-space [32 127]
+ :code-offset #x0E00)
+
+(define-charset 'tis620-2533
+ "TIS620.2533"
+ :short-name "TIS620.2533"
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :parents '(ascii eight-bit-control (thai-tis620 . -128)))
+
+(define-charset 'jisx0201
+ "JISX0201"
+ :short-name "JISX0201"
+ :long-name "JISX0201"
+ :code-space [33 254]
+ :map "jisx0201")
+
+(define-charset 'latin-jisx0201
+ "Roman Part of JISX0201.1976"
+ :short-name "JISX0201 Roman"
+ :long-name "Japanese Roman (JISX0201.1976)"
+ :iso-final-char ?J
+ :emacs-mule-id 138
+ :code-space [33 126]
+ :parents '(jisx0201))
+
+(define-charset 'katakana-jisx0201
+ "Katakana Part of JISX0201.1976"
+ :short-name "JISX0201 Katakana"
+ :long-name "Japanese Katakana (JISX0201.1976)"
+ :iso-final-char ?I
+ :emacs-mule-id 137
+ :code-space [33 126]
+ :parents '((jisx0201 . #x80)))
+
+(define-charset 'chinese-gb2312
+ "GB2312 Chinese simplified: ISO-IR-58"
+ :short-name "GB2312"
+ :long-name "GB2312: ISO-IR-58"
+ :iso-final-char ?A
+ :emacs-mule-id 145
+ :code-space [33 126 33 126]
+ :code-offset #x110000
+ :unify-map "gb2312-1980")
+
+(define-charset 'chinese-cns11643-1
+ "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"
+ :short-name "CNS11643-1"
+ :long-name "CNS11643-1 (Chinese traditional): ISO-IR-171"
+ :iso-final-char ?G
+ :emacs-mule-id 149
+ :code-space [33 126 33 126]
+ :code-offset #x114000
+ :unify-map "cns11643-1")
+
+(define-charset 'chinese-cns11643-2
+ "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"
+ :short-name "CNS11643-2"
+ :long-name "CNS11643-2 (Chinese traditional): ISO-IR-172"
+ :iso-final-char ?H
+ :emacs-mule-id 150
+ :code-space [33 126 33 126]
+ :code-offset #x118000
+ :unify-map "cns11643-2")
+
+(define-charset 'chinese-cns11643-3
+ "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"
+ :short-name "CNS11643-3"
+ :long-name "CNS11643-3 (Chinese traditional): ISO-IR-183"
+ :iso-final-char ?I
+ :code-space [33 126 33 126]
+ :emacs-mule-id 246
+ :code-offset #x11C000)
+
+(define-charset 'chinese-cns11643-4
+ "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"
+ :short-name "CNS11643-4"
+ :long-name "CNS11643-4 (Chinese traditional): ISO-IR-184"
+ :iso-final-char ?J
+ :emacs-mule-id 247
+ :code-space [33 126 33 126]
+ :code-offset #x120000)
+
+(define-charset 'chinese-cns11643-5
+ "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"
+ :short-name "CNS11643-5"
+ :long-name "CNS11643-5 (Chinese traditional): ISO-IR-185"
+ :iso-final-char ?K
+ :emacs-mule-id 248
+ :code-space [33 126 33 126]
+ :code-offset #x124000)
+
+(define-charset 'chinese-cns11643-6
+ "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"
+ :short-name "CNS11643-6"
+ :long-name "CNS11643-6 (Chinese traditional): ISO-IR-186"
+ :iso-final-char ?L
+ :emacs-mule-id 249
+ :code-space [33 126 33 126]
+ :code-offset #x128000)
+
+(define-charset 'chinese-cns11643-7
+ "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"
+ :short-name "CNS11643-7"
+ :long-name "CNS11643-7 (Chinese traditional): ISO-IR-187"
+ :iso-final-char ?M
+ :emacs-mule-id 250
+ :code-space [33 126 33 126]
+ :code-offset #x12C000)
+
+(define-charset 'big5
+ "Big5 (Chinese traditional)"
+ :short-name "Big5"
+ :long-name "Big5"
+ :code-space [#x40 #xFE #xA1 #xFE]
+ :code-offset #x130000
+ :unify-map "big5")
+
+(define-charset 'chinese-big5-1
+ "Frequentry used part (A141-C67E) of Big5 (Chinese traditional)"
+ :short-name "Big5 (Level-1)"
+ :long-name "Big5 (Level-1) A141-C67F"
+ :iso-final-char ?0
+ :emacs-mule-id 152
+ :code-space [#x21 #x7E #x21 #x7E]
+ :code-offset #x134000
+ :unify-map "big5-1")
+
+(define-charset 'chinese-big5-2
+ "Less frequentry used part (C940-FEFE) of Big5 (Chinese traditional)"
+ :short-name "Big5 (Level-2)"
+ :long-name "Big5 (Level-2) C940-FEFE"
+ :iso-final-char ?1
+ :emacs-mule-id 153
+ :code-space [#x21 #x7E #x21 #x7E]
+ :code-offset #x138000
+ :unify-map "big5-2")
+
+(define-charset 'japanese-jisx0208
+ "JISX0208.1983/1990 Japanese Kanji: ISO-IR-87"
+ :short-name "JISX0208"
+ :long-name "JISX0208.1983/1990 (Japanese): ISO-IR-87"
+ :iso-final-char ?B
+ :emacs-mule-id 146
+ :code-space [33 126 33 126]
+ :code-offset #x140000
+ :unify-map "jisx0208-1990")
+
+(define-charset 'japanese-jisx0208-1978
+ "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"
+ :short-name "JISX0208.1978"
+ :long-name "JISX0208.1978 (Japanese): ISO-IR-42"
+ :iso-final-char ?@
+ :emacs-mule-id 144
+ :code-space [33 126 33 126]
+ :code-offset #x144000
+ :unify-map "jisx0208-1978")
+
+(define-charset 'japanese-jisx0212
+ "JISX0212 Japanese supplement: ISO-IR-159"
+ :short-name "JISX0212"
+ :long-name "JISX0212 (Japanese): ISO-IR-159"
+ :iso-final-char ?D
+ :emacs-mule-id 148
+ :code-space [33 126 33 126]
+ :code-offset #x148000
+ :unify-map "jisx0212-1990")
+
+(define-charset 'japanese-jisx0213-1
+ "JISX0213 Plane 1 (Japanese)"
+ :short-name "JISX0213-1"
+ :long-name "JISX0213-1"
+ :iso-final-char ?O
+ :emacs-mule-id 151
+ :code-space [33 126 33 126]
+ :code-offset #x14C000)
+
+(define-charset 'japanese-jisx0213-2
+ "JISX0213 Plane 2 (Japanese)"
+ :short-name "JISX0213-2"
+ :long-name "JISX0213-2"
+ :iso-final-char ?P
+ :emacs-mule-id 254
+ :code-space [33 126 33 126]
+ :code-offset #x150000)
+
+(define-charset 'korean-ksc5601
+ "KSC5601 Korean Hangul and Hanja: ISO-IR-149"
+ :short-name "KSC5601"
+ :long-name "KSC5601 (Korean): ISO-IR-149"
+ :iso-final-char ?C
+ :emacs-mule-id 147
+ :code-space [33 126 33 126]
+ :map "ksc5601-1987")
+
+(define-charset 'chinese-sisheng
+ "SiSheng characters for PinYin/ZhuYin"
+ :short-name "SiSheng"
+ :long-name "SiSheng (PinYin/ZhuYin)"
+ :iso-final-char ?0
+ :emacs-mule-id 160
+ :code-space [33 126]
+ :code-offset #x200000)
+
+(define-charset 'ipa
+ "IPA (International Phonetic Association)"
+ :short-name "IPA"
+ :long-name "IPA"
+ :iso-final-char ?0
+ :emacs-mule-id 161
+ :code-space [32 127]
+ :code-offset #x200080)
+
+(define-charset 'viscii
+ "VISCII1.1"
+ :short-name "VISCII"
+ :long-name "VISCII 1.1"
+ :code-space [0 255]
+ :map "viscii")
+
+(define-charset 'vietnamese-viscii-lower
+ "VISCII1.1 lower-case"
+ :short-name "VISCII lower"
+ :long-name "VISCII lower-case"
+ :iso-final-char ?1
+ :emacs-mule-id 162
+ :code-space [32 127]
+ :map "viscii-lower")
+
+(define-charset 'vietnamese-viscii-upper
+ "VISCII1.1 upper-case"
+ :short-name "VISCII upper"
+ :long-name "VISCII upper-case"
+ :iso-final-char ?2
+ :emacs-mule-id 163
+ :code-space [32 127]
+ :map "viscii-upper")
+
+(define-charset 'vscii
+ "VSCII1.1"
+ :short-name "VSCII"
+ :long-name "VSCII"
+ :code-space [0 255]
+ :map "vscii")
+
+(define-charset 'koi8-r
+ "KOI8-R"
+ :short-name "KOI8-R"
+ :long-name "KOI8-R"
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :map "koi8-r")
+
+(define-charset-alias 'koi8 'koi8-r)
+
+(define-charset 'alternativnyj
+ "ALTERNATIVNYJ"
+ :short-name "alternativnyj"
+ :long-name "alternativnyj"
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :map "ibm866")
;; For Arabic, we need three different types of character sets.
;; Digits are of direction left-to-right and of width 1-column.
;; Others are of direction right-to-left and of width 1-column or
;; 2-column.
-(define-charset 164 'arabic-digit
- [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit"
- "Arabic digits."])
-(define-charset 165 'arabic-1-column
- [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column"
- "Arabic 1-column width glyphs."])
-
-;; ASCII with right-to-left direction.
-(define-charset 166 'ascii-right-to-left
- [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction"
- "ASCII (left half of ISO 8859-1) with right-to-left direction."])
+(define-charset 'arabic-digit
+ "Arabic digit"
+ :short-name "Arabic digit"
+ :long-name "Arabic digit"
+ :iso-final-char ?2
+ :emacs-mule-id 164
+ :code-space [34 42]
+ :code-offset #x0600)
+
+(define-charset 'arabic-1-column
+ "Arabic 1-column"
+ :short-name "Arabic 1-col"
+ :long-name "Arabic 1-column"
+ :iso-final-char ?3
+ :emacs-mule-id 165
+ :code-space [33 126]
+ :code-offset #x200100)
+
+(define-charset 'arabic-2-column
+ "Arabic 2-column"
+ :short-name "Arabic 2-col"
+ :long-name "Arabic 2-column"
+ :iso-final-char ?4
+ :emacs-mule-id 224
+ :code-space [33 126]
+ :code-offset #x200180)
;; Lao script.
-;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F.
-(define-charset 167 'lao
- [1 94 1 0 ?1 0 "Lao" "Lao"
- "Lao characters (U+0E80..U+0EDF)."])
+;; Codes 0x21..0x7E are mapped to Unicode U+0E81..U+0EDF.
+(define-charset 'lao
+ "Lao characters (ISO10646 0E81..0EDF)"
+ :short-name "Lao"
+ :long-name "Lao"
+ :iso-final-char ?1
+ :emacs-mule-id 167
+ :code-space [33 126]
+ :code-offset #x0E81)
+
+(define-charset 'mule-lao
+ "Lao characters (ISO10646 0E81..0EDF)"
+ :short-name "Lao"
+ :long-name "Lao"
+ :code-space [0 255]
+ :parents '(ascii eight-bit-control (lao . -128)))
-;; CHARSET-IDs 168..223 are not used.
-
-;; 1-byte 2-column charsets. Valid range of CHARSET-ID is 224..239.
-
-(define-charset 224 'arabic-2-column
- [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column"
- "Arabic 2-column glyphs."])
;; Indian scripts. Symbolic charset for data exchange. Glyphs are
;; not assigned. They are automatically converted to each Indian
;; script which IS-13194 supports.
-(define-charset 225 'indian-is13194
- [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194"
- "Generic Indian character set for data exchange with IS 13194."])
-
-;; CHARSET-IDs 226..239 are not used.
-
-(define-charset 240 'indian-glyph
- [2 96 1 0 ?4 0 "Indian glyph" "Indian glyph"
- "Glyphs for Indian characters."])
-;; 240 used to be [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column"]
-
-;; 2-byte 1-column charsets. Valid range of CHARSET-ID is 240..244.
+(define-charset 'indian-is13194
+ "Generic Indian charset for data exchange with IS 13194"
+ :short-name "IS 13194"
+ :long-name "Indian IS 13194"
+ :iso-final-char ?5
+ :emacs-mule-id 225
+ :code-space [33 126]
+ :code-offset #x180000)
+
+(define-charset 'indian-glyph
+ "Glyphs for Indian characters."
+ :short-name "Indian glyph"
+ :long-name "Indian glyph"
+ :iso-final-char ?4
+ :emacs-mule-id 240
+ :code-space [32 127 32 127]
+ :code-offset #x180100)
;; Actual Glyph for 1-column width.
-(define-charset 241 'tibetan-1-column
- [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column"
- "Tibetan 1-column glyphs."])
-
-;; Subsets of Unicode.
-
-(define-charset 242 'mule-unicode-2500-33ff
- [2 96 1 0 ?2 0 "Unicode subset 2" "Unicode subset (U+2500..U+33FF)"
- "Unicode characters of the range U+2500..U+33FF."])
-
-(define-charset 243 'mule-unicode-e000-ffff
- [2 96 1 0 ?3 0 "Unicode subset 3" "Unicode subset (U+E000+FFFF)"
- "Unicode characters of the range U+E000..U+FFFF."])
-
-(define-charset 244 'mule-unicode-0100-24ff
- [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)"
- "Unicode characters of the range U+0100..U+24FF."])
-
-;; 2-byte 2-column charsets. Valid range of CHARSET-ID is 245..254.
-
-;; Ethiopic characters (Amahric and Tigrigna).
-(define-charset 245 'ethiopic
- [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters"
- "Ethiopic characters."])
-
-;; Chinese CNS11643 Plane3 thru Plane7. Although these are official
-;; character sets, the use is rare and don't have to be treated
-;; space-efficiently in the buffer.
-(define-charset 246 'chinese-cns11643-3
- [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183"
- "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183."])
-(define-charset 247 'chinese-cns11643-4
- [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184"
- "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184."])
-(define-charset 248 'chinese-cns11643-5
- [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185"
- "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185."])
-(define-charset 249 'chinese-cns11643-6
- [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186"
- "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186."])
-(define-charset 250 'chinese-cns11643-7
- [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187"
- "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187."])
+(define-charset 'indian-1-column
+ "Indian charset for 1-column width glyphs"
+ :short-name "Indian 1-col"
+ :long-name "Indian 1 Column"
+ :iso-final-char ?6
+ :emacs-mule-id 240
+ :code-space [33 126 33 126]
+ :code-offset #x184000)
;; Actual Glyph for 2-column width.
-(define-charset 251 'indian-2-column
- [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column"
- "Indian character set for 2-column width glyphs."])
- ;; old indian-1-column characters will be translated to indian-2-column.
-(declare-equiv-charset 2 94 ?6 'indian-2-column)
-
-;; Tibetan script.
-(define-charset 252 'tibetan
- [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column"
- "Tibetan 2-column width glyphs."])
-
-;; CHARSET-ID 253 is not used.
-
-;; JISX0213 Plane 2
-(define-charset 254 'japanese-jisx0213-2
- [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2"
- "JISX0213 Plane 2 (Japanese)."])
-
-;; Tell C code charset ID's of several charsets.
-(setup-special-charsets)
+(define-charset 'indian-2-column
+ "Indian charset for 2-column width glyphs"
+ :short-name "Indian 2-col"
+ :long-name "Indian 2 Column"
+ :iso-final-char ?5
+ :emacs-mule-id 251
+ :code-space [33 126 33 126]
+ :parents '(indian-1-column))
+
+(define-charset 'tibetan
+ "Tibetan characters"
+ :iso-final-char ?7
+ :short-name "Tibetan 2-col"
+ :long-name "Tibetan 2 column"
+ :iso-final-char ?7
+ :emacs-mule-id 252
+ :code-space [33 126 33 126]
+ :code-offset #x190000)
+
+(define-charset 'tibetan-1-column
+ "Tibetan 1 column glyph"
+ :short-name "Tibetan 1-col"
+ :long-name "Tibetan 1 column"
+ :iso-final-char ?8
+ :emacs-mule-id 241
+ :code-space [33 126 33 37]
+ :parents '(tibetan))
+;; Subsets of Unicode.
+(define-charset 'mule-unicode-2500-33ff
+ "Unicode characters of the range U+2500..U+33FF."
+ :short-name "Unicode subset 2"
+ :long-name "Unicode subset (U+2500..U+33FF)"
+ :iso-final-char ?2
+ :emacs-mule-id 242
+ :code-space [#x20 #x7f #x20 #x47]
+ :code-offset #x2500)
+
+(define-charset 'mule-unicode-e000-ffff
+ "Unicode characters of the range U+E000..U+FFFF."
+ :short-name "Unicode subset 3"
+ :long-name "Unicode subset (U+E000+FFFF)"
+ :iso-final-char ?3
+ :emacs-mule-id 243
+ :code-space [#x20 #x7F #x20 #x75]
+ :code-offset #xE000)
+
+(define-charset 'mule-unicode-0100-24ff
+ "Unicode characters of the range U+0100..U+24FF."
+ :short-name "Unicode subset"
+ :long-name "Unicode subset (U+0100..U+24FF)"
+ :iso-final-char ?1
+ :emacs-mule-id 244
+ :code-space [#x20 #x7F #x20 #x7F]
+ :code-offset #x100)
+
+(define-charset 'ethiopic
+ "Ethiopic characters for Amahric and Tigrigna."
+ :short-name "Ethiopic"
+ :long-name "Ethiopic characters"
+ :iso-final-char ?3
+ :emacs-mule-id 245
+ :code-space [33 126 33 126]
+ :code-offset #x1A0000)
+
+(define-charset 'mac-roman
+ "Mac Roman charset"
+ :short-name "Mac Roman"
+ :long-name "Mac Roman"
+ :ascii-compatible-p t
+ :code-space [0 255]
+ :map "mac-roman")
+
+(unify-charset 'chinese-gb2312)
+(unify-charset 'chinese-cns11643-1)
+(unify-charset 'chinese-cns11643-2)
+(unify-charset 'big5)
+(unify-charset 'chinese-big5-1)
+(unify-charset 'chinese-big5-2)
\f
;; These are tables for translating characters on decoding and
;; encoding.
-(define-translation-table
- 'oldjis-newjis-jisroman-ascii
- (list (cons (make-char 'japanese-jisx0208-1978)
- (make-char 'japanese-jisx0208))
- (cons (make-char 'latin-jisx0201) (make-char 'ascii))))
-(aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
- (make-char 'latin-jisx0201 92) (make-char 'latin-jisx0201 92))
-(aset (get 'oldjis-newjis-jisroman-ascii 'translation-table)
- (make-char 'latin-jisx0201 126) (make-char 'latin-jisx0201 126))
-
-(setq standard-translation-table-for-decode
- (get 'oldjis-newjis-jisroman-ascii 'translation-table))
+(setq standard-translation-table-for-decode nil)
(setq standard-translation-table-for-encode nil)
\f
;;; Make fundamental coding systems.
-;; Miscellaneous coding systems which can't be made by
-;; `make-coding-system'.
+;; The coding system `no-conversion' is already defined in coding.c as
+;; below:
+;;
+;; (define-coding-system 'no-conversion
+;; "Do no conversion."
+;; :coding-type 'raw-text
+;; :mnemonic ?=)
-(put 'no-conversion 'coding-system
- (vector nil ?= "Do no conversion.
+(define-coding-system 'raw-text
+ "Raw text, which means text contains random 8-bit codes.
+Encoding text with this coding system produces the actual byte
+sequence of the text in buffers and strings. An exception is made for
+eight-bit-control characters. Each of them is encoded into a single
+byte.
When you visit a file with this coding, the file is read into a
-unibyte buffer as is, thus each byte of a file is treated as a
-character."
- (list 'coding-category 'coding-category-binary
- 'alias-coding-systems '(no-conversion))
- nil))
-(put 'no-conversion 'eol-type 0)
-(put 'coding-category-binary 'coding-systems '(no-conversion))
-(setq coding-system-list '(no-conversion))
-(setq coding-system-alist '(("no-conversion")))
-(register-char-codings 'no-conversion t)
-
-(define-coding-system-alias 'binary 'no-conversion)
-
-(put 'undecided 'coding-system
- (vector t ?- "No conversion on encoding, automatic conversion on decoding"
- (list 'alias-coding-systems '(undecided)
- 'safe-charsets '(ascii))
- nil))
-(setq coding-system-list (cons 'undecided coding-system-list))
-(setq coding-system-alist (cons '("undecided") coding-system-alist))
-(put 'undecided 'eol-type
- (make-subsidiary-coding-system 'undecided))
+unibyte buffer as is (except for EOL format), thus each byte of a file
+is treated as a character."
+ :coding-type 'raw-text
+ :mnemonic ?t)
+
+(define-coding-system 'undecided
+ "No conversion on encoding, automatic conversion on decoding"
+ :coding-type 'undecided
+ :mnemonic ?-
+ :charset-list '(ascii))
(define-coding-system-alias 'unix 'undecided-unix)
(define-coding-system-alias 'dos 'undecided-dos)
(define-coding-system-alias 'mac 'undecided-mac)
-;; Coding systems not specific to each language environment.
-
-(make-coding-system
- 'emacs-mule 0 ?=
- "Emacs internal format used in buffer and string.
+(define-coding-system 'iso-latin-1
+ "ISO 2022 based 8-bit encoding for Latin-1 (MIME:ISO-8859-1)."
+ :coding-type 'iso-2022
+ :mnemonic ?1
+ :charset-list '(ascii latin-iso8859-1)
+ :designation [ascii latin-iso8859-1 nil nil]
+ :mime-charset 'iso-8859-1)
-Encoding text with this coding system produces the actual byte
-sequence of the text in buffers and strings. An exception is made for
-eight-bit-control characters. Each of them is encoded into a single
-byte."
- nil
- '((safe-charsets . t)))
+(define-coding-system-alias 'iso-8859-1 'iso-latin-1)
+(define-coding-system-alias 'latin-1 'iso-latin-1)
-(make-coding-system
- 'raw-text 5 ?t
- "Raw text, which means text contains random 8-bit codes.
-Encoding text with this coding system produces the actual byte
-sequence of the text in buffers and strings. An exception is made for
-eight-bit-control characters. Each of them is encoded into a single
-byte.
+;; Coding systems not specific to each language environment.
-When you visit a file with this coding, the file is read into a
-unibyte buffer as is (except for EOL format), thus each byte of a file
-is treated as a character."
- nil
- '((safe-charsets . t)))
-
-(make-coding-system
- 'iso-2022-7bit 2 ?J
- "ISO 2022 based 7-bit encoding using only G0"
- '((ascii t) nil nil nil
- short ascii-eol ascii-cntl seven)
- '((safe-charsets . t)
- (composition . t)))
-
-(make-coding-system
- 'iso-2022-7bit-ss2 2 ?$
- "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
- '((ascii t) nil t nil
- short ascii-eol ascii-cntl seven nil single-shift)
- '((safe-charsets . t)
- (composition . t)))
-
-(make-coding-system
- 'iso-2022-7bit-lock 2 ?&
- "ISO-2022 coding system using Locking-Shift for 96-charset"
- '((ascii t) t nil nil
- nil ascii-eol ascii-cntl seven locking-shift)
- '((safe-charsets . t)
- (composition . t)))
+(define-coding-system 'emacs-mule
+ "Emacs 21 internal format used in buffer and string."
+ :coding-type 'emacs-mule
+ :mnemonic ?M)
+
+(define-coding-system 'utf-8
+ "UTF-8."
+ :coding-type 'utf-8
+ :mnemonic ?U
+ :charset-list '(unicode))
+
+(define-coding-system-alias 'mule-utf-8 'utf-8)
+
+(define-coding-system 'utf-8-emacs
+ "UTF-8 will full support for Emacs characters."
+ :coding-type 'utf-8
+ :mnemonic ?U
+ :charset-list '(emacs))
+
+(define-coding-system 'utf-16
+ "UTF-16"
+ :coding-type 'utf-16
+ :mnemonic ?U
+ :charset-list '(unicode))
+
+(define-coding-system 'utf-16-le-nosig
+ "UTF-16, little endian, no signature"
+ :coding-type 'utf-16
+ :mnemonic ?U
+ :charset-list '(unicode)
+ :endian 'little)
+
+(define-coding-system 'utf-16-be-nosig
+ "UTF-16, big endian, no signature"
+ :coding-type 'utf-16
+ :mnemonic ?U
+ :charset-list '(unicode)
+ :endian 'big)
+
+(define-coding-system 'utf-16-le
+ "UTF-16, little endian, with signature"
+ :coding-type 'utf-16
+ :mnemonic ?U
+ :charset-list '(unicode)
+ :signature t
+ :endian 'little)
+
+(define-coding-system 'utf-16-be
+ "UTF-16, big endian, with signature"
+ :coding-type 'utf-16
+ :mnemonic ?U
+ :charset-list '(unicode)
+ :signature t
+ :endian 'big)
+
+(define-coding-system 'iso-2022-7bit
+ "ISO 2022 based 7-bit encoding using only G0"
+ :coding-type 'iso-2022
+ :mnemonic ?J
+ :charset-list 'iso-2022
+ :designation [(ascii t) nil nil nil]
+ :flags '(short ascii-at-eol ascii-at-cntl 7-bit designation composition))
+
+(define-coding-system 'iso-2022-7bit-ss2
+ "ISO 2022 based 7-bit encoding using SS2 for 96-charset"
+ :coding-type 'iso-2022
+ :mnemonic ?$
+ :charset-list 'iso-2022
+ :designation [(ascii 94) nil (nil 96) nil]
+ :flags '(short ascii-at-eol ascii-at-cntl 7-bit
+ designation single-shift composition))
+
+(define-coding-system 'iso-2022-7bit-lock
+ "ISO-2022 coding system using Locking-Shift for 96-charset"
+ :coding-type 'iso-2022
+ :mnemonic ?&
+ :charset-list 'iso-2022
+ :designation [(ascii 94) (nil 96) nil nil]
+ :flags '(ascii-at-eol ascii-at-cntl 7-bit
+ designation locking-shift composition))
(define-coding-system-alias 'iso-2022-int-1 'iso-2022-7bit-lock)
-(make-coding-system
- 'iso-2022-7bit-lock-ss2 2 ?i
- "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
- '((ascii t)
- (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 t)
- (nil chinese-cns11643-2)
- (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
- chinese-cns11643-6 chinese-cns11643-7)
- short ascii-eol ascii-cntl seven locking-shift single-shift nil nil nil
- init-bol)
- '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
- korean-ksc5601 chinese-gb2312 chinese-cns11643-1
- chinese-cns11643-2 chinese-cns11643-3 chinese-cns11643-4
- chinese-cns11643-5 chinese-cns11643-6 chinese-cns11643-7)
- (composition . t)))
+(define-coding-system 'iso-2022-7bit-lock-ss2
+ "Mixture of ISO-2022-JP, ISO-2022-KR, and ISO-2022-CN"
+ :coding-type 'iso-2022
+ :mnemonic ?i
+ :charset-list '(ascii
+ japanese-jisx0208 japanese-jisx0208-1978 latin-jisx0201
+ korean-ksc5601
+ chinese-gb2312
+ chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
+ chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
+ chinese-cns11643-7)
+ :designation [(ascii 94)
+ (nil korean-ksc5601 chinese-gb2312 chinese-cns11643-1 96)
+ (nil chinese-cns11643-2)
+ (nil chinese-cns11643-3 chinese-cns11643-4 chinese-cns11643-5
+ chinese-cns11643-6 chinese-cns11643-7)]
+ :flags '(short ascii-at-eol ascii-at-cntl 7-bit locking-shift
+ single-shift init-bol))
(define-coding-system-alias 'iso-2022-cjk 'iso-2022-7bit-lock-ss2)
-(make-coding-system
- 'iso-2022-8bit-ss2 2 ?@
- "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
- '((ascii t) nil t nil
- nil ascii-eol ascii-cntl nil nil single-shift)
- '((safe-charsets . t)
- (composition . t)))
+(define-coding-system 'iso-2022-8bit-ss2
+ "ISO 2022 based 8-bit encoding using SS2 for 96-charset"
+ :coding-type 'iso-2022
+ :mnemonic ?@
+ :charset-list 'iso-2022
+ :designation [(ascii 94) nil (nil 96) nil]
+ :flags '(ascii-at-eol ascii-at-cntl designation single-shift composition))
-(make-coding-system
- 'compound-text 2 ?x
- "Compound text based generic encoding for decoding unknown messages.
+(define-coding-system 'compound-text
+ "Compound text based generic encoding for decoding unknown messages.
This coding system does not support ICCCM Extended Segments."
- '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
- nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
- init-bol nil nil)
- '((safe-charsets . t)
- (mime-charset . x-ctext)
- (composition . t)))
+ :coding-type 'iso-2022
+ :mnemonic ?x
+ :charset-list 'iso-2022
+ :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
+ :flags '(ascii-at-eol ascii-at-cntl
+ designation locking-shift single-shift composition)
+ :mime-charset 'x-ctext)
(define-coding-system-alias 'x-ctext 'compound-text)
(define-coding-system-alias 'ctext 'compound-text)
;; compound-text-with-extensions, see mule.el. Note that this should
;; not have a mime-charset property, to prevent it from showing up
;; close to the beginning of coding systems ordered by priority.
-(make-coding-system
- 'ctext-no-compositions 2 ?x
+(define-coding-system 'ctext-no-compositions 2 ?x
"Compound text based generic encoding for decoding unknown messages.
Like `compound-text', but does not produce escape sequences for compositions."
- '((ascii t) (latin-iso8859-1 katakana-jisx0201 t) t t
- nil ascii-eol ascii-cntl nil locking-shift single-shift nil nil nil
- init-bol nil nil)
- '((safe-charsets . t)))
-
-(make-coding-system
- 'compound-text-with-extensions 5 ?x
+ :coding-type 'iso-2022
+ :mnemonic ?x
+ :charset-list 'iso-2022
+ :designation [(ascii 94) (latin-iso8859-1 katakana-jisx0201 96) nil nil]
+ :flags '(ascii-at-eol ascii-at-cntl
+ designation locking-shift single-shift))
+
+(define-coding-system 'compound-text-with-extensions
"Compound text encoding with ICCCM Extended Segment extensions.
This coding system should be used only for X selections. It is inappropriate
for decoding and encoding files, process I/O, etc."
- nil
- '((post-read-conversion . ctext-post-read-conversion)
- (pre-write-conversion . ctext-pre-write-conversion)))
+ :coding-type 'raw-text
+ :mnemonic ?x
+ :post-read-conversion 'ctext-post-read-conversion
+ :pre-write-conversion 'ctext-pre-write-conversion)
(define-coding-system-alias
'x-ctext-with-extensions 'compound-text-with-extensions)
(define-coding-system-alias
'ctext-with-extensions 'compound-text-with-extensions)
-(make-coding-system
- 'iso-safe 2 ?-
- "Convert all characters but ASCII to `?'."
- '(ascii nil nil nil
- nil ascii-eol ascii-cntl nil nil nil nil nil nil nil nil t)
- '((safe-charsets ascii)))
+(define-coding-system 'us-ascii
+ "Convert all characters but ASCII to `?'."
+ :coding-type 'charset
+ :mnemonic ?-
+ :charset-list '(ascii)
+ :default-char ??
+ :mime-charset 'us-ascii)
+
+(define-coding-system-alias 'iso-safe 'us-ascii)
-;; Use iso-safe for terminal output if some other coding system is not
+;; Use us-ascii for terminal output if some other coding system is not
;; specified explicitly.
-(set-safe-terminal-coding-system-internal 'iso-safe)
+(set-safe-terminal-coding-system-internal 'us-ascii)
;; The other coding-systems are defined in each language specific
-;; section of languages.el.
+;; files under lisp/language.
;; Normally, set coding system to `undecided' before reading a file.
;; Compiled Emacs Lisp files (*.elc) are not decoded at all,
;; values are set by the command `set-language-environment' for each
;; language environment.
-(setq coding-category-emacs-mule 'emacs-mule
- coding-category-sjis 'japanese-shift-jis
- coding-category-iso-7 'iso-2022-7bit
- coding-category-iso-7-tight 'iso-2022-jp
- coding-category-iso-8-1 'iso-latin-1
- coding-category-iso-8-2 'iso-latin-1
- coding-category-iso-7-else 'iso-2022-7bit-lock
- coding-category-iso-8-else 'iso-2022-8bit-ss2
- coding-category-ccl nil
- coding-category-utf-8 'mule-utf-8
- coding-category-utf-16-be nil
- coding-category-utf-16-le nil
- coding-category-big5 'chinese-big5
- coding-category-raw-text 'raw-text
- coding-category-binary 'no-conversion)
-
-(set-coding-priority
- '(coding-category-iso-8-1
- coding-category-iso-8-2
- coding-category-iso-7-tight
- coding-category-iso-7
- coding-category-iso-7-else
- coding-category-iso-8-else
- coding-category-emacs-mule
- coding-category-raw-text
- coding-category-sjis
- coding-category-big5
- coding-category-ccl
- coding-category-binary
- coding-category-utf-8
- coding-category-utf-16-be
- coding-category-utf-16-le))
+(set-coding-system-priority
+ 'iso-latin-1
+ 'utf-8
+ 'iso-2022-7bit
+ )
\f
;;; Miscellaneous settings.
-(aset latin-extra-code-table ?\222 t)
-(aset latin-extra-code-table ?\223 t)
-(aset latin-extra-code-table ?\224 t)
-(update-coding-systems-internal)
+;; Make all multibyte characters self-insert.
+(set-char-table-range (nth 1 global-map)
+ (cons (make-char 'unicode 128) (max-char))
+ 'self-insert-command)
+
+(aset latin-extra-code-table ?\222 t)
;;; mule-conf.el ends here
projects / emacs.git / commitdiff