Mercurial > emacs
comparison lisp/international/mule-conf.el @ 29167:7b645b883dcb
Specify CHARSET-ID explicitely for private charsets.
(mule-unicode-0100-24ff, japanese-jisx0213-1,
japanese-jisx0213-2): New charsets.
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Thu, 25 May 2000 01:25:16 +0000 |
parents | f23c3e4e8a31 |
children | 4711a63436ee |
comparison
equal
deleted
inserted
replaced
29166:dc6d60c27c31 | 29167:7b645b883dcb |
---|---|
38 ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE | 38 ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE |
39 ;; SHORT-NAME LONG-NAME DESCRIPTION ]) | 39 ;; SHORT-NAME LONG-NAME DESCRIPTION ]) |
40 ;; ASCII charset is defined in src/charset.c as below. | 40 ;; ASCII charset is defined in src/charset.c as below. |
41 ;; (define-charset 0 ascii | 41 ;; (define-charset 0 ascii |
42 ;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"]) | 42 ;; [1 94 1 0 ?B 0 "ASCII" "ASCII" "ASCII (ISO646 IRV)"]) |
43 | |
44 ;; 1-byte charsets. Valid range of CHARSET-ID is 128..143. | |
45 | |
46 ;; CHARSET-ID 128 is not used. | |
43 | 47 |
44 (define-charset 129 'latin-iso8859-1 | 48 (define-charset 129 'latin-iso8859-1 |
45 [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100" | 49 [1 96 1 0 ?A 1 "RHP of Latin-1" "RHP of Latin-1 (ISO 8859-1): ISO-IR-100" |
46 "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"]) | 50 "Right-Hand Part of Latin Alphabet 1 (ISO/IEC 8859-1): ISO-IR-100"]) |
47 (define-charset 130 'latin-iso8859-2 | 51 (define-charset 130 'latin-iso8859-2 |
69 [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)" | 73 [1 94 1 0 ?I 1 "JISX0201 Katakana" "Japanese Katakana (JISX0201.1976)" |
70 "Katakana Part of JISX0201.1976"]) | 74 "Katakana Part of JISX0201.1976"]) |
71 (define-charset 138 'latin-jisx0201 | 75 (define-charset 138 'latin-jisx0201 |
72 [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)" | 76 [1 94 1 0 ?J 0 "JISX0201 Roman" "Japanese Roman (JISX0201.1976)" |
73 "Roman Part of JISX0201.1976"]) | 77 "Roman Part of JISX0201.1976"]) |
78 | |
79 ;; CHARSET-ID is not used 139. | |
80 | |
74 (define-charset 140 'cyrillic-iso8859-5 | 81 (define-charset 140 'cyrillic-iso8859-5 |
75 [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144" | 82 [1 96 1 0 ?L 1 "RHP of ISO8859/5" "RHP of Cyrillic (ISO 8859-5): ISO-IR-144" |
76 "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144"]) | 83 "Right-Hand Part of Latin/Cyrillic Alphabet (ISO/IEC 8859-5): ISO-IR-144"]) |
77 (define-charset 141 'latin-iso8859-9 | 84 (define-charset 141 'latin-iso8859-9 |
78 [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148" | 85 [1 96 1 0 ?M 1 "RHP of Latin-5" "RHP of Latin-5 (ISO 8859-9): ISO-IR-148" |
81 [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203" | 88 [1 96 1 0 ?b 1 "RHP of Latin-9" "RHP of Latin-9 (ISO 8859-15): ISO-IR-203" |
82 "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"]) | 89 "Right-Hand Part of Latin Alphabet 9 (ISO/IEC 8859-15): ISO-IR-203"]) |
83 (define-charset 143 'latin-iso8859-14 | 90 (define-charset 143 'latin-iso8859-14 |
84 [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14)" | 91 [1 96 1 0 ?_ 1 "RHP of Latin-8" "RHP of Latin-8 (ISO 8859-14)" |
85 "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"]) | 92 "Right-Hand Part of Latin Alphabet 8 (ISO/IEC 8859-14)"]) |
93 | |
94 ;; 2-byte charsets. Valid range of CHARSET-ID is 144..153. | |
95 | |
86 (define-charset 144 'japanese-jisx0208-1978 | 96 (define-charset 144 'japanese-jisx0208-1978 |
87 [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42" | 97 [2 94 2 0 ?@ 0 "JISX0208.1978" "JISX0208.1978 (Japanese): ISO-IR-42" |
88 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"]) | 98 "JISX0208.1978 Japanese Kanji (so called \"old JIS\"): ISO-IR-42"]) |
89 (define-charset 145 'chinese-gb2312 | 99 (define-charset 145 'chinese-gb2312 |
90 [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58" | 100 [2 94 2 0 ?A 0 "GB2312" "GB2312: ISO-IR-58" |
102 [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171" | 112 [2 94 2 0 ?G 0 "CNS11643-1" "CNS11643-1 (Chinese traditional): ISO-IR-171" |
103 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"]) | 113 "CNS11643 Plane 1 Chinese traditional: ISO-IR-171"]) |
104 (define-charset 150 'chinese-cns11643-2 | 114 (define-charset 150 'chinese-cns11643-2 |
105 [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172" | 115 [2 94 2 0 ?H 0 "CNS11643-2" "CNS11643-2 (Chinese traditional): ISO-IR-172" |
106 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"]) | 116 "CNS11643 Plane 2 Chinese traditional: ISO-IR-172"]) |
117 (define-charset 151 'japanese-jisx0213-1 | |
118 [2 94 2 0 ?O 0 "JISX0213-1" "JISX0213-1" "JISX0213 Plane 1 (Japanese)"]) | |
107 (define-charset 152 'chinese-big5-1 | 119 (define-charset 152 'chinese-big5-1 |
108 [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F" | 120 [2 94 2 0 ?0 0 "Big5 (Level-1)" "Big5 (Level-1) A141-C67F" |
109 "Frequentry used part (A141-C67F) of Big5 (Chinese traditional)"]) | 121 "Frequentry used part (A141-C67F) of Big5 (Chinese traditional)"]) |
110 (define-charset 153 'chinese-big5-2 | 122 (define-charset 153 'chinese-big5-2 |
111 [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE" | 123 [2 94 2 0 ?1 0 "Big5 (Level-2)" "Big5 (Level-2) C940-FEFE" |
113 | 125 |
114 ;; Additional (private) character sets. These character sets are | 126 ;; Additional (private) character sets. These character sets are |
115 ;; treated less space-efficiently in the buffer. | 127 ;; treated less space-efficiently in the buffer. |
116 | 128 |
117 ;; Syntax: | 129 ;; Syntax: |
118 ;; (define-charset nil CHARSET | 130 ;; (define-charset CHARSET-ID CHARSET |
119 ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE | 131 ;; [ DIMENSION CHARS WIDTH DIRECTION ISO-FINAL-CHAR ISO-GRAPHIC-PLANE |
120 ;; SHORT-NAME LONG-NAME DESCRIPTION ]) | 132 ;; SHORT-NAME LONG-NAME DESCRIPTION ]) |
121 | 133 |
122 ;; ISO-2022 allows a use of character sets not registered in ISO with | 134 ;; ISO-2022 allows a use of character sets not registered in ISO with |
123 ;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs | 135 ;; final characters `0' (0x30) through `?' (0x3F). Among them, Emacs |
124 ;; reserves `0' through `9' to support several private character sets. | 136 ;; reserves `0' through `9' to support several private character sets. |
125 ;; The remaining final characters `:' through `?' are for users. | 137 ;; The remaining final characters `:' through `?' are for users. |
126 | 138 |
127 (define-charset nil 'chinese-sisheng | 139 ;; 1-byte 1-column charsets. Valid range of CHARSET-ID is 160..223. |
140 | |
141 (define-charset 160 'chinese-sisheng | |
128 [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)" | 142 [1 94 1 0 ?0 0 "SiSheng" "SiSheng (PinYin/ZhuYin)" |
129 "SiSheng characters for PinYin/ZhuYin"]) | 143 "SiSheng characters for PinYin/ZhuYin"]) |
130 | 144 |
131 ;; IPA characters for phonetic symbols. | 145 ;; IPA characters for phonetic symbols. |
132 (define-charset nil 'ipa | 146 (define-charset 161 'ipa |
133 [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"]) | 147 [1 96 1 0 ?0 1 "IPA" "IPA" "IPA (International Phonetic Association)"]) |
134 | 148 |
135 ;; Vietnamese VISCII. VISCII is 1-byte character set which contains | 149 ;; Vietnamese VISCII. VISCII is 1-byte character set which contains |
136 ;; more than 96 characters. Since Emacs can't handle it as one | 150 ;; more than 96 characters. Since Emacs can't handle it as one |
137 ;; character set, it is divided into two: lower case letters and upper | 151 ;; character set, it is divided into two: lower case letters and upper |
138 ;; case letters. | 152 ;; case letters. |
139 (define-charset nil 'vietnamese-viscii-lower | 153 (define-charset 162 'vietnamese-viscii-lower |
140 [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"]) | 154 [1 96 1 0 ?1 1 "VISCII lower" "VISCII lower-case" "VISCII1.1 lower-case"]) |
141 (define-charset nil 'vietnamese-viscii-upper | 155 (define-charset 163 'vietnamese-viscii-upper |
142 [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"]) | 156 [1 96 1 0 ?2 1 "VISCII upper" "VISCII upper-case" "VISCII1.1 upper-case"]) |
143 | 157 |
144 ;; For Arabic, we need three different types of character sets. | 158 ;; For Arabic, we need three different types of character sets. |
145 ;; Digits are of direction left-to-right and of width 1-column. | 159 ;; Digits are of direction left-to-right and of width 1-column. |
146 ;; Others are of direction right-to-left and of width 1-column or | 160 ;; Others are of direction right-to-left and of width 1-column or |
147 ;; 2-column. | 161 ;; 2-column. |
148 (define-charset nil 'arabic-digit | 162 (define-charset 164 'arabic-digit |
149 [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"]) | 163 [1 94 1 0 ?2 0 "Arabic digit" "Arabic digit" "Arabic digit"]) |
150 (define-charset nil 'arabic-1-column | 164 (define-charset 165 'arabic-1-column |
151 [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"]) | 165 [1 94 1 1 ?3 0 "Arabic 1-col" "Arabic 1-column" "Arabic 1-column"]) |
152 (define-charset nil 'arabic-2-column | 166 |
167 ;; ASCII with right-to-left direction. | |
168 (define-charset 166 'ascii-right-to-left | |
169 [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction" | |
170 "ASCII (left half of ISO 8859-1) with right-to-left direction"]) | |
171 | |
172 ;; Lao script. | |
173 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F. | |
174 (define-charset 167 'lao | |
175 [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"]) | |
176 | |
177 ;; CHARSET-IDs 168..223 are not used. | |
178 | |
179 ;; 1-byte 2-column charsets. Valid range of CHARSET-ID is 224..239. | |
180 | |
181 (define-charset 224 'arabic-2-column | |
153 [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"]) | 182 [1 94 2 1 ?4 0 "Arabic 2-col" "Arabic 2-column" "Arabic 2-column"]) |
154 | 183 |
184 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are | |
185 ;; not assigned. They are automatically converted to each Indian | |
186 ;; script which IS-13194 supports. | |
187 | |
188 (define-charset 225 'indian-is13194 | |
189 [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194" | |
190 "Generic Indian charset for data exchange with IS 13194"]) | |
191 | |
192 ;; CHARSET-IDs 226..239 are not used. | |
193 | |
194 ;; 2-byte 1-column charsets. Valid range of CHARSET-ID is 240..244. | |
195 | |
196 ;; Actual Glyph for 1-column width. | |
197 (define-charset 240 'indian-1-column | |
198 [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column" | |
199 "Indian charset for 2-column width glyphs"]) | |
200 | |
201 (define-charset 241 'tibetan-1-column | |
202 [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"]) | |
203 | |
204 ;; CHARSET-IDs 242 and 243 are not used. | |
205 | |
206 ;; Subset of Unicode. | |
207 (define-charset 244 'mule-unicode-0100-24ff | |
208 [2 96 1 0 ?1 0 "Unicode subset" "Unicode subset (U+0100..U+24FF)" | |
209 "Unicode characters of the range U+0100..U+24FF."]) | |
210 | |
211 ;; 2-byte 2-column charsets. Valid range of CHARSET-ID is 245..254. | |
212 | |
155 ;; Ethiopic characters (Amahric and Tigrigna). | 213 ;; Ethiopic characters (Amahric and Tigrigna). |
156 (define-charset nil 'ethiopic | 214 (define-charset 245 'ethiopic |
157 [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"]) | 215 [2 94 2 0 ?3 0 "Ethiopic" "Ethiopic characters" "Ethiopic characters"]) |
158 | 216 |
159 ;; Chinese CNS11643 Plane3 thru Plane7. Although these are official | 217 ;; Chinese CNS11643 Plane3 thru Plane7. Although these are official |
160 ;; character sets, the use is rare and don't have to be treated | 218 ;; character sets, the use is rare and don't have to be treated |
161 ;; space-efficiently in the buffer. | 219 ;; space-efficiently in the buffer. |
162 (define-charset nil 'chinese-cns11643-3 | 220 (define-charset 246 'chinese-cns11643-3 |
163 [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183" | 221 [2 94 2 0 ?I 0 "CNS11643-3" "CNS11643-3 (Chinese traditional): ISO-IR-183" |
164 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"]) | 222 "CNS11643 Plane 3 Chinese Traditional: ISO-IR-183"]) |
165 (define-charset nil 'chinese-cns11643-4 | 223 (define-charset 247 'chinese-cns11643-4 |
166 [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184" | 224 [2 94 2 0 ?J 0 "CNS11643-4" "CNS11643-4 (Chinese traditional): ISO-IR-184" |
167 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"]) | 225 "CNS11643 Plane 4 Chinese Traditional: ISO-IR-184"]) |
168 (define-charset nil 'chinese-cns11643-5 | 226 (define-charset 248 'chinese-cns11643-5 |
169 [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185" | 227 [2 94 2 0 ?K 0 "CNS11643-5" "CNS11643-5 (Chinese traditional): ISO-IR-185" |
170 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"]) | 228 "CNS11643 Plane 5 Chinese Traditional: ISO-IR-185"]) |
171 (define-charset nil 'chinese-cns11643-6 | 229 (define-charset 249 'chinese-cns11643-6 |
172 [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186" | 230 [2 94 2 0 ?L 0 "CNS11643-6" "CNS11643-6 (Chinese traditional): ISO-IR-186" |
173 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"]) | 231 "CNS11643 Plane 6 Chinese Traditional: ISO-IR-186"]) |
174 (define-charset nil 'chinese-cns11643-7 | 232 (define-charset 250 'chinese-cns11643-7 |
175 [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187" | 233 [2 94 2 0 ?M 0 "CNS11643-7" "CNS11643-7 (Chinese traditional): ISO-IR-187" |
176 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"]) | 234 "CNS11643 Plane 7 Chinese Traditional: ISO-IR-187"]) |
177 | 235 |
178 ;; ASCII with right-to-left direction. | |
179 (define-charset nil 'ascii-right-to-left | |
180 [1 94 1 1 ?B 0 "rev ASCII" "ASCII with right-to-left direction" | |
181 "ASCII (left half of ISO 8859-1) with right-to-left direction"]) | |
182 | |
183 ;; Indian scripts. Symbolic charset for data exchange. Glyphs are | |
184 ;; not assigned. They are automatically converted to each Indian | |
185 ;; script which IS-13194 supports. | |
186 | |
187 (define-charset nil 'indian-is13194 | |
188 [1 94 2 0 ?5 1 "IS 13194" "Indian IS 13194" | |
189 "Generic Indian charset for data exchange with IS 13194"]) | |
190 ;; Actual Glyph for 2-column width. | 236 ;; Actual Glyph for 2-column width. |
191 (define-charset nil 'indian-2-column | 237 (define-charset 251 'indian-2-column |
192 [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column" | 238 [2 94 2 0 ?5 0 "Indian 2-col" "Indian 2 Column" |
193 "Indian charset for 2-column width glyphs"]) | 239 "Indian charset for 2-column width glyphs"]) |
194 ;; Actual Glyph for 1-column width. | |
195 (define-charset nil 'indian-1-column | |
196 [2 94 1 0 ?6 0 "Indian 1-col" "Indian 1 Column" | |
197 "Indian charset for 2-column width glyphs"]) | |
198 | |
199 ;; Lao script. | |
200 ;; ISO10646's 0x0E80..0x0EDF are mapped to 0x20..0x7F. | |
201 (define-charset nil 'lao | |
202 [1 94 1 0 ?1 0 "Lao" "Lao" "Lao characters (ISO10646 0E80..0EDF)"]) | |
203 | 240 |
204 ;; Tibetan script. | 241 ;; Tibetan script. |
205 (define-charset nil 'tibetan | 242 (define-charset 252 'tibetan |
206 [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"]) | 243 [2 94 2 0 ?7 0 "Tibetan 2-col" "Tibetan 2 column" "Tibetan characters"]) |
207 (define-charset nil 'tibetan-1-column | 244 |
208 [2 94 1 0 ?8 0 "Tibetan 1-col" "Tibetan 1 column" "Tibetan 1 column glyph"]) | 245 ;; CHARSET-ID 253 is not used. |
246 | |
247 ;; JISX0213 Plane 2 | |
248 (define-charset 254 'japanese-jisx0213-2 | |
249 [2 94 2 0 ?P 0 "JISX0213-2" "JISX0213-2" "JISX0213 Plane 2 (Japanese)"]) | |
209 | 250 |
210 ;; Tell C code charset ID's of several charsets. | 251 ;; Tell C code charset ID's of several charsets. |
211 (setup-special-charsets) | 252 (setup-special-charsets) |
212 | 253 |
213 | 254 |