Mercurial > hg > xemacs-beta

comparison lisp/unicode.el @ 2297:13a418960a88

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
[xemacs-hg @ 2004-09-22 02:05:42 by stephent] various doc patches <87isa7awrh.fsf@tleepslib.sk.tsukuba.ac.jp>
author stephent
date Wed, 22 Sep 2004 02:06:52 +0000
parents b531bf8658e9
children ecf1ebac70d8
comparison
equal deleted inserted replaced
2296:a58ea4d0d0cd 2297:13a418960a88
29 29
30 ;;; Code: 30 ;;; Code:
31 31
32 ; ;; Subsets of Unicode. 32 ; ;; Subsets of Unicode.
33 33
34 ; #### what is this bogosity ... "chars 96, final ?2" !!?!
34 ; (make-charset 'mule-unicode-2500-33ff 35 ; (make-charset 'mule-unicode-2500-33ff
35 ; "Unicode characters of the range U+2500..U+33FF." 36 ; "Unicode characters of the range U+2500..U+33FF."
36 ; '(dimension 37 ; '(dimension
37 ; 2 38 ; 2
38 ; registry "ISO10646-1" 39 ; registry "ISO10646-1"
122 ;; "CP936.TXT" 123 ;; "CP936.TXT"
123 ;; "CP949.TXT" 124 ;; "CP949.TXT"
124 ;; "CP950.TXT" 125 ;; "CP950.TXT"
125 ;; "GB12345.TXT" 126 ;; "GB12345.TXT"
126 ("GB2312.TXT" chinese-gb2312) 127 ("GB2312.TXT" chinese-gb2312)
127 ;; "HANGUL.TXT" 128 ;; "HANGUL.TXT"
129 ;; #### shouldn't JIS X 0201's upper limit be 7f?
128 ("JIS0201.TXT" latin-jisx0201 #x21 #x80) 130 ("JIS0201.TXT" latin-jisx0201 #x21 #x80)
129 ("JIS0201.TXT" katakana-jisx0201 #xA0 #xFF #x-80) 131 ("JIS0201.TXT" katakana-jisx0201 #xA0 #xFF #x-80)
130 ("JIS0208.TXT" japanese-jisx0208 nil nil nil ignore-first-column) 132 ("JIS0208.TXT" japanese-jisx0208 nil nil nil ignore-first-column)
131 ("JIS0212.TXT" japanese-jisx0212) 133 ("JIS0212.TXT" japanese-jisx0212)
132 ;; "JOHAB.TXT" 134 ;; "JOHAB.TXT"
137 ("KSX1001.TXT" korean-ksc5601) 139 ("KSX1001.TXT" korean-ksc5601)
138 ;; "OLD5601.TXT" 140 ;; "OLD5601.TXT"
139 ;; "SHIFTJIS.TXT" 141 ;; "SHIFTJIS.TXT"
140 ) 142 )
141 ("unicode/mule-ucs" 143 ("unicode/mule-ucs"
144 ;; #### we don't support surrogates?!??
142 ;; use these instead of the above ones once we support surrogates 145 ;; use these instead of the above ones once we support surrogates
143 ;;("chinese-cns11643-1.txt" chinese-cns11643-1) 146 ;;("chinese-cns11643-1.txt" chinese-cns11643-1)
144 ;;("chinese-cns11643-2.txt" chinese-cns11643-2) 147 ;;("chinese-cns11643-2.txt" chinese-cns11643-2)
145 ;;("chinese-cns11643-3.txt" chinese-cns11643-3) 148 ;;("chinese-cns11643-3.txt" chinese-cns11643-3)
146 ;;("chinese-cns11643-4.txt" chinese-cns11643-4) 149 ;;("chinese-cns11643-4.txt" chinese-cns11643-4)
247 (make-coding-system 250 (make-coding-system
248 'ucs-4-little-endian 'unicode 251 'ucs-4-little-endian 'unicode
249 "UCS-4 Little Endian" 252 "UCS-4 Little Endian"
250 '(mnemonic "UCS4-LE" 253 '(mnemonic "UCS4-LE"
251 documentation 254 documentation
255 ;; #### I don't think this is permitted by ISO 10646, only Unicode.
256 ;; Call it UTF-32 instead?
252 "Little-endian version of UCS-4 Unicode encoding. See `ucs-4' coding system." 257 "Little-endian version of UCS-4 Unicode encoding. See `ucs-4' coding system."
253 type ucs-4 258 type ucs-4
254 little-endian t)) 259 little-endian t))
255 260
256 (make-coding-system 261 (make-coding-system
257 'utf-8 'unicode 262 'utf-8 'unicode
258 "UTF-8" 263 "UTF-8"
259 '(mnemonic "UTF8" 264 '(mnemonic "UTF8"
260 documentation 265 documentation
261 "UTF-8 Unicode encoding -- ASCII-compatible 8-bit variable-width encoding 266 "UTF-8 Unicode encoding -- ASCII-compatible 8-bit variable-width encoding
262 with the same principles as the Mule-internal encoding: 267 sharing the following principles with the Mule-internal encoding:
263 268
264 -- All ASCII characters (codepoints 0 through 127) are represented 269 -- All ASCII characters (codepoints 0 through 127) are represented
265 by themselves (i.e. using one byte, with the same value as the 270 by themselves (i.e. using one byte, with the same value as the
266 ASCII codepoint), and these bytes are disjoint from bytes 271 ASCII codepoint), and these bytes are disjoint from bytes
267 representing non-ASCII characters. 272 representing non-ASCII characters.