Mercurial > emacs
changeset 33049:fed8d1ebdc15
(mac-roman-decoder, mac-roman-encoder): New translation tables.
(decode-mac-roman, encode-mac-roman): Definition of these CCL
programs are modified and moved from mac-win.el.
(mac-roman): Definition of this coding system is modified and
moved from mac-win.el.
author | Kenichi Handa <handa@m17n.org> |
---|---|
date | Mon, 30 Oct 2000 01:37:20 +0000 |
parents | 636ac3744ddd |
children | 84f89d78d87a |
files | lisp/language/european.el |
diffstat | 1 files changed, 183 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- a/lisp/language/european.el Mon Oct 30 01:36:20 2000 +0000 +++ b/lisp/language/european.el Mon Oct 30 01:37:20 2000 +0000 @@ -318,6 +318,189 @@ (documentation . t)) '("European")) + +;; Definitions for the Mac Roman character sets and coding system. +;; The Mac Roman encoding uses all 128 code points in the range 128 to +;; 255 for actual characters. Emacs decode them to one of the +;; following character sets. +;; ascii, latin-iso8859-1, mule-unicode-0100-24ff, +;; mule-unicode-2500-33ff, mule-unicode-e000-ffff + +(let + ((encoding-vector (make-vector 256 nil)) + (i 0) + (vec ;; mac-roman (128..255) -> UCS mapping + [ #x00C4 ;; 128:LATIN CAPITAL LETTER A WITH DIAERESIS + #x00C5 ;; 129:LATIN CAPITAL LETTER A WITH RING ABOVE + #x00C7 ;; 130:LATIN CAPITAL LETTER C WITH CEDILLA + #x00C9 ;; 131:LATIN CAPITAL LETTER E WITH ACUTE + #x00D1 ;; 132:LATIN CAPITAL LETTER N WITH TILDE + #x00D6 ;; 133:LATIN CAPITAL LETTER O WITH DIAERESIS + #x00DC ;; 134:LATIN CAPITAL LETTER U WITH DIAERESIS + #x00E1 ;; 135:LATIN SMALL LETTER A WITH ACUTE + #x00E0 ;; 136:LATIN SMALL LETTER A WITH GRAVE + #x00E2 ;; 137:LATIN SMALL LETTER A WITH CIRCUMFLEX + #x00E4 ;; 138:LATIN SMALL LETTER A WITH DIAERESIS + #x00E3 ;; 139:LATIN SMALL LETTER A WITH TILDE + #x00E5 ;; 140:LATIN SMALL LETTER A WITH RING ABOVE + #x00E7 ;; 141:LATIN SMALL LETTER C WITH CEDILLA + #x00E9 ;; 142:LATIN SMALL LETTER E WITH ACUTE + #x00E8 ;; 143:LATIN SMALL LETTER E WITH GRAVE + #x00EA ;; 144:LATIN SMALL LETTER E WITH CIRCUMFLEX + #x00EB ;; 145:LATIN SMALL LETTER E WITH DIAERESIS + #x00ED ;; 146:LATIN SMALL LETTER I WITH ACUTE + #x00EC ;; 147:LATIN SMALL LETTER I WITH GRAVE + #x00EE ;; 148:LATIN SMALL LETTER I WITH CIRCUMFLEX + #x00EF ;; 149:LATIN SMALL LETTER I WITH DIAERESIS + #x00F1 ;; 150:LATIN SMALL LETTER N WITH TILDE + #x00F3 ;; 151:LATIN SMALL LETTER O WITH ACUTE + #x00F2 ;; 152:LATIN SMALL LETTER O WITH GRAVE + #x00F4 ;; 153:LATIN SMALL LETTER O WITH CIRCUMFLEX + #x00F6 ;; 154:LATIN SMALL LETTER O WITH DIAERESIS + #x00F5 ;; 155:LATIN SMALL LETTER O WITH TILDE + #x00FA ;; 156:LATIN SMALL LETTER U WITH ACUTE + #x00F9 ;; 157:LATIN SMALL LETTER U WITH GRAVE + #x00FB ;; 158:LATIN SMALL LETTER U WITH CIRCUMFLEX + #x00FC ;; 159:LATIN SMALL LETTER U WITH DIAERESIS + #x2020 ;; 160:DAGGER + #x00B0 ;; 161:DEGREE SIGN + #x00A2 ;; 162:CENT SIGN + #x00A3 ;; 163:POUND SIGN + #x00A7 ;; 164:SECTION SIGN + #x2022 ;; 165:BULLET + #x00B6 ;; 166:PILCROW SIGN + #x00DF ;; 167:LATIN SMALL LETTER SHARP S + #x00AE ;; 168:REGISTERED SIGN + #x00A9 ;; 169:COPYRIGHT SIGN + #x2122 ;; 170:TRADE MARK SIGN + #x00B4 ;; 171:ACUTE ACCENT + #x00A8 ;; 172:DIAERESIS + #x2260 ;; 173:NOT EQUAL TO + #x00C6 ;; 174:LATIN CAPITAL LETTER AE + #x00D8 ;; 175:LATIN CAPITAL LETTER O WITH STROKE + #x221E ;; 176:INFINITY + #x00B1 ;; 177:PLUS-MINUS SIGN + #x2264 ;; 178:LESS-THAN OR EQUAL TO + #x2265 ;; 179:GREATER-THAN OR EQUAL TO + #x00A5 ;; 180:YEN SIGN + #x00B5 ;; 181:MICRO SIGN + #x2202 ;; 182:PARTIAL DIFFERENTIAL + #x2211 ;; 183:N-ARY SUMMATION + #x220F ;; 184:N-ARY PRODUCT + #x03C0 ;; 185:GREEK SMALL LETTER PI + #x222B ;; 186:INTEGRAL + #x00AA ;; 187:FEMININE ORDINAL INDICATOR + #x00BA ;; 188:MASCULINE ORDINAL INDICATOR + #x03A9 ;; 189:GREEK CAPITAL LETTER OMEGA + #x00E6 ;; 190:LATIN SMALL LETTER AE + #x00F8 ;; 191:LATIN SMALL LETTER O WITH STROKE + #x00BF ;; 192:INVERTED QUESTION MARK + #x00A1 ;; 193:INVERTED EXCLAMATION MARK + #x00AC ;; 194:NOT SIGN + #x221A ;; 195:SQUARE ROOT + #x0192 ;; 196:LATIN SMALL LETTER F WITH HOOK + #x2248 ;; 197:ALMOST EQUAL TO + #x2206 ;; 198:INCREMENT + #x00AB ;; 199:LEFT-POINTING DOUBLE ANGLE QUOTATION MARK + #x00BB ;; 200:RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK + #x2026 ;; 201:HORIZONTAL ELLIPSIS + #x00A0 ;; 202:NO-BREAK SPACE + #x00C0 ;; 203:LATIN CAPITAL LETTER A WITH GRAVE + #x00C3 ;; 204:LATIN CAPITAL LETTER A WITH TILDE + #x00D5 ;; 205:LATIN CAPITAL LETTER O WITH TILDE + #x0152 ;; 206:LATIN CAPITAL LIGATURE OE + #x0153 ;; 207:LATIN SMALL LIGATURE OE + #x2013 ;; 208:EN DASH + #x2014 ;; 209:EM DASH + #x201C ;; 210:LEFT DOUBLE QUOTATION MARK + #x201D ;; 211:RIGHT DOUBLE QUOTATION MARK + #x2018 ;; 212:LEFT SINGLE QUOTATION MARK + #x2019 ;; 213:RIGHT SINGLE QUOTATION MARK + #x00F7 ;; 214:DIVISION SIGN + #x25CA ;; 215:LOZENGE + #x00FF ;; 216:LATIN SMALL LETTER Y WITH DIAERESIS + #x0178 ;; 217:LATIN CAPITAL LETTER Y WITH DIAERESIS + #x2044 ;; 218:FRACTION SLASH + #x20AC ;; 219:EURO SIGN + #x2039 ;; 220:SINGLE LEFT-POINTING ANGLE QUOTATION MARK + #x203A ;; 221:SINGLE RIGHT-POINTING ANGLE QUOTATION MARK + #xFB01 ;; 222:LATIN SMALL LIGATURE FI + #xFB02 ;; 223:LATIN SMALL LIGATURE FL + #x2021 ;; 224:DOUBLE DAGGER + #x00B7 ;; 225:MIDDLE DOT + #x201A ;; 226:SINGLE LOW-9 QUOTATION MARK + #x201E ;; 227:DOUBLE LOW-9 QUOTATION MARK + #x2030 ;; 228:PER MILLE SIGN + #x00C2 ;; 229:LATIN CAPITAL LETTER A WITH CIRCUMFLEX + #x00CA ;; 230:LATIN CAPITAL LETTER E WITH CIRCUMFLEX + #x00C1 ;; 231:LATIN CAPITAL LETTER A WITH ACUTE + #x00CB ;; 232:LATIN CAPITAL LETTER E WITH DIAERESIS + #x00C8 ;; 233:LATIN CAPITAL LETTER E WITH GRAVE + #x00CD ;; 234:LATIN CAPITAL LETTER I WITH ACUTE + #x00CE ;; 235:LATIN CAPITAL LETTER I WITH CIRCUMFLEX + #x00CF ;; 236:LATIN CAPITAL LETTER I WITH DIAERESIS + #x00CC ;; 237:LATIN CAPITAL LETTER I WITH GRAVE + #x00D3 ;; 238:LATIN CAPITAL LETTER O WITH ACUTE + #x00D4 ;; 239:LATIN CAPITAL LETTER O WITH CIRCUMFLEX + #xF8FF ;; 240:Apple logo + #x00D2 ;; 241:LATIN CAPITAL LETTER O WITH GRAVE + #x00DA ;; 242:LATIN CAPITAL LETTER U WITH ACUTE + #x00DB ;; 243:LATIN CAPITAL LETTER U WITH CIRCUMFLEX + #x00D9 ;; 244:LATIN CAPITAL LETTER U WITH GRAVE + #x0131 ;; 245:LATIN SMALL LETTER DOTLESS I + #x02C6 ;; 246:MODIFIER LETTER CIRCUMFLEX ACCENT + #x02DC ;; 247:SMALL TILDE + #x00AF ;; 248:MACRON + #x02D8 ;; 249:BREVE + #x02D9 ;; 250:DOT ABOVE + #x02DA ;; 251:RING ABOVE + #x00B8 ;; 252:CEDILLA + #x02DD ;; 253:DOUBLE ACUTE ACCENT + #x02DB ;; 254:OGONEK + #x02C7 ;; 255:CARON + ]) + translation-table) + (while (< i 128) + (aset encoding-vector i i) + (setq i (1+ i))) + (while (< i 256) + (aset encoding-vector i + (decode-char 'ucs (aref vec (- i 128)))) + (setq i (1+ i))) + (setq translation-table + (make-translation-table-from-vector encoding-vector)) + (define-translation-table 'mac-roman-decoder translation-table) + (define-translation-table 'mac-roman-encoder + (char-table-extra-slot translation-table 0))) + +(define-ccl-program decode-mac-roman + `(4 + ((loop + (read r1) + (if (r1 < 128) ;; ASCII + (r0 = ,(charset-id 'ascii)) + (if (r0 < 160) + (r0 = ,(charset-id 'eight-bit-control)) + (r0 = ,(charset-id 'eight-bit-graphic)))) + (translate-character mac-roman-decoder r0 r1) + (write-multibyte-character r0 r1) + (repeat)))) + "CCL program to decode Mac Roman") + +(define-ccl-program encode-mac-roman + `(1 + ((loop + (read-multibyte-character r0 r1) + (translate-character mac-roman-encoder r0 r1) + (write-repeat r1)))) + "CCL program to encode Mac Roman") + +(make-coding-system + 'mac-roman 4 ?M "Mac Roman Encoding" + '(decode-mac-roman . encode-mac-roman) + '((safe-chars . mac-roman-encoder) + (valid-codes (0 . 255)))) + (provide 'european) ;;; european.el ends here