Mercurial > hg > xemacs-beta
annotate lisp/mule/japanese.el @ 5361:62b9ef1ed4ac
Change "special form" to "special operator" in the manuals, too
2011-03-01 Aidan Kehoe <kehoea@parhasard.net>
* lispref/commands.texi (Using Interactive):
* lispref/compile.texi (Eval During Compile):
* lispref/compile.texi (Compiled-Function Objects):
* lispref/control.texi (Sequencing):
* lispref/control.texi (Conditionals):
* lispref/control.texi (Combining Conditions):
* lispref/control.texi (Iteration):
* lispref/control.texi (Catch and Throw):
* lispref/control.texi (Handling Errors):
* lispref/control.texi (Cleanups):
* lispref/display.texi (Temporary Displays):
* lispref/eval.texi (Quoting):
* lispref/eval.texi (Multiple values):
* lispref/frames.texi (Input Focus):
* lispref/functions.texi (Argument List):
* lispref/functions.texi (Defining Functions):
* lispref/functions.texi (Anonymous Functions):
* lispref/internationalization.texi (Level 3 Primitives):
* lispref/internationalization.texi (Domain Specification):
* lispref/intro.texi (A Sample Function Description):
* lispref/intro.texi (A Sample Variable Description):
* lispref/lists.texi (Sets And Lists):
* lispref/macros.texi (Defining Macros):
* lispref/macros.texi (Backquote):
* lispref/positions.texi (Excursions):
* lispref/positions.texi (Narrowing):
* lispref/searching.texi (Saving Match Data):
* lispref/sequences.texi (Sequence Functions):
* lispref/sequences.texi (Array Functions):
* lispref/specifiers.texi (Adding Specifications):
* lispref/variables.texi (Local Variables):
* lispref/variables.texi (Defining Variables):
* lispref/variables.texi (Setting Variables):
* lispref/variables.texi (Default Value):
* lispref/windows.texi (Selecting Windows):
* lispref/windows.texi (Window Configurations):
No longer use @defspec, since we no longer use the term "special
form"; instead use @deffn {Special Operator}. Unfortunately
there's no way in texinfo to redefine @defspec in one place.
| author | Aidan Kehoe <kehoea@parhasard.net> |
|---|---|
| date | Tue, 01 Mar 2011 14:18:45 +0000 |
| parents | 1d74a1d115ee |
| children | 311f6817efc2 308d34e9f07d |
| rev | line source |
|---|---|
| 428 | 1 ;;; japanese.el --- Japanese support -*- coding: iso-2022-7bit; -*- |
| 2 | |
| 3 ;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN. | |
| 4 ;; Licensed to the Free Software Foundation. | |
| 5 ;; Copyright (C) 1997 MORIOKA Tomohiko | |
| 771 | 6 ;; Copyright (C) 2000, 2002 Ben Wing. |
| 428 | 7 |
| 8 ;; Keywords: multilingual, Japanese | |
| 9 | |
| 10 ;; This file is part of XEmacs. | |
| 11 | |
| 12 ;; XEmacs is free software; you can redistribute it and/or modify it | |
| 13 ;; under the terms of the GNU General Public License as published by | |
| 14 ;; the Free Software Foundation; either version 2, or (at your option) | |
| 15 ;; any later version. | |
| 16 | |
| 17 ;; XEmacs is distributed in the hope that it will be useful, but | |
| 18 ;; WITHOUT ANY WARRANTY; without even the implied warranty of | |
| 19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | |
| 20 ;; General Public License for more details. | |
| 21 | |
| 22 ;; You should have received a copy of the GNU General Public License | |
| 23 ;; along with XEmacs; see the file COPYING. If not, write to the Free | |
| 24 ;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA | |
| 25 ;; 02111-1307, USA. | |
| 26 | |
| 771 | 27 ;;; Synched up with: Emacs 20.6 (international/japanese.el). |
| 28 | |
| 428 | 29 ;;; Commentary: |
| 30 | |
| 31 ;; For Japanese, character sets JISX0201, JISX0208, JISX0212 are | |
| 32 ;; supported. | |
| 33 | |
| 34 ;;; Code: | |
| 35 | |
| 778 | 36 (make-charset 'japanese-jisx0213-1 "JISX0213 Plane 1 (Japanese)" |
| 37 '(dimension | |
| 38 2 | |
| 3659 | 39 registries ["JISX0213.2000-1"] |
| 778 | 40 chars 94 |
| 41 columns 2 | |
| 42 direction l2r | |
| 43 final ?O | |
| 44 graphic 0 | |
| 45 short-name "JISX0213-1" | |
| 46 long-name "JISX0213-1" | |
| 47 )) | |
| 48 | |
| 49 ;; JISX0213 Plane 2 | |
| 50 (make-charset 'japanese-jisx0213-2 "JISX0213 Plane 2 (Japanese)" | |
| 51 '(dimension | |
| 52 2 | |
| 3659 | 53 registries ["JISX0213.2000-2"] |
| 778 | 54 chars 94 |
| 55 columns 2 | |
| 56 direction l2r | |
| 57 final ?P | |
| 58 graphic 0 | |
| 59 short-name "JISX0213-2" | |
| 60 long-name "JISX0213-2" | |
| 61 )) | |
| 62 | |
| 428 | 63 ;;; Syntax of Japanese characters. |
| 64 (loop for row in '(33 34 40) | |
| 65 do (modify-syntax-entry `[japanese-jisx0208 ,row] "_")) | |
| 66 (loop for char in '(?$B!<(B ?$B!+(B ?$B!,(B ?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B) | |
| 67 do (modify-syntax-entry char "w")) | |
| 68 (modify-syntax-entry ?\$B!J(B "($B!K(B") | |
| 69 (modify-syntax-entry ?\$B!N(B "($B!O(B") | |
| 70 (modify-syntax-entry ?\$B!P(B "($B!Q(B") | |
| 71 (modify-syntax-entry ?\$B!V(B "($B!W(B") | |
| 72 (modify-syntax-entry ?\$B!X(B "($B!Y(B") | |
| 73 (modify-syntax-entry ?\$B!K(B ")$B!J(B") | |
| 74 (modify-syntax-entry ?\$B!O(B ")$B!N(B") | |
| 75 (modify-syntax-entry ?\$B!Q(B ")$B!P(B") | |
| 76 (modify-syntax-entry ?\$B!W(B ")$B!V(B") | |
| 77 (modify-syntax-entry ?\$B!Y(B ")$B!X(B") | |
| 78 | |
| 79 ;;; Character categories S, A, H, K, G, Y, and C | |
| 80 (define-category ?S "Japanese 2-byte symbol character.") | |
| 81 (modify-category-entry [japanese-jisx0208 33] ?S) | |
| 82 (modify-category-entry [japanese-jisx0208 34] ?S) | |
| 83 (modify-category-entry [japanese-jisx0208 40] ?S) | |
| 84 (define-category ?A "Japanese 2-byte Alphanumeric character.") | |
| 85 (modify-category-entry [japanese-jisx0208 35] ?A) | |
| 86 (define-category ?H "Japanese 2-byte Hiragana character.") | |
| 87 (modify-category-entry [japanese-jisx0208 36] ?H) | |
| 88 (define-category ?K "Japanese 2-byte Katakana character.") | |
| 89 (modify-category-entry [japanese-jisx0208 37] ?K) | |
| 90 (define-category ?G "Japanese 2-byte Greek character.") | |
| 91 (modify-category-entry [japanese-jisx0208 38] ?G) | |
| 92 (define-category ?Y "Japanese 2-byte Cyrillic character.") | |
| 93 (modify-category-entry [japanese-jisx0208 39] ?Y) | |
| 94 (define-category ?C "Japanese 2-byte Kanji characters.") | |
| 95 (loop for row from 48 to 126 | |
| 96 do (modify-category-entry `[japanese-jisx0208 ,row] ?C)) | |
| 97 (loop for char in '(?$B!<(B ?$B!+(B ?$B!,(B) | |
| 98 do (modify-category-entry char ?K) | |
| 99 (modify-category-entry char ?H)) | |
| 100 (loop for char in '(?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B) | |
| 101 do (modify-category-entry char ?C)) | |
| 102 (modify-category-entry 'japanese-jisx0212 ?C) | |
| 103 | |
| 104 (defvar japanese-word-regexp | |
| 105 "\\cA+\\cH*\\|\\cK+\\cH*\\|\\cC+\\cH*\\|\\cH+\\|\\ck+\\|\\sw+" | |
| 106 "Regular expression used to match a Japanese word.") | |
| 107 | |
| 108 (set-word-regexp japanese-word-regexp) | |
| 109 (setq forward-word-regexp "\\w\\>") | |
| 110 (setq backward-word-regexp "\\<\\w") | |
| 111 | |
| 112 ;;; Paragraph setting | |
| 113 (setq sentence-end | |
| 114 (concat | |
| 115 "\\(" | |
| 116 "\\(" | |
| 117 "[.?!][]\"')}]*" | |
| 118 "\\|" | |
| 119 "[$B!%!)!*(B][$B!O!I!G!K!Q!M!S!U!W!Y(B]*" | |
| 120 "\\)" | |
| 121 "\\($\\|\t\\| \\)" | |
| 122 "\\|" | |
| 123 "$B!#(B" | |
| 124 "\\)" | |
| 125 "[ \t\n]*")) | |
| 1891 | 126 |
| 127 ;; allow paragraphs to start with a zenkaku space | |
| 128 (setq paragraph-start "[ $B!!(B\t\n\f]") | |
| 129 (setq paragraph-separate "[ $B!!(B\t\f]*$") | |
| 428 | 130 |
| 131 ;; EGG specific setup | |
| 132 (define-egg-environment 'japanese | |
| 133 "Japanese settings for egg." | |
| 134 (lambda () | |
| 771 | 135 (with-boundp '(its:*standard-modes* its:*current-map* wnn-server-type) |
| 136 (with-fboundp 'its:get-mode-map | |
| 137 (when (not (featurep 'egg-jpn)) | |
| 138 (load "its-hira") | |
| 139 (load "its-kata") | |
| 140 (load "its-hankaku") | |
| 141 (load "its-zenkaku") | |
| 142 (setq its:*standard-modes* | |
| 143 (append | |
| 144 (list (its:get-mode-map "roma-kana") | |
| 145 (its:get-mode-map "roma-kata") | |
| 146 (its:get-mode-map "downcase") | |
| 147 (its:get-mode-map "upcase") | |
| 148 (its:get-mode-map "zenkaku-downcase") | |
| 149 (its:get-mode-map "zenkaku-upcase")) | |
| 150 its:*standard-modes*)) | |
| 151 (provide 'egg-jpn)) | |
| 152 (setq wnn-server-type 'jserver) | |
| 153 ;; Can't do this here any more. Must do it when selecting egg-wnn | |
| 154 ;; or egg-sj3 | |
| 155 ;; (setq egg-default-startup-file "eggrc-wnn") | |
| 156 (setq-default its:*current-map* (its:get-mode-map "roma-kana")))))) | |
| 428 | 157 |
| 450 | 158 ;; stuff for providing grammatic processing of Japanese text |
| 428 | 159 ;; something like this should probably be created for all environments... |
| 450 | 160 ;; #### Arrgh. This stuff should defvar'd in either fill.el or kinsoku.el. |
| 161 ;; Then the language environment should set these things, probably buffer- | |
| 162 ;; locally. | |
| 428 | 163 |
| 771 | 164 ;; #### will be moved to fill.el |
| 165 (defvar space-insertable | |
| 166 (let* ((aletter (concat "\\(" ascii-char "\\|" kanji-char "\\)")) | |
| 167 (kanji-space-insertable | |
| 168 (concat | |
| 428 | 169 "$B!"(B" aletter "\\|" |
| 170 "$B!#(B" aletter "\\|" | |
| 171 aletter "$B!J(B" "\\|" | |
| 172 "$B!K(B" aletter "\\|" | |
| 173 ascii-alphanumeric kanji-kanji-char "\\|" | |
| 771 | 174 kanji-kanji-char ascii-alphanumeric))) |
| 175 (concat " " aletter "\\|" kanji-space-insertable)) | |
| 176 "Regexp for finding points that can have spaces inserted into them for justification") | |
| 428 | 177 |
| 771 | 178 ;; Beginning of FSF synching with international/japanese.el. |
| 179 | |
| 428 | 180 ;; (make-coding-system |
| 181 ;; 'iso-2022-jp 2 ?J | |
| 182 ;; "ISO 2022 based 7bit encoding for Japanese (MIME:ISO-2022-JP)" | |
| 183 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208 | |
| 184 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201) nil nil nil | |
| 185 ;; short ascii-eol ascii-cntl seven) | |
| 186 ;; '((safe-charsets ascii japanese-jisx0208-1978 japanese-jisx0208 | |
| 187 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201) | |
| 188 ;; (mime-charset . iso-2022-jp))) | |
| 189 | |
| 190 (make-coding-system | |
| 191 'iso-2022-jp 'iso2022 | |
| 771 | 192 "ISO-2022-JP (Japanese mail)" |
| 428 | 193 '(charset-g0 ascii |
| 194 short t | |
| 195 seven t | |
| 196 input-charset-conversion ((latin-jisx0201 ascii) | |
| 197 (japanese-jisx0208-1978 japanese-jisx0208)) | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
198 safe-charsets (ascii japanese-jisx0208-1978 japanese-jisx0208 |
|
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
199 latin-jisx0201 japanese-jisx0212 katakana-jisx0201) |
| 428 | 200 mnemonic "MULE/7bit" |
| 771 | 201 documentation |
| 202 "Coding system used for communication with mail and news in Japan." | |
| 203 )) | |
| 204 | |
| 205 (make-coding-system | |
| 206 'jis7 'iso2022 | |
| 207 "JIS7 (old Japanese 7-bit encoding)" | |
| 208 '(charset-g0 ascii | |
| 209 charset-g1 katakana-jisx0201 | |
| 210 short t | |
| 211 seven t | |
| 212 lock-shift t | |
| 213 input-charset-conversion ((latin-jisx0201 ascii) | |
| 214 (japanese-jisx0208-1978 japanese-jisx0208)) | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
215 safe-charsets (latin-jisx0201 ascii japanese-jisx0208-1978 japanese-jisx0208) |
| 771 | 216 mnemonic "JIS7" |
| 217 documentation | |
| 218 "Old JIS 7-bit encoding; mostly superseded by ISO-2022-JP. | |
| 219 Uses locking-shift (SI/SO) to select half-width katakana." | |
| 220 )) | |
| 221 | |
| 222 (make-coding-system | |
| 223 'jis8 'iso2022 | |
| 224 "JIS8 (old Japanese 8-bit encoding)" | |
| 225 '(charset-g0 ascii | |
| 226 charset-g1 katakana-jisx0201 | |
| 227 short t | |
| 228 input-charset-conversion ((latin-jisx0201 ascii) | |
| 229 (japanese-jisx0208-1978 japanese-jisx0208)) | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
230 safe-charsets (latin-jisx0201 ascii japanese-jisx0208-1978 |
|
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
231 japanese-jisx0208) |
| 771 | 232 mnemonic "JIS8" |
| 233 documentation | |
| 234 "Old JIS 8-bit encoding; mostly superseded by ISO-2022-JP. | |
| 235 Uses high bytes for half-width katakana." | |
| 428 | 236 )) |
| 237 | |
| 238 (define-coding-system-alias 'junet 'iso-2022-jp) | |
| 239 | |
| 240 ;; (make-coding-system | |
| 241 ;; 'iso-2022-jp-2 2 ?J | |
| 242 ;; "ISO 2022 based 7bit encoding for CJK, Latin-1, and Greek (MIME:ISO-2022-JP-2)" | |
| 243 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208 | |
| 244 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201 | |
| 245 ;; chinese-gb2312 korean-ksc5601) nil | |
| 246 ;; (nil latin-iso8859-1 greek-iso8859-7) nil | |
| 247 ;; short ascii-eol ascii-cntl seven nil single-shift) | |
| 248 ;; '((safe-charsets ascii japanese-jisx0208-1978 japanese-jisx0208 | |
| 249 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201 | |
| 250 ;; chinese-gb2312 korean-ksc5601 | |
| 251 ;; latin-iso8859-1 greek-iso8859-7) | |
| 252 ;; (mime-charset . iso-2022-jp-2))) | |
| 253 | |
| 254 ;; (make-coding-system | |
| 255 ;; 'japanese-shift-jis 1 ?S | |
| 256 ;; "Shift-JIS 8-bit encoding for Japanese (MIME:SHIFT_JIS)" | |
| 257 ;; nil | |
| 258 ;; '((safe-charsets ascii japanese-jisx0208 japanese-jisx0208-1978 | |
| 259 ;; latin-jisx0201 katakana-jisx0201) | |
| 771 | 260 ;; (mime-charset . shift-jis) |
| 428 | 261 ;; (charset-origin-alist (japanese-jisx0208 "SJIS" encode-sjis-char) |
| 262 ;; (katakana-jisx0201 "SJIS" encode-sjis-char)))) | |
| 263 | |
| 264 (make-coding-system | |
| 771 | 265 'shift-jis 'shift-jis |
| 266 "Shift-JIS" | |
| 267 '(mnemonic "Ja/SJIS" | |
| 268 documentation "The standard Japanese encoding in MS Windows." | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
269 safe-charsets (ascii japanese-jisx0208 japanese-jisx0208-1978 |
|
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
270 latin-jisx0201 katakana-jisx0201) |
| 771 | 271 )) |
| 428 | 272 |
| 771 | 273 ;; A former name? |
| 274 (define-coding-system-alias 'shift_jis 'shift-jis) | |
| 275 | |
| 276 ;; FSF: | |
| 277 ;; (define-coding-system-alias 'shift-jis 'japanese-shift-jis) | |
| 428 | 278 ;; (define-coding-system-alias 'sjis 'japanese-shift-jis) |
| 279 | |
| 280 ;; (make-coding-system | |
| 281 ;; 'japanese-iso-7bit-1978-irv 2 ?j | |
| 282 ;; "ISO 2022 based 7-bit encoding for Japanese JISX0208-1978 and JISX0201-Roman" | |
| 283 ;; '((ascii japanese-jisx0208-1978 japanese-jisx0208 | |
| 284 ;; latin-jisx0201 japanese-jisx0212 katakana-jisx0201 t) nil nil nil | |
| 285 ;; short ascii-eol ascii-cntl seven nil nil use-roman use-oldjis) | |
| 286 ;; '(ascii japanese-jisx0208-1978 japanese-jisx0208 latin-jisx0201)) | |
| 287 | |
| 288 (make-coding-system | |
| 289 'iso-2022-jp-1978-irv 'iso2022 | |
| 771 | 290 "ISO-2022-JP-1978-IRV (Old JIS)" |
| 428 | 291 '(charset-g0 ascii |
| 292 short t | |
| 293 seven t | |
| 294 output-charset-conversion ((ascii latin-jisx0201) | |
| 295 (japanese-jisx0208 japanese-jisx0208-1978)) | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
296 safe-charsets (ascii latin-jisx0201 japanese-jisx0208 |
|
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
297 japanese-jisx0208-1978) |
| 771 | 298 documentation |
| 299 "This is a coding system used for old JIS terminals. It's an ISO | |
| 300 2022 based 7-bit encoding for Japanese JISX0208-1978 and JISX0201-Roman." | |
| 428 | 301 mnemonic "Ja-78/7bit" |
| 302 )) | |
| 303 | |
| 771 | 304 ;; FSF: |
| 428 | 305 ;; (define-coding-system-alias 'iso-2022-jp-1978-irv 'japanese-iso-7bit-1978-irv) |
| 306 ;; (define-coding-system-alias 'old-jis 'japanese-iso-7bit-1978-irv) | |
| 307 | |
| 308 (define-coding-system-alias 'old-jis 'iso-2022-jp-1978-irv) | |
| 309 | |
| 310 ;; (make-coding-system | |
| 311 ;; 'japanese-iso-8bit 2 ?E | |
| 312 ;; "ISO 2022 based EUC encoding for Japanese (MIME:EUC-JP)" | |
| 313 ;; '(ascii japanese-jisx0208 katakana-jisx0201 japanese-jisx0212 | |
| 314 ;; short ascii-eol ascii-cntl nil nil single-shift) | |
| 315 ;; '((safe-charsets ascii latin-jisx0201 japanese-jisx0208 japanese-jisx0208-1978 | |
| 771 | 316 ;; katakana-jisx0201 japanese-jisx0212) |
| 428 | 317 ;; (mime-charset . euc-jp))) |
| 771 | 318 ;; |
| 428 | 319 (make-coding-system |
| 320 'euc-jp 'iso2022 | |
| 771 | 321 "Japanese EUC" |
| 428 | 322 '(charset-g0 ascii |
| 323 charset-g1 japanese-jisx0208 | |
| 324 charset-g2 katakana-jisx0201 | |
| 325 charset-g3 japanese-jisx0212 | |
|
4568
1d74a1d115ee
Add #'query-coding-region tests; do the work necessary to get them running.
Aidan Kehoe <kehoea@parhasard.net>
parents:
4145
diff
changeset
|
326 safe-charsets (ascii japanese-jisx0208 katakana-jisx0201 japanese-jisx0212) |
| 428 | 327 short t |
| 328 mnemonic "Ja/EUC" | |
| 771 | 329 documentation |
| 330 "Japanese EUC (Extended Unix Code), the standard Japanese encoding in Unix. | |
| 331 Equivalent MIME encoding: EUC-JP. | |
| 332 | |
| 333 Japanese EUC was the forefather of all the different EUC's, which all follow | |
| 334 a similar structure: | |
| 335 | |
| 336 1. Up to four character sets can be encoded. | |
| 337 | |
| 338 2. This is a non-modal encoding, i.e. it is impossible to set a global state | |
| 339 that affects anything more than the directly following character. [Modal | |
| 340 encodings typically have escape sequences to change global settings, which | |
| 341 affect all the following characters until the setting is turned off. | |
| 342 Modal encodings are typically used when it's necessary to support text in | |
| 343 a wide variety of character sets and still keep basic ASCII compatibility, | |
| 344 or in cases (e.g. sending email) where the allowed characters that can | |
| 345 pass the gateway are small and (typically) no high-bit range is available. | |
| 346 | |
| 347 3. The first character set is always ASCII or some national variant of it, | |
| 348 and encoded in the standard ASCII position. All characters in all other | |
| 349 character sets are encoded entirely using high-half bytes. Therefore, | |
| 350 it is safe to scan for ASCII characters, such as '/' to separate path | |
| 351 components, in the obvious way. | |
| 352 | |
| 353 4. Each of the other three character sets can be of dimension 1, 2, or 3. | |
| 354 A dimension-1 character set contains 96 bytes; a dimension-2 character | |
| 355 set contains 96 x 96 bytes; and a dimension-3 character set contains | |
| 356 96 x 96 x 96 bytes. 94 instead of 96 as the number of characters per | |
| 357 dimension is also supported. Character sets of dimensions 1, 2, and 3 | |
| 358 use 1-3 bytes, respectively, to encode a character, and each byte is | |
| 359 in the range A0-FF (or A1-FE for those with 94 bytes per dimension). | |
| 360 | |
| 361 5. The four character sets encoded in EUC are called G0, G1, G2, and G3. | |
| 362 As mentioned earlier, G0 is ASCII or some variant, and encoded into | |
| 363 the ASCII positions 00 - 7F. G1 is encoded directly by laying out | |
| 364 its bytes. G2 is encoded using an 8E byte followed by the character's | |
| 365 bytes. G3 is encoded using an 8F byte followed by the character's bytes." | |
| 366 | |
| 428 | 367 )) |
| 368 | |
| 771 | 369 ;; FSF: |
| 428 | 370 ;; (define-coding-system-alias 'euc-japan-1990 'japanese-iso-8bit) |
| 371 ;; (define-coding-system-alias 'euc-japan 'japanese-iso-8bit) | |
| 372 ;; (define-coding-system-alias 'euc-jp 'japanese-iso-8bit) | |
| 373 | |
| 374 (define-coding-system-alias 'euc-japan 'euc-jp) ; only for w3 | |
| 375 (define-coding-system-alias 'japanese-euc 'euc-jp) | |
| 376 | |
| 377 (set-language-info-alist | |
| 378 "Japanese" '((setup-function . setup-japanese-environment-internal) | |
| 379 (exit-function . exit-japanese-environment) | |
| 380 (tutorial . "TUTORIAL.ja") | |
| 381 (charset japanese-jisx0208 japanese-jisx0208-1978 | |
| 382 japanese-jisx0212 latin-jisx0201 katakana-jisx0201) | |
| 383 (coding-system iso-2022-jp euc-jp | |
| 771 | 384 shift-jis iso-2022-jp-2) |
| 428 | 385 (coding-priority iso-2022-jp euc-jp |
| 771 | 386 shift-jis iso-2022-jp-2) |
| 387 ;; These locale names come from the X11R6 locale.alias file. | |
| 388 ;; What an incredible fucking mess!!!!!!!!!!!!!!!!!!!!!!!!!! | |
| 389 ;; What's worse is that typical Unix implementations of | |
| 390 ;; setlocale() return back exactly what you passed them, even | |
| 391 ;; though it's perfectly allowed (and in fact done under | |
| 392 ;; Windows) to expand the locale to its full form (including | |
| 393 ;; encoding), so you have some hint as to the encoding!!! | |
| 394 ;; | |
| 395 ;; We order them in such a way that we're maximally likely | |
| 396 ;; to get an encoding name. | |
| 397 ;; | |
| 398 (locale | |
| 399 ;; SunOS 5.7: ja ja_JP.PCK ja_JP.UTF-8 japanese | |
| 400 ;; RedHat Linux 6.2J: ja ja_JP ja_JP.eucJP ja_JP.ujis \ | |
| 401 ;; japanese japanese.euc | |
| 402 ;; HP-UX 10.20: ja_JP.SJIS ja_JP.eucJPput ja_JP.kana8 | |
| 403 ;; Cygwin b20.1: ja_JP.EUC | |
| 404 ;; FreeBSD 2.2.8: ja_JP.EUC ja_JP.SJIS | |
| 405 | |
| 406 ;; EUC locales | |
| 407 "ja_JP.EUC" | |
| 408 "ja_JP.eucJP" | |
| 409 "ja_JP.AJEC" | |
| 410 "ja_JP.ujis" | |
| 411 "Japanese-EUC" | |
| 412 "japanese.euc" | |
| 413 | |
| 414 ;; Shift-JIS locales | |
| 415 "ja_JP.SJIS" | |
| 416 "ja_JP.mscode" | |
| 417 "ja.SJIS" | |
| 418 | |
| 419 ;; 7-bit locales | |
| 420 "ja_JP.ISO-2022-JP" | |
| 421 "ja_JP.jis7" | |
| 422 "ja_JP.pjis" | |
| 423 "ja_JP.JIS" | |
| 424 "ja.JIS" | |
| 425 | |
| 426 ;; 8-bit locales | |
| 427 "ja_JP.jis8" | |
| 428 | |
| 429 ;; encoding-unspecified locales | |
| 430 "ja_JP" | |
| 431 "Ja_JP" | |
| 432 "Jp_JP" | |
| 433 "japanese" | |
| 434 "japan" | |
| 435 "ja" | |
| 436 ) | |
| 428 | 437 ;; (input-method . "japanese") |
| 438 (features japan-util) | |
| 450 | 439 (sample-text . "Japanese ($BF|K\8l(B) $B$3$s$K$A$O(B, (I:]FAJ(B") |
| 428 | 440 (documentation . t))) |
| 441 | |
| 4145 | 442 ;; Set the native-coding-system separately so the lambdas get compiled. (Not |
| 443 ;; a huge speed improvement, but this code is called at startup, and every | |
| 444 ;; little helps there.) | |
| 445 (set-language-info "Japanese" | |
| 446 'native-coding-system | |
| 447 (list | |
| 448 ;; first, see if an explicit encoding was given. | |
| 449 (lambda (locale) | |
| 450 (let ((case-fold-search t)) | |
| 451 (cond | |
| 452 ;; many unix versions | |
| 453 ((string-match "\\.euc" locale) 'euc-jp) | |
| 454 ((string-match "\\.sjis" locale) 'shift-jis) | |
| 455 | |
| 456 ;; X11R6 (CJKV p. 471) | |
| 457 ((string-match "\\.jis7" locale) 'jis7) | |
| 458 ((string-match "\\.jis8" locale) 'jis8) | |
| 459 ((string-match "\\.mscode" locale) 'shift-jis) | |
| 460 ((string-match "\\.pjis" locale) 'iso-2022-jp) | |
| 461 ((string-match "\\.ujis" locale) 'euc-jp) | |
| 462 | |
| 463 ;; other names in X11R6 locale.alias | |
| 464 ((string-match "\\.ajec" locale) 'euc-jp) | |
| 465 ((string-match "-euc" locale) 'euc-jp) | |
| 466 ((string-match "\\.iso-2022-jp" locale) 'iso-2022-jp) | |
| 467 ((string-match "\\.jis" locale) 'jis7) ;; or just jis? | |
| 468 ))) | |
| 469 | |
| 470 ;; aix (CJKV p. 465) | |
| 471 (lambda (locale) | |
| 472 (when (eq system-type 'aix) | |
| 473 (cond | |
| 474 ((string-match "^Ja_JP" locale) 'shift-jis) | |
| 475 ((string-match "^ja_JP" locale) 'euc-jp)))) | |
| 476 | |
| 477 ;; other X11R6 locale.alias | |
| 478 (lambda (locale) | |
| 479 (cond | |
| 480 ((string-match "^Jp_JP" locale) 'euc-jp) | |
| 481 ((and (eq system-type 'hpux) (eq locale "japanese")) | |
| 482 'shift-jis))) | |
| 483 | |
| 484 ;; fallback | |
| 485 'euc-jp)) | |
| 486 | |
| 428 | 487 ;;; japanese.el ends here |