1 ;;; internal.el --- support for PC internal terminal -*- coding: raw-text; -*-
3 ;; Copyright (C) 1993, 1994, 1998 Free Software Foundation, Inc.
5 ;; Author: Morten Welinder <terra@diku.dk>
7 ;; This file is part of GNU Emacs.
9 ;; GNU Emacs is free software; you can redistribute it and/or modify
10 ;; it under the terms of the GNU General Public License as published by
11 ;; the Free Software Foundation; either version 2, or (at your option)
14 ;; GNU Emacs is distributed in the hope that it will be useful,
15 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
16 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
17 ;; GNU General Public License for more details.
19 ;; You should have received a copy of the GNU General Public License
20 ;; along with GNU Emacs; see the file COPYING. If not, write to the
21 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
22 ;; Boston, MA 02111-1307, USA.
26 ;; ---------------------------------------------------------------------------
27 ;; keyboard setup -- that's simple!
28 (set-input-mode nil nil
0)
29 (define-key function-key-map
[backspace] "\177") ; Normal behaviour for BS
30 (define-key function-key-map [delete] "\C-d") ; ... and Delete
31 (define-key function-key-map [tab] [?\t])
32 (define-key function-key-map [linefeed] [?\n])
33 (define-key function-key-map [clear] [11])
34 (define-key function-key-map [return] [13])
35 (define-key function-key-map [escape] [?\e])
36 (define-key function-key-map [M-backspace] [?\M-\d])
37 (define-key function-key-map [M-delete] [?\M-d])
38 (define-key function-key-map [M-tab] [?\M-\t])
39 (define-key function-key-map [M-linefeed] [?\M-\n])
40 (define-key function-key-map [M-clear] [?\M-\013])
41 (define-key function-key-map [M-return] [?\M-\015])
42 (define-key function-key-map [M-escape] [?\M-\e])
43 (put 'backspace 'ascii-character 127)
44 (put 'delete 'ascii-character 127)
45 (put 'tab 'ascii-character ?\t)
46 (put 'linefeed 'ascii-character ?\n)
47 (put 'clear 'ascii-character 12)
48 (put 'return 'ascii-character 13)
49 (put 'escape 'ascii-character ?\e)
51 ;; ----------------------------------------------------------------------
55 ;; DOS can only support a single font. On most systems (with the
56 ;; possible exception of Far Eastern DOS versions), this means that
57 ;; two character sets are available at any given time: the ASCII
58 ;; charset, and a single national charset, usually mapped to codes
59 ;; above 128 (i.e., with 8th bit set). Which national charset is
60 ;; supported depends on the codepage loaded by the system when it
61 ;; boots; usually, this codepage cannot be changed without
64 ;; Since each codepage can usually display character of a single
65 ;; MULE charset, Emacs can display a single MULE charset with the
66 ;; glyphs of the current codepage. The mapping from DOS codepages
67 ;; to MULE charsets is established by the charset property of the
68 ;; cpNNN-decode-table variables in codepage.el, which also
69 ;; defines translation tables for each such pair, and a bunch of
70 ;; functions to generate coding systems that use those translation
71 ;; tables to convert codepage-encoded text to the appropriate MULE
72 ;; charset and back. When Emacs starts on DOS, it automatically
73 ;; sets its default coding systems for file I/O and terminal output
74 ;; according to the currend DOS codepage, given by the
75 ;; `dos-codepage' variable.
77 ;; This leaves us with the problem of displaying character sets
78 ;; other than the one which maps directly into the current codepage.
79 ;; The following functions and variables handle this nuisance by
80 ;; defining a display table where each character that doesn't have a
81 ;; glyph in some codepage is mapped to a string which represents it.
82 ;; For example, a small c with cedilla is mapped to the string
83 ;; "{,c}" (the braces serve as a sign that this is a single
84 ;; character). A nice feature of the display tables is that Emacs
85 ;; knows that the string represents a single character, and thus
86 ;; cursor motion works as you'd expect: a single `C-f' moves past
87 ;; the entire string which represents a single character.
88 ;; ----------------------------------------------------------------------
90 (defvar IT-character-translations
93 . [255 "!I" "|c" "Pd" "$$" "Ye" "|" "SE" "\"" "(c)"
94 "_a" "<<" "~" "--" "(R)" "'-" "^o" "+-" "^2" "^3"
95 "'" "u" ".P" "^." "'," "^1" "_o" ">>" "1/4" "1/2"
96 "3/4" "?I" "`A" "A'" "A^" "~A" "\"A" "Ao" "AE" ",C"
97 "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" "-D" "~N"
98 "`O" "O'" "O^" "~O" "\"O" "*x" "/O" "`U" "U'" "U^"
99 "\"U" "Y'" "-P" "ss" "`a" "a'" "a^" "~a" "\"a" "ao"
100 "ae" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i"
101 "-d" "~n" "`o" "o'" "o^" "~o" "\"o" "-:" "/o" "`u"
102 "u'" "u^" "\"u" "y'" "-p" "\"y"]
105 . [255 "A;" "'(" "/L" "$$" "L<" "S'" "SE" "\"" "S<"
106 ",S" "T<" "Z'" "--" "Z<" "Z^." "^o" "a;" "';" "/l"
107 "'" "l<" "s'" "'<" "'," "s<" ",s" "t<" "z'" "'"
108 "z<" "z^." "R'" "A'" "A^" "A(" "\"A" "L'" "C'" ",C"
109 "C<" "E'" "E;" "E:" "E<" "I'" "I^" "D<" "/D" "N'"
110 "N<" "O'" "O^" "O''" "\"O" "*x" "R<" "U^0" "U'" "U''"
111 "\"U" "Y'" ",T" "ss" "r'" "a'" "a^" "a(" "\"a" "l'"
112 "c'" ",c" "c<" "e'" "e;" "\"e" "e<" "i'" "i^" "d<"
113 "/d" "n'" "n<" "o'" "o^" "o''" "\"o" "-:" "r<" "u^0"
114 "u'" "u''" "\"u" "y'" ",t" "'."]
117 . [255 "/H" "'(" "Pd" "$$" " " "H^" "SE" "\"" "I^."
118 ",S" "G(" "J^" "--" " " "Z^." "^o" "/h" "^2" "^3"
119 "'" "u" "h^" "." "'," "i^." ",s" "g(" "j^" "1/2"
120 " " "z^." "`A" "A'" "A^" " " "\"A" "C^." "C^" ",C"
121 "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" " " "~N"
122 "`O" "O'" "O^" "G^." "\"O" "*x" "G^" "`U" "U'" "U^"
123 "\"U" "U(" "S^" "ss" "`a" "a'" "a^" " " "\"a" "c^."
124 "c^" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i"
125 " " "~n" "`o" "o'" "o^" "g^." "\"o" "-:" "g^" "`u"
126 "u'" "u^" "\"u" "u(" "s^" "^."]
129 . [255 "A;" "kk" ",R" "$$" "?I" ",L" "SE" "\"" "S<"
130 "E-" ",G" "/T" "--" "Z<" "'-" "^o" "a;" "';" ",r"
131 "'" "~i" ",l" "'<" "'," "s<" "e-" ",g" "/t" "NG"
132 "z<" "ng" "A-" "A'" "A^" "~A" "\"A" "Ao" "AE" "I;"
133 "C<" "E'" "E;" "\"E" "E^." "I'" "I^" "I-" "/D" ",N"
134 "O-" ",K" "O^" "~O" "\"O" "*x" "/O" "U;" "U'" "U^"
135 "\"U" "~U" "U-" "ss" "a-" "a'" "a^" "~a" "\"a" "ao"
136 "ae" "i;" "c<" "e'" "e;" "\"e" "e^." "i'" "i^" "i-"
137 "/d" ",n" "o-" ",k" "o^" "~o" "\"o" "-:" "/o" "u;"
138 "u'" "u^" "\"u" "~u" "u-" "^."]
141 . [255 "\"E" "Dj" "Gj" "IE" "Dz" "Ii" "Ji" "JE" "Lj"
142 "Nj" "Ts" "Kj" 240 "V%" "Dzh" 65 "B=" 66 226
143 68 69 "Z%" 51 85 "J=" 75 "L=" 77 72
144 79 "P=" 80 67 84 89 232 88 "C=" "C%"
145 "S%" "Sc" "=\"" "Y=" "%\"" "Ee" "Yu" "Ya" 97 98
146 "v=" "g=" 103 101 "z%" "z=" 117 "j=" 107 "l="
147 "m=" "n=" 111 110 112 99 "t=" 121 "f=" 120
148 "c=" "c%" "s%" "sc" "='" "y=" "%'" "ee" "yu" "ya"
149 "N0" "\"e" "dj" "gj" "ie" "dz" "ii" "ji" "je" "lj"
150 "nj" "ts" "kj" 21 "v%" "dzh"]
153 . [255 nil nil nil "$$" nil nil nil nil nil
154 nil nil ",+" "--" nil nil nil nil nil nil
155 nil nil nil nil nil nil nil ";+" nil nil
156 nil "?+" nil "H'" "aM" "aH" "wH" "ah" "yH"
157 "a+" "b+" "tm" "t+" "tk" "g+" "hk" "x+" "d+" "dk"
158 "r+" "z+" "s+" "sn" "c+" "dd" "tj" "zH" "e+" "i+"
159 nil nil nil nil nil "++" "f+" "q+" "k+" "l+"
160 "m+" "n+" "h+" "w+" "j+" "y+" ":+" "\"+" "=+" "/+"
161 "'+" "1+" "3+" "0+" nil nil nil nil nil nil
162 nil nil nil nil nil nil nil]
165 . [255 "9'" "'9" "Pd" nil nil "|" "SE" "\"" "(c)"
166 nil "<<" "~" "--" nil "-M" "^o" "+-" "^2" "^3"
167 "'" "'%" "'A" "^." "'E" "'H" "'I" ">>" "'O" "1/2"
168 "'Y" "W%" "i3" 65 66 "G*" "D*" 69 90 72
169 "TH" 73 74 "L*" 77 78 "C*" 79 "P*" 80
170 nil "S*" 84 89 "F*" 88 "Q*" "W*" "\"I" "\"Y"
171 "a%" "e%" "y%" "i%" "u3" "a*" "b*" "g*" "d*" "e*"
172 "z*" "y*" "h*" "i*" 107 "l*" "m*" "n*" "c*" 111
173 "p*" "r*" "*s" "s*" "t*" 117 "f*" "x*" "q*" "w*"
174 "\"i" "\"u" "'o" "'u" "'w" nil]
177 . [255 nil "|c" "Pd" "$$" "Ye" "|" "SE" "\"" "(c)"
178 "*x" "<<" "~" "--" "(R)" "'-" "^o" "+-" "^2" "^3"
179 "'" "u" ".P" "^." "'," "^1" "-:" ">>" "1/4" "1/2"
180 "3/4" nil nil nil nil nil nil nil nil nil
181 nil nil nil nil nil nil nil nil nil nil
182 nil nil nil nil nil nil nil nil nil nil
183 nil nil nil "=2" "A+" "B+" "G+" "D+" "H+" "W+"
184 "Z+" "X+" "Tj" "J+" "K%" "K+" "L+" "M%" "M+" "N%"
185 "N+" "S+" "E+" "P%" "P+" "Zj" "ZJ" "Q+" "R+" "Sh"
186 "T+" nil nil nil nil nil]
189 . [255 "!I" "|c" "Pd" "$$" "Ye" "|" "SE" "\"" "(c)"
190 "_a" "<<" "~" "--" "(R)" "'-" "^o" "+-" "^2" "^3"
191 "'" "u" ".P" "^." "'," "^1" "_o" ">>" "1/4" "1/2"
192 "3/4" "?I" "`A" "A'" "A^" "~A" "\"A" "Ao" "AE" ",C"
193 "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" "G(" "~N"
194 "`O" "O'" "O^" "~O" "\"O" "*x" "/O" "`U" "U'" "U^"
195 "\"U" "I^." ",S" "ss" "`a" "a'" "a^" "~a" "\"a" "ao"
196 "ae" ",c" "`e" "e'" "e<" "\"e" "e^." "i'" "i^" "i-"
197 "g(" "~n" "`o" "o'" "o^" "~o" "\"o" "-:" "/o" "`u"
198 "u'" "u^" "\"u" "i." ",s" "\"y"]
201 . [255 "B`" "b`" "Pd" "C`" "c`" "D`" "SE" "`W" "(c)"
202 "W'" "d`" "`Y" "--" "(R)" "\"Y" "F`" "f`" "G`" "g`"
203 "M`" "m`" ".P" "P`" "`w" "p`" "w'" "S`" "`y" "\"W"
204 "\"w" "s`" "`A" "A'" "A^" "~A" "\"A" "Ao" "AE" ",C"
205 "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" "W^" "~N"
206 "`O" "O'" "O^" "~O" "\"O" "T`" "/O" "`U" "U'" "U^"
207 "\"U" "Y'" "Y^" "ss" "`a" "a'" "a^" "~a" "\"a" "ao"
208 "ae" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i"
209 "w^" "~n" "`o" "o'" "o^" "~o" "\"o" "t`" "/o" "`u"
210 "u'" "u^" "\"u" "y'" "y^" "\"y"]
213 . [255 "!I" "|c" "Pd" "E=" "Ye" "S<" "SE" "s<" "(c)"
214 "_a" "<<" "~" "--" "(R)" "'-" "^o" "+-" "^2" "^3"
215 "Z<" "u" ".P" "^." "z<" "^1" "_o" ">>" "OE" "oe"
216 "\"Y" "?I" "`A" "A'" "A^" "~A" "\"A" "Ao" "AE" ",C"
217 "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" "-D" "~N"
218 "`O" "O'" "O^" "~O" "\"O" "*x" "/O" "`U" "U'" "U^"
219 "\"U" "Y'" "|P" "ss" "`a" "a'" "a^" "~a" "\"a" "ao"
220 "ae" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i"
221 "-d" "~n" "`o" "o'" "o^" "~o" "\"o" "-:" "/o" "`u"
222 "u'" "u^" "\"u" "y'" "|p" "\"y"]
225 "An alist of MULE ISO-8859 character sets and the strings that
226 should be used to represent the characters from each set on a DOS
227 terminal which does not have corresponding glyphs built into the
228 installed codepage.")
230 (defun IT-display-table-setup (codepage &optional table)
231 "Set up display table TABLE for a DOS terminal which supports
232 glyphs built into the codepage CODEPAGE.
234 If TABLE is nil or omitted, `standard-display-table' is used."
235 (let* ((surrogates IT-character-translations)
236 (disp-tab (or table standard-display-table))
237 (built-in-set (cp-charset-for-codepage codepage))
238 (offset (cp-offset-for-codepage codepage))
240 (symbol-value (intern-soft (format "%s-decode-table" codepage))))
241 (cp-decoder-len (length cp-decoder))
244 ;; Undo the effects of previous call (where they may have used
245 ;; a different codepage) by reverting the display table for the
246 ;; built-in charset to its pristine shape.
248 (aset disp-tab (make-char built-in-set c) nil)
251 (setq association (car surrogates))
252 (setq chset (car association))
253 (let* ((vector (cdr association))
254 (veclen (length vector))
258 (setq glyph (aref vector i))
260 (or (not (equal chset built-in-set))
261 (>= i cp-decoder-len)
262 (null (aref cp-decoder i))))
263 (aset disp-tab (make-char chset (+ i (logand offset 127)))
266 (char-to-string glyph)
267 (if (> (length glyph) 1) (concat "{" glyph "}")
270 (setq surrogates (cdr surrogates)))))
272 (defun dos-cpNNN-setup (codepage)
273 "Set up the MULE environment using the DOS codepage CODEPAGE.
275 This function creates the coding system cpNNN (where NNN is the value
276 of the argument CODEPAGE), and then uses this coding system to set up
277 display tables, and the language environment options as appropriate."
278 (let* ((cp (format "cp%s" codepage))
279 (charset (cp-charset-for-codepage cp))
280 (offset (cp-offset-for-codepage cp)))
281 (cp-make-coding-systems-for-codepage cp charset offset)
282 ;; This is done by set-language-environment.
283 ;;(setq nonascii-translation-table
284 ;; (symbol-value (intern (concat cp "-nonascii-translation-table"))))
285 (set-language-environment (cp-language-for-codepage cp))
286 (set-default-coding-systems (intern (concat cp "-dos")))
287 (set-selection-coding-system (intern (concat cp "-dos")))
288 (set-terminal-coding-system
289 (setq default-terminal-coding-system (intern (concat cp
291 (IT-display-table-setup cp)
292 (prefer-coding-system (intern (concat cp "-dos")))
293 (if default-enable-multibyte-characters
294 ;; We want this in multibyte version only, since unibyte version
295 ;; should not convert non-ASCII characters at all.
296 (setq unibyte-display-via-language-environment t)
297 ;; Let the unibyte version behave as Emacs 19 did. In particular,
298 ;; let it use and display native codepage-specific glyphs for
299 ;; non-ASCII characters. For this to work correctly, we need to
300 ;; establish the correspondence between lower-case letters and their
301 ;; upper-case brethren, as appropriate for the codepage in use. The
302 ;; code below makes this happen.
303 ;; (In the multibyte mode, the appropriate tables are prepared
304 ;; elsewhere, since multibyte Emacs uses normal MULE character sets,
305 ;; which are supported on all platforms.)
309 (modify-syntax-entry ch sy text-mode-syntax-table)
310 (if (boundp 'tex-mode-syntax-table)
311 (modify-syntax-entry ch sy tex-mode-syntax-table))
312 (modify-syntax-entry ch sy (standard-syntax-table))
314 (table (standard-case-table))
315 ;; The following are strings of letters, first lower then
316 ;; upper case. This will look funny on terminals which
317 ;; display other code pages. In particular, what is
318 ;; displayed as blanks or triangles are not what they
319 ;; look like at all! (Use `C-x =' to see what they
324 "‡€�š‚�ƒ¶„Ž…·†�ÆÇ µˆÒ‰ÓŠÔ‹ØŒ×�Þ¡Ö‘’“â”™•ã¢à›�–ê£é—ë˜Yìí¡I£é¤¥ÐÑçè")
326 "‡€�š‚�ƒA„Ž…A†�ˆE‰EŠE‹IŒI�I‘’“O”™•O–U£U˜Y›� A¡I¢O£U¤¥")
328 (t "‡€�š‚�ƒA„Ž…A†�ˆE‰EŠE‹IŒI�I‘’“O”™•O–U£U˜Y A¡I¢O£U¤¥"))))
331 (funcall modify i "_")
335 (while (< i (length chars))
336 (let ((ch1 (aref chars i))
337 (ch2 (aref chars (1+ i))))
339 (set-case-syntax-pair ch2 ch1 table))
342 (mapcar (lambda (b) (set-buffer b) (set-case-table table))
344 (set-standard-case-table table)))
345 ;; Some codepages have sporadic support for Latin-1, Greek, and
346 ;; symbol glyphs, which don't belong to their native character
347 ;; set. It's a nuisance to have all those glyphs here, for all
348 ;; the codepages (for starters, I don't even have references for
349 ;; all the codepages). So I provide a hook for those who want to
350 ;; squeeze every bit of support out of their terminal/font.
351 (run-hooks 'dos-codepage-setup-hook)
354 (defvar cjk-codepages-alist
355 '((932 "Japanese" japanese-shift-jis)
356 (950 "Chinese-BIG5" cn-big5)
357 (936 "Chinese-GB" cn-gb-2312)
358 (949 "Korean" euc-kr))
359 "An alist of Far-Eastern codepages and the names of the associated
360 language and supported coding system.")
362 (defun dos-codepage-setup ()
363 "Set up the MULE environment as appropriate for the installed DOS codepage.
365 This function sets coding systems, display tables, and the language
366 environment options as appropriate for the current value of `dos-codepage'.
368 This function is automatically run at startup via the `term-setup-hook'
369 list. You can (and should) also run it whenever the value of
370 `dos-codepage' changes."
372 (let* ((desc (cdr (assq dos-codepage cjk-codepages-alist)))
374 (coding (car (cdr desc)))
375 coding-dos coding-unix)
377 (dos-cpNNN-setup dos-codepage)
378 ;; We've got one of the Far-Eastern codepages which support
379 ;; MULE native coding systems directly.
380 (setq coding-dos (intern (format "%s-dos" coding))
381 coding-unix (intern (format "%s-unix" coding)))
382 (set-language-environment lang)
383 (set-selection-coding-system coding-dos)
384 (setq file-name-coding-system coding-unix)
385 (set-terminal-coding-system
386 (setq default-terminal-coding-system coding-unix))
387 ;; Assume they support non-ASCII Latin characters like the IBM
388 ;; codepage 437 does.
389 (IT-display-table-setup "cp437")
390 (prefer-coding-system coding-dos)
391 (if default-enable-multibyte-characters
392 (setq unibyte-display-via-language-environment t))
395 ;; We want to delay the terminal and other codepage-related setup
396 ;; until after the terminal is set and user's .emacs is processed,
397 ;; because people might define their `dos-codepage-setup-hook' there.
398 (add-hook 'term-setup-hook 'dos-codepage-setup)
400 ;; In multibyte mode, we want unibyte buffers to be displayed using
401 ;; the terminal coding system, so that they display correctly on the
402 ;; DOS terminal; in unibyte mode we want to see all 8-bit characters
403 ;; verbatim. In both cases, we want the entire range of 8-bit
404 ;; characters to arrive at our display code verbatim.
405 (standard-display-8bit 127 255)
407 ;;; internal.el ends here