Commit | Line | Data |
---|---|---|
c6a6499f | 1 | ;;; internal.el --- support for PC internal terminal -*- coding: raw-text; -*- |
c8b836f6 | 2 | |
0064ab85 | 3 | ;; Copyright (C) 1993, 1994, 1998 Free Software Foundation, Inc. |
c8b836f6 RS |
4 | |
5 | ;; Author: Morten Welinder <terra@diku.dk> | |
c8b836f6 RS |
6 | |
7 | ;; This file is part of GNU Emacs. | |
8 | ||
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) | |
12 | ;; any later version. | |
13 | ||
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. | |
18 | ||
19 | ;; You should have received a copy of the GNU General Public License | |
2fe590dc EN |
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. | |
23 | ||
24 | ;;; Code: | |
25 | ||
c8b836f6 RS |
26 | ;; --------------------------------------------------------------------------- |
27 | ;; keyboard setup -- that's simple! | |
28 | (set-input-mode nil nil 0) | |
c8b836f6 RS |
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) | |
0064ab85 EZ |
50 | |
51 | ;; ---------------------------------------------------------------------- | |
52 | ;; DOS display setup | |
53 | ;; ================= | |
54 | ;; | |
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 | |
62 | ;; rebooting. | |
63 | ;; | |
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. | |
76 | ;; | |
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 | ;; ---------------------------------------------------------------------- | |
89 | ||
90 | (defvar IT-character-translations | |
91 | '( | |
92 | (latin-iso8859-1 | |
93 | . [255 "!I" "|c" "Pd" "$$" "Ye" "|" "SE" "\"" "(c)" | |
94 | "_a" "<<" "~" "--" "(R)" "'-" "^o" "+-" "^2" "^3" | |
95 | "'" "u" ".P" "^." "'," "^1" "_o" ">>" "1/4" "1/2" | |
96 | "3/4" "?I" "`A" "A'" "A^" "~A" "\"A" "Ao" "AE" ",C" | |
97 | "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" "D-" "~N" | |
98 | "`O" "O'" "O^" "~O" "\"O" "*x" "/O" "`U" "U'" "U^" | |
99 | "\"U" "Y'" "TH" "ss" "`a" "a'" "a^" "~a" "\"a" "ao" | |
100 | "ae" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i" | |
101 | "d-" "~n" "`o" "o'" "o^" "~o" "\"o" "-:" "/o" "`u" | |
102 | "u'" "u^" "\"u" "y'" "th" "\"y"] | |
103 | ) | |
104 | (latin-iso8859-2 | |
105 | . [255 "A;" "'(" "/L" "$$" "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" "'."] | |
115 | ) | |
116 | (latin-iso8859-3 | |
117 | . [255 "/H" "'(" "Pd" "$$" " " "H^" "SE" "\"" "I^." | |
118 | ",S" "G(" "J^" "--" " " "Z^." "^o" "/h" "^2" "^3" | |
119 | "'" "u" "h^" "." "'," "i^." ",s" "g(" "j^" "1/2" | |
120 | " " "z^." "`A" "A'" "A^" " " "\"A" "C^." "C^" ",C" | |
121 | "`E" "E'" "E^" "\"E" "`I" "I'" "I^" "\"I" " " "~N" | |
122 | "`O" "O'" "O^" "G^." "\"O" "*x" "G^" "`U" "U'" "U^" | |
123 | "\"U" "U(" "S^" "ss" "`a" "a'" "a^" " " "\"a" "c^." | |
124 | "c^" ",c" "`e" "e'" "e^" "\"e" "`i" "i'" "i^" "\"i" | |
125 | " " "~n" "`o" "o'" "o^" "g^." "\"o" "-:" "g^" "`u" | |
126 | "u'" "u^" "\"u" "u(" "s^" "^."] | |
127 | ) | |
128 | (latin-iso8859-4 | |
129 | . [255 "A;" "kk" ",R" "$$" "?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-" "^."] | |
139 | ) | |
140 | (cyrillic-iso8859-5 | |
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"] | |
151 | ) | |
152 | (arabic-iso8859-6 | |
153 | . [255 nil nil nil "$$" nil nil nil nil nil | |
154 | nil nil ",+" "--" nil nil nil nil nil nil | |
155 | nil nil nil nil nil nil nil ";+" nil nil | |
156 | nil "?+" nil "H'" "aM" "aH" "wH" "ah" "yH" | |
157 | "a+" "b+" "tm" "t+" "tk" "g+" "hk" "x+" "d+" "dk" | |
158 | "r+" "z+" "s+" "sn" "c+" "dd" "tj" "zH" "e+" "i+" | |
159 | nil nil nil nil nil "++" "f+" "q+" "k+" "l+" | |
160 | "m+" "n+" "h+" "w+" "j+" "y+" ":+" "\"+" "=+" "/+" | |
161 | "'+" "1+" "3+" "0+" nil nil nil nil nil nil | |
162 | nil nil nil nil nil nil nil] | |
163 | ) | |
164 | (greek-iso8859-7 | |
165 | . [255 "9'" "'9" "Pd" nil nil "|" "SE" "\"" "(c)" | |
166 | nil "<<" "~" "--" nil "-M" "^o" "+-" "^2" "^3" | |
167 | "'" "'%" "A%" "^." "E%" "Y%" "I%" ">>" "O%" "1/2" | |
168 | "U%" "W%" "i3" "A*" "B*" "G*" "D*" "E*" "Z*" "Y*" | |
169 | "H*" "I*" "K*" "L*" "M*" "N*" "C*" "O*" "P*" "R*" | |
170 | nil "S*" "T*" "U*" "F*" "X*" "Q*" "W*" "J*" "V*" | |
171 | "a%" "e%" "y%" "i%" "u3" "a*" "b*" "g*" "d*" "e*" | |
172 | "z*" "y*" "h*" "i*" "k*" "l*" "m*" "n*" "c*" "o*" | |
173 | "p*" "r*" "*s" "s*" "t*" "u*" "f*" "x*" "q*" "w*" | |
174 | "j*" "v*" "o%" "u%" "w%" nil] | |
175 | ) | |
176 | (hebrew-iso8859-8 | |
177 | . [255 nil "|c" "Pd" "$$" "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] | |
187 | ) | |
188 | (latin-iso8859-9 | |
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"] | |
199 | ) | |
200 | ) | |
201 | "An alist of MULE ISO-8859 character sets and the strings that | |
202 | should be used to represent the characters from each set on a DOS | |
203 | terminal which does not have corresponding glyphs built into the | |
204 | installed codepage.") | |
205 | ||
206 | (defun IT-display-table-setup (codepage &optional table) | |
207 | "Set up display table TABLE for a DOS terminal which supports a | |
208 | glyphs built into the current codepage CODEPAGE. | |
209 | ||
210 | If TABLE is nil or omitted, `standard-display-table' is used." | |
211 | (let* ((surrogates IT-character-translations) | |
212 | (disp-tab (or table standard-display-table)) | |
213 | (built-in-set (cp-charset-for-codepage codepage)) | |
214 | (offset (cp-offset-for-codepage codepage)) | |
215 | (cp-decoder | |
216 | (symbol-value (intern-soft (format "%s-decode-table" codepage)))) | |
217 | (cp-decoder-len (length cp-decoder)) | |
218 | (c offset) | |
219 | association chset) | |
220 | ;; Undo the effects of previous call (where they may have used | |
221 | ;; a different codepage) by reverting the display table for the | |
222 | ;; built-in charset to its pristine shape. | |
223 | (while (< c (+ offset 128)) | |
224 | (aset disp-tab (make-char built-in-set c) nil) | |
225 | (setq c (1+ c))) | |
226 | (while surrogates | |
227 | (setq association (car surrogates)) | |
228 | (setq chset (car association)) | |
229 | (let* ((vector (cdr association)) | |
230 | (veclen (length vector)) | |
231 | (i 0) | |
232 | glyph) | |
233 | (while (< i veclen) | |
234 | (setq glyph (aref vector i)) | |
235 | (if (and glyph | |
236 | (or (not (equal chset built-in-set)) | |
237 | (>= i cp-decoder-len) | |
238 | (null (aref cp-decoder i)))) | |
239 | (aset disp-tab (make-char chset (+ i (logand offset 127))) | |
240 | (vconcat | |
241 | (if (numberp glyph) | |
242 | (char-to-string glyph) | |
243 | (if (> (length glyph) 1) (concat "{" glyph "}") | |
244 | glyph))))) | |
245 | (setq i (1+ i)))) | |
246 | (setq surrogates (cdr surrogates))) | |
247 | ;; Most Windows programs send out apostrophe's as \222. Most DOS | |
248 | ;; fonts contain a different character at that position. Map it | |
249 | ;; to the ASCII apostrophe. | |
250 | (aset standard-display-table 146 [39]))) | |
251 | ||
252 | (defun dos-codepage-setup () | |
253 | "Set up the MULE environment as appropriate for the installed DOS codepage. | |
254 | ||
255 | This function sets coding systems, display tables, and the language | |
256 | environment options as appropriate for the current value of `dos-codepage'. | |
257 | ||
258 | This function is automatically run at startup via the `term-setup-hook' | |
259 | list. You can (and should) also run it whenever the value of | |
260 | `dos-codepage' changes." | |
261 | (interactive) | |
262 | (let* ((cp (format "cp%s" dos-codepage)) | |
263 | (charset (cp-charset-for-codepage cp)) | |
264 | (offset (cp-offset-for-codepage cp))) | |
265 | (cp-make-coding-systems-for-codepage cp charset offset) | |
266 | ;; This is done by set-language-environment. | |
267 | ;;(setq nonascii-translation-table | |
268 | ;; (symbol-value (intern (concat cp "-nonascii-translation-table")))) | |
269 | (set-language-environment (cp-language-for-codepage cp)) | |
270 | (set-default-coding-systems (intern (concat cp "-dos"))) | |
271 | (set-terminal-coding-system | |
272 | (setq default-terminal-coding-system (intern (concat cp | |
273 | "-unix")))) | |
274 | (IT-display-table-setup cp) | |
275 | ;; Some codepages have sporadic support for Latin-1, Greek, and | |
276 | ;; symbol glyphs, which don't belong to their native character | |
277 | ;; set. It's a nuisance to have all those glyphs here, for all | |
278 | ;; the codepages (for starters, I don't even have references for | |
279 | ;; all the codepages). So I provide a hook for those who want to | |
280 | ;; squeeze every bit of support out of their terminal/font. | |
281 | (run-hooks 'dos-codepage-setup-hook) | |
282 | )) | |
283 | ||
284 | ;; We want to delay the terminal and other codepage-related setup | |
285 | ;; until after the terminal is set and user's .emacs is processed, | |
286 | ;; because people might define their `dos-codepage-setup-hook' there. | |
287 | (add-hook 'term-setup-hook 'dos-codepage-setup) | |
288 | ||
289 | ;; In multibyte mode, we want unibyte buffers to be displayed using | |
290 | ;; the terminal coding system, so that they display correctly on the | |
291 | ;; DOS terminal; in unibyte mode we want to see all 8-bit characters | |
292 | ;; verbatim. In both cases, we want the entire range of 8-bit | |
293 | ;; characters to arrive at our display code verbatim. | |
294 | (standard-display-8bit 127 254) | |
295 | ||
296 | (if default-enable-multibyte-characters | |
297 | ;; We want this in multibyte version only, since unibyte version | |
298 | ;; should not convert non-ASCII characters at all. | |
299 | (setq unibyte-display-via-language-environment t) | |
300 | ;; Let the unibyte version behave as Emacs 19 did. In particular, | |
301 | ;; let it use and display native codepage-specific glyphs for | |
302 | ;; non-ASCII characters. For this to work correctly, we need to | |
303 | ;; establish the correspondence between lower-case letters and their | |
304 | ;; upper-case brethren, as appropriate for the codepage in use. The | |
305 | ;; code below makes this happen. | |
306 | ;; (In the multibyte mode, the appropriate tables are prepared | |
307 | ;; elsewhere, since multibyte Emacs uses normal MULE character sets, | |
308 | ;; which are supported on all platforms.) | |
309 | (let* ((i 128) | |
310 | (modify (function | |
311 | (lambda (ch sy) | |
312 | (modify-syntax-entry ch sy text-mode-syntax-table) | |
313 | (if (boundp 'tex-mode-syntax-table) | |
314 | (modify-syntax-entry ch sy tex-mode-syntax-table)) | |
315 | (modify-syntax-entry ch sy (standard-syntax-table)) | |
316 | ))) | |
317 | (table (standard-case-table)) | |
318 | ;; The following are strings of letters, first lower then upper case. | |
319 | ;; This will look funny on terminals which display other code pages. | |
320 | ;; In particular, what is displayed as blanks are not blanks | |
321 | ;; at all! (Use `C-x =' to see what they really are.) | |
322 | (chars | |
323 | (cond | |
324 | ((= dos-codepage 850) | |
325 |