source: trunk/texinfo/makeinfo/lang.c@ 2772

Last change on this file since 2772 was 2617, checked in by bird, 20 years ago

GNU Texinfo 4.8
File size: 33.6 KB
Line 
1/* lang.c -- language-dependent support.
2 $Id: lang.c,v 1.14 2004/11/22 23:57:33 karl Exp $
3
4 Copyright (C) 1999, 2000, 2001, 2002, 2003, 2004 Free Software
5 Foundation, Inc.
6
7 This program is free software; you can redistribute it and/or modify
8 it under the terms of the GNU General Public License as published by
9 the Free Software Foundation; either version 2, or (at your option)
10 any later version.
11
12 This program is distributed in the hope that it will be useful,
13 but WITHOUT ANY WARRANTY; without even the implied warranty of
14 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 GNU General Public License for more details.
16
17 You should have received a copy of the GNU General Public License
18 along with this program; if not, write to the Free Software
19 Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
20
21 Originally written by Karl Heinz Marbaise <kama@hippo.fido.de>. */
22
23#include "system.h"
24#include "cmds.h"
25#include "files.h"
26#include "lang.h"
27#include "makeinfo.h"
28#include "xml.h"
29
30/* Current document encoding. */
31encoding_code_type document_encoding_code = no_encoding;
32
33/* Current language code; default is English. */
34language_code_type language_code = en;
35
36/* By default, unsupported encoding is an empty string. */
37char *unknown_encoding = NULL;
38
39static iso_map_type us_ascii_map [] = {{NULL, 0, 0}}; /* ASCII map is trivial */
40
41/* Translation table between HTML and ISO Codes. The last item is
42 hopefully the Unicode. It might be possible that those Unicodes are
43 not correct, cause I didn't check them. kama */
44static iso_map_type iso8859_1_map [] = {
45 { "nbsp", 0xA0, 0x00A0 },
46 { "iexcl", 0xA1, 0x00A1 },
47 { "cent", 0xA2, 0x00A2 },
48 { "pound", 0xA3, 0x00A3 },
49 { "curren", 0xA4, 0x00A4 },
50 { "yen", 0xA5, 0x00A5 },
51 { "brkbar", 0xA6, 0x00A6 },
52 { "sect", 0xA7, 0x00A7 },
53 { "uml", 0xA8, 0x00A8 },
54 { "copy", 0xA9, 0x00A9 },
55 { "ordf", 0xAA, 0x00AA },
56 { "laquo", 0xAB, 0x00AB },
57 { "not", 0xAC, 0x00AC },
58 { "shy", 0xAD, 0x00AD },
59 { "reg", 0xAE, 0x00AE },
60 { "hibar", 0xAF, 0x00AF },
61 { "deg", 0xB0, 0x00B0 },
62 { "plusmn", 0xB1, 0x00B1 },
63 { "sup2", 0xB2, 0x00B2 },
64 { "sup3", 0xB3, 0x00B3 },
65 { "acute", 0xB4, 0x00B4 },
66 { "micro", 0xB5, 0x00B5 },
67 { "para", 0xB6, 0x00B6 },
68 { "middot", 0xB7, 0x00B7 },
69 { "cedil", 0xB8, 0x00B8 },
70 { "sup1", 0xB9, 0x00B9 },
71 { "ordm", 0xBA, 0x00BA },
72 { "raquo", 0xBB, 0x00BB },
73 { "frac14", 0xBC, 0x00BC },
74 { "frac12", 0xBD, 0x00BD },
75 { "frac34", 0xBE, 0x00BE },
76 { "iquest", 0xBF, 0x00BF },
77 { "Agrave", 0xC0, 0x00C0 },
78 { "Aacute", 0xC1, 0x00C1 },
79 { "Acirc", 0xC2, 0x00C2 },
80 { "Atilde", 0xC3, 0x00C3 },
81 { "Auml", 0xC4, 0x00C4 },
82 { "Aring", 0xC5, 0x00C5 },
83 { "AElig", 0xC6, 0x00C6 },
84 { "Ccedil", 0xC7, 0x00C7 },
85 { "Ccedil", 0xC7, 0x00C7 },
86 { "Egrave", 0xC8, 0x00C8 },
87 { "Eacute", 0xC9, 0x00C9 },
88 { "Ecirc", 0xCA, 0x00CA },
89 { "Euml", 0xCB, 0x00CB },
90 { "Igrave", 0xCC, 0x00CC },
91 { "Iacute", 0xCD, 0x00CD },
92 { "Icirc", 0xCE, 0x00CE },
93 { "Iuml", 0xCF, 0x00CF },
94 { "ETH", 0xD0, 0x00D0 },
95 { "Ntilde", 0xD1, 0x00D1 },
96 { "Ograve", 0xD2, 0x00D2 },
97 { "Oacute", 0xD3, 0x00D3 },
98 { "Ocirc", 0xD4, 0x00D4 },
99 { "Otilde", 0xD5, 0x00D5 },
100 { "Ouml", 0xD6, 0x00D6 },
101 { "times", 0xD7, 0x00D7 },
102 { "Oslash", 0xD8, 0x00D8 },
103 { "Ugrave", 0xD9, 0x00D9 },
104 { "Uacute", 0xDA, 0x00DA },
105 { "Ucirc", 0xDB, 0x00DB },
106 { "Uuml", 0xDC, 0x00DC },
107 { "Yacute", 0xDD, 0x00DD },
108 { "THORN", 0xDE, 0x00DE },
109 { "szlig", 0xDF, 0x00DF },
110 { "agrave", 0xE0, 0x00E0 },
111 { "aacute", 0xE1, 0x00E1 },
112 { "acirc", 0xE2, 0x00E2 },
113 { "atilde", 0xE3, 0x00E3 },
114 { "auml", 0xE4, 0x00E4 },
115 { "aring", 0xE5, 0x00E5 },
116 { "aelig", 0xE6, 0x00E6 },
117 { "ccedil", 0xE7, 0x00E7 },
118 { "egrave", 0xE8, 0x00E8 },
119 { "eacute", 0xE9, 0x00E9 },
120 { "ecirc", 0xEA, 0x00EA },
121 { "euml", 0xEB, 0x00EB },
122 { "igrave", 0xEC, 0x00EC },
123 { "iacute", 0xED, 0x00ED },
124 { "icirc", 0xEE, 0x00EE },
125 { "iuml", 0xEF, 0x00EF },
126 { "eth", 0xF0, 0x00F0 },
127 { "ntilde", 0xF1, 0x00F1 },
128 { "ograve", 0xF2, 0x00F2 },
129 { "oacute", 0xF3, 0x00F3 },
130 { "ocirc", 0xF4, 0x00F4 },
131 { "otilde", 0xF5, 0x00F5 },
132 { "ouml", 0xF6, 0x00F6 },
133 { "divide", 0xF7, 0x00F7 },
134 { "oslash", 0xF8, 0x00F8 },
135 { "ugrave", 0xF9, 0x00F9 },
136 { "uacute", 0xFA, 0x00FA },
137 { "ucirc", 0xFB, 0x00FB },
138 { "uuml", 0xFC, 0x00FC },
139 { "yacute", 0xFD, 0x00FD },
140 { "thorn", 0xFE, 0x00FE },
141 { "yuml", 0xFF, 0x00FF },
142 { NULL, 0, 0 }
143};
144
145
146
147/* ISO 8859-15, also known as Latin 9, differs from Latin 1 in only a
148 few positions. http://www.cs.tut.fi/~jkorpela/latin9.html has a good
149 explanation and listing, summarized here. The names are abbreviated
150 from the official Unicode names, to fit in a decent line length.
151
152 code position
153 dec oct hex latin1 latin1 name latin9 latin9 name
154
155 164 0244 0xA4 U+00A4 currency symbol U+20AC euro sign
156 166 0246 0xA6 U+00A6 broken bar U+0160 S with caron
157 168 0250 0xA8 U+00A8 diaeresis U+0161 s with caron
158 180 0264 0xB4 U+00B4 acute accent U+017D Z with caron
159 184 0270 0xB8 U+00B8 cedilla U+017E z with caron
160 188 0274 0xBC U+00BC fraction 1/4 U+0152 ligature OE
161 189 0275 0xBD U+00BD fraction 1/2 U+0153 ligature oe
162 190 0276 0xBE U+00BE fraction 3/4 U+0178 Y with diaeresis
163*/
164
165static iso_map_type iso8859_15_map [] = {
166 { "nbsp", 0xA0, 0x00A0 },
167 { "iexcl", 0xA1, 0x00A1 },
168 { "cent", 0xA2, 0x00A2 },
169 { "pound", 0xA3, 0x00A3 },
170 { "euro", 0xA4, 0x20AC },
171 { "yen", 0xA5, 0x00A5 },
172 { "Scaron", 0xA6, 0x0160 },
173 { "sect", 0xA7, 0x00A7 },
174 { "scaron", 0xA8, 0x0161 },
175 { "copy", 0xA9, 0x00A9 },
176 { "ordf", 0xAA, 0x00AA },
177 { "laquo", 0xAB, 0x00AB },
178 { "not", 0xAC, 0x00AC },
179 { "shy", 0xAD, 0x00AD },
180 { "reg", 0xAE, 0x00AE },
181 { "hibar", 0xAF, 0x00AF },
182 { "deg", 0xB0, 0x00B0 },
183 { "plusmn", 0xB1, 0x00B1 },
184 { "sup2", 0xB2, 0x00B2 },
185 { "sup3", 0xB3, 0x00B3 },
186 { "Zcaron", 0xB4, 0x017D },
187 { "micro", 0xB5, 0x00B5 },
188 { "para", 0xB6, 0x00B6 },
189 { "middot", 0xB7, 0x00B7 },
190 { "zcaron", 0xB8, 0x017E },
191 { "sup1", 0xB9, 0x00B9 },
192 { "ordm", 0xBA, 0x00BA },
193 { "raquo", 0xBB, 0x00BB },
194 { "OElig", 0xBC, 0x0152 },
195 { "oelig", 0xBD, 0x0153 },
196 { "Yuml", 0xBE, 0x0178 },
197 { "iquest", 0xBF, 0x00BF },
198 { "Agrave", 0xC0, 0x00C0 },
199 { "Aacute", 0xC1, 0x00C1 },
200 { "Acirc", 0xC2, 0x00C2 },
201 { "Atilde", 0xC3, 0x00C3 },
202 { "Auml", 0xC4, 0x00C4 },
203 { "Aring", 0xC5, 0x00C5 },
204 { "AElig", 0xC6, 0x00C6 },
205 { "Ccedil", 0xC7, 0x00C7 },
206 { "Ccedil", 0xC7, 0x00C7 },
207 { "Egrave", 0xC8, 0x00C8 },
208 { "Eacute", 0xC9, 0x00C9 },
209 { "Ecirc", 0xCA, 0x00CA },
210 { "Euml", 0xCB, 0x00CB },
211 { "Igrave", 0xCC, 0x00CC },
212 { "Iacute", 0xCD, 0x00CD },
213 { "Icirc", 0xCE, 0x00CE },
214 { "Iuml", 0xCF, 0x00CF },
215 { "ETH", 0xD0, 0x00D0 },
216 { "Ntilde", 0xD1, 0x00D1 },
217 { "Ograve", 0xD2, 0x00D2 },
218 { "Oacute", 0xD3, 0x00D3 },
219 { "Ocirc", 0xD4, 0x00D4 },
220 { "Otilde", 0xD5, 0x00D5 },
221 { "Ouml", 0xD6, 0x00D6 },
222 { "times", 0xD7, 0x00D7 },
223 { "Oslash", 0xD8, 0x00D8 },
224 { "Ugrave", 0xD9, 0x00D9 },
225 { "Uacute", 0xDA, 0x00DA },
226 { "Ucirc", 0xDB, 0x00DB },
227 { "Uuml", 0xDC, 0x00DC },
228 { "Yacute", 0xDD, 0x00DD },
229 { "THORN", 0xDE, 0x00DE },
230 { "szlig", 0xDF, 0x00DF },
231 { "agrave", 0xE0, 0x00E0 },
232 { "aacute", 0xE1, 0x00E1 },
233 { "acirc", 0xE2, 0x00E2 },
234 { "atilde", 0xE3, 0x00E3 },
235 { "auml", 0xE4, 0x00E4 },
236 { "aring", 0xE5, 0x00E5 },
237 { "aelig", 0xE6, 0x00E6 },
238 { "ccedil", 0xE7, 0x00E7 },
239 { "egrave", 0xE8, 0x00E8 },
240 { "eacute", 0xE9, 0x00E9 },
241 { "ecirc", 0xEA, 0x00EA },
242 { "euml", 0xEB, 0x00EB },
243 { "igrave", 0xEC, 0x00EC },
244 { "iacute", 0xED, 0x00ED },
245 { "icirc", 0xEE, 0x00EE },
246 { "iuml", 0xEF, 0x00EF },
247 { "eth", 0xF0, 0x00F0 },
248 { "ntilde", 0xF1, 0x00F1 },
249 { "ograve", 0xF2, 0x00F2 },
250 { "oacute", 0xF3, 0x00F3 },
251 { "ocirc", 0xF4, 0x00F4 },
252 { "otilde", 0xF5, 0x00F5 },
253 { "ouml", 0xF6, 0x00F6 },
254 { "divide", 0xF7, 0x00F7 },
255 { "oslash", 0xF8, 0x00F8 },
256 { "ugrave", 0xF9, 0x00F9 },
257 { "uacute", 0xFA, 0x00FA },
258 { "ucirc", 0xFB, 0x00FB },
259 { "uuml", 0xFC, 0x00FC },
260 { "yacute", 0xFD, 0x00FD },
261 { "thorn", 0xFE, 0x00FE },
262 { "yuml", 0xFF, 0x00FF },
263 { NULL, 0, 0 }
264};
265
266
267
268
269/* Date: Mon, 31 Mar 2003 00:19:28 +0200
270 From: Wojciech Polak <polak@gnu.org>
271...
272 * Primary Polish site for ogonki is http://www.agh.edu.pl/ogonki/,
273 but it's only in Polish language (it has some interesting links).
274
275 * A general site about ISO 8859-2 at http://nl.ijs.si/gnusl/cee/iso8859-2.html
276
277 * ISO 8859-2 Character Set at http://nl.ijs.si/gnusl/cee/charset.html
278 This site provides almost all information about iso-8859-2,
279 including the character table!!! (must see!)
280
281 * ISO 8859-2 and even HTML entities !!! (must see!)
282 http://people.ssh.fi/mtr/genscript/88592.txt
283
284 * (minor) http://www.agh.edu.pl/ogonki/plchars.html
285 One more table, this time it includes even information about Polish
286 characters in Unicode.
287*/
288
289static iso_map_type iso8859_2_map [] = {
290 { "nbsp", 0xA0, 0x00A0 }, /* NO-BREAK SPACE */
291 { "", 0xA1, 0x0104 }, /* LATIN CAPITAL LETTER A WITH OGONEK */
292 { "", 0xA2, 0x02D8 }, /* BREVE */
293 { "", 0xA3, 0x0141 }, /* LATIN CAPITAL LETTER L WITH STROKE */
294 { "curren", 0xA4, 0x00A4 }, /* CURRENCY SIGN */
295 { "", 0xA5, 0x013D }, /* LATIN CAPITAL LETTER L WITH CARON */
296 { "", 0xA6, 0x015A }, /* LATIN CAPITAL LETTER S WITH ACUTE */
297 { "sect", 0xA7, 0x00A7 }, /* SECTION SIGN */
298 { "uml", 0xA8, 0x00A8 }, /* DIAERESIS */
299 { "", 0xA9, 0x0160 }, /* LATIN CAPITAL LETTER S WITH CARON */
300 { "", 0xAA, 0x015E }, /* LATIN CAPITAL LETTER S WITH CEDILLA */
301 { "", 0xAB, 0x0164 }, /* LATIN CAPITAL LETTER T WITH CARON */
302 { "", 0xAC, 0x0179 }, /* LATIN CAPITAL LETTER Z WITH ACUTE */
303 { "shy", 0xAD, 0x00AD }, /* SOFT HYPHEN */
304 { "", 0xAE, 0x017D }, /* LATIN CAPITAL LETTER Z WITH CARON */
305 { "", 0xAF, 0x017B }, /* LATIN CAPITAL LETTER Z WITH DOT ABOVE */
306 { "deg", 0xB0, 0x00B0 }, /* DEGREE SIGN */
307 { "", 0xB1, 0x0105 }, /* LATIN SMALL LETTER A WITH OGONEK */
308 { "", 0xB2, 0x02DB }, /* OGONEK */
309 { "", 0xB3, 0x0142 }, /* LATIN SMALL LETTER L WITH STROKE */
310 { "acute", 0xB4, 0x00B4 }, /* ACUTE ACCENT */
311 { "", 0xB5, 0x013E }, /* LATIN SMALL LETTER L WITH CARON */
312 { "", 0xB6, 0x015B }, /* LATIN SMALL LETTER S WITH ACUTE */
313 { "", 0xB7, 0x02C7 }, /* CARON (Mandarin Chinese third tone) */
314 { "cedil", 0xB8, 0x00B8 }, /* CEDILLA */
315 { "", 0xB9, 0x0161 }, /* LATIN SMALL LETTER S WITH CARON */
316 { "", 0xBA, 0x015F }, /* LATIN SMALL LETTER S WITH CEDILLA */
317 { "", 0xBB, 0x0165 }, /* LATIN SMALL LETTER T WITH CARON */
318 { "", 0xBC, 0x017A }, /* LATIN SMALL LETTER Z WITH ACUTE */
319 { "", 0xBD, 0x02DD }, /* DOUBLE ACUTE ACCENT */
320 { "", 0xBE, 0x017E }, /* LATIN SMALL LETTER Z WITH CARON */
321 { "", 0xBF, 0x017C }, /* LATIN SMALL LETTER Z WITH DOT ABOVE */
322 { "", 0xC0, 0x0154 }, /* LATIN CAPITAL LETTER R WITH ACUTE */
323 { "", 0xC1, 0x00C1 }, /* LATIN CAPITAL LETTER A WITH ACUTE */
324 { "", 0xC2, 0x00C2 }, /* LATIN CAPITAL LETTER A WITH CIRCUMFLEX */
325 { "", 0xC3, 0x0102 }, /* LATIN CAPITAL LETTER A WITH BREVE */
326 { "", 0xC4, 0x00C4 }, /* LATIN CAPITAL LETTER A WITH DIAERESIS */
327 { "", 0xC5, 0x0139 }, /* LATIN CAPITAL LETTER L WITH ACUTE */
328 { "", 0xC6, 0x0106 }, /* LATIN CAPITAL LETTER C WITH ACUTE */
329 { "", 0xC7, 0x00C7 }, /* LATIN CAPITAL LETTER C WITH CEDILLA */
330 { "", 0xC8, 0x010C }, /* LATIN CAPITAL LETTER C WITH CARON */
331 { "", 0xC9, 0x00C9 }, /* LATIN CAPITAL LETTER E WITH ACUTE */
332 { "", 0xCA, 0x0118 }, /* LATIN CAPITAL LETTER E WITH OGONEK */
333 { "", 0xCB, 0x00CB }, /* LATIN CAPITAL LETTER E WITH DIAERESIS */
334 { "", 0xCC, 0x011A }, /* LATIN CAPITAL LETTER E WITH CARON */
335 { "", 0xCD, 0x00CD }, /* LATIN CAPITAL LETTER I WITH ACUTE */
336 { "", 0xCE, 0x00CE }, /* LATIN CAPITAL LETTER I WITH CIRCUMFLEX */
337 { "", 0xCF, 0x010E }, /* LATIN CAPITAL LETTER D WITH CARON */
338 { "", 0xD0, 0x0110 }, /* LATIN CAPITAL LETTER D WITH STROKE */
339 { "", 0xD1, 0x0143 }, /* LATIN CAPITAL LETTER N WITH ACUTE */
340 { "", 0xD2, 0x0147 }, /* LATIN CAPITAL LETTER N WITH CARON */
341 { "", 0xD3, 0x00D3 }, /* LATIN CAPITAL LETTER O WITH ACUTE */
342 { "", 0xD4, 0x00D4 }, /* LATIN CAPITAL LETTER O WITH CIRCUMFLEX */
343 { "", 0xD5, 0x0150 }, /* LATIN CAPITAL LETTER O WITH DOUBLE ACUTE */
344 { "", 0xD6, 0x00D6 }, /* LATIN CAPITAL LETTER O WITH DIAERESIS */
345 { "times", 0xD7, 0x00D7 }, /* MULTIPLICATION SIGN */
346 { "", 0xD8, 0x0158 }, /* LATIN CAPITAL LETTER R WITH CARON */
347 { "", 0xD9, 0x016E }, /* LATIN CAPITAL LETTER U WITH RING ABOVE */
348 { "", 0xDA, 0x00DA }, /* LATIN CAPITAL LETTER U WITH ACUTE */
349 { "", 0xDB, 0x0170 }, /* LATIN CAPITAL LETTER U WITH DOUBLE ACUTE */
350 { "", 0xDC, 0x00DC }, /* LATIN CAPITAL LETTER U WITH DIAERESIS */
351 { "", 0xDD, 0x00DD }, /* LATIN CAPITAL LETTER Y WITH ACUTE */
352 { "", 0xDE, 0x0162 }, /* LATIN CAPITAL LETTER T WITH CEDILLA */
353 { "", 0xDF, 0x00DF }, /* LATIN SMALL LETTER SHARP S (German) */
354 { "", 0xE0, 0x0155 }, /* LATIN SMALL LETTER R WITH ACUTE */
355 { "", 0xE1, 0x00E1 }, /* LATIN SMALL LETTER A WITH ACUTE */
356 { "", 0xE2, 0x00E2 }, /* LATIN SMALL LETTER A WITH CIRCUMFLEX */
357 { "", 0xE3, 0x0103 }, /* LATIN SMALL LETTER A WITH BREVE */
358 { "", 0xE4, 0x00E4 }, /* LATIN SMALL LETTER A WITH DIAERESIS */
359 { "", 0xE5, 0x013A }, /* LATIN SMALL LETTER L WITH ACUTE */
360 { "", 0xE6, 0x0107 }, /* LATIN SMALL LETTER C WITH ACUTE */
361 { "", 0xE7, 0x00E7 }, /* LATIN SMALL LETTER C WITH CEDILLA */
362 { "", 0xE8, 0x010D }, /* LATIN SMALL LETTER C WITH CARON */
363 { "", 0xE9, 0x00E9 }, /* LATIN SMALL LETTER E WITH ACUTE */
364 { "", 0xEA, 0x0119 }, /* LATIN SMALL LETTER E WITH OGONEK */
365 { "", 0xEB, 0x00EB }, /* LATIN SMALL LETTER E WITH DIAERESIS */
366 { "", 0xEC, 0x011B }, /* LATIN SMALL LETTER E WITH CARON */
367 { "", 0xED, 0x00ED }, /* LATIN SMALL LETTER I WITH ACUTE */
368 { "", 0xEE, 0x00EE }, /* LATIN SMALL LETTER I WITH CIRCUMFLEX */
369 { "", 0xEF, 0x010F }, /* LATIN SMALL LETTER D WITH CARON */
370 { "", 0xF0, 0x0111 }, /* LATIN SMALL LETTER D WITH STROKE */
371 { "", 0xF1, 0x0144 }, /* LATIN SMALL LETTER N WITH ACUTE */
372 { "", 0xF2, 0x0148 }, /* LATIN SMALL LETTER N WITH CARON */
373 { "", 0xF3, 0x00F3 }, /* LATIN SMALL LETTER O WITH ACUTE */
374 { "", 0xF4, 0x00F4 }, /* LATIN SMALL LETTER O WITH CIRCUMFLEX */
375 { "", 0xF5, 0x0151 }, /* LATIN SMALL LETTER O WITH DOUBLE ACUTE */
376 { "", 0xF6, 0x00F6 }, /* LATIN SMALL LETTER O WITH DIAERESIS */
377 { "divide", 0xF7, 0x00F7 }, /* DIVISION SIGN */
378 { "", 0xF8, 0x0159 }, /* LATIN SMALL LETTER R WITH CARON */
379 { "", 0xF9, 0x016F }, /* LATIN SMALL LETTER U WITH RING ABOVE */
380 { "", 0xFA, 0x00FA }, /* LATIN SMALL LETTER U WITH ACUTE */
381 { "", 0xFB, 0x0171 }, /* LATIN SMALL LETTER U WITH DOUBLE ACUTE */
382 { "", 0xFC, 0x00FC }, /* LATIN SMALL LETTER U WITH DIAERESIS */
383 { "", 0xFD, 0x00FD }, /* LATIN SMALL LETTER Y WITH ACUTE */
384 { "", 0xFE, 0x0163 }, /* LATIN SMALL LETTER T WITH CEDILLA */
385 { "", 0xFF, 0x02D9 }, /* DOT ABOVE (Mandarin Chinese light tone) */
386 { NULL, 0, 0 }
387};
388
389encoding_type encoding_table[] = {
390 { no_encoding, "(no encoding)", NULL },
391 { US_ASCII, "US-ASCII", us_ascii_map },
392 { ISO_8859_1, "iso-8859-1", (iso_map_type *) iso8859_1_map },
393 { ISO_8859_2, "iso-8859-2", (iso_map_type *) iso8859_2_map },
394 { ISO_8859_3, "iso-8859-3", NULL },
395 { ISO_8859_4, "iso-8859-4", NULL },
396 { ISO_8859_5, "iso-8859-5", NULL },
397 { ISO_8859_6, "iso-8859-6", NULL },
398 { ISO_8859_7, "iso-8859-7", NULL },
399 { ISO_8859_8, "iso-8859-8", NULL },
400 { ISO_8859_9, "iso-8859-9", NULL },
401 { ISO_8859_10, "iso-8859-10", NULL },
402 { ISO_8859_11, "iso-8859-11", NULL },
403 { ISO_8859_12, "iso-8859-12", NULL },
404 { ISO_8859_13, "iso-8859-13", NULL },
405 { ISO_8859_14, "iso-8859-14", NULL },
406 { ISO_8859_15, "iso-8859-15", (iso_map_type *) iso8859_15_map },
407 { last_encoding_code, NULL, NULL }
408};
409
410
411language_type language_table[] = {
412 { aa, "aa", "Afar" },
413 { ab, "ab", "Abkhazian" },
414 { af, "af", "Afrikaans" },
415 { am, "am", "Amharic" },
416 { ar, "ar", "Arabic" },
417 { as, "as", "Assamese" },
418 { ay, "ay", "Aymara" },
419 { az, "az", "Azerbaijani" },
420 { ba, "ba", "Bashkir" },
421 { be, "be", "Byelorussian" },
422 { bg, "bg", "Bulgarian" },
423 { bh, "bh", "Bihari" },
424 { bi, "bi", "Bislama" },
425 { bn, "bn", "Bengali; Bangla" },
426 { bo, "bo", "Tibetan" },
427 { br, "br", "Breton" },
428 { ca, "ca", "Catalan" },
429 { co, "co", "Corsican" },
430 { cs, "cs", "Czech" },
431 { cy, "cy", "Welsh" },
432 { da, "da", "Danish" },
433 { de, "de", "German" },
434 { dz, "dz", "Bhutani" },
435 { el, "el", "Greek" },
436 { en, "en", "English" },
437 { eo, "eo", "Esperanto" },
438 { es, "es", "Spanish" },
439 { et, "et", "Estonian" },
440 { eu, "eu", "Basque" },
441 { fa, "fa", "Persian" },
442 { fi, "fi", "Finnish" },
443 { fj, "fj", "Fiji" },
444 { fo, "fo", "Faroese" },
445 { fr, "fr", "French" },
446 { fy, "fy", "Frisian" },
447 { ga, "ga", "Irish" },
448 { gd, "gd", "Scots Gaelic" },
449 { gl, "gl", "Galician" },
450 { gn, "gn", "Guarani" },
451 { gu, "gu", "Gujarati" },
452 { ha, "ha", "Hausa" },
453 { he, "he", "Hebrew" } /* (formerly iw) */,
454 { hi, "hi", "Hindi" },
455 { hr, "hr", "Croatian" },
456 { hu, "hu", "Hungarian" },
457 { hy, "hy", "Armenian" },
458 { ia, "ia", "Interlingua" },
459 { id, "id", "Indonesian" } /* (formerly in) */,
460 { ie, "ie", "Interlingue" },
461 { ik, "ik", "Inupiak" },
462 { is, "is", "Icelandic" },
463 { it, "it", "Italian" },
464 { iu, "iu", "Inuktitut" },
465 { ja, "ja", "Japanese" },
466 { jw, "jw", "Javanese" },
467 { ka, "ka", "Georgian" },
468 { kk, "kk", "Kazakh" },
469 { kl, "kl", "Greenlandic" },
470 { km, "km", "Cambodian" },
471 { kn, "kn", "Kannada" },
472 { ko, "ko", "Korean" },
473 { ks, "ks", "Kashmiri" },
474 { ku, "ku", "Kurdish" },
475 { ky, "ky", "Kirghiz" },
476 { la, "la", "Latin" },
477 { ln, "ln", "Lingala" },
478 { lo, "lo", "Laothian" },
479 { lt, "lt", "Lithuanian" },
480 { lv, "lv", "Latvian, Lettish" },
481 { mg, "mg", "Malagasy" },
482 { mi, "mi", "Maori" },
483 { mk, "mk", "Macedonian" },
484 { ml, "ml", "Malayalam" },
485 { mn, "mn", "Mongolian" },
486 { mo, "mo", "Moldavian" },
487 { mr, "mr", "Marathi" },
488 { ms, "ms", "Malay" },
489 { mt, "mt", "Maltese" },
490 { my, "my", "Burmese" },
491 { na, "na", "Nauru" },
492 { ne, "ne", "Nepali" },
493 { nl, "nl", "Dutch" },
494 { no, "no", "Norwegian" },
495 { oc, "oc", "Occitan" },
496 { om, "om", "(Afan) Oromo" },
497 { or, "or", "Oriya" },
498 { pa, "pa", "Punjabi" },
499 { pl, "pl", "Polish" },
500 { ps, "ps", "Pashto, Pushto" },
501 { pt, "pt", "Portuguese" },
502 { qu, "qu", "Quechua" },
503 { rm, "rm", "Rhaeto-Romance" },
504 { rn, "rn", "Kirundi" },
505 { ro, "ro", "Romanian" },
506 { ru, "ru", "Russian" },
507 { rw, "rw", "Kinyarwanda" },
508 { sa, "sa", "Sanskrit" },
509 { sd, "sd", "Sindhi" },
510 { sg, "sg", "Sangro" },
511 { sh, "sh", "Serbo-Croatian" },
512 { si, "si", "Sinhalese" },
513 { sk, "sk", "Slovak" },
514 { sl, "sl", "Slovenian" },
515 { sm, "sm", "Samoan" },
516 { sn, "sn", "Shona" },
517 { so, "so", "Somali" },
518 { sq, "sq", "Albanian" },
519 { sr, "sr", "Serbian" },
520 { ss, "ss", "Siswati" },
521 { st, "st", "Sesotho" },
522 { su, "su", "Sundanese" },
523 { sv, "sv", "Swedish" },
524 { sw, "sw", "Swahili" },
525 { ta, "ta", "Tamil" },
526 { te, "te", "Telugu" },
527 { tg, "tg", "Tajik" },
528 { th, "th", "Thai" },
529 { ti, "ti", "Tigrinya" },
530 { tk, "tk", "Turkmen" },
531 { tl, "tl", "Tagalog" },
532 { tn, "tn", "Setswana" },
533 { to, "to", "Tonga" },
534 { tr, "tr", "Turkish" },
535 { ts, "ts", "Tsonga" },
536 { tt, "tt", "Tatar" },
537 { tw, "tw", "Twi" },
538 { ug, "ug", "Uighur" },
539 { uk, "uk", "Ukrainian" },
540 { ur, "ur", "Urdu" },
541 { uz, "uz", "Uzbek" },
542 { vi, "vi", "Vietnamese" },
543 { vo, "vo", "Volapuk" },
544 { wo, "wo", "Wolof" },
545 { xh, "xh", "Xhosa" },
546 { yi, "yi", "Yiddish" } /* (formerly ji) */,
547 { yo, "yo", "Yoruba" },
548 { za, "za", "Zhuang" },
549 { zh, "zh", "Chinese" },
550 { zu, "zu", "Zulu" },
551 { last_language_code, NULL, NULL }
552};
553
554
555/* @documentlanguage. Maybe we'll do something useful with this in the
556 future. For now, we just recognize it. */
557
558/* XML documents can make use of this data. Unfortunately, it clashes with
559 the structure currently used. So instead of enclosing content into
560 a language block, we just output an empty element. Anyways, a stream based
561 parser can make good use of it. */
562void
563cm_documentlanguage (void)
564{
565 language_code_type c;
566 char *lang_arg;
567
568 /* Read the line with the language code on it. */
569 get_rest_of_line (0, &lang_arg);
570
571 /* Linear search is fine these days. */
572 for (c = aa; c != last_language_code; c++)
573 {
574 if (strcmp (lang_arg, language_table[c].abbrev) == 0)
575 { /* Set current language code. */
576 language_code = c;
577 break;
578 }
579 }
580
581 /* If we didn't find this code, complain. */
582 if (c == last_language_code)
583 warning (_("%s is not a valid ISO 639 language code"), lang_arg);
584
585 if (xml && !docbook)
586 {
587 xml_insert_element_with_attribute (DOCUMENTLANGUAGE, START, "xml:lang=\"%s\"", lang_arg);
588 xml_insert_element (DOCUMENTLANGUAGE, END);
589 }
590
591 free (lang_arg);
592}
593
594
595
596
597/* Search through the encoding table for the given character, returning
598 its equivalent. */
599
600static int
601cm_search_iso_map (char *html)
602{
603 int i;
604 iso_map_type *iso = encoding_table[document_encoding_code].isotab;
605
606 /* If no conversion table for this encoding, quit. */
607 if (!iso)
608 return -1;
609
610 for (i = 0; iso[i].html; i++)
611 {
612 if (strcmp (html, iso[i].html) == 0)
613 return i;
614 }
615
616 return -1;
617}
618
619
620/* @documentencoding. Set the translation table. */
621
622void
623cm_documentencoding (void)
624{
625 if (!handling_delayed_writes)
626 {
627 encoding_code_type enc;
628 char *enc_arg;
629
630 /* This is ugly and probably needs to apply to other commands'
631 argument parsing as well. When we're doing @documentencoding,
632 we're generally in the frontmatter of the document, and so the.
633 expansion in html/xml/docbook would generally be the empty string.
634 (Because those modes wait until the first normal text of the
635 document to start outputting.) The result would thus be a warning
636 "unrecognized encoding name `'". Sigh. */
637 int save_html = html;
638 int save_xml = xml;
639
640 html = 0;
641 xml = 0;
642 get_rest_of_line (1, &enc_arg);
643 html = save_html;
644 xml = save_xml;
645
646 /* See if we have this encoding. */
647 for (enc = no_encoding+1; enc != last_encoding_code; enc++)
648 {
649 if (strcasecmp (enc_arg, encoding_table[enc].encname) == 0)
650 {
651 document_encoding_code = enc;
652 break;
653 }
654 }
655
656 /* If we didn't find this code, complain. */
657 if (enc == last_encoding_code)
658 {
659 warning (_("unrecognized encoding name `%s'"), enc_arg);
660 /* Let the previous one go. */
661 if (unknown_encoding && *unknown_encoding)
662 free (unknown_encoding);
663 unknown_encoding = xstrdup (enc_arg);
664 }
665
666 else if (encoding_table[document_encoding_code].isotab == NULL)
667 warning (_("sorry, encoding `%s' not supported"), enc_arg);
668
669 free (enc_arg);
670 }
671 else if (xml)
672 {
673 char *encoding = current_document_encoding ();
674
675 if (encoding && *encoding)
676 {
677 insert_string (" encoding=\"");
678 insert_string (encoding);
679 insert_string ("\"");
680 }
681
682 free (encoding);
683 }
684}
685
686char *
687current_document_encoding (void)
688{
689 if (document_encoding_code != no_encoding)
690 return xstrdup (encoding_table[document_encoding_code].encname);
691 else if (unknown_encoding && *unknown_encoding)
692 return xstrdup (unknown_encoding);
693 else
694 return xstrdup ("");
695}
696
697
698/* If html or xml output, add &HTML_STR; to the output. If not html and
699 the user requested encoded output, add the real 8-bit character
700 corresponding to HTML_STR from the translation tables. Otherwise,
701 add INFO_STR. */
702
703static void
704add_encoded_char (char *html_str, char *info_str)
705{
706 if (html)
707 add_word_args ("&%s;", html_str);
708 else if (xml)
709 xml_insert_entity (html_str);
710 else if (enable_encoding)
711 {
712 /* Look for HTML_STR in the current translation table. */
713 int rc = cm_search_iso_map (html_str);
714 if (rc >= 0)
715 /* We found it, add the real character. */
716 add_char (encoding_table[document_encoding_code].isotab[rc].bytecode);
717 else
718 { /* We didn't find it, that seems bad. */
719 warning (_("invalid encoded character `%s'"), html_str);
720 add_word (info_str);
721 }
722 }
723 else
724 add_word (info_str);
725}
726
727
728
729
730/* Output an accent for HTML or XML. */
731
732static void
733cm_accent_generic_html (int arg, int start, int end, char *html_supported,
734 int single, int html_solo_standalone, char *html_solo)
735{
736 static int valid_html_accent; /* yikes */
737
738 if (arg == START)
739 { /* If HTML has good support for this character, use it. */
740 if (strchr (html_supported, curchar ()))
741 { /* Yes; start with an ampersand. The character itself
742 will be added later in read_command (makeinfo.c). */
743 int saved_escape_html = escape_html;
744 escape_html = 0;
745 valid_html_accent = 1;
746 add_char ('&');
747 escape_html = saved_escape_html;
748 }
749 else
750 { /* @dotless{i} is not listed in html_supported but HTML entities
751 starting with `i' can be used, such as &icirc;. */
752 int save_input_text_offset = input_text_offset;
753 char *accent_contents;
754
755 get_until_in_braces ("\n", &accent_contents);
756 canon_white (accent_contents);
757
758 if (strstr (accent_contents, "@dotless{i"))
759 {
760 add_word_args ("&%c", accent_contents[9]);
761 valid_html_accent = 1;
762 }
763 else
764 {
765 /* Search for @dotless{} wasn't successful, so rewind. */
766 input_text_offset = save_input_text_offset;
767 valid_html_accent = 0;
768 if (html_solo_standalone)
769 { /* No special HTML support, so produce standalone char. */
770 if (xml)
771 xml_insert_entity (html_solo);
772 else
773 add_word_args ("&%s;", html_solo);
774 }
775 else
776 /* If the html_solo does not exist as standalone character
777 (namely &circ; &grave; &tilde;), then we use
778 the single character version instead. */
779 add_char (single);
780 }
781
782 free (accent_contents);
783 }
784 }
785 else if (arg == END)
786 { /* Only if we saw a valid_html_accent can we use the full
787 HTML accent (umlaut, grave ...). */
788 if (valid_html_accent)
789 {
790 add_word (html_solo);
791 add_char (';');
792 }
793 }
794}
795
796
797static void
798cm_accent_generic_no_headers (int arg, int start, int end, int single,
799 char *html_solo)
800{
801 if (arg == END)
802 {
803 if (no_encoding)
804 add_char (single);
805 else
806 {
807 int rc;
808 char *buffer = xmalloc (1 + strlen (html_solo) + 1);
809 buffer[0] = output_paragraph[end - 1];
810 buffer[1] = 0;
811 strcat (buffer, html_solo);
812
813 rc = cm_search_iso_map (buffer);
814 if (rc >= 0)
815 /* A little bit tricky ;-)
816 Here we replace the character which has
817 been inserted in read_command with
818 the value we have found in converting table
819 Does there exist a better way to do this? kama. */
820 output_paragraph[end - 1]
821 = encoding_table[document_encoding_code].isotab[rc].bytecode;
822 else
823 { /* If we didn't find a translation for this character,
824 put the single instead. E.g., &Xuml; does not exist so X&uml;
825 should be produced. */
826 /* When the below warning is issued, an author has nothing
827 wrong in their document, let alone anything ``fixable''
828 on their side. So it is commented out for now. */
829 /* warning (_("%s is an invalid ISO code, using %c"),
830 buffer, single); */
831 add_char (single);
832 }
833
834 free (buffer);
835 }
836 }
837}
838
839
840
841
842/* Accent commands that take explicit arguments and don't have any
843 special HTML support. */
844
845void
846cm_accent (int arg)
847{
848 int old_escape_html = escape_html;
849 escape_html = 0;
850 if (arg == START)
851 {
852 /* Must come first to avoid ambiguity with overdot. */
853 if (strcmp (command, "udotaccent") == 0) /* underdot */
854 add_char ('.');
855 }
856 else if (arg == END)
857 {
858 if (strcmp (command, "=") == 0) /* macron */
859 add_word ((html || xml) ? "&macr;" : "=");
860 else if (strcmp (command, "H") == 0) /* Hungarian umlaut */
861 add_word ("''");
862 else if (strcmp (command, "dotaccent") == 0) /* overdot */
863 add_meta_char ('.');
864 else if (strcmp (command, "ringaccent") == 0) /* ring */
865 add_char ('*');
866 else if (strcmp (command, "tieaccent") == 0) /* long tie */
867 add_char ('[');
868 else if (strcmp (command, "u") == 0) /* breve */
869 add_char ('(');
870 else if (strcmp (command, "ubaraccent") == 0) /* underbar */
871 add_char ('_');
872 else if (strcmp (command, "v") == 0) /* hacek/check */
873 add_word ((html || xml) ? "&lt;" : "<");
874 }
875 escape_html = old_escape_html;
876}
877
878/* Common routine for the accent characters that have support in HTML.
879 If the character being accented is in the HTML_SUPPORTED set, then
880 produce &CHTML_SOLO;, for example, &Auml; for an A-umlaut. If not in
881 HTML_SUPPORTED, just produce &HTML_SOLO;X for the best we can do with
882 at an X-umlaut. If not producing HTML, just use SINGLE, a
883 character such as " which is the best plain text representation we
884 can manage. If HTML_SOLO_STANDALONE is nonzero the given HTML_SOLO
885 exists as valid standalone character in HTML, e.g., &uml;. */
886
887static void
888cm_accent_generic (int arg, int start, int end, char *html_supported,
889 int single, int html_solo_standalone, char *html_solo)
890{
891 /* Accentuating space characters makes no sense, so issue a warning. */
892 if (arg == START && isspace (input_text[input_text_offset]))
893 warning ("Accent command `@%s' must not be followed by whitespace",
894 command);
895
896 if (html || xml)
897 cm_accent_generic_html (arg, start, end, html_supported,
898 single, html_solo_standalone, html_solo);
899 else if (no_headers)
900 cm_accent_generic_no_headers (arg, start, end, single, html_solo);
901 else if (arg == END)
902 {
903 if (enable_encoding)
904 /* use 8-bit if available */
905 cm_accent_generic_no_headers (arg, start, end, single, html_solo);
906 else
907 /* use regular character */
908 add_char (single);
909 }
910}
911
912void
913cm_accent_umlaut (int arg, int start, int end)
914{
915 cm_accent_generic (arg, start, end, "aouAOUEeIiy", '"', 1, "uml");
916}
917
918void
919cm_accent_acute (int arg, int start, int end)
920{
921 cm_accent_generic (arg, start, end, "AEIOUYaeiouy", '\'', 1, "acute");
922}
923
924void
925cm_accent_cedilla (int arg, int start, int end)
926{
927 cm_accent_generic (arg, start, end, "Cc", ',', 1, "cedil");
928}
929
930void
931cm_accent_hat (int arg, int start, int end)
932{
933 cm_accent_generic (arg, start, end, "AEIOUaeiou", '^', 0, "circ");
934}
935
936void
937cm_accent_grave (int arg, int start, int end)
938{
939 cm_accent_generic (arg, start, end, "AEIOUaeiou", '`', 0, "grave");
940}
941
942void
943cm_accent_tilde (int arg, int start, int end)
944{
945 cm_accent_generic (arg, start, end, "ANOano", '~', 0, "tilde");
946}
947
948
949
950
951/* Non-English letters/characters that don't insert themselves. */
952void
953cm_special_char (int arg)
954{
955 int old_escape_html = escape_html;
956 escape_html = 0;
957
958 if (arg == START)
959 {
960 if ((*command == 'L' || *command == 'l'
961 || *command == 'O' || *command == 'o')
962 && command[1] == 0)
963 { /* Lslash lslash Oslash oslash.
964 Lslash and lslash aren't supported in HTML. */
965 if (command[0] == 'O')
966 add_encoded_char ("Oslash", "/O");
967 else if (command[0] == 'o')
968 add_encoded_char ("oslash", "/o");
969 else
970 add_word_args ("/%c", command[0]);
971 }
972 else if (strcmp (command, "exclamdown") == 0)
973 add_encoded_char ("iexcl", "!");
974 else if (strcmp (command, "questiondown") == 0)
975 add_encoded_char ("iquest", "?");
976 else if (strcmp (command, "euro") == 0)
977 /* http://www.cs.tut.fi/~jkorpela/html/euro.html suggests that
978 &euro; degrades best in old browsers. */
979 add_encoded_char ("euro", "Euro ");
980 else if (strcmp (command, "pounds") == 0)
981 add_encoded_char ("pound" , "#");
982 else if (strcmp (command, "ordf") == 0)
983 add_encoded_char ("ordf" , "a");
984 else if (strcmp (command, "ordm") == 0)
985 add_encoded_char ("ordm" , "o");
986 else if (strcmp (command, "AE") == 0)
987 add_encoded_char ("AElig", command);
988 else if (strcmp (command, "ae") == 0)
989 add_encoded_char ("aelig", command);
990 else if (strcmp (command, "OE") == 0)
991 add_encoded_char ("OElig", command);
992 else if (strcmp (command, "oe") == 0)
993 add_encoded_char ("oelig", command);
994 else if (strcmp (command, "AA") == 0)
995 add_encoded_char ("Aring", command);
996 else if (strcmp (command, "aa") == 0)
997 add_encoded_char ("aring", command);
998 else if (strcmp (command, "ss") == 0)
999 add_encoded_char ("szlig", command);
1000 else
1001 line_error ("cm_special_char internal error: command=@%s", command);
1002 }
1003 escape_html = old_escape_html;
1004}
1005
1006/* Dotless i or j. */
1007void
1008cm_dotless (int arg, int start, int end)
1009{
1010 if (arg == END)
1011 {
1012 xml_no_para --;
1013 if (output_paragraph[start] != 'i' && output_paragraph[start] != 'j')
1014 /* This error message isn't perfect if the argument is multiple
1015 characters, but it doesn't seem worth getting right. */
1016 line_error (_("%c%s expects `i' or `j' as argument, not `%c'"),
1017 COMMAND_PREFIX, command, output_paragraph[start]);
1018
1019 else if (end - start != 1)
1020 line_error (_("%c%s expects a single character `i' or `j' as argument"),
1021 COMMAND_PREFIX, command);
1022
1023 /* We've already inserted the `i' or `j', so nothing to do. */
1024 }
1025 else
1026 xml_no_para ++;
1027}
Note: See TracBrowser for help on using the repository browser.