xref: /openbsd/gnu/usr.bin/texinfo/makeinfo/lang.c (revision a1acfa9b)
1 /* lang.c -- language-dependent support.
2    $Id: lang.c,v 1.1.1.3 2006/07/17 16:03:47 espie 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.  */
31 encoding_code_type document_encoding_code = no_encoding;
32 
33 /* Current language code; default is English.  */
34 language_code_type language_code = en;
35 
36 /* By default, unsupported encoding is an empty string.  */
37 char *unknown_encoding = NULL;
38 
39 static 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 */
44 static 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 /* ISO 8859-15, also known as Latin 9, differs from Latin 1 in only a
147    few positions.  http://www.cs.tut.fi/~jkorpela/latin9.html has a good
148    explanation and listing, summarized here.  The names are abbreviated
149    from the official Unicode names, to fit in a decent line length.
150 
151   code position
152   dec	oct   hex   latin1 latin1 name	      latin9 latin9 name
153 
154   164  0244  0xA4   U+00A4 currency symbol    U+20AC euro sign
155   166  0246  0xA6   U+00A6 broken bar	      U+0160 S with caron
156   168  0250  0xA8   U+00A8 diaeresis	      U+0161 s with caron
157   180  0264  0xB4   U+00B4 acute accent	      U+017D Z with caron
158   184  0270  0xB8   U+00B8 cedilla	      U+017E z with caron
159   188  0274  0xBC   U+00BC fraction 1/4	      U+0152 ligature OE
160   189  0275  0xBD   U+00BD fraction 1/2	      U+0153 ligature oe
161   190  0276  0xBE   U+00BE fraction 3/4	      U+0178 Y with diaeresis
162 */
163 
164 static iso_map_type iso8859_15_map [] = {
165   { "nbsp",   0xA0, 0x00A0 },
166   { "iexcl",  0xA1, 0x00A1 },
167   { "cent",   0xA2, 0x00A2 },
168   { "pound",  0xA3, 0x00A3 },
169   { "euro",   0xA4, 0x20AC },
170   { "yen",    0xA5, 0x00A5 },
171   { "Scaron", 0xA6, 0x0160 },
172   { "sect",   0xA7, 0x00A7 },
173   { "scaron", 0xA8, 0x0161 },
174   { "copy",   0xA9, 0x00A9 },
175   { "ordf",   0xAA, 0x00AA },
176   { "laquo",  0xAB, 0x00AB },
177   { "not",    0xAC, 0x00AC },
178   { "shy",    0xAD, 0x00AD },
179   { "reg",    0xAE, 0x00AE },
180   { "hibar",  0xAF, 0x00AF },
181   { "deg",    0xB0, 0x00B0 },
182   { "plusmn", 0xB1, 0x00B1 },
183   { "sup2",   0xB2, 0x00B2 },
184   { "sup3",   0xB3, 0x00B3 },
185   { "Zcaron", 0xB4, 0x017D },
186   { "micro",  0xB5, 0x00B5 },
187   { "para",   0xB6, 0x00B6 },
188   { "middot", 0xB7, 0x00B7 },
189   { "zcaron", 0xB8, 0x017E },
190   { "sup1",   0xB9, 0x00B9 },
191   { "ordm",   0xBA, 0x00BA },
192   { "raquo",  0xBB, 0x00BB },
193   { "OElig",  0xBC, 0x0152 },
194   { "oelig",  0xBD, 0x0153 },
195   { "Yuml",   0xBE, 0x0178 },
196   { "iquest", 0xBF, 0x00BF },
197   { "Agrave", 0xC0, 0x00C0 },
198   { "Aacute", 0xC1, 0x00C1 },
199   { "Acirc",  0xC2, 0x00C2 },
200   { "Atilde", 0xC3, 0x00C3 },
201   { "Auml",   0xC4, 0x00C4 },
202   { "Aring",  0xC5, 0x00C5 },
203   { "AElig",  0xC6, 0x00C6 },
204   { "Ccedil", 0xC7, 0x00C7 },
205   { "Ccedil", 0xC7, 0x00C7 },
206   { "Egrave", 0xC8, 0x00C8 },
207   { "Eacute", 0xC9, 0x00C9 },
208   { "Ecirc",  0xCA, 0x00CA },
209   { "Euml",   0xCB, 0x00CB },
210   { "Igrave", 0xCC, 0x00CC },
211   { "Iacute", 0xCD, 0x00CD },
212   { "Icirc",  0xCE, 0x00CE },
213   { "Iuml",   0xCF, 0x00CF },
214   { "ETH",    0xD0, 0x00D0 },
215   { "Ntilde", 0xD1, 0x00D1 },
216   { "Ograve", 0xD2, 0x00D2 },
217   { "Oacute", 0xD3, 0x00D3 },
218   { "Ocirc",  0xD4, 0x00D4 },
219   { "Otilde", 0xD5, 0x00D5 },
220   { "Ouml",   0xD6, 0x00D6 },
221   { "times",  0xD7, 0x00D7 },
222   { "Oslash", 0xD8, 0x00D8 },
223   { "Ugrave", 0xD9, 0x00D9 },
224   { "Uacute", 0xDA, 0x00DA },
225   { "Ucirc",  0xDB, 0x00DB },
226   { "Uuml",   0xDC, 0x00DC },
227   { "Yacute", 0xDD, 0x00DD },
228   { "THORN",  0xDE, 0x00DE },
229   { "szlig",  0xDF, 0x00DF },
230   { "agrave", 0xE0, 0x00E0 },
231   { "aacute", 0xE1, 0x00E1 },
232   { "acirc",  0xE2, 0x00E2 },
233   { "atilde", 0xE3, 0x00E3 },
234   { "auml",   0xE4, 0x00E4 },
235   { "aring",  0xE5, 0x00E5 },
236   { "aelig",  0xE6, 0x00E6 },
237   { "ccedil", 0xE7, 0x00E7 },
238   { "egrave", 0xE8, 0x00E8 },
239   { "eacute", 0xE9, 0x00E9 },
240   { "ecirc",  0xEA, 0x00EA },
241   { "euml",   0xEB, 0x00EB },
242   { "igrave", 0xEC, 0x00EC },
243   { "iacute", 0xED, 0x00ED },
244   { "icirc",  0xEE, 0x00EE },
245   { "iuml",   0xEF, 0x00EF },
246   { "eth",    0xF0, 0x00F0 },
247   { "ntilde", 0xF1, 0x00F1 },
248   { "ograve", 0xF2, 0x00F2 },
249   { "oacute", 0xF3, 0x00F3 },
250   { "ocirc",  0xF4, 0x00F4 },
251   { "otilde", 0xF5, 0x00F5 },
252   { "ouml",   0xF6, 0x00F6 },
253   { "divide", 0xF7, 0x00F7 },
254   { "oslash", 0xF8, 0x00F8 },
255   { "ugrave", 0xF9, 0x00F9 },
256   { "uacute", 0xFA, 0x00FA },
257   { "ucirc",  0xFB, 0x00FB },
258   { "uuml",   0xFC, 0x00FC },
259   { "yacute", 0xFD, 0x00FD },
260   { "thorn",  0xFE, 0x00FE },
261   { "yuml",   0xFF, 0x00FF },
262   { NULL, 0, 0 }
263 };
264 
265 
266 
267 /* Date: Mon, 31 Mar 2003 00:19:28 +0200
268    From: Wojciech Polak <polak@gnu.org>
269 ...
270  * Primary Polish site for ogonki is http://www.agh.edu.pl/ogonki/,
271    but it's only in Polish language (it has some interesting links).
272 
273  * A general site about ISO 8859-2 at http://nl.ijs.si/gnusl/cee/iso8859-2.html
274 
275  * ISO 8859-2 Character Set at http://nl.ijs.si/gnusl/cee/charset.html
276    This site provides almost all information about iso-8859-2,
277    including the character table!!! (must see!)
278 
279  * ISO 8859-2 and even HTML entities !!! (must see!)
280    http://people.ssh.fi/mtr/genscript/88592.txt
281 
282  * (minor) http://www.agh.edu.pl/ogonki/plchars.html
283    One more table, this time it includes even information about Polish
284    characters in Unicode.
285 */
286 
287 static iso_map_type iso8859_2_map [] = {
288   { "nbsp",	0xA0, 0x00A0 }, /* NO-BREAK SPACE */
289   { "",	0xA1, 0x0104 }, /* LATIN CAPITAL LETTER A WITH OGONEK */
290   { "",	0xA2, 0x02D8 }, /* BREVE */
291   { "",	0xA3, 0x0141 }, /* LATIN CAPITAL LETTER L WITH STROKE */
292   { "curren",	0xA4, 0x00A4 }, /* CURRENCY SIGN */
293   { "",	0xA5, 0x013D }, /* LATIN CAPITAL LETTER L WITH CARON */
294   { "",	0xA6, 0x015A }, /* LATIN CAPITAL LETTER S WITH ACUTE */
295   { "sect",	0xA7, 0x00A7 }, /* SECTION SIGN */
296   { "uml",	0xA8, 0x00A8 }, /* DIAERESIS */
297   { "",	0xA9, 0x0160 }, /* LATIN CAPITAL LETTER S WITH CARON */
298   { "",	0xAA, 0x015E }, /* LATIN CAPITAL LETTER S WITH CEDILLA */
299   { "",	0xAB, 0x0164 }, /* LATIN CAPITAL LETTER T WITH CARON */
300   { "",	0xAC, 0x0179 }, /* LATIN CAPITAL LETTER Z WITH ACUTE */
301   { "shy",	0xAD, 0x00AD }, /* SOFT HYPHEN */
302   { "",	0xAE, 0x017D }, /* LATIN CAPITAL LETTER Z WITH CARON */
303   { "",	0xAF, 0x017B }, /* LATIN CAPITAL LETTER Z WITH DOT ABOVE */
304   { "deg",	0xB0, 0x00B0 }, /* DEGREE SIGN */
305   { "",	0xB1, 0x0105 }, /* LATIN SMALL LETTER A WITH OGONEK */
306   { "",	0xB2, 0x02DB }, /* OGONEK */
307   { "",	0xB3, 0x0142 }, /* LATIN SMALL LETTER L WITH STROKE */
308   { "acute",	0xB4, 0x00B4 }, /* ACUTE ACCENT */
309   { "",	0xB5, 0x013E }, /* LATIN SMALL LETTER L WITH CARON */
310   { "",	0xB6, 0x015B }, /* LATIN SMALL LETTER S WITH ACUTE */
311   { "",	0xB7, 0x02C7 }, /* CARON (Mandarin Chinese third tone) */
312   { "cedil",	0xB8, 0x00B8 }, /* CEDILLA */
313   { "",	0xB9, 0x0161 }, /* LATIN SMALL LETTER S WITH CARON */
314   { "",	0xBA, 0x015F }, /* LATIN SMALL LETTER S WITH CEDILLA */
315   { "",	0xBB, 0x0165 }, /* LATIN SMALL LETTER T WITH CARON */
316   { "",	0xBC, 0x017A }, /* LATIN SMALL LETTER Z WITH ACUTE */
317   { "",	0xBD, 0x02DD }, /* DOUBLE ACUTE ACCENT */
318   { "",	0xBE, 0x017E }, /* LATIN SMALL LETTER Z WITH CARON */
319   { "",	0xBF, 0x017C }, /* LATIN SMALL LETTER Z WITH DOT ABOVE */
320   { "",	0xC0, 0x0154 }, /* LATIN CAPITAL LETTER R WITH ACUTE */
321   { "",	0xC1, 0x00C1 }, /* LATIN CAPITAL LETTER A WITH ACUTE */
322   { "",	0xC2, 0x00C2 }, /* LATIN CAPITAL LETTER A WITH CIRCUMFLEX */
323   { "",	0xC3, 0x0102 }, /* LATIN CAPITAL LETTER A WITH BREVE */
324   { "",	0xC4, 0x00C4 }, /* LATIN CAPITAL LETTER A WITH DIAERESIS */
325   { "",	0xC5, 0x0139 }, /* LATIN CAPITAL LETTER L WITH ACUTE */
326   { "",	0xC6, 0x0106 }, /* LATIN CAPITAL LETTER C WITH ACUTE */
327   { "",	0xC7, 0x00C7 }, /* LATIN CAPITAL LETTER C WITH CEDILLA */
328   { "",	0xC8, 0x010C }, /* LATIN CAPITAL LETTER C WITH CARON */
329   { "",	0xC9, 0x00C9 }, /* LATIN CAPITAL LETTER E WITH ACUTE */
330   { "",	0xCA, 0x0118 }, /* LATIN CAPITAL LETTER E WITH OGONEK */
331   { "",	0xCB, 0x00CB }, /* LATIN CAPITAL LETTER E WITH DIAERESIS */
332   { "",	0xCC, 0x011A }, /* LATIN CAPITAL LETTER E WITH CARON */
333   { "",	0xCD, 0x00CD }, /* LATIN CAPITAL LETTER I WITH ACUTE */
334   { "",	0xCE, 0x00CE }, /* LATIN CAPITAL LETTER I WITH CIRCUMFLEX */
335   { "",	0xCF, 0x010E }, /* LATIN CAPITAL LETTER D WITH CARON */
336   { "",	0xD0, 0x0110 }, /* LATIN CAPITAL LETTER D WITH STROKE */
337   { "",	0xD1, 0x0143 }, /* LATIN CAPITAL LETTER N WITH ACUTE */
338   { "",	0xD2, 0x0147 }, /* LATIN CAPITAL LETTER N WITH CARON */
339   { "",	0xD3, 0x00D3 }, /* LATIN CAPITAL LETTER O WITH ACUTE */
340   { "",	0xD4, 0x00D4 }, /* LATIN CAPITAL LETTER O WITH CIRCUMFLEX */
341   { "",	0xD5, 0x0150 }, /* LATIN CAPITAL LETTER O WITH DOUBLE ACUTE */
342   { "",	0xD6, 0x00D6 }, /* LATIN CAPITAL LETTER O WITH DIAERESIS */
343   { "times",	0xD7, 0x00D7 }, /* MULTIPLICATION SIGN */
344   { "",	0xD8, 0x0158 }, /* LATIN CAPITAL LETTER R WITH CARON */
345   { "",	0xD9, 0x016E }, /* LATIN CAPITAL LETTER U WITH RING ABOVE */
346   { "",	0xDA, 0x00DA }, /* LATIN CAPITAL LETTER U WITH ACUTE */
347   { "",	0xDB, 0x0170 }, /* LATIN CAPITAL LETTER U WITH DOUBLE ACUTE */
348   { "",	0xDC, 0x00DC }, /* LATIN CAPITAL LETTER U WITH DIAERESIS */
349   { "",	0xDD, 0x00DD }, /* LATIN CAPITAL LETTER Y WITH ACUTE */
350   { "",	0xDE, 0x0162 }, /* LATIN CAPITAL LETTER T WITH CEDILLA */
351   { "",	0xDF, 0x00DF }, /* LATIN SMALL LETTER SHARP S (German) */
352   { "",	0xE0, 0x0155 }, /* LATIN SMALL LETTER R WITH ACUTE */
353   { "",	0xE1, 0x00E1 }, /* LATIN SMALL LETTER A WITH ACUTE */
354   { "",	0xE2, 0x00E2 }, /* LATIN SMALL LETTER A WITH CIRCUMFLEX */
355   { "",	0xE3, 0x0103 }, /* LATIN SMALL LETTER A WITH BREVE */
356   { "",	0xE4, 0x00E4 }, /* LATIN SMALL LETTER A WITH DIAERESIS */
357   { "",	0xE5, 0x013A }, /* LATIN SMALL LETTER L WITH ACUTE */
358   { "",	0xE6, 0x0107 }, /* LATIN SMALL LETTER C WITH ACUTE */
359   { "",	0xE7, 0x00E7 }, /* LATIN SMALL LETTER C WITH CEDILLA */
360   { "",	0xE8, 0x010D }, /* LATIN SMALL LETTER C WITH CARON */
361   { "",	0xE9, 0x00E9 }, /* LATIN SMALL LETTER E WITH ACUTE */
362   { "",	0xEA, 0x0119 }, /* LATIN SMALL LETTER E WITH OGONEK */
363   { "",	0xEB, 0x00EB }, /* LATIN SMALL LETTER E WITH DIAERESIS */
364   { "",	0xEC, 0x011B }, /* LATIN SMALL LETTER E WITH CARON */
365   { "",	0xED, 0x00ED }, /* LATIN SMALL LETTER I WITH ACUTE */
366   { "",	0xEE, 0x00EE }, /* LATIN SMALL LETTER I WITH CIRCUMFLEX */
367   { "",	0xEF, 0x010F }, /* LATIN SMALL LETTER D WITH CARON */
368   { "",	0xF0, 0x0111 }, /* LATIN SMALL LETTER D WITH STROKE */
369   { "",	0xF1, 0x0144 }, /* LATIN SMALL LETTER N WITH ACUTE */
370   { "",	0xF2, 0x0148 }, /* LATIN SMALL LETTER N WITH CARON */
371   { "",	0xF3, 0x00F3 }, /* LATIN SMALL LETTER O WITH ACUTE */
372   { "",	0xF4, 0x00F4 }, /* LATIN SMALL LETTER O WITH CIRCUMFLEX */
373   { "",	0xF5, 0x0151 }, /* LATIN SMALL LETTER O WITH DOUBLE ACUTE */
374   { "",	0xF6, 0x00F6 }, /* LATIN SMALL LETTER O WITH DIAERESIS */
375   { "divide",	0xF7, 0x00F7 }, /* DIVISION SIGN */
376   { "",	0xF8, 0x0159 }, /* LATIN SMALL LETTER R WITH CARON */
377   { "",	0xF9, 0x016F }, /* LATIN SMALL LETTER U WITH RING ABOVE */
378   { "",	0xFA, 0x00FA }, /* LATIN SMALL LETTER U WITH ACUTE */
379   { "",	0xFB, 0x0171 }, /* LATIN SMALL LETTER U WITH DOUBLE ACUTE */
380   { "",	0xFC, 0x00FC }, /* LATIN SMALL LETTER U WITH DIAERESIS */
381   { "",	0xFD, 0x00FD }, /* LATIN SMALL LETTER Y WITH ACUTE */
382   { "",	0xFE, 0x0163 }, /* LATIN SMALL LETTER T WITH CEDILLA */
383   { "",	0xFF, 0x02D9 }, /* DOT ABOVE (Mandarin Chinese light tone) */
384   { NULL, 0, 0 }
385 };
386 
387 encoding_type encoding_table[] = {
388   { no_encoding, "(no encoding)", NULL },
389   { US_ASCII,    "US-ASCII",    us_ascii_map },
390   { ISO_8859_1,  "iso-8859-1",  (iso_map_type *) iso8859_1_map },
391   { ISO_8859_2,  "iso-8859-2",  (iso_map_type *) iso8859_2_map },
392   { ISO_8859_3,  "iso-8859-3",  NULL },
393   { ISO_8859_4,  "iso-8859-4",  NULL },
394   { ISO_8859_5,  "iso-8859-5",  NULL },
395   { ISO_8859_6,  "iso-8859-6",  NULL },
396   { ISO_8859_7,  "iso-8859-7",  NULL },
397   { ISO_8859_8,  "iso-8859-8",  NULL },
398   { ISO_8859_9,  "iso-8859-9",  NULL },
399   { ISO_8859_10, "iso-8859-10", NULL },
400   { ISO_8859_11, "iso-8859-11", NULL },
401   { ISO_8859_12, "iso-8859-12", NULL },
402   { ISO_8859_13, "iso-8859-13", NULL },
403   { ISO_8859_14, "iso-8859-14", NULL },
404   { ISO_8859_15, "iso-8859-15", (iso_map_type *) iso8859_15_map },
405   { last_encoding_code, NULL, NULL }
406 };
407 
408 
409 language_type language_table[] = {
410   { aa, "aa", "Afar" },
411   { ab, "ab", "Abkhazian" },
412   { af, "af", "Afrikaans" },
413   { am, "am", "Amharic" },
414   { ar, "ar", "Arabic" },
415   { as, "as", "Assamese" },
416   { ay, "ay", "Aymara" },
417   { az, "az", "Azerbaijani" },
418   { ba, "ba", "Bashkir" },
419   { be, "be", "Byelorussian" },
420   { bg, "bg", "Bulgarian" },
421   { bh, "bh", "Bihari" },
422   { bi, "bi", "Bislama" },
423   { bn, "bn", "Bengali; Bangla" },
424   { bo, "bo", "Tibetan" },
425   { br, "br", "Breton" },
426   { ca, "ca", "Catalan" },
427   { co, "co", "Corsican" },
428   { cs, "cs", "Czech" },
429   { cy, "cy", "Welsh" },
430   { da, "da", "Danish" },
431   { de, "de", "German" },
432   { dz, "dz", "Bhutani" },
433   { el, "el", "Greek" },
434   { en, "en", "English" },
435   { eo, "eo", "Esperanto" },
436   { es, "es", "Spanish" },
437   { et, "et", "Estonian" },
438   { eu, "eu", "Basque" },
439   { fa, "fa", "Persian" },
440   { fi, "fi", "Finnish" },
441   { fj, "fj", "Fiji" },
442   { fo, "fo", "Faroese" },
443   { fr, "fr", "French" },
444   { fy, "fy", "Frisian" },
445   { ga, "ga", "Irish" },
446   { gd, "gd", "Scots Gaelic" },
447   { gl, "gl", "Galician" },
448   { gn, "gn", "Guarani" },
449   { gu, "gu", "Gujarati" },
450   { ha, "ha", "Hausa" },
451   { he, "he", "Hebrew" } /* (formerly iw) */,
452   { hi, "hi", "Hindi" },
453   { hr, "hr", "Croatian" },
454   { hu, "hu", "Hungarian" },
455   { hy, "hy", "Armenian" },
456   { ia, "ia", "Interlingua" },
457   { id, "id", "Indonesian" } /* (formerly in) */,
458   { ie, "ie", "Interlingue" },
459   { ik, "ik", "Inupiak" },
460   { is, "is", "Icelandic" },
461   { it, "it", "Italian" },
462   { iu, "iu", "Inuktitut" },
463   { ja, "ja", "Japanese" },
464   { jw, "jw", "Javanese" },
465   { ka, "ka", "Georgian" },
466   { kk, "kk", "Kazakh" },
467   { kl, "kl", "Greenlandic" },
468   { km, "km", "Cambodian" },
469   { kn, "kn", "Kannada" },
470   { ko, "ko", "Korean" },
471   { ks, "ks", "Kashmiri" },
472   { ku, "ku", "Kurdish" },
473   { ky, "ky", "Kirghiz" },
474   { la, "la", "Latin" },
475   { ln, "ln", "Lingala" },
476   { lo, "lo", "Laothian" },
477   { lt, "lt", "Lithuanian" },
478   { lv, "lv", "Latvian, Lettish" },
479   { mg, "mg", "Malagasy" },
480   { mi, "mi", "Maori" },
481   { mk, "mk", "Macedonian" },
482   { ml, "ml", "Malayalam" },
483   { mn, "mn", "Mongolian" },
484   { mo, "mo", "Moldavian" },
485   { mr, "mr", "Marathi" },
486   { ms, "ms", "Malay" },
487   { mt, "mt", "Maltese" },
488   { my, "my", "Burmese" },
489   { na, "na", "Nauru" },
490   { ne, "ne", "Nepali" },
491   { nl, "nl", "Dutch" },
492   { no, "no", "Norwegian" },
493   { oc, "oc", "Occitan" },
494   { om, "om", "(Afan) Oromo" },
495   { or, "or", "Oriya" },
496   { pa, "pa", "Punjabi" },
497   { pl, "pl", "Polish" },
498   { ps, "ps", "Pashto, Pushto" },
499   { pt, "pt", "Portuguese" },
500   { qu, "qu", "Quechua" },
501   { rm, "rm", "Rhaeto-Romance" },
502   { rn, "rn", "Kirundi" },
503   { ro, "ro", "Romanian" },
504   { ru, "ru", "Russian" },
505   { rw, "rw", "Kinyarwanda" },
506   { sa, "sa", "Sanskrit" },
507   { sd, "sd", "Sindhi" },
508   { sg, "sg", "Sangro" },
509   { sh, "sh", "Serbo-Croatian" },
510   { si, "si", "Sinhalese" },
511   { sk, "sk", "Slovak" },
512   { sl, "sl", "Slovenian" },
513   { sm, "sm", "Samoan" },
514   { sn, "sn", "Shona" },
515   { so, "so", "Somali" },
516   { sq, "sq", "Albanian" },
517   { sr, "sr", "Serbian" },
518   { ss, "ss", "Siswati" },
519   { st, "st", "Sesotho" },
520   { su, "su", "Sundanese" },
521   { sv, "sv", "Swedish" },
522   { sw, "sw", "Swahili" },
523   { ta, "ta", "Tamil" },
524   { te, "te", "Telugu" },
525   { tg, "tg", "Tajik" },
526   { th, "th", "Thai" },
527   { ti, "ti", "Tigrinya" },
528   { tk, "tk", "Turkmen" },
529   { tl, "tl", "Tagalog" },
530   { tn, "tn", "Setswana" },
531   { to, "to", "Tonga" },
532   { tr, "tr", "Turkish" },
533   { ts, "ts", "Tsonga" },
534   { tt, "tt", "Tatar" },
535   { tw, "tw", "Twi" },
536   { ug, "ug", "Uighur" },
537   { uk, "uk", "Ukrainian" },
538   { ur, "ur", "Urdu" },
539   { uz, "uz", "Uzbek" },
540   { vi, "vi", "Vietnamese" },
541   { vo, "vo", "Volapuk" },
542   { wo, "wo", "Wolof" },
543   { xh, "xh", "Xhosa" },
544   { yi, "yi", "Yiddish" } /* (formerly ji) */,
545   { yo, "yo", "Yoruba" },
546   { za, "za", "Zhuang" },
547   { zh, "zh", "Chinese" },
548   { zu, "zu", "Zulu" },
549   { last_language_code, NULL, NULL }
550 };
551 
552 /* @documentlanguage.  Maybe we'll do something useful with this in the
553    future.  For now, we just recognize it.  */
554 
555 /* XML documents can make use of this data.  Unfortunately, it clashes with
556    the structure currently used.  So instead of enclosing content into
557    a language block, we just output an empty element.  Anyways, a stream based
558    parser can make good use of it.  */
559 void
cm_documentlanguage(void)560 cm_documentlanguage (void)
561 {
562   language_code_type c;
563   char *lang_arg;
564 
565   /* Read the line with the language code on it.  */
566   get_rest_of_line (0, &lang_arg);
567 
568   /* Linear search is fine these days.  */
569   for (c = aa; c != last_language_code; c++)
570     {
571       if (strcmp (lang_arg, language_table[c].abbrev) == 0)
572         { /* Set current language code.  */
573           language_code = c;
574           break;
575         }
576     }
577 
578   /* If we didn't find this code, complain.  */
579   if (c == last_language_code)
580     warning (_("%s is not a valid ISO 639 language code"), lang_arg);
581 
582   if (xml && !docbook)
583     {
584       xml_insert_element_with_attribute (DOCUMENTLANGUAGE, START, "xml:lang=\"%s\"", lang_arg);
585       xml_insert_element (DOCUMENTLANGUAGE, END);
586     }
587 
588   free (lang_arg);
589 }
590 
591 
592 
593 /* Search through the encoding table for the given character, returning
594    its equivalent.  */
595 
596 static int
cm_search_iso_map(char * html)597 cm_search_iso_map (char *html)
598 {
599   int i;
600   iso_map_type *iso = encoding_table[document_encoding_code].isotab;
601 
602   /* If no conversion table for this encoding, quit.  */
603   if (!iso)
604     return -1;
605 
606   for (i = 0; iso[i].html; i++)
607     {
608       if (strcmp (html, iso[i].html) == 0)
609         return i;
610     }
611 
612   return -1;
613 }
614 
615 
616 /* @documentencoding.  Set the translation table.  */
617 
618 void
cm_documentencoding(void)619 cm_documentencoding (void)
620 {
621   if (!handling_delayed_writes)
622     {
623       encoding_code_type enc;
624       char *enc_arg;
625 
626       /* This is ugly and probably needs to apply to other commands'
627          argument parsing as well.  When we're doing @documentencoding,
628          we're generally in the frontmatter of the document, and so the.
629          expansion in html/xml/docbook would generally be the empty string.
630          (Because those modes wait until the first normal text of the
631          document to start outputting.)  The result would thus be a warning
632          "unrecognized encoding name `'".  Sigh.  */
633       int save_html = html;
634       int save_xml = xml;
635 
636       html = 0;
637       xml = 0;
638       get_rest_of_line (1, &enc_arg);
639       html = save_html;
640       xml = save_xml;
641 
642       /* See if we have this encoding.  */
643       for (enc = no_encoding+1; enc != last_encoding_code; enc++)
644         {
645           if (strcasecmp (enc_arg, encoding_table[enc].encname) == 0)
646             {
647               document_encoding_code = enc;
648               break;
649             }
650         }
651 
652       /* If we didn't find this code, complain.  */
653       if (enc == last_encoding_code)
654         {
655           warning (_("unrecognized encoding name `%s'"), enc_arg);
656           /* Let the previous one go.  */
657           if (unknown_encoding && *unknown_encoding)
658             free (unknown_encoding);
659           unknown_encoding = xstrdup (enc_arg);
660         }
661 
662       else if (encoding_table[document_encoding_code].isotab == NULL)
663         warning (_("sorry, encoding `%s' not supported"), enc_arg);
664 
665       free (enc_arg);
666     }
667   else if (xml)
668     {
669       char *encoding = current_document_encoding ();
670 
671       if (encoding && *encoding)
672         {
673           insert_string (" encoding=\"");
674           insert_string (encoding);
675           insert_string ("\"");
676         }
677 
678       free (encoding);
679     }
680 }
681 
682 char *
current_document_encoding(void)683 current_document_encoding (void)
684 {
685   if (document_encoding_code != no_encoding)
686     return xstrdup (encoding_table[document_encoding_code].encname);
687   else if (unknown_encoding && *unknown_encoding)
688     return xstrdup (unknown_encoding);
689   else
690     return xstrdup ("");
691 }
692 
693 
694 /* If html or xml output, add &HTML_STR; to the output.  If not html and
695    the user requested encoded output, add the real 8-bit character
696    corresponding to HTML_STR from the translation tables.  Otherwise,
697    add INFO_STR.  */
698 
699 static void
add_encoded_char(char * html_str,char * info_str)700 add_encoded_char (char *html_str, char *info_str)
701 {
702   if (html)
703     add_word_args ("&%s;", html_str);
704   else if (xml)
705     xml_insert_entity (html_str);
706   else if (enable_encoding)
707     {
708       /* Look for HTML_STR in the current translation table.  */
709       int rc = cm_search_iso_map (html_str);
710       if (rc >= 0)
711         /* We found it, add the real character.  */
712         add_char (encoding_table[document_encoding_code].isotab[rc].bytecode);
713       else
714         { /* We didn't find it, that seems bad.  */
715           warning (_("invalid encoded character `%s'"), html_str);
716           add_word (info_str);
717         }
718     }
719   else
720     add_word (info_str);
721 }
722 
723 
724 
725 /* Output an accent for HTML or XML. */
726 
727 static void
cm_accent_generic_html(int arg,int start,int end,char * html_supported,int single,int html_solo_standalone,char * html_solo)728 cm_accent_generic_html (int arg, int start, int end, char *html_supported,
729     int single, int html_solo_standalone, char *html_solo)
730 {
731   static int valid_html_accent; /* yikes */
732 
733   if (arg == START)
734     { /* If HTML has good support for this character, use it.  */
735       if (strchr (html_supported, curchar ()))
736         { /* Yes; start with an ampersand.  The character itself
737              will be added later in read_command (makeinfo.c).  */
738 	  int saved_escape_html = escape_html;
739 	  escape_html = 0;
740           valid_html_accent = 1;
741           add_char ('&');
742 	  escape_html = saved_escape_html;
743         }
744       else
745         { /* @dotless{i} is not listed in html_supported but HTML entities
746 	     starting with `i' can be used, such as &icirc;.  */
747 	  int save_input_text_offset = input_text_offset;
748 	  char *accent_contents;
749 
750 	  get_until_in_braces ("\n", &accent_contents);
751 	  canon_white (accent_contents);
752 
753 	  if (strstr (accent_contents, "@dotless{i"))
754 	    {
755 	      add_word_args ("&%c", accent_contents[9]);
756 	      valid_html_accent = 1;
757 	    }
758 	  else
759 	    {
760 	      /* Search for @dotless{} wasn't successful, so rewind.  */
761 	      input_text_offset = save_input_text_offset;
762 	      valid_html_accent = 0;
763 	      if (html_solo_standalone)
764 		{ /* No special HTML support, so produce standalone char.  */
765 		  if (xml)
766 		    xml_insert_entity (html_solo);
767 		  else
768 		    add_word_args ("&%s;", html_solo);
769 		}
770 	      else
771 		/* If the html_solo does not exist as standalone character
772 		   (namely &circ; &grave; &tilde;), then we use
773 		   the single character version instead.  */
774 		add_char (single);
775 	    }
776 
777 	  free (accent_contents);
778         }
779     }
780   else if (arg == END)
781     { /* Only if we saw a valid_html_accent can we use the full
782          HTML accent (umlaut, grave ...).  */
783       if (valid_html_accent)
784         {
785           add_word (html_solo);
786           add_char (';');
787         }
788     }
789 }
790 
791 
792 static void
cm_accent_generic_no_headers(int arg,int start,int end,int single,char * html_solo)793 cm_accent_generic_no_headers (int arg, int start, int end, int single,
794     char *html_solo)
795 {
796   if (arg == END)
797     {
798       if (no_encoding)
799         add_char (single);
800       else
801         {
802           int rc;
803           char *buffer = xmalloc (1 + strlen (html_solo) + 1);
804           buffer[0] = output_paragraph[end - 1];
805           buffer[1] = 0;
806           strcat (buffer, html_solo);
807 
808           rc = cm_search_iso_map (buffer);
809           if (rc >= 0)
810             /* A little bit tricky ;-)
811                Here we replace the character which has
812                been inserted in read_command with
813                the value we have found in converting table
814                Does there exist a better way to do this?  kama. */
815             output_paragraph[end - 1]
816               = encoding_table[document_encoding_code].isotab[rc].bytecode;
817           else
818             { /* If we didn't find a translation for this character,
819                  put the single instead. E.g., &Xuml; does not exist so X&uml;
820                  should be produced. */
821               /* When the below warning is issued, an author has nothing
822                  wrong in their document, let alone anything ``fixable''
823                  on their side.  So it is commented out for now.  */
824               /* warning (_("%s is an invalid ISO code, using %c"),
825                        buffer, single); */
826               add_char (single);
827             }
828 
829           free (buffer);
830         }
831     }
832 }
833 
834 
835 
836 /* Accent commands that take explicit arguments and don't have any
837    special HTML support.  */
838 
839 void
cm_accent(int arg)840 cm_accent (int arg)
841 {
842   int old_escape_html = escape_html;
843   escape_html = 0;
844   if (arg == START)
845     {
846       /* Must come first to avoid ambiguity with overdot.  */
847       if (strcmp (command, "udotaccent") == 0)      /* underdot */
848         add_char ('.');
849     }
850   else if (arg == END)
851     {
852       if (strcmp (command, "=") == 0)               /* macron */
853         add_word ((html || xml) ? "&macr;" : "=");
854       else if (strcmp (command, "H") == 0)          /* Hungarian umlaut */
855         add_word ("''");
856       else if (strcmp (command, "dotaccent") == 0)  /* overdot */
857         add_meta_char ('.');
858       else if (strcmp (command, "ringaccent") == 0) /* ring */
859         add_char ('*');
860       else if (strcmp (command, "tieaccent") == 0)  /* long tie */
861         add_char ('[');
862       else if (strcmp (command, "u") == 0)          /* breve */
863         add_char ('(');
864       else if (strcmp (command, "ubaraccent") == 0) /* underbar */
865         add_char ('_');
866       else if (strcmp (command, "v") == 0)          /* hacek/check */
867         add_word ((html || xml) ? "&lt;" : "<");
868     }
869   escape_html = old_escape_html;
870 }
871 
872 /* Common routine for the accent characters that have support in HTML.
873    If the character being accented is in the HTML_SUPPORTED set, then
874    produce &CHTML_SOLO;, for example, &Auml; for an A-umlaut.  If not in
875    HTML_SUPPORTED, just produce &HTML_SOLO;X for the best we can do with
876    at an X-umlaut.  If not producing HTML, just use SINGLE, a
877    character such as " which is the best plain text representation we
878    can manage.  If HTML_SOLO_STANDALONE is nonzero the given HTML_SOLO
879    exists as valid standalone character in HTML, e.g., &uml;.  */
880 
881 static void
cm_accent_generic(int arg,int start,int end,char * html_supported,int single,int html_solo_standalone,char * html_solo)882 cm_accent_generic (int arg, int start, int end, char *html_supported,
883     int single, int html_solo_standalone, char *html_solo)
884 {
885   /* Accentuating space characters makes no sense, so issue a warning.  */
886   if (arg == START && isspace (input_text[input_text_offset]))
887     warning ("Accent command `@%s' must not be followed by whitespace",
888         command);
889 
890   if (html || xml)
891     cm_accent_generic_html (arg, start, end, html_supported,
892                             single, html_solo_standalone, html_solo);
893   else if (no_headers)
894     cm_accent_generic_no_headers (arg, start, end, single, html_solo);
895   else if (arg == END)
896     {
897       if (enable_encoding)
898         /* use 8-bit if available */
899         cm_accent_generic_no_headers (arg, start, end, single, html_solo);
900       else
901         /* use regular character */
902         add_char (single);
903     }
904 }
905 
906 void
cm_accent_umlaut(int arg,int start,int end)907 cm_accent_umlaut (int arg, int start, int end)
908 {
909   cm_accent_generic (arg, start, end, "aouAOUEeIiy", '"', 1, "uml");
910 }
911 
912 void
cm_accent_acute(int arg,int start,int end)913 cm_accent_acute (int arg, int start, int end)
914 {
915   cm_accent_generic (arg, start, end, "AEIOUYaeiouy", '\'', 1, "acute");
916 }
917 
918 void
cm_accent_cedilla(int arg,int start,int end)919 cm_accent_cedilla (int arg, int start, int end)
920 {
921   cm_accent_generic (arg, start, end, "Cc", ',', 1, "cedil");
922 }
923 
924 void
cm_accent_hat(int arg,int start,int end)925 cm_accent_hat (int arg, int start, int end)
926 {
927   cm_accent_generic (arg, start, end, "AEIOUaeiou", '^', 0, "circ");
928 }
929 
930 void
cm_accent_grave(int arg,int start,int end)931 cm_accent_grave (int arg, int start, int end)
932 {
933   cm_accent_generic (arg, start, end, "AEIOUaeiou", '`', 0, "grave");
934 }
935 
936 void
cm_accent_tilde(int arg,int start,int end)937 cm_accent_tilde (int arg, int start, int end)
938 {
939   cm_accent_generic (arg, start, end, "ANOano", '~', 0, "tilde");
940 }
941 
942 
943 
944 /* Non-English letters/characters that don't insert themselves.  */
945 void
cm_special_char(int arg)946 cm_special_char (int arg)
947 {
948   int old_escape_html = escape_html;
949   escape_html = 0;
950 
951   if (arg == START)
952     {
953       if ((*command == 'L' || *command == 'l'
954            || *command == 'O' || *command == 'o')
955           && command[1] == 0)
956         { /* Lslash lslash Oslash oslash.
957              Lslash and lslash aren't supported in HTML.  */
958           if (command[0] == 'O')
959             add_encoded_char ("Oslash", "/O");
960           else if (command[0] == 'o')
961             add_encoded_char ("oslash", "/o");
962           else
963             add_word_args ("/%c", command[0]);
964         }
965       else if (strcmp (command, "exclamdown") == 0)
966         add_encoded_char ("iexcl", "!");
967       else if (strcmp (command, "questiondown") == 0)
968         add_encoded_char ("iquest", "?");
969       else if (strcmp (command, "euro") == 0)
970         /* http://www.cs.tut.fi/~jkorpela/html/euro.html suggests that
971            &euro; degrades best in old browsers.  */
972         add_encoded_char ("euro", "Euro ");
973       else if (strcmp (command, "pounds") == 0)
974         add_encoded_char ("pound" , "#");
975       else if (strcmp (command, "ordf") == 0)
976         add_encoded_char ("ordf" , "a");
977       else if (strcmp (command, "ordm") == 0)
978         add_encoded_char ("ordm" , "o");
979       else if (strcmp (command, "AE") == 0)
980         add_encoded_char ("AElig", command);
981       else if (strcmp (command, "ae") == 0)
982         add_encoded_char ("aelig",  command);
983       else if (strcmp (command, "OE") == 0)
984         add_encoded_char ("OElig", command);
985       else if (strcmp (command, "oe") == 0)
986         add_encoded_char ("oelig", command);
987       else if (strcmp (command, "AA") == 0)
988         add_encoded_char ("Aring", command);
989       else if (strcmp (command, "aa") == 0)
990         add_encoded_char ("aring", command);
991       else if (strcmp (command, "ss") == 0)
992         add_encoded_char ("szlig", command);
993       else
994         line_error ("cm_special_char internal error: command=@%s", command);
995     }
996   escape_html = old_escape_html;
997 }
998 
999 /* Dotless i or j.  */
1000 void
cm_dotless(int arg,int start,int end)1001 cm_dotless (int arg, int start, int end)
1002 {
1003   if (arg == END)
1004     {
1005       xml_no_para --;
1006       if (output_paragraph[start] != 'i' && output_paragraph[start] != 'j')
1007         /* This error message isn't perfect if the argument is multiple
1008            characters, but it doesn't seem worth getting right.  */
1009         line_error (_("%c%s expects `i' or `j' as argument, not `%c'"),
1010                     COMMAND_PREFIX, command, output_paragraph[start]);
1011 
1012       else if (end - start != 1)
1013         line_error (_("%c%s expects a single character `i' or `j' as argument"),
1014                     COMMAND_PREFIX, command);
1015 
1016       /* We've already inserted the `i' or `j', so nothing to do.  */
1017     }
1018   else
1019     xml_no_para ++;
1020 }
1021