1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
|
/*
* latex.c
*
* convert between latex special chars and unicode
*
* Copyright (c) Chris Putnam 2004-2009
*
* Source code released under the GPL
*
*/
#include <stdio.h>
#include <string.h>
#include "latex.h"
struct latex_chars {
unsigned int unicode;
char *bib1, *bib2, *bib3;
};
static struct latex_chars latex_chars[] = {
{ 35, "\\#", "", "" }, /* Number/pound/hash sign */
{ 36, "\\$", "", "" }, /* Dollar Sign */
{ 37, "\\%", "", "" }, /* Percent Sign */
{ 38, "\\&", "", "" }, /* Ampersand */
{ 92, "{\\backslash}", "\\backslash", "" }, /* Backslash */
{ 123, "\\{", "{\\textbraceleft}", "\\textbraceleft" }, /* Left Curly Bracket */
{ 125, "\\}", "{\\textbraceright}", "\\textbraceright" }, /* Right Curly Bracket */
{ 95, "\\_", "", "" }, /* Underscore alone indicates subscript */
{ 176, "{\\textdegree}", "\\textdegree", "^\\circ" }, /* Degree sign */
{ 32, "~", "\\ ", "" }, /* Tilde is a sticky space */
{ 126, "{\\textasciitilde}", "\\textasciitilde", "\\~{}" }, /* How to get a tilde in latex */
/* This is a cheat, should use "\verb" */
/* Need same for ^ character */
/* Latin Capital A */
{ 192, "{\\`A}", "\\`{A}", "\\`A" }, /* with grave */
{ 193, "{\\'A}", "\\'{A}", "\\'A" }, /* with acute */
{ 194, "{\\^A}", "\\^{A}", "\\^A" }, /* with circumflex */
{ 195, "{\\~A}", "\\~{A}", "\\~A" }, /* with tilde */
{ 196, "{\\\"A}", "\\\"{A}", "\\\"A" }, /* with diuresis */
{ 197, "{\\AA}", "", "" }, /* with ring above */
/* Latin Small a */
{ 224, "{\\`a}", "\\`{a}", "\\`a" }, /* with grave */
{ 225, "{\\'a}", "\\'{a}", "\\'a" }, /* with acute */
{ 226, "{\\^a}", "\\^{a}", "\\^a" }, /* with circumflex */
{ 227, "{\\~a}", "\\~{a}", "\\~a" }, /* with tilde */
{ 228, "{\\\"a}", "\\\"{a}", "\\\"a" }, /* with diuresis */
{ 229, "{\\aa}", "", "" }, /* with ring above */
{ 198, "{\\AE}", "\\AE", "" }, /* Latin Capital AE */
{ 230, "{\\ae}", "\\ae", "" }, /* Latin Small ae */
{ 199, "{\\c{C}}","\\c{C}", "" }, /* Latin Capital C with cedilla */
{ 231, "{\\c{c}}","\\c{c}", "" }, /* Latin small c with cedilla*/
{ 262, "{\\'C}", "\\'{C}", "\\'C" }, /* Latin Capital C with acute */
{ 263, "{\\'c}", "\\'{c}", "\\'c" }, /* Latin small c with acute */
/* Latin Capital E */
{ 200, "{\\`E}", "\\`{E}", "\\`E" }, /* with grave */
{ 201, "{\\'E}", "\\'{E}", "\\'E" }, /* with acute */
{ 202, "{\\^E}", "\\^{E}", "\\^E" }, /* with circumflex */
{ 203, "{\\\"E}", "\\\"{E}", "\\\"E" }, /* with diuresis */
/* Latin Small e */
{ 232, "{\\`e}", "\\`{e}", "\\`e" }, /* with grave */
{ 233, "{\\'e}", "\\'{e}", "\\'e" }, /* with acute */
{ 234, "{\\^e}", "\\^{e}", "\\^e" }, /* with circumflex */
{ 235, "{\\\"e}", "\\\"{e}", "\\\"e" }, /* with diuresis */
/* Latin Capital i */
{ 204, "{\\`I}", "\\`{I}", "\\`I" }, /* with grave */
{ 205, "{\\'I}", "\\'{I}", "\\'I" }, /* with acute */
{ 206, "{\\^I}", "\\^{I}", "\\^I" }, /* with circumflex */
{ 207, "{\\\"I}", "\\\"{I}", "\\\"I" }, /* with diuresis */
/* Latin Small i */
{ 236, "{\\`i}", "\\`{i}", "\\`i" }, /* with grave */
{ 237, "{\\'i}", "\\'{i}", "\\'i" }, /* with acute */
{ 238, "{\\^i}", "\\^{i}", "\\^i" }, /* with circumflex */
{ 239, "{\\\"i}", "\\\"{i}", "\\\"i" }, /* with diuresis */
/* Latex \i has no dot on "i"*/
{ 236, "{\\`\\i}", "\\`{\\i}", "\\`\\i" }, /* with grave */
{ 237, "{\\'\\i}", "\\'{\\i}", "\\'\\i" }, /* with acute */
{ 238, "{\\^\\i}", "\\^{\\i}", "\\^\\i" }, /* with circumflex */
{ 239, "{\\\"\\i}", "\\\"{\\i}", "\\\"\\i" }, /* with diuresis */
{ 209, "{\\~N}", "\\~{N}", "\\~N" }, /* Latin Capital N with tilde */
{ 327, "{\\vN}", "\\v{N}", "\\vN" }, /* Latin Capital N with caron */
{ 241, "{\\~n}", "\\~{n}", "\\~n" }, /* Latin Small n with tilde */
{ 328, "{\\vn}", "\\v{n}", "\\vn" }, /* Latin Small n with caron */
/* Latin Capital O */
{ 210, "{\\`O}", "\\`{O}", "\\`O" }, /* with grave */
{ 211, "{\\'O}", "\\'{O}", "\\'O" }, /* with acute */
{ 212, "{\\^O}", "\\^{O}", "\\^O" }, /* with circumflex */
{ 213, "{\\~O}", "\\~{O}", "\\~O" }, /* with tilde */
{ 214, "{\\\"O}", "\\\"{O}", "\\\"O" }, /* with diaeresis */
{ 216, "{\\O}", "\\O", "" }, /* with stroke */
/* Latin Small o */
{ 242, "{\\`o}", "\\`{o}", "\\`o" }, /* with grave */
{ 243, "{\\'o}", "\\'{o}", "\\'o" }, /* with acute */
{ 244, "{\\^o}", "\\^{o}", "\\^o" }, /* with circumflex */
{ 245, "{\\~o}", "\\~{o}", "\\~o" }, /* with tilde */
{ 246, "{\\\"o}", "\\\"{o}", "\\\"o" }, /* with diaeresis */
{ 248, "{\\o}", "\\o", "" }, /* with stroke */
{ 338, "{\\OE}", "\\OE", "" }, /* Latin Capital OE */
{ 339, "{\\oe}", "\\oe", "" }, /* Latin Small oe */
{ 341, "{\\vR}", "\\v{R}", "\\vR" }, /* Latin Capital R with caron */
{ 342, "{\\vr}", "\\v{r}", "\\vr" }, /* Latin Small r with caron */
{ 352, "{\\vS}", "\\v{S}", "\\vS" }, /* Latin Capital S with caron */
{ 353, "{\\vs}", "\\v{s}", "\\vs" }, /* Latin Small s with caron */
{ 223, "{\\ss}", "\\ss", "" }, /* German sz ligature, "sharp s" */
/* Latin Capital U */
{ 217, "{\\`U}", "\\`{U}", "\\`U" }, /* with grave */
{ 218, "{\\'U}", "\\'{U}", "\\'U" }, /* with acute */
{ 219, "{\\^U}", "\\^{U}", "\\^U" }, /* with circumflex */
{ 220, "{\\\"U}", "\\\"{U}", "\\\"U" }, /* with diaeresis */
/* Latin Small u */
{ 249, "{\\`u}", "\\`{u}", "\\`u" }, /* with grave */
{ 250, "{\\'u}", "\\'{u}", "\\'u" }, /* with acute */
{ 251, "{\\^u}", "\\^{u}", "\\^u" }, /* with circumflex */
{ 252, "{\\\"u}", "\\\"{u}", "\\\"u" }, /* with diaeresis */
/* Latin Capital Y */
{ 221, "{\\'Y}", "\\'{Y}", "\\'Y" }, /* with acute */
{ 376, "{\\\"Y}", "\\\"{Y}", "\\\"Y" }, /* with diaeresis */
/* Latin Small y */
{ 253, "{\\'y}", "\\'{y}", "\\'y" }, /* with acute */
{ 255, "{\\\"y}", "\\\"{y}", "\\\"y" }, /* with diaeresis */
/* Hacek-containing */
{ 269, "{\\v c}", "{\\v{c}}", "\\v{c}" }, /* c with a hacek */
/* Needs to be before \nu */
{ 8203, "$\\null$", "\\null", "" }, /* No space ​ */
{ 913, "$\\Alpha$", "\\Alpha", "" }, /*GREEKCAPITALLETTERALPHA*/
/* 902 = GREEKCAPITALLETTERALPHAWITHTONOS*/
{ 914, "$\\Beta$", "\\Beta", "" }, /*GREEKCAPITALLETTERBETA*/
{ 915, "$\\Gamma$", "\\Gamma", "" }, /*GREEKCAPITALLETTERGAMMA*/
{ 916, "$\\Delta$", "\\Delta", "" }, /*GREEKCAPITALLETTERDELTA*/
{ 917, "$\\Epsilon$", "\\Epsilon", "" }, /*GREEKCAPITALLETTEREPSILON*/
/* 904 = GREEKCAPITALLETTEREPSILONWITHTONOS*/
{ 918, "$\\Zeta$", "\\Zeta", "" }, /*GREEKCAPITALLETTERZETA*/
{ 919, "$\\Eta$", "\\Eta", "" }, /*GREEKCAPITALLETTERETA*/
/* 905 = GREEKCAPITALLETTERETAWITHTONOS*/
{ 920, "$\\Theta$", "\\Theta", "" }, /*GREEKCAPITALLETTERTHETA*/
{ 921, "$\\Iota$", "\\Iota", "" }, /*GREEKCAPITALLETTERIOTA*/
/* 938 = GREEKCAPITALLETTERIOTAWITHDIALYTIKA*/
/* 906 = GREEKCAPITALLETTERIOTAWITHTONOS*/
{ 922, "$\\Kappa$", "\\Kappa", "" }, /*GREEKCAPITALLETTERKAPPA*/
{ 923, "$\\Lambda$", "\\Lambda", "" }, /*GREEKCAPITALLETTERLAMDA*/
{ 924, "$\\Mu$", "\\Mu", "" }, /*GREEKCAPITALLETTERMU*/
{ 925, "$\\Nu$", "\\Nu", "" }, /*GREEKCAPITALLETTERNU*/
{ 926, "$\\Xi$", "\\Xi", "" }, /*GREEKCAPITALLETTERXI*/
{ 927, "$\\Omicron$", "\\Omicron", "" }, /*GREEKCAPITALLETTEROMICRON*/
/* 908 = GREEKCAPITALLETTEROMICRONWITHTONOS*/
{ 928, "$\\Pi$", "\\Pi", "" }, /*GREEKCAPITALLETTERPI*/
{ 929, "$\\Rho$", "\\Rho", "" }, /*GREEKCAPITALLETTERRHO*/
{ 931, "$\\Sigma$", "\\Sigma", "" }, /*GREEKCAPITALLETTERSIGMA*/
{ 932, "$\\Tau$", "\\Tau", "" }, /*GREEKCAPITALLETTERTAU*/
{ 933, "$\\Upsilon$", "\\Upsilon", "" }, /*GREEKCAPITALLETTERUPSILON*/
/* 939 = GREEKCAPITALLETTERUPSILONWITHDIALYTIKA*/
/* 910 = GREEKCAPITALLETTERUPSILONWITHTONOS*/
{ 934, "$\\Phi$", "\\Phi", "" }, /*GREEKCAPITALLETTERPHI*/
{ 935, "$\\Chi$", "\\Chi", "" }, /*GREEKCAPITALLETTERCHI*/
{ 936, "$\\Psi$", "\\Psi", "" }, /*GREEKCAPITALLETTERPSI*/
{ 937, "$\\Omega$", "\\Omega", "" }, /*GREEKCAPITALLETTEROMEGA*/
/* 911, = GREEKCAPITALLETTEROMEGAWITHTONOS*/
{ 945, "$\\alpha$", "\\alpha", "" }, /*GREEKSMALLLETTERALPHA*/
/* 940 = GREEKSMALLLETTERALPHAWITHTONOS*/
{ 946, "$\\beta$", "\\beta", "" }, /*GREEKSMALLLETTERBETA*/
{ 968, "$\\psi$", "\\psi", "" }, /*GREEKSMALLLETTERPSI*/
{ 948, "$\\delta$", "\\delta", "" }, /*GREEKSMALLLETTERDELTA*/
{ 949, "$\\epsilon$", "\\epsilon", "" }, /*GREEKSMALLLETTEREPSILON*/
/* 941 = GREEKSMALLLETTEREPSILONWITHTONOS*/
{ 966, "$\\phi$", "\\phi", "" }, /*GREEKSMALLLETTERPHI*/
{ 947, "$\\gamma$", "\\gamma", "" }, /*GREEKSMALLLETTERGAMMA*/
{ 951, "$\\eta$", "\\eta", "" }, /*GREEKSMALLLETTERETA*/
/* 942 = GREEKSMALLLETTERETAWITHTONOS */
{ 953, "$\\iota$", "\\iota", "" }, /*GREEKSMALLLETTERIOTA*/
/* 912 = GREEKSMALLLETTERIOTAWITHDIALYTIKAANDTONOS*/
/* 943 = GREEKSMALLLETTERIOTAWITHTONOS */
/* 970 = GREEKSMALLLETTERIOTAWITHDIALYTIKA */
{ 958, "$\\xi$", "\\xi", "" }, /*GREEKSMALLLETTERXI*/
{ 954, "$\\kappa$", "\\kappa" , "" }, /*GREEKSMALLLETTERKAPPA*/
{ 955, "$\\lambda$", "\\lambda", "" }, /*GREEKSMALLLETTERLAMDA*/
{ 956, "$\\mu$", "\\mu", "" }, /*GREEKSMALLLETTERMU*/
{ 957, "$\\nu$", "\\nu", "" }, /*GREEKSMALLLETTERNU*/
{ 959, "$\\omicron$", "\\omicron", "" }, /*GREEKSMALLLETTEROMICRON*/
/* 972 = GREEKSMALLLETTEROMICRONWITHTONOS*/
{ 960, "$\\pi$", "\\pi", "" }, /*GREEKSMALLLETTERPI*/
{ 961, "$\\rho$", "\\rho", "" }, /*GREEKSMALLLETTERRHO*/
{ 963, "$\\sigma$", "\\sigma", "" }, /*GREEKSMALLLETTERSIGMA*/
{ 964, "$\\tau$", "\\tau", "" }, /*GREEKSMALLLETTERTAU*/
{ 952, "$\\theta$", "\\theta", "" }, /*GREEKSMALLLETTERTHETA*/
{ 969, "$\\omega$", "\\omega", "" }, /*GREEKSMALLLETTEROMEGA*/
/* 974 = GREEKSMALLLETTEROMEGAWITHTONOS*/
{ 967, "$\\chi$", "\\chi", "" }, /*GREEKSMALLLETTERCHI*/
{ 965, "$\\upsilon$", "\\upsilon", "" }, /*GREEKSMALLLETTERUPSILON*/
/* 973 = GREEKSMALLLETTERUPSILONWITHTONOS*/
/* 971 = GREEKSMALLLETTERUPSILONWITHDIALYTIKA*/
/* 944 = GREEKSMALLLETTERUPSILONWITHDIALYTIKAANDTONOS*/
{ 950, "$\\zeta$", "\\zeta", "" }, /*GREEKSMALLLETTERZETA*/
{ 181, "{\\textmu}", "\\textmu", "$\\mu$" }, /* 181=micro sign, techically µ */
/* Make sure that these don't stomp on other latex things above */
{ 8242, "{\\textasciiacutex}", "\\textasciiacutex", "$'$" }, /* Prime symbol ′ */
{ 180, "{\\textasciiacute}", "\\textasciiacute", "\\'" }, /* acute accent ´ */
/* { 769, "\\'", "", "" },*/ /* Acute accent ́--apply to next char */
{ 8243, "{\\textacutedbl}", "\\textacutedbl", "$''$" }, /* Double prime ″ */
{ 8245, "{\\textasciigrave}", "\\textasciigrave", "\\`" }, /* Grave accent ‵ */
/* { 768, "\\`", "", "" },*/ /* Grave accent ̀--apply to next char */
{ 8963, "{\\textasciicircum}", "\\textasciicircum", ""} , /* ⌃ */
{ 184, "{\\textasciicedilla}", "\\textasciicedilla", "" }, /* cedilla ¸ */
{ 168, "{\\textasciidieresis}", "\\textasciidieresis", "" }, /* dieresis ¨ */
{ 175, "{\\textasciimacron}", "\\textasciimacron", "" }, /* macron ¯ */
{ 8593, "{\\textuparrow}", "\\textuparrow", "" }, /* Up arrow ↑ */
{ 8595, "{\\textdownarrow}", "\\textdownarrow", "" }, /* Down arrow ↓ */
{ 8594, "{\\textrightarrow}", "\\textrightarrow", "" }, /* Right arrow → */
{ 8592, "{\\textleftarrow}", "\\textleftarrow", "" }, /* Left arrow ← */
{ 12296, "{\\textlangle}", "\\textlangle", "" } , /* L-angle 〈 */
{ 12297, "{\\textrangle}", "\\textrangle", "" } , /* L-angle 〉 */
{ 166, "{\\textbrokenbar}", "\\textbrokenbar", "" }, /* Broken vertical bar ¦ */
{ 167, "{\\textsection}", "\\textsection", "" }, /* Section sign, § */
{ 170, "{\\textordfeminine}", "\\textordfeminine", "" }, /* ª */
{ 172, "{\\textlnot}", "\\textlnot", "" }, /* Lnot ¬ */
{ 182, "{\\textparagraph}", "\\textparagraph", "" }, /* Paragraph sign ¶ */
{ 183, "{\\textperiodcentered}", "\\textperiodcentered", "" }, /* Period-centered · */
{ 186, "{\\textordmasculine}", "\\textordmasculine", "" }, /* º */
{ 8214, "{\\textbardbl}", "\\textbardbl", "" }, /* Double vertical bar ‖ */
{ 8224, "{\\textdagger}", "\\textdagger", "" }, /* Dagger † */
{ 8225, "{\\textdaggerdbl}", "\\textdaggerdbl", "" },/* Double dagger &x2021; */
{ 8226, "{\\textbullet}", "\\textbullet", "" }, /* Bullet • */
{ 8494, "{\\textestimated}", "\\textestimated", "" },/* Estimated ℮ */
{ 9526, "{\\textopenbullet}", "\\textopenbullet", "" },/* ┶ */
{ 8220, "``", "{\\textquotedblleft}", "\\textquotedblleft" }, /* Opening double quote “ */
{ 8221, "''", "{\\textquotedblright}","\\textquotedblright" }, /* Closing double quote ” */
{ 8216, "`", "{\\textquoteleft}", "\\textquoteleft" }, /* Opening single quote ‘ */
{ 8217, "'", "{\\textquoteright}", "\\textquoteright" }, /* Closing single quote ’ */
{ 8261, "{\\textlquill}", "\\textlquill", "" }, /* Left quill ⁅ */
{ 8262, "{\\textrquill}", "\\textrquill", "" }, /* Right quill ⁆ */
{ 8212, "---", "{\\textemdash}", "\\textemdash" }, /* Em-dash — */
{ 8211, "--", "{\\textendash}", "\\textendash" }, /* En-dash – */
{ 8230, "\\ldots", "{\\textellipsis}", "\\textellipsis" }, /* Ellipsis … */
{ 8194, "\\enspace", "\\hspace{.5em}", "" }, /* En-space   */
{ 8195, "\\emspace", "\\hspace{1em}", "" }, /* Em-space   */
{ 8201, "\\thinspace", "", ""}, /* Thin space   */
{ 8203, "{\\textnospace}", "\\textnospace", "" }, /* No space ​ */
{ 9251, "{\\textvisiblespace}", "\\textvisiblespace", "" }, /* Visible space ␣ */
{ 215, "{\\texttimes}", "\\texttimes", "" }, /* Multiplication symbol × */
{ 247, "{\\textdiv}", "\\textdiv", "" }, /* Division symbol ÷ */
{ 177, "{\\textpm}", "\\textpm", "" }, /* Plus-minus character &#B1; */
{ 189, "{\\textonehalf}", "\\textonehalf", "" }, /* Vulgar fraction one half ½ */
{ 188, "{\\textonequarter}", "\\textonequarter", "" }, /* Vulgar fraction one quarter ½ */
{ 190, "{\\textthreequarters}", "\\textthreequarters", "" }, /* Vulgar fraction three quarters ¾ */
{ 8240, "{\\texttenthousand}", "\\texttenthousand", "" }, /* Per thousand sign ‰ */
{ 8241, "{\\textpertenthousand}", "\\textpertenthousand", "" }, /* Per ten thousand sign ‱*/
{ 8260, "{\\textfractionsolidus}", "\\textfractionsolidus", "" }, /* &x8260; */
{ 8451, "{\\textcelcius}", "\\textcelcius", "" }, /* Celcicus ℃ */
{ 8470, "{\\textnumero}", "\\textnumero", "" }, /* Numero symbol № */
{ 8486, "{\\textohm}", "\\textohm", "" }, /* Ohm symbol Ω */
{ 8487, "{\\textmho}", "\\textmho", "" }, /* Mho symbol ℧ */
{ 8730, "{\\textsurd}", "\\textsurd", "" }, /* √ */
{ 185, "{\\textonesuperior}", "\\textonesuperior", "" }, /*Superscript 1 ¹ */
{ 178, "{\\texttwosuperior}", "\\texttwosuperior", "" }, /*Superscript 2 ² */
{ 179, "{\\textthreesuperior}", "\\textthreesuperior", "" }, /*Superscript 3 ³ */
{ 161, "{\\textexclamdown}", "\\textexclamdown", "" }, /* Inverted exclamation mark ¡*/
{ 191, "{\\textquestiondown}", "\\textquestiondown", "" }, /* Inverted question mark ¿ */
{ 162, "{\\textcent}", "\\textcent", "" }, /* Cent sign ¢ */
{ 163, "{\\textsterling}", "\\textsterling", "\\pounds" }, /* Pound sign £ */
{ 165, "{\\textyen}", "\\textyen", "" }, /* Yen sign ¥ */
{ 402, "{\\textflorin}", "\\textflorin", "" }, /* Florin sign ƒ */
{ 3647, "{\\textbaht}", "\\textbaht", "" }, /* Thai currency ฿ */
{ 8355, "{\\textfrenchfranc}", "\\textfrenchfranc", "" }, /* French franc ₣ */
{ 8356, "{\\textlira}", "\\textlira", "" }, /* Lira ₤ */
{ 8358, "{\\textnaira}", "\\textnaria", "" }, /* Naira ₦ */
{ 8361, "{\\textwon}", "\\textwon", "" }, /* ₩ */
{ 8363, "{\\textdong}", "\\textdong", "" }, /* Vietnamese currency ₫ */
{ 8364, "{\\texteuro}", "\\texteuro", "" }, /* Euro sign */
{ 169, "{\\textcopyright}", "\\textcopyright", "" }, /* Copyright (C) © */
{ 175, "{\\textregistered}", "\\textregistered", "" }, /* Registered sign (R) ¯*/
{ 8482, "{\\texttrademark}", "\\texttrademark", "$^{TM}$" }, /* Trademark (TM) ™ */
{ 8480, "{\\textservicemark}", "\\textservicemark", "$^{SM}$" }, /* Servicemark (SM) ℠*/
{ 8471, "{\\textcircledP}", "\\textcircledP", "" }, /* Circled P ࡅ */
};
static int nlatex_chars = sizeof(latex_chars)/sizeof(struct latex_chars);
/* latex2char()
*
* Use the latex_chars[] lookup table to determine if any character
* is a special LaTeX code. Note that if it is, then the equivalency
* is a Unicode character and we need to flag (by setting *unicode to 1)
* that we know the output is Unicode. Otherwise, we set *unicode to 0,
* meaning that the output is whatever character set was given to us
* (which could be Unicode, but is not necessarily Unicode).
*
*/
unsigned int
latex2char( char *s, unsigned int *pos, int *unicode )
{
unsigned int value;
char *p, *q[3];
int i, j, l[3];
p = &( s[*pos] );
value = (unsigned char) *p;
if ( value=='{' || value=='\\' || value=='~' ||
value=='$' || value=='\'' || value=='`' ||
value=='-' || value=='^' ) {
for ( i=0; i<nlatex_chars; ++i ) {
q[0] = latex_chars[i].bib1;
l[0] = strlen( q[0] );
q[1] = latex_chars[i].bib2;
l[1] = strlen( q[1] );
q[2] = latex_chars[i].bib3;
l[2] = strlen( q[2] );
for ( j=0; j<3; ++j ) {
if ( l[j] && !strncmp( p, q[j], l[j] ) ) {
*pos = *pos + l[j];
*unicode = 1;
return latex_chars[i].unicode;
}
}
}
}
*unicode = 0;
*pos = *pos + 1;
return value;
}
void
uni2latex( unsigned int ch, char buf[], int buf_size )
{
int i;
buf[0] = '?';
buf[1] = '\0';
if ( ch==' ' ) {
buf[0] = ' '; /*special case to avoid */
return;
}
for ( i=0; i<nlatex_chars; ++i ) {
if ( ch == latex_chars[i].unicode ) {
strncpy( buf, latex_chars[i].bib1, buf_size );
buf[ buf_size-1 ] = '\0';
return;
}
}
if ( ch < 128 && buf[0]=='?' ) buf[0] = (char)ch;
}
|
