summaryrefslogtreecommitdiff
path: root/biblio/bibtex/utils/r2bib/dosToTex.c
blob: ff20068709aa73b925fee508fd81d772140a3b70 (plain)
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
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
/******************************************
dosToTex - converts 8bit encodings to (La)TeX
          multibyte escape sequences.

usage:

dosToTex [ -1 | -u ] < inputfile.dos > outputfile.tex
dosToTex -h

Switches:
-1 : assume that the input file has been encoded in the cp1252
     (Windows) character set
-u : assume that the input file has been encoded in the "US ASCII"
     (EndNote terminology) character set
-h : print a help line
neither -1 nor -u: assume that the input file has been encoded in
     the ANSI (EndNote terminology) character set

Note that it does NOT convert line feeds etc as does dos2unix; therefore
piping in addition through dos2unix may be useful:

dosToTex [ -1 | -u ] < inputfile.dos | dos2unix > outputfile.tex
dosToTex [ -1 | -u ] < inputfile.dos | sed 's/\r//' > outputfile.tex

As a more versatile alternative, one might combine the converter 'recode' with
the use of
   \usepackage{latin1}[inputenc]
in the LaTeX source: http://recode.progiciels-bpi.ca/
                      http://directory.fsf.org/recode.html

See also
    http://www.cs.uu.nl/wais/html/na-dir/internationalization/font-faq.html
    http://wwwvms.mppmu.mpg.de/FAQ/iso-charset.faq
    http://budling.nytud.hu/~szigetva/etcetera/Hungarian/converters/dos2tex
    http://www.ctan.org/tex-archive/support/xtexshell/tfc.cc
    http://billposer.org/Software/uni2ascii.html

Richard J. Mathar, http://www.mpia.de/~mathar
Dec 07, 2015
*****************************************/
#include "config.h"

#ifdef HAVE_STDLIB_H
#include <stdlib.h>
#endif

#ifdef HAVE_STDIO_H
#include <stdio.h>
#endif

#ifdef HAVE_UNISTD_H
#include <unistd.h>
#endif

void usage(char *argv0)
{
	printf("usage: %s ; # decode EndNote\n",argv0) ;
	printf("\t %s -1 ; # decode the CP1252 Windows character set\n",argv0) ;
	printf("\t %s -u ; # decode US ASCII\n",argv0) ;
	printf("\t %s -h ; # help: print these usage lines here\n",argv0) ;
	printf("Reads from the standard input, writes to the standard output.\n") ;
}

int main(int argc, char *argv[])
{
	int c ;
	char oc ;
	int useendnote = 1 , /* according to page 108 of the EndNote 7 Manual, default */
	    useUs = 0 , /* US ASCII according to the table on p 109 of the EndNote 7 manual */
	    usecpc1252 = 0 ; /* according to http://czyborra.com/charsets/cp1252.gif */
	while (  (oc=getopt(argc,argv,"1hu")) != -1 )
	{
		switch(oc)
		{
		case '1' :
			usecpc1252 = 1 ;
			useendnote = 0 ;
			break ;
		case 'u' :
			useUs = 1 ;
			useendnote = 0 ;
			break ;
		case 'h' :
			usage(argv[0]) ;
			return 0 ;
		case '?' :
			fprintf(stderr,"Invalid command line option %c\n",oc) ;
			usage(argv[0]) ;
			break ;
		}
	}

		/* start at 0x80, end at 0xff, according to http://czyborra.com/charsets/cp1252.gif */
	char *cpc1252[] = {
			NULL,
			NULL,
			",",
			"$f$",
			"``",
			"$\\ldots$",
			"\\dag ",
			"\\ddag ",
			"\\symbol{94}",
			NULL,
			"\\v{S}",
			"<",
			"{\\OE}",
			NULL,
			"\\v{Z}",
			NULL,
			NULL,
			"'",
			"'",
			"``",
			"''",
			NULL,
			"-",
			"--",
			"\\symbol{126}",
			NULL,
			"\\v{s}",
			">",
			"{\\oe}",
			NULL,
			"\\v{z}",
			"{\\\"Y}",
			NULL,
			"!'",
			NULL,
			"\\pounds ",
			NULL,
			NULL,
			"$\\mid$",
			"\\S ",
			"\\symbol{127}",
			"\\copyright ",
			NULL,
			"$\\ll$",
			"$\\neg$",
			NULL,
			NULL,
			"\\symbol{22}",
			"$^0$",
			"$\\pm$",
			"$^2$",
			"$^3$",
			"'",
			"$\\mu$",
			"\\P ",
			"$\\cdot$",
			NULL,
			"$^1$",
			NULL,
			"$\\gg$",
			"1/4",
			"1/2",
			"3/4",
			"?'",
			"\\`A" ,
			"\\'A" ,
			"\\^A" ,
			"\\~A" ,
			"{\\\"A}" ,
			"{\\AA}" ,
			"{\\AE}" ,
			"\\c{C}" ,
			"\\`E" ,
			"\\'E" ,
			"\\^E" ,
			"{\\\"E}" ,
			"\\`I" ,
			"\\'I" ,
			"\\^I" ,
			"{\\\"I}" ,
			NULL,
			"\\~N" ,
			"\\`O" ,
			"\\'O" ,
			"\\^O" ,
			"\\~O" ,
			"{\\\"O}" ,
			"$\\times$" ,
			"{\\O}" ,
			"\\`U" ,
			"\\'U" ,
			"\\^U" ,
			"{\\\"U}" ,
			"\\'Y" ,
			NULL,
			"\\ss " ,
			"\\`a" ,
			"\\'a" ,
			"\\^a" ,
			"\\~a" ,
			"{\\\"a}" ,
			"{\\aa}" ,
			"{\\ae}" ,
			"\\c{c}" ,
			"\\`e" ,
			"\\'e" ,
			"\\^e" ,
			"{\\\"e}" ,
			"\\`{\\i}" ,
			"\\'{\\i}" ,
			"\\^{\\i}" ,
			"{\\\"{\\i}}" ,
			NULL,
			"\\~n" ,
			"\\`o" ,
			"\\'o" ,
			"\\^o" ,
			"\\~o" ,
			"\\\"o" ,
			"$\\div$" ,
			"{\\o}" ,
			"\\`u" ,
			"\\'u" ,
			"\\^u" ,
			"{\\\"u}" ,
			"\\'y" ,
			NULL,
			"{\\\"y}"
	} ;
	/* starts at 129, ends at 255, according to page 108 of the EndNote 7 Manual */
	char *endn[] = {
			"\\_",
			NULL,
			NULL,
			NULL,
			"$\\ldots$",
			"\\dag ",
			"\\ddag ",
			"\\symbol{94}",
			NULL,
			NULL,
			NULL,
			"{\\OE}",
			NULL,
			NULL,
			NULL,
			NULL,
			NULL,
			NULL,
			"``",
			"''",
			NULL,
			NULL,
			"--",
			"\\symbol{126}",
			NULL,
			NULL,
			NULL,
			"{\\oe}",
			NULL,
			NULL,
			"{\\\"Y}",
			NULL,
			"!`", 
			NULL,
			"\\pounds ",
			NULL,
			NULL,
			"$\\mid$",
			"\\S ",
			"\\symbol{127}",
			"\\copyright ",
			NULL,
			"$\\ll$",
			"$\\neg$",
			NULL,
			NULL,
			"\\symbol{22}",
			"\\symbol{23}",
			"$\\pm$",
			"$^2$",
			NULL,
			"'",
			"$\\mu$",
			"\\P ",
			"$\\cdot$",
			NULL,
			"$^1$",
			"$^0$",
			"$\\gg$",
			"1/4","1/2","3/4",
			"?`",
			"\\`A",
			"\\'A",
			"\\^A",
			"\\~A",
			"{\\\"A}",
			"{\\AA}",
			"{\\AE}",
			"\\c{C}",
			"\\`E",
			"\\'E",
			"\\^E",
			"{\\\"E}",
			"\\`I",
			"\\'I",
			"\\^I",
			"{\\\"I}",
			NULL,
			"\\~N",
			"\\`O",
			"\\'O",
			"\\^O",
			"\\~O",
			"{\\\"O}",
			"$\\times$",
			"{\\O}",
			"\\`U",
			"\\'U",
			"\\^U",
			"{\\\"U}",
			"\\'Y",
			NULL,
			"\\ss ",
			"\\`a",
			"\\'a",
			"\\^a",
			"\\~a",
			"{\\\"a}",
			"{\\aa}",
			"{\\ae}",
			"\\c{c}",
			"\\`e",
			"\\'e",
			"\\^e",
			"{\\\"e}",
			"\\`{\\i}",
			"\\'{\\i}",
			"\\^{\\i}",
			"{\\\"{\\i}}",
			NULL,
			"\\~n",
			"\\`o",
			"\\'o",
			"\\^o",
			"\\~o",
			"{\\\"o}",
			"$\\div$",
			"{\\o}",
			"\\`u",
			"\\'u",
			"\\^u",
			"{\\\"u}",
			"\\'y",
			NULL,
			"{\\\"y}"
	} ;
	/* starts at 128, ends at 165 */
	char *usasc[] = {
			"\\c{C}",
			"{\\\"u}",
			"\\'e",
			"\\^a",
			"{\\\"a}",
			"\\`a",
			"{\\aa}",
			"\\c{c}",
			"\\^e",
			"{\\\"e}",
			"\\`e",
			"{\\\"{\\i}}",
			"\\^{\\i}",
			"\\`{\\i}",
			"{\\\"A}",
			"{\\AA}",
			"\\'E",
			"{\\ae}",
			"{\\AE}",
			"\\^o",
			"{\\\"o}",
			"\\`o",
			"\\^u",
			"\\`u",
			"{\\\"y}",
			"{\\\"O}",
			"{\\\"U}",
			NULL,
			"\\pounds ",NULL,
			"P",
			"$f$",
			"\\'a",
			"\\'{\\i}",
			"\\'o",
			"\\'u",
			"\\~n",
			"\\~N",NULL,NULL,
			"?'",
			"\\_",
			"$\\neg$",
			"1/2",
			"1/4",
			"!'",
			"$\\ll$",
			"$\\gg$"
		/*
		case 225 :
			"\\ss ",
		case 246 :
			"$\\div$",
		*/
	} ;

	if ( usecpc1252)
	{
		while( (c=getchar()) != EOF)
		{
			if( c >= 0x80 && c <= 0xff)	/* in the table ? */
				if ( cpc1252[c-0x80] )
					printf("%s",cpc1252[c-0x80]) ;
				else
					putchar(c) ;
			else
				putchar(c) ;
		}
	}
	else if ( useendnote)
	{
		while( (c=getchar()) != EOF)
		{
			if( c >= 128 && c <= 255)	/* in the table ? */
			{
				if ( endn[c-128] )
					printf("%s",endn[c-128]) ;
				else
					putchar(c) ;
			}
			else
				putchar(c) ;
		}
	}
	else if ( useUs)
	{
		while( (c=getchar()) != EOF)
		{
			if( c >= 128 && c <= 175)	/* in the table ? */
				if ( usasc[c-128] )
					printf("%s",usasc[c-128]) ;
				else
					putchar(c) ;
			else if ( c == 179)
				printf("$^3$") ;
			else if ( c == 225)
				printf("\\ss ") ;
			else if ( c == 227)
				printf("\\P ") ;
			else if ( c == 230)
				printf("$\\mu$") ;
			else if ( c == 241)
				printf("$\\pm$") ;
			else if ( c == 246)
				printf("$\\div$") ;
			else if ( c == 253)
				printf("$^2$") ;
			else
				putchar(c) ;
		}
	}
	return 0 ;
}