« back to all changes in this revision
Viewing changes to bibutils/risout.c
- browse files at revision 1
- compare with another revision
- download diff
- download tarball
- view history from revision 1
- Committer: Package Import Robot
- Author(s): Joachim Breitner
- Date: 2011-09-26 17:57:15 UTC
- Revision ID: package-import@ubuntu.com-20110926175715-muzp5giy0rzonss2
Tags: upstream-4.12
Import upstream version 4.12
- files added:
- bibutils
- cbits
- src
- src/Text
added
removed
bibutils/risout.c
1
/*
2
* risout.c
3
*
4
* Copyright (c) Chris Putnam 2003-2010
5
*
6
* Program and source code released under the GPL
7
*
8
*/
9
#include <stdio.h>
10
#include <stdlib.h>
11
#include <string.h>
12
#include <ctype.h>
13
#include "utf8.h"
14
#include "newstr.h"
15
#include "strsearch.h"
16
#include "fields.h"
17
#include "doi.h"
18
#include "risout.h"
19
20
void
21
risout_initparams( param *p, const char *progname )
22
{
23
p->writeformat = BIBL_RISOUT;
24
p->format_opts = 0;
25
p->charsetout = BIBL_CHARSET_DEFAULT;
26
p->charsetout_src = BIBL_SRC_DEFAULT;
27
p->latexout = 0;
28
p->utf8out = 0;
29
p->utf8bom = 0;
30
p->xmlout = 0;
31
p->nosplittitle = 0;
32
p->verbose = 0;
33
p->addcount = 0;
34
p->singlerefperfile = 0;
35
36
p->headerf = risout_writeheader;
37
p->footerf = NULL;
38
p->writef = risout_write;
39
}
40
41
enum {
42
TYPE_UNKNOWN,
43
TYPE_STD, /* standard/generic */
44
TYPE_ABSTRACT, /* abstract */
45
TYPE_ARTICLE, /* article */
46
TYPE_BOOK, /* book */
47
TYPE_CASE, /* case */
48
TYPE_INBOOK, /* chapter */
49
TYPE_CONF, /* conference */
50
TYPE_ELEC, /* electronic */
51
TYPE_HEAR, /* hearing */
52
TYPE_MAGARTICLE, /* magazine article */
53
TYPE_NEWS, /* newspaper */
54
TYPE_MPCT, /* mpct */
55
TYPE_PAMP, /* pamphlet */
56
TYPE_PATENT, /* patent */
57
TYPE_PCOMM, /* personal communication */
58
TYPE_PROGRAM, /* program */
59
TYPE_REPORT, /* report */
60
TYPE_STATUTE, /* statute */
61
TYPE_THESIS, /* thesis */
62
TYPE_MASTERSTHESIS, /* thesis */
63
TYPE_PHDTHESIS, /* thesis */
64
TYPE_DIPLOMATHESIS, /* thesis */
65
TYPE_DOCTORALTHESIS, /* thesis */
66
TYPE_HABILITATIONTHESIS, /* thesis */
67
TYPE_UNPUBLISHED, /* unpublished */
68
};
69
70
typedef struct match_type {
71
char *name;
72
int type;
73
} match_type;
74
75
/* Try to determine type of reference from <genre></genre>
76
* and <TypeOfResource></TypeOfResource>
77
*/
78
static int
79
get_type_genre( fields *info )
80
{
81
match_type match_genres[] = {
82
{ "academic journal", TYPE_ARTICLE },
83
{ "magazine", TYPE_MAGARTICLE },
84
{ "conference publication", TYPE_CONF },
85
{ "newspaper", TYPE_NEWS },
86
{ "legislation", TYPE_STATUTE },
87
{ "communication", TYPE_PCOMM },
88
{ "hearing", TYPE_HEAR },
89
{ "electronic", TYPE_ELEC },
90
{ "legal case and case notes", TYPE_CASE },
91
{ "Ph.D. thesis", TYPE_PHDTHESIS },
92
{ "Masters thesis", TYPE_MASTERSTHESIS },
93
{ "Diploma thesis", TYPE_DIPLOMATHESIS },
94
{ "Doctoral thesis", TYPE_DOCTORALTHESIS },
95
{ "Habilitation thesis", TYPE_HABILITATIONTHESIS },
96
{ "report", TYPE_REPORT },
97
{ "abstract or summary", TYPE_ABSTRACT },
98
{ "patent", TYPE_PATENT },
99
{ "unpublished", TYPE_UNPUBLISHED },
100
};
101
int nmatch_genres = sizeof( match_genres ) / sizeof( match_genres[0] );
102
match_type match_res[] = {
103
{ "software, multimedia", TYPE_PROGRAM },
104
};
105
int nmatch_res = sizeof( match_res ) / sizeof( match_res[0] );
106
char *tag, *data;
107
int type = TYPE_UNKNOWN, i, j;
108
for ( i=0; i<info->nfields; ++i ) {
109
tag = info->tag[i].data;
110
if ( strcasecmp( tag, "GENRE" ) &&
111
strcasecmp( tag, "NGENRE") ) continue;
112
data = info->data[i].data;
113
for ( j=0; j<nmatch_genres; ++j ) {
114
if ( !strcasecmp( data, match_genres[j].name ) )
115
type = match_genres[j].type;
116
}
117
if ( type==TYPE_UNKNOWN ) {
118
if ( !strcasecmp( data, "periodical" ) )
119
type = TYPE_ARTICLE;
120
else if ( !strcasecmp( data, "thesis" ) )
121
type = TYPE_THESIS;
122
else if ( !strcasecmp( data, "book" ) ) {
123
if ( info->level[i]==0 ) type=TYPE_BOOK;
124
else type=TYPE_INBOOK;
125
}
126
else if ( !strcasecmp( data, "collection" ) ) {
127
if ( info->level[i]==0 ) type=TYPE_BOOK;
128
else type=TYPE_INBOOK;
129
}
130
}
131
}
132
if ( type==TYPE_UNKNOWN ) {
133
for ( i=0; i<info->nfields; ++i ) {
134
tag = info->tag[i].data;
135
if ( strcasecmp( tag, "RESOURCE" ) ) continue;
136
data = info->data[i].data;
137
138
for ( j=0; j<nmatch_res; ++j ) {
139
if ( !strcasecmp( data, match_res[j].name ) )
140
type = match_res[j].type;
141
}
142
}
143
}
144
return type;
145
}
146
147
/* Try to determine type of reference from <issuance></issuance> and */
148
/* <typeOfReference></typeOfReference> */
149
static int
150
get_type_issuance( fields *info )
151
{
152
int type = TYPE_UNKNOWN;
153
int i, monographic = 0, text = 0, monographic_level = 0;
154
for ( i=0; i<info->nfields; ++i ) {
155
if ( !strcasecmp( info->tag[i].data, "issuance" ) &&
156
!strcasecmp( info->data[i].data, "MONOGRAPHIC" ) ){
157
monographic = 1;
158
monographic_level = info->level[i];
159
}
160
if ( !strcasecmp( info->tag[i].data, "typeOfResource" ) &&
161
!strcasecmp( info->data[i].data,"text") ) {
162
text = 1;
163
}
164
}
165
if ( monographic && text ) {
166
if ( monographic_level==0 ) type=TYPE_BOOK;
167
else if ( monographic_level>0 ) type=TYPE_INBOOK;
168
}
169
return type;
170
}
171
172
static int
173
get_type( fields *info )
174
{
175
int type;
176
type = get_type_genre( info );
177
if ( type==TYPE_UNKNOWN ) type = get_type_issuance( info );
178
if ( type==TYPE_UNKNOWN ) type = TYPE_STD;
179
return type;
180
}
181
182
static void
183
output_type( FILE *fp, int type, param *p )
184
{
185
match_type tyout[] = {
186
{ "STD", TYPE_STD },
187
{ "ABST", TYPE_ABSTRACT },
188
{ "JOUR", TYPE_ARTICLE },
189
{ "BOOK", TYPE_BOOK },
190
{ "CASE", TYPE_CASE },
191
{ "CHAP", TYPE_INBOOK },
192
{ "CONF", TYPE_CONF },
193
{ "ELEC", TYPE_ELEC },
194
{ "HEAR", TYPE_HEAR },
195
{ "MGZN", TYPE_MAGARTICLE },
196
{ "NEWS", TYPE_NEWS },
197
{ "MPCT", TYPE_MPCT },
198
{ "PAMP", TYPE_PAMP },
199
{ "PAT", TYPE_PATENT },
200
{ "PCOMM",TYPE_PCOMM },
201
{ "COMP", TYPE_PROGRAM },
202
{ "RPRT", TYPE_REPORT },
203
{ "STAT", TYPE_STATUTE },
204
{ "THES", TYPE_THESIS },
205
{ "THES", TYPE_MASTERSTHESIS },
206
{ "THES", TYPE_PHDTHESIS },
207
{ "THES", TYPE_DIPLOMATHESIS },
208
{ "THES", TYPE_DOCTORALTHESIS },
209
{ "THES", TYPE_HABILITATIONTHESIS },
210
{ "UNPB", TYPE_UNPUBLISHED }
211
};
212
int ntyout = sizeof( tyout ) / sizeof( tyout[0] );
213
int i, found;
214
215
fprintf( fp, "TY - " );
216
found = 0;
217
for ( i=0; i<ntyout && !found ; ++i ) {
218
if ( tyout[i].type == type ) {
219
fprintf( fp, "%s", tyout[i].name );
220
found = 1;
221
}
222
}
223
if ( !found ) {
224
if ( p->progname ) fprintf( stderr, "%s: ", p->progname );
225
fprintf( stderr, "Internal Error: Cannot identify type %d\n",
226
type );
227
}
228
fprintf( fp, "\n" );
229
}
230
231
static void
232
output_person ( FILE *fp, char *p )
233
{
234
int nseps = 0, nch;
235
while ( *p ) {
236
nch = 0;
237
if ( nseps==1 ) fprintf( fp, "," );
238
if ( nseps ) fprintf( fp, " " );
239
while ( *p && *p!='|' ) {
240
fprintf( fp, "%c", *p++ );
241
nch++;
242
}
243
if ( *p=='|' ) p++;
244
if ( nseps!=0 && nch==1 ) fprintf( fp, "." );
245
nseps++;
246
}
247
}
248
249
static void
250
output_people( FILE *fp, fields *info, long refnum, char *tag,
251
char *ristag, int level )
252
{
253
int i;
254
for ( i=0; i<info->nfields; ++i ) {
255
if ( level!=-1 && info->level[i]!=level ) continue;
256
if ( !strcasecmp( info->tag[i].data, tag ) ) {
257
fprintf( fp, "%s - ", ristag );
258
output_person ( fp, info->data[i].data );
259
fprintf( fp, "\n" );
260
}
261
}
262
}
263
264
static void
265
output_date( FILE *fp, fields *info, long refnum )
266
{
267
int year = fields_find( info, "YEAR", -1 );
268
int month = fields_find( info, "MONTH", -1 );
269
int day = fields_find( info, "DAY", -1 );
270
if ( year==-1 ) year = fields_find( info, "PARTYEAR", -1 );
271
if ( month==-1 ) month = fields_find( info, "PARTMONTH", -1 );
272
if ( day==-1 ) day = fields_find( info, "PARTDAY", -1 );
273
if ( year==-1 && month==-1 && day==-1 ) return;
274
fprintf( fp, "PY - " );
275
if ( year!=-1 ) fprintf( fp, "%s", info->data[year].data );
276
fprintf( fp, "/" );
277
if ( month!=-1 ) fprintf( fp, "%s", info->data[month].data );
278
fprintf( fp, "/" );
279
if ( day!=-1 ) fprintf( fp, "%s", info->data[day].data );
280
fprintf( fp, "\n" );
281
}
282
283
static void
284
output_title( FILE *fp, fields *info, char *ristag, int level )
285
{
286
int n1 = fields_find( info, "TITLE", level );
287
int n2 = fields_find( info, "SUBTITLE", level );
288
if ( n1!=-1 ) {
289
fprintf( fp, "%s - %s", ristag, info->data[n1].data );
290
if ( n2!=-1 ) {
291
if ( info->data[n1].data[info->data[n1].len]!='?' )
292
fprintf( fp, ": " );
293
else fprintf( fp, " " );
294
fprintf( fp, "%s", info->data[n2].data );
295
}
296
fprintf( fp, "\n" );
297
}
298
}
299
300
static void
301
output_abbrtitle( FILE *fp, fields *info, char *ristag, int level )
302
{
303
int n1 = fields_find( info, "SHORTTITLE", level );
304
int n2 = fields_find( info, "SHORTSUBTITLE", level );
305
if ( n1!=-1 ) {
306
fprintf( fp, "%s - %s", ristag, info->data[n1].data );
307
if ( n2!=-1 ){
308
if ( info->data[n1].data[info->data[n1].len]!='?' )
309
fprintf( fp, ": " );
310
else fprintf( fp, " " );
311
fprintf( fp, "%s", info->data[n2].data );
312
}
313
fprintf( fp, "\n" );
314
}
315
}
316
317
static void
318
output_pages( FILE *fp, fields *info, long refnum )
319
{
320
int sn = fields_find( info, "PAGESTART", -1 );
321
int en = fields_find( info, "PAGEEND", -1 );
322
int ar = fields_find( info, "ARTICLENUMBER", -1 );
323
if ( sn!=-1 || en!=-1 ) {
324
if ( sn!=-1 )
325
fprintf( fp, "SP - %s\n", info->data[sn].data );
326
if ( en!=-1 )
327
fprintf( fp, "EP - %s\n", info->data[en].data );
328
} else if ( ar!=-1 ) {
329
fprintf( fp, "SP - %s\n", info->data[ar].data );
330
}
331
}
332
333
static void
334
output_keywords( FILE *fp, fields *info )
335
{
336
int i;
337
for ( i=0; i<info->nfields; ++i ) {
338
if ( !strcmp( info->tag[i].data, "KEYWORD" ) )
339
fprintf( fp, "KW - %s\n", info->data[i].data );
340
}
341
}
342
343
static void
344
output_doi( FILE *fp, fields *info )
345
{
346
newstr doi_url;
347
int i;
348
newstr_init( &doi_url );
349
for ( i=0; i<info->nfields; ++i ) {
350
if ( strcmp( info->tag[i].data, "DOI" ) ) continue;
351
doi_to_url( info, i, "URL", &doi_url );
352
if ( doi_url.len )
353
fprintf( fp, "UR - %s\n", doi_url.data );
354
}
355
newstr_free( &doi_url );
356
}
357
358
static void
359
output_pmid( FILE *fp, fields *info )
360
{
361
newstr pmid_url;
362
int i;
363
newstr_init( &pmid_url );
364
for ( i=0; i<info->nfields; ++i ) {
365
if ( strcmp( info->tag[i].data, "PMID" ) ) continue;
366
pmid_to_url( info, i, "URL", &pmid_url );
367
if ( pmid_url.len )
368
fprintf( fp, "UR - %s\n", pmid_url.data );
369
}
370
newstr_free( &pmid_url );
371
}
372
373
static void
374
output_arxiv( FILE *fp, fields *info )
375
{
376
newstr arxiv_url;
377
int i;
378
newstr_init( &arxiv_url );
379
for ( i=0; i<info->nfields; ++i ) {
380
if ( strcmp( info->tag[i].data, "ARXIV" ) ) continue;
381
arxiv_to_url( info, i, "URL", &arxiv_url );
382
if ( arxiv_url.len )
383
fprintf( fp, "UR - %s\n", arxiv_url.data );
384
}
385
newstr_free( &arxiv_url );
386
}
387
388
static void
389
output_jstor( FILE *fp, fields *info )
390
{
391
newstr jstor_url;
392
int i;
393
newstr_init( &jstor_url );
394
for ( i=0; i<info->nfields; ++i ) {
395
if ( strcmp( info->tag[i].data, "JSTOR" ) ) continue;
396
jstor_to_url( info, i, "URL", &jstor_url );
397
if ( jstor_url.len )
398
fprintf( fp, "UR - %s\n", jstor_url.data );
399
}
400
newstr_free( &jstor_url );
401
}
402
403
static void
404
output_thesishint( FILE *fp, int type )
405
{
406
if ( type==TYPE_MASTERSTHESIS )
407
fprintf( fp, "%s - %s\n", "U1", "Masters thesis" );
408
else if ( type==TYPE_PHDTHESIS )
409
fprintf( fp, "%s - %s\n", "U1", "Ph.D. thesis" );
410
else if ( type==TYPE_DIPLOMATHESIS )
411
fprintf( fp, "%s - %s\n", "U1", "Diploma thesis" );
412
else if ( type==TYPE_DOCTORALTHESIS )
413
fprintf( fp, "%s - %s\n", "U1", "Doctoral thesis" );
414
else if ( type==TYPE_HABILITATIONTHESIS )
415
fprintf( fp, "%s - %s\n", "U1", "Habilitation thesis" );
416
}
417
418
static void
419
output_easy( FILE *fp, fields *info, long refnum, char *tag, char *ristag, int level )
420
{
421
int n = fields_find( info, tag, level );
422
if ( n!=-1 ) {
423
fprintf( fp, "%s - %s\n", ristag, info->data[n].data );
424
}
425
}
426
427
static void
428
output_easyall( FILE *fp, fields *info, long refnum, char *tag, char *ristag, int level )
429
{
430
int i;
431
for ( i=0; i<info->nfields; ++i ) {
432
if ( level!=-1 && level!=info->level[i] ) continue;
433
if ( !strcmp( info->tag[i].data, tag ) )
434
fprintf( fp, "%s - %s\n", ristag, info->data[i].data );
435
}
436
}
437
438
void
439
risout_write( fields *info, FILE *fp, param *p, unsigned long refnum )
440
{
441
int type;
442
type = get_type( info );
443
output_type( fp, type, p );
444
output_people( fp, info, refnum, "AUTHOR", "AU", 0 );
445
output_easyall( fp, info, refnum, "AUTHOR:CORP", "AU", 0 );
446
output_easyall( fp, info, refnum, "AUTHOR:ASIS", "AU", 0 );
447
output_people( fp, info, refnum, "AUTHOR", "A2", 1 );
448
output_easyall( fp, info, refnum, "AUTHOR:CORP", "A2", 1 );
449
output_easyall( fp, info, refnum, "AUTHOR:ASIS", "A2", 1 );
450
output_people( fp, info, refnum, "AUTHOR", "A3", 2 );
451
output_easyall( fp, info, refnum, "AUTHOR:CORP", "A3", 2 );
452
output_easyall( fp, info, refnum, "AUTHOR:ASIS", "A3", 2 );
453
output_people( fp, info, refnum, "EDITOR", "ED", -1 );
454
output_easyall( fp, info, refnum, "EDITOR:CORP", "ED", -1 );
455
output_easyall( fp, info, refnum, "EDITOR:ASIS", "ED", -1 );
456
output_date( fp, info, refnum );
457
output_title( fp, info, "TI", 0 );
458
output_abbrtitle( fp, info, "T2", -1 );
459
if ( type==TYPE_ARTICLE || type==TYPE_MAGARTICLE ) {
460
output_title( fp, info, "JO", 1 );
461
}
462
else output_title( fp, info, "BT", 1 );
463
output_title( fp, info, "T3", 2 );
464
output_pages( fp, info, refnum );
465
output_easy( fp, info, refnum, "VOLUME", "VL", -1 );
466
output_easy( fp, info, refnum, "ISSUE", "IS", -1 );
467
output_easy( fp, info, refnum, "NUMBER", "IS", -1 );
468
/* output article number as pages */
469
output_easy( fp, info, refnum, "PUBLISHER", "PB", -1 );
470
output_easy( fp, info, refnum, "DEGREEGRANTOR", "PB", -1 );
471
output_easy( fp, info, refnum, "DEGREEGRANTOR:ASIS", "PB", -1 );
472
output_easy( fp, info, refnum, "DEGREEGRANTOR:CORP", "PB", -1 );
473
output_easy( fp, info, refnum, "ADDRESS", "CY", -1 );
474
output_keywords( fp, info );
475
output_easy( fp, info, refnum, "ABSTRACT", "N2", -1 );
476
output_easy( fp, info, refnum, "ISSN", "SN", -1 );
477
output_easy( fp, info, refnum, "ISBN", "SN", -1 );
478
output_easyall( fp, info, refnum, "URL", "UR", -1 );
479
output_easyall( fp, info, refnum, "FILEATTACH", "L1", -1 );
480
output_doi( fp, info );
481
output_pmid( fp, info );
482
output_arxiv( fp, info );
483
output_jstor( fp, info );
484
output_easy( fp, info, refnum, "NOTES", "N1", -1 );
485
output_easy( fp, info, refnum, "REFNUM", "ID", -1 );
486
output_thesishint( fp, type );
487
fprintf( fp, "ER - \n" );
488
fflush( fp );
489
}
490
491
void
492
risout_writeheader( FILE *outptr, param *p )
493
{
494
if ( p->utf8bom ) utf8_writebom( outptr );
495
}
496
Loggerhead is a web-based interface for Breezy
Version: 2.0.1