forked from Koha-Community/Koha
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathRis.pm
1020 lines (889 loc) · 32.6 KB
/
Ris.pm
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
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
package C4::Ris;
# Original script :
## marc2ris: converts MARC21 and UNIMARC datasets to RIS format
## See comments below for compliance with other MARC dialects
##
## usage: perl marc2ris < infile.marc > outfile.ris
##
## Dependencies: perl 5.6.0 or later
## MARC::Record
## MARC::Charset
##
## markus@mhoenicka.de 2002-11-16
## This program is free software; you can redistribute it and/or modify
## it under the terms of the GNU General Public License as published by
## the Free Software Foundation; either version 2 of the License, or
## (at your option) any later version.
##
## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
## GNU General Public License for more details.
## You should have received a copy of the GNU General Public License
## along with this program; if not, write to the Free Software
## Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
## Some background about MARC as understood by this script
## The default input format used in this script is MARC21, which
## superseded USMARC and CANMARC. The specification can be found at:
## http://lcweb.loc.gov/marc/
## UNIMARC follows the specification at:
## http://www.ifla.org/VI/3/p1996-1/sec-uni.htm
## UKMARC support is a bit shaky because there is no specification available
## for free. The wisdom used in this script was taken from a PDF document
## comparing UKMARC to MARC21 found at:
## www.bl.uk/services/bibliographic/marcchange.pdf
# Modified 2008 by BibLibre for Koha
# Modified 2011 by Catalyst
# Modified 2011 by Equinox Software, Inc.
# Modified 2016 by Universidad de El Salvador
#
# This file is part of Koha.
#
# Koha is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 3 of the License, or
# (at your option) any later version.
#
# Koha is distributed in the hope that it will be useful, but
# WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Koha; if not, see <http://www.gnu.org/licenses>.
#
#
use Modern::Perl;
use List::MoreUtils qw/uniq/;
use vars qw(@ISA @EXPORT);
use Koha::SimpleMARC qw(read_field);
@ISA = qw(Exporter);
# only export API methods
@EXPORT = qw(
&marc2ris
);
our $marcprint = 0; # Debug flag;
=head1 marc2bibtex - Convert from UNIMARC to RIS
my ($ris) = marc2ris($record);
Returns a RIS scalar
C<$record> - a MARC::Record object
=cut
sub marc2ris {
my ($record) = @_;
my $output;
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
# Let's redirect stdout
open my $oldout, ">&STDOUT";
my $outvar;
close STDOUT;
open STDOUT,'>:encoding(utf8)', \$outvar;
## First we should check the character encoding. This may be
## MARC-8 or UTF-8. The former is indicated by a blank, the latter
## by 'a' at position 09 (zero-based) of the leader
my $leader = $record->leader();
if ( $intype eq "marc21" ) {
if ( $leader =~ /^.{9}a/ ) {
print "<marc>---\r\n<marc>UTF-8 data\r\n" if $marcprint;
}
else {
print "<marc>---\r\n<marc>MARC-8 data\r\n" if $marcprint;
}
}
## else: other MARC formats do not specify the character encoding
## we assume it's *not* UTF-8
my $RisExportAdditionalFields = C4::Context->preference('RisExportAdditionalFields');
my $ris_additional_fields;
if ($RisExportAdditionalFields) {
$RisExportAdditionalFields = "$RisExportAdditionalFields\n\n";
$ris_additional_fields = eval { YAML::Load($RisExportAdditionalFields); };
if ($@) {
warn "Unable to parse RisExportAdditionalFields : $@";
$ris_additional_fields = undef;
}
}
## start RIS dataset
if ( $ris_additional_fields && $ris_additional_fields->{TY} ) {
my ( $f, $sf ) = split( /\$/, $ris_additional_fields->{TY} );
my ( $type ) = read_field( { record => $record, field => $f, subfield => $sf, field_numbers => [1] } );
if ($type) {
print "TY - $type\r\n";
}
else {
&print_typetag($leader);
}
}
else {
&print_typetag($leader);
}
## retrieve all author fields and collect them in a list
my @author_fields;
if ($intype eq "unimarc") {
## Fields 700, 701, and 702 can contain author names
@author_fields = ($record->field('700'), $record->field('701'), $record->field('702'));
}
else { ## marc21, ukmarc
## Field 100 sometimes carries main author
## Field(s) 700 carry added entries - personal names
@author_fields = ($record->field('100'), $record->field('700'));
}
## loop over all author fields
foreach my $field (@author_fields) {
if (length($field)) {
my $author = &get_author($field);
print "AU - ",$author,"\r\n";
}
}
# ToDo: should we specify anonymous as author if we didn't find
# one? or use one of the corporate/meeting names below?
## add corporate names or meeting names as editors ??
my @editor_fields;
if ($intype eq "unimarc") {
## Fields 710, 711, and 712 can carry corporate names
## Field(s) 720, 721, 722, 730 have additional candidates
@editor_fields = ($record->field('710'), $record->field('711'), $record->field('712'), $record->field('720'), $record->field('721'), $record->field('722'), $record->field('730'));
}
else { ## marc21, ukmarc
## Fields 110 and 111 carry the main entries - corporate name and
## meeting name, respectively
## Field(s) 710, 711 carry added entries - personal names
@editor_fields = ($record->field('110'), $record->field('111'), $record->field('710'), $record->field('711'));
}
## loop over all editor fields
foreach my $field (@editor_fields) {
if (length($field)) {
my $editor = &get_editor($field);
print "ED - ",$editor,"\r\n";
}
}
## get info from the title field
if ($intype eq "unimarc") {
&print_title($record->field('200'));
}
else { ## marc21, ukmarc
&print_title($record->field('245'));
}
## series title
if ($intype eq "unimarc") {
&print_stitle($record->field('225'));
}
else { ## marc21, ukmarc
&print_stitle($record->field('490'));
}
## ISBN/ISSN
if ($intype eq "unimarc") {
&print_isbn($record->field('010'));
&print_issn($record->field('011'));
}
elsif ($intype eq "ukmarc") {
&print_isbn($record->field('021'));
## this is just an assumption
&print_issn($record->field('022'));
}
else { ## assume marc21
&print_isbn($record->field('020'));
&print_issn($record->field('022'));
}
if ($intype eq "marc21") {
&print_loc_callno($record->field('050'));
&print_dewey($record->field('082'));
}
## else: unimarc, ukmarc do not seem to store call numbers?
## publication info
if ($intype eq "unimarc") {
&print_pubinfo($record->field('210'));
}
else { ## marc21, ukmarc
if ($record->field('264')) {
&print_pubinfo($record->field('264'));
}
else {
&print_pubinfo($record->field('260'));
}
}
## 6XX fields contain KW candidates. We add all of them to a
my @field_list;
if ($intype eq "unimarc") {
@field_list = ('600', '601', '602', '604', '605', '606','607', '608', '610', '615', '620', '660', '661', '670', '675', '676', '680', '686');
} elsif ($intype eq "ukmarc") {
@field_list = ('600', '610', '611', '630', '650', '651','653', '655', '660', '661', '668', '690', '691', '692', '695');
} else { ## assume marc21
@field_list = ('600', '610', '611', '630', '650', '651','653', '654', '655', '656', '657', '658');
}
my @kwpool;
for my $f ( @field_list ) {
my @fields = $record->field($f);
push @kwpool, ( get_keywords("$f",$record->field($f)) );
}
# Remove duplicate
@kwpool = uniq @kwpool;
for my $kw ( @kwpool ) {
print "KW - ", $kw, "\r\n";
}
## 5XX have various candidates for notes and abstracts. We pool
## all notes-like stuff in one list.
my @notepool;
## these fields have notes candidates
if ($intype eq "unimarc") {
foreach ('300', '301', '302', '303', '304', '305', '306', '307', '308', '310', '311', '312', '313', '314', '315', '316', '317', '318', '320', '321', '322', '323', '324', '325', '326', '327', '328', '332', '333', '336', '337', '345') {
&pool_subx(\@notepool, $_, $record->field($_));
}
}
elsif ($intype eq "ukmarc") {
foreach ('500', '501', '502', '503', '504', '505', '506', '508', '514', '515', '516', '521', '524', '525', '528', '530', '531', '532', '533', '534', '535', '537', '538', '540', '541', '542', '544', '554', '555', '556', '557', '561', '563', '580', '583', '584', '586') {
&pool_subx(\@notepool, $_, $record->field($_));
}
}
else { ## assume marc21
foreach ('500', '501', '502', '504', '505', '506', '507', '508', '510', '511', '513', '514', '515', '516', '518', '521', '522', '524', '525', '526', '530', '533', '534', '535') {
&pool_subx(\@notepool, $_, $record->field($_));
}
}
my $allnotes = join "; ", @notepool;
if (length($allnotes) > 0) {
print "N1 - ", $allnotes, "\r\n";
}
## 320/520 have the abstract
if ($intype eq "unimarc") {
&print_abstract($record->field('320'));
}
elsif ($intype eq "ukmarc") {
&print_abstract($record->field('512'), $record->field('513'));
}
else { ## assume marc21
&print_abstract($record->field('520'));
}
# 856u has the URI
if ($record->field('856')) {
print_uri($record->field('856'));
}
if ($ris_additional_fields) {
foreach my $ris_tag ( keys %$ris_additional_fields ) {
next if $ris_tag eq 'TY';
my @fields =
ref( $ris_additional_fields->{$ris_tag} ) eq 'ARRAY'
? @{ $ris_additional_fields->{$ris_tag} }
: $ris_additional_fields->{$ris_tag};
for my $tag (@fields) {
my ( $f, $sf ) = split( /\$/, $tag );
my @values = read_field( { record => $record, field => $f, subfield => $sf } );
foreach my $v (@values) {
print "$ris_tag - $v\r\n";
}
}
}
}
## end RIS dataset
print "ER - \r\n";
# Let's re-redirect stdout
close STDOUT;
open STDOUT, ">&", $oldout;
return $outvar;
}
##********************************************************************
## print_typetag(): prints the first line of a RIS dataset including
## the preceding newline
## Argument: the leader of a MARC dataset
## Returns: the value at leader position 06
##********************************************************************
sub print_typetag {
my ($leader)= @_;
## the keys of typehash are the allowed values at position 06
## of the leader of a MARC record, the values are the RIS types
## that might appropriately represent these types.
my %ustypehash = (
"a" => "BOOK",
"c" => "MUSIC",
"d" => "MUSIC",
"e" => "MAP",
"f" => "MAP",
"g" => "ADVS",
"i" => "SOUND",
"j" => "SOUND",
"k" => "ART",
"m" => "DATA",
"o" => "GEN",
"p" => "GEN",
"r" => "ART",
"t" => "MANSCPT",
);
my %unitypehash = (
"a" => "BOOK",
"b" => "MANSCPT",
"c" => "MUSIC",
"d" => "MUSIC",
"e" => "MAP",
"f" => "MAP",
"g" => "ADVS",
"i" => "SOUND",
"j" => "SOUND",
"k" => "ART",
"l" => "ELEC",
"m" => "GEN",
"r" => "ART",
);
## The type of a MARC record is found at position 06 of the leader
my $typeofrecord = defined($leader) && length $leader >=6 ?
substr($leader, 6, 1): undef;
## Pos 07 == Bibliographic level
my $biblevel = defined($leader) && length $leader >=7 ?
substr($leader, 7, 1): '';
## TODO: for books, field 008 positions 24-27 might have a few more
## hints
my %typehash;
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
if ($intype eq "unimarc") {
%typehash = %unitypehash;
}
else {
%typehash = %ustypehash;
}
if (!defined $typeofrecord || !exists $typehash{$typeofrecord}) {
print "TY - GEN\r\n"; ## most reasonable default
warn ("no type found - assume GEN") if $marcprint;
} elsif ( $typeofrecord =~ "a" ) {
if ( $biblevel eq 'a' ) {
print "TY - GEN\r\n"; ## monographic component part
} elsif ( $biblevel eq 'b' || $biblevel eq 's' ) {
print "TY - SER\r\n"; ## serial or serial component part
} elsif ( $biblevel eq 'm' ) {
print "TY - $typehash{$typeofrecord}\r\n"; ## book
} elsif ( $biblevel eq 'c' || $biblevel eq 'd' ) {
print "TY - GEN\r\n"; ## collections, part of collections or made-up collections
} elsif ( $biblevel eq 'i' ) {
print "TY - DATA\r\n"; ## updating loose-leafe as Dataset
}
} else {
print "TY - $typehash{$typeofrecord}\r\n";
}
## use $typeofrecord as the return value, just in case
$typeofrecord;
}
##********************************************************************
## normalize_author(): normalizes an authorname
## Arguments: authorname subfield a
## authorname subfield b
## authorname subfield c
## name type if known: 0=direct order
## 1=only surname or full name in
## inverted order
## 3=family, clan, dynasty name
## Returns: the normalized authorname
##********************************************************************
sub normalize_author {
my($rawauthora, $rawauthorb, $rawauthorc, $nametype) = @_;
if ($nametype == 0) {
# ToDo: convert every input to Last[,(F.|First)[ (M.|Middle)[,Suffix]]]
warn("name >>$rawauthora<< in direct order - leave as is") if $marcprint;
return $rawauthora;
}
elsif ($nametype == 1) {
## start munging subfield a (the real name part)
## remove spaces after separators
$rawauthora =~ s%([,.]+) *%$1%g;
## remove trailing separators after spaces
$rawauthora =~ s% *[,;:/]*$%%;
## remove periods after a non-abbreviated name
$rawauthora =~ s%(\w{2,})\.%$1%g;
## start munging subfield b (something like the suffix)
## remove trailing separators after spaces
$rawauthorb =~ s% *[,;:/]*$%%;
## we currently ignore subfield c until someone complains
if (length($rawauthorb) > 0) {
return join ", ", ($rawauthora, $rawauthorb);
}
else {
return $rawauthora;
}
}
elsif ($nametype == 3) {
return $rawauthora;
}
}
##********************************************************************
## get_author(): gets authorname info from MARC fields 100, 700
## Argument: field (100 or 700)
## Returns: an author string in the format found in the record
##********************************************************************
sub get_author {
my ($authorfield) = @_;
my ($indicator);
## the sequence of the name parts is encoded either in indicator
## 1 (marc21) or 2 (unimarc)
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
if ($intype eq "unimarc") {
$indicator = 2;
}
else { ## assume marc21
$indicator = 1;
}
print "<marc>:Author(Ind$indicator): ", $authorfield->indicator("$indicator"),"\r\n" if $marcprint;
print "<marc>:Author(\$a): ", $authorfield->subfield('a'),"\r\n" if $marcprint;
print "<marc>:Author(\$b): ", $authorfield->subfield('b'),"\r\n" if $marcprint;
print "<marc>:Author(\$c): ", $authorfield->subfield('c'),"\r\n" if $marcprint;
print "<marc>:Author(\$h): ", $authorfield->subfield('h'),"\r\n" if $marcprint;
if ($intype eq "ukmarc") {
my $authorname = $authorfield->subfield('a') . "," . $authorfield->subfield('h');
normalize_author($authorname, $authorfield->subfield('b'), $authorfield->subfield('c'), $authorfield->indicator("$indicator"));
}
else {
normalize_author($authorfield->subfield('a') // '', $authorfield->subfield('b') // '', $authorfield->subfield('c') // '', $authorfield->indicator("$indicator"));
}
}
##********************************************************************
## get_editor(): gets editor info from MARC fields 110, 111, 710, 711
## Argument: field (110, 111, 710, or 711)
## Returns: an author string in the format found in the record
##********************************************************************
sub get_editor {
my ($editorfield) = @_;
if (!$editorfield) {
return;
}
else {
print "<marc>Editor(\$a): ", $editorfield->subfield('a'),"\r\n" if $marcprint;
print "<marc>Editor(\$b): ", $editorfield->subfield('b'),"\r\n" if $marcprint;
print "<marc>editor(\$c): ", $editorfield->subfield('c'),"\r\n" if $marcprint;
return $editorfield->subfield('a');
}
}
##********************************************************************
## print_title(): gets info from MARC field 245
## Arguments: field (245)
## Returns:
##********************************************************************
sub print_title {
my ($titlefield) = @_;
if (!$titlefield) {
print "<marc>empty title field (245)\r\n" if $marcprint;
warn("empty title field (245)") if $marcprint;
}
else {
print "<marc>Title(\$a): ",$titlefield->subfield('a'),"\r\n" if $marcprint;
print "<marc>Title(\$b): ",$titlefield->subfield('b'),"\r\n" if $marcprint;
print "<marc>Title(\$c): ",$titlefield->subfield('c'),"\r\n" if $marcprint;
## The title is usually written in a very odd notation. The title
## proper ($a) often ends with a space followed by a separator like
## a slash or a colon. The subtitle ($b) doesn't start with a space
## so simple concatenation looks odd. We have to conditionally remove
## the separator and make sure there's a space between title and
## subtitle
my $clean_title = $titlefield->subfield('a');
my $clean_subtitle = $titlefield->subfield('b');
$clean_subtitle ||= q{};
$clean_title =~ s% *[/:;.]$%%;
$clean_subtitle =~ s%^ *(.*) *[/:;.]$%$1%;
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
if (length($clean_title) > 0
|| (length($clean_subtitle) > 0 && $intype ne "unimarc")) {
print "TI - ", $clean_title;
## subfield $b is relevant only for marc21/ukmarc
if (length($clean_subtitle) > 0 && $intype ne "unimarc") {
print ": ",$clean_subtitle;
}
print "\r\n";
}
## The statement of responsibility is just this: horrors. There is
## no formal definition how authors, editors and the like should
## be written and designated. The field is free-form and resistant
## to all parsing efforts, so this information is lost on me
}
return;
}
##********************************************************************
## print_stitle(): prints info from series title field
## Arguments: field
## Returns:
##********************************************************************
sub print_stitle {
my ($titlefield) = @_;
if (!$titlefield) {
print "<marc>empty series title field\r\n" if $marcprint;
}
else {
print "<marc>Series title(\$a): ",$titlefield->subfield('a'),"\r\n" if $marcprint;
my $clean_title = $titlefield->subfield('a');
$clean_title =~ s% *[/:;.]$%%;
if (length($clean_title) > 0) {
print "T2 - ", $clean_title,"\r\n";
}
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
if ($intype eq "unimarc") {
print "<marc>Series vol(\$v): ",$titlefield->subfield('v'),"\r\n" if $marcprint;
if (length($titlefield->subfield('v')) > 0) {
print "VL - ", $titlefield->subfield('v'),"\r\n";
}
}
}
return;
}
##********************************************************************
## print_isbn(): gets info from MARC field 020
## Arguments: field (020)
##********************************************************************
sub print_isbn {
my($isbnfield) = @_;
if (!$isbnfield || length ($isbnfield->subfield('a')) == 0) {
print "<marc>no isbn found (020\$a)\r\n" if $marcprint;
warn("no isbn found") if $marcprint;
}
else {
if (length ($isbnfield->subfield('a')) < 10) {
print "<marc>truncated isbn (020\$a)\r\n" if $marcprint;
warn("truncated isbn") if $marcprint;
}
my $isbn = $isbnfield->subfield('a');
print "SN - ", $isbn, "\r\n";
}
}
##********************************************************************
## print_issn(): gets info from MARC field 022
## Arguments: field (022)
##********************************************************************
sub print_issn {
my($issnfield) = @_;
if (!$issnfield || length ($issnfield->subfield('a')) == 0) {
print "<marc>no issn found (022\$a)\r\n" if $marcprint;
warn("no issn found") if $marcprint;
}
else {
if (length ($issnfield->subfield('a')) < 9) {
print "<marc>truncated issn (022\$a)\r\n" if $marcprint;
warn("truncated issn") if $marcprint;
}
my $issn = substr($issnfield->subfield('a'), 0, 9);
print "SN - ", $issn, "\r\n";
}
}
###
# print_uri() prints info from 856 u
###
sub print_uri {
my @f856s = @_;
foreach my $f856 (@f856s) {
if (my $uri = $f856->subfield('u')) {
print "UR - ", $uri, "\r\n";
}
}
}
##********************************************************************
## print_loc_callno(): gets info from MARC field 050
## Arguments: field (050)
##********************************************************************
sub print_loc_callno {
my($callnofield) = @_;
if (!$callnofield || length ($callnofield->subfield('a')) == 0) {
print "<marc>no LOC call number found (050\$a)\r\n" if $marcprint;
warn("no LOC call number found") if $marcprint;
}
else {
print "AV - ", $callnofield->subfield('a'), " ", $callnofield->subfield('b'), "\r\n";
}
}
##********************************************************************
## print_dewey(): gets info from MARC field 082
## Arguments: field (082)
##********************************************************************
sub print_dewey {
my($deweyfield) = @_;
if (!$deweyfield || length ($deweyfield->subfield('a')) == 0) {
print "<marc>no Dewey number found (082\$a)\r\n" if $marcprint;
warn("no Dewey number found") if $marcprint;
}
else {
print "U1 - ", $deweyfield->subfield('a'), " ", $deweyfield->subfield('2'), "\r\n";
}
}
##********************************************************************
## print_pubinfo(): gets info from MARC field 260
## Arguments: field (260)
##********************************************************************
sub print_pubinfo {
my($pubinfofield) = @_;
if (!$pubinfofield) {
print "<marc>no publication information found (260/264)\r\n" if $marcprint;
warn("no publication information found") if $marcprint;
}
else {
## the following information is available in MARC21:
## $a place -> CY
## $b publisher -> PB
## $c date -> PY
## the corresponding subfields for UNIMARC:
## $a place -> CY
## $c publisher -> PB
## $d date -> PY
## all of them are repeatable. We pool all places into a
## comma-separated list in CY. We also pool all publishers
## into a comma-separated list in PB. We break the rule with
## the date field because this wouldn't make much sense. In
## this case, we use the first occurrence for PY, the second
## for Y2, and ignore the rest
my @pubsubfields = $pubinfofield->subfields();
my @cities;
my @publishers;
my $pycounter = 0;
my $pubsub_place;
my $pubsub_publisher;
my $pubsub_date;
my $marcflavour = C4::Context->preference("marcflavour");
my $intype = lc($marcflavour);
if ($intype eq "unimarc") {
$pubsub_place = "a";
$pubsub_publisher = "c";
$pubsub_date = "d";
}
else { ## assume marc21
$pubsub_place = "a";
$pubsub_publisher = "b";
$pubsub_date = "c";
}
## loop over all subfield list entries
for my $tuple (@pubsubfields) {
## each tuple consists of the subfield code and the value
if (@$tuple[0] eq $pubsub_place) {
## strip any trailing crap
$_ = @$tuple[1];
s% *[,;:/]$%%;
## pool all occurrences in a list
push (@cities, $_);
}
elsif (@$tuple[0] eq $pubsub_publisher) {
## strip any trailing crap
$_ = @$tuple[1];
s% *[,;:/]$%%;
## pool all occurrences in a list
push (@publishers, $_);
}
elsif (@$tuple[0] eq $pubsub_date) {
## the dates are free-form, so we want to extract
## a four-digit year and leave the rest as
## "other info"
my $protoyear = @$tuple[1];
print "<marc>Year (260\$c): $protoyear\r\n" if $marcprint;
## strip any separator chars at the end
$protoyear =~ s% *[\.;:/]*$%%;
## isolate a four-digit year. We discard anything
## preceding the year, but keep everything after
## the year as other info.
$protoyear =~ s%\D*([0-9\-]{4})(.*)%$1///$2%;
## check what we've got. If there is no four-digit
## year, make it up. If digits are replaced by '-',
## replace those with 0s
if (index($protoyear, "/") == 4) {
## have year info
## replace all '-' in the four-digit year
## by '0'
substr($protoyear,0,4) =~ s!-!0!g;
}
else {
## have no year info
print "<marc>no four-digit year found, use 0000\r\n" if $marcprint;
$protoyear = "0000///$protoyear";
warn("no four-digit year found, use 0000") if $marcprint;
}
if ($pycounter == 0 && length($protoyear)) {
print "PY - $protoyear\r\n";
}
elsif ($pycounter == 1 && length($_)) {
print "Y2 - $protoyear\r\n";
}
## else: discard
}
## else: discard
}
## now dump the collected CY and PB lists
if (@cities > 0) {
print "CY - ", join(", ", @cities), "\r\n";
}
if (@publishers > 0) {
print "PB - ", join(", ", @publishers), "\r\n";
}
}
}
##********************************************************************
## get_keywords(): prints info from MARC fields 6XX
## Arguments: list of fields (6XX)
##********************************************************************
sub get_keywords {
my($fieldname, @keywords) = @_;
my @kw;
## a list of all possible subfields
my @subfields = ('a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'x', 'y', 'z', '2', '3', '4');
## loop over all 6XX fields
foreach my $kwfield (@keywords) {
if ($kwfield != undef) {
## authornames get special treatment
if ($fieldname eq "600") {
my $val = normalize_author($kwfield->subfield('a'), $kwfield->subfield('b'), $kwfield->subfield('c'), $kwfield->indicator('1'));
push @kw, $val;
print "<marc>Field $kwfield subfield a:", $kwfield->subfield('a'), "\r\n<marc>Field $kwfield subfield b:", $kwfield->subfield('b'), "\r\n<marc>Field $kwfield subfield c:", $kwfield->subfield('c'), "\r\n" if $marcprint;
}
else {
## retrieve all available subfields
my @kwsubfields = $kwfield->subfields();
## loop over all available subfield tuples
foreach my $kwtuple (@kwsubfields) {
## loop over all subfields to check
foreach my $subfield (@subfields) {
## [0] contains subfield code
if (@$kwtuple[0] eq $subfield) {
## [1] contains value, remove trailing separators
@$kwtuple[1] =~ s% *[,;.:/]*$%%;
if (length(@$kwtuple[1]) > 0) {
push @kw, @$kwtuple[1];
print "<marc>Field $fieldname subfield $subfield:", @$kwtuple[1], "\r\n" if $marcprint;
}
## we can leave the subfields loop here
last;
}
}
}
}
}
}
return @kw;
}
##********************************************************************
## pool_subx(): adds contents of several subfields to a list
## Arguments: reference to a list
## field name
## list of fields (5XX)
##********************************************************************
sub pool_subx {
my($aref, $fieldname, @notefields) = @_;
## we use a list that contains the interesting subfields
## for each field
# ToDo: this is apparently correct only for marc21
my @subfields;
if ($fieldname eq "500") {
@subfields = ('a');
}
elsif ($fieldname eq "501") {
@subfields = ('a');
}
elsif ($fieldname eq "502") {
@subfields = ('a');
}
elsif ($fieldname eq "504") {
@subfields = ('a', 'b');
}
elsif ($fieldname eq "505") {
@subfields = ('a', 'g', 'r', 't', 'u');
}
elsif ($fieldname eq "506") {
@subfields = ('a', 'b', 'c', 'd', 'e');
}
elsif ($fieldname eq "507") {
@subfields = ('a', 'b');
}
elsif ($fieldname eq "508") {
@subfields = ('a');
}
elsif ($fieldname eq "510") {
@subfields = ('a', 'b', 'c', 'x', '3');
}
elsif ($fieldname eq "511") {
@subfields = ('a');
}
elsif ($fieldname eq "513") {
@subfields = ('a', 'b');
}
elsif ($fieldname eq "514") {
@subfields = ('a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'm', 'u', 'z');
}
elsif ($fieldname eq "515") {
@subfields = ('a');
}
elsif ($fieldname eq "516") {
@subfields = ('a');
}
elsif ($fieldname eq "518") {
@subfields = ('a', '3');
}
elsif ($fieldname eq "521") {
@subfields = ('a', 'b', '3');
}
elsif ($fieldname eq "522") {
@subfields = ('a');
}
elsif ($fieldname eq "524") {
@subfields = ('a', '2', '3');
}
elsif ($fieldname eq "525") {
@subfields = ('a');
}
elsif ($fieldname eq "526") {
@subfields = ('a', 'b', 'c', 'd', 'i', 'x', 'z', '5');
}
elsif ($fieldname eq "530") {
@subfields = ('a', 'b', 'c', 'd', 'u', '3');
}
elsif ($fieldname eq "533") {
@subfields = ('a', 'b', 'c', 'd', 'e', 'f', 'm', 'n', '3');
}
elsif ($fieldname eq "534") {
@subfields = ('a', 'b', 'c', 'e', 'f', 'k', 'l', 'm', 'n', 'p', 't', 'x', 'z');
}
elsif ($fieldname eq "535") {
@subfields = ('a', 'b', 'c', 'd', 'g', '3');
}
## loop over all notefields
foreach my $notefield (@notefields) {
if (defined $notefield) {
## retrieve all available subfield tuples
my @notesubfields = $notefield->subfields();
## loop over all subfield tuples
foreach my $notetuple (@notesubfields) {
## loop over all subfields to check
foreach my $subfield (@subfields) {
## [0] contains subfield code
if (@$notetuple[0] eq $subfield) {
## [1] contains value, remove trailing separators
print "<marc>field $fieldname subfield $subfield: ", @$notetuple[1], "\r\n" if $marcprint;
@$notetuple[1] =~ s% *[,;.:/]*$%%;
if (length(@$notetuple[1]) > 0) {
## add to list
push @{$aref}, @$notetuple[1];
}
last;
}
}
}
}
}
}
##********************************************************************
## print_abstract(): prints abstract fields
## Arguments: list of fields (520)
##********************************************************************
sub print_abstract {
# ToDo: take care of repeatable subfields
my(@abfields) = @_;
## we check the following subfields
my @subfields = ('a', 'b');
## we generate a list for all useful strings
my @abstrings;
## loop over all abfields
foreach my $abfield (@abfields) {
foreach my $field (@subfields) {
if ( length( $abfield->subfield($field) ) > 0 ) {
my $ab = $abfield->subfield($field);