3 |
@EXPORT = qw/ |
@EXPORT = qw/ |
4 |
_set_rec _set_lookup |
_set_rec _set_lookup |
5 |
_get_ds _clean_ds |
_get_ds _clean_ds |
6 |
|
_debug |
7 |
|
|
8 |
tag search display |
tag search display |
9 |
marc marc_indicators marc_repeatable_subfield |
marc marc_indicators marc_repeatable_subfield |
10 |
|
marc_compose marc_leader |
11 |
|
|
12 |
rec1 rec2 rec |
rec1 rec2 rec |
13 |
regex prefix suffix surround |
regex prefix suffix surround |
14 |
first lookup join_with |
first lookup join_with |
15 |
|
|
16 |
|
split_rec_on |
17 |
/; |
/; |
18 |
|
|
19 |
use warnings; |
use warnings; |
33 |
|
|
34 |
=head1 VERSION |
=head1 VERSION |
35 |
|
|
36 |
Version 0.06 |
Version 0.09 |
37 |
|
|
38 |
=cut |
=cut |
39 |
|
|
40 |
our $VERSION = '0.06'; |
our $VERSION = '0.09'; |
41 |
|
|
42 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
43 |
|
|
157 |
|
|
158 |
$marc->add_fields( WebPAC::Normalize:_get_marc_fields() ); |
$marc->add_fields( WebPAC::Normalize:_get_marc_fields() ); |
159 |
|
|
|
|
|
|
|
|
160 |
We are using I<magic> which detect repeatable fields only from |
We are using I<magic> which detect repeatable fields only from |
161 |
sequence of field/subfield data generated by normalization. |
sequence of field/subfield data generated by normalization. |
162 |
|
|
163 |
Repeatable field is created if there is second occurence of same subfield or |
Repeatable field is created when there is second occurence of same subfield or |
164 |
if any of indicators are different. This is sane for most cases except for |
if any of indicators are different. |
165 |
non-repeatable fields with repeatable subfields. |
|
166 |
|
This is sane for most cases. Something like: |
167 |
|
|
168 |
You can change behaviour of that using C<marc_repeatable_subfield>. |
900a-1 900b-1 900c-1 |
169 |
|
900a-2 900b-2 |
170 |
|
900a-3 |
171 |
|
|
172 |
|
will be created from any combination of: |
173 |
|
|
174 |
|
900a-1 900a-2 900a-3 900b-1 900b-2 900c-1 |
175 |
|
|
176 |
|
and following rules: |
177 |
|
|
178 |
|
marc('900','a', rec('200','a') ); |
179 |
|
marc('900','b', rec('200','b') ); |
180 |
|
marc('900','c', rec('200','c') ); |
181 |
|
|
182 |
|
which might not be what you have in mind. If you need repeatable subfield, |
183 |
|
define it using C<marc_repeatable_subfield> like this: |
184 |
|
|
185 |
|
.... |
186 |
|
|
187 |
=cut |
=cut |
188 |
|
|
196 |
$a->[0] . $a->[3] cmp $b->[0] . $b->[3] |
$a->[0] . $a->[3] cmp $b->[0] . $b->[3] |
197 |
} @{ $marc_record }; |
} @{ $marc_record }; |
198 |
|
|
199 |
|
@sorted_marc_record = @{ $marc_record }; ### FIXME disable sorting |
200 |
|
|
201 |
# output marc fields |
# output marc fields |
202 |
my @m; |
my @m; |
203 |
|
|
288 |
return @m; |
return @m; |
289 |
} |
} |
290 |
|
|
291 |
|
=head2 _debug |
292 |
|
|
293 |
|
Change level of debug warnings |
294 |
|
|
295 |
|
_debug( 2 ); |
296 |
|
|
297 |
|
=cut |
298 |
|
|
299 |
|
sub _debug { |
300 |
|
my $l = shift; |
301 |
|
return $debug unless defined($l); |
302 |
|
warn "debug level $l",$/ if ($l > 0); |
303 |
|
$debug = $l; |
304 |
|
} |
305 |
|
|
306 |
=head1 Functions to create C<data_structure> |
=head1 Functions to create C<data_structure> |
307 |
|
|
308 |
Those functions generally have to first in your normalization file. |
Those functions generally have to first in your normalization file. |
357 |
$out->{$name}->{search} = \@o; |
$out->{$name}->{search} = \@o; |
358 |
} |
} |
359 |
|
|
360 |
|
=head2 marc_leader |
361 |
|
|
362 |
|
Setup fields within MARC leader or get leader |
363 |
|
|
364 |
|
marc_leader('05','c'); |
365 |
|
my $leader = marc_leader(); |
366 |
|
|
367 |
|
=cut |
368 |
|
|
369 |
|
sub marc_leader { |
370 |
|
my ($offset,$value) = @_; |
371 |
|
|
372 |
|
if ($offset) { |
373 |
|
$out->{' leader'}->{ $offset } = $value; |
374 |
|
} else { |
375 |
|
return $out->{' leader'}; |
376 |
|
} |
377 |
|
} |
378 |
|
|
379 |
=head2 marc |
=head2 marc |
380 |
|
|
381 |
Save value for MARC field |
Save value for MARC field |
435 |
@{ $marc_indicators->{$f} } = ($i1,$i2); |
@{ $marc_indicators->{$f} } = ($i1,$i2); |
436 |
} |
} |
437 |
|
|
438 |
|
=head2 marc_compose |
439 |
|
|
440 |
|
Save values for each MARC subfield explicitly |
441 |
|
|
442 |
|
marc_compose('900', |
443 |
|
'a', rec('200','a') |
444 |
|
'b', rec('201','a') |
445 |
|
'a', rec('200','b') |
446 |
|
'c', rec('200','c') |
447 |
|
); |
448 |
|
|
449 |
|
=cut |
450 |
|
|
451 |
|
sub marc_compose { |
452 |
|
my $f = shift or die "marc_compose needs field"; |
453 |
|
die "marc_compose field must be numer" unless ($f =~ /^\d+$/); |
454 |
|
|
455 |
|
my ($i1,$i2) = defined($marc_indicators->{$f}) ? @{ $marc_indicators->{$f} } : (' ',' '); |
456 |
|
my $m = [ $f, $i1, $i2 ]; |
457 |
|
|
458 |
|
while (@_) { |
459 |
|
my $sf = shift or die "marc_compose $f needs subfield"; |
460 |
|
my $v = shift; |
461 |
|
|
462 |
|
next unless (defined($v) && $v !~ /^\s*$/); |
463 |
|
from_to($v, 'iso-8859-2', $marc_encoding) if ($marc_encoding); |
464 |
|
push @$m, ( $sf, $v ); |
465 |
|
warn "## ++ marc_compose($f,$sf,$v) ", dump( $m ),$/ if ($debug > 1); |
466 |
|
} |
467 |
|
|
468 |
|
warn "## marc_compose(d) ", dump( $m ),$/ if ($debug > 1); |
469 |
|
|
470 |
|
push @{ $marc_record }, $m if ($#{$m} > 2); |
471 |
|
} |
472 |
|
|
473 |
|
|
474 |
=head1 Functions to extract data from input |
=head1 Functions to extract data from input |
475 |
|
|
639 |
return join($d, grep { defined($_) && $_ ne '' } @_); |
return join($d, grep { defined($_) && $_ ne '' } @_); |
640 |
} |
} |
641 |
|
|
642 |
|
=head2 split_rec_on |
643 |
|
|
644 |
|
Split record subfield on some regex and take one of parts out |
645 |
|
|
646 |
|
$a_before_semi_column = |
647 |
|
split_rec_on('200','a', /\s*;\s*/, $part); |
648 |
|
|
649 |
|
C<$part> is optional number of element. First element is |
650 |
|
B<1>, not 0! |
651 |
|
|
652 |
|
If there is no C<$part> parameter or C<$part> is 0, this function will |
653 |
|
return all values produced by splitting. |
654 |
|
|
655 |
|
=cut |
656 |
|
|
657 |
|
sub split_rec_on { |
658 |
|
die "split_rec_on need (fld,sf,regex[,part]" if ($#_ < 2); |
659 |
|
|
660 |
|
my ($fld, $sf, $regex, $part) = @_; |
661 |
|
warn "### regex ", ref($regex), $regex, $/ if ($debug > 2); |
662 |
|
|
663 |
|
my @r = rec( $fld, $sf ); |
664 |
|
my $v = shift @r; |
665 |
|
warn "### first rec($fld,$sf) = ",dump($v),$/ if ($debug > 2); |
666 |
|
|
667 |
|
return '' if( ! defined($v) || $v =~ /^\s*$/); |
668 |
|
|
669 |
|
my @s = split( $regex, $v ); |
670 |
|
warn "## split_rec_on($fld,$sf,$regex,$part) = ",dump(@s),$/ if ($debug > 1); |
671 |
|
if ($part && $part > 0) { |
672 |
|
return $s[ $part - 1 ]; |
673 |
|
} else { |
674 |
|
return [ @s ]; |
675 |
|
} |
676 |
|
} |
677 |
|
|
678 |
# END |
# END |
679 |
1; |
1; |