9 |
marc marc_indicators marc_repeatable_subfield |
marc marc_indicators marc_repeatable_subfield |
10 |
marc_compose marc_leader |
marc_compose marc_leader |
11 |
marc_duplicate marc_remove |
marc_duplicate marc_remove |
12 |
|
marc_original_order |
13 |
|
|
14 |
rec1 rec2 rec |
rec1 rec2 rec |
15 |
regex prefix suffix surround |
regex prefix suffix surround |
36 |
|
|
37 |
=head1 VERSION |
=head1 VERSION |
38 |
|
|
39 |
Version 0.14 |
Version 0.15 |
40 |
|
|
41 |
=cut |
=cut |
42 |
|
|
43 |
our $VERSION = '0.14'; |
our $VERSION = '0.15'; |
44 |
|
|
45 |
=head1 SYNOPSIS |
=head1 SYNOPSIS |
46 |
|
|
526 |
'c', rec('200','c') |
'c', rec('200','c') |
527 |
); |
); |
528 |
|
|
529 |
|
If you specify C<+> for subfield, value will be appended |
530 |
|
to previous defined subfield. |
531 |
|
|
532 |
=cut |
=cut |
533 |
|
|
534 |
sub marc_compose { |
sub marc_compose { |
546 |
|
|
547 |
next unless (defined($v) && $v !~ /^\s*$/); |
next unless (defined($v) && $v !~ /^\s*$/); |
548 |
from_to($v, 'iso-8859-2', $marc_encoding) if ($marc_encoding); |
from_to($v, 'iso-8859-2', $marc_encoding) if ($marc_encoding); |
|
push @$m, ( $sf, $v ); |
|
549 |
warn "## ++ marc_compose($f,$sf,$v) ", dump( $m ),$/ if ($debug > 1); |
warn "## ++ marc_compose($f,$sf,$v) ", dump( $m ),$/ if ($debug > 1); |
550 |
|
if ($sf ne '+') { |
551 |
|
push @$m, ( $sf, $v ); |
552 |
|
} else { |
553 |
|
$m->[ $#$m ] .= $v; |
554 |
|
} |
555 |
} |
} |
556 |
|
|
557 |
warn "## marc_compose current marc = ", dump( $m ),$/ if ($debug > 1); |
warn "## marc_compose current marc = ", dump( $m ),$/ if ($debug > 1); |
642 |
warn "## full marc_record = ", dump( @{ $marc_record }), $/ if ($debug > 1); |
warn "## full marc_record = ", dump( @{ $marc_record }), $/ if ($debug > 1); |
643 |
} |
} |
644 |
|
|
645 |
|
=head2 marc_original_order |
646 |
|
|
647 |
|
Copy all subfields preserving original order to marc field. |
648 |
|
|
649 |
|
marc_original_order(210, 260); |
650 |
|
|
651 |
|
You might want to use this command if you are just renaming subfields or |
652 |
|
using pre-processing modify_record in C<config.yml> and don't need any |
653 |
|
post-processing or want to preserve order of original subfields. |
654 |
|
|
655 |
|
=cut |
656 |
|
|
657 |
|
sub marc_original_order { |
658 |
|
|
659 |
|
my ($from, $to) = @_; |
660 |
|
die "marc_original_order needs from and to fields\n" unless ($from && $to); |
661 |
|
|
662 |
|
my $r = $rec->{$from} || return; |
663 |
|
die "record field $from isn't array\n" unless (ref($r) eq 'ARRAY'); |
664 |
|
|
665 |
|
my ($i1,$i2) = defined($marc_indicators->{$to}) ? @{ $marc_indicators->{$to} } : (' ',' '); |
666 |
|
warn "## marc_original_order($from,$to) source = ", dump( $r ),$/ if ($debug > 1); |
667 |
|
|
668 |
|
foreach my $d (@$r) { |
669 |
|
|
670 |
|
my @sfs = @{ $d->{subfields} }; |
671 |
|
|
672 |
|
die "field $from doesn't have subfields specification\n" unless(@sfs); |
673 |
|
die "field $from doesn't have even number of subfields specifications\n" unless($#sfs % 2 == 1); |
674 |
|
|
675 |
|
warn "#--> d: ",dump($d), "\n#--> sfs: ",dump(@sfs),$/; |
676 |
|
|
677 |
|
my $m = [ $to, $i1, $i2 ]; |
678 |
|
|
679 |
|
while (my $sf = shift @sfs) { |
680 |
|
warn "#--> sf: ",dump($sf), $/; |
681 |
|
my $offset = shift @sfs; |
682 |
|
die "corrupted sufields specification for field $from\n" unless defined($offset); |
683 |
|
|
684 |
|
my $v; |
685 |
|
if (ref($d->{$sf}) eq 'ARRAY') { |
686 |
|
$v = $d->{$sf}->[$offset] if (defined($d->{$sf}->[$offset])); |
687 |
|
} elsif ($offset == 0) { |
688 |
|
$v = $d->{$sf}; |
689 |
|
} else { |
690 |
|
die "field $from subfield '$sf' need occurence $offset which doesn't exist", dump($d->{$sf}); |
691 |
|
} |
692 |
|
push @$m, ( $sf, $v ) if (defined($v)); |
693 |
|
} |
694 |
|
|
695 |
|
if ($#{$m} > 2) { |
696 |
|
push @{ $marc_record->[ $marc_record_offset ] }, $m; |
697 |
|
} |
698 |
|
} |
699 |
|
|
700 |
|
warn "## marc_record = ", dump( $marc_record ),$/ if ($debug > 1); |
701 |
|
|
702 |
|
warn "# marc_original_order is partly implemented"; |
703 |
|
} |
704 |
|
|
705 |
|
|
706 |
=head1 Functions to extract data from input |
=head1 Functions to extract data from input |
707 |
|
|
708 |
This function should be used inside functions to create C<data_structure> described |
This function should be used inside functions to create C<data_structure> described |
748 |
my $f = shift; |
my $f = shift; |
749 |
return unless (defined($rec && $rec->{$f})); |
return unless (defined($rec && $rec->{$f})); |
750 |
my $sf = shift; |
my $sf = shift; |
751 |
|
warn "rec2($f,$sf) = ", dump( $rec->{$f} ), $/ if ($debug > 1); |
752 |
return map { |
return map { |
753 |
if (ref($_->{$sf}) eq 'ARRAY') { |
if (ref($_->{$sf}) eq 'ARRAY') { |
754 |
@{ $_->{$sf} }; |
@{ $_->{$sf} }; |
986 |
my $v = shift @r; |
my $v = shift @r; |
987 |
warn "### first rec($fld,$sf) = ",dump($v),$/ if ($debug > 2); |
warn "### first rec($fld,$sf) = ",dump($v),$/ if ($debug > 2); |
988 |
|
|
989 |
return '' if( ! defined($v) || $v =~ /^\s*$/); |
return '' if ( ! defined($v) || $v =~ /^\s*$/); |
990 |
|
|
991 |
my @s = split( $regex, $v ); |
my @s = split( $regex, $v ); |
992 |
warn "## split_rec_on($fld,$sf,$regex,$part) = ",dump(@s),$/ if ($debug > 1); |
warn "## split_rec_on($fld,$sf,$regex,$part) = ",dump(@s),$/ if ($debug > 1); |