slubsipbuilder.pl

#!/usr/bin/env perl
#===============================================================================
#
#         FILE: slubsipbuilder.pl
#
#        USAGE: ./slubsipbuilder.pl
#
#  DESCRIPTION: A CLI tool to create a valid SIP for SLUBArchiv
#
# REQUIREMENTS: ---
#         BUGS: ---
#        NOTES: related to official document
#               "SIP Spezifikation (v1.4.2)"
#       AUTHOR: Andreas Romeyke (romeyke@slub-dresden.de)
# ORGANIZATION: SLUB
#      VERSION: 1.1
#      CREATED: 2019-07-23
#===============================================================================



use strict;
use warnings;
use Carp;
use 5.28.0;
package SLUB::LZA::SIPBuilder;
    use DateTime::Format::ISO8601;
    use File::Copy qw(cp);
    use File::Find;
    use Path::Tiny;
    use LWP::UserAgent; # to get MARC data
    use MARC::Record;
    use XML::LibXML;
    use XML::LibXSLT;
    use XML::XPath;
    use Carp;
    my $marc_mods_url = 'http://www.loc.gov/standards/mods/v3/MARC21slim2MODS3-6.xsl';
    my $marc_utils_url = 'http://www.loc.gov/standards/marcxml/xslt/MARC21slimUtils.xsl';
    my $swb_url = 'https://sru.bsz-bw.de/swb';
    my $searchkey = "pica.swn";
    my $recordschema = "marcxmlvbos";
    our $VERSION = '1.2';
    our $with_debug=0;


    # write data to file (UTF-8)
    sub write_file($$) {
        my $filename = $_[0];
        my $value = $_[1];
        open(my $fh, '>:encoding(UTF-8)', $filename) || (croak "Can't open '$filename', $!");
        print $fh $value;
        close($fh) || (croak "could not close file '$filename', $!");
        return 1;
    }

    # this will patch the mods-xml as a workaround for bugs in LOCs xslt files
    sub patch_mods($) {
        my $modsobj = shift; # mods expected as XML Parser object
        # TODO: Bugfix for /mets:mets/mets:dmdSec[1]/mets:mdWrap[1]/mets:xmlData[1]/mods:modsCollection[1]/mods:mods[1]/mods:relatedItem[2]/mods:internetMediaType[1]
        my $xslt_patch_string = <<'PATCH';
<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xs="http://www.w3.org/2001/XMLSchema"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xmlns:mods="http://www.loc.gov/mods/v3"
    xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-6.xsd"
    exclude-result-prefixes="xs"
    version="1.0">
    <xsl:output encoding="UTF-8" indent="yes" method="xml"/>
    <xsl:strip-space elements="*"/>