Created
April 2, 2014 07:11
-
-
Save MagnusEnger/9929280 to your computer and use it in GitHub Desktop.
Tab separated to MARC via Catmandu
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/perl | |
# Copyright 2013 Magnus Enger Libriotech | |
=head1 NAME | |
tab2marc.pl - Convert some tab-delimited data to MARCXML. | |
=head1 SYNOPSIS | |
$ perl csv2marc.pl -i records_tab.txt -v | |
To pretty-print the output: | |
$ perl csv2marc.pl -i records_tab.txt | xmllint --format - | |
=head1 NOTES | |
Some of the fields in the input file were given names after the | |
MARC fields they should go into, like 300a. This could probably | |
have been used to shove the data into the right MARC field | |
autmagically, but that was not attempted for this project. | |
Maybe next time? | |
=cut | |
use Catmandu::Importer::CSV; | |
use Catmandu::Exporter::MARC; | |
use Getopt::Long; | |
use Data::Dumper; | |
use Pod::Usage; | |
use Modern::Perl; | |
# Get options | |
my ( $input_file, $koha, $limit, $verbose, $debug ) = get_options(); | |
# Check that the file exists | |
if ( !-e $input_file ) { | |
print "The file $input_file does not exist...\n"; | |
exit; | |
} | |
my $importer = Catmandu::Importer::CSV->new( | |
file => $input_file, | |
sep_char => "\t", | |
); | |
my $exporter = Catmandu::Exporter::MARC->new( | |
# file => "kurdlib.marcxml", | |
type => "XML", | |
xml_declaration => 1, | |
collection => 1, | |
skip_empty_subfields => 1, | |
); | |
my $record_count = 0; | |
my $n = $importer->each(sub { | |
# Get the record | |
my $rec = $_[0]; | |
# say Dumper $rec; | |
# say "***|" . $rec->{ 'genre' } . "|"; | |
# Extract the "date entered on file" | |
my $date_entered = " "; | |
if ( $rec->{ '008/00-05_skapat datum' } && $rec->{ '008/00-05_skapat datum' } =~ m/\d\d(\d\d)-(\d\d)-(\d\d)/ ) { | |
$date_entered = "$1$2$3"; | |
} | |
# Extract the "date of last transaction" | |
my $last_transaction = " "; | |
if ( $rec->{ '000_andrat_datum' } && $rec->{ '000_andrat_datum' } =~ m/(\d\d\d\d)-(\d\d)-(\d\d)/ ) { | |
$last_transaction = "$1$2$3"; | |
} | |
# 007/00 | |
my $p007_00 = 't'; | |
if ( $rec->{ '008/18-34_format' } =~ m/digitised/i || $rec->{ '008/18-34_format' } =~ m/E-bok/i ) { | |
$p007_00 = 'c'; | |
} | |
# Build up the record | |
my $data = { | |
record => [ | |
['001', undef, undef, undef, $record_count+1], | |
['005', undef, undef, undef, $last_transaction], | |
['005', undef, undef, undef, $p007_00 . " " x 21], | |
['008', undef, undef, undef, $date_entered . " " x 34], | |
['020', ' ', ' ', 'a', $rec->{ '020a' }], | |
['035', ' ', ' ', 'a', $rec->{ 'ID-nummer' }], | |
['041', ' ', ' ', | |
'a', $rec->{ '041a1' }, | |
'a', $rec->{ '041a2' }, | |
'a', $rec->{ '041a3' }, | |
'b', $rec->{ '041b' }, | |
'h', $rec->{ '041h1' }, | |
'h', $rec->{ '041h2' }, | |
], | |
['084', ' ', ' ', 'a', $rec->{ '084a' }], | |
['100', ' ', ' ', 'a', $rec->{ '100a' }], | |
['240', ' ', ' ', | |
'a', $rec->{ '240a' }, | |
'l', $rec->{ '240l' }, | |
], | |
['245', ' ', ' ', | |
'a', $rec->{ '245a' }, | |
'b', $rec->{ '245b' }, | |
'c', $rec->{ '245c' }, | |
'h', $rec->{ '245h' }, | |
], | |
['250', ' ', ' ', 'a', $rec->{ '250a' }], | |
['260', ' ', ' ', | |
'a', $rec->{ '260a' }, | |
'b', $rec->{ '260b' }, | |
'c', $rec->{ '260c' }, | |
'e', $rec->{ 'Tryckeri_land' }, | |
'f', $rec->{ 'Tryckeri_namn' }, | |
], | |
['300', ' ', ' ', | |
'a', $rec->{ '300a' }, | |
'b', $rec->{ '300b' }, | |
'e', $rec->{ '300e' }, | |
], | |
['500', ' ', ' ', 'a', $rec->{ '500a' }], | |
['502', ' ', ' ', 'a', $rec->{ '502' }], | |
['504', ' ', ' ', 'a', $rec->{ '504' }], | |
['533', ' ', ' ', | |
'a', $rec->{ '533a' }, | |
'b', $rec->{ '533b' }, | |
'c', $rec->{ '533c' }, | |
'd', $rec->{ '533d' }, | |
], | |
['546', ' ', ' ', 'a', $rec->{ '546' }], | |
['653', '0', '6', 'a', $rec->{ 'sjanger' }], | |
['700', ' ', ' ', | |
'a', $rec->{ '700a1' }, | |
'4', $rec->{ '70041' }, | |
], | |
['700', ' ', ' ', | |
'a', $rec->{ '700a2' }, | |
'4', $rec->{ '70042' }, | |
], | |
['700', ' ', ' ', | |
'a', $rec->{ '700a3' }, | |
'4', $rec->{ '70043' }, | |
], | |
['700', ' ', ' ', | |
'a', $rec->{ '700a4' }, | |
'4', $rec->{ '70044' }, | |
], | |
['710', ' ', ' ', 'a', $rec->{ '710a' }], | |
['856', ' ', ' ', | |
'u', $rec->{ '856u' }, | |
'z', $rec->{ '856z' }, | |
], | |
], | |
}; | |
# Add fields that should only be used by Koha | |
if ( $koha ) { | |
# Add notes | |
push $data->{'record'}, | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Originalitet' }, "Originalitet: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Antal i upplaga' }, "Antal i upplaga: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Anskaffning' }, "Anskaffning: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Gåvagivare' }, "Gåvagivare: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Anteckningar' }, "Anteckningar: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Genre' }, "Genre: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Katalogisör' }, "Katalogisör: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Ej ISBN beteckning' }, "Ej ISBN beteckning: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ 'Placering' }, "Placering: " )], | |
['500', ' ', ' ', 'a', e2u( $rec->{ '008/15-17_utgivningsland' }, "Utgivningsland: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Dialekt_01' }, "Dialekt: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Dialekt_02' }, "Dialekt: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Alfabet_01' }, "Alfabet: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Alfabet_02' }, "Alfabet: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Originalalfabet' }, "Originalalfabet: " )], | |
['546', ' ', ' ', 'a', e2u( $rec->{ 'Oversettningvia' }, "Översättning via: " )]; | |
# Add items according to the Koha frameworks | |
if ( $rec->{ 'Antal i biblioteket' } ) { | |
for ( 1..$rec->{ 'Antal i biblioteket' } ) { | |
push @{ $data->{ record } }, [ '952', ' ', ' ', 'a', 'KURDLIB', 'b', 'KURDLIB' ]; | |
} | |
} | |
} | |
# Add the record to the exporter | |
$exporter->add($data); | |
# Count processed records and bail out if we reached the limit | |
$record_count++; | |
if ( $limit && $record_count == $limit ) { | |
last; | |
} | |
}); | |
$exporter->commit; | |
say "$n records found" if $verbose; | |
say "$record_count records processed" if $verbose; | |
sub e2u { | |
my ( $s, $prefix ) = @_; | |
if ( $s && $prefix ) { | |
return "$prefix$s"; | |
} | |
} | |
=head1 OPTIONS | |
=over 4 | |
=item B<-i, --infile> | |
Name of input file. | |
=item B<-l, --limit> | |
Only process the n first records. | |
=item B<-v --verbose> | |
More output. | |
=item B<-d --debug> | |
Even more output. | |
=item B<-h, -?, --help> | |
Prints this help message and exits. | |
=back | |
=cut | |
sub get_options { | |
# Options | |
my $input_file = ''; | |
my $koha = ''; | |
my $limit = '', | |
my $verbose = ''; | |
my $debug = ''; | |
my $help = ''; | |
GetOptions ( | |
'i|infile=s' => \$input_file, | |
'k|koha' => \$koha, | |
'l|limit=i' => \$limit, | |
'v|verbose' => \$verbose, | |
'd|debug' => \$debug, | |
'h|?|help' => \$help | |
); | |
pod2usage( -exitval => 0 ) if $help; | |
pod2usage( -msg => "\nMissing Argument: -i, --infile required\n", -exitval => 1 ) if !$input_file; | |
return ( $input_file, $koha, $limit, $verbose, $debug ); | |
} | |
=head1 LICENSE | |
This 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 file 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 file; if not, write to the Free Software | |
Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA | |
=cut |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment