From a0984ce9f4c0a38990f46cd54976a94dbb0a3376 Mon Sep 17 00:00:00 2001
From: Dobrica Pavlinusic <dpavlin@rot13.org>
Date: Thu, 12 Sep 2013 14:54:09 +0200
Subject: [PATCH] create liberated.marc file

---
 crolist2marc.pl | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/crolist2marc.pl b/crolist2marc.pl
index ef4b056..fdb5402 100755
--- a/crolist2marc.pl
+++ b/crolist2marc.pl
@@ -13,7 +13,7 @@ sub csv_file {
 	my ($file,$parse) = @_;
 
 	print STDERR "# reading $file ";
-	my $lines = 0;
+	my $lines = 1;
 
 	open(my $fh, '<', $file);
 	my $h = <$fh>; # header
@@ -23,7 +23,7 @@ sub csv_file {
 		$lines++;
 
 		if ( ! $text ) {
-			print STDERR "\nSKIP $lines [$_] ";
+			print STDERR "\nSKIP $file +$lines [$_] ";
 			next;
 		}
 
@@ -36,7 +36,7 @@ sub csv_file {
 
 		$sfi =~ s/^\$// || die "can't fix subfield [$sfi]";
 
-		$text =~ tr/^~]}\|[{@`/ČčĆćĐ𩹮ž/; # CROASCII (YUS|HRN) B1.002:1982
+		$text =~ tr/^~]}\\|[{@`/ČčĆćĐ𩹮ž/; # CROASCII (YUS|HRN) B1.002:1982
 
 		$data->{$idsl}->{$tag}->[ $tagno ]->[ 0 ] = $i1;
 		$data->{$idsl}->{$tag}->[ $tagno ]->[ 1 ] = $i2;
@@ -72,7 +72,31 @@ csv_file( 'LONTAG.csv', sub {
 print STDERR "\n# getting all ids ";
 my @ids = keys %$data;
 print STDERR scalar(@ids), " found\n";
+
+my $marc_file = 'liberated.marc';
+open(my $marc_fh, '>:encoding(UTF-8)', $marc_file);
+my $number = 0;
+
 foreach my $id ( @ids ) {
-	print "# $id ",dump($data->{$id});
+	my $rec = MARC::Record->new;
+	$rec->encoding( 'UTF-8' );
+	foreach my $field ( sort keys %{ $data->{$id} } ) {
+		foreach my $arr ( @{ $data->{$id}->{$field} } ) {
+			if ( ! $arr ) {
+				print STDERR "SKIPPED $id $field ",dump( $data->{$id} );
+				next;
+			}
+			$rec->add_fields( $field, @$arr );
+		}
+	}
+
+	#print $rec->as_formatted;
+	#print "# $id ",dump($data->{$id});
+
+	print $marc_fh $rec->as_usmarc;
+	$number++;
+	print "$number " if $number % 1000 == 0;
 }
 
+close($marc_fh);
+print "$marc_file ",-s $marc_file, " bytes\n";
-- 
2.20.1