X-Git-Url: http://git.rot13.org/?p=crolist2marc;a=blobdiff_plain;f=crolist2marc.pl;h=49aa86a5d33c4c144b54743e8c0bf13fe54706ca;hp=ef4b056174fd2d2a070eab5219fa8c38d72153c0;hb=11bf190ad5ab79edce6ab03045b87c8e72c8c64d;hpb=2dc6b222180984ce7c6bf1a5471724666d6df7c8

diff --git a/crolist2marc.pl b/crolist2marc.pl
index ef4b056..49aa86a 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 [$_] " if $idsl;
 			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;
@@ -69,10 +69,67 @@ csv_file( 'LONTAG.csv', sub {
 	return ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $text );
 });
 
+csv_file( 'IDNTAG.csv', sub {
+	my $line = shift;
+
+	my ( $idsl, $tag, $STSL, $KZVS, $BIBRAZ, $HIRAZ, $KPS, $OKO ) = split(/,/,$_);
+
+	my @leader;
+	$leader[5] = $STSL;
+	$leader[6] = $KZVS;
+	$leader[7] = $BIBRAZ;
+	$leader[8] = $HIRAZ;
+	$leader[17] = $KPS;
+	$leader[18] = $OKO;
+
+	$leader[23] = ' '; # last char;
+
+	my $full = join('', map { defined $_ ? $_ : ' ' } @leader);
+	$data->{$idsl}->{'leader'} = $full; 
+	return;
+});
+
+csv_file( 'OBRTAG.csv', sub {
+	my $line = shift;
+
+	my ( $IDSL, $TAG, $TAGNO, $ID, $SFI, $SFINO, $CODINF ) = split(/,/,$_);
+	return ( $IDSL, $TAG, $TAGNO, $ID, $SFI, $SFINO, $CODINF );
+});
+
 print STDERR "\n# getting all ids ";
 my @ids = keys %$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' );
+	$rec->add_fields( [ '001', $id ] );
+
+	foreach my $field ( sort keys %{ $data->{$id} } ) {
+		if ( $field eq 'leader' ) {
+			$rec->leader( $data->{$id}->{$field} );
+			next;
+		}
+		foreach my $arr ( @{ $data->{$id}->{$field} } ) {
+			if ( ! $arr ) {
+				print STDERR "SKIPPED $id $field ",dump( $data->{$id}->{$field} ), "\n";
+				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";