X-Git-Url: http://git.rot13.org/?p=crolist2marc;a=blobdiff_plain;f=crolist2marc.pl;h=39eb02885cb43f6a7ead227c9586fa1e18523c0a;hp=fdb5402346a49801aebf2847c9708c4dcb044e5d;hb=aa91fb3e8dfa676159100b20c0374cca84ccd886;hpb=a0984ce9f4c0a38990f46cd54976a94dbb0a3376

diff --git a/crolist2marc.pl b/crolist2marc.pl
index fdb5402..39eb028 100755
--- a/crolist2marc.pl
+++ b/crolist2marc.pl
@@ -23,7 +23,7 @@ sub csv_file {
 		$lines++;
 
 		if ( ! $text ) {
-			print STDERR "\nSKIP $file +$lines [$_] ";
+			print STDERR "\nSKIP $file +$lines [$_] " if $idsl;
 			next;
 		}
 
@@ -48,29 +48,56 @@ sub csv_file {
 	print STDERR "\n";
 }
 
-csv_file( 'TEKTAG.csv', sub {
+csv_file( 'tsv/TEKTAG.csv', sub {
 	my $line = shift;
 
-	my ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $textkey, $textres ) = split(/,/,$_);
+	my ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $textkey, $textres ) = split(/\t/,$_);
 
 	my $text = $textkey . $textres; # FIXME fix CAPITAL letters in $textkey
 
 	return ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $text );
 });
 
-csv_file( 'LONTAG.csv', sub {
+csv_file( 'tsv/LONTAG.csv', sub {
 	my $line = shift;
 
-	my ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $text ) = split(/;/,$_, 7);
+	my ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $text ) = split(/\t/,$_, 7);
 
-	$text =~ s/;+$//;
-	$text =~ s/;/\n/g; # join OPIS[1-11]
+	$text =~ s/\t+$//;
+	$text =~ s/\t/\n/g; # join OPIS[1-11]
 
 	return ( $idsl, $tag, $tagno, $id, $sfi, $sfino, $text );
 });
 
+csv_file( 'tsv/IDNTAG.csv', sub {
+	my $line = shift;
+
+	my ( $idsl, $tag, $STSL, $KZVS, $BIBRAZ, $HIRAZ, $KPS, $OKO ) = split(/\t/,$_);
+
+	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( 'tsv/OBRTAG.csv', sub {
+	my $line = shift;
+
+	my ( $IDSL, $TAG, $TAGNO, $ID, $SFI, $SFINO, $CODINF ) = split(/\t/,$_);
+	return ( $IDSL, $TAG, $TAGNO, $ID, $SFI, $SFINO, $CODINF );
+});
+
 print STDERR "\n# getting all ids ";
-my @ids = keys %$data;
+my @ids = sort keys %$data;
 print STDERR scalar(@ids), " found\n";
 
 my $marc_file = 'liberated.marc';
@@ -80,12 +107,19 @@ my $number = 0;
 foreach my $id ( @ids ) {
 	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} );
+#				print STDERR "SKIPPED $id $field ",dump( $data->{$id}->{$field} ), "\n";
 				next;
 			}
+			$arr = [ $arr->[3] ] if ( $field < 010 ); # control fields don't have idicators or subfields
 			$rec->add_fields( $field, @$arr );
 		}
 	}