X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=lib%2FWebPAC%2FInput.pm;h=462a303dede5dab5a21197b90559a2635fdd08ef;hb=3d8c0587feb95d81a4fa205aeb6305a67f182867;hp=94afb8ba78c0c565e436161a65055e6009d0d518;hpb=41189f41c13b9066afd55b2bff6b14aeb7538aa1;p=webpac2

diff --git a/lib/WebPAC/Input.pm b/lib/WebPAC/Input.pm
index 94afb8b..462a303 100644
--- a/lib/WebPAC/Input.pm
+++ b/lib/WebPAC/Input.pm
@@ -137,7 +137,7 @@ This function will read whole database in memory and produce lookups.
 
 By default, C<input_encoding> is assumed to be C<cp852>.
 
-C<offset> is optional parametar to position at some offset before reading from database.
+C<offset> is optional parametar to skip records at beginning.
 
 C<limit> is optional parametar to read just C<limit> records from database
 
@@ -182,9 +182,7 @@ sub open {
 	my $input_encoding = $arg->{'input_encoding'} || $self->{'input_encoding'} || 'cp852';
 
 	# store data in object
-	foreach my $v (qw/path offset limit/) {
-		$self->{$v} = $arg->{$v} if defined $arg->{$v};
-	}
+	$self->{$_} = $arg->{$_} foreach grep { defined $arg->{$_} } qw(path offset limit);
 
 	if ($arg->{load_row} || $arg->{save_row}) {
 		$log->logconfess("save_row and load_row must be defined in pair and be CODE") unless (
@@ -208,6 +206,7 @@ sub open {
 			while (@r) {
 				my $from = shift @r;
 				my $to = shift @r;
+				$from =~ s/^\\x([0-9a-f]{2})/chr(hex($1))/eig;
 				$recode_map->{$from} = $to;
 			}
 
@@ -264,10 +263,10 @@ sub open {
 	my $to_rec = $size;
 
 	if (my $s = $self->{offset}) {
-		$log->debug("skipping to MFN $s");
-		$from_rec = $s;
+		$log->debug("offset $s records");
+		$from_rec = $s + 1;
 	} else {
-		$self->{offset} = $from_rec;
+		$self->{offset} = $from_rec - 1;
 	}
 
 	if ($self->{limit}) {
@@ -276,21 +275,22 @@ sub open {
 		$to_rec = $size if ($to_rec > $size);
 	}
 
-	# store size for later
-	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
-
 	my $strict_encoding = $arg->{strict_encoding} || $self->{strict_encoding}; ## FIXME should be 1 really
 
-	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec]",
+	$log->info("processing ", $self->{size} || 'all', "/$size records [$from_rec-$to_rec]",
 		" encoding $input_encoding ", $strict_encoding ? ' [strict]' : '',
 		$self->{stats} ? ' [stats]' : '',
 	);
 
+	$self->{size} = 0;
+
 	# read database
 	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
 
 		$log->debug("position: $pos\n");
 
+		$self->{size}++; # XXX I could move this more down if I didn't want empty records...
+
 		my $rec = $ll_db->fetch_rec($pos, sub {
 				my ($l,$f_nr,$debug) = @_;
 #				return unless defined($l);
@@ -298,6 +298,8 @@ sub open {
 
 				return unless ( defined($l) && defined($f_nr) );
 
+				my $marc_subfields = $l =~ s/\x1F(\w)/\^$1/g; # fix MARC subfiled delimiters to ^
+
 				warn "-=> $f_nr ## |$l|\n" if ($debug);
 				$log->debug("-=> $f_nr ## $l");
 
@@ -325,6 +327,8 @@ sub open {
 					}
 				}
 
+				$l =~ s/\^(\w)/\x1F$1/g if $marc_subfields;
+
 				$log->debug("<=- $f_nr ## |$l|");
 				warn "<=- $f_nr ## $l\n" if ($debug);
 				return $l;
@@ -415,7 +419,7 @@ sub fetch {
 	$log->logconfess("it seems that you didn't load database!") unless ($self->{pos});
 
 	if ($self->{pos} == -1) {
-		$self->{pos} = $self->{offset};
+		$self->{pos} = $self->{offset} + 1;
 	} else {
 		$self->{pos}++;
 	}
@@ -473,7 +477,7 @@ because it takes into account C<offset> and C<limit>.
 
 sub size {
 	my $self = shift;
-	return $self->{size};
+	return $self->{size}; # FIXME this is buggy if open is called multiple times!
 }
 
 =head2 seek