--- trunk/lib/WebPAC/Input.pm	2005/12/20 19:01:22	308
+++ trunk/lib/WebPAC/Input.pm	2006/05/14 12:34:50	487
@@ -14,11 +14,11 @@
 
 =head1 VERSION
 
-Version 0.03
+Version 0.04
 
 =cut
 
-our $VERSION = '0.03';
+our $VERSION = '0.04';
 
 =head1 SYNOPSIS
 
@@ -47,9 +47,10 @@
     );
 
     $db->open('/path/to/database');
-    print "database size: ",$db->size,"\n";
-    while (my $rec = $db->fetch) {
-    }
+	print "database size: ",$db->size,"\n";
+	while (my $rec = $db->fetch) {
+		# do something with $rec
+	}
 
 
 
@@ -63,6 +64,8 @@
 	module => 'WebPAC::Input::MARC',
 	code_page => 'ISO-8859-2',
 	low_mem => 1,
+	recode => 'char pairs',
+	no_progress_bar => 1,
   );
 
 C<module> is low-level file format module. See L<WebPAC::Input::Isis> and
@@ -74,6 +77,11 @@
 
 Default is not to use C<low_mem> options (see L<MEMORY USAGE> below).
 
+C<recode> is optional string constisting of character or words pairs that
+should be replaced in input stream.
+
+C<no_progress_bar> disables progress bar output on C<STDOUT>
+
 This function will also call low-level C<init> if it exists with same
 parametars.
 
@@ -183,8 +191,37 @@
 	# create Text::Iconv object
 	$self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'});
 
+	my $filter_ref;
+
+	if ($self->{recode}) {
+		my @r = split(/\s/, $self->{recode});
+		if ($#r % 2 != 1) {
+			$log->logwarn("recode needs even number of elements (some number of valid pairs)");
+		} else {
+			my $recode;
+			while (@r) {
+				my $from = shift @r;
+				my $to = shift @r;
+				$recode->{$from} = $to;
+			}
+
+			my $regex = join '|' => keys %{ $recode };
+
+			$log->debug("using recode regex: $regex");
+			
+			$filter_ref = sub {
+				my $t = shift;
+				$t =~ s/($regex)/$recode->{$1}/g;
+				return $t;
+			};
+
+		}
+
+	}
+
 	my ($db, $size) = $self->{open_db}->( $self, 
 		path => $arg->{path},
+		filter => $filter_ref,
 	);
 
 	unless ($db) {
@@ -197,29 +234,29 @@
 		return;
 	}
 
-	my $offset = 1;
-	my $limit = $size;
+	my $from_rec = 1;
+	my $to_rec = $size;
 
 	if (my $s = $self->{offset}) {
 		$log->info("skipping to MFN $s");
-		$offset = $s;
+		$from_rec = $s;
 	} else {
-		$self->{offset} = $offset;
+		$self->{offset} = $from_rec;
 	}
 
 	if ($self->{limit}) {
 		$log->debug("limiting to ",$self->{limit}," records");
-		$limit = $offset + $self->{limit} - 1;
-		$limit = $size if ($limit > $size);
+		$to_rec = $from_rec + $self->{limit} - 1;
+		$to_rec = $size if ($to_rec > $size);
 	}
 
 	# store size for later
-	$self->{size} = ($limit - $offset) ? ($limit - $offset + 1) : 0;
+	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
 
-	$log->info("processing $self->{size} records in $code_page, convert to $self->{code_page}");
+	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{code_page}");
 
 	# read database
-	for (my $pos = $offset; $pos <= $limit; $pos++) {
+	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
 
 		$log->debug("position: $pos\n");
 
@@ -242,7 +279,7 @@
 		# create lookup
 		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
 
-		$self->progress_bar($pos,$limit);
+		$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
 
 	}
 
@@ -250,8 +287,8 @@
 	$self->{last_pcnt} = 0;
 
 	# store max mfn and return it.
-	$self->{max_pos} = $limit;
-	$log->debug("max_pos: $limit");
+	$self->{max_pos} = $to_rec;
+	$log->debug("max_pos: $to_rec");
 
 	return $size;
 }
@@ -288,7 +325,7 @@
 		return;
 	}
 
-	$self->progress_bar($mfn,$self->{max_pos});
+	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
 
 	my $rec;