--- trunk/lib/WebPAC/Input.pm	2006/05/14 12:34:50	487
+++ trunk/lib/WebPAC/Input.pm	2006/05/15 09:59:05	506
@@ -14,11 +14,11 @@
 
 =head1 VERSION
 
-Version 0.04
+Version 0.05
 
 =cut
 
-our $VERSION = '0.04';
+our $VERSION = '0.05';
 
 =head1 SYNOPSIS
 
@@ -160,6 +160,7 @@
 	limit => 500,
 	offset => 6000,
 	lookup => $lookup_obj,
+	stats => 1,
  );
 
 By default, C<code_page> is assumed to be C<852>.
@@ -168,6 +169,8 @@
 
 C<limit> is optional parametar to read just C<limit> records from database
 
+C<stats> create optional report about usage of fields and subfields
+
 Returns size of database, regardless of C<offset> and C<limit>
 parametars, see also C<size>.
 
@@ -224,7 +227,7 @@
 		filter => $filter_ref,
 	);
 
-	unless ($db) {
+	unless (defined($db)) {
 		$log->logwarn("can't open database $arg->{path}, skipping...");
 		return;
 	}
@@ -253,7 +256,7 @@
 	# store size for later
 	$self->{size} = ($to_rec - $from_rec) ? ($to_rec - $from_rec + 1) : 0;
 
-	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{code_page}");
+	$log->info("processing $self->{size}/$size records [$from_rec-$to_rec] convert $code_page -> $self->{code_page}", $self->{stats} ? ' [stats]' : '');
 
 	# read database
 	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
@@ -279,6 +282,25 @@
 		# create lookup
 		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
 
+		# update counters for statistics
+		if ($self->{stats}) {
+			map {
+				my $fld = $_;
+				$self->{_stats}->{fld}->{ $fld }++;
+				if (ref($rec->{ $fld }) eq 'ARRAY') {
+					map {
+						if (ref($_) eq 'HASH') {
+							map {
+								$self->{_stats}->{sf}->{ $fld }->{ $_ }++;
+							} keys %{ $_ };
+						} else {
+							$self->{_stats}->{repeatable}->{ $fld }++;
+						}
+					} @{ $rec->{$fld} };
+				}
+			} keys %{ $rec };
+		}
+
 		$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
 
 	}
@@ -400,6 +422,18 @@
 	return $self->{pos} = (($pos - 1) || -1);
 }
 
+=head2 stats
+
+Dump statistics about field and subfield usage
+
+  print Dumper( $input->stats );
+
+=cut
+
+sub stats {
+	my $self = shift;
+	return $self->{_stats};
+}
 
 =head1 MEMORY USAGE