--- trunk/lib/WebPAC/Input.pm	2005/12/31 16:50:11	339
+++ trunk/lib/WebPAC/Input.pm	2006/05/15 09:59:05	506
@@ -14,11 +14,11 @@
 
 =head1 VERSION
 
-Version 0.03
+Version 0.05
 
 =cut
 
-our $VERSION = '0.03';
+our $VERSION = '0.05';
 
 =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.
 
@@ -152,6 +160,7 @@
 	limit => 500,
 	offset => 6000,
 	lookup => $lookup_obj,
+	stats => 1,
  );
 
 By default, C<code_page> is assumed to be C<852>.
@@ -160,6 +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>.
 
@@ -183,11 +194,40 @@
 	# 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 ($db) {
+	unless (defined($db)) {
 		$log->logwarn("can't open database $arg->{path}, skipping...");
 		return;
 	}
@@ -216,7 +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++) {
@@ -242,7 +282,26 @@
 		# create lookup
 		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
 
-		$self->progress_bar($pos,$to_rec);
+		# update counters for statistics
+		if ($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});
 
 	}
 
@@ -288,7 +347,7 @@
 		return;
 	}
 
-	$self->progress_bar($mfn,$self->{max_pos});
+	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
 
 	my $rec;
 
@@ -363,6 +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