--- trunk/lib/WebPAC/Input.pm	2006/05/14 19:45:26	496
+++ trunk/lib/WebPAC/Input.pm	2006/07/09 15:22:39	593
@@ -3,6 +3,8 @@
 use warnings;
 use strict;
 
+use blib;
+
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Text::Iconv;
@@ -14,11 +16,11 @@
 
 =head1 VERSION
 
-Version 0.04
+Version 0.08
 
 =cut
 
-our $VERSION = '0.04';
+our $VERSION = '0.08';
 
 =head1 SYNOPSIS
 
@@ -42,7 +44,6 @@
     my $db = WebPAC::Input->new(
     	module => 'WebPAC::Input::ISIS',
 		config => $config,
-		lookup => $lookup_obj,
 		low_mem => 1,
     );
 
@@ -62,7 +63,7 @@
 
   my $db = new WebPAC::Input(
 	module => 'WebPAC::Input::MARC',
-	code_page => 'ISO-8859-2',
+	encoding => 'ISO-8859-2',
 	low_mem => 1,
 	recode => 'char pairs',
 	no_progress_bar => 1,
@@ -71,7 +72,7 @@
 C<module> is low-level file format module. See L<WebPAC::Input::Isis> and
 L<WebPAC::Input::MARC>.
 
-Optional parametar C<code_page> specify application code page (which will be
+Optional parametar C<encoding> specify application code page (which will be
 used internally). This should probably be your terminal encoding, and by
 default, it C<ISO-8859-2>.
 
@@ -94,6 +95,9 @@
 
 	my $log = $self->_get_logger;
 
+	$log->logconfess("code_page argument is not suppored any more. change it to encoding") if ($self->{lookup});
+	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_ref") if ($self->{lookup});
+
 	$log->logconfess("specify low-level file format module") unless ($self->{module});
 	my $module = $self->{module};
 	$module =~ s#::#/#g;
@@ -119,7 +123,7 @@
 		$self->{init}->($self, @_);
 	}
 
-	$self->{'code_page'} ||= 'ISO-8859-2';
+	$self->{'encoding'} ||= 'ISO-8859-2';
 
 	# running with low_mem flag? well, use DBM::Deep then.
 	if ($self->{'low_mem'}) {
@@ -160,6 +164,11 @@
 	limit => 500,
 	offset => 6000,
 	lookup => $lookup_obj,
+	stats => 1,
+	lookup_ref => sub {
+		my ($k,$v) = @_;
+		# store lookup $k => $v
+	},
  );
 
 By default, C<code_page> is assumed to be C<852>.
@@ -168,6 +177,11 @@
 
 C<limit> is optional parametar to read just C<limit> records from database
 
+C<stats> create optional report about usage of fields and subfields
+
+C<lookup_coderef> is closure to call when adding key => $value combinations to
+lookup.
+
 Returns size of database, regardless of C<offset> and C<limit>
 parametars, see also C<size>.
 
@@ -179,6 +193,10 @@
 
 	my $log = $self->_get_logger();
 
+	$log->logconfess("lookup argument is not suppored any more. rewrite call to lookup_coderef") if ($arg->{lookup});
+	$log->logconfess("lookup_coderef must be CODE, not ",ref($arg->{lookup_coderef}))
+		if ($arg->{lookup_coderef} && ref($arg->{lookup_coderef}) ne 'CODE');
+
 	$log->logcroak("need path") if (! $arg->{'path'});
 	my $code_page = $arg->{'code_page'} || '852';
 
@@ -189,7 +207,7 @@
 	}
 
 	# create Text::Iconv object
-	$self->{iconv} = Text::Iconv->new($code_page,$self->{'code_page'});
+	$self->{iconv} = Text::Iconv->new($code_page,$self->{'encoding'});	## FIXME remove!
 
 	my $filter_ref;
 
@@ -222,6 +240,7 @@
 	my ($db, $size) = $self->{open_db}->( $self, 
 		path => $arg->{path},
 		filter => $filter_ref,
+		%{ $arg },
 	);
 
 	unless (defined($db)) {
@@ -238,7 +257,7 @@
 	my $to_rec = $size;
 
 	if (my $s = $self->{offset}) {
-		$log->info("skipping to MFN $s");
+		$log->debug("skipping to MFN $s");
 		$from_rec = $s;
 	} else {
 		$self->{offset} = $from_rec;
@@ -253,7 +272,7 @@
 	# 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->{encoding}", $self->{stats} ? ' [stats]' : '');
 
 	# read database
 	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
@@ -277,7 +296,33 @@
 		}
 
 		# create lookup
-		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
+		$arg->{'lookup_coderef'}->( $rec ) if ($rec && $arg->{'lookup_coderef'});
+
+		# update counters for statistics
+		if ($self->{stats}) {
+
+			foreach my $fld (keys %{ $rec }) {
+				$self->{_stats}->{fld}->{ $fld }++;
+
+				$log->logdie("invalid record fild $fld, not ARRAY")
+					unless (ref($rec->{ $fld }) eq 'ARRAY');
+	
+				foreach my $row (@{ $rec->{$fld} }) {
+
+					if (ref($row) eq 'HASH') {
+
+						foreach my $sf (keys %{ $row }) {
+							$self->{_stats}->{sf}->{ $fld }->{ $sf }->{count}++;
+							$self->{_stats}->{sf}->{ $fld }->{ $sf }->{repeatable}++
+									if (ref($row->{$sf}) eq 'ARRAY');
+						}
+
+					} else {
+						$self->{_stats}->{repeatable}->{ $fld }++;
+					}
+				}
+			}
+		}
 
 		$self->progress_bar($pos,$to_rec) unless ($self->{no_progress_bar});
 
@@ -400,6 +445,56 @@
 	return $self->{pos} = (($pos - 1) || -1);
 }
 
+=head2 stats
+
+Dump statistics about field and subfield usage
+
+  print $input->stats;
+
+=cut
+
+sub stats {
+	my $self = shift;
+
+	my $log = $self->_get_logger();
+
+	my $s = $self->{_stats};
+	if (! $s) {
+		$log->warn("called stats, but there is no statistics collected");
+		return;
+	}
+
+	my $max_fld = 0;
+
+	my $out = join("\n",
+		map {
+			my $f = $_ || die "no field";
+			my $v = $s->{fld}->{$f} || die "no s->{fld}->{$f}";
+			$max_fld = $v if ($v > $max_fld);
+
+			my $o = sprintf("%4s %d ~", $f, $v);
+
+			if (defined($s->{sf}->{$f})) {
+				map {
+					$o .= sprintf(" %s:%d%s", $_, 
+						$s->{sf}->{$f}->{$_}->{count},
+						$s->{sf}->{$f}->{$_}->{repeatable} ? '*' : '',
+					);
+				} sort keys %{ $s->{sf}->{$f} };
+			}
+
+			if (my $v_r = $s->{repeatable}->{$f}) {
+				$o .= " ($v_r)" if ($v_r != $v);
+			}
+
+			$o;
+		} sort { $a cmp $b } keys %{ $s->{fld} }
+	);
+
+	$log->debug( sub { Dumper($s) } );
+
+	return $out;
+}
 
 =head1 MEMORY USAGE