--- trunk/lib/WebPAC/Input.pm	2005/12/20 00:03:04	307
+++ trunk/lib/WebPAC/Input.pm	2006/05/16 13:08:31	513
@@ -3,9 +3,12 @@
 use warnings;
 use strict;
 
+use blib;
+
 use WebPAC::Common;
 use base qw/WebPAC::Common/;
 use Text::Iconv;
+use Data::Dumper;
 
 =head1 NAME
 
@@ -13,11 +16,11 @@
 
 =head1 VERSION
 
-Version 0.03
+Version 0.05
 
 =cut
 
-our $VERSION = '0.03';
+our $VERSION = '0.05';
 
 =head1 SYNOPSIS
 
@@ -46,9 +49,10 @@
     );
 
     $db->open('/path/to/database');
-    print "database size: ",$db->size,"\n";
-    while (my $rec = $db->fetch) {
-    }
+	print "database size: ",$db->size,"\n";
+	while (my $rec = $db->fetch) {
+		# do something with $rec
+	}
 
 
 
@@ -62,6 +66,8 @@
 	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
@@ -73,6 +79,11 @@
 
 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.
 
@@ -151,6 +162,7 @@
 	limit => 500,
 	offset => 6000,
 	lookup => $lookup_obj,
+	stats => 1,
  );
 
 By default, C<code_page> is assumed to be C<852>.
@@ -159,6 +171,8 @@
 
 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>.
 
@@ -182,11 +196,40 @@
 	# 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;
 	}
@@ -196,34 +239,36 @@
 		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;
+		$log->debug("skipping to MFN $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}", $self->{stats} ? ' [stats]' : '');
 
 	# read database
-	for (my $pos = $offset; $pos <= $limit; $pos++) {
+	for (my $pos = $from_rec; $pos <= $to_rec; $pos++) {
 
 		$log->debug("position: $pos\n");
 
 		my $rec = $self->{fetch_rec}->($self, $db, $pos );
 
+		$log->debug(sub { Dumper($rec) });
+
 		if (! $rec) {
 			$log->warn("record $pos empty? skipping...");
 			next;
@@ -239,7 +284,26 @@
 		# create lookup
 		$self->{'lookup'}->add( $rec ) if ($rec && $self->{'lookup'});
 
-		$self->progress_bar($pos,$limit);
+		# update counters for statistics
+		if ($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});
 
 	}
 
@@ -247,8 +311,8 @@
 	$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;
 }
@@ -285,7 +349,7 @@
 		return;
 	}
 
-	$self->progress_bar($mfn,$self->{max_pos});
+	$self->progress_bar($mfn,$self->{max_pos}) unless ($self->{no_progress_bar});
 
 	my $rec;
 
@@ -360,6 +424,53 @@
 	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("%4d %d ~", $f, $v);
+
+			if (defined($s->{sf}->{$f})) {
+				map {
+					$o .= sprintf(" %s:%d", $_, $s->{sf}->{$f}->{$_});
+				} sort keys %{ $s->{sf}->{$f} };
+			}
+
+			if (my $v_r = $s->{repeatable}->{$f}) {
+				$o .= " ($v_r)" if ($v_r != $v);
+			}
+
+			$o;
+		} sort { $a <=> $b } keys %{ $s->{fld} }
+	);
+
+	$log->debug( sub { Dumper($s) } );
+
+	return $out;
+}
 
 =head1 MEMORY USAGE