--- trunk/PlusPlus.pm	2004/12/05 22:24:09	21
+++ trunk/PlusPlus.pm	2004/12/07 16:05:43	22
@@ -4,12 +4,13 @@
 use strict;
 use warnings;
 
-our $VERSION = '0.10';
+our $VERSION = '0.20';
 
 use Carp;
 use File::Temp qw/ tempdir /;
 use BerkeleyDB;
-#use YAML;
+use Storable qw(store retrieve freeze thaw);
+use YAML;
 
 =head1 NAME
 
@@ -18,7 +19,13 @@
 =head1 SYNOPSIS
 
   use SWISH::PlusPlus;
-  blah blah blah
+
+  my $i = new SWISH::PlusPlus(
+  	index_dir => '/tmp/foo',
+  );
+  $i->add( 42 => 'meaning of life' );
+
+  print $i->search("meaning");	# returns 42
 
 =head1 DESCRIPTION
 
@@ -164,7 +171,10 @@
 Quick way to add simple data to index.
 
   $i->index_document($path, $data);
-  $i->index_document( 42 => 'meaning of life' );
+  $i->index_document(
+  	42 => 'meaning of life',
+	1984 => 'Oh!',
+  );
 
 C<$path> value is really path, so you don't want to use directory
 separators (slashes, /) in it probably.
@@ -208,11 +218,40 @@
 sub add {
 	my $self = shift;
 
-	$self->_create_doc(@_);
+	return $self->_create_doc(@_);
+}
 
-	return 1;
+
+=head2 delete
+
+Delete document from index.
+
+  $i->delete("document/path");
+
+If deletion is succesfull returns revision of deleted document, otherwise
+undef.
+
+=cut
+
+sub delete {
+	my $self = shift;
+
+	my $path = shift || carp "empty path?";
+
+	print STDERR "## delete: $path\n" if ($self->{'debug'});
+
+	my $rev = $self->{'meta_db'}->{"R$path"};
+	if ($rev) {
+		$self->{'_deleted'}->{$path} = $rev;
+		$self->{'_deleted_counter'}++;
+		print STDERR "## deleted revision $rev, counter: ",$self->{'_deleted_counter'}++,"\n" if ($self->{'debug'});
+		return $rev;
+	}
+
+	return undef;
 }
 
+
 =head2 search
 
 Search your index using any valid SWISH++ query.
@@ -249,20 +288,31 @@
 		' |';
 	print STDERR "## search: $open_cmd\n" if ($self->{'debug'});
 
+	my %r;
+
 	open(SEARCH, $open_cmd) || confess "can't start $open_cmd: $!";
 	my $l;
 	while($l = <SEARCH>) {
 		next if ($l =~ /^#/);
 		chomp($l);
 		print STDERR "## $l\n" if ($self->{'debug'});
-		my ($rank,$path,$size,$title) = split(/ /,$l,4);
+		my ($rank,$path,$size,$rev,$title) = split(/ /,$l,5);
 		$path =~ s#^\./##; # strip from path
+
+		# get current revision
+		$r{$path} = $self->{'meta_db'}->{"R$path"};
+
+		# skip if old revision
+		next if ($r{$path} > $rev);
+
+		print STDERR "## current revision $rev\n" if ($self->{'debug'});
+
 		push @results, {
 			rank => $rank,
 			path => $path,
 			size => $size,
 			title => $title,
-		}
+		} unless ($self->{'_deleted'}->{$path} && $self->{'_deleted'}->{$path} <= $rev);
 	}
 
 	close(SEARCH) || confess "can't close search";
@@ -276,23 +326,37 @@
 
 Return stored meta property from result or result path.
 
-  print $i->property('path', 'title');
-  print $i->property($res->{'path'}, 'title');
+  print $i->property('path', 'meta name');
+  print $i->property($res->{'path'}, 'meta name');
+  print $i->property('path');
+  print $i->property($res->{'path'});
+
+Returns one meta property (if meta name is specified) or whole hash with
+all meta properties.
 
 =cut
 
 sub property {
 	my $self = shift;
 
-	my ($path,$meta) = @_;
+	my $path = shift || return;
+	my $meta = shift;
 
 	if ($path =~ m/^HASH/) {
 		$path = $path->{'path'} || confess "can't find path in input data";
 	}
 
-	my $val = $self->{'meta_db'}->{"$path-$meta"};
+	my $val = $self->{'meta_db'}->{"M$path"};
+
+	# FIXME should we die here like swish-e does?
+	return unless ($val);
+
+	$val = thaw($val);
+
+	print STDERR "## property $path $meta: ",(Dump($val) || 'undef'),"\n" if ($self->{'debug'});
+
+	return $val->{$meta} if ($meta);
 
-	print STDERR "## property $path-$meta: ",($val || 'undef'),"\n" if ($self->{'debug'});
 	return $val;
 }
 
@@ -349,10 +413,21 @@
 
 	chdir $tmp_dir || confess "can't chdir to ".$tmp_dir.": $!";
 
-	print STDERR "## tmp_dir: $tmp_dir" if ($self->{'debug'});
+	print STDERR "## tmp_dir: $tmp_dir\n" if ($self->{'debug'});
 
 	my $opt = "-v " . ($self->{'debug'} || '0');
 
+	my $index_dir = $self->{'index_dir'} || confess "no index_dir?";
+	my $index_file = $index_dir . '/index';
+
+	if (-e $index_file && ! -z $index_file) {
+		$opt .= ' -I ';
+		$self->{'_incremental'} = 1;
+		print STDERR "## using incremental indexing for $index_file\n" if ($self->{'debug'});
+	} else {
+		$self->{'_incremental'} = 0;
+	}
+
 	unless ($self->{'use_stopwrods'}) {
 		open(STOP, '>', "_stopwords_") || carp "can't create empty stopword file, skipping\n";
 		print STOP "  ";
@@ -360,9 +435,7 @@
 		$opt .= " -s _stopwords_";
 	}
 
-	my $index_dir = $self->{'index_dir'} || confess "no index_dir?";
-
-	my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$index_dir.'/index -';
+	my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$index_file.' -';
 
 	print STDERR "## init_indexer: $open_cmd\n" if ($self->{'debug'});
 
@@ -389,8 +462,6 @@
 	}
   );
 
-To delete document, just omit body and meta data.
-
 =cut
 
 sub _create_doc {
@@ -405,35 +476,53 @@
 	my $id = $arg->{'path'} || confess "no path?";
 	$path .= "/$id";
 
-	print STDERR "## _create_doc: $path\n" if ($self->{'debug'});
+	my $rev = $self->{'rev'}++;
+
+	print STDERR "## _create_doc: $path [$rev]\n" if ($self->{'debug'});
 
 	open(TMP, '>', $path) || die "can't create temp file $path: $!";
 
 	print TMP '<html><head>';
 
-	$arg->{'body'} ||= '';
+	my $body = $arg->{'body'};
+
+	if (defined($body)) {
+		$self->{'meta_db'}->{"B$id"} = $body;
+	} else {
+		$body = '';
+	}
+
+	my $title = $arg->{'title'};
 
 	if ($arg->{'meta'}) {
 		foreach my $name (keys %{$arg->{'meta'}}) {
 			my $content = $arg->{'meta'}->{$name};
 			print TMP qq{<meta name="$name" content="$content">};
-			$arg->{'body'} .= " $content" if ($self->{'meta_in_body'});
-			$self->{'meta_db'}->{"$id-$name"} = $content;
+			$body .= " $content" if ($self->{'meta_in_body'});
 		}
+		$arg->{'meta'}->{'title'} = $title;
+		$self->{'meta_db'}->{"M$id"} = freeze($arg->{'meta'});
 	}
 
-	my $title = $arg->{'title'};
 	if (defined($title)) {
-		print TMP "<title>$title</title>";
-		$arg->{'body'} .= " $title" if ($self->{'meta_in_body'});
-		$self->{'meta_db'}->{"$id-title"} = $title;
+		$title = "$rev $title";
+		$body .= " $title" if ($self->{'meta_in_body'});
+	} else {
+		$title = "$rev $id";
 	}
 
-	print TMP '</head><body>' . $arg->{'body'} . '</body></html>';
+	# dump html
+	print TMP "<title>$title</title></head><body>$body</body></html>";
 	
 	close(TMP) || confess "can't close tmp file ".$arg->{'path'}.": $!";
 
-	print { $self->{'_index_fh'} } "$id\n";
+	print { $self->{'_index_fh'} } "$id\n" || confess "can't pass document $id to indexer: $!";
+	
+	$self->{'meta_db'}->{"R$id"} = $rev;
+
+	# FIXME this is probably not the right place to update global
+	# maximum revision, but it keeps database in sane state
+	$self->{'meta_db'}->{"Crev"} = $rev;
 }
 
 =head2 _close_index
@@ -449,6 +538,8 @@
 sub _close_index {
 	my $self = shift;
 
+	$self->_store_deleted;
+
 	return unless ($self->{'_index_fh'});
 
 	print STDERR "## close index\n" if ($self->{'debug'});
@@ -456,6 +547,11 @@
 	close($self->{'_index_fh'}) || confess "can't close index: $!";
 	undef $self->{'_index_fh'};
 
+	if ($self->{'_incremental'}) {
+		print STDERR "## move new index over old\n" if ($self->{'debug'});
+		rename $self->{'index_dir'}.'/index.new',$self->{'index_dir'}.'/index' || die "can't move new index over old one: $!";
+	}
+
 	return 1;
 }
 
@@ -489,6 +585,18 @@
 		-Flags    => $flags
 	or confess "cannot open $file: $! $BerkeleyDB::Error\n" ;
 
+	$self->{'rev'} = $self->{'meta_db'}->{'Crev'} || 0;
+
+	my $delref = $self->{'meta_db'}->{'Cdeleted'};
+	if ($delref) {
+		$self->{'_deleted'} = thaw($delref);
+
+		print "## deleted ",keys %{$self->{'_deleted'}}," records\n" if ($self->{'debug'});
+	} else {
+		$self->{'_deleted'} = {};
+	}
+
+	$self->{'_deleted_counter'} = 0;
 	return 1;
 }
 
@@ -513,6 +621,33 @@
 	return 1;
 }
 
+
+=head2 _store_deleted
+
+Save hash of deleted files using L<Storable>.
+
+  $i->_store_deleted;
+
+=cut
+
+sub _store_deleted {
+	my $self = shift;
+
+	return if (! $self->{'_deleted_counter'});
+
+	print STDERR "## save deleted ",Dump($self->{'_deleted'}) if ($self->{'debug'});
+
+	my $d = freeze($self->{'_deleted'});
+
+	$self->_tie_meta_db(DB_CREATE);
+
+	$self->{'meta_db'}->{'Cdeleted'} = $d ||
+		carp "can't store deleted: $!";
+
+	# reset counter
+	$self->{'_deleted_counter'} = 0;
+}
+
 1;
 __END__