--- trunk/PlusPlus.pm	2004/12/04 17:49:20	8
+++ trunk/PlusPlus.pm	2004/12/05 15:35:53	14
@@ -4,7 +4,7 @@
 use strict;
 use warnings;
 
-our $VERSION = '0.02';
+our $VERSION = '0.06';
 
 use Carp;
 use File::Temp qw/ tempdir /;
@@ -31,18 +31,20 @@
 
 =head1 METHODS
 
-=head2 open
+=head2 new
 
 Create new indexing object.
 
-  my $i = SWISH::PlusPlus->open(
+  my $i = SWISH::PlusPlus->new(
   	index_dir => '/path/to/index',
 	index => 'index++',
 	search => 'search++',
 	debug => 1,
+	meta_in_body => 1,
+	use_stopwords => 1,
   );
 
-Options to open are following:
+Options to new are following:
 
 =over 5
 
@@ -65,11 +67,21 @@
 This option (off by default) will produce a lot of debugging output on
 C<STDERR> prefixed by C<##>.
 
+=item C<meta_in_body>
+
+This option (off by default) enables to search content of meta fields
+without specifing them (like they are in body of document). This will
+somewhat increate index size.
+
+=item C<use_stopwords>
+
+Use built-in SWISH++ stop words. By default, they are disabled.
+
 =back
 
 =cut
 
-sub open {
+sub new {
         my $class = shift;
         my $self = {@_};
 	bless($self, $class);
@@ -78,15 +90,27 @@
 		croak "need $_" unless $self->{$_};
 	}
 
-	if (! -e $self->{'index_dir'}) {
-		mkdir $self->{'index_dir'} || confess "can't create index ",$self->{'index'},": $!";
+	my $index_dir = $self->{'index_dir'};
+
+	my $cwd;
+	chomp($cwd = `pwd`);
+	$self->{'cwd'} = $cwd || carp "can't get cwd!";
+	
+	if ($index_dir !~ m#^/#) {
+		$index_dir = "$cwd/$index_dir";
+		print STDERR "## full path to index_dir: $index_dir\n" if ($self->{'debug'});
+		$self->{'index_dir'} = $index_dir;
+	}
+
+	if (! -e $index_dir) {
+		mkdir $index_dir || confess "can't create index ",$self->{'index'},": $!";
 	}
 
 	# default executables
 	$self->{'index'} ||= 'index';
 	$self->{'search'} ||= 'search';
 
-	print STDERR "## open index_dir: ",$self->{'index_dir'}," index: ",$self->{'index'}, " search: ",$self->{'search'},"\n" if ($self->{'debug'});
+	print STDERR "## new index_dir: ",$index_dir," index: ",$self->{'index'}, " search: ",$self->{'search'},"\n" if ($self->{'debug'});
 
 	$self ? return $self : return undef;
 }
@@ -94,7 +118,7 @@
 
 =head2 check_bin
 
-Check if swish++ binaries specified in L<open> are available and verify
+Check if swish++ binaries specified in L<new> are available and verify
 version signature.
 
   if ($i->check_bin) {
@@ -122,6 +146,7 @@
 	confess $self->{'search'}," binary is not SWISH++" unless ($s =~ m/^SWISH\+\+/);
 
 	if ($i eq $s) {
+		$i =~ s/^SWISH\+\+\s+// || confess "can't strip SWISH++ from version";
 		$self->{'version'} = $i;
 		return 1;
 	} else  {
@@ -155,6 +180,32 @@
 	return 1;
 }
 
+=head2 add
+
+Add document with metadata to index.
+
+  $i->add(
+  	path => 'path/to/document',
+	title => 'this is result title',
+  	meta => {
+		description => 'this is description meta tag',
+		date => '2004-11-04',
+		author => 'Dobrica Pavlinusic',
+	}
+	body => 'this is text without meta data',
+  );
+
+This is thin wrapper round L<_create_doc>.
+
+=cut
+
+sub add {
+	my $self = shift;
+
+	$self->_create_doc(@_);
+
+	return 1;
+}
 =head2 search
 
 Search your index.
@@ -170,7 +221,7 @@
 
 	my $query = shift || return;
 
-	$self->_close_index;
+	$self->finish_update;
 
 	my @results;
 
@@ -180,7 +231,7 @@
 	my $open_cmd = $self->{'search'}." -i ".$self->{'index_dir'}.'/index "'.$query.'" |';
 	print STDERR "## search $open_cmd\n" if ($self->{'debug'});
 
-	CORE::open(SEARCH, $open_cmd) || confess "can't start $open_cmd: $!";
+	open(SEARCH, $open_cmd) || confess "can't start $open_cmd: $!";
 	while(<SEARCH>) {
 		next if (/^#/);
 		chomp;
@@ -201,35 +252,76 @@
 	return @results;
 }
 
+=head2 finish_update
+
+This method will close index.
+
+  $i->finish_update;
+
+It will be called on DESTROY when $i goes out of scope.
+
+=cut
+
+sub finish_update {
+	my $self = shift;
+
+	print STDERR "## finish_update\n" if ($self->{'debug'});
+
+	$self->_close_index;
+}
+
+sub DESTROY {
+	my $self = shift;
+	$self->finish_update;
+}
+
 =head1 PRIVATE METHODS
 
 Private methods implement internals for creating temporary file needed for
 swish++. You should have no need to call them directly, and they are here
 just to have documentation.
 
-=head2 _init_index
+=head2 _init_indexer
 
 Create temporary directory in which files for indexing will be created and
 start index process.
 
-  my $i->_init_index || die "can't start indexer";
+  my $i->_init_indexer || die "can't start indexer";
+
+It will also create empty file C<_stopwords_> to disable stop words.
 
 =cut
 
-sub _init_index {
+sub _init_indexer {
 	my $self = shift;
 
-	$self->{'tmp_dir'} = tempdir( CLEANUP => 1 ) || confess "can't create temporary directory: $!";
+	return if ($self->{'_index_fh'});
+
+	my $tmp_dir = tempdir( CLEANUP => 1 ) || confess "can't create temporary directory: $!";
+	$self->{'tmp_dir'} = $tmp_dir;
+
+	chdir $tmp_dir || confess "can't chdir to ".$tmp_dir.": $!";
 
-	my $opt = "-v 4";
+	print STDERR "## tmp_dir: $tmp_dir" if ($self->{'debug'});
+
+	my $opt = "-v " . ($self->{'debug'} || '0');
+
+	unless ($self->{'use_stopwrods'}) {
+		open(STOP, '>', "_stopwords_") || carp "can't create empty stopword file, skipping\n";
+		print STOP "  ";
+		close(STOP);
+		$opt .= " -s _stopwords_";
+	}
 
 	my $open_cmd = '| '.$self->{'index'}.' '.$opt.' -e "html:*" -i '.$self->{'index_dir'}.'/index -';
 
-	chdir $self->{'tmp_dir'} || confess "can't chdir to ".$self->{'tmp_dir'}.": $!";
+	print STDERR "## init_indexer: $open_cmd\n" if ($self->{'debug'});
+
+	open($self->{'_index_fh'}, $open_cmd) || confess "can't start index with $open_cmd: $!";
 
-	CORE::open($self->{'index_fh'}, $open_cmd) || confess "can't start index with $open_cmd: $!";
+	chdir $self->{'cwd'} || confess "can't chdir to ".$self->{'cwd'}.": $!";
 
-	return $self->{'index_fh'};
+	return $self->{'_index_fh'};
 }
 
 =head2 _create_doc
@@ -238,6 +330,7 @@
 
   $i->_create_doc(
   	path => 'path/to/store/in/index',
+	title => 'this is title in results',
 	body => 'data to story in body tag',
 	meta => {
 		'meta name' => 'data for this meta',
@@ -255,23 +348,37 @@
 	my $arg = {@_};
 
 	# open indexer if needed
-	$self->{'index_fh'} ||= $self->_init_index;
+	$self->_init_indexer;
 
 	my $path = $self->{'tmp_dir'} || confess "no tmp_dir?";
+	$path .= '/' . $arg->{'path'};
 
-	CORE::open(TMP, '>', $arg->{'path'}) || die "can't create temp file ".$arg->{'path'}.": $!";
+	print STDERR "## _create_doc: $path\n" if ($self->{'debug'});
 
-	print TMP '<html>';
+	open(TMP, '>', $path) || die "can't create temp file $path: $!";
+
+	print TMP '<html><head>';
+
+	$arg->{'body'} ||= '';
 
 	if ($arg->{'meta'}) {
-		confess "not yet implemented";
+		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'});
+		}
 	}
-	
-	print TMP '<body>' . ($arg->{'body'} || '') . '</body></html>';
+
+	if (defined($arg->{'title'})) {
+		print TMP '<title>' . ($arg->{'title'} || '') . '</title>';
+		$arg->{'body'} .= " ".$arg->{'title'} if ($self->{'meta_in_body'});
+	}
+
+	print TMP '</head><body>' . $arg->{'body'} . '</body></html>';
 	
 	close(TMP) || confess "can't close tmp file ".$arg->{'path'}.": $!";
 
-	print { $self->{'index_fh'} } $arg->{'path'}."\n";
+	print { $self->{'_index_fh'} } $arg->{'path'}."\n";
 }
 
 =head2 _close_index
@@ -287,12 +394,12 @@
 sub _close_index {
 	my $self = shift;
 
-	return unless ($self->{'index_fh'});
+	return unless ($self->{'_index_fh'});
 
 	print STDERR "## close index\n" if ($self->{'debug'});
 
-	close($self->{'index_fh'});
-	undef $self->{'index_fh'};
+	close($self->{'_index_fh'});
+	undef $self->{'_index_fh'};
 }
 
 1;
@@ -309,7 +416,7 @@
 Debian version of swish++ is often old (version 5 at moment of this writing
 while version 6 is available in source code), so this module by default
 uses executable names B<index> and B<search> for self-compiled version
-instead of one from Debian package. See L<open> how to specify Debian
+instead of one from Debian package. See L<new> how to specify Debian
 default binaries B<index++> and B<search++>.
 
 =head2 SWISH++
@@ -333,6 +440,14 @@
 pages. To see my very relaxed sample configuration take a look at C<swish++>
 directory included in distribution.
 
+=head2 SWISH++ config
+
+C<config.h> located in C<swish++> directory of this distribution is relaxed
+SWISH++ configuration that will index all words passed to it. This
+configuration is needed for B<date test> because default configuration
+doesn't recognize 2004-12-05 as date. Have in mind that your index size
+might explode.
+
 =head1 SEE ALSO
 
 C<swish++> web site L<http://homepage.mac.com/pauljlucas/software/swish/>