--- trunk/PlusPlus.pm	2004/12/03 19:35:02	4
+++ trunk/PlusPlus.pm	2004/12/04 17:49:20	8
@@ -8,6 +8,7 @@
 
 use Carp;
 use File::Temp qw/ tempdir /;
+#use YAML;
 
 =head1 NAME
 
@@ -38,6 +39,7 @@
   	index_dir => '/path/to/index',
 	index => 'index++',
 	search => 'search++',
+	debug => 1,
   );
 
 Options to open are following:
@@ -58,6 +60,11 @@
 
 Full or partial path to SWISH++ search executable. By default, it's B<search>.
 
+=item C<debug>
+
+This option (off by default) will produce a lot of debugging output on
+C<STDERR> prefixed by C<##>.
+
 =back
 
 =cut
@@ -79,6 +86,8 @@
 	$self->{'index'} ||= 'index';
 	$self->{'search'} ||= 'search';
 
+	print STDERR "## open index_dir: ",$self->{'index_dir'}," index: ",$self->{'index'}, " search: ",$self->{'search'},"\n" if ($self->{'debug'});
+
 	$self ? return $self : return undef;
 }
 
@@ -146,6 +155,52 @@
 	return 1;
 }
 
+=head2 search
+
+Search your index.
+
+  my @results = $i->search("swhish query");
+
+Returns array with result IDs.
+
+=cut
+
+sub search {
+	my $self = shift;
+
+	my $query = shift || return;
+
+	$self->_close_index;
+
+	my @results;
+
+	# escape double quotes in query for shell
+	$query =~ s/"/\\"/g;
+
+	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: $!";
+	while(<SEARCH>) {
+		next if (/^#/);
+		chomp;
+		print STDERR "## $_\n" if ($self->{'debug'});
+		my ($rank,$path,$size,$title) = split(/ /,$_,4);
+		push @results, {
+			rank => $rank,
+			path => $path,
+			size => $size,
+			title => $title,
+		}
+	}
+
+	close(SEARCH) || confess "can't close search";
+
+	#print STDERR "## results: ",Dump(@results),"\n" if ($self->{'debug'});
+
+	return @results;
+}
+
 =head1 PRIVATE METHODS
 
 Private methods implement internals for creating temporary file needed for
@@ -168,7 +223,7 @@
 
 	my $opt = "-v 4";
 
-	my $open_cmd = '| index '.$opt.' -e "html:*" -i '.$self->{'index_dir'}.'/index -';
+	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'}.": $!";
 
@@ -190,6 +245,8 @@
 	}
   );
 
+To delete document, just omit body and meta data.
+
 =cut
 
 sub _create_doc {
@@ -217,6 +274,27 @@
 	print { $self->{'index_fh'} } $arg->{'path'}."\n";
 }
 
+=head2 _close_index
+
+Close index after indexing.
+
+  $i->_close_index;
+
+You have to close index before searching.
+
+=cut
+
+sub _close_index {
+	my $self = shift;
+
+	return unless ($self->{'index_fh'});
+
+	print STDERR "## close index\n" if ($self->{'debug'});
+
+	close($self->{'index_fh'});
+	undef $self->{'index_fh'};
+}
+
 1;
 __END__
 
@@ -234,20 +312,34 @@
 instead of one from Debian package. See L<open> how to specify Debian
 default binaries B<index++> and B<search++>.
 
-=head1 SEE ALSO
+=head2 SWISH++
 
-Mention other useful documentation such as the documentation of
-related modules or operating system documentation (such as man pages
-in UNIX), or any relevant external documentation such as RFCs or
-standards.
+Aside from very good rewrite in C++, SWISH++ is fatster because it has
+claver heuristics about which data in input files are words to index and
+which are not. It's based on English language and might be best choice if
+you plan to install large amount of long text documents.
+
+However, if you plan to index all data from structured storage (e.g. RDBMS)
+you might want B<all> words from data to end up in index as opposed to just
+those which look like English words. This is especially important if you
+don't plan to index English texts with this module.
+
+With distribution build versions of SWISH++ you might have problems with
+disepearing words. To overcome this problem, you will have to compile and
+configure SWISH++ yourself (because language characteristics are
+compilation-time option).
+
+Compilation of SWISH++ is easy process well described on project's web
+pages. To see my very relaxed sample configuration take a look at C<swish++>
+directory included in distribution.
 
-If you have a mailing list set up for your module, mention it here.
+=head1 SEE ALSO
 
-If you have a web site set up for your module, mention it here.
+C<swish++> web site L<http://homepage.mac.com/pauljlucas/software/swish/>
 
 =head1 AUTHOR
 
-Dobrica Pavlinusic, E<lt>dpavlin@E<gt>
+Dobrica Pavlinusic, E<lt>dpavlin@rot13.orgE<gt>
 
 =head1 COPYRIGHT AND LICENSE