first pass at doing xapian indexing

Still some TODOs to fill in.

3 files changed, 80 insertions, 22 deletions

diff --git a/IkiWiki/Plugin/search.pm b/IkiWiki/Plugin/search.pm
index e705d018a..a28d58a1d 100644
--- a/IkiWiki/Plugin/search.pm
+++ b/IkiWiki/Plugin/search.pm
@@ -9,8 +9,11 @@ use IkiWiki 2.00;
 sub import { #{{{
 	hook(type => "checkconfig", id => "search", call => \&checkconfig);
 	hook(type => "pagetemplate", id => "search", call => \&pagetemplate);
+	# run last so other needsbuild hooks can modify the list
+	hook(type => "needsbuild", id => "search", call => \&needsbuild,
+		last => 1);
+	hook(type => "filter", id => "search", call => \&filter);
 	hook(type => "delete", id => "search", call => \&delete);
-	hook(type => "change", id => "search", call => \&change);
 	hook(type => "cgi", id => "search", call => \&cgi);
 } # }}}
 
@@ -53,12 +56,53 @@ sub pagetemplate (@) { #{{{
 	}
 } #}}}
 
-sub delete (@) { #{{{
-	debug(gettext("cleaning xapian search index"));
+my %toindex;
+sub needsbuild ($) { #{{{
+	%toindex = map { $_ => 1 } @{shift()};
 } #}}}
 
-sub change (@) { #{{{
-	debug(gettext("updating xapian search index"));
+sub filter (@) { #{{{
+	my %params=@_;
+	
+	if ($params{page} eq $params{destpage} && $toindex{$params{page}}) {
+		# index page
+		my $db=xapiandb();
+		my $doc=Search::Xapian::Document->new();
+		my $title=$params{page};
+		if (exists $pagestate{$params{page}}{meta} &&
+		    exists $pagestate{$params{page}}{meta}{title}) {
+			$title=$pagestate{$params{page}}{meta}{title};
+		}
+
+		# data used by omega
+		$doc->set_data(
+			"url=".urlto($params{page}, "")."\n".
+			"sample=\n". # TODO
+			"caption=$title\n".
+			"modtime=$IkiWiki::pagemtime{$params{page}}\n".
+			"size=".length($params{content})."\n"
+		);
+
+		my $tg = Search::Xapian::TermGenerator->new();
+		$tg->set_stemmer(new Search::Xapian::Stem("english"));
+		$tg->set_document($doc);
+		$tg->index_text($params{page}, 2);
+		$tg->index_text($title, 2);
+		$tg->index_text($params{content}); # TODO html strip; preprocessor too
+
+		my $pageterm=pageterm($params{page});
+		$doc->add_term($pageterm);
+		$db->replace_document_by_term($pageterm, $doc);
+	}
+
+	return $params{content};
+} #}}}
+
+sub delete (@) { #{{{
+	my $db=xapiandb();
+	foreach my $page (@_) {
+		$db->delete_document_by_term(pageterm($page));
+	}
 } #}}}
 
 sub cgi ($) { #{{{
@@ -73,4 +117,26 @@ sub cgi ($) { #{{{
 	}
 } #}}}
 
+sub pageterm ($) { #{{{
+	my $page=shift;
+
+	# TODO: check if > 255 char page names overflow term
+	# length; use sha1 if so?
+	return "P".$page;
+} #}}}
+
+my $db;
+sub xapiandb () { #{{{
+	if (! defined $db) {
+		eval q{
+			use Search::Xapian;
+			use Search::Xapian::WritableDatabase;
+		};
+		error($@) if $@;
+		$db=Search::Xapian::WritableDatabase->new($config{wikistatedir}."/xapian/default",
+			Search::Xapian::DB_CREATE_OR_OPEN());
+	}
+	return $db;
+} #}}}
+
 1
diff --git a/doc/bugs/Search_results_should_point_to_dir__44___not_index.html__44___when_use__95__dirs_is_enabled.mdwn b/doc/bugs/Search_results_should_point_to_dir__44___not_index.html__44___when_use__95__dirs_is_enabled.mdwn
index 45a8f0abd..5f36e21df 100644
--- a/doc/bugs/Search_results_should_point_to_dir__44___not_index.html__44___when_use__95__dirs_is_enabled.mdwn
+++ b/doc/bugs/Search_results_should_point_to_dir__44___not_index.html__44___when_use__95__dirs_is_enabled.mdwn
@@ -11,3 +11,5 @@ point to `foo/bar/` instead.
 > This bug affects the [[plugins/amazon_s3]] plugin -- when using that
 > plugin plus the search plugin, you need to enable `amazon_s3_dupindex`.
 > So this definitly should be fixed. --[[Joey]]
+
+> [[done]], the new xapian search uses nice urls
diff --git a/doc/todo/different_search_engine.mdwn b/doc/todo/different_search_engine.mdwn
index 3737fb140..788473ec5 100644
--- a/doc/todo/different_search_engine.mdwn
+++ b/doc/todo/different_search_engine.mdwn
@@ -33,35 +33,25 @@ Possibilities:
   written on the page would be indexed. Not text generated by directives,
   pulled in by inlining, etc. There's something to be said for that. And
   something to be said against it. It would also get markdown formatted
-  content, mostly, though it would still need to strip html.
+  content, mostly, though it would still need to strip html, and also
+  probably strip preprocessor directives too.
 * `sanitize` - Would get the htmlized content, so would need to strip html.
-  Preprocessor directive output would be indexed.
+  Preprocessor directive output would be indexed. Doesn't get a destpage
+  parameter, making optimisation hard.
 * `format` - Would get the entire html page, including the page template.
   Probably not a good choice as indexing the same template for each page
   is unnecessary.
 
-Currently, a filter hook seems the best option.
-
 The hook would remove any html from the content, and index it.
-It would need to add the same document data that omindex would, as well as
-adding the same special terms (see
-http://xapian.org/docs/omega/overview.html "Boolean terms").
-
-(Note that the U term is a bit tricky because I'll have to replicate
-ominxes's hash_string() to hash terms > 240 chars.)
+It would need to add the same document data that omindex would.
 
 The indexer (and deleter) will need a way to figure out the ids in xapian
 of the documents to delete. One way is storing the id of each page in the
 ikiwiki index.
 
 The other way would be adding a special term to the xapian db that can be
-used with replace_document_by_term/delete_document_by_term. omindex uses
-U<url> as a term, and I guess I could just use that, and then map page
-names to urls when deleting a page  ... only real problem being the
-hashing; a collision would be bad.
-
-At the moment, storing xapian ids in the ikiwiki index file seems like the
-best approach.
+used with replace_document_by_term/delete_document_by_term. 
+Hmm, let's use a term named "P<pagename>".
 
 The hook should try to avoid re-indexing pages that have not changed since
 they were last indexed. One problem is that, if a page with an inline is