From 15f9bb7ce5034ca9a6c813a0bf7ddb55d73c67fc Mon Sep 17 00:00:00 2001 From: joey Date: Tue, 20 Feb 2007 19:22:26 +0000 Subject: [PATCH 1/1] web commit by http://id.inelegant.org/: Response. --- doc/todo/different_search_engine.mdwn | 251 ++++++++++++++++++++++++++ 1 file changed, 251 insertions(+) diff --git a/doc/todo/different_search_engine.mdwn b/doc/todo/different_search_engine.mdwn index 24f85f80f..592c159b3 100644 --- a/doc/todo/different_search_engine.mdwn +++ b/doc/todo/different_search_engine.mdwn @@ -5,3 +5,254 @@ time. So some other engine should be found and used instead. Enrico had one that he was using for debtags stuff that looked pretty good. + +>> I've done a bit of prototyping on this. The current hip search library is [Lucene](http://lucene.apache.org/java/docs/). There's a Perl port called [Plucene](http://search.cpan.org/~tmtm/Plucene-1.25/). Given that it's already packaged, as `libplucene-perl`, I assumed it would be a good starting point. I've written a **very rough** patch against `IkiWiki/Plugin/search.pm` to handle the indexing side (there's no facility to view the results yet, although I have a command-line interface working). That's below, and should apply to SVN trunk. + +>> Of course, there are problems. ;-) + +>> * Plucene throws up a warning when running under Taint mode. There's a patch on the mailing list, but I haven't tried applying it yet. So for now you'll have to build IkiWiki with `NOTAINT=1 make install`. +>> * If I kill `ikiwiki` while it's indexing, I can screw up Plucene's locks. I suspect that this will be an easy fix. + +>> There is a [C++ port of Lucene](http://sourceforge.net/projects/clucene/) which is packaged as `libclucene0`. The Perl interface to this is called [Lucene](http://search.cpan.org/~tbusch/Lucene-0.09/lib/Lucene.pm). This is supposed to be significantly faster, and presumably won't have the taint bug. The API is virtually the same, so it will be easy to switch over. I'd use this now, were it not for the lack of package. (I assume you won't want to make core functionality depend on installing a module from CPAN). I've never built a Debian package before, so I can either learn then try building this, or somebody else could do the honours. ;-) + +>> If this seems a sensible approach, I'll write the CGI interface, and clean up the plugin. -- Ben + +
+Index: IkiWiki/Plugin/search.pm
+===================================================================
+--- IkiWiki/Plugin/search.pm    (revision 2755)
++++ IkiWiki/Plugin/search.pm    (working copy)
+@@ -1,33 +1,55 @@
+ #!/usr/bin/perl
+-# hyperestraier search engine plugin
+ package IkiWiki::Plugin::search;
+ 
+ use warnings;
+ use strict;
+ use IkiWiki;
+ 
++use Plucene::Analysis::SimpleAnalyzer;
++use Plucene::Document;
++use Plucene::Document::Field;
++use Plucene::Index::Reader;
++use Plucene::Index::Writer;
++use Plucene::QueryParser;
++use Plucene::Search::HitCollector;
++use Plucene::Search::IndexSearcher;
++
++#TODO: Run the Plucene optimiser after a rebuild
++#TODO: CGI query interface
++
++my $PLUCENE_DIR;
++# $config{wikistatedir} may not be defined at this point, so we delay setting $PLUCENE_DIR
++# until a subroutine actually needs it.
++sub init () {
++  error("Plucene: Statedir <$config{wikistatedir}> does not exist!") 
++    unless -e $config{wikistatedir};
++  $PLUCENE_DIR = $config{wikistatedir}.'/plucene';  
++}
++
+ sub import { #{{{
+-       hook(type => "getopt", id => "hyperestraier",
+-               call => \&getopt);
+-       hook(type => "checkconfig", id => "hyperestraier",
++       hook(type => "checkconfig", id => "plucene",
+                call => \&checkconfig);
+-       hook(type => "pagetemplate", id => "hyperestraier",
+-               call => \&pagetemplate);
+-       hook(type => "delete", id => "hyperestraier",
++       hook(type => "delete", id => "plucene",
+                call => \&delete);
+-       hook(type => "change", id => "hyperestraier",
++       hook(type => "change", id => "plucene",
+                call => \&change);
+-       hook(type => "cgi", id => "hyperestraier",
+-               call => \&cgi);
+ } # }}}
+ 
+-sub getopt () { #{{{
+-        eval q{use Getopt::Long};
+-       error($@) if $@;
+-        Getopt::Long::Configure('pass_through');
+-        GetOptions("estseek=s" => \$config{estseek});
+-} #}}}
+ 
++sub writer {
++  init();
++  return Plucene::Index::Writer->new(
++      $PLUCENE_DIR, Plucene::Analysis::SimpleAnalyzer->new(), 
++      (-e "$PLUCENE_DIR/segments" ? 0 : 1));
++}
++
++#TODO: Better name for this function.
++sub src2rendered_abs (@) {
++  return map { Encode::encode_utf8($config{destdir}."/$_") } 
++    map { @{$renderedfiles{pagename($_)}} } 
++    grep { defined pagetype($_) } @_;
++}
++
+ sub checkconfig () { #{{{
+        foreach my $required (qw(url cgiurl)) {
+                if (! length $config{$required}) {
+@@ -36,112 +58,55 @@
+        }
+ } #}}}
+ 
+-my $form;
+-sub pagetemplate (@) { #{{{
+-       my %params=@_;
+-       my $page=$params{page};
+-       my $template=$params{template};
++#my $form;
++#sub pagetemplate (@) { #{{{
++#      my %params=@_;
++#      my $page=$params{page};
++#      my $template=$params{template};
++#
++#      # Add search box to page header.
++#      if ($template->query(name => "searchform")) {
++#              if (! defined $form) {
++#                      my $searchform = template("searchform.tmpl", blind_cache => 1);
++#                      $searchform->param(searchaction => $config{cgiurl});
++#                      $form=$searchform->output;
++#              }
++#
++#              $template->param(searchform => $form);
++#      }
++#} #}}}
+ 
+-       # Add search box to page header.
+-       if ($template->query(name => "searchform")) {
+-               if (! defined $form) {
+-                       my $searchform = template("searchform.tmpl", blind_cache => 1);
+-                       $searchform->param(searchaction => $config{cgiurl});
+-                       $form=$searchform->output;
+-               }
+-
+-               $template->param(searchform => $form);
+-       }
+-} #}}}
+-
+ sub delete (@) { #{{{
+-       debug(gettext("cleaning hyperestraier search index"));
+-       estcmd("purge -cl");
+-       estcfg();
++       debug("Plucene: purging: ".join(',',@_));
++       init();
++  my $reader = Plucene::Index::Reader->open($PLUCENE_DIR);
++  my @files = src2rendered_abs(@_);
++  for (@files) {
++    $reader->delete_term( Plucene::Index::Term->new({ field => "id", text => $_ }));
++  }
++  $reader->close;
+ } #}}}
+ 
+ sub change (@) { #{{{
+-       debug(gettext("updating hyperestraier search index"));
+-       estcmd("gather -cm -bc -cl -sd",
+-               map {
+-                       Encode::encode_utf8($config{destdir}."/".$_)
+-                               foreach @{$renderedfiles{pagename($_)}};
+-               } @_
+-       );
+-       estcfg();
++       debug("Plucene: updating search index");
++  init();
++  #TODO: Do we want to index source or rendered files?
++  #TODO: Store author, tags, etc. in distinct fields; may need new API hook.
++  my @files = src2rendered_abs(@_);
++  my $writer = writer();    
++   
++  for my $file (@files) {
++    my $doc = Plucene::Document->new;
++    $doc->add(Plucene::Document::Field->Keyword(id => $file));
++    my $data;
++    eval { $data = readfile($file) };
++    if ($@) {
++      debug("Plucene: can't read <$file> - $@");
++      next;
++    }
++    debug("Plucene: indexing <$file> (".length($data).")");
++    $doc->add(Plucene::Document::Field->UnStored('text' => $data));
++    $writer->add_document($doc);
++  }
+ } #}}}
+-
+-sub cgi ($) { #{{{
+-       my $cgi=shift;
+-
+-       if (defined $cgi->param('phrase') || defined $cgi->param("navi")) {
+-               # only works for GET requests
+-               chdir("$config{wikistatedir}/hyperestraier") || error("chdir: $!");
+-               exec("./".IkiWiki::basename($config{cgiurl})) || error("estseek.cgi failed");
+-       }
+-} #}}}
+-
+-my $configured=0;
+-sub estcfg () { #{{{
+-       return if $configured;
+-       $configured=1;
+-
+-       my $estdir="$config{wikistatedir}/hyperestraier";
+-       my $cgi=IkiWiki::basename($config{cgiurl});
+-       $cgi=~s/\..*$//;
+-
+-       my $newfile="$estdir/$cgi.tmpl.new";
+-       my $cleanup = sub { unlink($newfile) };
+-       open(TEMPLATE, ">:utf8", $newfile) || error("open $newfile: $!", $cleanup);
+-       print TEMPLATE IkiWiki::misctemplate("search", 
+-               "\n\n\n\n\n\n",
+-               baseurl => IkiWiki::dirname($config{cgiurl})."/") ||
+-                       error("write $newfile: $!", $cleanup);
+-       close TEMPLATE || error("save $newfile: $!", $cleanup);
+-       rename($newfile, "$estdir/$cgi.tmpl") ||
+-               error("rename $newfile: $!", $cleanup);
+-
+-       $newfile="$estdir/$cgi.conf";
+-       open(TEMPLATE, ">$newfile") || error("open $newfile: $!", $cleanup);
+-       my $template=template("estseek.conf");
+-       eval q{use Cwd 'abs_path'};
+-       $template->param(
+-               index => $estdir,
+-               tmplfile => "$estdir/$cgi.tmpl",
+-               destdir => abs_path($config{destdir}),
+-               url => $config{url},
+-       );
+-       print TEMPLATE $template->output || error("write $newfile: $!", $cleanup);
+-       close TEMPLATE || error("save $newfile: $!", $cleanup);
+-       rename($newfile, "$estdir/$cgi.conf") ||
+-               error("rename $newfile: $!", $cleanup);
+-
+-       $cgi="$estdir/".IkiWiki::basename($config{cgiurl});
+-       unlink($cgi);
+-       my $estseek = defined $config{estseek} ? $config{estseek} : '/usr/lib/estraier/estseek.cgi';
+-       symlink($estseek, $cgi) || error("symlink $estseek $cgi: $!");
+-} # }}}
+-
+-sub estcmd ($;@) { #{{{
+-       my @params=split(' ', shift);
+-       push @params, "-cl", "$config{wikistatedir}/hyperestraier";
+-       if (@_) {
+-               push @params, "-";
+-       }
+-
+-       my $pid=open(CHILD, "|-");
+-       if ($pid) {
+-               # parent
+-               foreach (@_) {
+-                       print CHILD "$_\n";
+-               }
+-               close(CHILD) || print STDERR "estcmd @params exited nonzero: $?\n";
+-       }
+-       else {
+-               # child
+-               open(STDOUT, "/dev/null"); # shut it up (closing won't work)
+-               exec("estcmd", @params) || error("can't run estcmd");
+-       }
+-} #}}}
+-
+-1
++1;
+
+ + -- 2.44.0