gnu-social/lib/search_engines.php
Brion Vibber 53c86c43c4 Bringing Sphinx search support up to code: broken out to a plugin, now supports multiple sites on a single server.
Upgrade notes:
* Index names have changed from hardcoded 'Identica_people' and 'Identica_notices' to use the database name and actual table names. Must reindex.

New events:
* GetSearchEngine to override default search engine class selection from plugins

New scripts:
* gen_config.php generates a sphinx.conf from database configuration (with theoretical support for status_network table, but it doesn't seem to be cleanly queriable right now without knowing the db setup info for that. Needs generalized support.)
* Replaced old sphinx-indexer.sh and sphinx-cron.sh with index_update.php

Other fixes:
* sphinx.conf.sample better matches our live config, skipping unused stopword list and using a more realistic indexer memory limit

Further notes:
* Probably doesn't work right with PostgreSQL yet; Sphinx can pull from PG but the extraction queries currently look like they use some MySQL-specific functions.
2009-11-10 13:44:40 -08:00

122 lines
3.9 KiB
PHP

<?php
/*
* StatusNet - the distributed open-source microblogging tool
* Copyright (C) 2008, 2009, StatusNet, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
if (!defined('STATUSNET') && !defined('LACONICA')) { exit(1); }
class SearchEngine
{
protected $target;
protected $table;
function __construct($target, $table)
{
$this->target = $target;
$this->table = $table;
}
function query($q)
{
}
function limit($offset, $count, $rss = false)
{
return $this->target->limit($offset, $count);
}
function set_sort_mode($mode)
{
if ('chron' === $mode)
return $this->target->orderBy('created desc');
}
}
class MySQLSearch extends SearchEngine
{
function query($q)
{
if ('profile' === $this->table) {
$this->target->whereAdd('MATCH(nickname, fullname, location, bio, homepage) ' .
'AGAINST (\''.addslashes($q).'\' IN BOOLEAN MODE)');
if (strtolower($q) != $q) {
$this->target->whereAdd('MATCH(nickname, fullname, location, bio, homepage) ' .
'AGAINST (\''.addslashes(strtolower($q)).'\' IN BOOLEAN MODE)', 'OR');
}
return true;
} else if ('notice' === $this->table) {
// Don't show imported notices
$this->target->whereAdd('notice.is_local != ' . Notice::GATEWAY);
if (strtolower($q) != $q) {
$this->target->whereAdd("( MATCH(content) AGAINST ('" . addslashes($q) .
"' IN BOOLEAN MODE)) OR ( MATCH(content) " .
"AGAINST ('" . addslashes(strtolower($q)) .
"' IN BOOLEAN MODE))");
} else {
$this->target->whereAdd('MATCH(content) ' .
'AGAINST (\''.addslashes($q).'\' IN BOOLEAN MODE)');
}
return true;
} else {
throw new ServerException('Unknown table: ' . $this->table);
}
}
}
class MySQLLikeSearch extends SearchEngine
{
function query($q)
{
if ('profile' === $this->table) {
$qry = sprintf('(nickname LIKE "%%%1$s%%" OR '.
' fullname LIKE "%%%1$s%%" OR '.
' location LIKE "%%%1$s%%" OR '.
' bio LIKE "%%%1$s%%" OR '.
' homepage LIKE "%%%1$s%%")', addslashes($q));
} else if ('notice' === $this->table) {
$qry = sprintf('content LIKE "%%%1$s%%"', addslashes($q));
} else {
throw new ServerException('Unknown table: ' . $this->table);
}
$this->target->whereAdd($qry);
return true;
}
}
class PGSearch extends SearchEngine
{
function query($q)
{
if ('profile' === $this->table) {
return $this->target->whereAdd('textsearch @@ plainto_tsquery(\''.addslashes($q).'\')');
} else if ('notice' === $this->table) {
// XXX: We need to filter out gateway notices (notice.is_local = -2) --Zach
return $this->target->whereAdd('to_tsvector(\'english\', content) @@ plainto_tsquery(\''.addslashes($q).'\')');
} else {
throw new ServerException('Unknown table: ' . $this->table);
}
}
}