From 53c86c43c4b8cba313335f5d70f7f77d4ab640d2 Mon Sep 17 00:00:00 2001
From: Brion Vibber <brion@pobox.com>
Date: Tue, 3 Nov 2009 16:57:39 -0800
Subject: 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.
---
 plugins/SphinxSearch/sphinxsearch.php | 96 +++++++++++++++++++++++++++++++++++
 1 file changed, 96 insertions(+)
 create mode 100644 plugins/SphinxSearch/sphinxsearch.php

(limited to 'plugins/SphinxSearch/sphinxsearch.php')

diff --git a/plugins/SphinxSearch/sphinxsearch.php b/plugins/SphinxSearch/sphinxsearch.php
new file mode 100644
index 000000000..71f330828
--- /dev/null
+++ b/plugins/SphinxSearch/sphinxsearch.php
@@ -0,0 +1,96 @@
+<?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')) {
+    exit(1);
+}
+
+class SphinxSearch extends SearchEngine
+{
+    private $sphinx;
+    private $connected;
+
+    function __construct($target, $table)
+    {
+        $fp = @fsockopen(common_config('sphinx', 'server'), common_config('sphinx', 'port'));
+        if (!$fp) {
+            $this->connected = false;
+            return;
+        }
+        fclose($fp);
+        parent::__construct($target, $table);
+        $this->sphinx = new SphinxClient;
+        $this->sphinx->setServer(common_config('sphinx', 'server'), common_config('sphinx', 'port'));
+        $this->connected = true;
+    }
+
+    function is_connected()
+    {
+        return $this->connected;
+    }
+
+    function limit($offset, $count, $rss = false)
+    {
+        //FIXME without LARGEST_POSSIBLE, the most recent results aren't returned
+        //      this probably has a large impact on performance
+        $LARGEST_POSSIBLE = 1e6;
+
+        if ($rss) {
+            $this->sphinx->setLimits($offset, $count, $count, $LARGEST_POSSIBLE);
+        }
+        else {
+            // return at most 50 pages of results
+            $this->sphinx->setLimits($offset, $count, 50 * ($count - 1), $LARGEST_POSSIBLE);
+        }
+
+        return $this->target->limit(0, $count);
+    }
+
+    function query($q)
+    {
+        $result = $this->sphinx->query($q, $this->remote_table());
+        if (!isset($result['matches'])) return false;
+        $id_set = join(', ', array_keys($result['matches']));
+        $this->target->whereAdd("id in ($id_set)");
+        return true;
+     }
+
+    function set_sort_mode($mode)
+    {
+        if ('chron' === $mode) {
+            $this->sphinx->SetSortMode(SPH_SORT_ATTR_DESC, 'created_ts');
+            return $this->target->orderBy('created desc');
+        }
+    }
+
+    function remote_table()
+    {
+        return $this->dbname() . '_' . $this->table;
+    }
+
+    function dbname()
+    {
+        // @fixme there should be a less dreadful way to do this.
+        // DB objects won't give database back until they connect, it's confusing
+        if (preg_match('!^.*?://.*?:.*?@.*?/(.*?)$!', common_config('db', 'database'), $matches)) {
+            return $matches[1];
+        }
+        throw new ServerException("Sphinx search could not identify database name");
+    }
+}
-- 
cgit v1.2.3-54-g00ecf