summaryrefslogtreecommitdiff
path: root/plugins/SphinxSearch
diff options
context:
space:
mode:
authorBrion Vibber <brion@pobox.com>2009-11-03 16:57:39 -0800
committerBrion Vibber <brion@pobox.com>2009-11-10 13:44:40 -0800
commit53c86c43c4b8cba313335f5d70f7f77d4ab640d2 (patch)
tree96de2e9f0793685e35702946ec8539edbcf80921 /plugins/SphinxSearch
parent1cd6650ae43d548f209d68e9feaaa7185d5ffecb (diff)
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.
Diffstat (limited to 'plugins/SphinxSearch')
-rw-r--r--plugins/SphinxSearch/README45
-rw-r--r--plugins/SphinxSearch/SphinxSearchPlugin.php100
-rwxr-xr-xplugins/SphinxSearch/scripts/gen_config.php126
-rwxr-xr-xplugins/SphinxSearch/scripts/index_update.php61
-rw-r--r--plugins/SphinxSearch/scripts/sphinx-utils.php63
-rwxr-xr-xplugins/SphinxSearch/scripts/sphinx.sh15
-rw-r--r--plugins/SphinxSearch/sphinx.conf.sample71
-rw-r--r--plugins/SphinxSearch/sphinxsearch.php96
8 files changed, 577 insertions, 0 deletions
diff --git a/plugins/SphinxSearch/README b/plugins/SphinxSearch/README
new file mode 100644
index 000000000..5a2c063bd
--- /dev/null
+++ b/plugins/SphinxSearch/README
@@ -0,0 +1,45 @@
+You can get a significant boost in performance using Sphinx Search
+instead of your database server to search for users and notices.
+<http://sphinxsearch.com/>.
+
+Configuration
+-------------
+
+In StatusNet's configuration, you can adjust the following settings
+under 'sphinx':
+
+enabled: Set to true to enable. Default false.
+server: a string with the hostname of the sphinx server.
+port: an integer with the port number of the sphinx server.
+
+
+Requirements
+------------
+
+To use a Sphinx server to search users and notices, you also need
+to install, compile and enable the sphinx pecl extension for php on the
+client side, which itself depends on the sphinx development files.
+"pecl install sphinx" should take care of that. Add "extension=sphinx.so"
+to your php.ini and reload apache to enable it.
+
+You can update your MySQL or Postgresql databases to drop their fulltext
+search indexes, since they're now provided by sphinx.
+
+
+You will also need a Sphinx server to serve the search queries.
+
+On the sphinx server side, a script reads the main database and build
+the keyword index. A cron job reads the database and keeps the sphinx
+indexes up to date. scripts/sphinx-cron.sh should be called by cron
+every 5 minutes, for example. scripts/sphinx.sh is an init.d script
+to start and stop the sphinx search daemon.
+
+
+Server configuration
+--------------------
+scripts/gen_config.php can generate a sphinx.conf file listing MySQL
+data sources for your databases. You may need to tweak paths afterwards.
+
+ $ plugins/SphinxSearch/scripts/gen_config.php > sphinx.conf
+
+If you wish, you can build a full config yourself based on sphinx.conf.sample
diff --git a/plugins/SphinxSearch/SphinxSearchPlugin.php b/plugins/SphinxSearch/SphinxSearchPlugin.php
new file mode 100644
index 000000000..7a27a4c04
--- /dev/null
+++ b/plugins/SphinxSearch/SphinxSearchPlugin.php
@@ -0,0 +1,100 @@
+<?php
+/**
+ * StatusNet, the distributed open-source microblogging tool
+ *
+ * PHP version 5
+ *
+ * LICENCE: 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/>.
+ *
+ * @category Plugin
+ * @package StatusNet
+ * @author Brion Vibber <brion@status.net>
+ * @copyright 2009 Control Yourself, Inc.
+ * @license http://www.fsf.org/licensing/licenses/agpl-3.0.html GNU Affero General Public License version 3.0
+ * @link http://laconi.ca/
+ */
+
+if (!defined('STATUSNET')) {
+ exit(1);
+}
+
+// Set defaults if not already set in the config array...
+global $config;
+$sphinxDefaults =
+ array('enabled' => true,
+ 'server' => 'localhost',
+ 'port' => 3312);
+foreach($sphinxDefaults as $key => $val) {
+ if (!isset($config['sphinx'][$key])) {
+ $config['sphinx'][$key] = $val;
+ }
+}
+
+
+
+/**
+ * Plugin for Sphinx search backend.
+ *
+ * @category Plugin
+ * @package StatusNet
+ * @author Brion Vibber <brion@status.net>
+ * @license http://www.fsf.org/licensing/licenses/agpl-3.0.html GNU Affero General Public License version 3.0
+ * @link http://laconi.ca/
+ * @link http://twitter.com/
+ */
+
+class SphinxSearchPlugin extends Plugin
+{
+ /**
+ * Automatically load any classes used
+ *
+ * @param string $cls the class
+ * @return boolean hook return
+ */
+ function onAutoload($cls)
+ {
+ switch ($cls) {
+ case 'SphinxSearch':
+ include_once INSTALLDIR . '/plugins/SphinxSearch/' .
+ strtolower($cls) . '.php';
+ return false;
+ default:
+ return true;
+ }
+ }
+
+ /**
+ * Create sphinx search engine object for the given table type.
+ *
+ * @param Memcached_DataObject $target
+ * @param string $table
+ * @param out &$search_engine SearchEngine object on output if successful
+ * @ return boolean hook return
+ */
+ function onGetSearchEngine(Memcached_DataObject $target, $table, &$search_engine)
+ {
+ if (common_config('sphinx', 'enabled')) {
+ if (!class_exists('SphinxClient')) {
+ throw new ServerException('Sphinx PHP extension must be installed.');
+ }
+ $engine = new SphinxSearch($target, $table);
+ if ($engine->is_connected()) {
+ $search_engine = $engine;
+ return false;
+ }
+ }
+ // Sphinx disabled or disconnected
+ return true;
+ }
+}
diff --git a/plugins/SphinxSearch/scripts/gen_config.php b/plugins/SphinxSearch/scripts/gen_config.php
new file mode 100755
index 000000000..d5a00b6b6
--- /dev/null
+++ b/plugins/SphinxSearch/scripts/gen_config.php
@@ -0,0 +1,126 @@
+#!/usr/bin/env php
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2009, StatusNet, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+define('INSTALLDIR', realpath(dirname(__FILE__) . '/../../..'));
+
+$longoptions = array('base=', 'network');
+
+$helptext = <<<END_OF_TRIM_HELP
+Generates sphinx.conf file based on StatusNet configuration.
+ --base Base dir to Sphinx install
+ (default /usr/local)
+ --network Use status_network global config table
+ (non-functional at present)
+
+
+END_OF_TRIM_HELP;
+
+require_once INSTALLDIR . '/scripts/commandline.inc';
+require dirname(__FILE__) . '/sphinx-utils.php';
+
+
+$timestamp = date('r');
+print <<<END
+#
+# Sphinx configuration for StatusNet
+# Generated {$timestamp}
+#
+
+END;
+
+sphinx_iterate_sites('sphinx_site_template');
+
+print <<<END
+
+indexer
+{
+ mem_limit = 300M
+}
+
+searchd
+{
+ port = 3312
+ log = {$base}/log/searchd.log
+ query_log = {$base}/log/query.log
+ read_timeout = 5
+ max_children = 30
+ pid_file = {$base}/log/searchd.pid
+ max_matches = 1000
+ seamless_rotate = 1
+ preopen_indexes = 0
+ unlink_old = 1
+}
+
+END;
+
+
+
+/**
+ * Build config entries for a single site
+ * @fixme we only seem to have master DB currently available...
+ */
+function sphinx_site_template($sn)
+{
+ return
+ sphinx_template($sn,
+ 'profile',
+ 'SELECT id, UNIX_TIMESTAMP(created) as created_ts, nickname, fullname, location, bio, homepage FROM profile',
+ 'SELECT * FROM profile where id = $id') .
+ sphinx_template($sn,
+ 'notice',
+ 'SELECT id, UNIX_TIMESTAMP(created) as created_ts, content FROM notice',
+ 'SELECT * FROM notice where notice.id = $id AND notice.is_local != -2');
+}
+
+function sphinx_template($sn, $table, $query, $query_info)
+{
+ $base = sphinx_base();
+ $dbtype = common_config('db', 'type');
+
+ print <<<END
+
+#
+# {$sn->sitename}
+#
+source {$sn->dbname}_src_{$table}
+{
+ type = {$dbtype}
+ sql_host = {$sn->dbhost}
+ sql_user = {$sn->dbuser}
+ sql_pass = {$sn->dbpass}
+ sql_db = {$sn->dbname}
+ sql_query_pre = SET NAMES utf8;
+ sql_query = {$query}
+ sql_query_info = {$query_info}
+ sql_attr_timestamp = created_ts
+}
+
+index {$sn->dbname}_{$table}
+{
+ source = {$sn->dbname}_src_{$table}
+ path = {$base}/data/{$sn->dbname}_{$table}
+ docinfo = extern
+ charset_type = utf-8
+ min_word_len = 3
+}
+
+
+END;
+}
diff --git a/plugins/SphinxSearch/scripts/index_update.php b/plugins/SphinxSearch/scripts/index_update.php
new file mode 100755
index 000000000..23c60ced7
--- /dev/null
+++ b/plugins/SphinxSearch/scripts/index_update.php
@@ -0,0 +1,61 @@
+#!/usr/bin/env php
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 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/>.
+ */
+
+define('INSTALLDIR', realpath(dirname(__FILE__) . '/../../..'));
+
+$longoptions = array('base=', 'network');
+
+$helptext = <<<END_OF_TRIM_HELP
+Runs Sphinx search indexer.
+ --rotate Have Sphinx run index update in background and
+ rotate updated indexes into place as they finish.
+ --base Base dir to Sphinx install
+ (default /usr/local)
+ --network Use status_network global config table for site list
+ (non-functional at present)
+
+
+END_OF_TRIM_HELP;
+
+require_once INSTALLDIR . '/scripts/commandline.inc';
+require dirname(__FILE__) . '/sphinx-utils.php';
+
+sphinx_iterate_sites('sphinx_index_update');
+
+function sphinx_index_update($sn)
+{
+ $base = sphinx_base();
+
+ $baseIndexes = array('notice', 'profile');
+ $params = array();
+
+ if (have_option('rotate')) {
+ $params[] = '--rotate';
+ }
+ foreach ($baseIndexes as $index) {
+ $params[] = "{$sn->dbname}_{$index}";
+ }
+
+ $params = implode(' ', $params);
+ $cmd = "$base/bin/indexer --config $base/etc/sphinx.conf $params";
+
+ print "$cmd\n";
+ system($cmd);
+}
diff --git a/plugins/SphinxSearch/scripts/sphinx-utils.php b/plugins/SphinxSearch/scripts/sphinx-utils.php
new file mode 100644
index 000000000..7bbc25270
--- /dev/null
+++ b/plugins/SphinxSearch/scripts/sphinx-utils.php
@@ -0,0 +1,63 @@
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2009, StatusNet, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+function sphinx_use_network()
+{
+ return have_option('network');
+}
+
+function sphinx_base()
+{
+ if (have_option('base')) {
+ return get_option_value('base');
+ } else {
+ return "/usr/local/sphinx";
+ }
+}
+
+function sphinx_iterate_sites($callback)
+{
+ if (sphinx_use_network()) {
+ // @fixme this should use, like, some kind of config
+ Status_network::setupDB('localhost', 'statusnet', 'statuspass', 'statusnet');
+ $sn = new Status_network();
+ if (!$sn->find()) {
+ die("Confused... no sites in status_network table or lookup failed.\n");
+ }
+ while ($sn->fetch()) {
+ $callback($sn);
+ }
+ } else {
+ if (preg_match('!^(mysqli?|pgsql)://(.*?):(.*?)@(.*?)/(.*?)$!',
+ common_config('db', 'database'), $matches)) {
+ list(/*all*/, $dbtype, $dbuser, $dbpass, $dbhost, $dbname) = $matches;
+ $sn = (object)array(
+ 'sitename' => common_config('site', 'name'),
+ 'dbhost' => $dbhost,
+ 'dbuser' => $dbuser,
+ 'dbpass' => $dbpass,
+ 'dbname' => $dbname);
+ $callback($sn);
+ } else {
+ print "Unrecognized database configuration string in config.php\n";
+ exit(1);
+ }
+ }
+}
+
diff --git a/plugins/SphinxSearch/scripts/sphinx.sh b/plugins/SphinxSearch/scripts/sphinx.sh
new file mode 100755
index 000000000..b8edeb302
--- /dev/null
+++ b/plugins/SphinxSearch/scripts/sphinx.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+if [[ $1 = "start" ]]
+then
+ echo "Stopping any running daemons..."
+ /usr/local/bin/searchd --config /usr/local/etc/sphinx.conf --stop 2> /dev/null
+ echo "Starting sphinx search daemon..."
+ /usr/local/bin/searchd --config /usr/local/etc/sphinx.conf 2> /dev/null
+fi
+
+if [[ $1 = "stop" ]]
+then
+ echo "Stopping sphinx search daemon..."
+ /usr/local/bin/searchd --config /usr/local/etc/sphinx.conf --stop 2> /dev/null
+fi
diff --git a/plugins/SphinxSearch/sphinx.conf.sample b/plugins/SphinxSearch/sphinx.conf.sample
new file mode 100644
index 000000000..3de62f637
--- /dev/null
+++ b/plugins/SphinxSearch/sphinx.conf.sample
@@ -0,0 +1,71 @@
+#
+# Minimal Sphinx configuration sample for statusnet
+#
+
+source src1
+{
+ type = mysql
+ sql_host = localhost
+ sql_user = USERNAME
+ sql_pass = PASSWORD
+ sql_db = identi_ca
+ sql_port = 3306
+ sql_query = SELECT id, UNIX_TIMESTAMP(created) as created_ts, nickname, fullname, location, bio, homepage FROM profile
+ sql_query_info = SELECT * FROM profile where id = $id
+ sql_attr_timestamp = created_ts
+}
+
+
+source src2
+{
+ type = mysql
+ sql_host = localhost
+ sql_user = USERNAME
+ sql_pass = PASSWORD
+ sql_db = identi_ca
+ sql_port = 3306
+ sql_query = SELECT id, UNIX_TIMESTAMP(created) as created_ts, content FROM notice
+ sql_query_info = SELECT * FROM notice where notice.id = $id AND notice.is_local != -2
+ sql_attr_timestamp = created_ts
+}
+
+index identica_notices
+{
+ source = src2
+ path = DIRECTORY/data/identica_notices
+ docinfo = extern
+ charset_type = utf-8
+ min_word_len = 3
+ stopwords = DIRECTORY/data/stopwords-en.txt
+}
+
+
+index identica_people
+{
+ source = src1
+ path = DIRECTORY/data/identica_people
+ docinfo = extern
+ charset_type = utf-8
+ min_word_len = 3
+ stopwords = DIRECTORY/data/stopwords-en.txt
+}
+
+indexer
+{
+ mem_limit = 32M
+}
+
+searchd
+{
+ port = 3312
+ log = DIRECTORY/log/searchd.log
+ query_log = DIRECTORY/log/query.log
+ read_timeout = 5
+ max_children = 30
+ pid_file = DIRECTORY/log/searchd.pid
+ max_matches = 1000
+ seamless_rotate = 1
+ preopen_indexes = 0
+ unlink_old = 1
+}
+
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");
+ }
+}