Sphinx
------
-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.
+To use a Sphinx server to search users and notices, you'll need to
+enable the SphinxSearch plugin. Add to your config.php:
-You can update your MySQL or Postgresql databases to drop their fulltext
-search indexes, since they're now provided by sphinx.
+ addPlugin('SphinxSearch');
+ $config['sphinx']['server'] = 'searchhost.local';
-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.
+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.
+
+See plugins/SphinxSearch/README for more details and server setup.
SMS
---
StatusNet site using your memcached server.
port: Port to connect to; defaults to 11211.
-sphinx
-------
-
-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/>.
-
-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.
-
emailpost
---------
{
$notice = new Notice();
- $search_engine = $notice->getSearchEngine('identica_notices');
+ $search_engine = $notice->getSearchEngine('notice');
$search_engine->set_sort_mode('chron');
// Ask for an extra to see if there's more.
$search_engine->limit((($page-1)*NOTICES_PER_PAGE), NOTICES_PER_PAGE + 1);
$notice = new Notice();
- $search_engine = $notice->getSearchEngine('identica_notices');
+ $search_engine = $notice->getSearchEngine('notice');
$search_engine->set_sort_mode('chron');
if (!$limit) $limit = 20;
function showResults($q, $page)
{
$profile = new Profile();
- $search_engine = $profile->getSearchEngine('identica_people');
+ $search_engine = $profile->getSearchEngine('profile');
$search_engine->set_sort_mode('chron');
// Ask for an extra to see if there's more.
$search_engine->limit((($page-1)*PROFILES_PER_PAGE), PROFILES_PER_PAGE + 1);
// lcase it for comparison
$q = strtolower($this->query);
- $search_engine = $notice->getSearchEngine('identica_notices');
+ $search_engine = $notice->getSearchEngine('notice');
$search_engine->set_sort_mode('chron');
$search_engine->limit(($this->page - 1) * $this->rpp,
$this->rpp + 1, true);
// lcase it for comparison
$q = strtolower($this->query);
- $search_engine = $notice->getSearchEngine('identica_notices');
+ $search_engine = $notice->getSearchEngine('notice');
$search_engine->set_sort_mode('chron');
$search_engine->limit(($this->page - 1) * $this->rpp, $this->rpp + 1, true);
if (false === $search_engine->query($q)) {
require_once INSTALLDIR.'/lib/search_engines.php';
static $search_engine;
if (!isset($search_engine)) {
- $connected = false;
- if (common_config('sphinx', 'enabled')) {
- $search_engine = new SphinxSearch($this, $table);
- $connected = $search_engine->is_connected();
- }
-
- // unable to connect to sphinx' search daemon
- if (!$connected) {
- if ('mysql' === common_config('db', 'type')) {
- $type = common_config('search', 'type');
- if ($type == 'like') {
- $search_engine = new MySQLLikeSearch($this, $table);
- } else if ($type == 'fulltext') {
- $search_engine = new MySQLSearch($this, $table);
- } else {
- throw new ServerException('Unknown search type: ' . $type);
- }
+ if (Event::handle('GetSearchEngine', array($this, $table, &$search_engine))) {
+ if ('mysql' === common_config('db', 'type')) {
+ $type = common_config('search', 'type');
+ if ($type == 'like') {
+ $search_engine = new MySQLLikeSearch($this, $table);
+ } else if ($type == 'fulltext') {
+ $search_engine = new MySQLSearch($this, $table);
} else {
- $search_engine = new PGSearch($this, $table);
+ throw new ServerException('Unknown search type: ' . $type);
}
+ } else {
+ $search_engine = new PGSearch($this, $table);
}
+ }
}
return $search_engine;
}
$config['db']['ini_'.$dbname] = INSTALLDIR.'/classes/status_network.ini';
$config['db']['table_status_network'] = $dbname;
- self::$cache = new Memcache();
+ if (class_exists('Memcache')) {
+ self::$cache = new Memcache();
- if (is_array($servers)) {
- foreach($servers as $server) {
- self::$cache->addServer($server);
+ if (is_array($servers)) {
+ foreach($servers as $server) {
+ self::$cache->addServer($server);
+ }
+ } else {
+ self::$cache->addServer($servers);
}
- } else {
- self::$cache->addServer($servers);
}
self::$base = $dbname;
static function memGet($k, $v)
{
+ if (!self::$cache) {
+ return self::staticGet($k, $v);
+ }
+
$ck = self::cacheKey($k, $v);
$sn = self::$cache->get($ck);
function decache()
{
- $keys = array('nickname', 'hostname', 'pathname');
- foreach ($keys as $k) {
- $ck = self::cacheKey($k, $this->$k);
- self::$cache->delete($ck);
+ if (self::$cache) {
+ $keys = array('nickname', 'hostname', 'pathname');
+ foreach ($keys as $k) {
+ $ck = self::cacheKey($k, $this->$k);
+ self::$cache->delete($ck);
+ }
}
}
'public' => array()), # JIDs of users who want to receive the public stream
'invite' =>
array('enabled' => true),
- 'sphinx' =>
- array('enabled' => false,
- 'server' => 'localhost',
- 'port' => 3312),
'tag' =>
array('dropoff' => 864000.0),
'popular' =>
}
}
-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, $this->table);
- if (!isset($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 $this->target->orderBy('created desc');
- }
- }
-}
-
class MySQLSearch extends SearchEngine
{
function query($q)
{
- if ('identica_people' === $this->table) {
+ if ('profile' === $this->table) {
$this->target->whereAdd('MATCH(nickname, fullname, location, bio, homepage) ' .
'AGAINST (\''.addslashes($q).'\' IN BOOLEAN MODE)');
if (strtolower($q) != $q) {
'AGAINST (\''.addslashes(strtolower($q)).'\' IN BOOLEAN MODE)', 'OR');
}
return true;
- } else if ('identica_notices' === $this->table) {
+ } else if ('notice' === $this->table) {
// Don't show imported notices
$this->target->whereAdd('notice.is_local != ' . Notice::GATEWAY);
{
function query($q)
{
- if ('identica_people' === $this->table) {
+ 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 ('identica_notices' === $this->table) {
+ } else if ('notice' === $this->table) {
$qry = sprintf('content LIKE "%%%1$s%%"', addslashes($q));
} else {
throw new ServerException('Unknown table: ' . $this->table);
{
function query($q)
{
- if ('identica_people' === $this->table) {
+ if ('profile' === $this->table) {
return $this->target->whereAdd('textsearch @@ plainto_tsquery(\''.addslashes($q).'\')');
- } else if ('identica_notices' === $this->table) {
+ } else if ('notice' === $this->table) {
// XXX: We need to filter out gateway notices (notice.is_local = -2) --Zach
--- /dev/null
+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
--- /dev/null
+<?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 = $engine;
+ return false;
+ }
+ }
+ // Sphinx disabled or disconnected
+ return true;
+ }
+}
--- /dev/null
+#!/usr/bin/env php
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2009, StatusNet, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+define('INSTALLDIR', realpath(dirname(__FILE__) . '/../../..'));
+
+$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;
+}
--- /dev/null
+#!/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($cmd);
+}
--- /dev/null
+<?php
+/*
+ * StatusNet - the distributed open-source microblogging tool
+ * Copyright (C) 2009, StatusNet, Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU Affero General Public License as published by
+ * the Free Software Foundation, either version 3 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU Affero General Public License for more details.
+ *
+ * You should have received a copy of the GNU Affero General Public License
+ * along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+function sphinx_use_network()
+{
+ return have_option('network');
+}
+
+function sphinx_base()
+{
+ if (have_option('base')) {
+ return get_option_value('base');
+ } else {
+ return "/usr/local/sphinx";
+ }
+}
+
+function sphinx_iterate_sites($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);
+ }
+ }
+}
+
--- /dev/null
+#!/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
--- /dev/null
+#
+# 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
+}
+
--- /dev/null
+<?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");
+ }
+}
+++ /dev/null
-#!/bin/sh
-
-# StatusNet - a 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/>.
-
-# This program tries to start the daemons for StatusNet.
-# Note that the 'maildaemon' needs to run as a mail filter.
-
-/usr/local/bin/indexer --config /usr/local/etc/sphinx.conf --all --rotate
-
+++ /dev/null
-#!/bin/sh
-
-# StatusNet - a 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/>.
-
-# This program tries to start the daemons for StatusNet.
-# Note that the 'maildaemon' needs to run as a mail filter.
-
-/usr/local/bin/indexer --config /usr/local/etc/sphinx.conf --all
-
+++ /dev/null
-#!/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
+++ /dev/null
-#
-# 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
-}
-
projects / quix0rs-gnu-social.git / commitdiff