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/scripts/gen_config.php | 126 ++++++++++++++++++++++++++++
 1 file changed, 126 insertions(+)
 create mode 100755 plugins/SphinxSearch/scripts/gen_config.php

(limited to 'plugins/SphinxSearch/scripts/gen_config.php')

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;
+}
-- 
cgit v1.2.3-54-g00ecf