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/sphinx.conf.sample | 71 +++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)
 create mode 100644 plugins/SphinxSearch/sphinx.conf.sample

(limited to 'plugins/SphinxSearch/sphinx.conf.sample')

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