Sphinx+MySQL5.1x+SphinxSE+mmseg
一.不停止mysql的情况下安装SphinxSE
1.确定mysql版本,下载对应源码包
此处下载5.1.69的mysql源码包
#wget ftp://ftp.ntu.edu.tw/pub/MySQL/Downloads/MySQL-5.1/mysql-5.1.69.tar.gz
解压
2.下载sphinx:
#wget http://sphinxsearch.com/downloads/sphinx-0.9.9.tar.gz
解压
3.拷贝mysqlse到mysql5.1.69下的storage/sphinx
#cp -r sphinx-0.9.9/mysqlse/ mysql-5.1.69/storage/sphinx
4.编译
#cd mysql-5.1.69
#sh BUILD/autorun.sh
#./configure
#make
5.mysql插入sphinx引擎
#cd ./mysql-5.1.69
#cd ./storage/sphinx/.libs
#cp ha_sphinx.* /usr/lib64/mysql/plugin
更改所有者
#chown mysql.mysql /usr/lib64/mysql/plugin/*
登录mysql,插入引擎
#mysql -u root -p -h localhost
#mysql> INSTALL PLUGIN sphinx SONAME 'ha_sphinx.so';
检查引擎是否安装
#mysql> show engines;
如果出现sphinx引擎,则表明已正常安装
二.安装Coreseek,使其支持中文索引及检索
1.安装autoconf
2.下载coreseek3.2.14.tar.gz,并解压缩
3.安装mmseg分词
#cd coreseek-3.2.14
#./bootstrap
#./configure --prefix=/usr/local/mmseg3
#make
#make install
4.安装csft
#cd ../csft-3.2.14/
#sh buildconf.sh
#./configure --prefix=/usr/local/coreseek --without-unixodbc --with-mmseg --with-mmseg-includes=/usr/local/mmseg3/include/mmseg/ --with-mmseg-libs=/usr/local/mmseg3/lib/ --with-mysql
===========================================================
##如果出现错误提示:“ERROR: cannot find MySQL include files.......To disable MySQL support, use --without-mysql option.“,可按照如下方法处理:
##请找到头文件mysql.h所在的目录,一般是/usr/local/mysql/include,请替换为实际的
##请找到库文件libmysqlclient.a所在的目录,一般是/usr/local/mysql/lib,请替换为实际的
##configure参数加上:--with-mysql-includes=/usr/local/mysql/include --with-mysql-libs=/usr/local/mysql/lib,执行后,重新编译安装
============================================================
#make
#make install
三.配置并测试
1.进入coreseek目录
#cd /usr/local/coreseek/etc
#ls
可以看到三个文件
example.sql sphinx.conf.dist sphinx-min.conf.dist
#cp sphinx.conf.dist sphinx.conf
2.配置sphinx.conf
source src1
{
type = mysql
sql_host = localhost
sql_user = root
sql_pass = 123456
sql_db = test
sql_port = 3306 # optional, default is 3306
sql_sock = /var/lib/mysql/mysql.sock
sql_query_pre = SET NAMES utf8
sql_query = \
SELECT id, group_id, UNIX_TIMESTAMP(date_added) AS date_added, title, content \
FROM documents
sql_attr_uint = group_id
sql_attr_timestamp = date_added
sql_query_info = SELECT * FROM documents WHERE id=$id
}
index test1
{
source = src1
path = /usr/local/coreseek/var/data/test1
docinfo = extern
charset_type = zh_cn.utf-8
mlock = 0
morphology = none
min_word_len = 1
html_strip = 0
charset_dictpath = /usr/local/mmseg3/etc/
ngram_len = 0
}
indexer
{
mem_limit = 32M
}
searchd
{
port = 9312
log = /usr/local/coreseek/var/log/searchd.log
query_log = /usr/local/coreseek/var/log/query.log
read_timeout = 5
max_children = 30
pid_file = /usr/local/coreseek/var/log/searchd.pid
max_matches = 1000
seamless_rotate = 1
preopen_indexes = 0
unlink_old = 1
}
3.创建test数据库,并建立表documents,sql语句如下
DROP TABLE IF EXISTS test.documents;
CREATE TABLE test.documents
(
id INTEGER PRIMARY KEY NOT NULL AUTO_INCREMENT,
group_id INTEGER NOT NULL,
group_id2 INTEGER NOT NULL,
date_added DATETIME NOT NULL,
title VARCHAR(255) NOT NULL,
content TEXT NOT NULL
);
REPLACE INTO test.documents ( id, group_id, group_id2, date_added, title, content ) VALUES
( 1, 1, 5, NOW(), 'test one', 'this is my test document number one. also checking search within phrases.' ),
( 2, 1, 6, NOW(), 'test two', 'this is my test document number two' ),
( 3, 2, 7, NOW(), 'another doc', 'this is another group' ),
( 4, 2, 8, NOW(), 'doc number four', 'this is to test groups' );
DROP TABLE IF EXISTS test.tags;
CREATE TABLE test.tags
(
docid INTEGER NOT NULL,
tagid INTEGER NOT NULL,
UNIQUE(docid,tagid)
);
INSERT INTO test.tags VALUES
(1,1), (1,3), (1,5), (1,7),
(2,6), (2,4), (2,2),
(3,15),
(4,7), (4,40);
4.生成索引
#/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/sphinx.conf --all
其中参数--all表示生成所有索引
当然也可以是索引的名字例如:#/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/sphinx.conf test1
执行后可以在/usr/local/coreseek/var/data目录中看到多出一些文件,是以索引名为文件名的不同的扩展名的文件
在不启动sphinx的情况下即可测试命令:
#/usr/local/coreseek/bin/search -c /usr/local/coreseek/etc/sphinx.conf number
#/usr/local/coreseek/bin/search -c /usr/local/coreseek/etc/sphinx.conf number --filter group_id 2
限定group_id 为2 返回一条记录
我们插入几条数据来测试中文
set names utf8 之前一定要设置字符集
INSERT INTO `test`.`documents` (
`id` ,
`group_id` ,
`group_id2` ,
`date_added` ,
`title` ,
`content`
)
VALUES (
NULL , '2', '3', '2011-02-01 00:37:12', '研究生的故事', '研究生自主创业'
), (
NULL , '1', '1', '2011-01-28 00:38:22', '研究', '为了创业而研究生命科学'
);
插入数据后需要重新索引
#/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/sphinx.conf test1
进行测试
#/usr/local/coreseek/bin/search -c /usr/local/coreseek/etc/sphinx.conf 研究生创业
四.实际使用
1.作为守护进程启动
#/usr/local/coreseek/bin/searchd -c /usr/local/coreseek/etc/sphinx.conf
2.建立一个sphinx引擎的表
CREATE TABLE t1
(
id INTEGER UNSIGNED NOT NULL,
weight INTEGER NOT NULL,
query VARCHAR(3072) NOT NULL,
group_id INTEGER,
INDEX(query)
) ENGINE=SPHINX CONNECTION="sphinx://localhost:9312/test1";
搜索表前三列的类型必须是INTEGER,INTEGER和VARCHAR,这三列分别对应文档ID,匹配权值和搜索查询。查询列必须被索引,其他列必须无索引。列的名字会被忽略,所以可以任意命名,参数CONNECTION来指定用这个表搜索时的默认搜索主机、端口号和索引,语法格式:CONNECTION="sphinx://HOST:PORT/INDEXNAME"。
执行SQL语句 select d.id,d.title,d.content from t1 join documents as d on t1.id = d.id and t1.query = '研究生创业';
即可查询结果
3.在不停止searchd的情况下主索引
插入数据后创建主索引
#/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/sphinx.conf test1 --rotate
对于实际应用,应该是主索引+增量索引