sphinx的安装和测试:
sphinx的安装
yum install sphinx -y
2. 配置文件
#
# Minimal Sphinx configuration sample (clean, simple, functional)
#
source sbtest_sbtest1
{
type = mysql
sql_host = localhost
sql_user = root
sql_pass = redhat
sql_db = sbtest
sql_port = 3306 # optional, default is 3306
sql_query = \
SELECT userid as id, \
k, \
c, \
pad \
FROM sbtest1 \
where c like '%03679578678%' \
sql_attr_uint = k #数据类型int或者timestamp
sql_field_string = c #数据类型text或者string
sql_attr_string = pad #数据类型string
}
index sbtest1
{
source = sbtest_sbtest1
path = /var/lib/sphinx/sbtest1 #索引文件的路径
}
index testrt
{
type = rt
rt_mem_limit = 128M
path = /var/lib/sphinx/testrt
rt_field = title
rt_field = content
rt_attr_uint = gid
}
indexer
{
mem_limit = 128M
}
searchd
{
listen = 9312
listen = 9306:mysql41 #对外提供服务的端口,类似与mysql中的3306端口
log = /var/log/sphinx/searchd.log
query_log = /var/log/sphinx/query.log
read_timeout = 5
max_children = 30
pid_file = /var/run/sphinx/searchd.pid
seamless_rotate = 1
preopen_indexes = 1
unlink_old = 1
workers = threads # for RT to work
binlog_path = /var/lib/sphinx/
}
注意：在配置文件中需要注意的是:
a. 在sql_query参数后面是sql语句,但是这个sql语句的第一个字段必须是id字段，在后面的参数类型定义的时候不需要定义,否则的话sphinx是不能识别这个属性的。
b. 在属性的定义的时候必须包含一个sql_filed_string类型的字段，否则sphinx认为你没有必须使用全文检索这个功能。
3.创建索引
indexer sbtest1
4.启动searchd 服务
service searchd start
5.查看searchd服务状态
[root@TiDB-node2 data]# searchd --status
Sphinx 2.3.2-id64-beta (4409612)
Copyright (c) 2001-2016, Andrew Aksyonoff
Copyright (c) 2008-2016, Sphinx Technologies Inc (http://sphinxsearch.com)
using config file '/etc/sphinx/sphinx.conf'...
searchd status
--------------
uptime: 80403
connections: 11
maxed_out: 0
command_search: 7
command_excerpt: 0
command_update: 0
command_delete: 0
command_keywords: 0
command_persist: 0
command_status: 1
command_flushattrs: 0
agent_connect: 0
agent_retry: 0
queries: 7
dist_queries: 0
query_wall: 0.010
query_cpu: OFF
dist_wall: 0.000
dist_local: 0.000
dist_wait: 0.000
query_reads: OFF
query_readkb: OFF
query_readtime: OFF
avg_query_wall: 0.001
avg_query_cpu: OFF
avg_dist_wall: 0.000
avg_dist_local: 0.000
avg_dist_wait: 0.000
avg_query_reads: OFF
avg_query_readkb: OFF
avg_query_readtime: OFF
qcache_max_bytes: 16777216
qcache_thresh_msec: 3000
qcache_ttl_sec: 60
qcache_cached_queries: 0
qcache_used_bytes: 0
qcache_hits: 0
6.测试使用：mysql 客户端
[root@TiDB-node2 data]# mysql -uroot -predhat -h127.0.0.1 -P9306 -e "select id,k,c,pad from sbtest1 where match('03679578678')"
mysql: [Warning] Using a password on the command line interface can be insecure.
+------+----------+-------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------+
| id | k | c | pad |
+------+----------+-------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------+
| 1 | 15324329 | 64733237507-56788752464-03679578678-53343296505-31167207241-10603050901-64148678956-82738243332-73912678420-24566188603 | 78326593386-76411244360-77646817949-14319822046-41963083322 |
+------+----------+-------------------------------------------------------------------------------------------------------------------------+-------------------------------------------------------------+
7.python测试使用
#!/usr/bin/env python
#coding:utf-8
import pymysql
con = pymysql.connect(host='127.0.0.1', port=9306, user="", passwd="", db="")
with con.cursor(pymysql.cursors.DictCursor) as cur:
cur.execute("select * from sbtest1 where match('%03679578678%')")
print(cur.fetchall())
[root@TiDB-node2 ~]# python sphinx.py
[{u'c': '64733237507-56788752464-03679578678-53343296505-31167207241-10603050901-64148678956-82738243332-73912678420-24566188603', u'k': 15324329, u'pad': '78326593386-76411244360-77646817949-14319822046-41963083322', u'id': 1}]
8.表结构：
root@mysqldb 18:06: [sbtest]> show create table sbtest1 \G
*************************** 1. row ***************************
Table: sbtest1
Create Table: CREATE TABLE `sbtest1` (
`id` int(11) NOT NULL AUTO_INCREMENT,
`k` int(11) NOT NULL DEFAULT '0',
`c` char(120) NOT NULL DEFAULT '',
`pad` char(60) NOT NULL DEFAULT '',
PRIMARY KEY (`id`),
KEY `k_1` (`k`)
) ENGINE=InnoDB AUTO_INCREMENT=25000000 DEFAULT CHARSET=utf8mb4
测试环境中表sbtest1的数据有2500万行,测试sql是select * from sbtest1 where c like '%03679578678%'。在MySQL执行这个sql的时候由于使用不了索引只能进行全表扫描，花费了将近4分钟，但是在sphinx创建索引的时候也花费了70多秒的样子。在索引创建成功之后基本上面执行python脚本或者使用mysql客户端获取得到的花费基本是在毫秒级别的。性能提升了很多，并且sphinx和MySQL的在创建索引成功之后之间就没有链接了。并不会影响MySQL的操作，sphinx可以独立部署到一台服务器上面。
9.更新索引文件:增量更新索引文件
indexer --rotate test1
【Sphinx】MySQL+Sphinx 全文检索的使用和测试
原文地址：http://blog.51cto.com/11819159/2052167
