全文索引大体分为两个过程:
yum install make gcc gcc-c++ libtool autoconf automake imake mysql-devel libxml2-devel expat-devel
[root@localhost.localdomain /usr/local/src]
# wget http://www.coreseek.cn/uploads/csft/3.2/coreseek-3.2.14.tar.gz
[root@localhost.localdomain /usr/local/src]
# tar xf coreseek-3.2.14.tar.gz
[root@localhost.localdomain /usr/local/src]
# cd coreseek-3.2.14
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14]
# ls
csft-3.2.14(sphinx) mmseg-3.2.14 README.txt testpack
其中-- csft-4.1是修改适应了中文环境后的sphinx
Mmseg 是中文分词插件
Testpack是测试用的软件包
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14]
# cd mmseg-3.2.14/
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/mmseg-3.2.14]
# ./bootstrap
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/mmseg-3.2.14]
# ./configure --prefix=/usr/local/mmseg
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/mmseg-3.2.14]
# make && make install
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/csft-3.2.14]
# ./buildconf.sh
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/csft-3.2.14]
# ./configure --prefix=/usr/local/coreseek --without-unixodbc --with-mmseg --with-mmseg-includes=/usr/local/mmseg/include/mmseg/ --with-mmseg-libs=/usr/local/mmseg/lib/ --with-mysql
[root@localhost.localdomain /usr/local/src/coreseek-3.2.14/csft-3.2.14]
# make && make install
- 数据源---要让sphinx知道,查哪些数据,即针对哪些数据做索引(可以定义多个源)
- 索引配置---针对哪个源做索引, 索引文件放在哪个目录?? 等等
- 搜索服务器---sphinx可以在某个端口(默认9312),以其自身的协议,与外部程序做交互.
配置数据源
[root@localhost.localdomain /usr/local/coreseek/etc]
# cp sphinx.conf.dist sphinx.conf
[root@localhost.localdomain /usr/local/coreseek/etc]
# vim sphinx.conf
如下配置:
source src1 {
type = mysql
sql_host = localhost
sql_user = root
sql_pass = aaaaaa
sql_db = test
sql_query_pre = set names utf8
sql_query_pre = set session query_cache_type=off
sql_query = `select a_id as id,cat_id,title,simtitle,seotitle,tags,source,description,content,dateline,editdateline from article`
sql_attr_uint = a_id
sql_attr_uint = cat_id
sql_attr_timestamp = dateline
sql_attr_timestamp = editdateline
sql_query_info = `SELECT * FROM article WHERE a_id=$id`
}
索引典型配置
> index test1 {
> source = test
> path = /usr/local/sphinx/var/data/test1 # 生成索引放在哪
> # stopwords = G:\data\stopwords.txt
> # wordforms = G:\data\wordforms.txt
> # exceptions = /data/exceptions.txt
> charset_dictpath = /usr/local/mmseg/etc/
> charset_type = zh_cn.utf-8
> }
生成索引文件
[root@localhost.localdomain /usr/local/coreseek/etc]
# /usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/sphinx.conf test1 (test1为索引名称)
Coreseek Fulltext 3.2 [ Sphinx 0.9.9-release (r2117)]
Copyright (c) 2007-2011,
Beijing Choice Software Technologies Inc (http://www.coreseek.com)
using config file '/usr/local/coreseek/etc/sphinx.conf'...
indexing index 'test1'...
collected 8122 docs, 47.6 MB
sorted 8.7 Mhits, 100.0% done
total 8122 docs, 47596333 bytes
total 17.782 sec, 2676636 bytes/sec, 456.75 docs/sec
total 5 reads, 0.011 sec, 4559.8 kb/call avg, 2.3 msec/call avg
total 58 writes, 0.429 sec, 903.8 kb/call avg, 7.3 msec/call avg
Error 注意:
/usr/local/coreseek/bin/indexer: error while loading shared libraries: libmysqlclient.so.18: cannot open shared object file: No such file or directory
发现sphinx的indexer
依赖库ibmysqlclient.so.18
找不到,通过编辑此文件来修复这个错误/etc/ld.so.conf
vi /etc/ld.so.conf
将下面这句加到文件到尾部,并保存文件/usr/local/mysql/lib
然后运行下面这个命令即可ldconfig
在命令行测试查询
[root@localhost.localdomain /usr/local/coreseek]
# ./bin/search -c etc/sphinx.conf 留学
```
内容来源于网络,如有侵权,请联系作者删除!