sphinx+MySQL的安装使用 [转]

sphinx-0.9.8-rc2-chinese.zip可以去http://www.s135.com/read.php/360.htm下
unzip sphinx-0.9.8-rc2-chinese.zip
tar zxvf mmseg-0.7.3.tar.gz
cd mmseg-0.7.3/
./configure
make
make install
cd ../

tar zxvf mysql-5.1.26-rc.tar.gz

tar zxvf sphinx-0.9.8-rc2.tar.gz
cd sphinx-0.9.8-rc2/
patch -p1 < ../sphinx-0.98rc2.zhcn-support.patch
patch -p1 < ../fix-crash-in-excerpts.patch
cp -rf mysqlse ../mysql-5.1.26-rc/storage/sphinx
cd ../

cd mysql-5.1.26-rc/
sh BUILD/autorun.sh
./configure –with-plugins=sphinx –prefix=/usr/local/mysql1/ –enable-assembler –with-extra-charsets=complex –enable-thread-safe-client –with-big-tables –with-readline –with-ssl –with-embedded-server –enable-local-infile
make && make install
cd ../
检查下是否安装好sphinx    show engines; 有个sphinx引擎

cd sphinx-0.9.8-rc2/
CPPFLAGS=-I/usr/include/python2.4
LDFLAGS=-lpython2.4
./configure –prefix=/usr/local/sphinx –with-mysql=/usr/local/mysql1
make
make install
cd ../
cp /usr/local/sphinx/etc/sphinx.conf.dist /usr/local/sphinx/etc/sphinx.conf

进入mysql
mysql>source /usr/local/sphinx/etc/example.sql;
假如要插入中文的要在my.cnf中加default_character_set=utf8重启服务就可以了
set names utf8;显示出中文 有关字符集以后有一个专题

配置sphinx vim /usr/local/sphinx/etc/sphinx.conf
source src1
{
type                    = mysql

sql_host                = localhost
sql_user                = root
sql_pass                =123
sql_db                    = test
sql_port                = 3307    # optional, default is 3306
sql_sock                = /usr/local/mysql1/var/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_ranged_throttle    = 0
sql_query_info        = SELECT * FROM documents WHERE id=$id
}
index test1
{
source            = src1
path            = /usr/local/sphinx/var/data/test1
docinfo            = extern
mlock            = 0
morphology        = none
min_word_len        = 1
charset_type        = utf-8
charset_table = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6,\
U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101,\
U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109,\
U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F,\
U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, \
U+0116->U+0117,U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D,\
U+011D,U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, \
U+0134->U+0135,U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, \
U+013C,U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, \
U+0143->U+0144,U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, \
U+014B,U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, \
U+0152->U+0153,U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159,\
U+0159,U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, \
U+0160->U+0161,U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, \
U+0167,U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, \
U+016E->U+016F,U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175,\
U+0175,U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, \
U+017B->U+017C,U+017C, U+017D->U+017E, U+017E, U+0410..U+042F->U+0430..U+044F, \
U+0430..U+044F,U+05D0..U+05EA, U+0531..U+0556->U+0561..U+0586, U+0561..U+0587, \
U+0621..U+063A, U+01B9,U+01BF, U+0640..U+064A, U+0660..U+0669, U+066E, U+066F, \
U+0671..U+06D3, U+06F0..U+06FF,U+0904..U+0939, U+0958..U+095F, U+0960..U+0963, \
U+0966..U+096F, U+097B..U+097F,U+0985..U+09B9, U+09CE, U+09DC..U+09E3, U+09E6..U+09EF, \
U+0A05..U+0A39, U+0A59..U+0A5E,U+0A66..U+0A6F, U+0A85..U+0AB9, U+0AE0..U+0AE3, \
U+0AE6..U+0AEF, U+0B05..U+0B39,U+0B5C..U+0B61, U+0B66..U+0B6F, U+0B71, U+0B85..U+0BB9, \
U+0BE6..U+0BF2, U+0C05..U+0C39,U+0C66..U+0C6F, U+0C85..U+0CB9, U+0CDE..U+0CE3, \
U+0CE6..U+0CEF, U+0D05..U+0D39, U+0D60,U+0D61, U+0D66..U+0D6F, U+0D85..U+0DC6, \
U+1900..U+1938, U+1946..U+194F, U+A800..U+A805,U+A807..U+A822, U+0386->U+03B1, \
U+03AC->U+03B1, U+0388->U+03B5, U+03AD->U+03B5,U+0389->U+03B7, U+03AE->U+03B7, \
U+038A->U+03B9, U+0390->U+03B9, U+03AA->U+03B9,U+03AF->U+03B9, U+03CA->U+03B9, \
U+038C->U+03BF, U+03CC->U+03BF, U+038E->U+03C5,U+03AB->U+03C5, U+03B0->U+03C5, \
U+03CB->U+03C5, U+03CD->U+03C5, U+038F->U+03C9,U+03CE->U+03C9, U+03C2->U+03C3, \
U+0391..U+03A1->U+03B1..U+03C1,U+03A3..U+03A9->U+03C3..U+03C9, U+03B1..U+03C1, \
U+03C3..U+03C9, U+0E01..U+0E2E,U+0E30..U+0E3A, U+0E40..U+0E45, U+0E47, U+0E50..U+0E59, \
U+A000..U+A48F, U+4E00..U+9FBF,U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF, \
U+2F800..U+2FA1F, U+2E80..U+2EFF,U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF, \
U+3040..U+309F, U+30A0..U+30FF,U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF, \
U+3130..U+318F, U+A000..U+A48F,U+A490..U+A4CF

min_prefix_len    = 0
min_infix_len        = 1
ngram_len                = 1
ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,\
U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,\
U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,\
U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF

html_strip                = 0

}

indexer
{
mem_limit            = 32M

}
searchd
{
port                = 3312

log                    = /usr/local/sphinx/var/log/searchd.log

query_log            = /usr/local/sphinx/var/log/query.log

read_timeout        = 5

max_children        = 30

pid_file            = /usr/local/sphinx/var/log/searchd.pid

max_matches            = 1000

seamless_rotate        = 1

preopen_indexes        = 0
unlink_old            = 1
}
Source部分配置项说明

#type 数据库类型,目前支持mysql与pgsql
#strip_html 是否去掉html标签
#sql_host 数据库主机地址
#sql_user 数据库用户名
#sql_pass 数据库密码
#sql_db   数据库名称
#sql_port 数据库采用的端口
#sql_query_pre 执行sql前要设置的字符集,用utf8必须SET NAMES utf8
#sql_query  全文检索要显示的内容,在这里尽可能不使用where或group by,将where与groupby的内容交给sphinx,由sphinx进行条件过滤与groupby效率会更高
#注意:select 出来的字段必须至少包括一个唯一主键(ARTICLESID)以及要全文检索的字段,你计划原本在where中要用到的字段也要select出来
#这里不用使用orderby
#sql_attr_开头的表示一些属性字段,你原计划要用在where,orderby,groupby中的字段要在这里定义
#根据我们原先的SQL:
#select * from eht_articles where title like ? and catalogid=? And edituserid=?  And addtime between ? and ? order by hits desc
#我们需要对catalogid,edituserid,addtime,hits进行属性定义(这四个字段也要在select的字段列表中),定义时不同的字段类型有不同的属性名称,具体可以见sphinx.conf.in中的说明

index部分配置项说明

#source 数据源名
#path   索引记录存放目录,如d:/sphinx/data/cgfinal,实际存放时会存放在d:/sphinx/data目录,然后创建多个cgfinal名称,不同扩展名的索引文件。
#其他的配置如min_word_len,charset_type,charset_table,ngrams_chars,ngram_len这些则是支持中文检索需要设置的内容。
#如果检索的不是中文,则charset_table,ngrams_chars,min_word_len就要设置不同的内容,具体官方网站的论坛中有很多,大家可以去搜索看看。

具体的参数设置可以参考http://www.sphinxsearch.com/doc.html#searching

创建索引
./usr/local/sphinx/bin/indexer test1

启动sphinx守护进程

./usr/local/sphinx/bin/searchd

CREATE TABLE `sphinx` (
`id` int(11) NOT NULL,
`weight` int(11) NOT NULL,
`query` varchar(255) NOT NULL,
`group_id` int(11) NOT NULL,
`group_id2` int(11) NOT NULL,
`title` varchar(255) NOT NULL,
KEY `Query` (`Query`)
) ENGINE=SPHINX CONNECTION=’sphinx://localhost:3312/test1′;

select content,date_added from test.documents docs join sphinx on (docs.id=sphinx.id) where query=’one document;mode=any’;

假如原来的表更新以后这个搜索引擎就不能搜到新的数据,因为他的索引没有及时创建。假如想要得到更新后的数据,需要从创建索引开始

以上要对原来的mysql要重新编译安装很是麻烦,但它提供了sphinx引擎使用起来非常方便。在网上找了半天也没有找到这个引擎的插件,很是郁闷。

可以通过sphinx自己的搜索来查看结果

./usr/local/sphinx/bin/search test

能够搜出中文 就是显示是乱码

发表评论

电子邮件地址不会被公开。 必填项已用 * 标注


*

您可以使用这些 HTML 标签和属性: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>