sphinx php搜索引擎,sphinx 全文搜索引擎

sphinx 全文搜索引擎：顾名思义，是做收索用的，因为普通的搜索在数据量小的时候，能应对自如，但是当数据量上千万，或者上亿的时候。纯粹的sql搜索显得缓慢，无力。因而为了提高用户体验，增快用户的搜索速度，出现了sphinx 。简单的例子比如大型网站的首页搜索。

1.安装须知

Coreseek发布了3.2.14版本和4.1版本等多个版本

3.2.14版本是2010年发布的，它是基于Sphinx0.9.9搜索引擎的。4.1版本是2011年发布的

，它是基于Sphinx2.0.2以后的

2.使用sphinx需要的工作

1.检查中文环境语言

2.升级依赖包

3.下载并安装mmseg(coreseek所需要的词典)

4.安装coreseek的csf-3.2-14(也就是sphinx)

5.安装配置sphinx并运行生成相应的索引

6.启动sphinx，php文件调用sphinx服务即可

7.配置php支持sphinx (或者引用sphinx类直接调用sphinx也行)

注意事项：①、采用API调用，如使用PHP、java等的API函数或方法查询。优点是可不必对mysql重新编译，服务端进程“低耦合”，且程序可灵活、方便的调用；需要二次查询。

二次查询注：到现在发布版本为止——sphinx-0.9.9，sphinx在检索到结果后只能返回记录的ID，而非要查的sql数据，故需要重新根据这些ID再次从数据库中查询，

3.检查环境语言

[root@localhost ~]# locale

LANG=en_US.UTF-8

LC_CTYPE="en_US.UTF-8"

LC_NUMERIC="en_US.UTF-8"

LC_TIME="en_US.UTF-8"

LC_COLLATE="en_US.UTF-8"

LC_MONETARY="en_US.UTF-8"

LC_MESSAGES="en_US.UTF-8"

LC_PAPER="en_US.UTF-8"

LC_NAME="en_US.UTF-8"

LC_ADDRESS="en_US.UTF-8"

LC_TELEPHONE="en_US.UTF-8"

LC_MEASUREMENT="en_US.UTF-8"

LC_IDENTIFICATION="en_US.UTF-8"

#如上显示英文的(如果是中文的直接进行下一步)

LANG=en_US.UTF-8

LC = en_US.UTF-8

#要配置成中文的

export LANG=zh_CN.UTF-8

export LC_ALL=zh_CN.UTF-8

#运行之后

[root@localhost ~]# export LANG=zh_CN.UTF-8

[root@localhost ~]# export LC_ALL=zh_CN.UTF-8

[root@localhost ~]# locale

LANG=zh_CN.UTF-8

LC_CTYPE="zh_CN.UTF-8"

LC_NUMERIC="zh_CN.UTF-8"

LC_TIME="zh_CN.UTF-8"

LC_COLLATE="zh_CN.UTF-8"

LC_MONETARY="zh_CN.UTF-8"

LC_MESSAGES="zh_CN.UTF-8"

LC_PAPER="zh_CN.UTF-8"

LC_NAME="zh_CN.UTF-8"

LC_ADDRESS="zh_CN.UTF-8"

LC_TELEPHONE="zh_CN.UTF-8"

LC_MEASUREMENT="zh_CN.UTF-8"

LC_IDENTIFICATION="zh_CN.UTF-8"

LC_ALL=zh_CN.UTF-8

4升级依赖包

yum -y install glibc-common libtool autoconf automake mysql-devel expat-devel

# 手动升级 autoconf

tar -zxvf autoconf-2.69.tar.gz

cd autoconf-2.69

./configure

make

make install

5.安装coreseek的mmseg

tar -zxvf coreseek-3.2.13.tar.gz

cd coreseek-3.2.13

cd mmseg-3.2.13/

./bootstrap #输出的warning信息可以忽略，如果出现error则需要解决

./configure --prefix=/usr/local/mmseg3

make

make install

# 检测是否安装完成

mmseg

提示：-bash: mmseg: command not found

# 问题解决方法

ln -s /usr/local/mmseg3/bin/mmseg /bin/mmseg

#

mmseg

# 显示以下内容表示安装成功

Coreseek COS(tm) MM Segment 1.0

Copyright By Coreseek.com All Right Reserved.

Usage: mmseg

-u Unigram Dictionary

-r Combine with -u, used a plain text build Unigram Dictionary, default Off

-b Synonyms Dictionary

-t Thesaurus Dictionary

-h print this help and exit

安装csf-3.2-14

cd csft-3.2.13/

sh buildconf.sh #输出的warning信息可以忽略，如果出现error则需要解决

./configure \

--prefix=/usr/local/sphinx \

--without-unixodbc \

--with-mmseg \

--with-mmseg-includes=/usr/local/mmseg3/include/mmseg/ \

--with-mmseg-libs=/usr/local/mmseg3/lib/ \

--with-mysql=/usr/local/mysql/ \

make

make install

#./configure --prefix=/usr/local/sphinx/ --with-mysql=/usr/local/mysql/ --enable-id64

make

make install

# 注意1：采用这种方式安装不支持中文分词。

# 注意2：--enable-id64 系统是64位，开启后Sphinx存储模块可以支持4-5G,不开启支持2G左右，不开启检索效率会高些，一般情况下建议不开启

# 错误：

collect2: ld 返回 1

make[2]: *** [indexer] 错误 1

# 修改configure文件中：

LIBS="$LIBS -L/usr/local/lib"

# 改为：

LIBS="$LIBS -liconv -L/usr/local/lib"

6.再测试下mmseg分词和coreseek搜索

cd testpack

cat var/test/test.xml #此时应该正确显示中文

/usr/local/mmseg3/bin/mmseg -d /usr/local/mmseg3/etc var/test/test.xml

/usr/local/sphinx/bin/indexer -c etc/csft.conf --all

/usr/local/sphinx/bin/search -c etc/csft.conf 网络搜索

此时正确的应该返回

words:

1. '网络': 1 documents, 1 hits

2. '搜索': 2 documents, 5 hits

3.sphinx.conf配置文件

[root@localhost ~]#cd /usr/local/sphinx/etc #进入sphinx的配置文件目录

[root@localhost etc]# cp sphinx.conf.dist sphinx.conf #新建Sphinx配置文件

[root@localhost etc]# vim sphinx.conf #编辑sphinx.conf

##### 索引源 ###########

source userinfo

{

type = mysql

sql_host = localhost

sql_user = root

sql_pass = 123456

sql_db = zb3_zhibo

sql_port = 3306

sql_query_pre= SET NAMES utf8

sql_query = SELECT userid,username,passwd,phone,ctime FROM live_userinfo_base

}

### 索引 ###

index info

{

source = userinfo

path = /usr/local/sphinx/var/data/info #######索引文件存放路径及索引的文件名

docinfo = extern

mlock = 0

stopwords =

min_prefix_len = 0

min_infix_len = 0

morphology = none

min_word_len = 2

charset_type = zh_cn.utf-8

charset_dictpath =/usr/local/mmseg3/etc/

#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

html_strip = 0

}

######### 索引器配置 #####

indexer

{

mem_limit = 256M ####### 内存限制

}

searchd

{

port = 9312

read_timeout = 5

max_children = 10

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

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

max_matches = 1000

seamless_rotate = 1

}

客户端测试

$times1 = microtime() ;

//csf-3.1.4中有testpack里面有相应的类包

require ( "sphinxapi.php" );

$sphinx_api = new SphinxClient('172.20.17.110', 9312);

$sphinx_api->SetArrayResult(true);

$sphinx_api->SetMatchMode(SPH_MATCH_ANY);

# 开始查询

$res = $sphinx_api->Query('老师', 'info');

if(!$res)

{

$error = $sphinx_api->GetLastError();

var_dump($error);

exit;

}

// echo '

';

// print_r($res['matches']);

$coon = @mysql_connect('172.20.17.110','root','123456');

@mysql_query("SET NAMES UTF8");

@mysql_select_db('zb3_zhibo',$coon);

$array = array();

foreach($res['matches'] as $key => $val){

$sql = "select userid,username from live_userinfo_base where userid=".$val['id'];

$res = mysql_query($sql,$coon);

$re = mysql_fetch_array($res);

// echo '

';

// print_r($re);

// exit;

$array[] =$re;

}

$times2 = microtime();

echo $times2-$times1;

4.sphinx命令

建立索引：./indexer -c etc/sphinx.conf --all ### 建立索引(article )文件的命令

启动服务： ./searchd -c /usr/location/sphinx/etc/sphinx.conf

停止服务： pkill -9 search