記一次安裝sphinx+scws+mysql+php

一、安裝前提必備先安裝工具

注意gcc版本一定是>4.8

yum -y install make gcc g++ gcc-c++ libtool autoconf automake imake mysql-devel libxml2-devel expat-devel

二、下載安裝sphinx

2.2版本的sphinx需要進行編譯安裝, 3.0版本的sphinx則不需要進行編譯安裝直接使用

#創建文件夾
mkdir /usr/local/sphinx
#進入下載文件夾
ce /usr/local/src
#下載文件
wget http://sphinxsearch.com/files/sphinx-3.0.3-facc3fb-linux-amd64.tar.gz
#解壓縮
tar -zxvf sphinx-3.0.3-facc3fb-linux-amd64.tar.gz
#打開文件夾
cd sphinx-3.0.3

錯誤描述

/usr/local/sphinx/src/sphinx.cpp:20060:undefined reference to `libiconv_open'
/usr/local/sphinx/src/sphinx.cpp:20078: undefined reference to `libiconv'
/usr/local/sphinx/src/sphinx.cpp:20084: undefined reference to `libiconv_close'
collect2: ld returned 1exit status
make[2]:***[indexer]Error1
make[2]:Leaving directory `/home/sphinx/src'
make[1]: *** [all] Error 2
make[1]: Leaving directory `/home/sphinx/src'
make: *** [all-recursive] Error 1

解決辦法:打開configure文件,找到“#define USE_LIBICONV 1”,將註釋去掉,並將1改成0。

三、安裝libsphinxclient客戶端來供PHP使用

cd /api/libsphinxclient
./configure --prefix=/usr/local/sphinx
make
make install

如果安裝過程中出現 memcpy 的錯誤,則在test.c中增加

#include<string.php>

如果出現 const char ** 類型的錯誤,則將test.c中將所有的const char * docs[] 更改爲char * docs

sphinxclient.csphinx_build_excerpts函數中const char docs 改爲char docs
sphinxclient.hsphinx_build_excerpts函數中const char docs 改爲char docs

四、安裝PHP sphinx擴展

wget http://pecl.php.net/get/sphinx-1.3.3.tgz

tar -zxvf sphinx-1.3.3.tgz
cd sphinx-1.3.3
phpize
./configure --with-php-config=/usr/bin/php-config --with-sphinx=/usr/local/sphinx
make
make install

五、安裝scws

http://www.xunsearch.com

wget http://www.xunsearch.com/scws/down/scws-1.2.3.tar.bz2
bzip2 -d scws-1.2.3.tar.bz2
tar -xvf scws-dict-chs-gbk.tar
cd scws-1.2.3
./configure --prefix=/usr/local/scws
make
make install

六、安裝scws php擴展

在上一步解壓的scws文件夾中
cd phpext
phpize
./configure --with-php-config=/usr/bin/php-config --with-scws=/usr/local/soft/scws
make 
make install

七、安裝scws詞典

wget http://www.xunsearch.com/scws/down/scws-dict-chs-gbk.tar.bz2
bzip2 -d scws-dict-chs-gbk.tar.bz2
tar -xvf scws-dict-chs-gbk.tar
cp dict.xdb /usr/local/scws/etc

八、配置sphinx

其中searchd 以下3個配置比較重要。mysql -h 127.0.0.1 -P 9306訪問。9312可以給php訪問。query_log_format 記錄日誌的格式。

1 # php listen = 9312

2 # mysql listen = 9306:mysql41

3 # log_format

query_log_format = sphinxql

# vim /usr/local/sphinx2/etc/sphinx.conf
source users
{
	type			= mysql
	sql_host		= 127.0.0.1
	sql_user		= root
	sql_pass		= 123456
	sql_db			= test
	sql_port		= 3306	# optional, default is 3306
	sql_query_pre = SET NAMES utf8 
        sql_query_pre = SET SESSION query_cache_type=OFF  
        sql_query = 	SELECT a.id, a.userid,b.username, UNIX_TIMESTAMP(a.addtime) AS addtime, a.post, a.summary 	FROM userinfo a left join users b on a.userid = b.id  
	sql_attr_uint = userid  
	sql_field_string = username  
	sql_field_string = post  
	sql_attr_timestamp = addtime
	sql_ranged_throttle = 0  
	#sql_attr_uint		= group_id
	#sql_attr_timestamp	= date_added
	#sql_ranged_throttle	= 0
}
source src1throttled : users 
{
	sql_ranged_throttle	= 100
}

index users 
{  
	source = users 
	path = /usr/local/sphinx2/var/data/users 
	docinfo = extern  
	mlock = 0  
	morphology = none  
	min_word_len = 1  
	html_strip = 1  
	
	#charset_table非常重要
	
	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  
	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  
}
common
{
}
indexer
{
	mem_limit		= 128M
}
searchd
{
	
	#php
	listen          = 9312
	
	#mysql
    listen          = 9306:mysql41
	
	log			= /usr/local/sphinx2/var/log/searchd.log
	query_log		= /usr/local/sphinx2/var/log/query.log
	query_log_format = sphinxql
	read_timeout		= 5
	client_timeout		= 300
	max_children		= 30
	persistent_connections_limit	= 30
	pid_file		= /usr/local/sphinx2/var/log/searchd.pid
	seamless_rotate		= 1
	preopen_indexes		= 1
	unlink_old		= 1
	mva_updates_pool	= 1M
	max_packet_size		= 8M
	max_filters		= 256
	max_filter_values	= 4096
	max_batch_queries	= 32
	workers			= threads # for RT to work
}

九、配置php.ini

# vim /etc/php.ini 

添加

[sphinx]  
extension = sphinx.so  
  
[scws]  
extension = scws.so  
scws.default.charset = utf-8  
scws.default.fpath = /usr/local/scws/etc  

十、開啓sphinx

# pkill searchd
# /usr/local/sphinx2/bin/indexer --config /usr/local/sphinx2/etc/sphinx.conf --all  
# /usr/local/sphinx2/bin/searchd --config /usr/local/sphinx2/etc/sphinx.conf
如果報錯libmysqlclient.so.18。
ln -s /usr/local/mysql/lib/libmysqlclient.so.18 /usr/lib/libmysqlclient.so.18 #32機器
ln -s /usr/local/mysql/lib/libmysqlclient.so.18 /usr/lib64/libmysqlclient.so.18 #64位機器

十一、PHP測試

<?php
 header("Content-type: text/html; charset=utf-8");
 $b_time = microtime(true);
 $key = "洪荒之力";
 $index = "users";
 //========================================分詞

 $so = scws_new();
 $so->set_charset('utf-8');
 //默認詞庫
 $so->add_dict(ini_get('scws.default.fpath') . '/dict.utf8.xdb');
 //自定義詞庫
// $so->add_dict('./dd.txt',SCWS_XDICT_TXT);
 //默認規則
 $so->set_rule(ini_get('scws.default.fpath') . '/rules.utf8.ini');

 //設定分詞返回結果時是否去除一些特殊的標點符號
 $so->set_ignore(true);

 //設定分詞返回結果時是否複式分割,如“中國人”返回“中國+人+中國人”三個詞。
 // 按位異或的 1 | 2 | 4 | 8 分別表示: 短詞 | 二元 | 主要單字 | 所有單字
 //1,2,4,8 分別對應常量 SCWS_MULTI_SHORT SCWS_MULTI_DUALITY SCWS_MULTI_ZMAIN SCWS_MULTI_ZALL
 $so->set_multi(false);

 //設定是否將閒散文字自動以二字分詞法聚合
 $so->set_duality(false);

 //設定搜索詞
 $so->send_text($key);
 $words_array = $so->get_result();
 $words = "";
 foreach($words_array as $v)
 {
 $words = $words.'|('.$v['word'].')';
 }

 //加入全詞
 #$words = '('.$key.')'.$words;
 $words = trim($words,'|');
 $so->close();
 echo '<p>輸入:'.$key.'</p>'."\r\n";
 echo '<p>分詞:'.$words.'</p>'."\r\n";
//========================================搜索
 $sc = new SphinxClient();
 $sc->SetServer('127.0.0.1',9312);
 #$sc->SetMatchMode(SPH_MATCH_ALL);
 $sc->SetMatchMode(SPH_MATCH_EXTENDED);
 $sc->SetArrayResult(TRUE);
 $res = $sc->Query($words,$index);
 print_r($res);
 $e_time = microtime(true);
 $time = $e_time - $b_time;
 exit;
?>

發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章