北京SEO

sphinx scws全文检索的安装配置步骤

2019/10/10/17:32:07  阅读:1834  来源:谷歌SEO算法  标签: 自学SEO

scws是一个由php做的免费的开源的中文分词系统了,支持 PHP 的扩展方式调用了,下面我们来看看scws全文检索的安装配置.

这次搭建的环境:centos 6.5 x86,php 5.3.3,mysql 5.5.8,三次搭建各不相同.

一,下载sphinx,scws相关包

sphinx下载地址:http://sphinxsearch.com/downloads/release/

sphinx php扩展下载地址:http://pecl.php.net/package/sphinx

scws下载地址:http://www.xunsearch.com/scws/download.php

scws词库下载地址:http://www.xunsearch.com/scws/down/scws-dict-chs-utf8.tar.bz2

二,安装sphinx,scws,以及php扩展

1,安装sphinx,代码如下:

  1. #tarzxvfsphinx-2.2.5-release.tar.gz
  2. #cdsphinx-2.2.5-release
  3. #./configure--prefix=/usr/local/sphinx2--with-mysql=/usr/local/mysql
  4. #make&&makeinstall

2,安装sphinx客户端,代码如下:

  1. #cdapi/libsphinxclient//sphinx-2.2.5-release目录下
  2. #./configure--prefix=/usr/local/sphinx2/libsphinxclient
  3. #make&&makeinstall

3,安装sphinx php扩展,代码如下:

  1. #tarzxvfsphinx-1.3.1.tgz
  2. #cdsphinx-1.3.1
  3. #phpize
  4. #./configure--with-sphinx=/usr/local/sphinx2/libsphinxclient--with-php-config=/usr/bin/php-config
  5. #make&&makeinstall

4,安装scws,代码如下:

  1. #tarxvjfscws-1.2.2.tar.bz2
  2. #mkdir/usr/local/scws
  3. #cdscws-1.2.2
  4. #./configure--prefix=/usr/local/scws/
  5. #make&&makeinstall

5,安装scws php扩展,代码如下:

  1. #cd./phpext/
  2. #phpize
  3. #./configure--with-php-config=/usr/bin/php-config
  4. #make&&makeinstall

三,配置sphinx,scws,php等.

1,创建测试表和数据,代码如下:

  1. mysql>descusers;
  2. +----------+-------------+------+-----+---------+----------------+
  3. |Field|Type|Null|Key|Default|Extra|
  4. +----------+-------------+------+-----+---------+----------------+
  5. |user_id|int(11)|NO|PRI|NULL|auto_increment|
  6. |username|varchar(20)|NO||NULL||
  7. +----------+-------------+------+-----+---------+----------------+
  8. 2rowsinset(0.00sec)
  9. mysql>select*fromusers;
  10. +------------+------------+
  11. |user_id|username|
  12. +------------+------------+
  13. |1311895262|张三|
  14. |1311895263|tank张二|
  15. |1311895264|tank张一|
  16. |1311895265|tank张|
  17. +------------+------------+
  18. 4rowsinset(0.00sec)
  19. mysql>descorders;
  20. +--------------+-------------+------+-----+---------+----------------+
  21. |Field|Type|Null|Key|Default|Extra|
  22. +--------------+-------------+------+-----+---------+----------------+
  23. |id|int(11)|NO|PRI|NULL|auto_increment|
  24. |user_id|int(11)|NO||NULL||
  25. |create_time|datetime|NO||NULL||
  26. |product_name|varchar(20)|NO||NULL||
  27. |summary|text|NO||NULL||
  28. +--------------+-------------+------+-----+---------+----------------+
  29. 5rowsinset(0.00sec)
  30. mysql>select*fromorders;
  31. +----+------------+---------------------+----------------+--------------+
  32. |id|user_id|create_time|product_name|summary|
  33. +----+------------+---------------------+----------------+--------------+
  34. |9|1311895262|2014-08-0100:24:54|tankis坦克|技术总监|
  35. |10|1311895263|2014-08-0100:24:54|tankis坦克|技术经理|
  36. |11|1311895264|2014-08-0100:24:54|tankis坦克|DNB经理|
  37. |12|1311895265|2014-08-0100:24:54|tankis坦克|运维总监|
  38. +----+------------+---------------------+----------------+--------------+
  39. 4rowsinset(0.00sec)

上面二张表,都是真实的mysql表.

2,配置sphinx.conf,加上以下内容,代码如下:

  1. sourcemyorder
  2. {
  3. type=mysql
  4. sql_host=localhost
  5. sql_user=root
  6. sql_pass=
  7. sql_db=test
  8. sql_query_pre=SETNAMESutf8
  9. sql_query_pre=SETSESSIONquery_cache_type=OFF
  10. sql_query=
  11. SELECTa.id,a.user_id,b.username,UNIX_TIMESTAMP(a.create_time)AScreate_time,a.product_name,a.summary
  12. FROMordersaleftjoinusersbona.user_id=b.user_id
  13. sql_attr_uint=user_id
  14. sql_field_string=username
  15. sql_field_string=product_name
  16. sql_attr_timestamp=create_time
  17. sql_ranged_throttle=0
  18. #sql_query_info=SELECT*FROMordersWHEREid=$id
  19. }
  20. indexmyorder
  21. {
  22. source=myorder
  23. path=/usr/local/sphinx2/var/data/myorder
  24. docinfo=extern
  25. mlock=0
  26. morphology=none
  27. min_word_len=1
  28. #charset_type=zh_cn.utf-8
  29. html_strip=1
  30. 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
  31. ngram_len=1
  32. 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
  33. }

注意:新的sphinx,不支持sql_query_info,charset_type设置了,代码如下:

  1. WARNING:key'sql_query_info'waspermanentlyremovedfromSphinxconfiguration.Refertodocumentationfordetails.
  2. WARNING:key'charset_type'waspermanentlyremovedfromSphinxconfiguration.Refertodocumentationfordetails.

3,安装scws词库,代码如下:

# tar xvjf scws-dict-chs-utf8.tar.bz2 -C /usr/local/scws/etc/

# chown tank:tank /usr/local/scws/etc/dict.utf8.xdb

在这里一定要加权限,也就是说让php-fpm或者php-cgi的运行用户,拥有dict.utf8.xdb的所有权限,如果不这么做的话,php 扩展调用词库会报如下错误:

Warning:SimpleCWS::add_dict(): Failed to add the dict file

怎么查看php-fpm,php-cgi的运行用户呢?代码如下:

  1. #psaux|grepphp-fpm
  2. root234870.00.12849284652?SsNov050:00php-fpm:masterprocess(/etc/php-fpm.conf)
  3. tank234880.01.333610852328?SNov050:02php-fpm:poolwww//在这里就是tank了
  4. tank234890.00.831048434028?SNov050:02php-fpm:poolwww
  5. tank234900.00.730662030156?SNov050:02php-fpm:poolwww
  6. tank234910.00.831009633748?SNov050:02php-fpm:poolwww
  7. tank234920.01.233181247712?SNov050:02php-fpm:poolwww
  8. tank246690.01.233352048896?SNov050:01php-fpm:poolwww
  9. tank297470.00.730500027340?S03:270:00php-fpm:poolwww
  10. tank297610.01.032053639928?S03:270:00php-fpm:poolwww
  11. root307050.00.0103260872pts/5S+04:110:00grepphp-fpm

4,配置php.ini,代码如下:

  1. #vim/etc/php.ini
  2. [sphinx]
  3. extension=sphinx.so
  4. [scws]
  5. extension=scws.so
  6. scws.default.charset=utf-8
  7. scws.default.fpath=/usr/local/scws/etc

四,启动sphinx,php-fpm,代码如下:

1,启动sphinx

  1. #/usr/local/sphinx2/bin/indexer--config/usr/local/sphinx2/etc/sphinx.conf--all
  2. #/usr/local/sphinx2/bin/searchd--config/usr/local/sphinx2/etc/sphinx.conf

2,重启php-fpm

# /etc/init.d/php-fpm restart

前二次,我安装sphinx,必须在mysql中安装sphinx存储插件,而这次没有.

五,测试sphinx全文检索

1,命令行的测试,代码如下:

  1. [root@localhostphpext]#mysql-h127.0.0.1-P9306
  2. WelcometotheMySQLmonitor.Commandsendwith;org.
  3. YourMySQLconnectionidis1
  4. Serverversion:2.2.5-id64-release(r4825)
  5. Copyright(c)2000,2013,Oracleand/oritsaffiliates.Allrightsreserved.
  6. OracleisaregisteredtrademarkofOracleCorporationand/orits
  7. affiliates.Othernamesmaybetrademarksoftheirrespective
  8. owners.
  9. Type'help;'or'h'forhelp.Type'c'toclearthecurrentinputstatement.
  10. mysql>select*frommyorderwherematch('张');
  11. +------+------------+------------+-------------+----------------+
  12. |id|user_id|username|create_time|product_name|
  13. +------+------------+------------+-------------+----------------+
  14. |9|1311895262|张三|1406823894|tankis坦克|
  15. |10|1311895263|tank张二|1406823894|tankis坦克|
  16. |11|1311895264|tank张一|1406823894|tankis坦克|
  17. |12|1311895265|tank张|1406823894|tankis坦克|
  18. +------+------------+------------+-------------+----------------+
  19. 4rowsinset(0.00sec)

2,利用php 扩展,代码如下:

  1. <?php
  2. header("Content-type:text/html;charset=utf-8");
  3. $b_time=microtime(true);
  4. echo'<p>'.$b_time.'</p>';
  5. $key="张三";
  6. $index="myorder";
  7. //========================================分词
  8. $so=scws_new();
  9. $so->set_charset('utf-8');
  10. //默认词库
  11. $so->add_dict(ini_get('scws.default.fpath').'/dict.utf8.xdb');
  12. //自定义词库
  13. //$so->add_dict('./dd.txt',SCWS_XDICT_TXT);
  14. //默认规则
  15. $so->set_rule(ini_get('scws.default.fpath').'/rules.utf8.ini');
  16. //设定分词返回结果时是否去除一些特殊的标点符号
  17. $so->set_ignore(true);
  18. //设定分词返回结果时是否复式分割,如“中国人”返回“中国+人+中国人”三个词。
  19. //按位异或的1|2|4|8分别表示:短词|二元|主要单字|所有单字
  20. //1,2,4,8分别对应常量SCWS_MULTI_SHORTSCWS_MULTI_DUALITYSCWS_MULTI_ZMAINSCWS_MULTI_ZALL
  21. $so->set_multi(false);
  22. //设定是否将闲散文字自动以二字分词法聚合
  23. $so->set_duality(false);
  24. //设定搜索词
  25. $so->send_text($key);
  26. $words_array=$so->get_result();
  27. $words="";
  28. foreach($words_arrayas$v)
  29. {
  30. $words=$words.'|('.$v['word'].')';
  31. }
  32. //加入全词
  33. #$words='('.$key.')'.$words;
  34. $words=trim($words,'|');
  35. $so->close();
  36. echo'<p>输入:'.$key.'</p>';
  37. echo'<p>分词:'.$words.'</p>';
  38. //========================================搜索
  39. $sc=newSphinxClient();
  40. $sc->SetServer('127.0.0.1',9312);
  41. #$sc->SetMatchMode(SPH_MATCH_ALL);
  42. $sc->SetMatchMode(SPH_MATCH_EXTENDED);
  43. $sc->SetArrayResult(TRUE);
  44. $res=$sc->Query($words,$index);
  45. print_r($res);
  46. $e_time=microtime(true);
  47. $time=$e_time-$b_time;
  48. echo'<p>'.$e_time.'</p>';
  49. echo'<p>'.$time.'</p>';
  50. exit;
  51. ?>
  52. 结果如下:
  53. <p>1415214126.9106</p><p>输入:张三</p><p>分词:(张三)</p>Array
  54. (
  55. [error]=>
  56. [warning]=>
  57. [status]=>0
  58. [fields]=>Array
  59. (
  60. [0]=>username
  61. [1]=>product_name
  62. [2]=>summary
  63. )
  64. [attrs]=>Array
  65. (
  66. [user_id]=>1
  67. [username]=>7
  68. [create_time]=>2
  69. [product_name]=>7
  70. )
  71. [matches]=>Array
  72. (
  73. [0]=>Array
  74. (
  75. [id]=>9
  76. [weight]=>2500
  77. [attrs]=>Array
  78. (
  79. [user_id]=>1311895262
  80. [username]=>张三
  81. [create_time]=>1406823894
  82. [product_name]=>tankis坦克
  83. )
  84. )
  85. )
  86. [total]=>1
  87. [total_found]=>1
  88. [time]=>0
  89. [words]=>Array
  90. (
  91. [张]=>Array
  92. (
  93. [docs]=>4
  94. [hits]=>4
  95. )
  96. [三]=>Array
  97. (
  98. [docs]=>1
  99. [hits]=>1
  100. )
  101. )
  102. )
  103. <p>1415214126.9516</p><p>0.041085958480835</p>

广告内容

sphinx scws全文检索的安装配置步骤 sphinx scws全文检索的安装配置步骤 sphinx scws全文检索的安装配置步骤

相关阅读

热门评论

精选文章

RMAN中catalog和nocatalog区别介绍 小技巧:为Linux下的文件分配多个权限 zimbra8.5.1安装第三方签名ssl证书的步骤 解决mysql不能远程连接数据库方法 windows服务器mysql增量备份批处理数据库 mysql中slow query log慢日志查询分析 JavaScript跨域问题总结 Linux下负载均衡软件LVS配置(VS/DR)教程 mysql中权限参数说明 MYSQL(错误1053)无法正常启动

SEO最新算法