標籤:
1 安裝之前先安裝php,mysql
php5.5.29安裝:http://blog.csdn.net/clevercode/article/details/52198698。
mysql-5.5.27:http://blog.csdn.net/clevercode/article/details/45499231。
2 下載
2.1 本次安裝的資源套件,設定檔,測試檔案
http://download.csdn.net/detail/clevercode/9602949。
2.2 其它
sphinx:http://sphinxsearch.com/downloads/release/
sphinx php擴充:http://pecl.php.net/package/sphinx
scws:http://www.xunsearch.com/scws/download.php
scws詞庫:http://www.xunsearch.com/scws/down/scws-dict-chs-utf8.tar.bz2
3 其它參考資料
《sphinx scws 全文檢索索引 安裝 配置 詳解》:http://blog.51yip.com/mysql/1659.html。
《PHP基於Sphinx+Swcs中文分詞的全文的檢索》:http://www.bubuko.com/infodetail-1024880.html。
《sphinx倒排表介紹("sph", "spa", "spi", "spd", "spp", "spm")》:http://blog.csdn.net/todaylxp/article/details/4269223。
《sphinx 設定檔全解析》:http://www.cnblogs.com/yjf512/p/3598332.html。
4 安裝
4.1 安裝sphinx
# mkdir -p /usr/local/src/sphinx# cd /usr/local/src/sphinx # tar zxvf sphinx-2.2.5-release.tar.gz # cd sphinx-2.2.5-release # ./configure --prefix=/usr/local/sphinx2 --with-mysql=/usr/local/mysql # make && make install
4.2 安裝sphinx用戶端
# cd /usr/local/src/sphinx/sphinx-2.2.5-release/api/libsphinxclient //sphinx-2.2.5-release目錄下 # ./configure --prefix=/usr/local/sphinx2/libsphinxclient # make && make install
4.3 安裝sphinx php擴充
(phpize在/usr/local/php5/bin/phpize ,如果沒有phpize命令,ln -s 到 /usr/bin下)
# cd /usr/local/src/sphinx# tar zxvf sphinx-1.3.1.tgz # cd sphinx-1.3.1 # phpize # ./configure --with-sphinx=/usr/local/sphinx2/libsphinxclient --with-php-config=/usr/local/php5/bin/php-config # make && make install
4.4 安裝scws
# cd /usr/local/src/sphinx# tar xvjf scws-1.2.3.tar.bz2# mkdir /usr/local/scws # cd scws-1.2.3 # ./configure --prefix=/usr/local/scws/ # make && make install
4.5 安裝scws php擴充
# cd /usr/local/src/sphinx/scws-1.2.3/phpext # phpize # ./configure --with-php-config=/usr/local/php5/bin/php-config # make && make install
4.6 安裝scws詞庫
# tar xvjf scws-dict-chs-utf8.tar.bz2 -C /usr/local/scws/etc/# www為php-fpm運行使用者# chown www:www /usr/local/scws/etc/dict.utf8.xdb
5 建立mysql資料來源
5.1 test.sql
/*Navicat MySQL Data TransferSource Server : 192.168.101.130Source Server Version : 50527Source Host : 192.168.101.130:3306Source Database : testTarget Server Type : MYSQLTarget Server Version : 50527File Encoding : 65001Date: 2016-08-14 13:46:48*/SET FOREIGN_KEY_CHECKS=0;-- ------------------------------ Table structure for `userinfo`-- ----------------------------DROP TABLE IF EXISTS `userinfo`;CREATE TABLE `userinfo` ( `id` int(11) unsigned NOT NULL AUTO_INCREMENT, `userid` int(11) unsigned NOT NULL DEFAULT '0', `addtime` datetime NOT NULL, `post` varchar(20) NOT NULL DEFAULT '', `summary` text NOT NULL, PRIMARY KEY (`id`)) ENGINE=InnoDB AUTO_INCREMENT=21 DEFAULT CHARSET=utf8;-- ------------------------------ Records of userinfo-- ----------------------------INSERT INTO `userinfo` VALUES ('17', '1', '2012-06-01 00:24:54', '洪', '奧運');INSERT INTO `userinfo` VALUES ('18', '2', '2014-08-19 10:24:54', '中國人', '洪荒');INSERT INTO `userinfo` VALUES ('19', '3', '2015-08-01 12:24:54', '洪荒之', 'nimne');INSERT INTO `userinfo` VALUES ('20', '4', '2013-08-01 00:24:54', '洪荒之力', '23金');-- ------------------------------ Table structure for `users`-- ----------------------------DROP TABLE IF EXISTS `users`;CREATE TABLE `users` ( `id` int(11) unsigned NOT NULL AUTO_INCREMENT, `username` varchar(20) NOT NULL DEFAULT '', PRIMARY KEY (`id`)) ENGINE=InnoDB AUTO_INCREMENT=5 DEFAULT CHARSET=utf8;-- ------------------------------ Records of users-- ----------------------------INSERT INTO `users` VALUES ('1', 'zhangsan');INSERT INTO `users` VALUES ('2', 'zhangsi');INSERT INTO `users` VALUES ('3', '李四');INSERT INTO `users` VALUES ('4', '王五');
5.2 執行source test.sql
5.3 資料來源
6 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= mysqlsql_host= 127.0.0.1sql_user= rootsql_pass= 123456sql_db= testsql_port= 3306# optional, default is 3306sql_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 = addtimesql_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 = 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{#phplisten = 9312#mysql listen = 9306:mysql41log= /usr/local/sphinx2/var/log/searchd.logquery_log= /usr/local/sphinx2/var/log/query.logquery_log_format = sphinxqlread_timeout= 5client_timeout= 300max_children= 30persistent_connections_limit= 30pid_file= /usr/local/sphinx2/var/log/searchd.pidseamless_rotate= 1preopen_indexes= 1unlink_old= 1mva_updates_pool= 1Mmax_packet_size= 8Mmax_filters= 256max_filter_values= 4096max_batch_queries= 32workers= threads # for RT to work}
7 配置php.ini
# vim /etc/php.ini 添加
[sphinx]extension = sphinx.so[scws]extension = scws.soscws.default.charset = utf-8scws.default.fpath = /usr/local/scws/etc
8 啟動sphinx,php-fpm8.1,啟動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
8.2,重啟php-fpm(如果是web調用php)
重啟php-fpm
9 測試sphinx全文檢索索引9.1 用戶端測試
9.2 php測試
test.php
<?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'); //預設詞庫 $so->add_dict(ini_get('scws.default.fpath') . '/dict.utf8.xdb'); //自訂詞庫// $so->add_dict('./dd.txt',SCWS_XDICT_TXT); //預設規則 $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); //設定是否將閑散文字自動以二字分詞法彙總 $so->set_duality(false); //設定搜尋字詞 $so->send_text($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";//========================================搜尋 $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;?>
3)列印結果
從words結果中可以看出一元分詞後命中的文章數。
<p>輸入:洪荒之力</p><p>分詞:(洪荒)|(之)|(力)</p>Array( [error] => [warning] => [status] => 0 [fields] => Array ( [0] => username [1] => post [2] => summary ) [attrs] => Array ( [userid] => 1 [username] => 7 [addtime] => 2 [post] => 7 ) [matches] => Array ( [0] => Array ( [id] => 20 [weight] => 4500 [attrs] => Array ( [userid] => 4 [username] => 王五 [addtime] => 1375345494 [post] => 洪荒之力 ) ) [1] => Array ( [id] => 19 [weight] => 3451 [attrs] => Array ( [userid] => 3 [username] => 李四 [addtime] => 1438460694 [post] => 洪荒之 ) ) [2] => Array ( [id] => 18 [weight] => 2436 [attrs] => Array ( [userid] => 2 [username] => zhangsi [addtime] => 1408472694 [post] => 中國人 ) ) ) [total] => 3 [total_found] => 3 [time] => 0 [words] => Array ( [洪] => Array ( [docs] => 4 [hits] => 4 ) [荒] => Array ( [docs] => 3 [hits] => 3 ) [之] => Array ( [docs] => 2 [hits] => 2 ) [力] => Array ( [docs] => 1 [hits] => 1 ) ))
4 查詢query.log
sphinx + scws + Mysql + PHP全文檢索索引