phpmysql网站开发入门与提高
PHP+MySQL+sphinx+scws实现全文检索功能详解本文实例讲述了PHP+MySQL+sphinx+scws实现全文检索功能。分享给大家供大家参考，具体如下：
我的个人环境是PHP7.1+MariaDB10.1.23
下载安装资源包
- sphinx地址
http://sphinxsearch.com/downloads/release/
- PHP的sphinx扩展下载
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
安装过程
因为我的是PHP 7 版本，安装sphinx的时候遇到点问题
-
安装
sphinx
|
|
[root@MevHost sphinxb]# mkdir -p /usr/local/src/sphinx[root@MevHost sphinxb]# cd /usr/local/src/sphinx [root@MevHost sphinxb]# tar -xf sphinx-2.2.11-release.tar.gz [root@MevHost sphinxb]# cd sphinx-2.2.11-release// 这里是指定安装的目录，还有引用mysql,(我这里是mariadb的安装目录)[root@MevHost sphinxb]# ./configure --prefix=/usr/local/sphinx2 --with-mysql=/usr/local/mariadb/[root@MevHost sphinxb]# make && make install |
-
安装
sphinx客户端
这个要安装上，不然安装PHP安装sphinx扩展时会出现报错
|
|
[root@MevHost sphinxb]# cd /usr/local/src/sphinx/sphinx-2.2.11-release/api/libsphinxclient //sphinx-2.2.11-release目录下 [root@MevHost sphinxb]# ./configure --prefix=/usr/local/sphinx2/libsphinxclient [root@MevHost sphinxb]# make && make install |
-
为PHP安装
sphinx扩展
|
|
[root@MevHost sphinxb]# cd /usr/local/src/sphinx[root@MevHost sphinxb]# tar zxvf sphinx-1.3.1.tgz [root@MevHost sphinxb]# cd sphinx-1.3.1 [root@MevHost sphinxb]# phpize [root@MevHost sphinxb]# ./configure --with-sphinx=/usr/local/sphinx2/libsphinxclient --with-php-config=/usr/local/php/bin/php-config [root@MevHost sphinxb]# make && make install |
成功后再 php.ini 添加：
|
|
extension=sphinx.so |
PHP7版本sphinx扩展下载
下载地址
http://git.php.net/?p=pecl/search_engine/sphinx.git;a=shortlog;h=refs/heads/php7
- 安装scws
|
|
[root@MevHost sphinxb]# tar -jxvf scws-1.2.3.tar.bz2[root@MevHost sphinxb]# mkdir /usr/local/scws [root@MevHost sphinxb]# cd scws-1.2.3 [root@MevHost sphinxb]# ./configure --prefix=/usr/local/scws/ [root@MevHost sphinxb]# make && make install |
- 为PHP安装scws扩展
|
|
[root@MevHost sphinxb]# cd /usr/local/src/sphinx/scws-1.2.3/phpext [root@MevHost sphinxb]# phpize [root@MevHost sphinxb]# ./configure --with-php-config=/usr/local/php/bin/php-config[root@MevHost sphinxb]# make && make install |
在php.ini 加入
|
|
extension = scws.soscws.default.charset=utf-8scws.default.fpath = /usr/local/scws/etc |
- 安装scws词库
|
|
[root@MevHost sphinxb]# tar jxvf scws-dict-chs-utf8.tar.bz2 -C /usr/local/scws/etc/#www为php-fpm运行用户[root@MevHost sphinxb]# chown www:www /usr/local/scws/etc/dict.utf8.xdb |
创建MySQL数据源
mtest.sql
|
|
/*Navicat MySQL Data TransferSource Database : mtestTarget Server Type : MYSQLTarget Server Version : 50505File Encoding : 65001Date: 2017-12-10 17:47:58*/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', '2017-12-10 00:24:54', '在CentOS7中使用Sendmail通', 'sendmail');INSERT INTO `userinfo` VALUES ('18', '2', '2017-12-10 10:24:54', '彻底理解PHP的SESSION机制', 'session');INSERT INTO `userinfo` VALUES ('19', '3', '2017-12-10 12:24:54', '手把手编写自己的PHPMVC框架实例教程', 'mvc');INSERT INTO `userinfo` VALUES ('20', '4', '2017-12-10 00:24:54', 'php获取今日、昨日、上周、本月的起始时', '时间');-- ------------------------------ 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', 'Lionee');INSERT INTO `users` VALUES ('2', 'libber');INSERT INTO `users` VALUES ('3', 'sysmob');INSERT INTO `users` VALUES ('4', '学习'); |
配置sphinx
配置文件在/usr/local/sphinx2/etc
|
|
cp sphinx-min.conf.dist sphinx.conf |
|
|
source users{ type = mysql sql_host = 127.0.0.1 sql_user = root sql_pass = 123456 sql_db = mtest 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 = 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} |
启动sphinx
|
|
[root@MevHost ~]# pkill searchd[root@MevHost ~]# /usr/local/sphinx2/bin/indexer --config /usr/local/sphinx2/etc/sphinx.conf --all [root@MevHost ~]# /usr/local/sphinx2/bin/searchd --config /usr/local/sphinx2/etc/sphinx.conf |
如果出现下面的报错
"Oops! It seems that sphinx was built with wrong endianess (cross-compiling?)
either reconfigure and rebuild, defining ac_cv_c_bigendian=no in the environment of
./configure script,
either ensure that '#define USE_LITTLE_ENDIAN = 1' in config/config.h"
我是直接把sphinx下面的config/config.h 改成了他提示的这个 #define USE_LITTLE_ENDIAN = 1，之后make的,
接下来的这段是我们的PHP代码了
|
|
<!DOCTYPE html><html lang="en"><head> <meta charset="UTF-8"> <title>Document</title></head><body> <form method="post" action='test.php'> <p>输入：</p> <input type="text" name="q" autocomplete="false"> </form></body></html><?php// phpinfo();die;ini_set('display_errors','1');error_reporting(E_ALL);header("Content-type: text/html; charset=utf-8");if($_POST){$b_time = microtime(true);$key = $_POST['q'];$index = "users";//========================================分词$so = scws_new();$so->set_charset('utf-8');//默认词库$so->add_dict(ini_get('scws.default.fpath') . '/dict.utf8.xdb');//自定义词库// $so->add_dict('./dd.txt',SCWS_XDICT_TXT);//默认规则$so->set_rule(ini_get('scws.default.fpath') . '/rules.utf8.ini');//设定分词返回结果时是否去除一些特殊的标点符号$so->set_ignore(true);//设定分词返回结果时是否复式分割，如“中国人”返回“中国＋人＋中国人”三个词。// 按位异或的 1 | 2 | 4 | 8 分别表示: 短词 | 二元 | 主要单字 | 所有单字//1,2,4,8 分别对应常量 SCWS_MULTI_SHORT SCWS_MULTI_DUALITY SCWS_MULTI_ZMAIN SCWS_MULTI_ZALL$so->set_multi(false);//设定是否将闲散文字自动以二字分词法聚合$so->set_duality(false);//设定搜索词$so->send_text($key);$words_array = $so->get_result();$words = "";foreach($words_array as $v){ $words = $words.'|('.$v['word'].')';}//加入全词#$words = '('.$key.')'.$words;$words = trim($words,'|');猜您喜欢
|