coreseek 中文搜索和高亮

Posted 2020-08-21 brady-wang

配置文件

#
# Minimal Sphinx configuration sample (clean, simple, functional)
#

source post
{
    type                    = mysql

    sql_host                = 192.168.33.90
    sql_user                = root
    sql_pass                = root
    sql_db                    = test
    sql_port                = 3306    # optional, default is 3306
    sql_sock                                = /tmp/mysql.sock 
    sql_query_pre = SET NAMES utf8
    sql_query_pre = SET SESSION query_cache_type=OFF
    sql_query                = \\
        SELECT * from post

    sql_query_info            = SELECT * FROM post WHERE id=$id
}


index post
{
    source                    = post
    path                    = /usr/local/coreseek/var/data/post
    
    charset_type            = zh_cn.utf-8
    charset_dictpath                = /usr/local/mmseg/etc/
}


indexer
{
    mem_limit                = 32M
}


searchd
{
    port                    = 9312
    log                        = /usr/local/coreseek/var/log/searchd.log
    query_log                = /usr/local/coreseek/var/log/query.log
    read_timeout            = 5
    max_children            = 30
    pid_file                = /usr/local/coreseek/var/log/searchd.pid
    max_matches                = 1000
    seamless_rotate            = 1
    preopen_indexes            = 0
    unlink_old                = 1
}

 

数据库数据

/*
Navicat MySQL Data Transfer

Source Server         : 33.90
Source Server Version : 50548
Source Host           : 192.168.33.90:3306
Source Database       : test

Target Server Type    : MYSQL
Target Server Version : 50548
File Encoding         : 65001

Date: 2016-11-25 22:52:55
*/

SET FOREIGN_KEY_CHECKS=0;

-- ----------------------------
-- Table structure for `post`
-- ----------------------------
DROP TABLE IF EXISTS `post`;
CREATE TABLE `post` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `title` varchar(100) DEFAULT NULL,
  `content` text,
  PRIMARY KEY (`id`)
) ENGINE=MyISAM AUTO_INCREMENT=11 DEFAULT CHARSET=utf8;

-- ----------------------------
-- Records of post
-- ----------------------------
INSERT INTO `post` VALUES (\'1\', \'linux1\', \'linux11\');
INSERT INTO `post` VALUES (\'2\', \'php1\', \'php11\');
INSERT INTO `post` VALUES (\'3\', \'php1\', \'php222\');
INSERT INTO `post` VALUES (\'4\', \'php3\', \'php333\');
INSERT INTO `post` VALUES (\'5\', \'php5\', \'php333\');
INSERT INTO `post` VALUES (\'8\', \'兄弟连\', \'格兰仕的减肥了开始的减肥了时间发\');
INSERT INTO `post` VALUES (\'7\', \'linux is very good\', \' linux is aaaaaaa连\');
INSERT INTO `post` VALUES (\'9\', \'时间\', \'收到减肥老兄弟\');
INSERT INTO `post` VALUES (\'10\', \'二位二位二时间\', \'lamp兄弟连\');

php代码

<?php
header("Content-type:text/html;charset=utf-8");
ini_set("display_errors",1);
error_reporting(E_ALL);
$keyword = $_GET[\'key\'];
//实例化Sphinx对象
$sphinx=new SphinxClient();

//连接sphinx服务器
$sphinx->SetServer("192.168.33.90",9312);
//拆词
//SPH_MATCH_ALL 和 SPH_MATCH_ANY 的区别：
//搜索“LAMP兄弟连”，ALL的结果：完整包含“LAMP兄弟连”才能被搜出来，
//单纯包含“LAMP”或单纯包含“兄弟连”的搜索不出来，没有拆词的功能。
//ANY则可以搜索出来拆开后的词的结果。此处使用ANY
$sphinx->SetMatchMode(SPH_MATCH_ANY);
//通过query方法搜索,“*”表示在所有的索引中搜索，相当于命令行里面的“./indexer --all”
$result=$sphinx->query("$keyword","*");
//打印搜索的结果
// echo "<pre>";
// print_r($result);
// echo "</pre>";

//上面打印的结果中，数组的 [matches]循环便利，下标就是搜索到的文档的主键Id
//使用PHP中的 array_keys()函数即可拿到下标，即：要查找的文档的主键
//print_r(array_keys($result[\'matches\']));
//结果如下：Array([0]=>1)

//使用implode或者 join用逗号把查询出来的主键连接起来：
$ids = join(\',\',array_keys($result[\'matches\']));
//echo $ids; //6,7

/*连接数据库的操作*/
$p1 = mysql_connect("192.168.33.90","root","root");
mysql_select_db("test");
mysql_query("set names utf8");
$sql="select * from post where id in ($ids)";
$rst=mysql_query($sql);

$opts=array(
   "before_match"=>"<font color=\'red\'>",
   "after_match"=>"</font>",
);
while($row=mysql_fetch_assoc($rst)){

    //下面是高亮显示所需，具体可以查手册    
    $final=$sphinx->buildExcerpts($row,"post",$keyword,$opts);
    
    echo "标题：".$final[\'1\']."<br>";
    echo $final[2].\'<hr>\';
}

?>

 

效果图片：