【整理】Linux下中文检索引擎coreseek4安装，以及PHP使用sphinx的三种方式(sphinxapi，sphinx的php扩展，SphinxSe作为mysql存储引擎)

yum install make gcc g++ gcc-c++ libtool autoconf automake imake mysql-devel libxml2-devel expat-devel
#或
apt-get install make gcc g++ automake libtool mysql-client libmysqlclient15-dev libxml2-dev libexpat1-dev
#更多系统配置请点此传送查看

##前提：需提前安装操作系统基础开发库及mysql依赖库以支持mysql数据源和xml数据源
##安装mmseg
$ cd mmseg-3.2.14
$ ./bootstrap    #输出的warning信息可以忽略，如果出现error则需要解决
$ ./configure --prefix=/usr/local/mmseg3 
$ make && make install
$ cd ..

#下面命令提示没有安装，则先安装
aclocal
libtoolize --force 运行后有一个错误，不用管它。
automake --add-missing
autoconf
autoheader
make clean
./configure --prefix=/usr/local/mmseg3

##安装coreseek
$ cd csft-4.1
$ sh buildconf.sh    #输出的warning信息可以忽略，如果出现error则需要解决
$ ./configure --prefix=/usr/local/coreseek  --without-unixodbc --with-mmseg --with-mmseg-includes=/usr/local/mmseg3/include/mmseg/ --with-mmseg-libs=/usr/local/mmseg3/lib/ --with-mysql    ##如果提示mysql问题，可以查看MySQL数据源安装说明

#不想麻烦，可以直接使用下面这句
$ ./configure --prefix=/usr/local/coreseek  --without-unixodbc --with-mmseg --with-mmseg-includes=/usr/local/mmseg3/include/mmseg/ --with-mmseg-libs=/usr/local/mmseg3/lib/ --with-mysql-includes=《mysql安装目录》/include --with-mysql-libs=《mysql安装目录》/lib

$ make && make install
$ cd ..

##测试mmseg分词，coreseek搜索（需要预先设置好字符集为zh_CN.UTF-8，确保正确显示中文）
$ cd testpack
$ cat var/test/test.xml    #此时应该正确显示中文
$ /usr/local/mmseg3/bin/mmseg -d /usr/local/mmseg3/etc var/test/test.xml
$ /usr/local/coreseek/bin/indexer -c etc/csft.conf --all
$ /usr/local/coreseek/bin/search -c etc/csft.conf 网络搜索

mysql> use test_qq;
Database changed
mysql> desc say;
+---------+------------------+------+-----+---------+----------------+
| Field   | Type             | Null | Key | Default | Extra          |
+---------+------------------+------+-----+---------+----------------+
| id      | int(10) unsigned | NO   | PRI | NULL    | auto_increment |
| fromid  | int(10) unsigned | NO   |     | 0       |                |
| toid    | int(10) unsigned | NO   |     | 0       |                |
| content | text             | NO   |     | NULL    |                |
+---------+------------------+------+-----+---------+----------------+

cp /coreseek安装包位置/testpack/etc/csft_mysql.conf /usr/local/coreseek/etc/

mysql> desc sph_say_counter;
+------------+---------------------+------+-----+---------+----------------+
| Field      | Type                | Null | Key | Default | Extra          |
+------------+---------------------+------+-----+---------+----------------+
| id         | tinyint(3) unsigned | NO   | PRI | NULL    | auto_increment |
| max_offset | int(10) unsigned    | NO   |     | 0       |                |
+------------+---------------------+------+-----+---------+----------------+

#增加以下配置
source delta : mysql #此写法为delta继承mysql源中的所有配置，如果子配置中有相同配置，则覆盖父配置
{
        sql_query       =       SELECT id,fromid,toid,content FROM say WHERE id > (SELECT max_offset FROM sph_say_counter WHERE id = 1) #从记录大于max_offset后的数据开始索引
        sql_query_post  =       REPLACE INTO sph_say_counter(id,max_offset) SELECT 1,MAX(id) FROM say #索引后更新最大记录,sql_query_pre是执行查询前执行的语句，sql_query_post是执行查询后再执行的语句
}
index delta : mysql
{
        source          =       delta
        path            =       /usr/local/coreseek/var/data/delta
}

sql_query_pre           = REPLACE INTO sph_say_counter(id,max_offset) SELECT 1,MAX(id) FROM say

cd /usr/local/coreseek/sh
vi all.sh
/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/csft_mysql.conf --all --rotate

vi delta.sh
/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/csft_mysql.conf delta --rotate 

vi merge.sh
/usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/csft_mysql.conf --merge mysql delta --rotate --merge-dst-range deleted 0 0 

*/1 * * * * /bin/sh /usr/local/coreseek/sh/delta.sh >/dev/null 2>&1 ##每1分钟执行增量索引
*/5 * * * * /bin/sh /usr/local/coreseek/sh/merge.sh >/dev/null 2>&1 ##每5分钟合并索引
30 1 * * *  /bin/sh /usr/local/coreseek/sh/all.sh >/dev/null 2>&1   ##每天的1:30执行整体索引

 1 <?php
 2 
 3 /*
 4    test_sph.php 
 5     SphinxClient类测试
 6 */
 7 
 8 $key=trim($_GET[‘key‘]);
 9 echo $key;
10 include(‘sphinxapi.php‘);
11 
12 $sp=new SphinxClient();
13 $sp->SetServer(‘localhost‘,9312);
14 $sp->SetArrayResult(true);
15 $sp->SetMatchMode(SPH_MATCH_ALL);
16 $sp->SetSortMode(SPH_SORT_RELEVANCE);
17 $res=$sp->Query($key,‘mysql‘);
18 
19 echo ‘<pre>‘;
20 print_r($res);
21 echo ‘</pre>‘;
22 
23 if(isset($res[‘matches‘])&&count($res[‘matches‘])>0)
24 {
25     $mysql=new PDO("mysql:localhost;dbname=test_qq",‘root‘,‘123‘);
26     $mysql->query(‘set names utf8‘);
27     $mysql->query(‘use test_qq‘);
28     $sql=‘select * from say where id in(‘;
29 
30     foreach ($res[‘matches‘] as $v)
31     {
32         $sql.=$v[‘id‘].‘,‘;
33     }
34     $sql=trim($sql,‘,‘).‘)‘;
35 
36     echo $sql;
37     foreach($mysql->query($sql) as $v)
38     {
39         echo ‘<pre>‘;
40         print_r($v);
41         echo ‘</pre>‘;
42     }
43 }
44 else
45 {
46     echo ‘没有记录‘;
47 }

 1 # cd /coreseek安装包目录/csft-4.1/api/libsphinxclient/
 2 # ./configure  --prefix=/usr/local/sphinxclient
 3 
 4 configure: creating ./config.status
 5 config.status: creating Makefile
 6 config.status: error: cannot find input file: Makefile.in   #报错configure失败    
 7 
 8 //处理configure报错
 9 编译过程中报了一个config.status: error: cannot find input file: src/Makefile.in这个的错误，然后运行下列指令再次编译就能通过了：
10 # aclocal
11 # libtoolize --force
12 # automake --add-missing
13 # autoconf
14 # autoheader
15 # make clean
16 
17 //从新configure编译
18 # ./configure
19 
20 # make && make install

 1 http://pecl.php.net/package/sphinx
 2 # wget http://pecl.php.net/get/sphinx-1.3.0.tgz
 3 # tar zxvf sphinx-1.3.0.tgz
 4 # cd sphinx-1.3.0
 5 # phpize
 6 # ./configure --with-php-config=/usr/bin/php-config --with-sphinx=/usr/local/sphinxclient
 7 # make && make install
 8 # cd /etc/php.d/
 9 # cp gd.ini  sphinx.ini
10 # vi sphinx.ini
11 
12 extension=sphinx.so
13 
14 # service php-fpm restart

 1 <?php
 2     header("Content-type: text/html; charset=utf-8");
 3     require("./sphinxapi.php");
 4     $s = new SphinxClient;
 5     $s->setServer("192.168.252.132", 9312);
 6     
 7     //SPH_MATCH_ALL, 匹配所有查询词(默认模式); SPH_MATCH_ANY, 匹配查询词中的任意一个; SPH_MATCH_EXTENDED2, 支持特殊运算符查询
 8     $s->setMatchMode(SPH_MATCH_ALL);
 9     $s->setMaxQueryTime(30);                                        //设置最大搜索时间
10     $s->SetArrayResult(false);                                        //是否将Matches的key用ID代替
11     $s->SetSelect ( "*" );                                            //设置返回信息的内容,等同于SQL
12     $s->SetRankingMode(SPH_RANK_BM25);                                //设置评分模式，SPH_RANK_BM25可能使包含多个词的查询的结果质量下降。 
13     //$s->SetSortMode(SPH_SORT_EXTENDED);                            //发现增加此参数会使结果不准确
14     //$s->SetSortMode(SPH_SORT_EXTENDED,"from_id asc,id desc");        //设置匹配项的排序模式, SPH_SORT_EXTENDED按一种类似SQL的方式将列组合起来，升序或降序排列。
15     $weights = array (‘company_name‘ => 20);
16     $s->SetFieldWeights($weights);                                    //设置字段权重
17     $s->SetLimits ( 0, 30, 1000, 0 );                                //设置结果集偏移量  SetLimits (便宜量,匹配项数目,查询的结果集数默认1000,阀值达到后停止)
18     //$s->SetFilter ( $attribute, $values, $exclude=false );        //设置属性过滤
19     //$s->SetGroupBy ( $attribute, $func, $groupsort="@group desc" );    //设置分组的属性
20     $res = $s->query(‘@* "汽车"‘,‘main‘,‘--single-0-query--‘); #[宝马]关键字，[news]数据源source
21     
22     
23     //代码高亮
24     $tags = array();
25     $tags_name = array();
26     foreach($res[‘matches‘] as $key=>$value){
27         $tags[] = $value[‘attrs‘];
28           $company_name[] = $value[‘attrs‘][‘company_name‘];
29           $description[] = $value[‘attrs‘][‘description‘];
30     }
31     $company_name = $s->BuildExcerpts ($company_name, ‘main‘, ‘汽车‘, $opts=array() );        //执行高亮，这里索引名字千万不能用*
32     $description = $s->BuildExcerpts ($description, ‘main‘, ‘汽车‘, $opts=array() );        //执行高亮，这里索引名字千万不能用*
33     foreach($tags as $k=>$v)
34     {
35         $tags[$k][‘company_name‘] = $company_name[$k];    //高亮后覆盖
36         $tags[$k][‘description‘] = $description[$k];    //高亮后覆盖
37     }
38     
39     // 高亮后覆盖
40     $i = 0;
41     foreach($res[‘matches‘] as $key=>$value){
42         $res[‘matches‘][$key] = $tags[$i];
43         $i++;
44     }
45     
46     $err = $s->GetLastError();
47     
48     echo ‘<pre>‘;
49     var_export($res);
50     var_export($err);
51     echo ‘</pre>‘;

#---------------MySQL 5.5 基本设置编译-----------

#以下指令中的VERSION表示MySQL的版本，例如：5.5.8，或者5.5.9
$ tar xzvf coreseek-4.1-beta.tar.gz
$ tar xzvf mysql-VERSION.tar.gz #就是上面下载的mysql源码包
$ cp -R coreseek-4.1-beta/csft-4.1/mysqlse mysql-VERSION/storage/sphinx
#上面语句是将mysqlse文件夹复制到storage文件夹下并更名为sphinx，请注意
$ cd mysql-VERSION
$ cmake . -DCMAKE_BUILD_TYPE=Release -DWITH_SPHINX_STORAGE_ENGINE=1 #如果提示没有命令 先"yum -y install cmake" 安装cmake
#如果上面语句报“Warning: Bison executable not found in PATH”，则安装bison，再运行此语句
#如果提示缺少ncurses库,则 apt-get install libncurses-dev 或 yum -y install ncurses-devel 安装ncurses库后,删除CMakeCache.txt文件,再重新cmake即可

#如要查看cmake可用参数，请执行：cmake . -LH
$ make


#----------将SphinxSE安装到已经安装的MySQL 5.5中-----------

#首先执行：MySQL 5.5 基本设置编译过程
#特别注意：需要选择与当前已安装的MySQL 5.5对应的版本进行编译
$ cp storage/sphinx/ha_sphinx.so /path_to_your_mysql_5.5/lib/plugin
$ mysql -uroot -p???
mysql>install plugin sphinx soname "ha_sphinx.so";
mysql>show engines;
#ENGINE列表显示出SPHINX表示安装成功

#-------------------------测试SphinxSe--------------------------------------
mysql> use test_qq;

mysql> CREATE TABLE documents_sphinxse
-> (
-> id INTEGER UNSIGNED NOT NULL,
-> weight INTEGER NOT NULL,
-> query VARCHAR(3072) NOT NULL,
-> group_id INTEGER,
-> INDEX(query)
-> ) ENGINE=SPHINX CONNECTION="sphinx://localhost:9312/mysql";

#-----------执行sphinxse查询-----------------------------
mysql>SELECT * FROM documents_sphinxse WHERE query=‘网络搜索;mode=any‘;

#--------执行关联SphinxSE查询，获取原始数据信息：-----------

mysql>SELECT dse.*, d.title FROM documents_sphinxse AS dse LEFT JOIN documents AS d USING(id) WHERE query=‘网络搜索;mode=any‘;