PHP搜索优化 sphinx 实战

Posted 2020-11-01 懒牛拉车

环境：win7 64 wamp

解压sphinx安装包后，简历如下结构。注意，conf目录是我的配置文件目录

在conf目录下，简历newdefend.conf文件，配置内容如下

# 配置数据源
source domain_src
{
    type            = mysql
    sql_host        = 192.168.185.210
    sql_user        = root
    sql_pass        =
    sql_db            = mydb
    sql_port        = 3306    
    
    sql_ranged_throttle    = 0
    sql_query_pre        = SET NAMES utf8
    # sql_query_pre       = SET SESSION query_cache_type=OFF
    sql_query_pre         = REPLACE INTO sph_counter SELECT 1, MAX(id) FROM domain
　　 # 注意这个地方，至少要有各自字段没有定义成sql_attr_***,好像是需要有一个字段是全文索引什么的。反正多查询一个字段就对了。或者定义一个sql_field_string也可以
    sql_query            = SELECT id,uid,type,package_level,ct,domain FROM domain \\
        WHERE id<=( SELECT max_id FROM sph_counter WHERE counter_id = 1 ) 
    sql_attr_uint        = uid
    sql_attr_uint        = type
    sql_attr_uint        = package_level
    # sql_field_string        = ct
    sql_attr_timestamp    = ct
}

# 配置增量数据源
source delta_domain_src:domain_src{
    sql_ranged_throttle = 100
    sql_query_pre       = SET NAMES utf8
    # sql_query_pre       = SET SESSION query_cache_type=OFF
    sql_query            = SELECT id,uid,type,package_level,ct,domain FROM domain \\
        WHERE id>( SELECT max_id FROM sph_counter WHERE counter_id = 1 ) 
}
 

# 索引
index domain_suggest
{
    source            = domain_src
    path            = D:/sphinx/data/domain_suggest
    charset_table     = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F
    docinfo            = extern
    dict            = keywords
    mlock            = 0
    morphology        = none
    min_word_len    = 1
    ngram_len        = 1
    ngram_chars        = U+3000..U+2FA1F
    html_strip        = 0
}

# 增量索引
index delta_domain_suggest:domain_suggest {
    source             = delta_domain_src
    path            = D:/sphinx/data/delta_domain_suggest
}

indexer
{
    mem_limit        = 128M
}

# 配置Sphinx服务器的信息
searchd
{
    listen            = 9312
    listen            = 9306:mysql41
    log                = D:/sphinx/log/searchd.log
    query_log        = D:/sphinx/log/query.log
    read_timeout        = 5
    client_timeout        = 300
    max_children        = 30
    persistent_connections_limit    = 30
    pid_file            = D:/sphinx/log/searchd.pid
    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 
    
    # windows下启动searchd服务一定要注释掉这个
 　 # seamless_rotate  = 1
 
    # 开启sphinx服务时，会生成几个log文件，这里配置文件生成目录。默认会生成在searchd.exe同级目录下
    binlog_path       = D:/sphinx/log/
}

定义一个启动sphinx的脚本“sphinx重启.bat”。脚本内容如下，双击启动

@echo off 

::停止sphinx服务
d:/sphinx/bin/searchd --stop

::建立配置文件中所有索引（也可以建立某个索引）
d:/sphinx/bin/indexer -c d:/sphinx/conf/newdefend.conf --all

::启动sphinx服务
d:/sphinx/bin/searchd -c d:/sphinx/conf/newdefend.conf

::窗口不要关闭
pause

启动成功界面

测试代码

$keyword = \'\';
$sphinx = new SphinxClient;
$sphinx->setServer("localhost", 9312);
$sphinx->setMatchMode(SPH_MATCH_ALL);   //匹配模式 ANY为关键词自动拆词，ALL为不拆词匹配（完全匹配）
$sphinx->SetArrayResult ( true );    //返回的结果集为数组
$result = $sphinx->query($keyword,"domain_suggest delta_domain_suggest");    //星号为所有索引源
$count=$result[\'total\'];        //查到的结果条数
$time=$result[\'time\'];            //耗时
$arr=$result[\'matches\'];        //结果集
$id=\'\';
foreach($arr as $i => $val){
    $id.=$arr[$i][\'id\'].\',\';
}
$id=substr($id,0,-1);            //结果集的id字符串

echo $id;

运行结果