php sphinx搜寻分词 windows7

程序员文章站 2023-12-25 19:32:09

...

php sphinx搜索分词 windows7

本地开发环境

1.下载coreseek词库，下载地址：http://www.coreseek.cn/products-install/install_on_windows/

coreseek3.2.14通用版php 5.4.3

2.下载好后，再环境变量里配置：

打开cmd#->CD c:\usr\local\coreseek-3.2.14-win32#->SET PATH=%CD%\bin;%PATH%

3.在项目录目下添加一个sphinx.conf文件（名字随自己定），关联查询product与product_type表

#MySQL数据源配置，详情请查看：http://www.coreseek.cn/products-install/mysql/#请先将var/test/documents.sql导入数据库，并配置好以下的MySQL用户密码数据库#源定义#sql_attr_uint#sql_attr_bool    #sql_attr_bigint     #sql_attr_timestamp   时间行#sql_attr_str2ordinal  字符串行#sql_attr_float   浮点型#sql_attr_multi  source mysql{    type                     = mysql    sql_host                 = 192.168.8.229    sql_user                 = feiyang    sql_pass                 = 123456    sql_db                   = feiyang_prd    sql_port                 = 3306    sql_query_pre            = SET NAMES utf8    sql_query                = SELECT SQL_NO_CACHE `product`.`ID` * CAST(1 AS SIGNED) + 0 AS `ID`, `product`.`MinPrice` AS `MinPrice`, `product`.`ProductTypeid` AS `product_type_id`, UNIX_TIMESTAMP(`product`.`ShowStartTime`) AS date_added , `product`.`WebTitle` AS `WebTitle`, `product`.`SubTitle` AS `SubTitle`, `product`.`AddressNames` AS `AddressNames`, `product_type`.`Title` AS `product_type_title` FROM `product` LEFT OUTER JOIN `product_type` ON `product_type`.`ID` = `product`.`ProductTypeid` where `product`.`ShowStatus` = 1 GROUP BY `product`.`ID` ORDER BY NULL         #sql_query第一列ID需为整数         #WebTitle、SubTitle, ProductType表中title作为字符串/文本字段，被全文索引    sql_attr_uint            = sphinx_internal_id           #从SQL读取到的值必须为整数    sql_attr_uint            = class_crc    sql_attr_uint            = Sort    sql_attr_uint            = ShowStatus    sql_attr_float           = MinPrice    sql_attr_timestamp       = date_added #从SQL读取到的值必须为整数，作为时间属性    sql_attr_str2ordinal     = WebTitle_sort    sql_attr_str2ordinal     = SubTitle_sort    sql_attr_str2ordinal     = AddressNames_sort    sql_attr_str2ordinal     = StartCity_sort    sql_attr_str2ordinal     = ToTraffic_sort    sql_attr_str2ordinal     = BackTraffic_sort    sql_attr_str2ordinal     = Notes_sort        sql_query_info_pre       = SET NAMES utf8                                        #命令行查询时，设置正确的字符集    sql_query_info           = SELECT * FROM product WHERE `ID` = (($id - 0) / 1) #命令行查询时，从数据库读取原始数据信息}#index定义index mysql{    source            = mysql             #对应的source名称    path              = E:/projects/test_php/data/product #索引路径，请修改为实际使用的绝对路径，例如：/usr/local/coreseek/var/...    docinfo           = extern    mlock             = 0    morphology        = none    min_word_len      = 1    ngram_len         = 1   #1为搜索中文    html_strip        = 0    #charset_dictpath = /usr/local/mmseg3/etc/ #BSD、Linux环境下设置，/符号结尾    charset_dictpath  = D:/coreseek/etc/                             #Windows环境下设置，/符号结尾，最好给出绝对路径，例如：C:/usr/local/coreseek/etc/...    charset_type      = utf-8    charset_table     = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F    ngram_chars      = U+3000..U+2FA1F}#全局index定义indexer{    mem_limit            = 128M}#searchd服务定义searchd{    listen              = 9312    read_timeout        = 5    max_children        = 30    max_matches         = 1000   # seamless_rotate    = 0  #windows下启动必须注释掉这行    preopen_indexes     = 0    unlink_old          = 1    pid_file            = ../log/searchd_mysql.pid  #请修改为实际使用的绝对路径，例如：/usr/local/coreseek/var/...    log                 = ../log/searchd_mysql.log        #请修改为实际使用的绝对路径，例如：/usr/local/coreseek/var/...    query_log           = ../log/query_mysql.log #请修改为实际使用的绝对路径，例如：/usr/local/coreseek/var/...}

4.生成索引，启动搜索

cmd下面运行下面代码：#-> indexer --config  config/sphinx.conf --all  #生成索引#-> searchd --config config/sphinx.conf  启动搜索

5.php里的配置

$cl = new SphinxClient ();$cl->SetServer ( '127.0.0.1', 9312);$cl->SetMatchMode ( SPH_MATCH_ANY );  //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  $cl->SetConnectTimeout ( 3 );$cl->SetArrayResult ( true );$weights = array('WebTitle'=>10, 'SubTitle'=>9, 'AddressNames'=>8, 'product_type_title'=>7);$cl->SetFieldWeights($weights);$cl->SetMaxQueryTime(10);   //最大搜索时间$res = $cl->Query ( $_GET['keyword'], "*" );  //"*"全部索引， 在conf文件中，会配置多个索引文件// 从名称为index的sphinx索引查询“电影票”$sp->SetGroupBy('item_id',SPH_GROUP_ATTR,'s_order desc');$sp->SetFilter('city_id','1');$sp->SetFilter('cat_id',array(1));$sp->SetLimit(0,10,1000);$sp->AddQuery('电影票','index');$sp->ResetFilters();//重置筛选条件$sp->SetGroupBy('item_id', SPH_GROUPBY_ATTR, 's_order desc');$sp->setFilter('city_id', '2');$sp->setFilter('cat_id', array(2));$sp->setLimits(0, 20, 1000);$sp->AddQuery('温泉', 'index');$sp->ResetFilters();// 重置筛选条件$sp->ResetGroupBy();//重置分组$results = $sp->RunQuries();