为什么Sphinx查的数据比用SQL查还少?

时间:2021-08-15 19:33:28


本来想要的是模糊匹配

比如test

全部匹配test   优先级最高

少一个字匹配tes

再少一字匹配te

等等


select * from file where filename like'%test%';   --1029条

与Sphinx下面结果不一致? 更要命的是Sphinx搜的数据还少

下面结果257条   ,且这257条在SQL查的结果中全部有。

coreseek 4.1

<?php
// --------------------------------------------------------------------------
// File name : test_coreseek.php
// Description : coreseek中文全文检索系统测试程序
// Requirement : PHP5 (http://www.php.net)
//
// Copyright(C), HonestQiao, 2011, All Rights Reserved.
//
// Author: HonestQiao (honestqiao@gmail.com)
//
// 最新使用文档,请查看:http://www.coreseek.cn/products/products-install/
//
// --------------------------------------------------------------------------

require ( "sphinxapi.php" );
$cl = new SphinxClient ();
$cl->SetServer ( '127.0.0.1', 9312);
$cl->SetConnectTimeout ( 10 );
$cl->SetArrayResult ( true );
$cl->SetMatchMode ( SPH_MATCH_ALL);
//$cl->SetMatchMode ( SPH_MATCH_EXTENDED2);
$cl->SetLimits(0, 1000);
$info = 'test';
$res = $cl->Query($info, 'mysql');//shopstore_search
//print_r($cl);
//print_r($res);




//结果处理
if ( $res===false )
{
print "Query failed: " . $cl->GetLastError() . ".\n";

} else
{
if ( $cl->GetLastWarning() )
print "WARNING: " . $cl->GetLastWarning() . "\n\n";

print "Query '$info' retrieved $res[total] of $res[total_found] matches in $res[time] sec.<br>\n";
print "Query stats:\n";
if ( is_array($res["words"]) )
foreach ( $res["words"] as $word => $info )
print " '$word' found $info[hits] times in $info[docs] documents\n";
print "\n";

if ( is_array($res["matches"]) )
{
$n = 1;
print "Matches:<br>\n";
foreach ( $res["matches"] as $docinfo )
{
print "$n. doc_id=$docinfo[id], weight=$docinfo[weight]";
foreach ( $res["attrs"] as $attrname => $attrtype )
{
$value = $docinfo["attrs"][$attrname];
if ( $attrtype==SPH_ATTR_MULTI || $attrtype==SPH_ATTR_MULTI64 )
{
$value = "(" . join ( ",", $value ) .")";
} else
{
if ( $attrtype==SPH_ATTR_TIMESTAMP )
$value = date ( "Y-m-d H:i:s", $value );
}
print ", $attrname=$value";
}
print "<br>\n";
$n++;
}
}
}


#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
source mysql
{
type = mysql

sql_host = 我改了
sql_user = 我改了
sql_pass = 我改了
sql_db = wangpansou
sql_port = 3306
sql_query_pre = SET NAMES utf8

sql_query = SELECT id,id, filename, uk, category,weight,valid FROM file
#sql_query第一列id需为整数
#title、content作为字符串/文本字段,被全文索引
sql_attr_uint = id #从SQL读取到的值必须为整数
# sql_attr_timestamp = date_added #从SQL读取到的值必须为整数,作为时间属性

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 file WHERE id=$id #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:/WWW/coreseek/var/data/mysql #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
html_strip = 0

#中文分词配置,详情请查看:http://www.coreseek.cn/products-install/coreseek_mmseg/
#charset_dictpath = /usr/local/mmseg3/etc/ #BSD、Linux环境下设置,/符号结尾
charset_dictpath = E:/WWW/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 = zh_cn.utf-8
}

#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
preopen_indexes = 0
unlink_old = 1
pid_file = E:/WWW/coreseek/var/log/searchd_mysql.pid #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
log = E:/WWW/coreseek/var/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 = E:/WWW/coreseek/var/log/query_mysql.log #请修改为实际使用的绝对路径,例如:/usr/local/coreseek/var/...
binlog_path = #关闭binlog日志
}