0

0

【实战】sphinx的配置文件

php中文网

php中文网

发布时间:2016-06-07 16:11:02

|

1596人浏览过

|

来源于php中文网

原创

#源定义source src1{ type = mysql sql_host = localhost sql_user = root sql_pass =password sql_db = test sql_sock = /usr/local/mysql/mysql.sock sql_query_pre = SET NAMES utf8 sql_query_pre = REPLACE INTO sph_counter SELECT 1, MAX(id) FROM do

#源定义
source src1
{
        type                    = mysql
        sql_host                = localhost
        sql_user                = root
        sql_pass                =password
        sql_db                  = test
        sql_sock                = /usr/local/mysql/mysql.sock
        sql_query_pre           = SET NAMES utf8
        sql_query_pre           = REPLACE INTO sph_counter SELECT 1, MAX(id) FROM documents
        sql_query               = \
                SELECT id, group_id, UNIX_TIMESTAMP(date_added) AS date_added, title, content \
                FROM documents where id<=(SELECT max_doc_id FROM sph_counter WHERE counter_id=1)
        sql_attr_uint           = group_id
        sql_attr_timestamp      = date_added
        sql_ranged_throttle     = 0
}



#######源
#tblpnr
source src2
{
        type                    = mysql
        sql_host                = localhost
        sql_user                = root
        sql_pass                =password
        sql_db                  = jinripnr
        sql_sock                = /usr/local/mysql/mysql.sock
        sql_query_pre           = SET NAMES utf8
				sql_query_pre         	= REPLACE INTO jinri.sph_counter SELECT 2, MAX(id),max(update_time) FROM tblpnr
        sql_query               = \
                SELECT id,orderno,pnr,ordertime FROM tblpnr where \
		update_time<=(SELECT last_time FROM jinri.sph_counter WHERE counter_id=2) 
        #字符串属性设置、需要过滤、排序的时候用到
	#sql_attr_uint           = 
        sql_attr_timestamp      = ordertime
	sql_attr_string		= orderno  #只检索orderno
	sql_field_string 	= pnr  
	#sql_field_string 用于全文即保存索引,sql_attr_string只用于检索即不保存索引
	
	#分区查询设置
	#sql_query_range = SELECT MIN(id),MAX(id) FROM tblpnr
	#sql_range_step = 500000
	#sql_query = SELECT * FROM tblpnr WHERE id>=$start AND id<=$end
  sql_ranged_throttle     = 0  #无时间间隔,单位是秒
}




#tblticketno
source src3
{
        type                    = mysql
        sql_host                = localhost
        sql_user                = root
        sql_pass                =password
        sql_db                  = jinritickno
        sql_sock                = /usr/local/mysql/mysql.sock
        sql_query_pre           = SET NAMES utf8
				sql_query_pre         	= REPLACE INTO jinri.sph_counter SELECT 3, MAX(id), \
				max(update_time) FROM tblticketno
        sql_query               = \
                SELECT id,orderno, ticketno,ordertime \
                FROM tblticketno where update_time<=(SELECT last_time FROM jinri.sph_counter \
		WHERE counter_id=3)
        #字符串属性设置、需要过滤、排序的时候用到
	#sql_attr_uint           = 
        sql_attr_timestamp      = ordertime
	sql_attr_string		= orderno  #只检索orderno
	sql_field_string	= ticketno 
	#sql_field_string 用于全文即保存索引,sql_attr_string只用于检索即不保存索引
  #分区查询设置
	#sql_query_range = SELECT MIN(id),MAX(id) FROM tblticketno
	#sql_range_step = 1000000
	#sql_query = SELECT * FROM tblticketno WHERE id>=$start AND id<=$end
  sql_ranged_throttle     = 0
}



#tblpassengername
source src4
{
        type                    = mysql
        sql_host                = localhost
        sql_user                = root
        sql_pass                =password
        sql_db                  = jinripname
        sql_sock                = /usr/local/mysql/mysql.sock
        sql_query_pre           = SET NAMES utf8
	sql_query_pre         	= REPLACE INTO jinri.sph_counter SELECT 4, MAX(id), \
				max(update_time) FROM tblpassengername
        sql_query               = \
                SELECT id,orderno, passengername,ordertime \
                FROM tblpassengername where update_time<=(SELECT last_time FROM jinri.sph_counter \
		WHERE counter_id=4)
        #字符串属性设置、需要过滤、排序的时候用到
	#sql_attr_uint           = 
        sql_attr_timestamp      = ordertime
	sql_attr_string		= orderno  #只检索orderno
	sql_field_string	= passengername 
	#sql_field_string 用于全文即保存索引,sql_attr_string只用于检索即不保存索引
        sql_ranged_throttle     = 0
}



#tblorderno
source src5
{
        type                    = mysql
        sql_host                = localhost
        sql_user                = root
        sql_pass                =password
        sql_db                  = jinriorderno
        sql_sock                = /usr/local/mysql/mysql.sock
        sql_query_pre           = SET NAMES utf8
        sql_query_pre           = REPLACE INTO jinri.sph_counter SELECT 5, MAX(id), \
                                max(update_time) FROM tblorderno
        sql_query               = \
                SELECT id,orderno,ordertime \
                FROM tblorderno where update_time<=(SELECT last_time FROM jinri.sph_counter \
                WHERE counter_id=5)
        #字符串属性设置、需要过滤、排序的时候用到
        #sql_attr_uint           =
        sql_attr_timestamp      = ordertime
        sql_field_string        = orderno
        #sql_field_string 用于全文即保存索引,sql_attr_string只用于检索即不保存索引
        sql_ranged_throttle     = 0
}


#tblpnr
source src2throttled : src2
{
	sql_ranged_throttle	= 100
}

#tblticketno
source src3throttled : src3
{
	sql_ranged_throttle	= 100
}

#tblpassengername
source src4throttled : src4
{
	sql_ranged_throttle	= 100
}

#tblorderno
source src5throttled : src5
{
	sql_ranged_throttle	= 100
}


########增量源
#tblpnr
source src2_delta:src2
{
        sql_query_pre           = SET NAMES utf8
	sql_query_pre         	= 
        sql_query               = \
               SELECT id,orderno, pnr,ordertime \
               FROM tblpnr where update_time>(SELECT last_time \
	       FROM jinri.sph_counter WHERE counter_id=2)
}


#tblticketno
source src3_delta:src3
{
        sql_query_pre           = SET NAMES utf8
	sql_query_pre         	= 
        sql_query               = \
               SELECT id,orderno, ticketno,ordertime \
               FROM tblticketno where update_time>(SELECT last_time  \
	       FROM jinri.sph_counter WHERE counter_id=3)
}


#tblpassengername
source src4_delta:src4
{
        sql_query_pre           = SET NAMES utf8
	sql_query_pre         	= 
        sql_query               = \
               SELECT id,orderno,passengername,ordertime \
               FROM tblpassengername where update_time>(SELECT last_time  \
	       FROM jinri.sph_counter WHERE counter_id=4)
}


#tblorderno
source src5_delta:src5
{
        sql_query_pre           = SET NAMES utf8
        sql_query_pre           =
        sql_query               = \
               SELECT id,orderno,ordertime \
               FROM tblorderno where update_time>(SELECT last_time  \
               FROM jinri.sph_counter WHERE counter_id=5)
}


######索引
#tblpnr
index src2
{
        source                  = src2
        path                    = /usr/local/sphinx/var/data/src2
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}

#tblticketno
index src3
{
        source                  = src3
        path                    = /usr/local/sphinx/var/data/src3
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}


#tblpassengername
index src4
{
        source                  = src4
        path                    = /usr/local/sphinx/var/data/src4
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+3000..U+2FA1F,U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}


#tblorderno
index src5
{
        source                  = src5
        path                    = /usr/local/sphinx/var/data/src5
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 1 #最小中缀,支持模糊查询
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+3000..U+2FA1F,U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}



######增量索引
#tblprn
index src2_delta
{
        source                  = src2_delta
        path                    = /usr/local/sphinx/var/data/src2_delta
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}

#tblticketno
index src3_delta
{
        source                  = src3_delta
        path                    = /usr/local/sphinx/var/data/src3_delta
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}

#tblpassengername

index src4_delta
{
        source                  = src4_delta
        path                    = /usr/local/sphinx/var/data/src4_delta
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 0 #最小中缀
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}


#tblorderno
index src5_delta
{
        source                  = src5_delta
        path                    = /usr/local/sphinx/var/data/src5_delta
        docinfo                 = extern
        dict                    = keywords
        mlock                   = 0
        morphology              = none
        min_word_len            = 1
        html_strip              = 0
        min_prefix_len = 0 #最小前缀
        min_infix_len = 1 #最小中缀,支持模糊查询
        ngram_len = 1 # 对于非字母型数据的长度切割,支持中文需要设置为1
        ngram_chars = U+4E00..U+9FBF, U+3400..U+4DBF, U+20000..U+2A6DF, U+F900..U+FAFF,U+2F800..U+2FA1F, U+2E80..U+2EFF, U+2F00..U+2FDF, U+3100..U+312F, U+31A0..U+31BF,U+3040..U+309F, U+30A0..U+30FF, U+31F0..U+31FF, U+AC00..U+D7AF, U+1100..U+11FF,U+3130..U+318F, U+A000..U+A48F, U+A490..U+A4CF
}


#########inherited index :索引继承 
#tblpnr
#index src2stemmed : src2
#{
#	path			= /usr/local/sphinx/var/data/src2stemmed
#	morphology		= stem_en
#}

#tblticketno
#index src3stemmed : src3
#{
#	path			= /usr/local/sphinx/var/data/src3stemmed
#	morphology		= stem_en
#}


#tblpassengername
#index src4stemmed : src4
#{
#	path			= /usr/local/sphinx/var/data/src4stemmed
#	morphology		= stem_en
#}

#########分布式搜索
#tblpnr
index dist2
{
        type                    = distributed
        local                   = src2
        local                   = src2_delta
}


#tblticketno
index dist3
{
        type                    = distributed
        local                   = src3
        local                   = src3_delta
}

#tblpassengername
index dist4
{
        type                    = distributed
        local                   = src4
        local                   = src4_delta
}


#orderno:intpu value include *,not support dist query
#index dist5
#{
#        type                    = distributed
#        local                   = src5
#        local                   = src5_delta
#}


index rt
{
        type                    = rt
        path                    = /usr/local/sphinx/var/data/rt
        rt_field                = title
        rt_field                = content
        rt_attr_uint            = gid
}

indexer
{
        mem_limit               = 1024M
}

searchd
{
#        listen                  = /var/run/searchd.sock
        listen                  = 127.0.0.1:9312:sphinx
        listen                  = 9306:mysql41
        listen                  = 192.168.0.128:9312:sphinx
        log                     = /usr/local/sphinx/var/log/searchd.log
        query_log               = /usr/local/sphinx/var/log/query.log
        read_timeout            = 5
        client_timeout          = 300
        max_children            = 30
        persistent_connections_limit    = 30
        pid_file                = /usr/local/sphinx/var/log/searchd.pid
        seamless_rotate         = 1 ### 是否支持无缝切换,做增量索引时通常需要
        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
        dist_threads            = 2

}
common
{
}

热门AI工具

更多
DeepSeek
DeepSeek

幻方量化公司旗下的开源大模型平台

豆包大模型
豆包大模型

字节跳动自主研发的一系列大型语言模型

通义千问
通义千问

阿里巴巴推出的全能AI助手

腾讯元宝
腾讯元宝

腾讯混元平台推出的AI助手

文心一言
文心一言

文心一言是百度开发的AI聊天机器人,通过对话可以生成各种形式的内容。

讯飞写作
讯飞写作

基于讯飞星火大模型的AI写作工具,可以快速生成新闻稿件、品宣文案、工作总结、心得体会等各种文文稿

即梦AI
即梦AI

一站式AI创作平台,免费AI图片和视频生成。

ChatGPT
ChatGPT

最最强大的AI聊天机器人程序,ChatGPT不单是聊天机器人,还能进行撰写邮件、视频脚本、文案、翻译、代码等任务。

相关专题

更多
java入门学习合集
java入门学习合集

本专题整合了java入门学习指南、初学者项目实战、入门到精通等等内容,阅读专题下面的文章了解更多详细学习方法。

2

2026.01.29

java配置环境变量教程合集
java配置环境变量教程合集

本专题整合了java配置环境变量设置、步骤、安装jdk、避免冲突等等相关内容,阅读专题下面的文章了解更多详细操作。

2

2026.01.29

java成品学习网站推荐大全
java成品学习网站推荐大全

本专题整合了java成品网站、在线成品网站源码、源码入口等等相关内容,阅读专题下面的文章了解更多详细推荐内容。

0

2026.01.29

Java字符串处理使用教程合集
Java字符串处理使用教程合集

本专题整合了Java字符串截取、处理、使用、实战等等教程内容,阅读专题下面的文章了解详细操作教程。

0

2026.01.29

Java空对象相关教程合集
Java空对象相关教程合集

本专题整合了Java空对象相关教程,阅读专题下面的文章了解更多详细内容。

3

2026.01.29

clawdbot ai使用教程 保姆级clawdbot部署安装手册
clawdbot ai使用教程 保姆级clawdbot部署安装手册

Clawdbot是一个“有灵魂”的AI助手,可以帮用户清空收件箱、发送电子邮件、管理日历、办理航班值机等等,并且可以接入用户常用的任何聊天APP,所有的操作均可通过WhatsApp、Telegram等平台完成,用户只需通过对话,就能操控设备自动执行各类任务。

25

2026.01.29

clawdbot龙虾机器人官网入口 clawdbot ai官方网站地址
clawdbot龙虾机器人官网入口 clawdbot ai官方网站地址

clawdbot龙虾机器人官网入口:https://clawd.bot/,clawdbot ai是一个“有灵魂”的AI助手,可以帮用户清空收件箱、发送电子邮件、管理日历、办理航班值机等等,并且可以接入用户常用的任何聊天APP,所有的操作均可通过WhatsApp、Telegram等平台完成,用户只需通过对话,就能操控设备自动执行各类任务。

16

2026.01.29

Golang 网络安全与加密实战
Golang 网络安全与加密实战

本专题系统讲解 Golang 在网络安全与加密技术中的应用,包括对称加密与非对称加密(AES、RSA)、哈希与数字签名、JWT身份认证、SSL/TLS 安全通信、常见网络攻击防范(如SQL注入、XSS、CSRF)及其防护措施。通过实战案例,帮助学习者掌握 如何使用 Go 语言保障网络通信的安全性,保护用户数据与隐私。

8

2026.01.29

俄罗斯Yandex引擎入口
俄罗斯Yandex引擎入口

2026年俄罗斯Yandex搜索引擎最新入口汇总,涵盖免登录、多语言支持、无广告视频播放及本地化服务等核心功能。阅读专题下面的文章了解更多详细内容。

622

2026.01.28

热门下载

更多
网站特效
/
网站源码
/
网站素材
/
前端模板

精品课程

更多
相关推荐
/
热门推荐
/
最新课程
Node.js 教程
Node.js 教程

共57课时 | 9.7万人学习

CSS3 教程
CSS3 教程

共18课时 | 5万人学习

Rust 教程
Rust 教程

共28课时 | 5.1万人学习

关于我们 免责申明 举报中心 意见反馈 讲师合作 广告合作 最新更新
php中文网:公益在线php培训,帮助PHP学习者快速成长!
关注服务号 技术交流群
PHP中文网订阅号
每天精选资源文章推送

Copyright 2014-2026 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号