Sphinx 2.2.3 安装和配置,英文数字中文搜索

本文涉及的产品
云数据库 RDS MySQL Serverless,0.5-2RCU 50GB
简介: 注:项目中,中文分词比较少,所以直接使用原版Sphinx 一元分词 作者:凨.FOX 编译前, 先要把mysql安装好。 开始安装sphinx tar zxvf sphinx-2.2.3-beta.tar.gzcd sphinx-2.2.3-beta./configure --prefix=/var/lanmps/sphinx --without-unixodbc --w

注:项目中,中文分词比较少,所以直接使用原版Sphinx 一元分词

作者:凨.FOX

编译前,
先要把mysql安装好。

开始安装sphinx

tar zxvf sphinx-2.2.3-beta.tar.gz
cd sphinx-2.2.3-beta
./configure --prefix=/var/lanmps/sphinx --without-unixodbc --with-mysql --enable-id64
make && make install

配置如下

#
# Minimal Sphinx configuration sample (clean, simple, functional)
#http://www.cnblogs.com/yjf512/p/3598332.html

source goods
{
	type			= mysql

	sql_host		= 127.0.0.1
	sql_user		= root
	sql_pass		= root
	sql_db			= zhaohuo
	sql_port		= 3306

	sql_query		= SELECT goods_id,name,specification,market,brand_name,cat_name,name as name_str FROM zh_goods

	#sql_attr_uint		= group_id
	sql_attr_string     = name_str
	sql_attr_string     = specification
	sql_attr_string     = market
	sql_attr_string     = brand_name
	sql_attr_string     = cat_name
	#sql_attr_timestamp	= date_added
}

index goods
{
	#type			= plain
	source			= goods
	path			= /var/lanmps/sphinx/var/data/goods
    docinfo         = extern
	mlock           = 0
	morphology      = none
	#wordforms      = /var/lanmps/sphinx/var/data/wordforms.txt
	
	min_word_len        = 1
	min_prefix_len      =1
	min_infix_len      =0
	expand_keywords   =1
	#charset_table     = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F
	charset_table = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
  A..Z->a..z, a..z, U+0149, U+017F, U+0138, U+00DF, U+00FF, U+00C0..U+00D6->U+00E0..U+00F6,\
  U+00E0..U+00F6, U+00D8..U+00DE->U+00F8..U+00FE, U+00F8..U+00FE, U+0100->U+0101, U+0101,\
  U+0102->U+0103, U+0103, U+0104->U+0105, U+0105, U+0106->U+0107, U+0107, U+0108->U+0109,\
  U+0109, U+010A->U+010B, U+010B, U+010C->U+010D, U+010D, U+010E->U+010F, U+010F,\
  U+0110->U+0111, U+0111, U+0112->U+0113, U+0113, U+0114->U+0115, U+0115, \
  U+0116->U+0117,U+0117, U+0118->U+0119, U+0119, U+011A->U+011B, U+011B, U+011C->U+011D,\
  U+011D,U+011E->U+011F, U+011F, U+0130->U+0131, U+0131, U+0132->U+0133, U+0133, \
  U+0134->U+0135,U+0135, U+0136->U+0137, U+0137, U+0139->U+013A, U+013A, U+013B->U+013C, \
  U+013C,U+013D->U+013E, U+013E, U+013F->U+0140, U+0140, U+0141->U+0142, U+0142, \
  U+0143->U+0144,U+0144, U+0145->U+0146, U+0146, U+0147->U+0148, U+0148, U+014A->U+014B, \
  U+014B,U+014C->U+014D, U+014D, U+014E->U+014F, U+014F, U+0150->U+0151, U+0151, \
  U+0152->U+0153,U+0153, U+0154->U+0155, U+0155, U+0156->U+0157, U+0157, U+0158->U+0159,\
  U+0159,U+015A->U+015B, U+015B, U+015C->U+015D, U+015D, U+015E->U+015F, U+015F, \
  U+0160->U+0161,U+0161, U+0162->U+0163, U+0163, U+0164->U+0165, U+0165, U+0166->U+0167, \
  U+0167,U+0168->U+0169, U+0169, U+016A->U+016B, U+016B, U+016C->U+016D, U+016D, \
  U+016E->U+016F,U+016F, U+0170->U+0171, U+0171, U+0172->U+0173, U+0173, U+0174->U+0175,\
  U+0175,U+0176->U+0177, U+0177, U+0178->U+00FF, U+00FF, U+0179->U+017A, U+017A, \
  U+017B->U+017C,U+017C, U+017D->U+017E, U+017E, U+0410..U+042F->U+0430..U+044F, \
  U+0430..U+044F,U+05D0..U+05EA, U+0531..U+0556->U+0561..U+0586, U+0561..U+0587, \
  U+0621..U+063A, U+01B9,U+01BF, U+0640..U+064A, U+0660..U+0669, U+066E, U+066F, \
  U+0671..U+06D3, U+06F0..U+06FF,U+0904..U+0939, U+0958..U+095F, U+0960..U+0963, \
  U+0966..U+096F, U+097B..U+097F,U+0985..U+09B9, U+09CE, U+09DC..U+09E3, U+09E6..U+09EF, \
  U+0A05..U+0A39, U+0A59..U+0A5E,U+0A66..U+0A6F, U+0A85..U+0AB9, U+0AE0..U+0AE3, \
  U+0AE6..U+0AEF, U+0B05..U+0B39,U+0B5C..U+0B61, U+0B66..U+0B6F, U+0B71, U+0B85..U+0BB9, \
  U+0BE6..U+0BF2, U+0C05..U+0C39,U+0C66..U+0C6F, U+0C85..U+0CB9, U+0CDE..U+0CE3, \
  U+0CE6..U+0CEF, U+0D05..U+0D39, U+0D60,U+0D61, U+0D66..U+0D6F, U+0D85..U+0DC6, \
  U+1900..U+1938, U+1946..U+194F, U+A800..U+A805,U+A807..U+A822, U+0386->U+03B1, \
  U+03AC->U+03B1, U+0388->U+03B5, U+03AD->U+03B5,U+0389->U+03B7, U+03AE->U+03B7, \
  U+038A->U+03B9, U+0390->U+03B9, U+03AA->U+03B9,U+03AF->U+03B9, U+03CA->U+03B9, \
  U+038C->U+03BF, U+03CC->U+03BF, U+038E->U+03C5,U+03AB->U+03C5, U+03B0->U+03C5, \
  U+03CB->U+03C5, U+03CD->U+03C5, U+038F->U+03C9,U+03CE->U+03C9, U+03C2->U+03C3, \
  U+0391..U+03A1->U+03B1..U+03C1,U+03A3..U+03A9->U+03C3..U+03C9, U+03B1..U+03C1, \
  U+03C3..U+03C9, U+0E01..U+0E2E,U+0E30..U+0E3A, U+0E40..U+0E45, U+0E47, U+0E50..U+0E59, \
  U+A000..U+A48F, 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 
	ngram_len     = 1
    #ngram_chars       = U+3000..U+2FA1F
	ngram_chars = U+FF10..U+FF19->0..9, 0..9, U+FF41..U+FF5A->a..z, U+FF21..U+FF3A->a..z,\
						A..Z->a..z, a..z,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	
	#phrase_boundary       = -,., ?, !, U+2026 # horizontal ellipsis
    #phrase_boundary_step  = 100
	blend_chars       = +, &, U+23
    blend_mode        = trim_tail, skip_pure
	html_strip      = 0
	## 字典文件是保持在磁盘上还是将他预先缓冲在内存中。
    # ondisk_dict       = 1
}


indexer
{
	mem_limit		= 256M
}


searchd
{
	listen			= 9312
	listen			= 9306:mysql41
	log			= /var/lanmps/sphinx/var/log/searchd.log
	query_log		= /var/lanmps/sphinx/var/log/query.log
	read_timeout		= 5
	max_children		= 30
	client_timeout      = 300
	pid_file		= /var/lanmps/sphinx/var/log/searchd.pid
	seamless_rotate		= 1
	preopen_indexes		= 1
	unlink_old		= 1
	workers			= threads # for RT to work
	binlog_path		= /var/lanmps/sphinx/var/data
	mva_updates_pool    = 1M
	max_packet_size     = 8M
	max_filters     = 256
	max_filter_values   = 4096
	max_batch_queries   = 32
}


因为是站在巨人们的肩膀上,要感谢N多人。

http://www.coreseek.cn/  其实我一直想用这个的,但是作者好长时间不更新了,ubuntu14.04竟然无法安装。

sphinx-for-chinese         这个我也使用过了,发现和项目有点不适合


相关实践学习
基于CentOS快速搭建LAMP环境
本教程介绍如何搭建LAMP环境,其中LAMP分别代表Linux、Apache、MySQL和PHP。
全面了解阿里云能为你做什么
阿里云在全球各地部署高效节能的绿色数据中心,利用清洁计算为万物互联的新世界提供源源不断的能源动力,目前开服的区域包括中国(华北、华东、华南、香港)、新加坡、美国(美东、美西)、欧洲、中东、澳大利亚、日本。目前阿里云的产品涵盖弹性计算、数据库、存储与CDN、分析与搜索、云通信、网络、管理与监控、应用服务、互联网中间件、移动服务、视频服务等。通过本课程,来了解阿里云能够为你的业务带来哪些帮助     相关的阿里云产品:云服务器ECS 云服务器 ECS(Elastic Compute Service)是一种弹性可伸缩的计算服务,助您降低 IT 成本,提升运维效率,使您更专注于核心业务创新。产品详情: https://www.aliyun.com/product/ecs
目录
相关文章
|
9月前
VS2019.NetCore智能提示英文改为中文
VS2019.NetCore智能提示英文改为中文
123 0
Redhat英文改为中文
Redhat英文改为中文
PHP:overtrue/pinyin 中文转拼音工具
PHP:overtrue/pinyin 中文转拼音工具
225 0
|
数据安全/隐私保护 Windows
Windows 技术篇-搜狗输入法中文状态下却输入为英文,原因及解决办法。明明是中文却输入不了中文,只能输入英文
Windows 技术篇-搜狗输入法中文状态下却输入为英文,原因及解决办法。明明是中文却输入不了中文,只能输入英文
919 0
Windows 技术篇-搜狗输入法中文状态下却输入为英文,原因及解决办法。明明是中文却输入不了中文,只能输入英文
|
Ubuntu 数据安全/隐私保护
ubuntu16.04在英文状态下安装中文语言包的过程(法一:图形界面的方式) 以及 安装中文语言包后无法选择汉语问题的解决
1、笔记本安装的ubuntu是桌面的,安装语言包非常方便,桌面版本选择 齿轮 --> System --> System Settings... --> Language Support 再选择中文语言包安装。
1544 0
|
机器学习/深度学习
Zebra 在SAP中的使用示例(中英文版本)
最近一段时间一直在研究Zebra Printer,这是一个专门用于打印标签的打印机。而作为制造企业来说是有很多标签需要来打印的:Production Label, Production Pre-Labels, Production Hazard Label, Production Address label, GR Label.....。
2208 0