当前位置:首页 > 开发 > 行业应用 > 正文

Sphinx或coreseek做全文索引相关备忘

发表于: 2013-05-27   作者:bsr1983   来源:转载   浏览次数:
摘要: 1.下载sphinx或coreseek sphinx:http://sphinxsearch.com/ coreseek:http://www.coreseek.cn/ 2.配置 根据安装目录,修改配置文件中的索引配置目录 (1)sphinx配置,此处安装目录为C:/Sphinx/,支持中文的具体配置为: # # Minimal Sphinx configuration sa
1.下载sphinx或coreseek
sphinx:http://sphinxsearch.com/
coreseek:http://www.coreseek.cn/
2.配置
根据安装目录,修改配置文件中的索引配置目录
(1)sphinx配置,此处安装目录为C:/Sphinx/,支持中文的具体配置为:
#
# Minimal Sphinx configuration sample (clean, simple, functional)
#

source nickname_src
{
	type			= mysql

	sql_host		= 127.0.0.1
	sql_user		= root
	sql_pass		= root
	sql_db			= imeeta_utf8
	sql_port		= 3306	# optional, default is 3306

	sql_query		= \
		SELECT uid, nickname, birthday AS date_added \
		FROM user_info

	sql_attr_uint		= uid
	sql_field_string	=nickname
	sql_attr_timestamp	= date_added

	sql_query_info		= SELECT * FROM user_info WHERE uid=$id

	sql_query_pre       = SET NAMES utf8
}


index nickname_index
{
	source			= nickname_src
	path			= C:/Sphinx/nickname_data/nickname_index
	docinfo			= extern
	charset_type  = utf-8  
	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
}


index nickname_index_rt
{
	type			= rt
	rt_mem_limit		= 32M

	path			= C:/Sphinx/nickname_data/nickname_index_rt
	charset_type		= utf-8

	rt_field		= nickname
	rt_attr_uint		= uid
	rt_attr_string		= nickname
}


indexer
{
	mem_limit		= 32M
}


searchd
{
	listen			= 9312
	listen			= 9306:mysql41
	log			= C:/Sphinx/log/nickname_searchd.log
	query_log		= C:/Sphinx/log/nickname_query.log
	read_timeout		= 5
	max_children		= 30
	pid_file		= C:/Sphinx/log/nickname_searchd.pid
	max_matches		= 1000
	seamless_rotate		= 1
	preopen_indexes		= 1
	unlink_old		= 1
	workers			= threads # for RT to work
	binlog_path		= C:/Sphinx/nickname_data
}


(2)coreseek的具体配置为:
#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 nickname_src
{
    type                    = mysql
    sql_host                = localhost
    sql_user                = root
    sql_pass                = root
    sql_db                  = imeeta_utf8
    sql_port                = 3306
    sql_query                = SELECT uid, nickname \
		FROM user_info
    sql_attr_uint	= uid
    sql_field_string    = nickname
    sql_query_info	= SELECT uid,nickname FROM user_info WHERE uid=$id
    sql_query_pre       = SET NAMES utf8
}

#index定义
index nickname_index
{
    source			= nickname_src
    path			= C:/coreseek-4.1-win32/nickname_data/nickname_index
    docinfo			= extern
    #中文分词配置,详情请查看:http://www.coreseek.cn/products-install/coreseek_mmseg/
    #charset_dictpath = C:/coreseek-4.1-win32/mmseg3/etc/ #BSD、Linux环境下设置,/符号结尾
    charset_dictpath = C:/coreseek-4.1-win32/etc/                             #Windows环境下设置,/符号结尾,最好给出绝对路径,例如:C:C:/coreseek-4.1-win32/etc/...
    charset_type        = zh_cn.utf-8
}

#全局index定义
indexer
{
    mem_limit            = 128M
}

#searchd服务定义
searchd
{
	listen			= 9312
	listen			= 9306:mysql41
	log			= C:/coreseek-4.1-win32/log/nickname_searchd.log
	query_log		= C:/coreseek-4.1-win32/log/nickname_query.log
	read_timeout		= 5
	max_children		= 30
	pid_file		= C:/coreseek-4.1-win32/log/nickname_searchd.pid
	max_matches		= 1000
	seamless_rotate		= 1
	preopen_indexes		= 1
	unlink_old		= 1
	workers			= threads # for RT to work
	binlog_path		= C:/coreseek-4.1-win32/nickname_data
}

3.创建索引
命令:indexer -c 配置文件路径 -all
4.查询索引
将安装程序中的api文件夹下的java文件夹下的文件打包为jar
运行命令:
java -jar xxx.jar -h 服务ip -p 服务端口 查询内容
5.windows设置相关备忘
C:\coreseek-4.1-win32\bin\searchd.exe --ntservice --config C:\coreseek-4.1-win32\etc\gamepay_mysql.conf --servicename SphinxSearch

C:\Sphinx\bin\searchd.exe --ntservice --config C:\Sphinx\sphinx_nickname-min.conf --servicename SphinxSearch

indexer -c C:\coreseek-4.1-win32\etc\gamepay_mysql.conf gamepay_index

Sphinx或coreseek做全文索引相关备忘

  • 0

    开心

    开心

  • 0

    板砖

    板砖

  • 0

    感动

    感动

  • 0

    有用

    有用

  • 0

    疑问

    疑问

  • 0

    难过

    难过

  • 0

    无聊

    无聊

  • 0

    震惊

    震惊

编辑推荐
------------------------------------------------------------------------------------ 搜索分为
sphinx coreseek 使用安装的简单描述 1、简介 1.1.Sphinx是什么 Sphinx是由俄罗斯人Andrew Aksyonof
基于Sphinx+MySQL全文检索架构设计   前言:本文阐述的是一款经过生产环境检验的千万级数据全文检
1、什么是全文检索 全文检索是指以文档的全部文本信息作为检索对象的一种信息检索技术。检索的对象有
参考官网http://www.coreseek.cn/products-install/install_on_bsd_linux/ 下载coreseek:coreseek
参考官网http://www.coreseek.cn/products-install/install_on_bsd_linux/ 下载coreseek:coreseek
     昨天闲下来研究了MYSQL的索引优化,继而了解了MYSQL的全文检索,在大数据量下如果你使用li
git 创建仓库和本地与仓库关联 1.创建仓库(远端仓库) mkdir project # 创建项目目录 cd project #
导入一份数据: year out 1999 13736.4 16159.8 2000 18638.8 20634.4 2001 20159.2 22024.4 2002 2
1.安装JDK1.6 oracle官网从jdk1.7开始才有Mac版的安装包,但有的项目必须使用jdk1.6,所以必须从其
版权所有 IT知识库 CopyRight © 2009-2015 IT知识库 IT610.com , All Rights Reserved. 京ICP备09083238号