Sphinx与mysql和sphinx与mongodb分别结合通过xmlpipe2 生成索引库的方法
来源:互联网 发布:java中重写equals方法 编辑:程序博客网 时间:2024/06/06 08:30
安装sphinx索引配置文件内容如下:/usr/local/etc/csft.conf
############### sphinx生成Mysql索引库数据库配置 ######################################
#Base sourcesource base_main{ type = mysql sql_host = 192.168.1.100 sql_user = root sql_pass = ******* sql_db = db_test sql_port = 3307 sql_query_pre = SET NAMES utf8 sql_query_pre = replace into index_delta select 2,'user',UNIX_TIMESTAMP() from user sql_query = SELECT SQL_NO_CACHE id as id, ctime,2 as type,title,alias_name FROM user where status=1 and mtime <= ( select max_mtime from index_delta where type='user' ) sql_attr_uint = type sql_attr_timestamp = ctime}
##########################基础数据字典############################################################
#Base indexindex topic_main_idx{ source = base_main path = /var/search/topic docinfo = extern mlock = 0 morphology = none min_word_len = 1 ngram_len = 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 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 #----------------- html_strip = 0}######################### mongodb存储数据生成递增内容索引库blog模块实例 ################################Blog delta index sourcesource blog_delta : base_main{ type = xmlpipe2 xmlpipe_command = cat /var/search/data/cache/sch_blog_delta.xml}#Blog delta indexindex blog_delta_idx : topic_main_idx{ source = blog_delta path = /var/search/blog_delta ngram_len = 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}
######################### mysql存储数据生成所有用户主索引库user模块做实例 ################################User main index sourcesource user_main : base_main{ sql_query_pre = SET NAMES utf8 sql_query_pre = replace into sch_index_delta select 4,'user',UNIX_TIMESTAMP() from sch_user sql_query = SELECT SQL_NO_CACHE uid as id, 4 as type,ctime, uname, identity_name FROM sch_user where mtime <= ( select max_mtime from sch_index_delta where type='user' ) sql_attr_uint = type sql_attr_timestamp = ctime}#User main indexindex user_main_idx : topic_main_idx{ source = user_main path = /var/search/user_main ngram_len = 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}######################### mysql存储数据生成增量用户主索引库user模块做实例 ################################User delta index sourcesource user_delta : base_main{ sql_query_pre = SET NAMES utf8 sql_query = SELECT SQL_NO_CACHE uid as id,4 as type,ctime, uname, identity_name FROM sch_user where mtime > ( select max_mtime from sch_index_delta where type='user' ) sql_attr_uint = type sql_attr_timestamp = ctime}#User delta indexindex user_delta_idx : topic_main_idx{ source = user_delta path = /var/search/user_delta ngram_len = 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}#################################################################global index indexer{ mem_limit = 256M max_iops = 0 write_buffer = 4M}#searchd servicesearchd{ listen = 9000 read_timeout = 5 max_children = 256 max_matches = 1000 seamless_rotate = 1 preopen_indexes = 0 unlink_old = 1 max_packet_size = 8M read_buffer = 1M pid_file = /var/search/log/searchd.pid log = /var/search/log/searchd.log query_log = /var/search/log/query.log #binlog_path = /var/search/log/}
注:
source blog_delta : base_main
{
type = xmlpipe2
xmlpipe_command = cat /var/search/data/cache/sch_blog_delta.xml
}
其中sch_blog_delta.xml数据格式为:
<?xml version="1.0" encoding="utf-8"?><sphinx:docset><sphinx:schema><sphinx:field name='id' /><sphinx:field name='title' /><sphinx:field name='type' /><sphinx:field name='str_test1_name' /><sphinx:field name='str_test2_name' /><sphinx:field name='ctime' /><sphinx:attr name='ctime' type='timestamp' /><sphinx:attr name='type' type='int' bits='32' default='1'/><sphinx:attr name='id' type='int' bits='32' default='1'/></sphinx:schema><sphinx:document id='14503'><title><![CDATA[[]]></title><type>3</type><str_test1_name><![CDATA[[]]></str_test1_name><str_test2_name><![CDATA[[]]></str_test2_name><ctime>2012-06-05 18:06</ctime></sphinx:document></sphinx:docset>
1)、 xmlpipe_command = cat /var/search/data/cache/sch_blog_all.xml
针对mongodb数据初始化一天生成一次全数据索引
2)、对增量数据每隔10分钟生成一次,其xml的内容格式与全索引格式内容一致生成数据为当天数据即可
xmlpipe_command = cat /var/search/data/cache/sch_blog_delta.xml
中文关键词分词包:
http://www.ftphp.com/scws/
- Sphinx与mysql和sphinx与mongodb分别结合通过xmlpipe2 生成索引库的方法
- sphinx 使用 python xmlpipe2 数据源 生成索引
- Sphinx搜索引擎架构与使用文档(和MySQL结合)
- sphinx xmlpipe2数据源配置
- Sphinx中通过mysql客户端访问Sphinx,实现实时索引,需要注意的要点
- coreeek 和 sphinx 的配置与使用
- sphinx索引生成
- sphinx mysql 增量索引
- sphinx mysql 增量索引
- sphinx安装、配置、索引与检索
- Solr与Sphinx的比较
- Solr与Sphinx的比较
- Solr与Sphinx的比较
- Solr与Sphinx的比较
- sphinx的安装与使用
- sphinx 的安装与应用
- Sphinx的安装、创建工程、生成文件与基本语法
- sphinx的实时索引
- iPhone中录制和播放声音
- DevExpress.XtraLayout.LayoutControl 动态添加控件
- 内核态下的设备文件操作(filp_open)
- 获取文件夹中的子文件夹或文件的名字以及路径
- 如何调整UIButton里面的文字位置
- Sphinx与mysql和sphinx与mongodb分别结合通过xmlpipe2 生成索引库的方法
- Java网络爬虫的实现
- poj 1250 Tanning Salon
- hdu1217
- 常用MySQL命令
- C# datagridview 连接服务器oracle数据库
- 关注网络安全
- Hadoop 2.0 安装向导
- htonl()_htons()及inet_ntoa()_inet_addr()的用法