ubuntu下的中文搜索sphinx实时索引的安装配置

06/04/2012 19:48:14Sphinx已关闭评论6,892字数 12861阅读42分52秒阅读模式

一.安装中文分词文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo wget -c http://www.coreseek.cn/uploads/csft/4.0/coreseek-4.0.1-beta.tar.gz文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo tar zxvf coreseek-4.0.1-beta.tar.gz -C ../software/文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ cd /usr/local/src/software/coreseek-4.0.1-beta/mmseg-3.2.14/文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo ./bootstrap文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo ./configure --prefix=/usr/local/mmseg-3.2.14文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo make文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo make install文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

二.安装sphinx文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ cd /usr/local/src/software/coreseek-4.0.1-beta/csft-4.0.1/文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo ./buildconf.sh文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo ./configure --prefix=/usr/local/csft-4.0.1 --with-mysql=/usr/local/mysql --with-mysql-includes=/usr/local/mysql/include --with-mysql-libs=/usr/local/mysql/lib --with-mmseg=/usr/local/mmseg-3.2.14 --with-mmseg-includes=/usr/local/mmseg-3.2.14/include/mmseg --with-mmseg-libs=/usr/local/mmseg-3.2.14/lib文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo make文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo make install文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

三.配置sphinx文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

$ sudo vim sphinx.conf文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

index bbs_post文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

{文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

type = rt文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

docinfo = extern文章源自运维生存时间-https://www.ttlsa.com/sphinx/install-sphinx-on-ubuntu/

mlock = 0

morphology = none

min_word_len = 1

html_strip = 0

charset_type = zh_cn.utf-8

charset_dictpath = /usr/local/mmseg-3.2.14/etc/

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_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

rt_field = message

rt_attr_uint = fid

rt_attr_uint = tid

rt_attr_uint = first

rt_attr_uint = invisible

rt_attr_uint = authorid

rt_attr_timestamp = dateline

rt_mem_limit = 512M

}

searchd

{

workers = threads

read_timeout = 30

max_children = 30

max_matches = 1000

seamless_rotate = 0

preopen_indexes = 0

unlink_old = 1

binlog_flush = 2

binlog_max_log_size = 16M

thread_stack = 128K

}

$ sudo /usr/local/csft-4.0.1/bin/searchd --config /usr/local/csft-4.0.1/etc/sphinx.conf

[sudo] password for ubuntu:

Coreseek Fulltext 4.0 [ Sphinx 1.11-dev (r2540)]

Beijing Choice Software Technologies Inc (http://www.coreseek.com)

using config file '/usr/local/csft-4.0.1/etc/sphinx.conf'...

listening on 127.0.0.1:9306

precaching index 'bbs_post'

precached 1 indexes in 0.001 sec

四.测试

$ mysql -h127.0.0.1 -P9306

Welcome to the MySQL monitor. Commands end with ; or \g.

Your MySQL connection id is 1

Server version: 1.11-dev (r2540)

Type 'help;' or '\h' for help. Type '\c' to clear the current input statement.

mysql> show tables;

+----------+------+

| Index | Type |

+----------+------+

| bbs_post | rt |

+----------+------+

1 row in set (0.00 sec)

mysql> desc bbs_post;

+-----------+-----------+

| Field | Type |

+-----------+-----------+

| id | integer |

| author | field |

| subject | field |

| message | field |

| fid | integer |

| tid | integer |

| first | integer |

| invisible | integer |

| authorid | integer |

| dateline | timestamp |

| author | string |

| subject | string |

| message | string |

+-----------+-----------+

13 rows in set (0.00 sec)

mysql> insert into bbs_post values (1,'默北','sphinx实时索引','测试sphinx实时索引',1,1,1,0,1,1311841260,'默北','sphinx实时索引','测试sphinx实时索引');

Query OK, 1 row affected (0.09 sec)

mysql> insert into bbs_post values (2,'帝弑天', '[贴图第一帖]我的照片', '[upload=jpg]UploadFile/2004-12/20041221233944671.jpg[/upload]\r\n\r\n不用怀疑抱的是猫\r\n[align=right][color=#000066][此贴子已经被作者于2004-12-21 23:41:44编辑过][/color][/align]\r',1,1,1,0,2,131184130,'帝弑天', '[贴图第一帖]我的照片', '[upload=jpg]UploadFile/2004-12/20041221233944671.jpg[/upload]\r\n\r\n不用怀疑抱的是猫\r\n[align=right][color=#000066][此贴子已经被作者于2004-12-21 23:41:44编辑过][/color][/align]\r');

Query OK, 1 row affected (0.00 sec)

mysql> select * from bbs_post;

+------+--------+------+------+-------+-----------+----------+------------+-----------+-------------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

| 1 | 1 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

| 2 | 1 | 1 | 1 | 1 | 0 | 2 | 131184130 | 帝弑天 | [贴图第一帖]我的照片 | [upload=jpg]UploadFile/2004-12/20041221233944671.jpg[/upload]

不用怀疑抱的是猫

|lign=right][color=#000066][此贴子已经被作者于2004-12-21 23:41:44编辑过][/color][/align]

mysql> select * from bbs_post where match('默北');

+------+--------+------+------+-------+-----------+----------+------------+--------+--------------------+--------------------------+

+------+--------+------+------+-------+-----------+----------+------------+--------+--------------------+--------------------------+

| 1 | 1643 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

+------+--------+------+------+-------+-----------+----------+------------+--------+--------------------+--------------------------+

1 row in set (0.00 sec)

mysql> select * from bbs_post where match('操蛋');

Empty set (0.00 sec)

mysql> insert into bbs_post values (5,'默北-2','2-sphinx实时索引','2-测试sphinx实时索引',1,1,1,0,1,1311841260,'默北-2','2-sphinx实时索引','2-测试sphinx实时索引');

Query OK, 1 row affected (0.00 sec)

mysql> select * from bbs_post;

| 1 | 1 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

| 2 | 1 | 1 | 1 | 1 | 0 | 2 | 131184130 | 帝弑天 | [贴图第一帖]我的照片 | [upload=jpg]UploadFile/2004-12/20041221233944671.jpg[/upload]

不用怀疑抱的是猫

|lign=right][color=#000066][此贴子已经被作者于2004-12-21 23:41:44编辑过][/color][/align]

| 5 | 1 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北-2 | 2-sphinx实时索引 | 2-测试sphinx实时索引 |

mysql> select * from bbs_post where match('默北');

+------+--------+------+------+-------+-----------+----------+------------+----------+----------------------+----------------------------+

+------+--------+------+------+-------+-----------+----------+------------+----------+----------------------+----------------------------+

| 1 | 1500 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

| 5 | 1500 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北-2 | 2-sphinx实时索引 | 2-测试sphinx实时索引 |

+------+--------+------+------+-------+-----------+----------+------------+----------+----------------------+----------------------------+

2 rows in set (0.00 sec)

mysql> replace into bbs_post values (5,'默北-2','操蛋','2-测试sphinx实时索引',1,1,1,0,1,1311841260,'默北-2','操蛋','2-测试sphinx实时索引');

Query OK, 1 row affected (0.00 sec)

mysql> select * from bbs_post where match('默北');

+------+--------+------+------+-------+-----------+----------+------------+----------+--------------------+----------------------------+

+------+--------+------+------+-------+-----------+----------+------------+----------+--------------------+----------------------------+

| 1 | 1500 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

| 5 | 1500 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北-2 | 操蛋 | 2-测试sphinx实时索引 |

+------+--------+------+------+-------+-----------+----------+------------+----------+--------------------+----------------------------+

2 rows in set (0.00 sec)

mysql> select * from bbs_post where match('操蛋');

+------+--------+------+------+-------+-----------+----------+------------+----------+---------+----------------------------+

+------+--------+------+------+-------+-----------+----------+------------+----------+---------+----------------------------+

| 5 | 1680 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北-2 | 操蛋 | 2-测试sphinx实时索引 |

+------+--------+------+------+-------+-----------+----------+------------+----------+---------+----------------------------+

1 row in set (0.00 sec)

mysql> select * from bbs_post;

| 1 | 1 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北 | sphinx实时索引 | 测试sphinx实时索引 |

| 2 | 1 | 1 | 1 | 1 | 0 | 2 | 131184130 | 帝弑天 | [贴图第一帖]我的照片 | [upload=jpg]UploadFile/2004-12/20041221233944671.jpg[/upload]

不用怀疑抱的是猫

|lign=right][color=#000066][此贴子已经被作者于2004-12-21 23:41:44编辑过][/color][/align]

| 5 | 1 | 1 | 1 | 1 | 0 | 1 | 1311841260 | 默北-2 | 操蛋 | 2-测试sphinx实时索引 |

3 rows in set (0.00 sec)

我的微信

微信公众号

扫一扫关注运维生存时间公众号，获取最新技术文章~

ubuntu下的中文搜索sphinx实时索引的安装配置

Haproxy+keepalived实现sphinx高可用负载均衡

全文索引sphinx通用配置

ubuntu 将第三方模块编译到nginx包中

ubuntu / centos6 error: “net.ipv4.ip_conntrack_max” is an unknown key