安装sphinx中文分词coreseek
一、获取coreseek安装包
目前，CoreSeek/Sphinx的发布包包括如下软件：
indexer: 用于创建全文索引;
search: 一个简单的命令行(CLI) 的测试程序，用于测试全文索引;
searchd: 一个守护进程，其他软件（例如WEB程序）可以通过这个守护进程进行全文检索;
sphinxapi: 一系列searchd 的客户端API 库，用于流行的Web脚本开发语言(PHP, Python, Perl, Ruby, Java).
spelldump: 一个简单的命令行工具，用于从 ispell 或者 MySpell (OpenOffice内置绑定) 格式的字典中提取词条。当使用 wordforms时可用这些词条对索引进行定制.
indextool: 工具程序，用来转储关于索引的多项调试信息。此工具是从版本Coreseek 3.1(Sphinx 0.9.9-rc2)开始加入的。
mmseg: 工具程序和库，Coreseek用于提供中文分词和词典处理
二、编译安装coreseek
1、将你下载的tar包解压，并进入coreseek 子目录：
$ tar zxvf coreseek-4.1-beta.tar.gz
$ cd coreseek-4.1-beta
2、首先安装MMSeg:
$ cd mmseg-3.2.14
$ ./configure --prefix=/usr/local/mmseg3
$ make
提示错误：config.status: error: cannot find input file: `src/Makefile.in'
通过网上参考资料，输入以下命令后就解决了：
[stevelee@liyuanchun mmseg-3.2.14]$ aclocal
[stevelee@liyuanchun mmseg-3.2.14]$ libtoolize –force
[stevelee@liyuanchun mmseg-3.2.14]$ automake –add-missing
[stevelee@liyuanchun mmseg-3.2.14]$ autoconf
[stevelee@liyuanchun mmseg-3.2.14]$ autoheader
[stevelee@liyuanchun mmseg-3.2.14]$ make clean
[stevelee@liyuanchun mmseg-3.2.14]$ ./configure --prefix=/usr/local/share/mmseg3
[stevelee@liyuanchun mmseg-3.2.14]$ make
[stevelee@liyuanchun mmseg-3.2.14]$ sudo make install
3、安装coreseek:
$ cd ../csft-4.1
$ ./buildconf.sh
$ ./configure --prefix=/usr/local/sphinx --without-unixodbc --with-mmseg --with-mmseg-includes=/usr/local/mmseg3/include/mmseg/ --with-mmseg-libs=/usr/local/mmseg3/lib/ --with-mysql
$ make
$ make install
4、配置mmseg中文分词
$ cd /usr/local/mmseg3
$ ./bin/mmseg -u /usr/local/mmseg3/etc/unigram.txt (将会生成unigram.txt.uni)
$ vi etc/mmseg.ini
[mmseg]
merge_number_and_ascii=0; ;合并英文和数字 abc123/x
number_and_ascii_joint=; ;定义可以连接英文和数字的字符
compress_space=1; ;暂不支持
seperate_number_ascii=0; ;将字母和数字打散
$ cp etc/mmseg.ini /usr/local/sphinx/dict/mmseg.ini(复制到sphinx/dict目录)
$ cp etc/unigram.txt.uni /usr/local/sphinx/dict/uni.lib(复制到sphinx/dict目录)
注:coreseek4.1中已自带上面两个文件，直接复制到sphinx/dict目录下即可
5、配置coreseek索引文件
$ cd /usr/local/sphinx
$ vi csft.conf
# Minimal Sphinx configuration sample (clean, simple, functional)
source src1
{
type = mysql
sql_host = localhost
sql_user = test
sql_pass =
sql_db = test
sql_port = 3306
sql_query_pre = SET NAMES UTF8(SET SESSION query_cache_type=OFF可以关闭sql查询缓存)
sql_query = SELECT id,group_id,UNIX_TIMESTAMP(date_added) AS date_added,title,content FROM documents #title和content作为字符串/文本字段被全文索引
sql_attr_uint = group_id #从SQL读取到的值必须为整数
sql_attr_timestamp = date_added #从SQL读取到的值必须为时间属性整数
sql_query_info_pre = SET NAMES UTF8#命令行查询时设置正确字符集
sql_query_info = SELECT * FROM documents WHERE id=$id #命令行查询时，从数据库读取原始数据信息
}
index test1
{
source = src1
path = /usr/local/sphinx/var/data/test1
docinfo = extern
mlock = 0
morphology = none
min_word_len = 1
html_strip = 0
# 中文分词设置
charset_type = zh_cn.utf-8
charset_dictpath = /usr/local/sphinx/dict/
ngram_len = 0
}
index testrt
{
type = rt
rt_mem_limit = 32M
path = /usr/local/sphinx/var/data/testrt
rt_field = title
rt_field = content
rt_attr_uint = group_id #从SQL读取到的值必须为整数
# 中文分词设置
charset_type = zh_cn.utf-8
charset_dictpath = /usr/local/sphinx/dict/
ngram_len = 0
}
indexer
{
mem_limit = 32M
}
searchd
{
listen = 9312
listen = 9306:mysql41
log = /usr/local/sphinx/var/log/searchd.log
query_log = /usr/local/sphinx/var/log/query.log
read_timeout = 5
max_children = 30
pid_file = /usr/local/sphinx/var/log/searchd.pid
max_matches = 1000
seamless_ratate = 1
preopen_indexes = 1
unlink_old = 1
workers = threads # for RT to work
}
6、一元分词
index test
{
type = rt
rt_mem_limit = 512M
docinfo = extern
mlock = 0
morphology = none
min_word_len = 1
html_strip = 0
path = /data/sphinx/var/data/rt/test
rt_field = name
rt_field = introduction
rt_attr_uint = gid
# charset_dictpath = /usr/local/mmseg3/etc/
charset_type = utf-8
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
}
indexer
{
mem_limit = 512M
}
searchd
{
listen = 9312
listen = 9306:mysql41
read_timeout = 1800
max_children = 30
max_matches = 1000
seamless_rotate = 1
preopen_indexes = 0
unlink_old = 1
log = /data/sphinx/var/log/searchd.log
query_log = /data/sphinx/var/log/query.log
pid_file = /data/sphinx/var/log/searchd.pid
workers = threads
}
三、测试coreseek
1、建立索引
$ ./usr/local/sphinx/bin/indexer --all (建立所有索引)
$ ./usr/local/sphinx/bin/searchd (开启sphinx守护进程)
$ ./usr/local/sphinx/bin/search -c /usr/local/sphinx/etc/csft.conf -i test1 测试 (使用csft.conf配置文件的test1索引匹配含有 '测试' 的记录)
2、 RT实时索引
$ mysql -h 127.0.0.1 -P 9306
四、参考资料
coreseek参考手册 ：http://www.coreseek.cn/docs/coreseek_4.1-sphinx_2.0.1-beta.html#getting
coreseek核心配置 ：http://www.coreseek.cn/products-install/coreseek_mmseg/
php-sphinx扩展安装 ：http://linux008.blog.51cto.com/2837805/622171
sphinx RT实时索引API：http://www.sphinxsearch.org/sphinx-realtime-api