sphinx一元索引配置

对于一般的数据库全文搜索应用，sphinx还是非常好用的。

搜了几篇文章，对中文的搜索基本上可以归结为2种方法

1，使用coreseek.cn的修改版. 支持中文的分词索引
2，blog.s135.com的方法，中文使用一元索引。在查询分析的时候，再使用中文分词，将词组写在查询语法里。这种方法比较简单，不hack原代码，而且分词也可以选择自己熟悉的方式。不过只支持utf8.（这样才能把单个汉字分出来建索引）

配置成功，记录下来

#
# Minimal Sphinx configuration sample (clean, simple, functional)
#


# 索引源 和 索引配置
source ts_ask
{
	type			= mysql
	sql_host		= 127.0.0.1
	sql_user		= root
	sql_pass		= 
	sql_db			= kmp
	sql_port		= 3306
	sql_query_pre		= SET NAMES utf8
        sql_query		= SELECT askId,uid,uname,title,infoId,cTime,readCount,status,type,digCount FROM ts_ask

	sql_attr_timestamp	= cTime
	sql_attr_uint		= uid
	sql_attr_uint		= readCount

	sql_query_info		= SELECT * FROM ts_ask WHERE askId=$id
}

index ts_ask
{
	source			= ts_ask
	path			= E:/sphinx/index/ts_ask
	docinfo			= extern
        mlock                   = 0
        morphology              = none
        html_strip              = 1

        min_word_len            = 1
        charset_type            = utf-8
        charset_table           = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F
        ngram_len              = 1
        ngram_chars            = U+3000..U+2FA1F
}

# 全局配置


indexer
{
	mem_limit				= 32M
}


searchd
{
	address					= 127.0.0.1
	port					= 3312
	log					= E:/sphinx/log/searchd.log
	query_log				= E:/sphinx/log/query.log
	read_timeout				= 5
	max_children				= 30
	pid_file				= E:/sphinx/log/searchd.pid
	max_matches				= 1000
#	seamless_rotate				= 0
	preopen_indexes				= 0
	unlink_old				= 1
}