golang全文搜索--使用sphinx

不多废话,测试环境 ubuntu 13.10

安装

sudo apt-get install sphinxsearch

配置

nano /etc/sphinxsearch/sphinx.conf

# 数据源配置
source default
{
        type                            = xmlpipe2
        xmlpipe_command                 = /path/xmlpipe2
        xmlpipe_fixup_utf8              = 1
}

# 索引配置
index default
{
        type                    = plain
        source                  = default

        # 索引文件路径
        path                    = /path/filename

        # 不存储文档信息
        docinfo                 = none

        #最小索引词长度
        min_word_len            = 2

        charset_type            = utf-8

        # 指定utf-8的编码表
        charset_table  = 0..9, A..Z->a..z, _, a..z, U+410..U+42F->U+430..U+44F, U+430..U+44F

        # 简单分词，只支持0和1，如果要搜索中文，请指定为1
        ngram_len    = 1

        # 需要分词的字符，如果要搜索中文，去掉前面的注释
        ngram_chars   = U+3000..U+2FA1F

}

xmlpipe2的格式

<!--?xml version="1.0" encoding="utf-8"?-->
<sphinx:docset>

<!-- 文档模式 -->
<sphinx:schema>
  <!-- 全文数据字段 -->
  <sphinx:field name="content"> 
</sphinx:field></sphinx:schema>

<!-- 文档内容 -->
<sphinx:document id="1">
  <!-- content字段 -->
  <content><!--[CDATA[[文档内容,这是内容内容!11111111]]--></content>
</sphinx:document>
<!-- 更多的内容 -->
<sphinx:document id="2">
  ...
</sphinx:document>
...
...
...
</sphinx:docset>

只要配置文件中 xmlpipe_command 字段配置的可执行文件输出为相应的xml流即可,这样几乎适配了所有数据源

生成索引

$ indexer default

Sphinx 2.0.4-release (r3135)
Copyright (c) 2001-2012, Andrew Aksyonoff
Copyright (c) 2008-2012, Sphinx Technologies Inc (http://sphinxsearch.com)

using config file '/etc/sphinxsearch/sphinx.conf'...
indexing index 'default'...
WARNING: Attribute count is 0: switching to none docinfo
WARNING: collect_hits: mem_limit=0 kb too low, increasing to 12288 kb
collected 4 docs, 0.0 MB
sorted 0.0 Mhits, 100.0% done
total 4 docs, 47 bytes
total 0.000 sec, 54970 bytes/sec, 4678.36 docs/sec
total 2 reads, 0.000 sec, 0.0 kb/call avg, 0.0 msec/call avg
total 6 writes, 0.000 sec, 0.0 kb/call avg, 0.0 msec/call avg

查询

$ search 55

Sphinx 2.0.4-release (r3135)
Copyright (c) 2001-2012, Andrew Aksyonoff
Copyright (c) 2008-2012, Sphinx Technologies Inc (http://sphinxsearch.com)

using config file '/etc/sphinxsearch/sphinx.conf'...
index 'default': query '55 ': returned 1 matches of 1 total in 0.000 sec

displaying matches:
1. document=233221, weight=1695

words:
1. '55': 1 documents, 1 hits

配置searchd

编辑sphinx配置文件,添加:

监听地址

searchd
{
    # 监听地址(Unix socket)
    listen = /var/log/searchd.sock

    # 日志文件
    log = /var/log/searchd.log

    # 查询日志
    query_log = /var/log/query.log

    # 客户端读取超时时间
    read_timeout = 5

    # 客户端请求超时时间
    client_timeout = 3000

    # PID 文件
    pid_file = /var/log/searchd.pid
}

运行searchd

$ sudo searchd

Sphinx 2.0.4-release (r3135)
Copyright (c) 2001-2012, Andrew Aksyonoff
Copyright (c) 2008-2012, Sphinx Technologies Inc (http://sphinxsearch.com)

using config file '/etc/sphinxsearch/sphinx.conf'...
WARNING: compat_sphinxql_magics=1 is deprecated; please update your application and config
listening on UNIX socket /var/log/searchd.sock
precaching index 'default'
precached 1 indexes in 0.000 sec

验证一下状态

$ searchd --status

Sphinx 2.0.4-release (r3135)
Copyright (c) 2001-2012, Andrew Aksyonoff
Copyright (c) 2008-2012, Sphinx Technologies Inc (http://sphinxsearch.com)

using config file '/etc/sphinxsearch/sphinx.conf'...

searchd status
--------------
uptime: 7 
connections: 1 
maxed_out: 0

golang客户端

package main

import (
    "github.com/yunge/sphinx"
    "log"
)

func main() {
    // 链接参数
    opts := &sphinx.Options{
        Socket: "/var/log/searchd.sock",
        Timeout: 5000,
    }

    // 创建客户端
    spClient := &sphinx.Client{Options: opts}
    if err := spClient.Error(); err != nil {
        log.Fatal(err)
    }

    // 打开链接
    if err := spClient.Open(); err != nil {
        log.Fatal(err)
    }

    // 获取实例信息
    status, err := spClient.Status()
    if err != nil {
        log.Fatal(err)
    }

    for _, row := range status {
        log.Printf("%20s:\t%s\n", row[0], row[1])
    }

    // 查询
res, err := spClient.Query("33", "default", "Test Query()")
if err != nil {
    log.Fatal(err)
}

log.Println(res)
}

输出:

2013/12/05 01:14:55               uptime:   148
2013/12/05 01:14:55          connections:   2
2013/12/05 01:14:55            maxed_out:   0
2013/12/05 01:14:55       command_search:   0
2013/12/05 01:14:55      command_excerpt:   0
2013/12/05 01:14:55       command_update:   0
2013/12/05 01:14:55     command_keywords:   0
2013/12/05 01:14:55      command_persist:   2
2013/12/05 01:14:55       command_status:   2
2013/12/05 01:14:55   command_flushattrs:   0
2013/12/05 01:14:55        agent_connect:   0
2013/12/05 01:14:55          agent_retry:   0
2013/12/05 01:14:55              queries:   0
2013/12/05 01:14:55         dist_queries:   0
2013/12/05 01:14:55           query_wall:   0.000
2013/12/05 01:14:55            query_cpu:   OFF
2013/12/05 01:14:55            dist_wall:   0.000
2013/12/05 01:14:55           dist_local:   0.000
2013/12/05 01:14:55            dist_wait:   0.000
2013/12/05 01:14:55          query_reads:   OFF
2013/12/05 01:14:55         query_readkb:   OFF
2013/12/05 01:14:55       query_readtime:   OFF
2013/12/05 01:14:55       avg_query_wall:   0.000
2013/12/05 01:14:55        avg_query_cpu:   OFF
2013/12/05 01:14:55        avg_dist_wall:   0.000
2013/12/05 01:14:55       avg_dist_local:   0.000
2013/12/05 01:14:55        avg_dist_wait:   0.000
2013/12/05 01:14:55      avg_query_reads:   OFF
2013/12/05 01:14:55     avg_query_readkb:   OFF
2013/12/05 01:14:55   avg_query_readtime:   OFF
2013/12/05 01:14:55 &amp;{[content] [] [] [] 1 1 0.001 [{33 1 1}]  <nil> 0}

api参考 http://gowalker.org/github.com/yunge/sphinx

sphinx配置参考 http://www.coreseek.cn/docs/coreseek_4.1-sphinx_2.0.1-beta.html