Discuz! X2 sphinx全文搜索安装配置实战

首先说明下我的使用环境：win2003 + coreseek 3.2.14 + gbk的mysql ，如有环境变更，请相应做些变更。
首先下载coreseek-3.2.14稳定版:
http://www.coreseek.cn/uploads/csft/3.2/coreseek-3.2.14-win32.zip

同时下载Microsoft Visual C++ 2005 运行环境 (x86)
http://www.microsoft.com/downloads/details.aspx?FamilyID=32bc1bee-a3f9-4c13-9c99-220b62a191ee&displaylang=zh-cn
如果您的win2003补丁更新的比较新，建议您用
Microsoft Visual C++ 2005 SP1 Redistributable Package (x86) 代替上面的，这是是SP1版本，我开始安装的上面的，运行coreseek后报indexer.exe应用程序出错，可能是跟比较高的系统补丁的兼容性的问题，我是升级到最新补丁的。这个地方 coreseek官方都没有更新说明，提醒大家注意。
http://www.microsoft.com/downloads/zh-cn/details.aspx?FamilyID=200B2FD9-AE1A-4A14-984D-389C36F85647

同样，如果您要用coreseek 4.0.1 这个最新版的，我也建议您下载Microsoft Visual C++ 2008的SP1版本，具体不再详述。

现在解压缩coreseek-3.2.14-win32.zip ，比如解压到D:/ coreseek/ ，现在我们切换到这个目录来说.

修改sphinx配置文件etc\csft.conf

#threads
source threads
{
type = mysql

    sql_host                = localhost
    sql_user                = root
    sql_pass                = 填入数据库密码
    sql_db                    = 填入你的discuz x2.0数据库名称
    sql_port                = 3306
    sql_query_pre            = SET NAMES UTF8     (这里如果数据库是GBK的就修改为gbk，下面所有SET NAME设置同这里)
    sql_query_pre           = SET SESSION query_cache_type=OFF
    sql_query_pre           = CREATE TABLE IF NOT EXISTS sph_counter ( counter_id INTEGER PRIMARY KEY NOT NULL,max_doc_id INTEGER NOT NULL)
    sql_query_pre            = REPLACE INTO sph_counter SELECT 1, MAX(tid)-100 FROM pre_forum_thread

    sql_query                = SELECT t.tid AS id,t.tid,t.subject,t.digest,t.displayorder,t.authorid,t.lastpost,t.special \
                                FROM pre_forum_thread AS t \
                                WHERE t.tid>=$start AND t.tid<=$end

sql_query_range = SELECT (SELECT MIN(tid) FROM pre_forum_thread),max_doc_id FROM sph_counter WHERE counter_id=1
sql_range_step = 4096

    sql_attr_uint            = tid
    sql_attr_uint            = digest
    sql_attr_uint            = displayorder
    sql_attr_uint            = authorid
    sql_attr_uint            = special

sql_attr_timestamp =lastpost

sql_query_info = SELECT * FROM pre_forum_thread WHERE tid=$id
}

#threads
index threads
{
    source            = threads
    path            = var/data/threads #windows下最好用全路径
    docinfo            = extern
    mlock            = 0
    morphology        = none
    #charset_dictpath = /usr/local/mmseg3/etc/    #BSD、Linux环境下设置，/符号结尾
    charset_dictpath= etc/                        #Windows环境下设置，/符号结尾
    charset_debug   =   0
#### 索引的词最小长度
min_word_len = 1
charset_type = utf-8    （这里如果是GBK数据库就修改为zh_cn.gbk ，下同）
html_strip = 0

##### 字符表，注意：如使用这种方式，则sphinx会对中文进行单字切分，
##### 即进行字索引，若要使用中文分词，必须使用其他分词插件如 coreseek，sfc
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
min_prefix_len = 0
min_infix_len = 1
ngram_len = 1

}

#threads_minute
source threads_minute : threads
{
    sql_query_pre            =
    sql_query_pre            = SET NAMES UTF8
    sql_query_pre           = SET SESSION query_cache_type=OFF

sql_query_range = SELECT max_doc_id+1,(SELECT MAX(tid) FROM pre_forum_thread) FROM sph_counter WHERE counter_id=1
}

#threads_minute
index threads_minute : threads
{
source = threads_minute
path = var/data/threads_minute #windows下最好用全路径
}

#posts
source posts : threads
{
type = mysql

    sql_query_pre            =
    sql_query_pre            = SET NAMES UTF8
    sql_query_pre           = SET SESSION query_cache_type=OFF
    sql_query_pre           = CREATE TABLE IF NOT EXISTS sph_counter ( counter_id INTEGER PRIMARY KEY NOT NULL,max_doc_id INTEGER NOT NULL)
    sql_query_pre            = REPLACE INTO sph_counter SELECT 2, MAX(pid)-5000 FROM pre_forum_post

    sql_query                = SELECT p.pid AS id,p.tid,p.subject,p.message,t.digest,t.displayorder,t.authorid,t.lastpost,t.special \
                                FROM pre_forum_post AS p LEFT JOIN pre_forum_thread AS t USING(tid) \
                                WHERE p.pid>=$start AND p.pid<=$end

sql_query_range = SELECT (SELECT MIN(pid) FROM pre_forum_post),max_doc_id FROM sph_counter WHERE counter_id=2
sql_range_step = 4096

    sql_attr_uint            = tid
    sql_attr_uint            = digest
    sql_attr_uint            = displayorder
    sql_attr_uint            = authorid
    sql_attr_uint            = special

sql_attr_timestamp =lastpost

sql_query_info = SELECT * FROM pre_forum_post WHERE pid=$id
}

#posts
index posts
{
    source            = posts
    path            = var/data/posts #windows下最好用全路径
    docinfo            = extern
    mlock            = 0
    morphology        = none
    #charset_dictpath = /usr/local/mmseg3/etc/    #BSD、Linux环境下设置，/符号结尾
    charset_dictpath= etc/                        #Windows环境下设置，/符号结尾
    charset_debug   =   0
#### 索引的词最小长度
min_word_len = 1
charset_type = utf-8
html_strip = 0

}

#posts_minute
source posts_minute : posts
{
    sql_query_pre            =
    sql_query_pre            = SET NAMES UTF8
    sql_query_pre           = SET SESSION query_cache_type=OFF

sql_query_range = SELECT max_doc_id+1,(SELECT MAX(pid) FROM pre_forum_post) FROM sph_counter WHERE counter_id=2
}

#posts_minute
index posts_minute : posts
{
source = posts_minute
path = var/data/posts_minute #windows下最好用全路径
}

#全局indexer定义
indexer
{
mem_limit = 256M
}

#searchd服务定义
searchd
{
    listen              = 3312
    read_timeout        = 5
    max_children        = 30
    max_matches            = 10000
    seamless_rotate        = 0
    preopen_indexes        = 0
    unlink_old            = 1
    pid_file            = var/log/searchd_discuzx.pid #windows下最好用全路径
    log                 = var/log/searchd_discuzx.log #windows下最好用全路径
    query_log           = var/log/query_discuzx.log #windows下最好用全路径
}

设置好csft.conf 后我们就可以点击test.cmd 开始生成索引并开启全文搜索服务了，此过程跟你的数据库大小有关系，耐心等待一会。

至此全文搜索服务器搭建好了，开始Discuz的设置
登录后台：全局 – 搜索开启全文搜索
这里要修改两个个地方，discuz自己写错了一个单词 threads_mintue 和posts_mintue
后面分钟的单词写错了，我不知道是不是他们故意的，邪恶下~~
分别修改为：threads_minute 和posts_minute

再要修改程序source\module\search\search_forum.php
找到237行左右
if($srchtype == 'fulltext' && $_G['setting']['sphinxon']) {

修改为：
// if($srchtype == 'fulltext' && $_G['setting']['sphinxon']) {
if($srchtxt && $_G['setting']['sphinxon']) {

对于要修改的原代码我习惯用//屏蔽，方便以后找回或者对照。
网上大部分说是直接用if($_G['setting']['sphinxon']) {
这样子是有问题的，就是搜索最新帖子的时候没有关键字，只能用系统自带的。

至此，discuz x2 的全文搜索就ok了，这个对于拥有独立服务器并且帖子数量相对多些的论坛非常有用，且占用服务器资源非常小。discuz x2 全文搜索演示站点：http://bbs.tumuzhe.com 土木者论坛。

本文由tumuzhe 原创，转摘请注明出处，谢谢！

本文出自 “土木者” 博客，请务必保留此出处http://2527925.blog.51cto.com/2517925/595830

秒客网

Discuz! X2 sphinx全文搜索安装配置实战

相关文章