周梦康 发表于 2014-11-25 4083 次浏览 标签 : redisCoreseekSphinx

背景:系统用户基数200万,高级用户可以创建小组,普通用户加入小组。目前来看,一个小组的用户数暂时不会超过10万。

需求:对某一个小组内的成员做搜索

两张表:

# 表:  group_member
# 字段:id gid uid stat create_time update_time
# 表:  user_profile
# 字段:uid name fans pingyin py

Coreseek配置:参考 http://www.coreseek.cn/docs/coreseek_3.2-sphinx_0.9.9.html

source group_member_pinyin
{
	type		= mysql
	sql_host	= 192.168.1.1
	sql_user	= root
	sql_pass	= 123456
	sql_db		= test
	sql_port	= 3306

	sql_query_pre	= SET NAMES utf8
	sql_query_pre	= SET SESSION query_cache_type=OFF
	sql_query_pre	= REPLACE INTO `sph_counter` SELECT 8,MAX(id) FROM `group_member`
	sql_query_range	= SELECT 1,max_doc_id FROM `sph_counter` WHERE `counter_id`=8
	sql_range_step	= 2000
	sql_ranged_throttle	= 300
	sql_query	    = SELECT g.id,g.stat,g.uid,g.gid,u.name,u.pinyin,u.py,u.fans FROM `group_member`as g,user_profile as u WHERE g.id>=$start AND g.id<=$end AND g.uid=u.id
	sql_attr_uint	= stat
	sql_attr_uint	= gid
	sql_attr_uint	= fans
}
source delta:group_member_pinyin
{
	sql_query_pre	= SET NAMES utf8
	sql_query_pre   = SET SESSION query_cache_type=OFF
	sql_query_range = select (SELECT max_doc_id FROM `sph_counter` WHERE `counter_id`=8), max(id) from group_member;
	sql_range_step  = 2000
	sql_ranged_throttle     = 300
	sql_query	= SELECT g.id,g.stat,g.uid,g.gid,u.name,u.pinyin,u.py,u.fans FROM `group_mobile_member`as g,user_profile as u WHERE g.id>=$start AND g.id<=$end AND g.uid=u.id
	sql_attr_uint	= stat
	sql_attr_uint	= gid
        sql_attr_uint   = fans
}
index group_member_pinyin
{
	source		= group_member_pinyin          
	path		= /xxx/sphinx/data/group_member_pinyin
	docinfo		= extern
	mlock		= 0
	morphology	= none
	min_word_len	= 1
	html_strip	= 0
	charset_type	= utf-8
	enable_star	= 1
	min_infix_len	= 2
	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

}
index delta:group_member_pinyin
{
	source		= delta
	path		= /xxx/sphinx/data/group_member_pinyin_delta
}
indexer
{
    mem_limit               = 128M
}
searchd
{
    listen                  = 192.168.1.1:9321
    read_timeout            = 5
    max_children            = 60
    max_matches             = 3000
    seamless_rotate         = 0
    preopen_indexes         = 0
    unlink_old              = 1
    pid_file                = /xxx/sphinx/log/searchd_group_member_pinyin.pid  
    log                     = /xxx/sphinx/log/searchd_group_member_pinyin.log       
    query_log               = /xxx/sphinx/log/query_group_member_pinyin.log 
}

先查看端口是否被占用,然后后台启动搜索监听

lsof -i:9321
/usr/local/coreseek/bin/indexer -c /xxx/sphinx/conf/group_member_pinyin.conf --all
/usr/local/coreseek/bin/searchd -c /data0/sphinx/conf/group_member_pinyin.conf

配置计划任务:

20 03 * * * root /usr/local/coreseek/bin/indexer -c /xxx/sphinx/conf/group_member_pinyin.conf --all --rotate
*/5 * * * * root /usr/local/coreseek/bin/indexer -c /data0/sphinx/conf/group_member_pinyin.conf delta --rotate

PHP调用:

/**
 * 小组内成员搜索
 * @param int       $gid              小组id
 * @param string    $query            搜索关键字
 * @param int       $type             用户类型
 * @param int       $page             分页
 * @param int       $pageSize         单页数目
 * @return array
 */
public static function searchMember($gid, $query, $type, $page = 1, $pageSize = 10)
{
	//定义返回数据的格式
    $return = array(
    	'info' => array('num' => 0), 
    	'item' => array()
    );

    $cl = new SphinxClient();
    $cl->SetServer('192.168.1.1', 9321);
    //设置匹配模式为匹配所有查询词
    $cl->SetMatchMode( SPH_MATCH_PHRASE );
    //设置排序索引字段
    $cl->SetSortMode( SPH_SORT_RELEVANCE, 'fans');
    //仅查询该小组内的成员
    $cl->SetFilter('gid',array($gid));
    //根据搜索的成员类型过滤
    if(in_array($type,array(1,2,3,4,5))){
        $cl->SetFilter('stat',array($type));
    }
    //设置分页
    $cl->SetLimits(($page - 1)*$pageSize, $pageSize, 1000);
    //在索引和增量索引信息中查询
    $rs = $cl->Query($query, 'group_member_pinyin, delta');

    if (isset($rs['matches'])) {
        $idsArr = array();
        foreach ($rs['matches'] as $id => $v) {
            $idsArr[] = $id;
        }
        //这里做排重是因为有的用户会重复加入索引未见里加入了,之后又退出了,然后在增量索引统计的时候又加入了,而此时完整索引里的数据还没来得及更新,就会出现一个用户两次加入了同一小组的情况
        $idsArr = array_unique($idsArr);
        $ids = implode(',',$idsArr);
        $andSql = "";
        if(in_array($type,array(1,2,3,4,5))){
            $andSql = " and stat=".$type;
        }
        //重新再查一次是防止有的用户在建立索引的时候还是正是用户,但是在搜索的时候已经退出小组了或者已经是黑名单了。
        $sql = "select DISTINCT uid,stat from group_member where gid = $gid and id in ($ids)".$andSql;
        $rows = SqlExecute::getAll($sql);

        if(count($rows) < 1){
            return $return;
        }

        $uids = array();

        foreach ($rows as $info) {
            $uids[] = $info['uid'];
        }

        $userClass = new User();
        $userInfoArr = $userClass->getUsersCacheInfo($uids);

        foreach ($rows as $n => $info) {
            $rows[$n]['name'] = $userInfoArr[$info['uid']]['uname'];
            //....其他业务
            $rows[$n]['next'] = L_API."user.get&id=".$info['uid'];
        }

        if (!empty($rows)) {
            $return['info']['num'] = $rs['total'];
            $return['item'] = $rows;
        }
    }

    return $return;
}

👇 下面是我的公众号,高质量的博文我会第一时间同步到公众号,给个关注吧!

评论列表

回复 康哥 2015-01-30 12:14:48
查看端口号是否被占用 netstat -pan | grep :80 或者 lsof -i:80
回复 康哥 2015-01-30 13:43:50
http://phpff.com/945.html