sphinx （coreseek）——3、区段查询 与 增量索引实例

首先本文测试数据100多万的域名的wwwtitle 信息  检索数据：

• 首先建立临时表格:

CREATE TABLE `sph_counter` (
`index_id` tinyint(1) NOT NULL,
`max_id` int(11) NOT NULL,
PRIMARY KEY (`index_id`)
) ENGINE=MyISAM DEFAULT CHARSET=utf8

• csft.complex.conf 文件修改配置：

#增量数据索引 区段查询 合并为一个文件实现 测试 配置文件
#数据源
source src
{
        # data source type. mandatory, no default value
        # known types are mysql, pgsql, mssql, xmlpipe, xmlpipe2, odbc
        type                    = mysql

        #####################################################################
        ## SQL settings (for 'mysql' and 'pgsql' types)
        #####################################################################

        # some straightforward parameters for SQL source types
        sql_host                = localhost
        sql_user                = root
        sql_pass                = 201671zhuang
        sql_db                  = whomx
        sql_port                =   # optional, default is
        sql_query_pre          = SET NAMES utf8
        sql_query_pre          = SET SESSION query_cache_type=OFF
        sql_query_pre          = REPLACE INTO sph_counter SELECT , MAX(id) FROM mx_domain_wwwinfo
        #分次查询数据，不要一次将全部数据取
        sql_query_range         = SELECT MIN(id), (SELECT max_id FROM sph_counter WHERE index_id = ) FROM mx_domain_wwwinfo
        #每一次的 数据条数量
        sql_range_step          =
        sql_query               = \
                SELECT * \
                FROM mx_domain_wwwinfo \
                WHERE id>=$start AND id<=$end
         sql_query_info          = SELECT * FROM mx_domain_wwwinfo WHERE id=$id
}
# 表示增量数据源
source moresrc : src
{
        sql_query_pre          = SET NAMES utf8
        sql_query_pre          = SET SESSION query_cache_type=OFF
        #增量索引实现
        sql_query_range        = SELECT (SELECT max_id FROM sph_counter WHERE index_id=),MAX(id) from mx_domain_wwwinfo
        sql_range_step          =
        sql_query              = \
                SELECT * \
                FROM mx_domain_wwwinfo \
                WHERE id>=$start AND id<=$end
        sql_query_post                  = \
                REPLACE INTO sph_counter SELECT ,MAX(id) FROM mx_domain_wwwinfo
        #获取数据后，改写sph_counter增量索引计数表中的数据
}

#其他配置参照以前

•   更新主索引

 root@timeless-HP-Pavilion-g4-Notebook-PC:/usr/local/coreseek/bin# /usr/local/coreseek/bin/indexer -c /usr/local/coreseek/etc/csft.complex.conf  -all --rotate
Coreseek Fulltext 4.1 [ Sphinx 2.0.-dev (r2922)]
Copyright (c) -,
Beijing Choice Software Technologies Inc (http://www.coreseek.com)

 using config file '/usr/local/coreseek/etc/csft.complex.conf'...
indexing index 'src'...
WARNING: Attribute count is : switching to none docinfo
collected  docs, 117.1 MB
sorted 20.5 Mhits, 100.0% done
total  docs,  bytes
total 39.557 sec,  bytes/sec, 37941.06 docs/sec
indexing index 'moresrc'...
WARNING: Attribute count is : switching to none docinfo
collected  docs, 0.0 MB
sorted 0.0 Mhits, 100.0% done
total  docs,  bytes
total 0.001 sec,  bytes/sec, 632.51 docs/sec
total  reads, 0.047 sec, 3240.3 kb/call avg, 1.2 msec/call avg
total  writes, 0.216 sec, 834.8 kb/call avg, 0.8 msec/call avg
rotating indices: succesfully sent SIGHUP to searchd (pid=).

•  数据库mx_doimain_wwwinfo表格添加测试数据。更新增量索引

root@timeless-HP-Pavilion-g4-Notebook-PC:/usr/local/coreseek/bin# /usr/local/coreseek/bin/indexer moresrc -c /usr/local/coreseek/etc/csft.complex.conf --rotate
Coreseek Fulltext 4.1 [ Sphinx 2.0.-dev (r2922)]
Copyright (c) -,
Beijing Choice Software Technologies Inc (http://www.coreseek.com)

 using config file '/usr/local/coreseek/etc/csft.complex.conf'...
indexing index 'moresrc'...
WARNING: Attribute count is : switching to none docinfo
collected  docs, 0.0 MB
sorted 0.0 Mhits, 100.0% done
total  docs,  bytes
total 0.013 sec,  bytes/sec, 74.83 docs/sec
total  reads, 0.000 sec, 0.0 kb/call avg, 0.0 msec/call avg
total  writes, 0.000 sec, 0.0 kb/call avg, 0.0 msec/call avg
rotating indices: succesfully sent SIGHUP to searchd (pid=).

• 合并增量索引到主索引

root@timeless-HP-Pavilion-g4-Notebook-PC:/usr/local/coreseek/bin# /usr/local/coreseek/bin/indexer --merge src moresrc  -c /usr/local/coreseek/etc/csft.complex.conf --rotate
Coreseek Fulltext 4.1 [ Sphinx 2.0.-dev (r2922)]
Copyright (c) -,
Beijing Choice Software Technologies Inc (http://www.coreseek.com)

 using config file '/usr/local/coreseek/etc/csft.complex.conf'...
read 11.5 of 11.5 MB, 100.0% done
merged 2268.5 Kwords
merged in 2.724 sec
total  reads, 0.075 sec, 1.5 kb/call avg, 0.0 msec/call avg
total  writes, 0.110 sec, 253.4 kb/call avg, 0.2 msec/call avg
rotating indices: succesfully sent SIGHUP to searchd (pid=).

• 测试 增量索引

root@timeless-HP-Pavilion-g4-Notebook-PC:/usr/local/coreseek/bin# ./search -c /usr/local/coreseek/etc/csft.complex.conf 济南Coreseek Fulltext 4.1 [ Sphinx 2.0.-dev (r2922)]
Copyright (c) -,
Beijing Choice Software Technologies Inc (http://www.coreseek.com)

 using config file '/usr/local/coreseek/etc/csft.complex.conf'...
index 'src': query '济南 ': returned  matches of  total in 0.001 sec

displaying matches:
. document=, weight=
    id=
    domain_id=
    title=?????????????,??????,??????,?????????????????????????????????????,??????,??????,????,????,??????,??????,??????,??????,????????,????,??????,??????,??????,??????,????????,????????,?????????,?????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=??--??????,?????,????????,????????,??????,??????,?????,?????,???,?????,?????,?????,?????,????,????,??????,??????,??????,?????,?????,?????,???,???????,
    addtime=
. document=, weight=
    id=
    domain_id=
    title=???????-???.??.???.???????/?????/?????/?????????/?????/?????/???? ????? ????? ????? ????? ????? ????? ??POS??? ????? ????? ????? ??POS?
    addtime=
. document=, weight=
    id=
    domain_id=
    title=???????-???.??.???.???????/?????/?????/?????????/?????/?????/???? ????? ????? ????? ????? ????? ????? ??POS??? ????? ????? ????? ??POS?
    addtime=
. document=, weight=
    id=
    domain_id=
    title=?????? - ???? | ????? | ????? | ?????? | ?????? | ?????? | ?????? | ?????? | ?????? | ?????? | ?????? | ?????? | ?????? | ??????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????????|????????|?????????|?????????|??????|?????|????????????????|????????|?????????|?????????|??????|?????|????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=???????????????????????????????????????????????????????????????????????????????????????????????????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????|??????|????????|??????|??????|??????|??????|??????|??????|??????|??????-????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????????????????????????????????????????????????????????????????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=??????|??????|??SKF??|??NSK??|??FAG??|??NTN??|??KOYO??|??TIMKEN??|??FAG??|????|????????|????????|??????|-??
    addtime=
. document=, weight=
    id=
    domain_id=
    title=???????|??????????|???????|??????????|??????|???????|?????????|????????|?????????|???????|??????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=???? ?????? ?????? ?????? ????? ?????? ???? ???? ?????? ???? ??????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=??????|????|?????|?????????|???????????|??????|??????|????|?????|?????|?????|?????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=??????????????????????????????????????????????????????????????????????????????_??????????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=?????????????????????????????????????????????????????????????????????????_??????????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????????????????????????????????????????????????????????????????????????????_??????????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=??????|??????|??????|??????|??????|?????|??????|????????|???????????|????????????|???--
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????????? ???????????? ??????? ?????????? ??????? ??????? ????????? ??????? ??????? ???????_?????????
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????-|??????|??????????????|????????|???????|??????|????T1|????T3|????T6|????U8
    addtime=
. document=, weight=
    id=
    domain_id=
    title=????|?????|?????|?????|?????|?????|?????|?????|????|??????????
    addtime=

words:
#起作用
1. '济南': 11041 documents, 22216 hits

index 'moresrc': query '济南 ': returned 1 matches of 1 total in 0.000 sec

displaying matches:
1. document=1501042, weight=1500
    id=1501042
    domain_id=4
    title=????  ??
    addtime=

words:
1. '济南': 1 documents, 2 hits

增量索引起作用