(1
)在
hadoop102
的
/home/atguigu/bin
目录下创建脚本
[atguigu@hadoop102 bin]$ vim ods_to_dwd_log.sh
在脚本中编写如下内容
#!/bin/bash
hive=/opt/module/hive/bin/hive
APP=gmall
#
如果是输入的日期按照取输入日期;如果没输入日期取当前时间的前一天
if [ -n "$1" ] ;then
do_date=$1
else
do_date=`date -d "-1 day" +%F`
fi
sql="
SET mapreduce.job.queuename=hive;
SET hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFo
rmat;
insert overwrite table ${APP}.dwd_start_log
partition(dt='$do_date')
select
get_json_object(line,'$.common.ar'),
get_json_object(line,'$.common.ba'),
get_json_object(line,'$.common.ch'),
get_json_object(line,'$.common.md'),
get_json_object(line,'$.common.mid'),
get_json_object(line,'$.common.os'),
get_json_object(line,'$.common.uid'),
get_json_object(line,'$.common.vc'),
get_json_object(line,'$.start.entry'),
get_json_object(line,'$.start.loading_time'),
get_json_object(line,'$.start.open_ad_id'),
get_json_object(line,'$.start.open_ad_ms'),
get_json_object(line,'$.start.open_ad_skip_ms'),
get_json_object(line,'$.ts')
from ${APP}.ods_log
where dt='$do_date'
and get_json_object(line,'$.start') is not null;
insert overwrite table ${APP}.dwd_action_log
partition(dt='$do_date')
select
get_json_object(line,'$.common.ar'),
get_json_object(line,'$.common.ba'),
get_json_object(line,'$.common.ch'),
get_json_object(line,'$.common.md'),
get_json_object(line,'$.common.mid'),
get_json_object(line,'$.common.os'),
get_json_object(line,'$.common.uid'),
get_json_object(line,'$.common.vc'),
get_json_object(line,'$.page.during_time'),
get_json_object(line,'$.page.item'),
get_json_object(line,'$.page.item_type'),
get_json_object(line,'$.page.last_page_id'),
get_json_object(line,'$.page.page_id'),
get_json_object(line,'$.page.sourceType'),
get_json_object(action,'$.action_id'),
get_json_object(action,'$.item'),
get_json_object(action,'$.item_type'),
get_json_object(action,'$.ts')
from ${APP}.ods_log lateral view
${APP}.explode_json_array(get_json_object(line,'$.actions'))
tmp as action
where dt='$do_date'
and get_json_object(line,'$.actions') is not null;
insert overwrite table ${APP}.dwd_display_log
partition(dt='$do_date')
select
get_json_object(line,'$.common.ar'),
get_json_object(line,'$.common.ba'),
get_json_object(line,'$.common.ch'),
get_json_object(line,'$.common.md'),
get_json_object(line,'$.common.mid'),
get_json_object(line,'$.common.os'),
get_json_object(line,'$.common.uid'),
get_json_object(line,'$.common.vc'),
get_json_object(line,'$.page.during_time'),
get_json_object(line,'$.page.item'),
get_json_object(line,'$.page.item_type'),
get_json_object(line,'$.page.last_page_id'),
get_json_object(line,'$.page.page_id'),
get_json_object(line,'$.page.sourceType'),
get_json_object(line,'$.ts'),
get_json_object(display,'$.displayType'),
get_json_object(display,'$.item'),
get_json_object(display,'$.item_type'),
get_json_object(display,'$.order')
from ${APP}.ods_log lateral view
${APP}.explode_json_array(get_json_object(line,'$.displays'))
tmp as display
where dt='$do_date'
and get_json_object(line,'$.displays') is not null;
insert overwrite table ${APP}.dwd_page_log
partition(dt='$do_date')
select
get_json_object(line,'$.common.ar'),
get_json_object(line,'$.common.ba'),
get_json_object(line,'$.common.ch'),
get_json_object(line,'$.common.md'),
get_json_object(line,'$.common.mid'),
get_json_object(line,'$.common.os'),
get_json_object(line,'$.common.uid'),
get_json_object(line,'$.common.vc'),
get_json_object(line,'$.page.during_time'),
get_json_object(line,'$.page.item'),
get_json_object(line,'$.page.item_type'),
get_json_object(line,'$.page.last_page_id'),
get_json_object(line,'$.page.page_id'),
get_json_object(line,'$.page.sourceType'),
get_json_object(line,'$.ts')
from ${APP}.ods_log
where dt='$do_date'
and get_json_object(line,'$.page') is not null;
insert overwrite table ${APP}.dwd_error_log
partition(dt='$do_date')
select
get_json_object(line,'$.common.ar'),
get_json_object(line,'$.common.ba'),
get_json_object(line,'$.common.ch'),
get_json_object(line,'$.common.md'),
get_json_object(line,'$.common.mid'),
get_json_object(line,'$.common.os'),
get_json_object(line,'$.common.uid'),
get_json_object(line,'$.common.vc'),
get_json_object(line,'$.page.item'),
get_json_object(line,'$.page.item_type'),
get_json_object(line,'$.page.last_page_id'),
get_json_object(line,'$.page.page_id'),
get_json_object(line,'$.page.sourceType'),
get_json_object(line,'$.start.entry'),
get_json_object(line,'$.start.loading_time'),
get_json_object(line,'$.start.open_ad_id'),
get_json_object(line,'$.start.open_ad_ms'),
get_json_object(line,'$.start.open_ad_skip_ms'),
get_json_object(line,'$.actions'),
get_json_object(line,'$.displays'),
get_json_object(line,'$.ts'),
get_json_object(line,'$.err.error_code'),
get_json_object(line,'$.err.msg')
from ${APP}.ods_log
where dt='$do_date'
and get_json_object(line,'$.err') is not null;
"
$hive -e "$sql"
2
)增加脚本执行权限
[atguigu@hadoop102 bin]$ chmod 777 ods_to_dwd_log.sh
3
)脚本使用
[atguigu@hadoop102 module]$ ods_to_dwd_log.sh 2020-06-15
4
)查询导入结果
hive (gmall)>
select * from dwd_start_log where dt='2020-06-15' limit 2;
5
)脚本执行时间
企业开发中一般在每日凌晨
30
分
~1
点