0 簡介

對ODS層資料進行清洗（去除空值，髒資料，超過極限範圍的資料，行式儲存改為列儲存，改壓縮格式）。

1 DWD層啟動表資料解析

1.1建立啟動表

1）建表語句

hive (gmall)> 
drop table if exists dwd_start_log;
CREATE EXTERNAL TABLE dwd_start_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`entry` string, 
`open_ad_type` string, 
`action` string, 
`loading_time` string, 
`detail` string, 
`extend1` string
)
PARTITIONED BY (dt string)
stored as parquet
location '/warehouse/gmall/dwd/dwd_start_log/'
TBLPROPERTIES('parquet.compression'='lzo');
 

或者（無壓縮）

hive (gmall)> 
drop table if exists dwd_start_log;
CREATE EXTERNAL TABLE dwd_start_log(
`mid_id` string,
`user_id` string, 
`version_code` string, 
`version_name` string, 
`lang` string, 
`source` string, 
`os` string, 
`area` string, 
`model` string,
`brand` string, 
`sdk_version` string, 
`gmail` string, 
`height_width` string,  
`app_time` string,
`network` string, 
`lng` string, 
`lat` string, 
`entry` string, 
`open_ad_type` string, 
`action` string, 
`loading_time` string, 
`detail` string, 
`extend1` string
)
PARTITIONED BY (dt string)
stored as parquet
location '/warehouse/gmall/dwd/dwd_start_log/';
 

1.2向啟動表匯入資料

hive (gmall)> 
insert overwrite table dwd_start_log
PARTITION (dt='2019-12-14')
select 
    get_json_object(line,'$.mid') mid_id,
    get_json_object(line,'$.uid') user_id,
    get_json_object(line,'$.vc') version_code,
    get_json_object(line,'$.vn') version_name,
    get_json_object(line,'$.l') lang,
    get_json_object(line,'$.sr') source,
    get_json_object(line,'$.os') os,
    get_json_object(line,'$.ar') area,
    get_json_object(line,'$.md') model,
    get_json_object(line,'$.ba') brand,
    get_json_object(line,'$.sv') sdk_version,
    get_json_object(line,'$.g') gmail,
    get_json_object(line,'$.hw') height_width,
    get_json_object(line,'$.t') app_time,
    get_json_object(line,'$.nw') network,
    get_json_object(line,'$.ln') lng,
    get_json_object(line,'$.la') lat,
    get_json_object(line,'$.entry') entry,
    get_json_object(line,'$.open_ad_type') open_ad_type,
    get_json_object(line,'$.action') action,
    get_json_object(line,'$.loading_time') loading_time,
    get_json_object(line,'$.detail') detail,
    get_json_object(line,'$.extend1') extend1
from ods_start_log 
where dt='2019-12-14';
 

3）測試

hive (gmall)> select * from dwd_start_loglimit 2;

1.3 DWD層啟動表載入資料指令碼

1）在hadoop102的/home/atguigu/bin目錄下建立指令碼

[atguigu@hadoop102 bin]$ vim dwd_start_log.sh

在指令碼中編寫如下內容

#!/bin/bash
if [ -n "$1" ]
then
         do_date=$1
else
        do_date=$(date -d yesterday +%F)
fi

echo ===日誌日期為$do_date===


sql="

insert overwrite table gmall.dwd_start_log
PARTITION (dt='$do_date')
select 
    get_json_object(line,'$.mid') mid_id,
    get_json_object(line,'$.uid') user_id,
    get_json_object(line,'$.vc') version_code,
    get_json_object(line,'$.vn') version_name,
    get_json_object(line,'$.l') lang,
    get_json_object(line,'$.sr') source,
    get_json_object(line,'$.os') os,
    get_json_object(line,'$.ar') area,
    get_json_object(line,'$.md') model,
    get_json_object(line,'$.ba') brand,
    get_json_object(line,'$.sv') sdk_version,
    get_json_object(line,'$.g') gmail,
    get_json_object(line,'$.hw') height_width,
    get_json_object(line,'$.t') app_time,
    get_json_object(line,'$.nw') network,
    get_json_object(line,'$.ln') lng,
    get_json_object(line,'$.la') lat,
    get_json_object(line,'$.entry') entry,
    get_json_object(line,'$.open_ad_type') open_ad_type,
    get_json_object(line,'$.action') action,
    get_json_object(line,'$.loading_time') loading_time,
    get_json_object(line,'$.detail') detail,
    get_json_object(line,'$.extend1') extend1
from gmall.ods_start_log 
where dt='$do_date';

"
hive  -e "$sql"