數據倉庫 業務數倉 DWD層

業務數倉的DWD層一般有兩個典型操作：

①因為是DWD層，所以要進行數據清洗。

②因為數據來源於web項目的數據庫，標的設計遵循三范式，因此在數倉里需要進行降維，以減少join次數。

在示例的8張表中，訂單表，訂單詳情表，用戶表，支付流水表字段與ODS層一致。對商品表的分類進行降維。增加二級分類，一級分類的id和名稱。

drop table if exists dwd_sku_info;
create external table dwd_sku_info(
    `id` string COMMENT 'skuId',
    `spu_id` string COMMENT 'spuid',
    `price` decimal(10,2) COMMENT '',
    `sku_name` string COMMENT '',
    `sku_desc` string COMMENT '',
    `weight` string COMMENT '',
    `tm_id` string COMMENT 'id',
    `category3_id` string COMMENT '1id',
    `category2_id` string COMMENT '2id',
    `category1_id` string COMMENT '3id',
    `category3_name` string COMMENT '3',
    `category2_name` string COMMENT '2',
    `category1_name` string COMMENT '1',
    `create_time` string COMMENT ''
) 
PARTITIONED BY (`dt` string)
stored as parquet
location '/warehouse/gmall/dwd/dwd_sku_info/'
tblproperties ("parquet.compression"="snappy")
;

DWD層數據導入腳本，降維時，只需對相關表進行join即可。

#!/bin/bash

# 定義變量方便修改
APP=gmall
hive=/opt/module/hive/bin/hive

# 如果是輸入的日期按照取輸入日期；如果沒輸入日期取當前時間的前一天
if [ -n "$1" ] ;then
    do_date=$1
else 
    do_date=`date -d "-1 day" +%F`  
fi 

sql="

set hive.exec.dynamic.partition.mode=nonstrict;

insert overwrite table "$APP".dwd_order_info partition(dt)
select * from "$APP".ods_order_info 
where dt='$do_date' and id is not null;
 
insert overwrite table "$APP".dwd_order_detail partition(dt)
select * from "$APP".ods_order_detail 
where dt='$do_date'   and id is not null;

insert overwrite table "$APP".dwd_user_info partition(dt)
select * from "$APP".ods_user_info
where dt='$do_date' and id is not null;
 
insert overwrite table "$APP".dwd_payment_info partition(dt)
select * from "$APP".ods_payment_info
where dt='$do_date' and id is not null;

insert overwrite table "$APP".dwd_sku_info partition(dt)
select  
    sku.id,
    sku.spu_id,
    sku.price,
    sku.sku_name,
    sku.sku_desc,
    sku.weight,
    sku.tm_id,
    sku.category3_id,
    c2.id category2_id,
    c1.id category1_id,
    c3.name category3_name,
    c2.name category2_name,
    c1.name category1_name,
    sku.create_time,
    sku.dt
from
    "$APP".ods_sku_info sku
join "$APP".ods_base_category3 c3 on sku.category3_id=c3.id 
    join "$APP".ods_base_category2 c2 on c3.category2_id=c2.id 
    join "$APP".ods_base_category1 c1 on c2.category1_id=c1.id 
where sku.dt='$do_date'  and c2.dt='$do_date'
and c3.dt='$do_date' and c1.dt='$do_date'
and sku.id is not null;
"

$hive -e "$sql"