[英]Designing a slowly changing dimension type 2 script with postgresql
假设我有以下目标表:
CREATE TABLE DimCustomer (
CustomerKey serial PRIMARY KEY,
CustomerNum int NOT NULL,
CustomerName varchar(25) NOT NULL,
Planet varchar(25) NOT NULL,
RowIsCurrent char(1) NOT NULL DEFAULT 'Y',
RowStartDate date NOT NULL DEFAULT CURRENT_TIMESTAMP,
RowEndDate date NOT NULL DEFAULT '12/31/9999'
);
INSERT INTO DimCustomer
(CustomerNum, CustomerName, Planet, RowStartDate)
VALUES (101,'Anakin Skywalker', 'Tatooine', CURRENT_TIMESTAMP - INTERVAL '101 days'),
(102,'Yoda', 'Coruscant', CURRENT_TIMESTAMP - INTERVAL '100 days'),
(103,'Obi-Wan Kenobi', 'Coruscant', CURRENT_TIMESTAMP - INTERVAL '100 days')
我有以下临时表:
CREATE TABLE Staging_DimCustomer
(
CustomerNum int NOT NULL,
CustomerName varchar(25) NOT NULL,
Planet varchar(25) NOT NULL,
ChangeDate date NOT NULL DEFAULT CURRENT_TIMESTAMP,
RankNo int NOT NULL DEFAULT 1
)
INSERT INTO Staging_DimCustomer(CustomerNum, CustomerName, Planet, ChangeDate)
VALUES
(103,'Ben Kenobi', 'Coruscant', CURRENT_TIMESTAMP - INTERVAL '99 days')
在临时表中,看起来像'Obi-Wan Kenobi'
( customernum 103
)将他的名字更改为'Ben Kenobi'
。 我想创建一个脚本来实现 scd 类型 2 并产生以下结果(缓慢变化的维度类型 2):
以下是我的尝试:
INSERT INTO DimCustomer (
CustomerNum, CustomerName, Planet, RowIsCurrent, RowStartDate, RowEndDate
)
select CustomerNum, CustomerName, Planet, 'Y', ChangeDate, '12/31/9999'
from Staging_DimCustomer
ON CONFLICT (CustomerNum) and RowIsCurrent = 'Y'
DO UPDATE SET
CustomerName = EXCLUDED.CustomerName,
Planet = EXCLUDED.Planet,
RowIsCurrent = 'N',
RowEndDate = EXCLUDED.ChangeDate
我不知道如何查找更改的值,更新现有行以rowiscurrent = 'Y'
它,然后插入带有rowiscurrent = 'Y'
标志的新行。 我正在尝试根据这篇 sql server 文章http://www.made2mentor.com/2013/08/how-to-load-slowly-changed-dimensions-using-t-sql-merge/为我的解决方案建模。
假设更改都在最新行上,那么您可以更新当前行,然后插入:
with u as (
update dimCustomer c
set RowIsCurrent = 'N',
RowEndDate = sc.ChangeDate
from Staging_DimCustomer sc
where sc.CustomerNum = c.CustomerNum and
c.RowIsCurrent = 'Y'
)
insert into dimCustomer (CustomerNum, CustomerName, Planet, RowIsCurrent, RowStartDate, RowEndDate
)
select CustomerNum, CustomerName, Planet, 'Y', ChangeDate, '9999-12-31'::date
from Staging_DimCustomer sc;
这假设更改发生在最新的记录上。 实施历史性更改相当棘手,我猜这没有必要。
请注意,您可能需要额外检查插入的行实际上与当前行不同。
编辑:
如果要避免更改已存在的行,可以执行以下操作:
with sc as (
select *
from Staging_DimCustomer
where not exists (select 1
from DimCustomer c
where c.CustomerNum = sc.CustomerNum and
c.CustomerName = sc.CustomerName and
. . . -- whatever other columns you want to check
)
),
u as (
update dimCustomer c
set RowIsCurrent = 'N',
RowEndDate = sc.ChangeDate
from sc
where sc.CustomerNum = c.CustomerNum and
c.RowIsCurrent = 'Y'
)
insert into dimCustomer (CustomerNum, CustomerName, Planet, RowIsCurrent, RowStartDate, RowEndDate
)
select CustomerNum, CustomerName, Planet, 'Y', ChangeDate, '9999-12-31'::date
from sc;
我认为这应该可以正常工作,而不是更新或插入已经存在的记录:
with us as (
update dimCustomer c
set RowIsCurrent = 'N',
RowEndDate = sc.ChangeDate
from Staging_DimCustomer sc
where sc.CustomerNum = c.CustomerNum and
c.RowIsCurrent = 'Y' and
sc.customername <> c.customername
),
u as (
select stg.customernum,stg.customername,stg.planet ,stg.changedate from Staging_DimCustomer stg
Inner join DimCustomer dim on dim.customernum=stg.customernum and dim.rowiscurrent='Y'
and (dim.customername <> stg.customername
or dim.planet <> stg.planet
)
UNION
select stg.customernum,stg.customername,stg.planet ,stg.changedate from Staging_DimCustomer stg
where stg.customernum not IN(select dim.customernum from DimCustomer dim where dim.rowiscurrent='Y')
)
insert into dimCustomer (CustomerNum, CustomerName, Planet, RowIsCurrent, RowStartDate, RowEndDate
)
select CustomerNum, CustomerName, Planet, 'Y', ChangeDate, '9999-12-31'::date
from u ;
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.