使用SQL从类型2缓慢变化的维度中删除重复项

我正在构建一个数据仓库，其中包含存储相同数据的多层。其中一个中间层中的所有数据都使用开始日期和结束日期进行版本控制，就好像它是一个类型2缓慢变化的维度。当我查询这些表时，问题就出现了。表中的列通常多于查询中的列，因此查询中的相邻版本具有不同的开始日期和结束日期，但在其他方面是相同的。我想要组合这些版本，以显示查询中的列更改的日期，而不是表中的行更改的日期

我有一些SQL几乎可以工作：

create table versions 
(id int
, name varchar(100) Not null
, RowStartDate datetime Not null
, RowEndDate datetime Not null
, primary key (id,RowStartDate)
, check (RowStartDate < RowEndDate));

insert into versions values 
 (1,'A','2014-01-01','9999-12-31')
,(2,'B','2014-01-01','2014-12-31')
,(2,'B','2014-12-31','9999-12-31')
,(3,'C','2014-01-01','2014-12-31')
,(3,'CC','2014-12-31','2015-12-31')
,(3,'CC','2015-12-31','9999-12-31')
,(4,'D','2014-01-01','2014-12-31')
,(4,'DD','2014-12-31','2015-12-31')
,(4,'DD','2015-12-31','2016-12-31')
,(4,'D','2016-12-31','9999-12-31')
,(5,'E','2014-01-01','2014-12-31')
,(5,'E','2014-12-31','2015-12-31')
,(5,'E','2015-12-31','2016-12-31')
,(5,'E','2016-12-31','2017-12-31')
,(5,'E','2017-12-31','9999-12-31')
;

WITH CTE_detect_duplicates AS (SELECT [id]
      ,[name]
      ,[RowStartDate]
      ,[RowEndDate]
      ,LAST_VALUE(RowEndDate) OVER (PARTITION BY id, name ORDER BY RowStartDate, RowEndDate ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING) as LastEndDate
      ,rank() OVER (PARTITION BY id, name ORDER BY RowStartDate, RowEndDate) as duplicateNumber
  FROM versions
 )
SELECT [id]
      ,[name]
      ,[RowStartDate]
      ,LastEndDate as RowEndDate
FROM CTE_detect_duplicates
WHERE duplicateNumber = 1

这里的问题是，当需要三行时，它为ID4返回两行。 实际： 渴望的： 值DD正确时，值D不正确，因此my查询中第一行4“D”上的版本日期不正确

---

我希望能够在纯SQL或内嵌表值函数中删除这些重复项我有一个生成器，它可以创建多语句表值函数，但结果函数的性能很差。有人有什么想法吗？

下面的查询包含多个CTE，它压缩更新的日期范围并删除重复的值

1根据RowStartDate在每个id组内分配第一个等级

2接下来，确定具有相同名称值的列组范围的最大列组Next_rank_编号。因此，对于示例数据，id=5的行1将具有next_rank_no=5，id=4的行2将具有next_rank_no=3。此版本仅处理“名称”列。如果要处理其他列，它们也必须包含在条件中。例如，如果要包括位置列，则连接条件应为：

  left join sorted_versions sv2 on sv2.id = sv1.id and sv2.rank_no > sv1.rank_no and sv2.name = sv1.name and sv2.location = sv1.location
  left join sorted_versions sv3 on sv3.id = sv1.id and sv3.rank_no > sv1.rank_no and (sv3.name <> sv1.name or sv3.location <> sv1.location)

id name RowStartDate RowEndDate 4 D 2014-01-01 00:00:00.000 2014-12-31 00:00:00.000 4 DD 2014-12-31 00:00:00.000 2016-12-31 00:00:00.000 4 D 2016-12-31 00:00:00.000 9999-12-31 00:00:00.000

  left join sorted_versions sv2 on sv2.id = sv1.id and sv2.rank_no > sv1.rank_no and sv2.name = sv1.name and sv2.location = sv1.location
  left join sorted_versions sv3 on sv3.id = sv1.id and sv3.rank_no > sv1.rank_no and (sv3.name <> sv1.name or sv3.location <> sv1.location)

with sorted_versions as --ranks are assigned within each id group
(
  select 
    v1.id,
    v1.name,
    v1.RowStartDate,
    v1.RowEndDate,
    rank() over (partition by v1.id order by v1.RowStartDate) rank_no
  from versions v1
  left join versions v2 on (v1.id = v2.id and v2.RowStartDate = v1.RowEndDate)
),
next_rank as --the maximum rank of the range of ranks which has the same value for NAME
(
  select 
  sv1.id id, sv1.rank_no rank_no, COALESCE(min(sv3.rank_no)-1 , COALESCE(max(sv2.rank_no), sv1.rank_no)) next_rank_no
  from sorted_versions sv1
  left join sorted_versions sv2 on sv2.id = sv1.id and sv2.rank_no > sv1.rank_no and sv2.name = sv1.name
  left join sorted_versions sv3 on sv3.id = sv1.id and sv3.rank_no > sv1.rank_no and sv3.name <> sv1.name
  group by sv1.id, sv1.rank_no
),
versions_cte as --the rowenddate of the "maximum rank" is selected 
(
  select sv.id, sv.name, sv.rowstartdate, sv3.rowenddate, nr.next_rank_no rank_no
  from sorted_versions sv
  inner join next_rank nr on sv.id = nr.id and sv.rank_no = nr.rank_no and sv.rank_no = 1
  inner join sorted_versions sv3 on nr.id = sv3.id and nr.next_rank_no = sv3.rank_no  
  union all
  select
    sv2.id,
    sv2.name, 
    sv2.rowstartdate,
    sv3.rowenddate,
    nr.next_rank_no
  from versions_cte vc
  inner join sorted_versions sv2 on sv2.id = vc.id and sv2.rank_no = vc.rank_no + 1
  inner join next_rank nr on sv2.id = nr.id and sv2.rank_no = nr.rank_no  
  inner join sorted_versions sv3 on nr.id = sv3.id and nr.next_rank_no = sv3.rank_no
)
select id, name, rowstartdate, rowenddate
from versions_cte
order by id, rowstartdate;