-->

日期范围交叉口劈裂SQL(Date Range Intersection Splitting in

2019-08-04 10:19发布

我有一个包含一个表名为成员一个SQL Server 2005数据库。

表模式是:

PersonID int, Surname nvarchar(30), FirstName nvarchar(30), Description nvarchar(100), StartDate datetime, EndDate datetime

我目前工作的一个网格功能,显示成员的被人闯入了下来。 其中一个要求就是分裂成员行,其中有日期范围的交集。 交集必须由姓氏和名字绑定,即分裂只能使用相同姓氏和名字的会员记录发生。

实施例表中的数据:

18  Smith  John  Poker Club  01/01/2009  NULL
18  Smith  John  Library     05/01/2009  18/01/2009
18  Smith  John  Gym         10/01/2009  28/01/2009
26  Adams  Jane  Pilates     03/01/2009  16/02/2009

预期的结果集:

18  Smith  John  Poker Club                  01/01/2009  04/01/2009
18  Smith  John  Poker Club / Library        05/01/2009  09/01/2009
18  Smith  John  Poker Club / Library / Gym  10/01/2009  18/01/2009
18  Smith  John  Poker Club / Gym            19/01/2009  28/01/2009
18  Smith  John  Poker Club                  29/01/2009  NULL
26  Adams  Jane  Pilates                     03/01/2009  16/02/2009

没有人有任何想法我怎么能写一个存储过程,将返回具有上述击穿的结果集。

Answer 1:

你将不得不与这个问题的问题是,随着数据集的增长,解决方案与TSQL解决它不会很好地扩展。 以下使用一系列建立在飞解决问题的临时表。 这将每个日期范围进入用数字表其各自的日子。 这是它无法扩展,主要是由于你的开放范围这似乎是inifinity NULL值,所以你必须在固定的日期交换远成限制转换的范围内的时间长度是可行的未来。 你可以通过建立天的表或每天的优化渲染适当的索引日历表很可能会看到更好的性能。

一旦范围被分割,描述使用XML路径,以使每天范围内的系列拥有所有它列出的描述的合并。 由是PersonID和日期行编号允许为每个区域的第一个和最后一行用两个NOT EXISTS检查,以寻找到前一行不以获取匹配的是PersonID和说明set存在的实例可以发现,或者下一行没有按”吨存在一个匹配是PersonID和描述集。

然后,这个结果集使用ROW_NUMBER,以便他们可以配对以建立最终的结果重新编号。

/*
SET DATEFORMAT dmy
USE tempdb;
GO
CREATE TABLE Schedule
( PersonID int, 
 Surname nvarchar(30), 
 FirstName nvarchar(30), 
 Description nvarchar(100), 
 StartDate datetime, 
 EndDate datetime)
GO
INSERT INTO Schedule VALUES (18, 'Smith', 'John', 'Poker Club', '01/01/2009', NULL)
INSERT INTO Schedule VALUES (18, 'Smith', 'John', 'Library', '05/01/2009', '18/01/2009')
INSERT INTO Schedule VALUES (18, 'Smith', 'John', 'Gym', '10/01/2009', '28/01/2009')
INSERT INTO Schedule VALUES (26, 'Adams', 'Jane', 'Pilates', '03/01/2009', '16/02/2009')
GO

*/

SELECT 
 PersonID, 
 Description, 
 theDate
INTO #SplitRanges
FROM Schedule, (SELECT DATEADD(dd, number, '01/01/2008') AS theDate
    FROM master..spt_values
    WHERE type = N'P') AS DayTab
WHERE theDate >= StartDate 
  AND theDate <= isnull(EndDate, '31/12/2012')

SELECT 
 ROW_NUMBER() OVER (ORDER BY PersonID, theDate) AS rowid,
 PersonID, 
 theDate, 
 STUFF((
  SELECT '/' + Description
  FROM #SplitRanges AS s
  WHERE s.PersonID = sr.PersonID 
    AND s.theDate = sr.theDate
  FOR XML PATH('')
  ), 1, 1,'') AS Descriptions
INTO #MergedDescriptions
FROM #SplitRanges AS sr
GROUP BY PersonID, theDate


SELECT 
 ROW_NUMBER() OVER (ORDER BY PersonID, theDate) AS ID, 
 *
INTO #InterimResults
FROM
(
 SELECT * 
 FROM #MergedDescriptions AS t1
 WHERE NOT EXISTS 
  (SELECT 1 
   FROM #MergedDescriptions AS t2 
   WHERE t1.PersonID = t2.PersonID 
     AND t1.RowID - 1 = t2.RowID 
     AND t1.Descriptions = t2.Descriptions)
UNION ALL
 SELECT * 
 FROM #MergedDescriptions AS t1
 WHERE NOT EXISTS 
  (SELECT 1 
   FROM #MergedDescriptions AS t2 
   WHERE t1.PersonID = t2.PersonID 
     AND t1.RowID = t2.RowID - 1
     AND t1.Descriptions = t2.Descriptions)
) AS t

SELECT DISTINCT 
 PersonID, 
 Surname, 
 FirstName
INTO #DistinctPerson
FROM Schedule

SELECT 
 t1.PersonID, 
 dp.Surname, 
 dp.FirstName, 
 t1.Descriptions, 
 t1.theDate AS StartDate, 
 CASE 
  WHEN t2.theDate = '31/12/2012' THEN NULL 
  ELSE t2.theDate 
 END AS EndDate
FROM #DistinctPerson AS dp
JOIN #InterimResults AS t1 
 ON t1.PersonID = dp.PersonID
JOIN #InterimResults AS t2 
 ON t2.PersonID = t1.PersonID 
  AND t1.ID + 1 = t2.ID 
  AND t1.Descriptions = t2.Descriptions

DROP TABLE #SplitRanges
DROP TABLE #MergedDescriptions
DROP TABLE #DistinctPerson
DROP TABLE #InterimResults

/*

DROP TABLE Schedule

*/

上述解决方案还将处理其他描述之间的差距一样,所以如果你要添加其他说明的是PersonID 18留下一个缺口:

INSERT INTO Schedule VALUES (18, 'Smith', 'John', 'Gym', '10/02/2009', '28/02/2009')

它会适当地填补了国内空白。 正如评论指出的那样,你不应该在这个表名信息,应该归出一个人的表,可以在最后结果中得到JOIN'd到。 我通过使用SELECT DISTINCT建立一个临时表创建JOIN模拟这个其他表。



Answer 2:

试试这个

SET DATEFORMAT dmy
DECLARE @Membership TABLE( 
    PersonID    int, 
    Surname     nvarchar(16), 
    FirstName   nvarchar(16), 
    Description nvarchar(16), 
    StartDate   datetime, 
    EndDate     datetime)   
INSERT INTO @Membership VALUES (18, 'Smith', 'John', 'Poker Club', '01/01/2009', NULL)
INSERT INTO @Membership VALUES (18, 'Smith', 'John','Library', '05/01/2009', '18/01/2009')
INSERT INTO @Membership VALUES (18, 'Smith', 'John','Gym', '10/01/2009', '28/01/2009')
INSERT INTO @Membership VALUES (26, 'Adams', 'Jane','Pilates', '03/01/2009', '16/02/2009')

--Program Starts
declare @enddate datetime
--Measuring extreme condition when all the enddates are null(i.e. all the memberships for all members are in progress)
-- in such a case taking any arbitary date e.g. '31/12/2009' here else add 1 more day to the highest enddate
select @enddate =  case when max(enddate) is null then '31/12/2009' else max(enddate) + 1 end from @Membership

--Fill the null enddates
; with fillNullEndDates_cte as
(
    select
            row_number() over(partition by PersonId order by PersonId) RowNum
            ,PersonId
            ,Surname
            ,FirstName
            ,Description
            ,StartDate
            ,isnull(EndDate,@enddate) EndDate
    from @Membership
)
--Generate a date calender
, generateCalender_cte as
(
    select 
        1 as CalenderRows
        ,min(startdate) DateValue
    from @Membership
       union all
        select 
            CalenderRows+1
            ,DateValue + 1
        from    generateCalender_cte   
        where   DateValue + 1 <= @enddate
)
--Generate Missing Dates based on Membership
,datesBasedOnMemberships_cte as
 (
    select 
            t.RowNum
            ,t.PersonId
            ,t.Surname
            ,t.FirstName
            ,t.Description          
            , d.DateValue
            ,d.CalenderRows
    from generateCalender_cte d 
    join fillNullEndDates_cte t ON d.DateValue between t.startdate and t.enddate
)
--Generate Dscription Based On Membership Dates
, descriptionBasedOnMembershipDates_cte as
(
    select    
        PersonID
        ,Surname
        ,FirstName
        ,stuff((
            select '/' + Description
            from datesBasedOnMemberships_cte d1
            where d1.PersonID = d2.PersonID 
            and d1.DateValue = d2.DateValue
            for xml path('')
        ), 1, 1,'') as Description
        , DateValue
        ,CalenderRows
    from datesBasedOnMemberships_cte d2
    group by PersonID, Surname,FirstName,DateValue,CalenderRows
)
--Grouping based on membership dates
,groupByMembershipDates_cte as
(
    select d.*,
    CalenderRows - row_number() over(partition by Description order by PersonID, DateValue) AS  [Group]
    from descriptionBasedOnMembershipDates_cte d
)
select PersonId
,Surname
,FirstName
,Description
,convert(varchar(10), convert(datetime, min(DateValue)), 103) as StartDate
,case when max(DateValue)= @enddate then null else convert(varchar(10), convert(datetime, max(DateValue)), 103) end as EndDate
from groupByMembershipDates_cte 
group by [Group],PersonId,Surname,FirstName,Description
order by PersonId,StartDate
option(maxrecursion 0)


Answer 3:

[只有很多很多年以后。]

我创建了一个存储过程,将对准并在一个表中由隔板打破段,然后就可以使用这些对准符的描述枢转到使用子查询和XML PATH不齐整柱。

看看下面的帮助:

  1. 文档: https://github.com/Quebe/SQL-Algorithms/blob/master/Temporal/Date%20Segment%20Manipulation/DateSegments_AlignWithinTable.md

  2. 存储过程: https://github.com/Quebe/SQL-Algorithms/blob/master/Temporal/Date%20Segment%20Manipulation/DateSegments_AlignWithinTable.sql

例如,您的通话可能看起来像:

EXEC dbo.DateSegments_AlignWithinTable
@tableName = 'tableName',
@keyFieldList = 'PersonID',
@nonKeyFieldList = 'Description',
@effectivveDateFieldName = 'StartDate',
@terminationDateFieldName = 'EndDate'

你会想要捕捉的结果(这是一个表)到另一个表或临时表(假设它被称为“AlignedDataTable”在下面的例子)。 然后,您可以转动使用子查询。

SELECT 
    PersonID, StartDate, EndDate,

    SUBSTRING ((SELECT ',' + [Description] FROM AlignedDataTable AS innerTable 
        WHERE 
            innerTable.PersonID = AlignedDataTable.PersonID
            AND (innerTable.StartDate = AlignedDataTable.StartDate) 
            AND (innerTable.EndDate = AlignedDataTable.EndDate)
        ORDER BY id
        FOR XML PATH ('')), 2, 999999999999999) AS IdList

 FROM AlignedDataTable
 GROUP BY PersonID, StartDate, EndDate 
 ORDER BY PersonID, StartDate


文章来源: Date Range Intersection Splitting in SQL