Sql server 合并/拆分具有优先级的重叠日期范围

我有三张桌子。一张表格告诉我某个供应商何时签订合同。第二条告诉我我们与所有供应商签订的基本费用表。第三种情况告诉我，某一特定合同中的一项费用是否有不同的合同费率。这些表如下所示：

CREATE TABLE [dbo].[Facility](
    [FacilityID] [bigint] IDENTITY(1,1) NOT NULL,
    [ProviderID] [varchar](50) NOT NULL,
    [VendorID] [bigint] NOT NULL,
    [FacilityName] [varchar](300) NOT NULL,
    [FacilityAddress1] [varchar](300) NOT NULL,
    [FacilityAddress2] [varchar](300) NOT NULL,
    [FacilityCity] [varchar](300) NOT NULL,
    [FacilityState] [char](2) NOT NULL,
    [FacilityZip] [varchar](10) NOT NULL,
    [ContractEffectiveDate] [date] NOT NULL,
    [ContractTermDate] [date] NOT NULL,
 CONSTRAINT [PK_Facility] PRIMARY KEY CLUSTERED 
(
    [FacilityID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO


CREATE TABLE [dbo].[BaseFeeSchedule](
    [BaseFeeScheduleID] [int] IDENTITY(1,1) NOT NULL,
    [FeeCode] [varchar](10) NOT NULL,
    [Description] [varchar](800) NOT NULL,
    [Rate] [money] NOT NULL,
    [CategoryID] [int] NOT NULL,
    [RateEffectiveDate] [date] NOT NULL,
    [RateTermDate] [date] NOT NULL,
 CONSTRAINT [PK_BaseFeeSchedule] PRIMARY KEY CLUSTERED 
(
    [BaseFeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

CREATE TABLE [dbo].[OverrideFeeSchedule](
    [OverrideFeeScheduleID] [bigint] IDENTITY(1,1) NOT NULL,
    [FacilityID] [bigint] NOT NULL,
    [FeeCode] [varchar](10) NOT NULL,
    [OverrideRate] [money] NOT NULL,
    [RateEffectiveDate] [date] NOT NULL,
    [RateTermDate] [date] NOT NULL,
 CONSTRAINT [PK_OverrideFeeSchedule] PRIMARY KEY CLUSTERED 
(
    [OverrideFeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

ALTER TABLE [dbo].[OverrideFeeSchedule]  WITH CHECK ADD  CONSTRAINT [FK_OverrideFeeSchedule_Facility] FOREIGN KEY([FacilityID])
REFERENCES [dbo].[Facility] ([FacilityID])
GO

ALTER TABLE [dbo].[OverrideFeeSchedule] CHECK CONSTRAINT [FK_OverrideFeeSchedule_Facility]
GO

CREATE TABLE [dbo].[FeeSchedule](
    [FeeScheduleID] [int] IDENTITY(1,1) NOT NULL,
    [VendorID] [int] NULL,
    [FeeCd] [varchar](10) NOT NULL,
    [StartDate] [date] NOT NULL,
    [EndDate] [date] NOT NULL,
    [ContractedAmount] [money] NOT NULL,
    [ProgramTypeID] [int] NULL,
 CONSTRAINT [PK_FeeSchedule] PRIMARY KEY CLUSTERED 
(
    [FeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

我们有一个现有系统，其中一个表如下所示：

CREATE TABLE [dbo].[Facility](
    [FacilityID] [bigint] IDENTITY(1,1) NOT NULL,
    [ProviderID] [varchar](50) NOT NULL,
    [VendorID] [bigint] NOT NULL,
    [FacilityName] [varchar](300) NOT NULL,
    [FacilityAddress1] [varchar](300) NOT NULL,
    [FacilityAddress2] [varchar](300) NOT NULL,
    [FacilityCity] [varchar](300) NOT NULL,
    [FacilityState] [char](2) NOT NULL,
    [FacilityZip] [varchar](10) NOT NULL,
    [ContractEffectiveDate] [date] NOT NULL,
    [ContractTermDate] [date] NOT NULL,
 CONSTRAINT [PK_Facility] PRIMARY KEY CLUSTERED 
(
    [FacilityID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO


CREATE TABLE [dbo].[BaseFeeSchedule](
    [BaseFeeScheduleID] [int] IDENTITY(1,1) NOT NULL,
    [FeeCode] [varchar](10) NOT NULL,
    [Description] [varchar](800) NOT NULL,
    [Rate] [money] NOT NULL,
    [CategoryID] [int] NOT NULL,
    [RateEffectiveDate] [date] NOT NULL,
    [RateTermDate] [date] NOT NULL,
 CONSTRAINT [PK_BaseFeeSchedule] PRIMARY KEY CLUSTERED 
(
    [BaseFeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

CREATE TABLE [dbo].[OverrideFeeSchedule](
    [OverrideFeeScheduleID] [bigint] IDENTITY(1,1) NOT NULL,
    [FacilityID] [bigint] NOT NULL,
    [FeeCode] [varchar](10) NOT NULL,
    [OverrideRate] [money] NOT NULL,
    [RateEffectiveDate] [date] NOT NULL,
    [RateTermDate] [date] NOT NULL,
 CONSTRAINT [PK_OverrideFeeSchedule] PRIMARY KEY CLUSTERED 
(
    [OverrideFeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

ALTER TABLE [dbo].[OverrideFeeSchedule]  WITH CHECK ADD  CONSTRAINT [FK_OverrideFeeSchedule_Facility] FOREIGN KEY([FacilityID])
REFERENCES [dbo].[Facility] ([FacilityID])
GO

ALTER TABLE [dbo].[OverrideFeeSchedule] CHECK CONSTRAINT [FK_OverrideFeeSchedule_Facility]
GO

CREATE TABLE [dbo].[FeeSchedule](
    [FeeScheduleID] [int] IDENTITY(1,1) NOT NULL,
    [VendorID] [int] NULL,
    [FeeCd] [varchar](10) NOT NULL,
    [StartDate] [date] NOT NULL,
    [EndDate] [date] NOT NULL,
    [ContractedAmount] [money] NOT NULL,
    [ProgramTypeID] [int] NULL,
 CONSTRAINT [PK_FeeSchedule] PRIMARY KEY CLUSTERED 
(
    [FeeScheduleID] ASC
)WITH (PAD_INDEX = OFF, STATISTICS_NORECOMPUTE = OFF, IGNORE_DUP_KEY = OFF, ALLOW_ROW_LOCKS = ON, ALLOW_PAGE_LOCKS = ON) ON [PRIMARY]
) ON [PRIMARY]
GO

该表在代码中用于确定每个供应商的正确付款率。我的工作是更新该表，但事实证明这是有问题的，因为不同的设施在不同的日期签订了合同。每份合同都包括基本费用表。然而，合同允许某些费用被覆盖，当有折扣时，不同的费用通常低于正常合同费用，当需要增加附加费时，有时更高。这三个表是我构建的用来存储所有当前数据的表，我一直在使用它们来构建软件所需的FeeSchedule表。处理更改很容易，但我的任务是验证FeeSchedule表中的数据是否准确

FeeSchedule表不仅包括我唯一更改的新数据，还包括以前的数据。因此，计划是获取三个表中的数据，运行查询以合并日期范围，其中OverrideFeeSchedule表中的费用优先于BaseFeeSchedule表中的费用

例如：

INSERT INTO Facility(VendorID,ContractEffectiveDate,ContractTermDate,...) 
VALUES(1,'1/1/2017','12/31/9999',...) --Assume FacilityID=1

INSERT INTO BaseFeeSchedule(FeeCode,Rate,RateEffectiveDate,RateTermDate,...) 
VALUES('1',100,'1/1/2015','10/15/2016',...),
('1',120,'10/16/2016','4/5/2018',...),
('1',140,'4/6/2018','12/31/9999',...)

INSERT INTO OverrideFeeSchedule(FacilityID,FeeCode,OverrideRate,RateEffectiveDate,RateTermDate,...) 
VALUES(1,'1',50,'3/1/2017','5/31/2018',...),
(1,'1',70,'7/1/2018','12/31/9999',...)

And from this data, I would want:

INSERT INTO FeeSchedule(VendorID, FeeCd, StartDate,EndDate,ContractedAmount)
VALUES(1,'1','1/1/2017','2/28/2017',120), --From BaseFeeSchedule
(1,'1','3/1/2017','5/31/2018',50), --From OverrideFeeSchedule
(1,'1','6/1/2018','6/30/2018',140), --From BaseFeeSchedule
(1,'1','7/1/2018','12/31/9999',70) --From OverrideFeeSchedule

我已经验证，OverrideFeeSchedule表中没有重叠的单个设施/FeeCode组合的数据，BaseFeeSchedule中也没有重叠的单个FeeCode的数据。我目前的解决方案需要很长时间。我正在做以下工作：

建立一个表格，记录自第一个合同设施开始的每天。BigTable只是一个有大约一百万条记录的表，从第一次与供应商签订合同到一年后的每一天，我只取足够的记录。然而，由于最大递归大约是20000天，当从第一个签约供应商到从今天开始的一年的范围超过20000天时，我可能会因为违反最大递归而得到错误。所以，我希望有一个不同的解决方案

SELECT DATEADD(DAY,ROW_NUMBER() OVER (ORDER BY A.TableID) - 1,B.MinDate) CheckDate 
INTO #DatesToCheck
FROM BigTable A
CROSS JOIN 
    (SELECT MIN(ContractEffectiveDate) MinDate
    FROM Facility) B
WHERE DATEADD(DAY,ROW_NUMBER() OVER (ORDER BY A.TableID) - 1,B.MinDate) < DATEADD(YEAR,1,GETDATE())

将此表连接到另一个表，以构建一个庞大的表，其中包括每天、当天签约的每个设施、当天应收取的每个费用代码以及当天的具体费率。我不会为这个连接的代码操心，但是它并不难写

接下来，我使用此处描述的技术合并日期范围：

---

虽然这项技术可行，但速度非常慢。有没有更直接的方法来生成我正在寻找的结果集？基本上，我正在寻找如何修改该链接中的方法，以考虑不同优先级的潜在重叠，如我提供的示例中所示。

我希望我正确地理解了这一点

首先，您应该实现一个数字/日期表。这不是绝对必要的，但在很多情况下都很漂亮。你

有了这样的列表，您可以尝试以下内容：

DECLARE @endDate DATE='20191231';

WITH DailyBaseRate AS
(
    SELECT CoveredDays.CalendarDate
          ,CONCAT('base ',bfs.RateEffectiveDate) AS RateKey
          ,bfs.FeeCode
          ,bfs.Rate
    FROM BaseFeeSchedule bfs
    CROSS APPLY(SELECT * FROM RunningNumbers rn WHERE rn.CalendarDate<=@endDate AND rn.CalendarDate>=bfs.RateEffectiveDate AND rn.CalendarDate<=bfs.RateTermDate) CoveredDays

)
,OverrideRates AS
(
    SELECT CoveredDays.CalendarDate
          ,o.FacilityID 
          ,CONCAT('override ',o.RateEffectiveDate) AS RateKey
          ,o.FeeCode
          ,o.OverrideRate
    FROM OverrideFeeSchedule o
    CROSS APPLY(SELECT * FROM RunningNumbers rn WHERE  rn.CalendarDate<=@endDate AND rn.CalendarDate>=o.RateEffectiveDate AND rn.CalendarDate<=o.RateTermDate) CoveredDays
) 
,EffectiveRates AS
(
    SELECT f.*
          ,dbr.CalendarDate
          ,COALESCE(ovr.RateKey, dbr.RateKey) AS EffectiveRateKey
          ,COALESCE(ovr.FeeCode, dbr.FeeCode) AS EffectiveFeeCode
          ,COALESCE(ovr.OverrideRate, dbr.Rate) AS EffectiveRate
    FROM dbo.Facility f
    CROSS JOIN DailyBaseRate dbr
    LEFT JOIN OverrideRates ovr ON ovr.FacilityID=f.FacilityID AND ovr.CalendarDate=dbr.CalendarDate
    WHERE dbr.CalendarDate<=@endDate 
      AND dbr.CalendarDate>=f.ContractEffectiveDate 
      AND dbr.CalendarDate<=f.ContractTermDate
)
SELECT FacilityID,FacilityName
      ,EffectiveRateKey,EffectiveFeeCode,EffectiveRate
      ,MIN(CalendarDate) AS FromDate
      ,MAX(CalendarDate) AS ToDate
FROM EffectiveRates
GROUP BY FacilityID,FacilityName,EffectiveRateKey,EffectiveFeeCode,EffectiveRate
ORDER BY FacilityID,FromDate;

简言之，这个想法

第一个CTE会将您的基本日程转换为每天一行的日期列表，其中包含每天的当前代码和费率 第二个CTE将执行相同的操作，但使用覆盖计划 第三个CTE将交叉连接您的设施和基本计划。如果有许多设施，并且没有额外的行，那么这可能会变得相当大 该集合被过滤到实际使用的范围 最后，我们可以按一些列进行分组，并使用“最小”和“最大”选择间隔边界 提示：我们需要EffectiveRateKey来避免以相同的速率和代码将不同的间隔组合在一起。作为一个副作用，你可以看到，从哪个来源的速度采取

---

Hint2：由于我们永远不知道引擎将以何种顺序运行，请考虑索引，使用索引临时表而不是CTE可能会有很大帮助…

这看起来很棒，而且比我目前正在做的工作效率更高。昨晚，我有了另一个想法。我可以使用三通技术。第一次通过将添加设施合同范围内的所有覆盖率。接下来，我可以在第一个覆盖日期之前获取基本利率。最后，我可以通过使用LEAD获取下一个RateEffectiveDate并查找RateTermDate和下一个RateEffectiveDate之间的基准利率来获取覆盖日期之间的基准利率。这样会更有效率吗？