使用带分页的 CTE 从 3 个表中获取记录

Question

我有三个 tables TableA，TableB，TableC，TableA 有数百万条记录。

Table A 有 AccountId，table B 有 accountId、客户及其证书，TableC 有证书。

情况是 Table B AccountId 有多个客户端和多个证书。

当我尝试通过加入 table B 和 C 从 table A 获取数据时，它获取了重复的记录，因为在 table B AccountId 中有多个客户端和多个证书。

您可以使用此脚本填充 tables 和数据以测试情况

SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO

CREATE TABLE [dbo].[TableA]
(
    [AccountId] [int] NOT NULL,
    [Name] [nvarchar](50) NULL,
    [Mobile] [nchar](10) NULL,
 CONSTRAINT [PK_Accounts] PRIMARY KEY CLUSTERED 
(
    [AccountId] 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

SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO

CREATE TABLE [dbo].[TableB]
(
    [Id] [int] NOT NULL,
    [ClientId] [int] NOT NULL,
    [CertificateId] [int] NOT NULL,
    [AccountId] [int] NOT NULL,
 CONSTRAINT [PK_TableB] PRIMARY KEY CLUSTERED 
(
    [Id] ASC,
    [ClientId] ASC,
    [CertificateId] 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

SET ANSI_NULLS ON
GO
SET QUOTED_IDENTIFIER ON
GO

CREATE TABLE [dbo].[TableC]
(
    [CertificateId] [int] NOT NULL,
    [Status] [bit] NOT NULL,
    [Description] [nvarchar](50) NULL,
 CONSTRAINT [PK_TableC] PRIMARY KEY CLUSTERED 
(
    [CertificateId] 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

INSERT [dbo].[TableA] ([AccountId], [Name], [Mobile]) VALUES (1, N'John', N'98        ')
INSERT [dbo].[TableA] ([AccountId], [Name], [Mobile]) VALUES (2, N'Henry', N'9808      ')
INSERT [dbo].[TableA] ([AccountId], [Name], [Mobile]) VALUES (3, N'Paine', N'9045      ')
INSERT [dbo].[TableA] ([AccountId], [Name], [Mobile]) VALUES (4, N'Andrew', N'887       ')
INSERT [dbo].[TableA] ([AccountId], [Name], [Mobile]) VALUES (5, N'Stocks', N'78        ')
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (1, 5, 34, 1)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (2, 8, 34, 1)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (3, 7, 36, 2)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (4, 9, 37, 3)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (5, 10, 37, 4)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (6, 4, 37, 4)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (7, 61, 37, 4)
INSERT [dbo].[TableB] ([Id], [ClientId], [CertificateId], [AccountId]) VALUES (8, 45, 35, 5)
INSERT [dbo].[TableC] ([CertificateId], [Status], [Description]) VALUES (34, 1, N'Certificate 1')
INSERT [dbo].[TableC] ([CertificateId], [Status], [Description]) VALUES (35, 1, N'Certificate 2')
INSERT [dbo].[TableC] ([CertificateId], [Status], [Description]) VALUES (36, 1, N'Certificate 3')
INSERT [dbo].[TableC] ([CertificateId], [Status], [Description]) VALUES (37, 0, N'Certificate 4')
ALTER TABLE [dbo].[TableB]  WITH CHECK ADD  CONSTRAINT [FK_TableB_TableA] FOREIGN KEY([AccountId])
REFERENCES [dbo].[TableA] ([AccountId])
GO
ALTER TABLE [dbo].[TableB] CHECK CONSTRAINT [FK_TableB_TableA]
GO
ALTER TABLE [dbo].[TableB]  WITH CHECK ADD  CONSTRAINT [FK_TableB_TableC] FOREIGN KEY([CertificateId])
REFERENCES [dbo].[TableC] ([CertificateId])
GO
ALTER TABLE [dbo].[TableB] CHECK CONSTRAINT [FK_TableB_TableC]
GO

我的查询

DECLARE @From int=1
DECLARE @To int=5
; WITH CTE_Data_WITH_PAGING  AS 
  (SELECT ROW_NUMBER() OVER( ORDER BY A.AccountId) AS [ROW_NUMBERS], 
        A.AccountId, A.Name, A.Mobile FROM TableA A
        LEFT JOIN  TableB B  
        ON B.AccountId = A.AccountId
        INNER JOIN TableC C
        ON C.CertificateId=B.CertificateId 
        AND C.CertificateId<>01

        )
        SELECT  * FROM CTE_Data_WITH_PAGING WHERE ROW_NUMBERS BETWEEN @From AND @To;

我尝试用这种方式使用distinct但是分页问题。

SELECT DISTINCT(AccountId), Name, Mobile 
FROM CTE_Data_WITH_PAGING 
WHERE ROW_NUMBERS BETWEEN @From AND @To;

分页问题：尝试@from=1 @to=4 并看到 output.It 应该得到 AccountId：1, 2, 3,4

Answer 1

一个快速的解决方法是使用 dense_rank 代替，并结合 distinct。这确保每个帐户都被计算在内。还按照评论中的建议使用内部联接：

DECLARE @From int=1
DECLARE @To int=5
; WITH CTE_Data_WITH_PAGING  AS 
  (SELECT distinct dense_rank() OVER( ORDER BY A.AccountId) AS [ROW_NUMBERS], 
    A.AccountId, A.Name, A.Mobile FROM TableA A
    inner JOIN  TableB B  
    ON B.AccountId = A.AccountId
    INNER JOIN TableC C
    ON C.CertificateId=B.CertificateId 
    AND C.CertificateId<>01

    )
    SELECT  * FROM CTE_Data_WITH_PAGING WHERE ROW_NUMBERS BETWEEN @From AND @To;

我更喜欢使用 group by，而不是 distinct - 尤其是与分析函数结合使用，所以另一个选择 - 使用 row_number 可能是：

DECLARE @From int=1
DECLARE @To int=5
; WITH CTE_Data_WITH_PAGING  AS 
  (SELECT  row_number() OVER( ORDER BY A.AccountId) AS [ROW_NUMBERS], 
    A.AccountId, A.Name, A.Mobile FROM TableA A
    inner JOIN  TableB B  
    ON B.AccountId = A.AccountId
    INNER JOIN TableC C
    ON C.CertificateId=B.CertificateId 
    AND C.CertificateId<>01
    group by  A.AccountId, A.Name, A.Mobile
    )
    SELECT  * FROM CTE_Data_WITH_PAGING WHERE ROW_NUMBERS BETWEEN @From AND @To;

在这里我分组以获得唯一值。

最后，如果你只是为了分页，不需要行号，就用OFFSET和FETCH，像这样：

声明@From int=1 声明@To int=5

 SELECT  
  A.AccountId, A.Name, A.Mobile FROM TableA A
  inner JOIN  TableB B  
  ON B.AccountId = A.AccountId
  INNER JOIN TableC C
  ON C.CertificateId=B.CertificateId 
  AND C.CertificateId<>01
 group by  A.AccountId, A.Name, A.Mobile
 order by  A.AccountId
 OFFSET (@FROM-1) ROWS FETCH NEXT (@TO-(@FROM-1)) ROWS ONLY;

使用带分页的 CTE 从 3 个表中获取记录

Using CTE with paging to fetch records from 3 tables

tsql

sql-server

join

common-table-expression