使用 merge..output 获取 source.id 和 target.id 之间的映射

Question

很简单，我有两张表Source和Target。

declare @Source table (SourceID int identity(1,2), SourceName varchar(50))
declare @Target table (TargetID int identity(2,2), TargetName varchar(50))

insert into @Source values ('Row 1'), ('Row 2')

我想将所有行从 @Source 移动到 @Target 并知道每个 SourceID 的 TargetID 因为还有表 SourceChild 和 TargetChild 也需要复制，并且我需要将新的TargetID 添加到TargetChild.TargetID FK 列中。

有几个解决方案。

1. 使用 while 循环或游标一次将一行 (RBAR) 插入到 Target，并使用 scope_identity() 填充 TargetChild 的 FK。
2. 将临时列添加到@Target 并插入SourceID。然后，您可以加入该列以获取 TargetID 中的 FK 的 TargetChild。
3. SET IDENTITY_INSERT OFF 用于 @Target 并自己处理分配新值。您会得到一个范围，然后在 TargetChild.TargetID 中使用。

我不是很喜欢他们中的任何一个。我目前使用的是游标。

我真正想做的是使用插入语句的output 子句。

insert into @Target(TargetName)
output inserted.TargetID, S.SourceID
select SourceName
from @Source as S

但这是不可能的

The multi-part identifier "S.SourceID" could not be bound.

但是可以通过合并来实现。

merge @Target as T
using @Source as S
on 0=1
when not matched then
  insert (TargetName) values (SourceName)
output inserted.TargetID, S.SourceID;

结果

TargetID    SourceID
----------- -----------
2           1
4           3

我想知道你有没有用过这个？如果您对解决方案有任何想法或发现任何问题？它在简单的场景中运行良好，但当查询计划由于复杂的源查询而变得非常复杂时，可能会发生一些丑陋的事情。最坏的情况是 TargetID/SourceID 对实际上不匹配。

MSDN 对output 子句的from_table_name 有这样的说法。

是一个列前缀，它指定包含在 DELETE、UPDATE 或 MERGE 语句的 FROM 子句中的表，用于指定要更新或删除的行。

出于某种原因，他们不会说“要插入、更新或删除的行”，而只会说“要更新或删除的行”。

欢迎提出任何想法，非常感谢对原始问题完全不同的解决方案。

Answer 1

在我看来，这是对 MERGE 和输出的一个很好的使用。我已经在几个场景中使用过，到目前为止还没有遇到任何奇怪的事情。 例如，这是将文件夹和其中的所有文件（身份）克隆到新创建的文件夹（guid）中的测试设置。

DECLARE @FolderIndex TABLE (FolderId UNIQUEIDENTIFIER PRIMARY KEY, FolderName varchar(25));
INSERT INTO @FolderIndex 
    (FolderId, FolderName)
    VALUES(newid(), 'OriginalFolder');

DECLARE @FileIndex TABLE (FileId int identity(1,1) PRIMARY KEY, FileName varchar(10));
INSERT INTO @FileIndex 
    (FileName)
    VALUES('test.txt');

DECLARE @FileFolder TABLE (FolderId UNIQUEIDENTIFIER, FileId int, PRIMARY KEY(FolderId, FileId));
INSERT INTO @FileFolder 
    (FolderId, FileId)
    SELECT  FolderId, 
            FileId
    FROM    @FolderIndex
    CROSS JOIN  @FileIndex;  -- just to illustrate

DECLARE @sFolder TABLE (FromFolderId UNIQUEIDENTIFIER, ToFolderId UNIQUEIDENTIFIER);
DECLARE @sFile TABLE (FromFileId int, ToFileId int);

-- copy Folder Structure
MERGE @FolderIndex fi
USING   (   SELECT  1 [Dummy],
                    FolderId, 
                    FolderName
            FROM    @FolderIndex [fi]
            WHERE   FolderName = 'OriginalFolder'
        ) d ON  d.Dummy = 0
WHEN NOT MATCHED 
THEN INSERT 
    (FolderId, FolderName)
    VALUES (newid(), 'copy_'+FolderName)
OUTPUT  d.FolderId,
        INSERTED.FolderId
INTO    @sFolder (FromFolderId, toFolderId);

-- copy File structure
MERGE   @FileIndex fi
USING   (   SELECT  1 [Dummy],
                    fi.FileId, 
                    fi.[FileName]
            FROM    @FileIndex fi
            INNER
            JOIN    @FileFolder fm ON 
                    fi.FileId = fm.FileId
            INNER
            JOIN    @FolderIndex fo ON 
                    fm.FolderId = fo.FolderId
            WHERE   fo.FolderName = 'OriginalFolder'
        ) d ON  d.Dummy = 0
WHEN NOT MATCHED 
THEN INSERT ([FileName])
    VALUES ([FileName])
OUTPUT  d.FileId,
        INSERTED.FileId
INTO    @sFile (FromFileId, toFileId);

-- link new files to Folders
INSERT INTO @FileFolder (FileId, FolderId)
    SELECT  sfi.toFileId, sfo.toFolderId
    FROM    @FileFolder fm
    INNER
    JOIN    @sFile sfi ON  
            fm.FileId = sfi.FromFileId
    INNER
    JOIN    @sFolder sfo ON 
            fm.FolderId = sfo.FromFolderId
-- return    
SELECT  * 
FROM    @FileIndex fi 
JOIN    @FileFolder ff ON  
        fi.FileId = ff.FileId 
JOIN    @FolderIndex fo ON  
        ff.FolderId = fo.FolderId

Answer 2

我想添加另一个示例以添加到 @Nathan 的示例中，因为我发现它有些混乱。

我的大部分使用真实表，而不是临时表。

我的灵感也是从这里得到的：another example

-- Copy the FormSectionInstance
DECLARE @FormSectionInstanceTable TABLE(OldFormSectionInstanceId INT, NewFormSectionInstanceId INT)

;MERGE INTO [dbo].[FormSectionInstance]
USING
(
    SELECT
        fsi.FormSectionInstanceId [OldFormSectionInstanceId]
        , @NewFormHeaderId [NewFormHeaderId]
        , fsi.FormSectionId
        , fsi.IsClone
        , @UserId [NewCreatedByUserId]
        , GETDATE() NewCreatedDate
        , @UserId [NewUpdatedByUserId]
        , GETDATE() NewUpdatedDate
    FROM [dbo].[FormSectionInstance] fsi
    WHERE fsi.[FormHeaderId] = @FormHeaderId 
) tblSource ON 1=0 -- use always false condition
WHEN NOT MATCHED
THEN INSERT
( [FormHeaderId], FormSectionId, IsClone, CreatedByUserId, CreatedDate, UpdatedByUserId, UpdatedDate)
VALUES( [NewFormHeaderId], FormSectionId, IsClone, NewCreatedByUserId, NewCreatedDate, NewUpdatedByUserId, NewUpdatedDate)

OUTPUT tblSource.[OldFormSectionInstanceId], INSERTED.FormSectionInstanceId
INTO @FormSectionInstanceTable(OldFormSectionInstanceId, NewFormSectionInstanceId);


-- Copy the FormDetail
INSERT INTO [dbo].[FormDetail]
    (FormHeaderId, FormFieldId, FormSectionInstanceId, IsOther, Value, CreatedByUserId, CreatedDate, UpdatedByUserId, UpdatedDate)
SELECT
    @NewFormHeaderId, FormFieldId, fsit.NewFormSectionInstanceId, IsOther, Value, @UserId, CreatedDate, @UserId, UpdatedDate
FROM [dbo].[FormDetail] fd
INNER JOIN @FormSectionInstanceTable fsit ON fsit.OldFormSectionInstanceId = fd.FormSectionInstanceId
WHERE [FormHeaderId] = @FormHeaderId

Answer 3

这是一个不使用 MERGE 的解决方案（我曾多次遇到问题，如果可能的话，我会尽量避免）。它依赖于两个内存表（如果需要，您可以使用临时表）与匹配的 IDENTITY 列，重要的是，在执行 INSERT 时使用 ORDER BY，以及在两个 INSERT 之间匹配的 WHERE 条件......第一个持有源 ID，第二个保存目标 ID。

-- Setup...   We have a table that we need to know the old IDs and new IDs after copying.
-- We want to copy all of DocID=1
DECLARE @newDocID int = 99;
DECLARE @tbl table (RuleID int PRIMARY KEY NOT NULL IDENTITY(1, 1), DocID int, Val varchar(100));
INSERT INTO @tbl (DocID, Val) VALUES (1, 'RuleA-2'), (1, 'RuleA-1'), (2, 'RuleB-1'), (2, 'RuleB-2'), (3, 'RuleC-1'), (1, 'RuleA-3')

-- Create a break in IDENTITY values.. just to simulate more realistic data
INSERT INTO @tbl (Val) VALUES ('DeleteMe'), ('DeleteMe');
DELETE FROM @tbl WHERE Val = 'DeleteMe';
INSERT INTO @tbl (DocID, Val) VALUES (6, 'RuleE'), (7, 'RuleF');

SELECT * FROM @tbl t;

-- Declare TWO temp tables each with an IDENTITY - one will hold the RuleID of the items we are copying, other will hold the RuleID that we create
DECLARE @input table (RID int IDENTITY(1, 1), SourceRuleID int NOT NULL, Val varchar(100));
DECLARE @output table (RID int IDENTITY(1,1), TargetRuleID int NOT NULL, Val varchar(100));

-- Capture the IDs of the rows we will be copying by inserting them into the @input table
-- Important - we must specify the sort order - best thing is to use the IDENTITY of the source table (t.RuleID) that we are copying
INSERT INTO @input (SourceRuleID, Val) SELECT t.RuleID, t.Val FROM @tbl t WHERE t.DocID = 1 ORDER BY t.RuleID;

-- Copy the rows, and use the OUTPUT clause to capture the IDs of the inserted rows.
-- Important - we must use the same WHERE and ORDER BY clauses as above
INSERT INTO @tbl (DocID, Val)
OUTPUT Inserted.RuleID, Inserted.Val INTO @output(TargetRuleID, Val)
SELECT @newDocID, t.Val FROM @tbl t 
WHERE t.DocID = 1
ORDER BY t.RuleID;

-- Now @input and @output should have the same # of rows, and the order of both inserts was the same, so the IDENTITY columns (RID) can be matched
-- Use this as the map from old-to-new when you are copying sub-table rows
-- Technically, @input and @output don't even need the 'Val' columns, just RID and RuleID - they were included here to prove that the rules matched
SELECT i.*, o.* FROM @output o
INNER JOIN @input i ON i.RID = o.RID

-- Confirm the matching worked
SELECT * FROM @tbl t