我更喜欢CTE从sql server表中删除重复的行

强烈推荐阅读本文::http://codaffection.com/sql-server-article/delete-duplicate-rows-in-sql-server/

保持原创性

WITH CTE AS
(
SELECT *,ROW_NUMBER() OVER (PARTITION BY col1,col2,col3 ORDER BY col1,col2,col3) AS RN
FROM MyTable
)

DELETE FROM CTE WHERE RN<>1

不保留原创

WITH CTE AS
(SELECT *,R=RANK() OVER (ORDER BY col1,col2,col3)
FROM MyTable)
 
DELETE CTE
WHERE R IN (SELECT R FROM CTE GROUP BY R HAVING COUNT(*)>1)

DECLARE @TB TABLE(NAME VARCHAR(100));
INSERT INTO @TB VALUES ('Red'),('Red'),('Green'),('Blue'),('White'),('White')
--**Delete by Rank**
;WITH CTE AS(SELECT NAME,DENSE_RANK() OVER (PARTITION BY NAME ORDER BY NEWID()) ID FROM @TB)
DELETE FROM CTE WHERE ID>1
SELECT NAME FROM @TB;
--**Delete by Row Number** 
;WITH CTE AS(SELECT NAME,ROW_NUMBER() OVER (PARTITION BY NAME ORDER BY NAME) ID FROM @TB)
DELETE FROM CTE WHERE ID>1;
SELECT NAME FROM @TB;

请参见下面的删除方式。

Declare @table table
(col1 varchar(10),col2 int,col3 int, col4 int, col5 int, col6 int, col7 int)
Insert into @table values 
('john',1,1,1,1,1,1),
('john',1,1,1,1,1,1),
('sally',2,2,2,2,2,2),
('sally',2,2,2,2,2,2)

创建一个名为@table的样例表，并用给定的数据加载它。

Delete  aliasName from (
Select  *,
        ROW_NUMBER() over (Partition by col1,col2,col3,col4,col5,col6,col7 order by col1) as rowNumber
From    @table) aliasName 
Where   rowNumber > 1

Select * from @table

注意:如果您按部分给出分区中的所有列，那么按顺序没有多大意义。

我知道，这个问题是三年前问的，我的答案是蒂姆发布的另一个版本，但发布只是为了对任何人有帮助。

如果你有能力临时添加一个列到表中，这是一个适合我的解决方案:

ALTER TABLE dbo.DUPPEDTABLE ADD RowID INT NOT NULL IDENTITY(1,1)

然后使用MIN和GROUP BY的组合执行DELETE

DELETE b
FROM dbo.DUPPEDTABLE b
WHERE b.RowID NOT IN (
                     SELECT MIN(RowID) AS RowID
                     FROM dbo.DUPPEDTABLE a WITH (NOLOCK)
                     GROUP BY a.ITEM_NUMBER,
                              a.CHARACTERISTIC,
                              a.INTVALUE,
                              a.FLOATVALUE,
                              a.STRINGVALUE
                 );

验证DELETE执行正确:

SELECT a.ITEM_NUMBER,
    a.CHARACTERISTIC,
    a.INTVALUE,
    a.FLOATVALUE,
    a.STRINGVALUE, COUNT(*)--MIN(RowID) AS RowID
FROM dbo.DUPPEDTABLE a WITH (NOLOCK)
GROUP BY a.ITEM_NUMBER,
    a.CHARACTERISTIC,
    a.INTVALUE,
    a.FLOATVALUE,
    a.STRINGVALUE
ORDER BY COUNT(*) DESC 

结果中不应有计数大于1的行。最后，删除rowid列:

ALTER TABLE dbo.DUPPEDTABLE DROP COLUMN RowID;

在sql server中可以通过多种方式来实现 最简单的方法是: 将重复行表中的不同行插入到新的临时表中。然后从重复的行表中删除所有数据，然后从没有重复的临时表中插入所有数据，如下所示。

select distinct * into #tmp From table
   delete from table
   insert into table
   select * from #tmp drop table #tmp

   select * from table

使用公共表表达式(CTE)删除重复行

With CTE_Duplicates as 
(select id,name , row_number() 
over(partition by id,name order by id,name ) rownumber  from table  ) 
delete from CTE_Duplicates where rownumber!=1

-- this query will keep only one instance of a duplicate record.
;WITH cte
     AS (SELECT ROW_NUMBER() OVER (PARTITION BY col1, col2, col3-- based on what? --can be multiple columns
                                       ORDER BY ( SELECT 0)) RN
         FROM   Mytable)



delete  FROM cte
WHERE  RN > 1