sql server 找重复值 sql如何找出重复数据

转载

IT剑客之家 2023-09-24 21:29:13

文章标签 sql server 找重复值 sql delete table insert 文章分类 SQL Server 数据库

--功能概述:删除重复记录

--做成时间:2008/10/31

在几千条记录里,存在着些相同的记录,如何能用SQL语句,删除掉重复的呢?谢谢!

1、查找表中多余的重复记录，重复记录是根据单个字段（peopleId）来判断

select * from people

where peopleId in (select peopleId from people group by peopleId having count(peopleId) > 1)

2、删除表中多余的重复记录，重复记录是根据单个字段（peopleId）来判断，只留有rowid最小的记录

delete from people

where peopleId in (select peopleId from people group by peopleId having count(peopleId) > 1)

and rowid not in (select min(rowid) from people group by peopleId having count(peopleId )>1)

3、查找表中多余的重复记录（多个字段）

select * from vitae a

where (a.peopleId,a.seq) in (select peopleId,seq from vitae group by peopleId,seq having count(*) > 1)

4、删除表中多余的重复记录（多个字段），只留有rowid最小的记录

delete from vitae a

where (a.peopleId,a.seq) in (select peopleId,seq from vitae group by peopleId,seq having count(*) > 1)

and rowid not in (select min(rowid) from vitae group by peopleId,seq having count(*)>1)

5、查找表中多余的重复记录（多个字段），不包含rowid最小的记录

select * from vitae a

where (a.peopleId,a.seq) in (select peopleId,seq from vitae group by peopleId,seq having count(*) > 1)

and rowid not in (select min(rowid) from vitae group by peopleId,seq having count(*)>1)

比方说在A表中存在一个字段“name”，而且不同记录之间的“name”值有可能会相同，

现在就是需要查询出在该表中的各记录之间，“name”值存在重复的项；

Select Name,Count(*) From A Group By Name Having Count(*) > 1

如果还查性别也相同大则如下:

Select Name,sex,Count(*) From A Group By Name,sex Having Count(*) > 1

--处理表重复记录(查询和删除)

/******************************************************************************************************************************************************

1、Num、Name相同的重复值记录,没有大小关系只保留一条

2、Name相同,ID有大小关系时,保留大或小其中一个记录

整理人：中国风(Roy)

日期:2008.06.06

******************************************************************************************************************************************************/

--1、用于查询重复处理记录(如果列没有大小关系时2000用生成自增列和临时表处理,SQL2005用row_number函数处理)

--> --> (Roy)生成測試數據

if not object_id('Tempdb..#T') is null

drop table #T

Create table #T([ID] int,[Name] nvarchar(1),[Memo] nvarchar(2))

Insert #T

select 1,N'A',N'A1' union all

select 2,N'A',N'A2' union all

select 3,N'A',N'A3' union all

select 4,N'B',N'B1' union all

select 5,N'B',N'B2'

--I、Name相同ID最小的记录(推荐用1,2,3),方法3在SQl05时，效率高于1、2

方法1:

Select * from #T a where not exists(select 1 from #T where Name=a.Name and ID<a.ID)

方法2:

select a.* from #T a join (select min(ID)ID,Name from #T group by Name) b on a.Name=b.Name and a.ID=b.ID

方法3:

select * from #T a where ID=(select min(ID) from #T where Name=a.Name)

方法4:

select a.* from #T a join #T b on a.Name=b.Name and a.ID>=b.ID group by a.ID,a.Name,a.Memo having count(1)=1

方法5:

select * from #T a group by ID,Name,Memo having ID=(select min(ID)from #T where Name=a.Name)

方法6:

select * from #T a where (select count(1) from #T where Name=a.Name and ID<a.ID)=0

方法7:

select * from #T a where ID=(select top 1 ID from #T where Name=a.name order by ID)

方法8:

select * from #T a where ID!>all(select ID from #T where Name=a.Name)

方法9(注:ID为唯一时可用):

select * from #T a where ID in(select min(ID) from #T group by Name)

--SQL2005:

方法10:

select ID,Name,Memo from (select *,min(ID)over(partition by Name) as MinID from #T a)T where ID=MinID

方法11:

select ID,Name,Memo from (select *,row_number()over(partition by Name order by ID) as MinID from #T a)T where MinID=1

生成结果:

ID Name Memo

----------- ---- ----

1 A A1

4 B B1

(2 行受影响)

--II、Name相同ID最大的记录,与min相反:

方法1:

Select * from #T a where not exists(select 1 from #T where Name=a.Name and ID>a.ID)

方法2:

select a.* from #T a join (select max(ID)ID,Name from #T group by Name) b on a.Name=b.Name and a.ID=b.ID order by ID

方法3:

select * from #T a where ID=(select max(ID) from #T where Name=a.Name) order by ID

方法4:

select a.* from #T a join #T b on a.Name=b.Name and a.ID<=b.ID group by a.ID,a.Name,a.Memo having count(1)=1

方法5:

select * from #T a group by ID,Name,Memo having ID=(select max(ID)from #T where Name=a.Name)

方法6:

select * from #T a where (select count(1) from #T where Name=a.Name and ID>a.ID)=0

方法7:

select * from #T a where ID=(select top 1 ID from #T where Name=a.name order by ID desc)

方法8:

select * from #T a where ID!<all(select ID from #T where Name=a.Name)

方法9(注:ID为唯一时可用):

select * from #T a where ID in(select max(ID) from #T group by Name)

--SQL2005:

方法10:

select ID,Name,Memo from (select *,max(ID)over(partition by Name) as MinID from #T a)T where ID=MinID

方法11:

select ID,Name,Memo from (select *,row_number()over(partition by Name order by ID desc) as MinID from #T a)T where MinID=1

生成结果2:

ID Name Memo

----------- ---- ----

3 A A3

5 B B2

(2 行受影响)

--2、删除重复记录有大小关系时,保留大或小其中一个记录

--> --> (Roy)生成測試數據

if not object_id('Tempdb..#T') is null

drop table #T

Create table #T([ID] int,[Name] nvarchar(1),[Memo] nvarchar(2))

Insert #T

select 1,N'A',N'A1' union all

select 2,N'A',N'A2' union all

select 3,N'A',N'A3' union all

select 4,N'B',N'B1' union all

select 5,N'B',N'B2'

--I、Name相同ID最小的记录(推荐用1,2,3),保留最小一条

方法1:

delete a from #T a where exists(select 1 from #T where Name=a.Name and ID<a.ID)

方法2:

delete a from #T a left join (select min(ID)ID,Name from #T group by Name) b on a.Name=b.Name and a.ID=b.ID where b.Id is null

方法3:

delete a from #T a where ID not in (select min(ID) from #T where Name=a.Name)

方法4(注:ID为唯一时可用):

delete a from #T a where ID not in(select min(ID)from #T group by Name)

方法5:

delete a from #T a where (select count(1) from #T where Name=a.Name and ID<a.ID)>0

方法6:

delete a from #T a where ID<>(select top 1 ID from #T where Name=a.name order by ID)

方法7:

delete a from #T a where ID>any(select ID from #T where Name=a.Name)

select * from #T

生成结果:

ID Name Memo

----------- ---- ----

1 A A1

4 B B1

(2 行受影响)

--II、Name相同ID保留最大的一条记录:

方法1:

delete a from #T a where exists(select 1 from #T where Name=a.Name and ID>a.ID)

方法2:

delete a from #T a left join (select max(ID)ID,Name from #T group by Name) b on a.Name=b.Name and a.ID=b.ID where b.Id is null

方法3:

delete a from #T a where ID not in (select max(ID) from #T where Name=a.Name)

方法4(注:ID为唯一时可用):

delete a from #T a where ID not in(select max(ID)from #T group by Name)

方法5:

delete a from #T a where (select count(1) from #T where Name=a.Name and ID>a.ID)>0

方法6:

delete a from #T a where ID<>(select top 1 ID from #T where Name=a.name order by ID desc)

方法7:

delete a from #T a where ID<any(select ID from #T where Name=a.Name)

select * from #T

ID Name Memo

----------- ---- ----

3 A A3

5 B B2

(2 行受影响)

--3、删除重复记录没有大小关系时，处理重复值

--> --> (Roy)生成測試數據

if not object_id('Tempdb..#T') is null

drop table #T

Create table #T([Num] int,[Name] nvarchar(1))

Insert #T

select 1,N'A' union all

select 2,N'B' union all

select 2,N'B'

方法1:

if object_id('Tempdb..#') is not null

drop table #

Select distinct * into # from #T--排除重复记录结果集生成临时表#

truncate table #T--清空表

insert #T select * from # --把临时表#插入到表#T中

--查看结果

select * from #T

Num Name

----------- ----

1 A

2 B

(2 行受影响)

--重新执行测试数据后用方法2

方法2:

alter table #T add ID int identity--新增标识列

delete a from #T a where exists(select 1 from #T where Num=a.Num and Name=a.Name and ID>a.ID)--只保留一条记录

alter table #T drop column ID--删除标识列

--查看结果

select * from #T

Num Name

----------- ----

1 A

2 B

(2 行受影响)

--重新执行测试数据后用方法3

方法3:

declare Roy_Cursor cursor local for

select count(1)-1,Num,Name from #T group by Num,Name having count(1)>1

declare @con int,@Num int,@Name nvarchar(1)

open Roy_Cursor

fetch next from Roy_Cursor into @con,@Num,@Name

while @@Fetch_status=0

begin

set rowcount @con;

delete #T where Num=@Num and Name=@Name

set rowcount 0;

fetch next from Roy_Cursor into @con,@Num,@Name

end

close Roy_Cursor

deallocate Roy_Cursor

--查看结果

select * from #T

Num Name

----------- ----

1 A

2 B

(2 行受影响)

本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。

上一篇：java damo java大模型

下一篇：java 根据文件名生成Hash值 java计算文件hash码

提问和评论都可以，用心的回复会被更多人看到评论

发布评论

相关文章

官方博客	全部文章	热门标签	班级博客
了解我们	网站地图	意见反馈

鸿蒙开发者社区	51CTO学堂
51CTO	软考资讯

sql server 找重复值 sql如何找出重复数据

sql server 找重复值 sql如何找出重复数据

51CTO博客