SQL操作语句之查询及删除重复记录的方法

delete from 表
where id not in(select min(id) from 表 group by name ) //删除重复名字的记录

删除之前请用语句
select *
from 表
where id in(select min(id) from 表 group by name )
查看能保留下来的数据。

eg.delete from T_bbs_subject
where subjectId not in(select min(subjectId) from T_bbs_subject group by clsid )

几个删除重复记录的SQL语句

（1）用group by方法

查数据:
　　select count(num), max(name) from student --列出重复的记录数，并列出他的name属性 
　　group by num 
　　having count(num) >1 --按num分组后找出表中num列重复，即出现次数大于一次 
删数据：
　　delete from student 
　　group by num 
　　having count(num) >1
　　这样的话就把所有重复的都删除了。

查询重复

select * from tablename where id in (select id from tablename group by id having count(id) > 1)

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)

 

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

 

＂重复记录＂有两个意义上的重复记录，一是完全重复的记录，也即所有字段均重复的记录，二是部分关键字段重复的记录，比如Name字段重复，而其他字段不一定重复或都重复可以忽略。

 

1、对于第一种重复，比较容易解决，使用

select distinct * from tableName

　　就可以得到无重复记录的结果集。

　　如果该表需要删除重复的记录（重复记录保留1条），可以按以下方法删除

select distinct * into #Tmp from tableName

drop table tableName

select * into tableName from #Tmp

drop table #Tmp

　　发生这种重复的原因是表设计不周产生的，增加唯一索引列即可解决。

 

2、这类重复问题通常要求保留重复记录中的第一条记录，操作方法如下

　　假设有重复的字段为Name,Address，要求得到这两个字段唯一的结果集

select identity(int,1,1) as autoID, * into #Tmp from tableName

select min(autoID) as autoID into #Tmp2 from #Tmp group by Name,Address,autoID

select * from #Tmp where autoID in(select autoID from #tmp2)

　　最后一个select即得到了Name，Address不重复的结果集（但多了一个autoID字段，实际写时可以写在select子句中省去此列）, 用select identity(int,1,1) as id,* into #temp保存到一张临时表中，然后就可以对临时表#temp进行操作了

 

 

--I、Name相同ID最小的记录,方法在SQl05时，效率高于、
方法:
Select * from #T a where not exists(select 1 from #T where Name=a.Name and ID<a.ID)

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

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

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

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

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

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

方法:

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

--II、Name相同ID最大的记录,与min相反:
方法:
Select * from #T a where not exists(select 1 from #T where Name=a.Name and ID>a.ID)

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

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

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

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

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

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

方法:
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

 删除重复记录有大小关系时,保留大或小其中一个记录

--I、Name相同ID最小的记录,保留最小一条
方法:
delete a from #T a where  exists(select 1 from #T where Name=a.Name and ID<a.ID)

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

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

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

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

--II、Name相同ID保留最大的一条记录:

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

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

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

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

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

--3、删除重复记录没有大小关系时，处理重复值
方法:
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



--重新执行测试数据后用方法
方法:

alter table #T add ID int identity--新增标识列
go
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
go
alter table #T drop column ID--删除标识列

--查看结果
select * from #T