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。
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,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)
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,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)
3、部分关键字段重复,且记录中有ID.
第一种方法可一次删除所有重复的..(只保留重复中ID最小的记录)。
delete from table where id not in ( select min(id) from table group by name)
delete from table where id not in ( select min(id) from table group by name)
第二种方法每次只删除重复中ID最大的一条记录。
delete from table where id in ( select max(id) from table group by name having count(*)>1)
4、SQL程序删除
declare @max integer,@id integer
declare cur_rows cursor local for select 主字段,count(*) from 表名 group by 主字段 having count(*) > 1
open cur_rows
fetch cur_rows into @id,@max
while @@fetch_status=0
begin
select @max = @max -1
set rowcount @max
delete from 表名 where 主字段 = @id
fetch cur_rows into @id,@max
end
close cur_rows
set rowcount 0
自己还得出的办法:
select * from user1 where [id] not in (select top 1 [id] from user1 a where name=user1.name)
--删就这样写
delete from user1 where [id] not in (select top 1 [id] from user1 a where name=user1.name)
或 delete from user where id not in ( select max(id) from user where name=user.name)
delete [user] where id not in (select max(id) from [user] group by name having count(*) > 1)
max 或 min看具体情况而论。
其他方法:
----A:保留id最大的行,删除其它行
--方法1
delete [user] from [user] t
inner join(select name,max(id) as id from [user] group by name) a
on t.name = a.name and t.id <> a.id
--方法2
delete [user] from [user] t
where exists(select * from [user] where name = t.name and id > t.id)
----B:保留id最小的行,删除其它行
--方法1
delete [user] from [user] t
inner join(select name,min(id) as id from [user] group by name) a
on t.name = a.name and t.id <> a.id
--方法2
delete [user] from [user] t
where exists(select * from [user] where name = t.name and id < t.id)
----C:删除所有重复的name行,一行也不留
delete [user] from [user] t
inner join
(select id from [user] a where exists(select * from [user] where name = a.name group by name having count(*) > 1)) as b
on t.id = b.id
declare cur_rows cursor local for select 主字段,count(*) from 表名 group by 主字段 having count(*) > 1
open cur_rows
fetch cur_rows into @id,@max
while @@fetch_status=0
begin
select @max = @max -1
set rowcount @max
delete from 表名 where 主字段 = @id
fetch cur_rows into @id,@max
end
close cur_rows
set rowcount 0
自己还得出的办法:
select * from user1 where [id] not in (select top 1 [id] from user1 a where name=user1.name)
--删就这样写
delete from user1 where [id] not in (select top 1 [id] from user1 a where name=user1.name)
或 delete from user where id not in ( select max(id) from user where name=user.name)
delete [user] where id not in (select max(id) from [user] group by name having count(*) > 1)
max 或 min看具体情况而论。
其他方法:
----A:保留id最大的行,删除其它行
--方法1
delete [user] from [user] t
inner join(select name,max(id) as id from [user] group by name) a
on t.name = a.name and t.id <> a.id
--方法2
delete [user] from [user] t
where exists(select * from [user] where name = t.name and id > t.id)
----B:保留id最小的行,删除其它行
--方法1
delete [user] from [user] t
inner join(select name,min(id) as id from [user] group by name) a
on t.name = a.name and t.id <> a.id
--方法2
delete [user] from [user] t
where exists(select * from [user] where name = t.name and id < t.id)
----C:删除所有重复的name行,一行也不留
delete [user] from [user] t
inner join
(select id from [user] a where exists(select * from [user] where name = a.name group by name having count(*) > 1)) as b
on t.id = b.id