日期:2014-05-18  浏览次数:20417 次

一组30万数据怎么查找多项重复的能快一点。
如何写一个sql 语句把 字段2 并且 字段1 双重重复 的数据删除只保留一条最新时间的数据。

id 字段1 字段2 字段3
1 22 xx 2010-10-01
2 32 kd 2009-09-08
3 22 xx 2009-10-01
4 44 jj 2009-09-08
5 44 jj 2010-09-08

........................
........................
........................



如果没有 主键ID 如何删除重复的 字段2 数据 只保留一条最新时间的数据。(如下图)

  字段1 字段2 字段3
  22 xx 2010-10-01
  32 kd 2009-09-08
  22 xx 2009-10-01
  22 jj 2009-09-08
........................
........................
........................
请问如何写SQL 能快一点 谢谢。

------解决方案--------------------
SQL code

--一个样
select * from [table] t
where 字段3=(select max(字段3) from [table] where 字段1=t.字段1 and 字段2=t.字段2)

------解决方案--------------------
SQL code
select *
--delete a   --建议先查询,确认数据无误后del。
from 表名 as a
where exists (
select *
from 表名
where a.字段1 = 字段1 and a.字段2 =字段2 and a.字段3 < 字段3)

------解决方案--------------------
SQL code

SELECT * FROM t a 
WHERE NOT EXISTS(SELECT 1 FROM t WHERE a.字段1=字段1 AND a.字段2=字段2 AND 字段3>a.字段3)

------解决方案--------------------
SQL code
--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
Go
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'
Go


--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.Me