文章版权归小F所有!特此声明!--功能概述:删除重复记录在几千条记录里,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
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.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 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),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) */
id name sex 1 dd 女 1 dd 男 2 aa 女 2 aa 男删除后得到的结果是什么样呢? 1 dd 女 1 dd 男 中你打算删除哪一条?
1 dd 女 2 aa 男就是这样显示,删除掉多余的重复的数据!
id name sex 1 dd 女 1 dd 男 2 aa 女 2 aa 男能简单说明一下为什么删除这两条记录,而不是删除另外的两条吗?
---------------------------------------------------------------- -- Author :fredrickhu(小F,向高手学习) -- Date :2009-12-21 20:44:25 -- Version: -- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86) -- Nov 24 2008 13:01:59 -- Copyright (c) 1988-2005 Microsoft Corporation -- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3) -- ---------------------------------------------------------------- --> 测试数据:[tb] if object_id('[tb]') is not null drop table [tb] go create table [tb]([id] int,[name] varchar(2),[sex] varchar(2)) insert [tb] select 1,'dd','女' union all select 1,'dd','男' union all select 2,'aa','女' union all select 2,'aa','男' --------------开始查询--------------------------select * from [tb] t where id=(select min(id) from tb where sex=t.sex) ----------------结果---------------------------- /* id name sex ----------- ---- ---- 1 dd 男 1 dd 女(2 行受影响)
*/
delete from table1 a where exists (select 1 from table1 where id=a.id and name=a.name and sex>a.sex)
---------------------------------------------------------------- -- Author :fredrickhu(小F,向高手学习) -- Date :2009-12-21 20:44:25 -- Version: -- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86) -- Nov 24 2008 13:01:59 -- Copyright (c) 1988-2005 Microsoft Corporation -- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3) -- ---------------------------------------------------------------- --> 测试数据:[tb] if object_id('[tb]') is not null drop table [tb] go create table [tb]([id] int,[name] varchar(2),[sex] varchar(2)) insert [tb] select 1,'dd','女' union all select 1,'dd','男' union all select 2,'aa','女' union all select 2,'aa','男' --------------开始查询-------------------------- delete a from tb a where exists (select 1 from tb where name=a.name and sex>a.sex)select * from tb ----------------结果---------------------------- /* id name sex ----------- ---- ---- 1 dd 女 2 aa 女(2 行受影响) */
1> select * from tb 2> go id |name|sex -----------|----|--- 1|dd |女 1|dd |男 2|aa |女 2|aa |男(4 rows affected) 1> delete a from tb a 2> where exists (select 1 3> from tb 4> where id=a.id and name=a.name and sex>a.sex) 5> go(2 rows affected) 1> select * from tb 2> go id |name|sex -----------|----|--- 1|dd |女 2|aa |女(2 rows affected) 1>
--奇怪 ---------------------------------------------------------------- -- Author :fredrickhu(小F,向高手学习) -- Date :2009-12-21 20:44:25 -- Version: -- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86) -- Nov 24 2008 13:01:59 -- Copyright (c) 1988-2005 Microsoft Corporation -- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3) -- ---------------------------------------------------------------- --> 测试数据:[tb] if object_id('[tb]') is not null drop table [tb] go create table [tb]([id] int,[name] varchar(2),[sex] varchar(2)) insert [tb] select 1,'dd','女' union all select 1,'dd','男' union all select 2,'aa','女' union all select 2,'aa','男' --------------开始查询-------------------------- delete a from tb a where id=(select min(id) from tb where sex=a.sex)select * from tb ----------------结果---------------------------- /* id name sex ----------- ---- ---- 2 aa 女 2 aa 男(2 行受影响) */
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
/******************************************************************************************************************************************************
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.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
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),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)
*/
参考一下这个贴子的提问方式http://topic.csdn.net/u/20091130/20/8343ee6a-417c-4c2d-9415-fa46604a00cf.html
1. 你的 create table xxx .. 语句
2. 你的 insert into xxx ... 语句
3. 结果是什么样,(并给以简单的算法描述)
4. 你用的数据库名称和版本(经常有人在MS SQL server版问 MySQL)
这样想帮你的人可以直接搭建和你相同的环境,并在给出方案前进行测试,避免文字描述理解上的误差。
1 dd 女
1 dd 男
2 aa 女
2 aa 男
1 dd 女
1 dd 男
2 aa 女
2 aa 男删除后得到的结果是什么样呢?
1 dd 女
1 dd 男
中你打算删除哪一条?
2 aa 男就是这样显示,删除掉多余的重复的数据!
1 dd 女
1 dd 男2 aa 女
2 aa 男能简单说明一下为什么删除这两条记录,而不是删除另外的两条吗?
-- Author :fredrickhu(小F,向高手学习)
-- Date :2009-12-21 20:44:25
-- Version:
-- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86)
-- Nov 24 2008 13:01:59
-- Copyright (c) 1988-2005 Microsoft Corporation
-- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3)
--
----------------------------------------------------------------
--> 测试数据:[tb]
if object_id('[tb]') is not null drop table [tb]
go
create table [tb]([id] int,[name] varchar(2),[sex] varchar(2))
insert [tb]
select 1,'dd','女' union all
select 1,'dd','男' union all
select 2,'aa','女' union all
select 2,'aa','男'
--------------开始查询--------------------------select * from [tb] t where id=(select min(id) from tb where sex=t.sex)
----------------结果----------------------------
/*
id name sex
----------- ---- ----
1 dd 男
1 dd 女(2 行受影响)
*/
where exists (select 1
from table1
where id=a.id and name=a.name and sex>a.sex)
'a' 附近有语法错误。有错啊,delete 后加 a 就没错了,但是受影响行数为0
delete a from table1 a
where exists (select 1
from table1
where name=a.name and sex>a.sex)
-- Author :fredrickhu(小F,向高手学习)
-- Date :2009-12-21 20:44:25
-- Version:
-- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86)
-- Nov 24 2008 13:01:59
-- Copyright (c) 1988-2005 Microsoft Corporation
-- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3)
--
----------------------------------------------------------------
--> 测试数据:[tb]
if object_id('[tb]') is not null drop table [tb]
go
create table [tb]([id] int,[name] varchar(2),[sex] varchar(2))
insert [tb]
select 1,'dd','女' union all
select 1,'dd','男' union all
select 2,'aa','女' union all
select 2,'aa','男'
--------------开始查询--------------------------
delete
a
from
tb a
where
exists (select 1 from tb where name=a.name and sex>a.sex)select * from tb
----------------结果----------------------------
/*
id name sex
----------- ---- ----
1 dd 女
2 aa 女(2 行受影响)
*/
2> go
id |name|sex
-----------|----|---
1|dd |女
1|dd |男
2|aa |女
2|aa |男(4 rows affected)
1> delete a from tb a
2> where exists (select 1
3> from tb
4> where id=a.id and name=a.name and sex>a.sex)
5> go(2 rows affected)
1> select * from tb
2> go
id |name|sex
-----------|----|---
1|dd |女
2|aa |女(2 rows affected)
1>
----------------------------------------------------------------
-- Author :fredrickhu(小F,向高手学习)
-- Date :2009-12-21 20:44:25
-- Version:
-- Microsoft SQL Server 2005 - 9.00.4035.00 (Intel X86)
-- Nov 24 2008 13:01:59
-- Copyright (c) 1988-2005 Microsoft Corporation
-- Developer Edition on Windows NT 5.1 (Build 2600: Service Pack 3)
--
----------------------------------------------------------------
--> 测试数据:[tb]
if object_id('[tb]') is not null drop table [tb]
go
create table [tb]([id] int,[name] varchar(2),[sex] varchar(2))
insert [tb]
select 1,'dd','女' union all
select 1,'dd','男' union all
select 2,'aa','女' union all
select 2,'aa','男'
--------------开始查询--------------------------
delete
a
from
tb a
where
id=(select min(id) from tb where sex=a.sex)select * from tb
----------------结果----------------------------
/*
id name sex
----------- ---- ----
2 aa 女
2 aa 男(2 行受影响)
*/