SQL查询重复处理记录
来源:互联网 发布:血手幽灵数据共享平台 编辑:程序博客网 时间:2024/05/22 21:01
- --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:
-
- --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:
-
- --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:
-
- --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
-
- --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
- Go
- Create table #T([Num] int,[Name] nvarchar(1))
- Insert #T
- select 1,N'A' union all
- select 1,N'A' union all
- select 1,N'A' union all
- select 2,N'B' union all
- select 2,N'B'
- Go
- 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
-
- --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
- 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
-
- --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
- --创建表并插入数据:
- create table tb(name varchar(10),val int,memo varchar(20))
- insert into tb values('a', 2, 'a2(a的第二个值)')
- insert into tb values('a', 1, 'a1--a的第一个值')
- insert into tb values('a', 3, 'a3:a的第三个值')
- insert into tb values('b', 1, 'b1--b的第一个值')
- insert into tb values('b', 3, 'b3:b的第三个值')
- insert into tb values('b', 2, 'b2b2b2b2')
- insert into tb values('b', 4, 'b4b4')
- insert into tb values('b', 5, 'b5b5b5b5b5')
- go
- --一、按name分组取val最大的值所在行的数据。
- --方法1:
- select a.* from tb a where val = (select max(val) from tb where name = a.name) order by a.name
- --方法2:
- select a.* from tb a where not exists(select 1 from tb where name = a.name and val > a.val)
- --方法3:
- select a.* from tb a,(select name,max(val) val from tb group by name) b where a.name = b.name and a.val = b.val order by a.name
- --方法4:
- select a.* from tb a inner join (select name , max(val) val from tb group by name) b on a.name = b.name and a.val = b.val order by a.name
- --方法5
- select a.* from tb a where 1 > (select count(*) from tb where name = a.name and val > a.val ) order by a.name
- --二、按name分组取val最小的值所在行的数据。
- --方法1:
- select a.* from tb a where val = (select min(val) from tb where name = a.name) order by a.name
- --方法2:
- select a.* from tb a where not exists(select 1 from tb where name = a.name and val < a.val)
- --方法3:
- select a.* from tb a,(select name,min(val) val from tb group by name) b where a.name = b.name and a.val = b.val order by a.name
- --方法4:
- select a.* from tb a inner join (select name , min(val) val from tb group by name) b on a.name = b.name and a.val = b.val order by a.name
- --方法5
- select a.* from tb a where 1 > (select count(*) from tb where name = a.name and val < a.val) order by a.name
- --三、按name分组取第一次出现的行所在的数据。
- select a.* from tb a where val = (select top 1 val from tb where name = a.name) order by a.name
- --四、按name分组随机取一条数据。
- select a.* from tb a where val = (select top 1 val from tb where name = a.name order by newid()) order by a.name
- --五、按name分组取最小的两个(N个)val
- select a.* from tb a where 2 > (select count(*) from tb where name = a.name and val < a.val ) order by a.name,a.val
- select a.* from tb a where val in (select top 2 val from tb where name=a.name order by val) order by a.name,a.val
- select a.* from tb a where exists (select count(*) from tb where name = a.name and val < a.val having Count(*) < 2) order by a.name
- --六、按name分组取最大的两个(N个)val
- select a.* from tb a where 2 > (select count(*) from tb where name = a.name and val > a.val ) order by a.name,a.val
- select a.* from tb a where val in (select top 2 val from tb where name=a.name order by val desc) order by a.name,a.val
- select a.* from tb a where exists (select count(*) from tb where name = a.name and val > a.val having Count(*) < 2) order by a.name
- --七,如果整行数据有重复,所有的列都相同。
- --在sql server 2000中只能用一个临时表来解决,生成一个自增列,先对val取最大或最小,然后再通过自增列来取数据。
- --创建表并插入数据:
- create table tb(name varchar(10),val int,memo varchar(20))
- insert into tb values('a', 2, 'a2(a的第二个值)')
- insert into tb values('a', 1, 'a1--a的第一个值')
- insert into tb values('a', 1, 'a1--a的第一个值')
- insert into tb values('a', 3, 'a3:a的第三个值')
- insert into tb values('a', 3, 'a3:a的第三个值')
- insert into tb values('b', 1, 'b1--b的第一个值')
- insert into tb values('b', 3, 'b3:b的第三个值')
- insert into tb values('b', 2, 'b2b2b2b2')
- insert into tb values('b', 4, 'b4b4')
- insert into tb values('b', 5, 'b5b5b5b5b5')
- go
- select * , px = identity(int,1,1) into tmp from tb
- select m.name,m.val,m.memo from
- (
- select t.* from tmp t where val = (select min(val) from tmp where name = t.name)
- ) m where px = (select min(px) from
- (
- select t.* from tmp t where val = (select min(val) from tmp where name = t.name)
- ) n where n.name = m.name)
- drop table tb,tmp
- --在sql server 2005中可以使用row_number函数,不需要使用临时表。
- --创建表并插入数据:
- create table tb(name varchar(10),val int,memo varchar(20))
- insert into tb values('a', 2, 'a2(a的第二个值)')
- insert into tb values('a', 1, 'a1--a的第一个值')
- insert into tb values('a', 1, 'a1--a的第一个值')
- insert into tb values('a', 3, 'a3:a的第三个值')
- insert into tb values('a', 3, 'a3:a的第三个值')
- insert into tb values('b', 1, 'b1--b的第一个值')
- insert into tb values('b', 3, 'b3:b的第三个值')
- insert into tb values('b', 2, 'b2b2b2b2')
- insert into tb values('b', 4, 'b4b4')
- insert into tb values('b', 5, 'b5b5b5b5b5')
- go
- select m.name,m.val,m.memo from
- (
- select * , px = row_number() over(order by name , val) from tb
- ) m where px = (select min(px) from
- (
- select * , px = row_number() over(order by name , val) from tb
- ) n where n.name = m.name)
- drop table tb
- select * from @T t where userid=(select min(userid) from @T where left(loginname,3)=left(t.loginname,3))
- ----------------------------------------------------
- --------------删除所有重复记录
- delete a where col1 in (select col1 from a group by col001 having count(*)>1)
- ------------------全部重复 保留一条数据,
- select * into #b from a ---备份
- truncate table #b
- insert into a
- select disitnct * from #b
- ---------------某个字段重复,只保留一条数据库(用游标)
- -------------------------用游标过滤重复记录
- declare @aa varchar(60)
- declare www cursor for
- select h_name from join_product_ty_bf
- open www
- fetch next from www into @aa
- while(@@fetch_status=0)
- begin
- fetch next from www into @aa
- if exists
- (select h_name from join_product_ty_bf where h_name like @aa group by h_name having count(*)>1)
- delete join_product_ty_bf where current of www
- end