导航
  • 主页
  • 基础类
  • 应用实例
  • 新技术前沿

求一SQL语句,同一字段重复的数据只取一条

bitm 2008-01-18 04:03:53
如表:A

id attachid name
1 23 sss
2 33 sdfs
3 33 4434
4 45 dsdsd



数据量挺大的。。上万条。

将重复的attachid只取一条记录。请教 sql
...全文
2112 点赞 收藏 7
写回复
7 条回复
切换为时间正序
当前发帖距今超过3年,不再开放新的回复
发表回复
dawugui 2008-01-18
--以下二选一.
select t.* from a t where id = (select min(id) from a where a.id = t.id)
select t.* from a t where id = (select max(id) from a where a.id = t.id)
回复
dawugui 2008-01-18
--按某一字段分组取最大(小)值所在行的数据
(爱新觉罗.毓华 2007-10-23于浙江杭州)
/*
数据如下:
name val memo
a 2 a2(a的第二个值)
a 1 a1--a的第一个值
a 3 a3:a的第三个值
b 1 b1--b的第一个值
b 3 b3:b的第三个值
b 2 b2b2b2b2
b 4 b4b4
b 5 b5b5b5b5b5
*/
--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
/*
name val memo
---------- ----------- --------------------
a 3 a3:a的第三个值
b 5 b5b5b5b5b5
*/

--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
/*
name val memo
---------- ----------- --------------------
a 1 a1--a的第一个值
b 1 b1--b的第一个值
*/

--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
/*
name val memo
---------- ----------- --------------------
a 2 a2(a的第二个值)
b 1 b1--b的第一个值
*/

--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
/*
name val memo
---------- ----------- --------------------
a 1 a1--a的第一个值
b 5 b5b5b5b5b5
*/

--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
/*
name val memo
---------- ----------- --------------------
a 1 a1--a的第一个值
a 2 a2(a的第二个值)
b 1 b1--b的第一个值
b 2 b2b2b2b2
*/

--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
/*
name val memo
---------- ----------- --------------------
a 2 a2(a的第二个值)
a 3 a3:a的第三个值
b 4 b4b4
b 5 b5b5b5b5b5
*/
--七,如果整行数据有重复,所有的列都相同。
/*
数据如下:
name val memo
a 2 a2(a的第二个值)
a 1 a1--a的第一个值
a 1 a1--a的第一个值
a 3 a3:a的第三个值
a 3 a3:a的第三个值
b 1 b1--b的第一个值
b 3 b3:b的第三个值
b 2 b2b2b2b2
b 4 b4b4
b 5 b5b5b5b5b5
*/
--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

/*
name val memo
---------- ----------- --------------------
a 1 a1--a的第一个值
b 1 b1--b的第一个值

(2 行受影响)
*/
--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

/*
name val memo
---------- ----------- --------------------
a 1 a1--a的第一个值
b 1 b1--b的第一个值

(2 行受影响)
*/
回复 1
青锋-SS 2008-01-18
上面错了:
select * from A where not exists(select 1 from A a1 where a.attachid=a1.attachid and a.ud<a1.id)
回复

select * from a a1
where not exists (
select 1 from a
where attachid=a1.attachid and id<a1.id
)

回复
青锋-SS 2008-01-18
select * from A where not exists(select 1 from A a1 where a.attachid>a.attachid)
回复
青锋-SS 2008-01-18
select max(id) as id,attachid,max(name) from A group by attachid
回复
kk19840210 2008-01-18


--如果相同取 NAME 最大的一条

create table #(id int identity(1,1),attachid int,name varchar(10))

insert into # values(23,'sss')
insert into # values(33,'sdfs')
insert into # values(33,'4434')
insert into # values(45,'dsdsd')

select * from # a where not exists (select 1 from # where attachid=a.attachid and name<a.name)



id attachid name
----------- ----------- ----------
1 23 sss
3 33 4434
4 45 dsdsd

(3 行受影响)
回复
发动态
发帖子
MS-SQL Server
创建于2007-09-28

3.2w+

社区成员

MS-SQL Server相关内容讨论专区
申请成为版主
社区公告
暂无公告