求个删除重复记录的查询

[JJkukow]

use tempdb
go

if object_id('tempdb.dbo.t1') is not null drop table t1
create table t1 (id int identity(1,1),staff_id varchar(10),sign_time datetime)
insert into t1 select '2004033','2005-01-01 10:22:21'
union all select '2004033','2008-03-20 08:25:00'
union all select '2004033','2008-03-20 08:26:00'
union all select '2004033','2008-03-20 08:27:00'
union all select '2004033','2008-03-20 08:35:00'
union all select '2004033','2008-03-20 08:24:00'
union all select '2004033','2008-03-20 08:25:01'
union all select '2004033','2008-03-20 08:30:00'
union all select '2004033','2008-03-20 08:30:01'
union all select '2004033','2008-03-20 17:30:00'

select * from t1 order by 2,3

declare @dt1 datetime,@dt2 datetime
declare @se int
set @dt1='2005-01-01'
set @dt2='2008-08-01'
set @se=4



--删除在日期@dt1，@dt2范围内,时间相差@se内相同的数据,并保留第一条数据.
--执行结果


/*

1 2004033 2005-01-01 10:22:21
6 2004033 2008-03-20 08:24:00
8 2004033 2008-03-20 08:30:00
5 2004033 2008-03-20 08:35:00
10 2004033 2008-03-20 17:30:00
*/


--如何写这个删除语句,请教

[liangCK]

--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)
*/

[-狙击手-]

create table t1 (id int identity(1,1),staff_id varchar(10),sign_time datetime) 
insert into t1 select '2004033','2005-01-01 10:22:21' 
union all  select '2004033','2008-03-20 08:25:00' 
union all  select '2004033','2008-03-20 08:26:00' 
union all  select '2004033','2008-03-20 08:27:00' 
union all  select '2004033','2008-03-20 08:35:00' 
union all  select '2004033','2008-03-20 08:24:00' 
union all  select '2004033','2008-03-20 08:25:01' 
union all  select '2004033','2008-03-20 08:30:00' 
union all  select '2004033','2008-03-20 08:30:01' 
union all  select '2004033','2008-03-20 17:30:00' 



declare @dt1 datetime,@dt2 datetime
declare @se int 
set @dt1='2005-01-01' 
set @dt2='2008-08-01' 
set @se=4 



select *,datediff(mi,@dt1,sign_time)/@se as px
into #
from t1
order by datediff(mi,@dt1,sign_time)/@se,sign_time


select id,staff_id,sign_time
from # a
where not exists(select 1 from # where staff_id = a.staff_id and px = a.px and sign_time < a.sign_time)
if object_id('t1') is not null drop table t1 
drop table #

/*
id          staff_id   sign_time                                              
----------- ---------- ------------------------------------------------------ 
1           2004033    2005-01-01 10:22:21.000
6           2004033    2008-03-20 08:24:00.000
8           2004033    2008-03-20 08:30:00.000
5           2004033    2008-03-20 08:35:00.000
10          2004033    2008-03-20 17:30:00.000

（所影响的行数为 5 行）
*/

[viva369]

up楼上的~

[JJkukow]

高手啊,我研究了那么久,你两分钟都搞定了,郁闷....

[sasalar]

只学过用select distinct ? from ??

[JJkukow]

我写了个
delete a from t1 a where exists (select 1 from t1 where staff_id=a.staff_id and sign_time<a.sign_time and datediff(minute,sign_time,a.sign_time)<=@se and convert(varchar(10),sign_time,120) between @dt1 and @dt2)

结果就是不对.
你们SQL怎么那么厉害.咋学的啊?