当前位置: 数据库>sqlserver
sql数据库删除重复记录方法示例
来源: 互联网 发布时间:2014-08-29
本文导语: 在sql数据库中,如果数据结构设计不够严谨,会产生越来越多的重复数据,就不得不寻找sql server 查询重复记录的多种方法,找到重复数据以后,接下来就是使用distinct筛选重复记录,继而完成重复数据的删除。 这里推荐一条...
在sql数据库中,如果数据结构设计不够严谨,会产生越来越多的重复数据,就不得不寻找sql server 查询重复记录的多种方法,找到重复数据以后,接下来就是使用distinct筛选重复记录,继而完成重复数据的删除。
这里推荐一条sql语句删除表中重复记录的方法,大多数时候可以解决我们遇到的问题。
如果遇到复杂些的重复记录处理方法,可以参考下面介绍的一些sql语句实例。
分享四种删除重复记录的方式,用于不同的情况。
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
代码示例:
select * from people where peopleId in (select peopleId from people group by peopleId having count(peopleId) > 1)
2、sql删除重复记录,重复记录是根据单个字段(peopleid)来判断,只留有rowid最小的记录
代码示例:
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)
代码示例:
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
代码示例:
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)
附,去除重复记录sql语句。
对重复记录的处理,对搜索结果影响最大。
如何去除数据库中的重复记录呢?(sql语句大全)
--按某一字段分组取最大(小)值所在行的数据
/*
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,a.val
/*
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 , a.val
/*
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)
*/
/*
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,a.val
/*
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 , a.val
/*
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)
*/