lyfz_repos/经典版源码/document/数据库维护脚本/跨年转数据/删除重复记录.sql

select sy1.* from dindanjd Sy, dindanjd sy2 
--where sy1.id<>sy2.id 
--and sy1.id = sy2.id
where sy1.id = sy2.id
and sy1.name = sy2.name
and sy1.date = sy2.date
and sy1.time = sy2.time
and sy1.waiter1 = sy2.waiter1
and sy1.waiter2 = sy2.waiter2
and sy1.status = sy2.status
and sy1.waiter12 = sy2.waiter12
and sy1.waiter22 = sy2.waiter22
and sy1.bookingdate = sy2.bookingdate
and sy1.dress = sy2.dress
and sy1.bz = sy2.bz
and sy1.clerk = sy2.clerk
and sy1.inputtime = sy2.inputtime
and sy1.branch = sy2.branch

/*
删除重复记录的SQL语句
1.用rowid方法
2.用group by方法
3.用distinct方法

1。用rowid方法

据据oracle带的rowid属性，进行判断，是否存在重复,语句如下： 
查数据: 
     select * from table1 a where rowid !=(select   max(rowid)   
     from table1 b where a.name1=b.name1 and a.name2=b.name2......) 
删数据： 
    delete   from table1 a where rowid !=(select   max(rowid)   
     from table1 b where a.name1=b.name1 and a.name2=b.name2......)

2.group by方法

查数据: 
select count(num), max(name) from student --列出重复的记录数，并列出他的name属性 
group by num 
having count(num) >1 --按num分组后找出表中num列重复，即出现次数大于一次 
删数据： 
delete from student 
group by num 
having count(num) >1 
这样的话就把所有重复的都删除了。

3.用distinct方法 -对于小的表比较有用

create table table_new as   select distinct *   from table1 minux 
truncate table table1; 
insert into table1 select * from table_new;

 

查询及删除重复记录的方法大全 
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)

(二) 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

(三) 方法一

declare @max integer,@id integer

declare cur_rows cursor local for select 主字段,count(*) from 表名 group by 主字段 having count(*) >； 1

open cur_rows

fetch cur_rows into @id,@max

while @@fetch_status=0

begin

select @max = @max -1

set rowcount @max

delete from 表名 where 主字段 = @id

fetch cur_rows into @id,@max

end

close cur_rows

set rowcount 0

方法二

＂重复记录＂有两个意义上的重复记录，一是完全重复的记录，也即所有字段均重复的记录，二是部分关键字段重复的记录，比如Name字段重复，而其他字段不一定重复或都重复可以忽略。

1、对于第一种重复，比较容易解决，使用

select distinct * from tableName

就可以得到无重复记录的结果集。

如果该表需要删除重复的记录（重复记录保留1条），可以按以下方法删除

select distinct * into #Tmp from tableName

drop table tableName

select * into tableName from #Tmp

drop table #Tmp

发生这种重复的原因是表设计不周产生的，增加唯一索引列即可解决。

2、这类重复问题通常要求保留重复记录中的第一条记录，操作方法如下

假设有重复的字段为Name,Address，要求得到这两个字段唯一的结果集

select identity(int,1,1) as autoID, * into #Tmp from tableName

select min(autoID) as autoID into #Tmp2 from #Tmp group by Name,autoID

select * from #Tmp where autoID in(select autoID from #tmp2)

最后一个select即得到了Name，Address不重复的结果集（但多了一个autoID字段，实际写时可以写在select子句中省去此列）

(四) 查询重复

select * from tablename where id in (

select id from tablename

group by id

having count(id) > 1)
*/