--先建立个存储过程:
CREATE PROCEDURE FindDistinct @tbl_name varchar(100), @col_name varchar(100),@i varchar(100) AS
EXECUTE ('SELECT * FROM '
+@tbl_name+
' a,(SELECT '
+@col_name+
' FROM '
+@tbl_name+
' GROUP BY '
+@col_name+
' HAVING (COUNT('
+@col_name+
') > '+@i+')) b where a.'
+@col_name+
'= b.'
+@col_name)
GO
---调用例子?
FindDistinct '表名','列名',写1的话查出的是该字段在该表出现次数大于1次
--结果为把该字段重复的都显示出来,检查完后随便你怎么删都行
CREATE PROCEDURE FindDistinct @tbl_name varchar(100), @col_name varchar(100),@i varchar(100) AS
EXECUTE ('SELECT * FROM '
+@tbl_name+
' a,(SELECT '
+@col_name+
' FROM '
+@tbl_name+
' GROUP BY '
+@col_name+
' HAVING (COUNT('
+@col_name+
') > '+@i+')) b where a.'
+@col_name+
'= b.'
+@col_name)
GO
---调用例子?
FindDistinct '表名','列名',写1的话查出的是该字段在该表出现次数大于1次
--结果为把该字段重复的都显示出来,检查完后随便你怎么删都行
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)
group by shuibiao_id
having count(*) >1先看一下是哪些重复了如果数据重复很多,那就
delete from table
where shuibiao_id in (select shuibiao_id from table
where shuibiao_dushu is null
and shuibiao_id in (select shuibiao_id from table group by shuibiao_id
having count(*)>1)删除有水表_id,水表_dushu为NULL的记录用了2个in,有点慢