工做中,咱们常常有须要删除一些重复数据的这种需求。重复数据多是程序bug形成的数据库
好,让咱们看看如何删除这些重复数据ide
删除重复数据的思路呢,是这样的,查看根据这个重复字段分组后的结果有没有大于1的状况
若是有大于的1的状况呢,那就说明是有重复数据的!3d
1) 建立数据库code
create database ceshi;
2) 建立表blog
CREATE TABLE t1 ( id int(10) unsigned NOT NULL AUTO_INCREMENT, name varchar(20) not null, createdAt timestamp NOT NULL DEFAULT current_timestamp(), updatedAt timestamp NOT NULL DEFAULT current_timestamp() ON UPDATE current_timestamp(), PRIMARY KEY (id) ) ENGINE=InnoDB AUTO_INCREMENT=1 DEFAULT CHARSET=utf8mb4;
3) 插入数据insert into t1 values(null,'haha',now(),now()),(null,'haha',now(),now()),(null,'xixi',now(),now()),(null,'heihei',now(),now()),(null,'hoho',now(),now()),(null,'hoho',now(),now()),(null,'sasa',now(),now()),(null,'haha',now(),now()),(null,'sasa',now(),now()),(null,'xixi',now(),now());
it
4) 查看数据select * from t1;
table
5) 根据最小id,重复字段name分组,假设咱们的需求就是最后要保留第最小id的这些数据,把其它重复的删除
select min(id),name from t1 group by name having count(name)>1 order by id;class
6) 使用别名关联一下,这些数据就是重复的,最后要删除的
select a.*
from t1 a,(select *,min(id) from t1 group by name having count(name)>1)as b where a.name=b.name and a.id>b.id;date
7) 记得先备份一下数据
create table bak_t1_20190621 like t1;select
insert into bak_t1_20190621 select * from t1;
8) 删除数据
delete a from t1 a,(select *
,min(id) from t1 group by name having count(name)>1)as b where a.name=b.name and a.id>b.id;
9) 最后检查一下,确实已经没有重复数据了