目录
概述
一、Oracle数据库去重(推荐放在在第6点)
二、MySQL数据库去重
三、sqlserver数据库去重
四、pg数据库删除重复数据
转发这个主要是有时会有重复数据的需求,留一个查询方法,大家有空也可以测试一下..
1、环境准备
可以看到“ALLEN”和“SMITH”这两个人的数据重复了,现在要求表中name重复的数据只保留一行,其他的删除。
CREATE TABLE hwb(
id int,
name varchar(10)
);
INSERT INTO hwb VALUES(1, 'TOM');
INSERT INTO hwb VALUES(2, 'ALLEN');
INSERT INTO hwb VALUES(3, 'ALLEN');
INSERT INTO hwb VALUES(4, 'SMITH');
INSERT INTO hwb VALUES(5, 'SMITH');
INSERT INTO hwb VALUES(6, 'SMITH');
commit;
SELECT * FROM hwb;
2、实现方法一:通过分组后,拿最小的id重复删除
delete from hwb a where a.id in
(select min(id) FROM hwb a group by name having count(name) > 1)
3、实现方法二:通过name相同,id不同的方式来判断
DELETE FROM hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.id > b.id);
4、实现方法三:用rowid代替id,替换删除
DELETE FROM hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.rowid > b.rowid);
5、实现方法四:通过分析函数根据name分组生成序号,然后删除序号大于1的数据。
语法格式:row_number() over(partition by 分组列 order by 排序列 desc)
在使用 row_number() over()函数时候,over()里头的分组以及排序的执行晚于 where 、group by、 order by 的执行。
DELETE FROM hwb a
WHERE ROWID IN (SELECT rid
FROM (SELECT ROWID as rid,
ROW_NUMBER() OVER(PARTITION BY name ORDER BY id) AS seq
FROM hwb)
WHERE seq > 1);
6、【推荐】实现方法五:根据rowid删除
DELETE FROM hwb a
WHERE a.ROWID > (SELECT MIN(b.ROWID) FROM hwb b WHERE a.name = b.name);
1、环境准备
CREATE TABLE hwb(
id BIGINT (4) not null,
name varchar(10),
PRIMARY KEY (id)
) ENGINE = INNODB;
INSERT INTO hwb VALUES(1, 'TOM');
INSERT INTO hwb VALUES(2, 'ALLEN');
INSERT INTO hwb VALUES(3, 'ALLEN');
INSERT INTO hwb VALUES(4, 'SMITH');
INSERT INTO hwb VALUES(5, 'SMITH');
INSERT INTO hwb VALUES(6, 'SMITH');
commit;
SELECT * FROM hwb;
2、实现方法一:通过分组后,拿最大/最小的id重复删除
--重复删除多次
delete from hwb
where id in (select id from
(select max(b.id) as id FROM hwb b group by name having count(name) > 1)c )
--或者修改为以下,只需删除一次
delete from hwb
WHERE
NAME IN (select name from ( SELECT NAME FROM hwb b GROUP BY NAME HAVING count( NAME ) > 1 ) t)
AND id NOT IN (select tt.id from (SELECT max(c.id ) as id FROM hwb c GROUP BY NAME HAVING count( NAME ) > 1 ) tt)
3、实现方法二:
根据name分组,查找出id最小的,然后再查找id不包含刚才查出来的。这样就查询出了所有的重复数据(除了id最小的那行)
delete from hwb
WHERE
id NOT IN (select tt.id from (SELECT min(c.id ) as id FROM hwb c GROUP BY NAME ) tt)
4、实现方法三:通过name相同,id不同的方式来判断
delete from hwb where id in (
select id from (
select * from hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.id > b.id))c );
5、实现方法四:用rowid代替id,替换删除
在 Oracle 数据库的表中的每一行数据都有一个唯一的标识符,称为 rowid ,在 Oracle 内部通常就是使用它来访问数据的。
而在 MySQL 中也有一个类似的隐藏列 _rowid 来标记唯一的标识。但是需要注意 _rowid 并不是一个真实存在的列,其本质是一个 非空唯一列 的别名。
在某些情况下 _rowid 是不存在的,其只存在于以下情况:
1)当表中存在一个 数字类型 的单列主键时, _rowid 其实就是指的是这个主键列
2)当表中 不存在主键 但存在一个 数字类型 的 非空唯一列 时, _rowid 其实就是指的是对应 非空唯一列 。
需要注意以下情况是不存在 _rowid 的
1)主键列 或者 非空唯一列 的类型不是 数字类型
2)主键 是联合主键
3)唯一 列不是非空的。
delete from hwb where id in (
select id from (
select * from hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a._rowid > b._rowid))c );
ps:还可考虑表切换完成去重步骤。
1、环境准备
CREATE TABLE [dbo].[hwb] (
[id] decimal(12) NULL,
[name] nvarchar(10) COLLATE Chinese_PRC_CI_AS NOT NULL
)
GO
ALTER TABLE [dbo].[hwb] SET (LOCK_ESCALATION = TABLE)
GO
INSERT INTO hwb VALUES(1, 'TOM');
INSERT INTO hwb VALUES(2, 'ALLEN');
INSERT INTO hwb VALUES(3, 'ALLEN');
INSERT INTO hwb VALUES(4, 'SMITH');
INSERT INTO hwb VALUES(5, 'SMITH');
INSERT INTO hwb VALUES(6, 'SMITH');
GO
2、实现方法一:通过分组后,拿最大/最小的id重复删除
--重复删除多次
delete from hwb
where id in
(select min(id) FROM hwb a group by name having count(name) > 1)
--或者修改为以下,只需删除一次
select * from hwb
-- delete from hwb
WHERE
NAME IN (SELECT NAME FROM hwb b GROUP BY NAME HAVING count( NAME ) > 1 )
AND id NOT IN (SELECT max(c.id ) as id FROM hwb c GROUP BY NAME HAVING count( NAME ) > 1 )
3、实现方法二:根据name分组,查找出id最小的,然后再查找id不包含刚才查出来的
这样就查询出了所有的重复数据(除了id最小的那行)
delete from hwb
WHERE
id NOT IN (select tt.id from (SELECT min(c.id ) as id FROM hwb c GROUP BY NAME ) tt)
4、实现方法三:通过name相同,id不同的方式来判断
DELETE FROM hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.id > b.id);
5、实现方法四:用hash值代替id,替换删除
%%lockres%%会返回聚集索引键的hash值,
非聚集索引,%%lockres%%会返回非聚集索引键的hash值
delete from hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.%%lockres%% > b.%%lockres%%);
6、实现方法五:通过分析函数根据name分组生成序号,然后删除序号大于1的数据。
语法格式:row_number() over(partition by 分组列 order by 排序列 desc)
在使用 row_number() over()函数时候,over()里头的分组以及排序的执行晚于 where 、group by、 order by 的执行。
DELETE FROM hwb a
WHERE
id IN (
SELECT b.id
FROM (SELECT id, ROW_NUMBER () OVER ( PARTITION BY name ORDER BY id ) AS seq FROM hwb) b
WHERE b.seq > 1 );
7、【推荐】实现方法六:根据hash值删除
DELETE FROM hwb a
WHERE a.%%lockres%% > (SELECT MIN(b.%%lockres%%) FROM hwb b WHERE a.name = b.name);
1、环境准备
set search_path to 'public';
\dt --list tables
CREATE TABLE hwb(
id INT PRIMARY KEY NOT NULL,
name CHAR(10));
INSERT INTO hwb VALUES(1, 'TOM');
INSERT INTO hwb VALUES(2, 'ALLEN');
INSERT INTO hwb VALUES(3, 'ALLEN');
INSERT INTO hwb VALUES(4, 'SMITH');
INSERT INTO hwb VALUES(5, 'SMITH');
INSERT INTO hwb VALUES(6, 'SMITH');
SELECT * FROM hwb;
2、实现方法一:通过分组后,拿最大/最小的id重复删除
--重复删除多次
delete from hwb
where id in (select max(b.id) as id FROM hwb b group by name having count(name) > 1)
--或者修改为以下,只需删除一次
delete from hwb
WHERE
NAME IN (SELECT NAME FROM hwb b GROUP BY NAME HAVING count(NAME) > 1)
AND id NOT IN (SELECT max(c.id ) as id FROM hwb c GROUP BY NAME HAVING count( NAME ) > 1);
3、实现方法二:
根据name分组,查找出id最小的,然后再查找id不包含刚才查出来的。这样就查询出了所有的重复数据(除了id最小的那行)
delete from hwb
WHERE id NOT IN (SELECT min(c.id ) as id FROM hwb c GROUP BY NAME );
4、实现方法三:通过name相同,id不同的方式来判断
delete from hwb a
WHERE EXISTS (SELECT 1
FROM hwb b
WHERE a.name = b.name
AND a.id > b.id);
5、[推荐]实现方法四:用ctid代替id,替换删除
delete from hwb a
WHERE EXISTS (SELECT 1 FROM hwb b
WHERE a.name = b.name AND a.ctid > b.ctid);
--或者如下:
select * from hwb WHERE ctid NOT IN (SELECT min(ctid) as id FROM hwb GROUP BY NAME );
6、[最高效推荐]实现方法五:用ctid代替id,结合row_number替换删除
delete FROM hwb a WHERE a.ctid =
ANY (array (SELECT ctid FROM (SELECT row_number() over(PARTITION BY NAME) as seq, ctid FROM hwb ) t
WHERE t.seq > 1));
本文转载至头条用户“波波说运维”