在SQL Server中查找重复的行

我有一个组织的SQL Server数据库，有许多重复的行。我想运行一个选择语句来获取所有这些和被欺骗的数量，同时还返回与每个组织相关的id。

这样的陈述:

SELECT     orgName, COUNT(*) AS dupes  
FROM         organizations  
GROUP BY orgName  
HAVING      (COUNT(*) > 1)

将返回如下内容

orgName        | dupes  
ABC Corp       | 7  
Foo Federation | 5  
Widget Company | 2

但我也想要他们的id。有什么办法可以做到吗?也许就像

orgName        | dupeCount | id  
ABC Corp       | 1         | 34  
ABC Corp       | 2         | 5  
...  
Widget Company | 1         | 10  
Widget Company | 2         | 2

原因是还有一个单独的用户表链接到这些组织，我想把它们统一起来(因此删除dupes，用户链接到同一个组织，而不是dupe组织)。但我想手动部分，所以我不会搞砸任何事情，但我仍然需要一个语句返回所有的dupe组织的id，这样我就可以通过用户列表。

当前回答

Select * from (Select orgName,id,
ROW_NUMBER() OVER(Partition By OrgName ORDER by id DESC) Rownum
From organizations )tbl Where Rownum>1

所以rowum> 1的记录将是表中的重复记录。'分区由'第一组记录，然后通过给他们序列号序列化他们。所以rownum> 1将是重复的记录，可以这样删除。

2015-03-10 05:58:02

其他回答

select o.orgName, oc.dupeCount, o.id
from organizations o
inner join (
    SELECT orgName, COUNT(*) AS dupeCount
    FROM organizations
    GROUP BY orgName
    HAVING COUNT(*) > 1
) oc on o.orgName = oc.orgName

2010-01-21 20:32:02

select * from [Employees]

查找重复记录 1)使用CTE

with mycte
as
(
select Name,EmailId,ROW_NUMBER() over(partition by Name,EmailId order by id) as Duplicate from [Employees]
)
select * from mycte

2)使用GroupBy

select Name,EmailId,COUNT(name) as Duplicate from  [Employees] group by Name,EmailId

2016-11-18 12:44:38

你可以试试这个，这对你是最好的

 WITH CTE AS
    (
    SELECT *,RN=ROW_NUMBER() OVER (PARTITION BY orgName ORDER BY orgName DESC) FROM organizations 
    )
    select * from CTE where RN>1
    go

2013-11-07 08:01:59

有几种方法可以选择重复的行。

对于我的解决方案，首先考虑以下表格为例

CREATE TABLE #Employee
(
ID          INT,
FIRST_NAME  NVARCHAR(100),
LAST_NAME   NVARCHAR(300)
)

INSERT INTO #Employee VALUES ( 1, 'Ardalan', 'Shahgholi' );
INSERT INTO #Employee VALUES ( 2, 'name1', 'lname1' );
INSERT INTO #Employee VALUES ( 3, 'name2', 'lname2' );
INSERT INTO #Employee VALUES ( 2, 'name1', 'lname1' );
INSERT INTO #Employee VALUES ( 3, 'name2', 'lname2' );
INSERT INTO #Employee VALUES ( 4, 'name3', 'lname3' );

第一个解决方案:

SELECT DISTINCT *
FROM   #Employee;

WITH #DeleteEmployee AS (
                     SELECT ROW_NUMBER()
                            OVER(PARTITION BY ID, First_Name, Last_Name ORDER BY ID) AS
                            RNUM
                     FROM   #Employee
                 )

SELECT *
FROM   #DeleteEmployee
WHERE  RNUM > 1

SELECT DISTINCT *
FROM   #Employee

第二个解决方案:使用标识字段

SELECT DISTINCT *
FROM   #Employee;

ALTER TABLE #Employee ADD UNIQ_ID INT IDENTITY(1, 1)

SELECT *
FROM   #Employee
WHERE  UNIQ_ID < (
    SELECT MAX(UNIQ_ID)
    FROM   #Employee a2
    WHERE  #Employee.ID = a2.ID
           AND #Employee.FIRST_NAME = a2.FIRST_NAME
           AND #Employee.LAST_NAME = a2.LAST_NAME
)

ALTER TABLE #Employee DROP COLUMN UNIQ_ID

SELECT DISTINCT *
FROM   #Employee

所有解决方案的最后使用这个命令

DROP TABLE #Employee

2013-11-07 07:06:30

Try

SELECT orgName, id, count(*) as dupes
FROM organizations
GROUP BY orgName, id
HAVING count(*) > 1;

2014-01-22 06:29:47

在SQL Server中查找重复的行

推荐文章

最新文章

标签