使用一个字段很容易找到重复项：
SELECT email, COUNT(email)
FROM users
GROUP BY email
HAVING COUNT(email) > 1
所以如果我们有一张桌子
ID NAME EMAIL
1 John asd@asd.com
2 Sam asd@asd.com
3 Tom asd@asd.com
4 Bob bob@asd.com
5 Tom asd@asd.com
这个查询将告诉我们John、Sam、Tom和Tom，因为他们都有相同的电子邮件。
然而，我想要的是获得相同电子邮件和名称的副本。
也就是说，我想得到“汤姆”，“汤姆”。
我需要这个的原因是：我犯了一个错误，允许插入重复的名称和电子邮件值。现在我需要删除/更改重复项，所以我需要先找到它们。
当前回答
select name, email
, case
when ROW_NUMBER () over (partition by name, email order by name) > 1 then 'Yes'
else 'No'
end "duplicated ?"
from users
其他回答
如果您希望查看表中是否有重复的行，我使用以下查询：
create table my_table(id int, name varchar(100), email varchar(100));
insert into my_table values (1, 'shekh', 'shekh@rms.com');
insert into my_table values (1, 'shekh', 'shekh@rms.com');
insert into my_table values (2, 'Aman', 'aman@rms.com');
insert into my_table values (3, 'Tom', 'tom@rms.com');
insert into my_table values (4, 'Raj', 'raj@rms.com');
Select COUNT(1) As Total_Rows from my_table
Select Count(1) As Distinct_Rows from ( Select Distinct * from my_table) abc
试试看：
declare @YourTable table (id int, name varchar(10), email varchar(50))
INSERT @YourTable VALUES (1,'John','John-email')
INSERT @YourTable VALUES (2,'John','John-email')
INSERT @YourTable VALUES (3,'fred','John-email')
INSERT @YourTable VALUES (4,'fred','fred-email')
INSERT @YourTable VALUES (5,'sam','sam-email')
INSERT @YourTable VALUES (6,'sam','sam-email')
SELECT
name,email, COUNT(*) AS CountOf
FROM @YourTable
GROUP BY name,email
HAVING COUNT(*)>1
输出：
name email CountOf
---------- ----------- -----------
John John-email 2
sam sam-email 2
(2 row(s) affected)
如果您想要重复数据集的ID，请使用以下命令：
SELECT
y.id,y.name,y.email
FROM @YourTable y
INNER JOIN (SELECT
name,email, COUNT(*) AS CountOf
FROM @YourTable
GROUP BY name,email
HAVING COUNT(*)>1
) dt ON y.name=dt.name AND y.email=dt.email
输出：
id name email
----------- ---------- ------------
1 John John-email
2 John John-email
5 sam sam-email
6 sam sam-email
(4 row(s) affected)
要删除重复项，请尝试：
DELETE d
FROM @YourTable d
INNER JOIN (SELECT
y.id,y.name,y.email,ROW_NUMBER() OVER(PARTITION BY y.name,y.email ORDER BY y.name,y.email,y.id) AS RowRank
FROM @YourTable y
INNER JOIN (SELECT
name,email, COUNT(*) AS CountOf
FROM @YourTable
GROUP BY name,email
HAVING COUNT(*)>1
) dt ON y.name=dt.name AND y.email=dt.email
) dt2 ON d.id=dt2.id
WHERE dt2.RowRank!=1
SELECT * FROM @YourTable
输出：
id name email
----------- ---------- --------------
1 John John-email
3 fred John-email
4 fred fred-email
5 sam sam-email
(4 row(s) affected)
试试看：
DECLARE @myTable TABLE
(
id INT,
name VARCHAR(10),
email VARCHAR(50)
);
INSERT @myTable
VALUES
(1, 'John', 'John-email');
INSERT @myTable
VALUES
(2, 'John', 'John-email');
INSERT @myTable
VALUES
(3, 'fred', 'John-email');
INSERT @myTable
VALUES
(4, 'fred', 'fred-email');
INSERT @myTable
VALUES
(5, 'sam', 'sam-email');
INSERT @myTable
VALUES
(6, 'sam', 'sam-email');
WITH cte
AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 1)) AS rowNum,
*
FROM @myTable)
SELECT c1.id,
c1.name,
c1.email
FROM cte AS c1
WHERE 1 <
(
SELECT COUNT(c2.rowNum)
FROM cte AS c2
WHERE c1.name = c2.name
AND c1.email = c2.email
);
这是我想出的最简单的办法。它使用一个公共表表达式（CTE）和一个分区窗口（我认为这些特性在SQL 2008和更高版本中）。
此示例查找所有具有重复名称和dob的学生。要检查重复的字段位于OVER子句中。可以在投影中包含任何其他字段。
with cte (StudentId, Fname, LName, DOB, RowCnt)
as (
SELECT StudentId, FirstName, LastName, DateOfBirth as DOB, SUM(1) OVER (Partition By FirstName, LastName, DateOfBirth) as RowCnt
FROM tblStudent
)
SELECT * from CTE where RowCnt > 1
ORDER BY DOB, LName
SELECT column_name，COUNT（*）FROM TABLE_name GROUP BY column1，HAVING COUNT；
