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
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
其他回答
与其他答案不同，您可以查看包含所有列（如果有的话）的整个记录。在row_number函数的PARTITION BY部分中，选择所需的唯一/双工列。
SELECT *
FROM (
SELECT a.*
, Row_Number() OVER (PARTITION BY Name, Age ORDER BY Name) AS r
FROM Customers AS a
) AS b
WHERE r > 1;
当您想选择所有字段中的所有重复记录时，可以这样写
CREATE TABLE test (
id bigint GENERATED ALWAYS AS IDENTITY PRIMARY KEY
, c1 integer
, c2 text
, d date DEFAULT now()
, v text
);
INSERT INTO test (c1, c2, v) VALUES
(1, 'a', 'Select'),
(1, 'a', 'ALL'),
(1, 'a', 'multiple'),
(1, 'a', 'records'),
(2, 'b', 'in columns'),
(2, 'b', 'c1 and c2'),
(3, 'c', '.');
SELECT * FROM test ORDER BY 1;
SELECT *
FROM test
WHERE (c1, c2) IN (
SELECT c1, c2
FROM test
GROUP BY 1,2
HAVING count(*) > 1
)
ORDER BY 1;
在PostgreSQL中测试。
select name, email
, case
when ROW_NUMBER () over (partition by name, email order by name) > 1 then 'Yes'
else 'No'
end "duplicated ?"
from users
派对晚了一点，但我找到了一个非常酷的解决方法来查找所有重复的ID：
SELECT email, GROUP_CONCAT(id)
FROM users
GROUP BY email
HAVING COUNT(email) > 1;
如果要删除重复项，这里有一种比在三个子选择中查找偶数/奇数行更简单的方法：
SELECT id, name, email
FROM users u, users u2
WHERE u.name = u2.name AND u.email = u2.email AND u.id > u2.id
因此，删除：
DELETE FROM users
WHERE id IN (
SELECT id/*, name, email*/
FROM users u, users u2
WHERE u.name = u2.name AND u.email = u2.email AND u.id > u2.id
)
更容易阅读和理解IMHO
注意：唯一的问题是您必须执行请求，直到没有删除行，因为每次只删除每个重复项中的一行
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)
