removing duplicates rows whilte runngin insert query in sql code example
Example 1: sql delete duplicate rows but keep one
# Step 1: Copy distinct values to temporary table
CREATE TEMPORARY TABLE tmp_user (
SELECT id, name
FROM user
GROUP BY name
);
# Step 2: Remove all rows from original table
DELETE FROM user;
# Step 3: Remove all rows from original table
INSERT INTO user (SELECT * FROM tmp_user);
# Step 4: Remove temporary table
DROP TABLE tmp_user;
Example 2: sql query to delete duplicate records
--ID should be primary key
--get duplicate records using RANK
SELECT E.ID,
E.firstname,
E.lastname,
E.country,
T.rank
FROM [SampleDB].[dbo].[Employee] E
INNER JOIN
(
SELECT *,
RANK() OVER(PARTITION BY firstname,
lastname,
country
ORDER BY id) rank
FROM [SampleDB].[dbo].[Employee]
) T ON E.ID = t.ID;
--delete duplications
DELETE E
FROM [SampleDB].[dbo].[Employee] E
INNER JOIN
(
SELECT *,
RANK() OVER(PARTITION BY firstname,
lastname,
country
ORDER BY id) rank
FROM [SampleDB].[dbo].[Employee]
) T ON E.ID = t.ID
WHERE rank > 1;