需求描述

doc表有很多重复的title,想去除掉重复的记录

表结构

CREATE TABLE doc (
    id INT PRIMARY KEY,
    title VARCHAR(255),
    content TEXT
);

去重SQL

-- 创建临时表
CREATE TEMPORARY TABLE temp_doc AS
SELECT * FROM doc
WHERE 1=0;

-- 插入唯一的记录（每个title最小的id）
INSERT INTO temp_doc
SELECT *
FROM doc d
WHERE id IN (
    SELECT MIN(id)
    FROM doc
    GROUP BY title
);

-- 删除原始表中的所有记录
DELETE FROM doc;

-- 将临时表中的记录插入回原始表中
INSERT INTO doc
SELECT * FROM temp_doc;

-- 删除临时表
DROP TEMPORARY TABLE temp_doc;

 查看是否有重复的记录

SELECT id, title, COUNT(*) 
FROM doc
GROUP BY title 
ORDER BY COUNT(*) DESC;