我有一个表与以下字段:
id (Unique)
url (Unique)
title
company
site_id
现在，我需要删除具有相同标题、company和site_id的行。一种方法是使用下面的SQL和脚本(PHP):
SELECT title, site_id, location, id, count( * )
FROM jobs
GROUP BY site_id, company, title, location
HAVING count( * ) >1
运行此查询后，可以使用服务器端脚本删除重复项。
但是，我想知道这是否只能使用SQL查询。
当前回答
更快的方法是在临时表中插入不同的行。使用delete，我花了几个小时从一个800万行的表中删除重复项。使用insert和distinct，只花了13分钟。
CREATE TABLE tempTableName LIKE tableName;
CREATE INDEX ix_all_id ON tableName(cellId,attributeId,entityRowId,value);
INSERT INTO tempTableName(cellId,attributeId,entityRowId,value) SELECT DISTINCT cellId,attributeId,entityRowId,value FROM tableName;
TRUNCATE TABLE tableName;
INSERT INTO tableName SELECT * FROM tempTableName;
DROP TABLE tempTableName;
其他回答
我想更具体地说明我删除了哪些记录，下面是我的解决方案:
delete
from jobs c1
where not c1.location = 'Paris'
and c1.site_id > 64218
and exists
(
select * from jobs c2
where c2.site_id = c1.site_id
and c2.company = c1.company
and c2.location = c1.location
and c2.title = c1.title
and c2.site_id > 63412
and c2.site_id < 64219
)
MySQL对引用要删除的表有限制。你可以用一个临时表来解决这个问题，比如:
create temporary table tmpTable (id int);
insert into tmpTable
(id)
select id
from YourTable yt
where exists
(
select *
from YourTabe yt2
where yt2.title = yt.title
and yt2.company = yt.company
and yt2.site_id = yt.site_id
and yt2.id > yt.id
);
delete
from YourTable
where ID in (select id from tmpTable);
以下是Kostanos在评论中的建议: 上面唯一缓慢的查询是DELETE，适用于数据库非常大的情况。这个查询可以更快:
DELETE FROM YourTable USING YourTable, tmpTable WHERE YourTable.id=tmpTable.id
简单和快速的所有情况:
CREATE TEMPORARY TABLE IF NOT EXISTS _temp_duplicates AS (SELECT dub.id FROM table_with_duplications dub GROUP BY dub.field_must_be_uniq_1, dub.field_must_be_uniq_2 HAVING COUNT(*) > 1);
DELETE FROM table_with_duplications WHERE id IN (SELECT id FROM _temp_duplicates);
更快的方法是在临时表中插入不同的行。使用delete，我花了几个小时从一个800万行的表中删除重复项。使用insert和distinct，只花了13分钟。
CREATE TABLE tempTableName LIKE tableName;
CREATE INDEX ix_all_id ON tableName(cellId,attributeId,entityRowId,value);
INSERT INTO tempTableName(cellId,attributeId,entityRowId,value) SELECT DISTINCT cellId,attributeId,entityRowId,value FROM tableName;
TRUNCATE TABLE tableName;
INSERT INTO tableName SELECT * FROM tempTableName;
DROP TABLE tempTableName;
如果IGNORE语句在我的例子中不起作用，你可以使用下面的语句:
CREATE TABLE your_table_deduped LIKE your_table;
INSERT your_table_deduped
SELECT *
FROM your_table
GROUP BY index1_id,
index2_id;
RENAME TABLE your_table TO your_table_with_dupes;
RENAME TABLE your_table_deduped TO your_table;
#OPTIONAL
ALTER TABLE `your_table` ADD UNIQUE `unique_index` (`index1_id`, `index2_id`);
#OPTIONAL
DROP TABLE your_table_with_dupes;
