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
这个解决方案将把重复的数据移到一个表中，唯一的数据移到另一个表中。
-- speed up creating uniques table if dealing with many rows
CREATE INDEX temp_idx ON jobs(site_id, company, title, location);
-- create the table with unique rows
INSERT jobs_uniques SELECT * FROM
(
SELECT *
FROM jobs
GROUP BY site_id, company, title, location
HAVING count(1) > 1
UNION
SELECT *
FROM jobs
GROUP BY site_id, company, title, location
HAVING count(1) = 1
) x
-- create the table with duplicate rows
INSERT jobs_dupes
SELECT *
FROM jobs
WHERE id NOT IN
(SELECT id FROM jobs_uniques)
-- confirm the difference between uniques and dupes tables
SELECT COUNT(1)
AS jobs,
(SELECT COUNT(1) FROM jobs_dupes) + (SELECT COUNT(1) FROM jobs_uniques)
AS sum
FROM jobs
其他回答
删除表中重复的记录。
delete from job s
where rowid < any
(select rowid from job k
where s.site_id = k.site_id and
s.title = k.title and
s.company = k.company);
or
delete from job s
where rowid not in
(select max(rowid) from job k
where s.site_id = k.site_id and
s.title = k.title and
s.company = k.company);
你可以很容易地从这个代码中删除重复的记录。
$qry = mysql_query("SELECT * from cities");
while($qry_row = mysql_fetch_array($qry))
{
$qry2 = mysql_query("SELECT * from cities2 where city = '".$qry_row['city']."'");
if(mysql_num_rows($qry2) > 1){
while($row = mysql_fetch_array($qry2)){
$city_arry[] = $row;
}
$total = sizeof($city_arry) - 1;
for($i=1; $i<=$total; $i++){
mysql_query( "delete from cities2 where town_id = '".$city_arry[$i][0]."'");
}
}
//exit;
}
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
)
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;
我找到了一个简单的方法。(保持最新的)
DELETE t1 FROM table_name t1 INNER JOIN table_name t2
WHERE t1.primary_id < t2.primary_id
AND t1.check_duplicate_col_1 = t2.check_duplicate_col_1
AND t1.check_duplicate_col_2 = t2.check_duplicate_col_2
...
