MySQL从重复条目中清除表，并在依赖表中重新链接FK
这是我的情况：我有两张表，MySQL从重复条目中清除表，并在依赖表中重新链接FK,mysql,foreign-keys,duplicates,duplicate-removal,Mysql,Foreign Keys,Duplicates,Duplicate Removal,这是我的情况：我有两张表，患者和研究 每个表都有自己的PK，使用autoincrement 在我的例子中，pat_id应该是唯一的。它在数据库级别并没有声明为唯一的，因为在某些用途中它可能是非唯一的（它不是自制的系统）。我发现如何配置系统来考虑PATSID是唯一的，但是我现在需要清理重复患者的数据库，并将重复的患者在学习表中遗留给唯一的患者，然后删除重复的患者。 患者表格： CREATE TABLE `patient` ( `pk` BIGINT(20) NOT NULL AUTO_INCR
患者研究患者CREATE TABLE `patient` (
`pk` BIGINT(20) NOT NULL AUTO_INCREMENT,
`pat_id` VARCHAR(250) COLLATE latin1_bin DEFAULT NULL,
...
`pat_name` VARCHAR(250) COLLATE latin1_bin DEFAULT NULL,
...
`pat_custom1` VARCHAR(250) COLLATE latin1_bin DEFAULT NULL
....
PRIMARY KEY (`pk`)
)ENGINE=InnoDB;
CREATE TABLE `study` (
`pk` BIGINT(20) NOT NULL AUTO_INCREMENT,
`patient_fk` BIGINT(20) DEFAULT NULL,
...
PRIMARY KEY (`pk`),
...
CONSTRAINT `patient_fk` FOREIGN KEY (`patient_fk`) REFERENCES `patient` (`pk`)
)ENGINE=InnoDB;
patient/*1: List duplicated */
select pk,pat_id, t.`pat_id_issuer`, t.`pat_name`, t.pat_custom1
from patient t
where pat_id in (
select pat_id from (
select pat_id, count(*)
from patient
group by 1
having count(*)>1
) xxx);
/*2: Delete orphan patients */
delete from patient where pk not in (select patient_fk from study);
/*3: Reset flag for duplicated (or not) patients*/
update patient t set t.`pat_custom1`='N';
/*4: Mark all duplicated */
update patient t set t.`pat_custom1`='Y'
where pat_id in (
select pat_id from (
select pat_id, count(*)
from patient
group by 1
having count(*)>1
) xxx) ;
/*5: Unmark the 1st of the duplicated*/
update patient t
join (select pk from (
select min(pk) as pk, pat_id from patient
where pat_custom1='Y'
group by pat_id
) xxx ) x
on (x.pk=t.pk)
set t.`pat_custom1`='X'
where pat_custom1='Y'
;
/*6: Verify update is correct*/
select pk, pat_id,pat_custom1
from `patient`
where pat_custom1!='N'
order by pat_id, pat_custom1;
/*7: Verify studies linked to duplicated patient */
select p.* from study s
join patient p on (p.pk=s.patient_fk)
where p.pat_custom1='Y';
/*8: Relink duplicated patients */
update study s
join patient p on (p.pk=s.patient_fk)
set patient_fk = (select pk from patient pp
where pp.pat_id=p.pat_id and pp.pat_custom1='X')
where p.pat_custom1='Y';
/*9: Delete newly orphan patients */
delete from patient where pk not in (select patient_fk from study);
/* 10: reset flag */
update patient t set t.`pat_custom1`=null;
/* 11: Commit changes */
commit;