Is it possible to create multiple relations from one table, to another table?
I have a table containing purchases, each of these purchases have a origin_country and a destination_country.
I would like to have relations (as foreign keys) to a single PK on a table from these two columns from the same table.
i have tried the following queries:
alter table Purchases
add constraint FK_Purchases_OriginCountries
foreign key (FK_OriginCountryCode) references dbo.countries
go
alter table Purchases
add constraint FK_Purchases_DestinationCountries
foreign key (FK_DestinationCountryCode) references dbo.countries
go
But end up getting a conflict, I can't however find documentation that this is not possible...
[23000][547] The ALTER TABLE statement conflicted with the FOREIGN KEY
constraint "FK_Purchases_DestinationCountries". The conflict occurred
in database "Market", table "dbo.countries", column 'ID'.
Is this relationship intentionally not possible, or did i just make a mistake?
Thank you
Yes you can.
The error is not a result of trying to create two foreign keys back to a single table, that's perfectly fine. Try running this to see it work:
create table t(i int primary key);
create table u
(
j int foreign key references t(i),
k int foreign key references t(i)
);
The problem you have is that you have some data in your Purchases table where the value in the column on which you are trying to create the foreign key does not exist in the countries table's ID column.
To find them run a query like this:
select p.*
from dbo.purchases p
where not exists
(
select *
from dbo.countries
where ID = p.FK_DestinationCountryCode
)
Note that I think your column names are a little weird here, You shouldn't call a column FK_DestinationCountryCode just because it has a foreign key on it, and a "code" is not the same kind of thing as an "ID". Your purchases table's columns should probably be called DestinationCountryID and OriginCountryID.
I'm using SQL Server 2014 to create and insert data into tables and came along a problem when it comes to populating a table with a foreign key constraint in it. I have a table user and and a table city which were created beforehand.
I used code to alter the user table to include a cityId foreign key from table city with this code:
ALTER TABLE [Schema].[user]
ADD cityId UNIQUEIDENTIFIER NOT NULL
CONSTRAINT usr_cid_fk
FOREIGN KEY (cityId) REFERENCES [Schema].[city] (cityId);
GO
Basically I modified the user table by adding a field called cityId which i made foreign key. now the problem is that when inserting data, in the first line
INSERT INTO [Schema].[user](name, surname, dob, gender, .. )
cityId cannot be found to be mapped. Dunno why it ain't showing. In the design view it is listed as a foreign key so there should be no problems.
Thanks a lot
try :
ALTER TABLE [Schema].[user]
ADD cityId NUMBER NOT NULL
CONSTRAINT usr_cid_fk
FOREIGN KEY (cityId) REFERENCES [Schema].[city] (cityId);
Note :
For ADD cityId UNIQUEIDENTIFIER NOT NULL
By the SQL standard, a foreign key must reference either the primary key or a unique key of the parent table. If the primary key has multiple columns, the foreign key must have the same number and order of columns. Therefore the foreign key references a unique row in the parent table; there can be no duplicates.
I have a table Categories with columns Id, ParentId (for "subcategories" whom can have any level of nesting) and some other. Using SQL Server 2012 I can't make foreign key in same table, FK_Categories_Categories (Id -> ParentId).
Error message is
'Categories' table
- Unable to create relationship 'FK_Categories_Categories'. The ALTER TABLE statement conflicted with the FOREIGN KEY SAME TABLE constraint "FK_Categories_Categories". The conflict occurred in database "pokupaykadb", table "dbo.Categories", column 'Id'.
That needs for cascade deletion of subcategories. What solution can be? It's desirable to be a some property, like cascade deletion from another table by foreign key
http://i.stack.imgur.com/kXiMS.png
If there are orphaned records that does not meet your constraint criteria - delete them before creating the foreign key.
Usually there are few records which doesn't go by the new constraint and that the DBMS doesn't allow to create the constraint.
In the case of orphaned values, the first occurrence is provided in the error label with the value that is orphaned.
It would certainly have helped to see what code you have tried to execute.
Below is a valid table definition :
CREATE TABLE dbo.Categories
(
Id int NOT NULL IDENTITY(-2147483648, 1)
CONSTRAINT PK_Categories PRIMARY KEY
, ParentId int NOT NULL
CONSTRAINT FK_Categories_ParentId
FOREIGN KEY (ParentId) REFERENCES dbo.Categories
)
I have two tables, Table JOB and Table USER, here is the structure
CREATE TABLE JOB
(
ID NUMBER NOT NULL ,
USERID NUMBER,
CONSTRAINT B_PK PRIMARY KEY ( ID ) ENABLE
);
CREATE TABLE USER
(
ID NUMBER NOT NULL ,
CONSTRAINT U_PK PRIMARY KEY ( ID ) ENABLE
);
Now, i want to add foreign key constraint to JOB referencing to USER table, as
Alter Table JOB ADD CONSTRAINT FK_USERID FOREIGN KEY(USERID) REFERENCES USER(ID);
this throws Oracle (ORA-02270) : no matching unique or primary key for this column-list error, doing some investigation it appears that we need to have either unique key or primary key constraint on USERID but I cannot have that as one USERID can have multiple JOBS associated with him, any thoughts or suggestions on how to fix this issue?
Researched ORA-02270 and SO related question
The ORA-2270 error is a straightforward logical error: it happens when the columns we list in the foreign key do not match a primary key or unique constraint on the parent table. Common reasons for this are
the parent lacks a PRIMARY KEY or UNIQUE constraint altogether
the foreign key clause references the wrong column in the parent table
the parent table's constraint is a compound key and we haven't referenced all the columns in the foreign key statement.
Neither appears to be the case in your posted code. But that's a red herring, because your code does not run as you have posted it. Judging from the previous edits I presume you are not posting your actual code but some simplified example. Unfortunately in the process of simplification you have eradicated whatever is causing the ORA-2270 error.
SQL> CREATE TABLE JOB
(
ID NUMBER NOT NULL ,
USERID NUMBER,
CONSTRAINT B_PK PRIMARY KEY ( ID ) ENABLE
); 2 3 4 5 6
Table created.
SQL> CREATE TABLE USER
(
ID NUMBER NOT NULL ,
CONSTRAINT U_PK PRIMARY KEY ( ID ) ENABLE
); 2 3 4 5
CREATE TABLE USER
*
ERROR at line 1:
ORA-00903: invalid table name
SQL>
That statement failed because USER is a reserved keyword so we cannot name a table USER. Let's fix that:
SQL> 1
1* CREATE TABLE USER
SQL> a s
1* CREATE TABLE USERs
SQL> l
1 CREATE TABLE USERs
2 (
3 ID NUMBER NOT NULL ,
4 CONSTRAINT U_PK PRIMARY KEY ( ID ) ENABLE
5* )
SQL> r
1 CREATE TABLE USERs
2 (
3 ID NUMBER NOT NULL ,
4 CONSTRAINT U_PK PRIMARY KEY ( ID ) ENABLE
5* )
Table created.
SQL> Alter Table JOB ADD CONSTRAINT FK_USERID FOREIGN KEY(USERID) REFERENCES USERS(ID);
Table altered.
SQL>
And lo! No ORA-2270 error.
Alas, there's not much we can do here to help you further. You have a bug in your code. You can post your code here and one of us can spot your mistake. Or you can check your own code and discover it for yourself.
Note: an earlier version of the code defined HOB.USERID as VARCHAR2(20). Because USER.ID is defined as a NUMBER the attempt to create a foreign key would have hurl a different error:
ORA-02267: column type incompatible with referenced column type
An easy way to avoid mismatches is to use foreign key syntax to default the datatype of the column:
CREATE TABLE USERs
(
ID number NOT NULL ,
CONSTRAINT U_PK PRIMARY KEY ( ID ) ENABLE
);
CREATE TABLE JOB
(
ID NUMBER NOT NULL ,
USERID constraint FK_USERID references users,
CONSTRAINT B_PK PRIMARY KEY ( ID ) ENABLE
);
The data type in the Job table (Varchar2(20)) does not match the data type in the USER table (NUMBER NOT NULL).
In my case the problem was cause by a disabled PK.
In order to enable it:
I look for the Constraint name with:
SELECT * FROM USER_CONS_COLUMNS WHERE TABLE_NAME = 'referenced_table_name';
Then I took the Constraint name in order to enable it with the following command:
ALTER TABLE table_name ENABLE CONSTRAINT constraint_name;
We have the following script for create a new table:
CREATE TABLE new_table
(
id NUMBER(32) PRIMARY KEY,
referenced_table_id NUMBER(32) NOT NULL,
CONSTRAINT fk_new_table_referenced_table_id
FOREIGN KEY (referenced_table_id)
REFERENCES referenced_table (id)
);
and we were getting this error on execution:
[42000][2270] ORA-02270: no matching unique or primary key for this
column-list
The issue was due to disabled primary key of the referenced table in our case. We have to enable it using the following sql:
ALTER TABLE referenced_table ENABLE PRIMARY KEY USING INDEX;
after that we created new table using first script without any issues
The scheme is correct, User.ID must be the primary key of User, Job.ID should be the primary key of Job and Job.UserID should be a foreign key to User.ID. Also, your commands appear to be syntactically correct.
So what could be wrong? I believe you have at least a Job.UserID which doesn't have a pair in User.ID. For instance, if all values of User.ID are: 1,2,3,4,6,7,8 and you have a value of Job.UserID of 5 (which is not among 1,2,3,4,6,7,8, which are the possible values of UserID), you will not be able to create your foreign key constraint. Solution:
delete from Job where UserID in (select distinct User.ID from User);
will delete all jobs with nonexistent users. You might want to migrate these to a copy of this table which will contain archive data.
Most Probably when you have a missing Primary key is not defined from parent table. then It occurs.
Like Add the primary key define in parent as below:
ALTER TABLE "FE_PRODUCT" ADD CONSTRAINT "FE_PRODUCT_PK" PRIMARY KEY ("ID") ENABLE;
Hope this will work.
I faced the same issue in my scenario as follow:
I created textbook table first with
create table textbook(txtbk_isbn varchar2(13)
primary key,txtbk_title varchar2(40),
txtbk_author varchar2(40) );
Then chapter table:
create table chapter(txtbk_isbn varchar2(13),chapter_title varchar2(40),
constraint pk_chapter primary key(txtbk_isbn,chapter_title),
constraint chapter_txtbook foreign key (txtbk_isbn) references textbook (txtbk_isbn));
Then topic table:
create table topic(topic_id varchar2(20) primary key,topic_name varchar2(40));
Now when I wanted to create a relationship called chapter_topic between chapter (having composite primary key) and topic (having single column primary key), I faced issue with following query:
create table chapter_topic(txtbk_isbn varchar2(13),chapter_title varchar2(40),topic_id varchar2(20),
primary key (txtbk_isbn, chapter_title, topic_id),
foreign key (txtbk_isbn) references textbook(txtbk_isbn),
foreign key (chapter_title) references chapter(chapter_title),
foreign key (topic_id) references topic (topic_id));
The solution was to refer to composite foreign key as below:
create table chapter_topic(txtbk_isbn varchar2(13),chapter_title varchar2(40),topic_id varchar2(20),
primary key (txtbk_isbn, chapter_title, topic_id),
foreign key (txtbk_isbn, chapter_title) references chapter(txtbk_isbn, chapter_title),
foreign key (topic_id) references topic (topic_id));
Thanks to APC post in which he mentioned in his post a statement that:
Common reasons for this are
- the parent lacks a constraint altogether
- the parent table's constraint is a compound key and we haven't referenced all the columns in the foreign key statement.
- the referenced PK constraint exists but is DISABLED
When running this command:
ALTER TABLE MYTABLENAME MODIFY CONSTRAINT MYCONSTRAINTNAME_FK ENABLE;
I got this error:
ORA-02270: no matching unique or primary key for this column-list
02270. 00000 - "no matching unique or primary key for this column-list"
*Cause: A REFERENCES clause in a CREATE/ALTER TABLE statement
gives a column-list for which there is no matching unique or primary
key constraint in the referenced table.
*Action: Find the correct column names using the ALL_CONS_COLUMNS
The referenced table has a primary key constraint with matching type. The root cause of this error, in my case, was that the primary key constraint was disabled.
Isn't the difference between your declaration of USERID the problem
JOB: UserID is Varchar
USER: UserID is Number?
If primary key is not already defined on parent table then this issue may arise. Please try to define the primary key on existing table.
For eg:
ALTER TABLE table_name
ADD PRIMARY KEY (the_column_which_is_primary_key);
create table articles(code varchar2(30)constraint articles_pk primary key,titre varchar2(30),
support varchar2(30) constraint support_fk references supports(support),type_support varchar2(30),
numeroDePage varchar2(30),datepublication date,categorie varchar2(30)constraint categorie_fk references organismes(categorie),
tendance varchar2(30)constraint tendance_fk references apreciations(tendance));
I have a database scheme with versioning data rows, e.g.
Table Person has the columns
id (int, PK)
name (String)
current (Bool)
firstid (int)
Current is 0 for previous data, 1 for the latest entry. All rows for the same entity have the same FirstID, which points to the first ID of the set.
Referencing table: Adress with the same principle:
id (int, PK)
street (String)
person_id (int)
current (Bool)
firstid (int)
Person_id points to patient.firstid. So firstid is never unique, only if current=1
My problem is: I would like to add referential integrity to my tables, but this only works, if the referenced column (patient.firstid) is unique...
You should look at refactoring your table structure. But to keep within the current structure, add a self-referencing foreign key to person
firstid references person(id)
Then, reference the "base person" from the address table
address.person_id references person(id) -- which should ONLY store a link to the first id
A FOREIGN KEY constraint does not have
to be linked only to a PRIMARY KEY
constraint in another table; it can
also be defined to reference the
columns of a UNIQUE constraint in
another table. A FOREIGN KEY
constraint can contain null values;
however, if any column of a composite
FOREIGN KEY constraint contains null
values, then verification of the
FOREIGN KEY constraint will be skipped.
Data from two related tables can be combined even if no PRIMARY KEY or FOREIGN KEY constraints are defined between the tables, but a foreign key relationship between two tables indicates that the two tables have been optimized to be combined in a query that uses the keys as its criteria.
reference http://msdn.microsoft.com/en-us/library/aa933117(v=sql.80).aspx