Lookup primary ID from multiple tables having another (unique) field - sql-server

I'm trying to add values in a junction table of a many to many relationship.
Tables look like these (all IDs are integers):
Table A
+------+----------+
| id_A | ext_id_A |
+------+----------+
| 1 | 100 |
| 2 | 101 |
| 3 | 102 |
+------+----------+
Table B is conceptually similar
+------+----------+
| id_B | ext_id_B |
+------+----------+
| 1 | 200 |
| 2 | 201 |
| 3 | 202 |
+------+----------+
Tables PK are id_A and id_B, as columns in my junction table are FK to those columns, but I have to insert values having only external ids (ext_id_A, ext_id_B).
External IDs are unique columns, (and therefore in a 1:1 with table id itself), so having ext_id I can lookup the exact row and get the id need to insert into junction table.
This is an example of what I've done so far, but doesn't look like an optimized sql statement:
-- Example table I receive with test values
declare #temp as table (
ext_id_a int not null,
ext_id_b int not null
);
insert into #temp values (100, 200), (101, 200), (101, 201);
--Insertion - code from my sp
declare #final as table (
id_a int not null,
id_b int not null
);
insert into #final
select a.id_a, b.id_b
from #temp as t
inner join table_a a on a.ext_id_a = t.ext_id_a
inner join table_b b on b.ext_id_b = t.ext_id_b
merge into junction_table as jt
using #final as f
on f.id_a = jt.id_a and f.id_b = tj.id_b
when not matched by target then
insert (id_a, id_b) values (id_a, id_b);
I was thinking about a MERGE statement since my stored procedure receives data in a Table Value Parameters parameter and I also have to check for already existing references.
Is anything I can do to improve insertion of these values?

No need to use the #final table variable:
; with cte as (
select tA.id_A, tB.id_B
from #temp t
join table_A tA on t.ext_id_a = tA.ext_id_A
join table_B tB on t.ext_id_B = tB.ext_id_B
)
merge into junction_table
using cte
on cte.id_A = junction_table.id_A and cte.id_B = junction_table.id_B
when not matched by target then
insert (id_A, id_B) values (cte.id_A, cte.id_B);

Related

SQL Server : except with results from both datasets

I have the following tables:
Stores:
StoreID | Name
1 | Store1
2 | Store2
3 | Store3
EmID | StoreID
1 | 1
2 | 1
3 | 1
1 | 2
3 | 2
Employee:
EmID | Employee | Important
1 | Cashier | 1
2 | Manager | 1
3 | Guard | 0
I need a query to return StoreID and EmID where Employee is important (Important = 1) and the store and employee are not connected. Basically, the result should be:
StoreID | EmId
--------+-------
2 | 2
3 | 1
3 | 2
I have tried joins, outer joins / apply-es, except, cte, temporary tables, but still haven't found the answer.
Can someone help me with the code, or at least point me in the right direction?
Any idea will be very much appreciated.
Thanks.
You use a cross join to get the set of all possible employee/store combinations, and a left join to then remove the combinations that exist in the join table1:
declare #Stores table (StoreID int, Name char(6))
insert into #Stores (StoreID,Name) values
(1,'Store1'),
(2,'Store2'),
(3,'Store3')
declare #Employees table (EmID int, Employee varchar(8), Important bit)
insert into #Employees (EmID,Employee,Important) values
(1,'Cashier',1),
(2,'Manager',1),
(3,'Guard' ,0)
declare #Staffing table (EmID int, StoreID int)
insert into #Staffing (EmID,StoreID) values
(1,1),
(2,1),
(3,1),
(1,2),
(3,2)
select
*
from
#Stores s
cross join
#Employees e
left join
#Staffing st
on
s.StoreID = st.StoreID and
e.EmID = st.EmID
where
e.Important = 1 and
st.EmID is null
Results:
StoreID Name EmID Employee Important EmID StoreID
----------- ------ ----------- -------- --------- ----------- -----------
3 Store3 1 Cashier 1 NULL NULL
2 Store2 2 Manager 1 NULL NULL
3 Store3 2 Manager 1 NULL NULL
1The one I've named Staffing and you didn't name in the question. Note also (for future questions) that my presentation of the sample data takes up approximately as much space as yours in the question, provides the data types, and is a runnable script.
Please use Cross join followed by Left join and filter on IMP and StoreID null.
create table #Stores
(storeID int, Name varchar(100))
create table #ES
(empid int,storeID int)
create table #E
(eid int,employee varchar(100), imp int)
insert into #stores values(
1,'Store1'),
(2,'Store2'),
(3,'Store3')
insert into #ES values(
1,1),(2,1),(3,1),(1,2),(3,2)
insert into #E values
(1,'Cashier',1),
(2,'Manager', 1),
(3,'Guard',0)
select * from #Stores
select * from #ES
select * from #E
select #stores.storeid,#E.eid from #Stores
cross join #E
LEFT join #ES
on #ES.storeid = #Stores.storeid
and #E.eid = #ES.empid
where #E.imp = 1
and #ES.storeID is null
Try this query.
I assumed the table name of the "Employee" is dbo.Employee and table name of "Stores" is dbo.Stores and the intermediate table is "dbo.EmpStore"
SELECT S.StoreID, E.EmID
FROM dbo.Stores S
CROSS JOIN dbo.Employees E
LEFT JOIN dbo.EmpStore ES ON ES.EmID = E.EmID AND ES.StoreID = S.StoreID
WHERE E.Important=1 AND ES.EmID IS NULL

Update Table1 adding values from Table2

Table1
Columns PK_Table1 Name | DoYouGoToSchool |DoYouhaveACar |DoYouWorkFullTime | DoYouWorkPartTime | Score
1 joe Yes Yes No Yes
2 amy No Yes Yes No
Table2
Columns Pk_Table2 |Question | Answer(Bit Column) |Value
1 DoYouGoToSchool True 3
2 DoYouhaveACar True 2
3 DoYouWorkFullTime True 4
4 DoYouWorkPartTime True 2
Based on the information from Table2 What i need to do is UPDATE Table1 ColumnName Score by summing up the Value from Table2 with the information he has provided.
for example i expect the Score column in table1 to be 7 for record 1
and 5 for record 2
Here is a query to play with
IF OBJECT_ID('tempdb..#Table2') IS NOT NULL DROP TABLE #Table2
GO
IF OBJECT_ID('tempdb..#Table1') IS NOT NULL DROP TABLE #Table1
GO
create table #Table1
(
PK_Table1 int,
Name Varchar(50),
DoYouGoToSchool Varchar(8),
DoYouhaveACar Varchar(8),
DoYouWorkFullTime Varchar(8),
DoYouWorkPartTime Varchar(8),
Score INT NULL,
)
create table #Table2
(
PK_Table2 int,
Questions Varchar(50),
Answer BIT NOT NULL DEFAULT(0),
VALUE INT NULL
)
INSERT INTO #Table1 (Name,DoYouGoToSchool,DoYouhaveACar,DoYouWorkFullTime,DoYouWorkPartTime)
VALUES ('joe','Yes','Yes','No','Yes'), ('amy','NO','Yes','Yes','No')
INSERT INTO #Table2(Questions,Answer,VALUE)
VALUES ('DoYouGoToSchool','True',3 ),('DoYouhaveACar','True',2 ),('DoYouWorkFullTime','True',4 ),('DoYouWorkPartTime','True',2 )
This is what is missing from answer below that tells you to create new FK contraint to the Table2 --Inserting Data into the table with the new FK Column
insert into #Table2 (FK_Table1, Questions, Answer) select t.PK_Table1, t1.cols, colsval from #Table1 t cross apply (values (PK_Table1,'DoYouGoToSchool', DoYouGoToSchool), (PK_Table1,'DoYouhaveACar', DoYouhaveACar), (PK_Table1,'DoYouWorkFullTime', DoYouWorkFullTime), (PK_Table1,'DoYouWorkPartTime', DoYouWorkPartTime) ) t1 (PK_Table1,cols, colsval);
First create a relation between these two tables and add Primary key of Table1 in Table2 as a foreign key so your Table2 becomes:
Table2 Columns:
FK_Table1 |Pk_Table2 |Question | Answer(Bit Column) |Value
1 1 DoYouGoToSchool True 3
1 2 DoYouhaveACar True 2
1 3 DoYouWorkFullTime True 4
1 4 DoYouWorkPartTime True 2
You can add in table by using this Query:
ALTER TABLE Table2
ADD FK_Table1 INTEGER,
ADD CONSTRAINT FOREIGN KEY(FK_Table1) REFERENCES Table1(PK_Table1)
means that it is only for that person whose PK_Table1 = 1
Then you can extract his score from this query:
SELECT Sum(Value) FROM Table2 WHERE FK_Table1 = 1;
And then update query:
UPDATE Table1
SET score = (enter here the returned score from above query)
WHERE PK_Table1 = 1;
Or you can do in a single query like this:
UPDATE Table1
SET score = (SELECT Sum(Value) FROM Table2 WHERE FK_Table1 = 1)
WHERE PK_Table1 = 1;
You will need to add another table. This table will be your relational table. It can be called Table1_Table2 with three columns. The first column will be the primary key for the table. The next column will be the primary key of Table1 and the third column will be the primary key for Table 2.
When an instance of Table2 occurs that relates with Table1, insert a record into Table1_Table2 that relates the two tables together with each others primary key. Then a query can be done on the relational table, Table1_Table2 that allows you to sum the relationships.
|Table1_Table2 |
| PK | PK_Table1 | PK_Table2 |
| 1 | 1 | 1 |
| 2 | 1 | 3 |
| 3 | 2 | 1 |
| 4 | 2 | 4 |
As we can see, we can now perform an update on Table1
UPDATE TABLE1 A SET A.SCORE = (Select SUM(B.Value) FROM Table2 B, Table1_Table2 C WHERE C.PK_Table2 = B.PK_Table2 AND C.PK_Table1 = A.PK_Table1);

Return all results from left table when NULL present in right table and results of inner join when no null present in right table

Hi just wondering if this scenario is possible?
I have two tables and a relationship table to create a many to many relationships between the two tables. See the below tables for a simple representation;
| Security ID | Security Group |
| 1 | Admin |
| 2 | Basic |
| Security ID | Access ID |
| 1 | NULL |
| 2 | 1 |
| Function ID | Function Code |
| 1 | Search |
| 2 | Delete |
What I want to achieve is while checking the relationship table I want to return all functions a user on a security group has access to. If the user is assigned to a security group that contains a NULL value in the relationship table then grant them access to all functions.
For instance, a user on the "Basic" security group would have access to the search function while a user on the "Admin" security group should have access to both Search and Delete.
The reason it is set up this way is because a user can have 0 to many security groups and the list of functions is very large requiring the use of a whitelist of functions you can access instead of a list of a blacklist of functions you can't access.
Thank you for your time.
Your tables' sample:
CREATE TABLE #G
(
Security_ID INT,
Security_Group VARCHAR(32)
)
INSERT INTO #G
VALUES (1, 'Admin'), (2, 'Basic')
CREATE TABLE #A
(
Security_ID INT,
Access_ID INT
)
INSERT INTO #A
VALUES (1, NULL), (2, 1)
CREATE TABLE #F
(
Function_ID INT,
Function_CODE VARCHAR(32)
)
INSERT INTO #F
VALUES (1, 'Search'), (2, 'Delete')
Query:
SELECT #G.Security_Group, #F.Function_CODE
FROM #G
JOIN #A ON #G.Security_ID = #A.Security_ID
JOIN #F ON #F.Function_ID = #A.Access_ID OR #A.Access_ID IS NULL
Dropping the sample tables:
DROP TABLE #G
DROP TABLE #A
DROP TABLE #F

Reverse order of a XML Column in SQL Server

In a SQL Server table, I have a XML column where status are happened (first is oldest, last current status).
I have to write a stored procedure that returns the statuses: newest first, oldest last.
This is what I wrote:
ALTER PROCEDURE [dbo].[GetDeliveryStatus]
#invoiceID nvarchar(255)
AS
BEGIN
SET NOCOUNT ON;
DECLARE #xml xml
SET #xml = (SELECT statusXML
FROM Purchase
WHERE invoiceID = #invoiceID )
SELECT
t.n.value('text()[1]', 'nvarchar(50)') as DeliveryStatus
FROM
#xml.nodes('/statuses/status') as t(n)
ORDER BY
DeliveryStatus DESC
END
Example of value in the statusXML column:
<statuses>
<status>A</status>
<status>B</status>
<status>A</status>
<status>B</status>
<status>C</status>
</statuses>
I want the procedure to return:
C
B
A
B
A
with ORDER BY .... DESC it return ALPHABETIC reversed (C B B A A)
How should I correct my procedure ?
Create a sequence for the nodes based on the existing order then reverse it.
WITH [x] AS (
SELECT
t.n.value('text()[1]', 'nvarchar(50)') as DeliveryStatus
,ROW_NUMBER() OVER (ORDER BY t.n.value('..', 'NVARCHAR(100)')) AS [Order]
FROM
#xml.nodes('/statuses/status') as t(n)
)
SELECT
DeliveryStatus
FROM [x]
ORDER BY [x].[Order] DESC
... results ...
DeliveryStatus
C
B
A
B
A
There is no need to declare a variable first. You can (and you should!) read the needed values from your table column directly. Best was an inline table valued function (rather than a SP just to read something...)
Better performance
inlineable
You can query many InvoiceIDs at once
set-based
Try this (I drop the mock-table at the end - carefull with real data!):
CREATE TABLE Purchase(ID INT IDENTITY,statusXML XML, InvocieID INT, OtherValues VARCHAR(100));
INSERT INTO Purchase VALUES('<statuses>
<status>A</status>
<status>B</status>
<status>A</status>
<status>B</status>
<status>C</status>
</statuses>',100,'Other values of your row');
GO
WITH NumberedStatus AS
(
SELECT ID
,InvocieID
, ROW_NUMBER() OVER(ORDER BY (SELECT NULL)) AS Nr
,stat.value('.','nvarchar(max)') AS [Status]
,OtherValues
FROM Purchase
CROSS APPLY statusXML.nodes('/statuses/status') AS A(stat)
WHERE InvocieID=100
)
SELECT *
FROM NumberedStatus
ORDER BY Nr DESC
GO
--Clean-Up
--DROP TABLE Purchase;
The result
+---+-----+---+---+--------------------------+
| 1 | 100 | 5 | C | Other values of your row |
+---+-----+---+---+--------------------------+
| 1 | 100 | 4 | B | Other values of your row |
+---+-----+---+---+--------------------------+
| 1 | 100 | 3 | A | Other values of your row |
+---+-----+---+---+--------------------------+
| 1 | 100 | 2 | B | Other values of your row |
+---+-----+---+---+--------------------------+
| 1 | 100 | 1 | A | Other values of your row |
+---+-----+---+---+--------------------------+

SQL Server : Bulk insert a Datatable into 2 tables

Consider this datatable :
word wordCount documentId
---------- ------- ---------------
Ball 10 1
School 11 1
Car 4 1
Machine 3 1
House 1 2
Tree 5 2
Ball 4 2
I want to insert these data into two tables with this structure :
Table WordDictionary
(
Id int,
Word nvarchar(50),
DocumentId int
)
Table WordDetails
(
Id int,
WordId int,
WordCount int
)
FOREIGN KEY (WordId) REFERENCES WordDictionary(Id)
But because I have thousands of records in initial table, I have to do this just in one transaction (batch query) for example using bulk insert can help me doing this purpose.
But the question here is how I can separate this data into these two tables WordDictionary and WordDetails.
For more details :
Final result must be like this :
Table WordDictionary:
Id word
---------- -------
1 Ball
2 School
3 Car
4 Machine
5 House
6 Tree
and table WordDetails :
Id wordId WordCount DocumentId
---------- ------- ----------- ------------
1 1 10 1
2 2 11 1
3 3 4 1
4 4 3 1
5 5 1 2
6 6 5 2
7 1 4 2
Notice :
The words in the source can be duplicated so I must check word existence in table WordDictionary before any insert record in these tables and if a word is found in table WordDictionary, the just found Word ID must be inserted into table WordDetails (please see Word Ball)
Finally the 1 M$ problem is: this insertion must be done as fast as possible.
If you're looking to just load the table the first time without any updates to the table over time you could potentially do it this way (I'm assuming you've already created the tables you're loading into):
You can put all of the distinct words from the datatable into the WordDictionary table first:
SELECT DISTINCT word
INTO WordDictionary
FROM datatable;
Then after you populate your WordDictionary you can then use the ID values from it and the rest of the information from datatable to load your WordDetails table:
SELECT WD.Id as wordId, DT.wordCount as WordCount, DT.documentId AS DocumentId
INTO WordDetails
FROM datatable as DT
INNER JOIN WordDictionary AS WD ON WD.word = DT.word
There a little discrepancy between declared table schema and your example data, but it was solved:
1) Setup
-- this the table with the initial data
-- drop table DocumentWordData
create table DocumentWordData
(
Word NVARCHAR(50),
WordCount INT,
DocumentId INT
)
GO
-- these are result table with extra information (identity, primary key constraints, working foreign key definition)
-- drop table WordDictionary
create table WordDictionary
(
Id int IDENTITY(1, 1) CONSTRAINT PK_WordDictionary PRIMARY KEY,
Word nvarchar(50)
)
GO
-- drop table WordDetails
create table WordDetails
(
Id int IDENTITY(1, 1) CONSTRAINT PK_WordDetails PRIMARY KEY,
WordId int CONSTRAINT FK_WordDetails_Word REFERENCES WordDictionary,
WordCount int,
DocumentId int
)
GO
2) The actual script to put data in the last two tables
begin tran
-- this is to make sure that if anything in this block fails, then everything is automatically rolled back
set xact_abort on
-- the dictionary is obtained by considering all distinct words
insert into WordDictionary (Word)
select distinct Word
from DocumentWordData
-- details are generating from initial data joining the word dictionary to get word id
insert into WordDetails (WordId, WordCount, DocumentId)
SELECT W.Id, DWD.WordCount, DWD.DocumentId
FROM DocumentWordData DWD
JOIN WordDictionary W ON W.Word = DWD.Word
commit
-- just to test the results
select * from WordDictionary
select * from WordDetails
I expect this script to run very fast, if you do not have a very large number of records (millions at most).
This is the query. I'm using temp table to be able to test.
if you use the 2 CTEs, you'll be able to generate the final result
1.Setting up a sample data for test.
create table #original (word varchar(10), wordCount int, documentId int)
insert into #original values
('Ball', 10, 1),
('School', 11, 1),
('Car', 4, 1),
('Machine', 3, 1),
('House', 1, 2),
('Tree', 5, 2),
('Ball', 4, 2)
2. Use cte1 and cte2. In your real database, you need to replace #original with the actual table name you have all initial records.
;with cte1 as (
select ROW_NUMBER() over (order by word) Id, word
from #original
group by word
)
select * into #WordDictionary
from cte1
;with cte2 as (
select ROW_NUMBER() over (order by #original.word) Id, Id as wordId,
#original.word, #original.wordCount, #original.documentId
from #WordDictionary
inner join #original on #original.word = #WordDictionary.word
)
select * into #WordDetails
from cte2
select * from #WordDetails
This will be data in #WordDetails
+----+--------+---------+-----------+------------+
| Id | wordId | word | wordCount | documentId |
+----+--------+---------+-----------+------------+
| 1 | 1 | Ball | 10 | 1 |
| 2 | 1 | Ball | 4 | 2 |
| 3 | 2 | Car | 4 | 1 |
| 4 | 3 | House | 1 | 2 |
| 5 | 4 | Machine | 3 | 1 |
| 6 | 5 | School | 11 | 1 |
| 7 | 6 | Tree | 5 | 2 |
+----+--------+---------+-----------+------------+

Resources