SQL JOIN with COALESCE in condition is duplicating rows - sql-server

I am trying to join two tables together. The first table contains data records that I do not want to duplicate. The second table I am joining to the first table to lookup a [value] by a distinct [profileId] and [role]. The [profileId], [role] column in the second table has a unique constraint on the combination, but [role] can sometimes be NULL, in which case I treat that value as the default for that profile.
How can I join these tables together without duplicating the rows, and without using multiple left joins? My actual query is more complex than the example.
See example below.
DECLARE #temp TABLE ([profileId] int, [role] int)
DECLARE #temp2 TABLE ([profileId] int, [role] int, [value] nvarchar(50))
INSERT INTO #temp ([profileId], [role]) VALUES (1, 1)
INSERT INTO #temp ([profileId], [role]) VALUES (1, 2)
INSERT INTO #temp ([profileId], [role]) VALUES (2, 1)
INSERT INTO #temp ([profileId], [role]) VALUES (2, 2)
INSERT INTO #temp2 ([profileId], [role], [value]) VALUES (1, 1, 'MATCH')
INSERT INTO #temp2 ([profileId], [role], [value]) VALUES (1, NULL, 'DEFAULT1')
INSERT INTO #temp2 ([profileId], [role], [value]) VALUES (2, NULL, 'DEFAULT2')
SELECT
T1.[profileId],
T1.[role],
T2.value
FROM
#temp T1
JOIN #temp2 T2 ON T1.profileId = T2.profileId AND COALESCE(T2.[role], T1.[role]) = T1.[role]
This gives me (and I understand why)
================================
| profileId | role | value |
================================
| 1 | 1 | MATCH |
--------------------------------
| 1 | 1 | DEFAULT1 |
--------------------------------
| 1 | 2 | DEFAULT1 |
--------------------------------
| 2 | 1 | DEFAULT2 |
--------------------------------
| 2 | 2 | DEFAULT2 |
================================
While I want
================================
| profileId | role | value |
================================
| 1 | 1 | MATCH |
--------------------------------
| 1 | 2 | DEFAULT1 |
--------------------------------
| 2 | 1 | DEFAULT2 |
--------------------------------
| 2 | 2 | DEFAULT2 |
================================

This SQL works fine:
SELECT
T1.[role],
Value = coalesce(max(nullif(T2.value,'DEFAULT')),'DEFAULT')
FROM
#temp T1
JOIN #temp2 T2 ON COALESCE(T2.[role], T1.[role]) = T1.[role]
group by
T1.[role]
;

You can use APPLY and TOP:
SELECT
t.profileId,
t.role,
x.value
FROM #temp t
OUTER APPLY(
SELECT TOP 1 value
FROM #temp2
WHERE
profileId = t.profileId
AND (role = t.role OR role IS NULL)
ORDER BY
CASE WHEN role IS NOT NULL THEN 0 ELSE 1 END
)x

if you know the DEFAULT value use left join.
SQL Fiddle Demo
SELECT
T1.[role],
COALESCE(T2.value, 'DEFAULT') as value
FROM
temp T1
LEFT JOIN temp2 T2
ON T1.[role] = T2.[role];
Otherwise
SELECT
T1.[role],
COALESCE(T2.value, (SELECT value
FROM temp2
WHERE role is NULL and temp2.profileID = T1.profileID)) as value
FROM
temp T1
LEFT JOIN temp2 T2
ON T1.[role] = T2.[role]
AND T1.[profileID] = T2.[profileID]
;

Related

SQL Server split field and create addition rows with values from main row

I have a table with rows and in one field there are values like this A,B,C
Table 'Mytable':
|ID | Date | MyValue | SplitID |
|1 | 2019-12-17 | A | |
|2 | 2019-12-15 | A,B | |
|3 | 2019-12-16 | B,C | |
Result should be:
|1 | 2019-12-17 | A | 1 |
|2 | 2019-12-15 | A | 2 |
|4 | 2019-12-15 | B | 2 |
|3 | 2019-12-16 | B | 3 |
|5 | 2019-12-16 | C | 3 |
(Sorry, I could not find HOW to format a table in the Stackoverflow help)
I tried a inline table function which splits the Field Myvalue into more lines but could not pass my rows with
charindex(',',[MyValue])>0
from MyTable as input lines.
The code is this:
ALTER function [dbo].[fncSplitString](#input Varchar(max), #Splitter Varchar(99), #ID int)
returns table as
Return
with tmp (DataItem, ix, ID) as
( select LTRIM(#input) , CHARINDEX('',#Input), #ID --Recu. start, ignored val to get the types right
union all
select LTRIM(Substring(#input, ix+1,ix2-ix-1)), ix2, #ID
from (Select *, CHARINDEX(#Splitter,#Input+#Splitter,ix+1) ix2 from tmp) x where ix2<>0
) select DataItem,ID from tmp where ix<>0
Thanks for help
Michael
You can try the following query.
Create table #Temp(
Id int,
DateField Date,
MyValue Varchar(10),
SplitID int
)
CREATE FUNCTION [dbo].[SplitPra] (#Value VARCHAR(MAX), #delimiter CHAR)
RETURNS #DataResult TABLE([Position] TINYINT IDENTITY(1,1),[Value] NVARCHAR(128))
AS
BEGIN
DECLARE #XML xml = N'<r><![CDATA[' + REPLACE(#Value, #delimiter, ']]></r><r><![CDATA[') + ']]></r>'
INSERT INTO #DataResult ([Value])
SELECT RTRIM(LTRIM(T.c.value('.', 'NVARCHAR(128)')))
FROM #xml.nodes('//r') T(c)
RETURN
END
insert into #Temp Values(1, '2019-12-17', 'A', NULL),(2, '2019-12-15', 'A,B', NULL), (3, '2019-12-16', 'B,C', NULL)
Select
#Temp.Id, DateField, b.Value as MyValue, b.Id as SplitValue
from #Temp inner join (
select
Id, f.*
from
#Temp u
cross apply [dbo].[SplitPra](u.MyValue, ',') f
)b on #Temp.Id = b.Id
Drop table #Temp
This will give an output as shown below.
Id DateField MyValue SplitValue
---------------------------------
1 2019-12-17 A 1
2 2019-12-15 A 2
2 2019-12-15 B 2
3 2019-12-16 B 3
3 2019-12-16 C 3
You can find the live demo here.
I found this solution, i hope it will work for you. But i didn't use your function to solve this problem. Instead of that, i used cross apply function.You can find the query below:
-- Creating Test Table
CREATE TABLE #Test
(
ID int,
Date date,
MyValue nvarchar(max),
SplitID int
);
GO
-- Inserting data into test table
INSERT INTO #Test VALUES (1, '2019-12-17', 'A', NULL);
INSERT INTO #Test VALUES (2, '2019-12-15', 'A,B', NULL);
INSERT INTO #Test VALUES (3, '2019-12-16', 'B,C', NULL);
GO
-- Select query
SELECT
*,
(SELECT ID FROM test t1 WHERE t.Date = t1.date) AS SplitID
FROM
(
SELECT
ROW_NUMBER() OVER (ORDER BY ID) AS ID,
Date,
substring(A.value,1,
CASE WHEN charindex(',',rtrim(ltrim(A.value))) = 0 then LEN(A.value)
ELSE charindex(',',rtrim(ltrim(A.value))) -1 end) as MyValue
FROM Test
CROSS APPLY string_split (MyValue, ',') A) AS T
ORDER BY MyValue ASC;
And the result must be like that:
ID Date MyValue SplitID
1 2019-12-17 A 1
2 2019-12-15 A 2
3 2019-12-15 B 2
4 2019-12-16 B 3
5 2019-12-16 C 3

Get multiple rows from a subquery SQL

Basically I have 2 Tables, the first with the raw material amount (QT) for each serial number and the second one with how much raw material was spent (Qt_Added) on batch's production. Like this:
Table 1
+----------+------------+-----+
| Code_Raw | Serial_Raw | Qt |
+----------+------------+-----+
| 1 | 1 | 100 |
| 1 | 2 | 150 |
| 2 | 1 | 80 |
| 1 | 3 | 100 |
+----------+------------+-----+
And Table 2
+------------+----------+------------+----------+--+
| Code_Batch | Code_Raw | Serial_Raw | Qt_Added | |
+------------+----------+------------+----------+--+
| 1 | 1 | 1 | 80 | |
| 2 | 1 | 1 | 10 | |
| 3 | 1 | 2 | 150 | |
| 4 | 1 | 3 | 80 | |
+------------+----------+------------+----------+--+
I tried to do a query for a specific Code_Raw, show me how much left for each serial number, But worked only when there's a single serial_raw.
My query:
select *
from
(select
Serial_Raw,
(Select QT From Table_1 where Code_Raw = 1) - Sum(qt_added) as Total_Remaining
from
Table_2
where
Cod_Raw = 1
group by
Serial_Raw) e
where
Total_Remaining > 0
but it throws this error
Subquery returned more than 1 value. This is not permitted when the subquery follows =, !=, <, <= , >, >= or when the subquery is used as an expression
And I expect :
Serial_Raw Total_Remaining
-------------------------------
1 10
3 20
Is there a struct problem or another way to do this?
I'm using SQL Server 2014
Thanks guys
Try this:
DECLARE #tbl1 TABLE
( CodeRaw INT,
Serial_Raw INT,
Qty INT)
DECLARE #tbl2 TABLE
(
CodeBatch INT,
CodeRaw INT,
Serial_Raw INT,
QtyAdded INT)
INSERT INTO #tbl1 VALUES(1,1,100)
INSERT INTO #tbl1 VALUES(1,2,150)
INSERT INTO #tbl1 VALUES(2,1,80)
INSERT INTO #tbl1 VALUES(1,3,100)
INSERT INTO #tbl2 VALUES(1,1,1,80)
INSERT INTO #tbl2 VALUES(2,1,1,10)
INSERT INTO #tbl2 VALUES(3,1,2,150)
INSERT INTO #tbl2 VALUES(4,1,3,80)
--Inner table has the summary of the Quantity added with columns CodeRaw and SerialRaw. Outer table make join with inner table and just substruct with the Qty and Sum of Qty Added.
SELECT t2.Serial_Raw, t1.Qty - t2.QtyAdded AS Total_Remaining FROM #tbl1 t1
INNER JOIN (SELECT CodeRaw, Serial_Raw , SUM(QtyAdded) QtyAdded FROM #tbl2
GROUP BY CodeRaw, Serial_Raw) AS t2 ON t2.CodeRaw = t1.CodeRaw AND t1.Serial_Raw = t2.Serial_Raw
WHERE t1.Qty - t2.QtyAdded > 0
If I understood you right, this might be what you are after
declare #tbl1 table (CodeRaw INT, Serial_Raw INT, Qty INT)
declare #tbl2 table (CodeBatch INT, CodeRaw INT, Serial_Raw INT, QtyAdded INT)
insert into #tbl1 values (1,1,100), (1,2,150), (2,1,80), (1,3,100)
insert into #tbl2 values (1,1,1,80), (2,1,1,10), (3,1,2,150), (4,1,3,80)
select t2.Serial_Raw,
t3.Qty - sum(t2.QtyAdded) as Total_Remaining
from #tbl2 t2
inner join ( select t1.Serial_Raw,
t1.CodeRaw,
sum(t1.Qty) as Qty
from #tbl1 t1
group by t1.Serial_Raw, t1.CodeRaw
) t3
on t2.Serial_Raw = t3.Serial_Raw
and t2.CodeRaw = t3.CodeRaw
group by t2.Serial_Raw, t3.Qty
So in t2 we get all distinct Serial_Raw values, and sum their QtyAdded from the first table.
In t3 we get all Qty values from the 2nd table.
All we need to do is join them together and subtract
The result of this query is
Serial_Raw Total_Remaining
---------- ---------------
1 10
2 0
3 20

Merge multiple results to one Column

I would like to create a select statement to merge multiple results into one rot
I was able to realized what I want via PHP but i think it should be possible to work directly with Sql.
Notes
| ID | Name |
|----|------|
| 2 | Test |
| 3 | Test |
EditorAssignment
| UserID | NoteID |
|--------|--------|
| 1 | 2 |
| 2 | 2 |
UserList
| ID | username |
|----|----------|
| 1 | testuser |
| 2 | bUser |
| 3 | cUser |
I would like to have the following Result:
| NoteID | User |
|--------|-----------------|
| 2 | testuser, bUser |
| 3 | cUser |
How can i create a select like that in SQL2012?
Before SQL Server 2017 (which has STRING_AGG aggregate function for this), you need to use the famous FOR XML PATH correlated subquery:
SetUp:
DECLARE #Notes TABLE (ID INT, Name VARCHAR(10))
INSERT INTO #Notes (ID, Name)
VALUES (2, 'Test'), (3, 'Test')
DECLARE #EditorAssignment TABLE (UserID INT, NoteID INT)
INSERT INTO #EditorAssignment (UserID, NoteID)
VALUES (1, 2), (2, 2),
(3, 3) -- Added missing row here
DECLARE #UserList TABLE (ID INT, username VARCHAR(100))
INSERT INTO #UserList (ID, username)
VALUES (1, 'testuser'), (2, 'bUser'), (3, 'cUser')
Query:
SELECT
NoteID = N.ID,
[User] = STUFF(
(
SELECT
', ' + U.username
FROM
#EditorAssignment AS E
INNER JOIN #UserList AS U ON E.UserID = U.ID
WHERE
N.ID = E.NoteID -- Link the outmost Notes' note with the inner EditorAssignment (correlated subquery)
FOR XML
PATH ('') -- FOR XML PATH('') makes the SELECT return a string value, not a result set
),
1,
2,
'')
FROM
#Notes AS N
Results:
NoteID User
2 testuser, bUser
3 cUser
The subquery generates a string with each username for the related assignment for each note.
The STUFF function is used just to replace the first ', ', since the string is build with a leading comma and a space. This is why the parameters of the STUFF are 1 (first position of the string), 2 (amount of places to remove, the comma and the space), and '' (replacement for those characters).
I'm guessing that you have a row missing for the EditorAssignment table that holds the values 3, 3 on your example.

Update postgres table to squash duplicate values in second table

I have a postgresql schema with two tables:
tableA: tableB:
| id | username | | fk_id | resource |
| 1 | user1 | | 2 | item1 |
| 2 | user1 | | 1 | item3 |
| 3 | user1 | | 1 | item2 |
| 4 | user2 | | 4 | item5 |
| 5 | user2 | | 5 | item8 |
| 6 | user3 | | 3 | item9 |
The foreign key fk_id in tableB references id in tableA.
How can I update all of the foreign key id's of tableB to point to the lowest entry for a unique username in tableA?
update table_b b
set fk_id = d.id
from table_a a
join (
select distinct on (username) username, id
from table_a
order by 1, 2
) d using(username)
where a.id = b.fk_id;
Test it here.
The query used inside the update gives actual_id, username, desired_id:
select a.id actual_id, username, d.id desired_id
from table_a a
join (
select distinct on (username) username, id
from table_a
order by 1, 2
) d using(username)
actual_id | username | desired_id
-----------+----------+------------
1 | user1 | 1
2 | user1 | 1
3 | user1 | 1
4 | user2 | 4
5 | user2 | 4
6 | user3 | 6
(6 rows)
We define your tables:
CREATE TABLE tableA (id, username) AS
SELECT * FROM
(
VALUES
(1, 'user1'),
(2, 'user1'),
(3, 'user1'),
(4, 'user2'),
(5, 'user2'),
(6, 'user2')
) AS x ;
CREATE TABLE tableB (fk_id, resource) AS
SELECT * FROM
(
VALUES
(2, 'item1'),
(1, 'item3'),
(1, 'item2'),
(4, 'item5'),
(5, 'item8'),
(3, 'item9')
) AS x ;
With that info, you can create a (virtual) conversion table, and use it to update your data:
-- Using tableA, make a new table with the
-- minimum id for every username
WITH username_to_min_id AS
(
SELECT
min(id) AS min_id, username
FROM
tableA
GROUP BY
username
)
-- Convert the previous table to a id -> min_id
-- conversion table
, id_to_min_id AS
(
SELECT
id, min_id
FROM
tableA
JOIN username_to_min_id USING(username)
)
-- Use this conversion table to update tableB
UPDATE
tableB
SET
fk_id = min_id
FROM
id_to_min_id
WHERE
-- JOIN condition with table to update
id_to_min_id.id = tableB.fk_id
-- Take out the ones that won't change
AND (fk_id <> min_id)
RETURNING
* ;
The result you would get is:
+-------+----------+----+--------+
| fk_id | resource | id | min_id |
+-------+----------+----+--------+
| 1 | item1 | 2 | 1 |
| 1 | item9 | 3 | 1 |
| 4 | item8 | 5 | 4 |
+-------+----------+----+--------+
Shows you that three rows have been updated, that had fk_id = (2, 3, 5), and have now (1, 1, 4). (The id is the "old" fk_id value).
You can check it at http://rextester.com/EQPH47434
You can "squeeze everything" [change every virtual table name by its definition, and do a couple of SELECT optimizations] and get this equivalent query (probably less clear, yet totally equivalent):
UPDATE
tableB
SET
fk_id = min_id
FROM
tableA
JOIN
(
SELECT
min(id) AS min_id, username
FROM
tableA
GROUP BY
username
) AS username_to_min_id
USING (username)
WHERE
tableA.id = tableB.fk_id
AND (fk_id <> min_id)
RETURNING
* ;

Split column with delimited values for an inner join

I need to perform an inner join to a column containing delimited values like:
123;124;125;12;3433;35343;
Now what I am currently doing is this:
ALTER procedure [dbo].[GetFruitDetails]
(
#CrateID int
)
AS
SELECT Fruits.*, Fruits_Crates.CrateID
FROM Fruits_Crates INNER JOIN Fruits
ON Fruits_Crates.FruitID = Fruits.ID
WHERE Fruits_Crates.CrateID = #CrateID
Now the issue is I am saving the data this way:
FruitCrateID FruitID
1 1;
2 1;2;3;4
3 3;
How can I inner join FruitsIDs to the fruit table to get fruit details as well?
Using the method posted in this answer, you can convert the delimited string into rows of a temp table and then join to that:
SQL Fiddle
Schema Setup:
CREATE TABLE Fruits_Crates
([FruitCrateID] int, [FruitID] varchar(10))
;
INSERT INTO Fruits_Crates
([FruitCrateID], [FruitID])
VALUES
(1, '1;'),
(2, '1;2;3;4;'),
(3, '3;')
;
CREATE TABLE Fruits
([FruitID] int, [FruitName] varchar(10))
;
INSERT INTO Fruits
([FruitID], [FruitName])
VALUES
(1, 'Apple'),
(2, 'Banana'),
(3, 'Orange'),
(4, 'Pear')
;
Insert to temp table:
SELECT A.[FruitCrateID],
Split.a.value('.', 'VARCHAR(100)') AS FruitId
INTO #fruits
FROM (SELECT [FruitCrateID],
CAST ('<M>' + REPLACE([FruitID], ';', '</M><M>') + '</M>' AS XML) AS String
FROM Fruits_Crates) AS A CROSS APPLY String.nodes ('/M') AS Split(a)
Join temp table to lookup:
SELECT t1.*, t2.FruitName
FROM #Fruits t1
INNER JOIN Fruits t2 on t1.FruitId = t2.FruitId
Results:
| FRUITCRATEID | FRUITID | FRUITNAME |
|--------------|---------|-----------|
| 1 | 1 | Apple |
| 2 | 1 | Apple |
| 2 | 2 | Banana |
| 2 | 3 | Orange |
| 2 | 4 | Pear |
| 3 | 3 | Orange |

Resources