How to join first two child records to parent? - sql-server

I am trying to select the top 25 parent records and join to it the first two child records ordered by date. The parent record can have 0 to n children.
The end result would be something like:
P1, C1, C2
P2, C1, C2
...
P25, C1, C2
I have found an example using max date, but I am having trouble getting a specific row number
select top 25 *
from parentTable p
left join childTable c
on p.Key = c.Key
and c.dateColumn = (
select Max(c.dateColumn)
from c
where p.Key = c.Key
)

You should be able to get what you are looking for using ROW_NUMBER():
WITH c AS
(
SELECT ROW_NUMBER() OVER (PARTITION BY [key] ORDER BY [date] asc) as rn
,[key]
,[date]
from child
)
SELECT top 25 p.[key], c1.[key], c1.[date], c2.[key], c2.[date]
FROM parent p
LEFT JOIN c c1
ON p.[key] = c1.[key]
AND c1.rn = 1
LEFT JOIN c c2
ON p.[key] = c2.[key]
AND c2.rn = 2
Check SQLFiddle for test data/results

You can use CTE.
;with cte as (
select top (25) *
from parentTable
)
select *
from cte p
left join childTable c
on p.[Key] = c.[Key];

First solution (because data set seems to be small) one solution is to use OUTER APPLY:
select top (25) ... columns ...
from parentTable p
outer apply (
select top (2) ... columns ...
from childTable c
where p.[Key] = c.[Key]
order by c.dateColumn desc -- asc ?
) a
-- Most of the times, when top filter is used order by clause should be also used
order by p.dateColumn desc -- asc ?
-- order by p.idColumn desc -- asc ?
Second solution (could be less eficient):
select top (25) ... columns ...
from parentTable p
left join (
select top (2) ... columns ..., ROW_NUMBER() over(partition by c.[Key] order by c.dateColumn desc) as rn -- asc ?
from childTable c
) a on p.[Key] = a.[Key] and a.rn < 3
-- Most of the times, when top filter is used order by clause should be also used
order by p.dateColumn desc -- asc ?
-- order by p.idColumn desc -- asc ?
Note: at least for the first solution one of following indices could help from the point of view of performance:
create index ix_name on dbo.childTable ([Key], [dateColumn])
--or
create index ix_name on dbo.childTable ([Key], [dateColumn])
include (... columns from select top(2) clause ...)

Related

Return only rows from the joined table with the latest date

By running the following query I realized that I have duplicates on the column QueryExecutionId.
SELECT DISTINCT qe.QueryExecutionid AS QueryExecutionId,
wfi.workflowdefinitionid AS FlowId,
qe.publishing_date AS [Date],
c.typename AS [Type],
c.name As Name
INTO #Send
FROM
[QueryExecutions] qe
JOIN [Campaign] c ON qe.target_campaign_id = c.campaignid
LEFT JOIN [WorkflowInstanceCampaignActivities] wfica ON wfica.queryexecutionresultid = qe.executionresultid
LEFT JOIN [WorkflowInstances] wfi ON wfica.workflowinstanceid = wfi.workflowinstanceid
WHERE qe.[customer_idhash] IS NOT NULL;
E.g. When I test with one of these QueryExecutionIds, I can two results
select * from ##Send
where QueryExecutionId = 169237
We realized the reason is that these two rows have a different FlowId (second returned value in the first query). After discussing this issue, we decided to take the record with a FlowId that has the latest date. This date is a column called lastexecutiontime that sits in the third joined table [WorkflowInstances] which is also the table where FlowId comes from.
How do I only get unique values of QueryExecutionId with the latest value of WorkflowInstances.lastexecution time and remove the duplicates?
You can use a derived table with first_value partitioned by workflowinstanceid ordered by lastexecutiontime desc:
SELECT DISTINCT qe.QueryExecutionid AS QueryExecutionId,
wfi.FlowId,
qe.publishing_date AS [Date],
c.typename AS [Type],
c.name As Name
INTO #Send
FROM
[QueryExecutions] qe
JOIN [Campaign] c ON qe.target_campaign_id = c.campaignid
LEFT JOIN [WorkflowInstanceCampaignActivities] wfica ON wfica.queryexecutionresultid = qe.executionresultid
LEFT JOIN
(
SELECT DISTINCT workflowinstanceid, FIRST_VALUE(workflowdefinitionid) OVER(PARTITION BY workflowinstanceid ORDER BY lastexecutiontime DESC) As FlowId
FROM [WorkflowInstances]
) wfi ON wfica.workflowinstanceid = wfi.workflowinstanceid
WHERE qe.[customer_idhash] IS NOT NULL;
Please note that your distinct query is pertaining to the selected variables,
eg. Data 1 (QueryExecutionId = 169237 and typename = test 1)
    Data 2 (QueryExecutionId = 169237 and typename = test 2)
The above 2 data are considered as distinct
Try partition by and selection the [seq] = 1 (the below code are partition by their date)
SELECT *
into #Send
FROM
(
SELECT *,ROW_NUMBER() OVER (PARTITION BY [QueryExecutionid] ORDER BY [Date] DESC) [Seq]
FROM
(
SELECT qe.QueryExecutionid AS QueryExecutionId,
wfi.FlowId,
qe.publishing_date AS [Date], --should not have any null values
qe.[customer_idhash]
c.typename AS [Type],
c.name As Name
FROM [QueryExecutions] qe
JOIN [Campaign] c
ON qe.target_campaign_id = c.campaignid
LEFT JOIN [WorkflowInstanceCampaignActivities] wfica
ON wfica.queryexecutionresultid = qe.executionresultid
LEFT JOIN
(
SELECT DISTINCT workflowinstanceid, FIRST_VALUE(workflowdefinitionid) OVER(PARTITION BY workflowinstanceid ORDER BY lastexecutiontime DESC) As FlowId
FROM [WorkflowInstances]
) wfi ON wfica.workflowinstanceid = wfi.workflowinstanceid
) a
WHERE [customer_idhash] IS NOT NULL
) b
WHERE [Seq] = 1
ORDER BY [QueryExecutionid]

SQL Simple Join with two tables, but one is random

I am stuck with this. I have a simple set-up with two tables. One table is holding emailaddresses one table is holding vouchercodes. I want to join them in a third table, so that each emailaddress has one random vouchercode.
Unfortunatly I am stuck with this as there are no identic Ids to match both values. What I have so far brings no result:
Select
A.Email
B.CouponCode
FROM Emailaddresses as A
JOIN CouponCodes as B
on A.Email = B.CouponCode
A hint would be great as search did not bring me any further yet.
Edit -
Table A (Addresses)
-------------------
Column A | Column B
-------------------------
email1#gmail.com True
email2#gmail.com
email3#gmail.com True
email4#gmail.com
Table B (Voucher)
-------------------
ABCD1234
ABCD5678
ABCD9876
ABCD5432
Table C
-------------------------
column A | column B
-------------------------
email1#gmail.com ABCD1234
email2#gmail.com ABCD5678
email3#gmail.com ABCD9876
email4#gmail.com ABCD5432
Sample Data:
While joining without proper keys is not a good solution, for your case you can try this. (note: not tested, just a quick suggestion)
;with cte_email as (
select row_number() over (order by Email) as rownum, Email
from Emailaddresses
)
;with cte_coupon as (
select row_number() over (order by CouponCode) as rownum, CouponCode
from CouponCodes
)
select a.Email,b.CouponCode
from cte_email a
join cte_coupon b
on a.rownum = b.rownum
You want to randomly join records, one email with one coupon each. So create random row numbers and join on these:
select
e.email,
c.couponcode
from (select t.*, row_number() over (order by newid()) as rn from emailaddresses t) e
join (select t.*, row_number() over (order by newid()) as rn from CouponCodes t) c
on c.rn = e.rn;
Give a row number for both the tables and join it with row number.
Query
;with cte as(
select [rn] = row_number() over(
order by [Column_A]
), *
from [Table_A]
),
cte2 as(
select [rn] = row_number() over(
order by [Column_A]
), *
from [Table_B]
)
select t1.[Column_A] as [Email_Id], t2.[Column_A] as [Coupon]
from cte t1
join cte2 t2
on t1.rn = t2.rn;
Find a demo here

Get full hierarchy by children

I have 2 tables:
contains full tree data
contains only specific childs
I need to get full hierarchy by child values. I can do it by one specific child node by following way:
;with tree as
(
select id, parent_id, name, level from f_all where id = #specefic_id
union all
select f.id, f.parent_id, f.name, f.level from f_all f
inner join tree t on f.id = t.parent_id and f.id <> f.parent_id
)
select *
from tree
OPTION (Maxrecursion 0)
I have an idea but I think it is not good. My idea is create function with above code. And call it by select my second table. I even didn't try it. Can you give me a right direction.
This is 2012+ ( Using concat() ... easily converted ).
Declare #f_all table (id int,parent_id int,name varchar(50))
Insert into #f_all values
(1,null,'1'),(2,1,'2'),(3,1,'3'),(4,2,'4'),(5,2,'5'),(6,3,'6'),(7,null,'7'),(8,7,'8')
Declare #Top int = null --<< Sets top of Hier Try 9
Declare #Nest varchar(25) = '|-----' --<< Optional: Added for readability
Declare #Filter varchar(25) = '4,6' --<< Empty for All or try 4,6
;with cteP as (
Select Seq = cast(1000+Row_Number() over (Order by name) as varchar(500))
,ID
,parent_id
,Lvl=1
,name
From #f_all
Where IsNull(#Top,-1) = case when #Top is null then isnull(parent_id,-1) else ID end
Union All
Select Seq = cast(concat(p.Seq,'.',1000+Row_Number() over (Order by r.name)) as varchar(500))
,r.ID
,r.parent_id
,p.Lvl+1
,r.name
From #f_all r
Join cteP p on r.parent_id = p.ID)
,cteR1 as (Select *,R1=Row_Number() over (Order By Seq) From cteP)
,cteR2 as (Select A.Seq,A.ID,R2=Max(B.R1) From cteR1 A Join cteR1 B on (B.Seq like A.Seq+'%') Group By A.Seq,A.ID )
Select Distinct
A.R1
,B.R2
,A.ID
,A.parent_id
,A.Lvl
,name = Replicate(#Nest,A.Lvl-1) + A.name
From cteR1 A
Join cteR2 B on A.ID=B.ID
Join (Select R1 From cteR1 where IIF(#Filter='',1,0)+CharIndex(concat(',',ID,','),concat(',',#Filter+','))>0) F on F.R1 between A.R1 and B.R2
Order By A.R1
Returns (#Top=null and #Filter='4,6')
Return Full Hier (#Top=null and #Filter='')
Returns Just a portion (#Top=2 and #Filter='')
The problem for me was that i didn't know how cte recursion works. Now i know how it works line by line: Recursive Queries Using Common Table Expressions.
Code below returns all hierarchy by children nodes:
;with tree as(
select id, parent_id, name, level from f_all fa
inner join #2nd_table_cildren_id c on c.id = fa.id
union all
select f.id, f.parent_id, f.name, f.level from f_all f
inner join tree t on f.id = t.parent_id and f.id <> f.parent_id
)
select distinct *
from tree
OPTION (Maxrecursion 0)

How do i get the next value and previous in a column

Suppose i have an ID column that has the values 1 , 5 , 7 .What SQL statement can i use to get the next value of in the column based on another.
Example : The next value after 1 is 5.
Example 2 : the value before 7 is 5
Without any window functions or CTEs:
select
t.id,
(select max(t1.id) from tbl t1 where t1.id < t.id) as previd,
(select min(t2.id) from tbl t2 where t2.id > t.id) as nextid
from tbl t
There are some great Windowed functions for working across records in later versions of SQL Server (2012+). But in 2008 these aren't available. Instead you could use an OUTER APPLY. This will allow you to filter a sub query using values from your main query.
Outer Apply Query Example
WITH SampleValues AS
(
/* This CTE creates some sample values.
*/
SELECT
r.n
FROM
(
VALUES
(1),
(5),
(7)
) AS r(n)
)
SELECT
o.n,
prev.Previous_n,
[next].Next_n
FROM
SampleValues AS o
OUTER APPLY
(
-- Find the previou value by looking for the TOP 1 before the current.
SELECT TOP 1
o.n AS Original_n,
p.n AS Previous_n
FROM
SampleValues AS p
WHERE
p.n < o.n
ORDER BY
p.n DESC
) AS prev
OUTER APPLY
(
-- Find the next value by looking for the TOP 1 after the current.
SELECT TOP 1
n.n AS Original_n,
n.n AS Next_n
FROM
SampleValues AS n
WHERE
n.n > o.n
ORDER BY
n.n ASC
)AS [next]
;

SQL Server Full Text Search - Weighting Certain Columns Over Others

If I have the following full text search query:
SELECT *
FROM dbo.Product
INNER JOIN CONTAINSTABLE(Product, (Name, Description, ProductType), 'model') ct
ON ct.[Key] = Product.ProductID
Is it possible to weigh the columns that are being searched?
For example, I care more about the word model appearing in the Name column than I do the
Description or ProductType columns.
Of course if the word is in all 3 columns then I would expect it to rank higher than if it was just in the name column. Is there any way to have a row rank higher if it just appears in Name vs just in Description/ProductType?
You can do something like the following query. Here, WeightedRank is computed by multiplying the rank of the individual matches. NOTE: unfortunately I don't have Northwind installed so I couldn't test this, so look at it more like pseudocode and let me know if it doesn't work.
declare #searchTerm varchar(50) = 'model';
SELECT 100 * coalesce(ct1.RANK, 0) +
10 * coalesce(ct2.RANK, 0) +
1 * coalesce(ct3.RANK, 0) as WeightedRank,
*
FROM dbo.Product
LEFT JOIN
CONTAINSTABLE(Product, Name, #searchTerm) ct1 ON ct1.[Key] = Product.ProductID
LEFT JOIN
CONTAINSTABLE(Product, Description, #searchTerm) ct2 ON ct2.[Key] = Product.ProductID
LEFT JOIN
CONTAINSTABLE(Product, ProductType, #searchTerm) ct3 ON ct3.[Key] = Product.ProductID
order by WeightedRank desc
Listing 3-25. Sample Column Rank-Multiplier Search of Pro Full-Text Search in SQL Server 2008
SELECT *
FROM (
SELECT Commentary_ID
,SUM([Rank]) AS Rank
FROM (
SELECT bc.Commentary_ID
,c.[RANK] * 10 AS [Rank]
FROM FREETEXTTABLE(dbo.Contributor_Birth_Place, *, N'England') c
INNER JOIN dbo.Contributor_Book cb ON c.[KEY] = cb.Contributor_ID
INNER JOIN dbo.Book_Commentary bc ON cb.Book_ID = bc.Book_ID
UNION ALL
SELECT c.[KEY]
,c.[RANK] * 5
FROM FREETEXTTABLE(dbo.Commentary, Commentary, N'England') c
UNION ALL
SELECT ac.[KEY]
,ac.[RANK]
FROM FREETEXTTABLE(dbo.Commentary, Article_Content, N'England') ac
) s
GROUP BY Commentary_ID
) s1
INNER JOIN dbo.Commentary c1 ON c1.Commentary_ID = s1.Commentary_ID
ORDER BY [Rank] DESC;
Similar to Henry's solution but simplified, tested and using the details the question provided.
NB: I ran performance tests on both the union and left join styles and found the below to require far less logical reads on the union style below with my datasets YMMV.
declare #searchTerm varchar(50) = 'model';
declare #nameWeight int = 100;
declare #descriptionWeight int = 10;
declare #productTypeWeight int = 1;
SELECT ranksGroupedByProductID.*, outerProduct.*
FROM (SELECT [key],
Sum([rank]) AS WeightedRank
FROM (
-- Each column that needs to be weighted separately
-- should be added here and unioned with the other queries
SELECT [key],
[rank] * #nameWeight as [rank]
FROM Containstable(dbo.Product, [Name], #searchTerm)
UNION ALL
SELECT [key],
[rank] * #descriptionWeight as [rank]
FROM Containstable(dbo.Product, [Description], #searchTerm)
UNION ALL
SELECT [key],
[rank] * #productTypeWeight as [rank]
FROM Containstable(dbo.Product, [ProductType], #searchTerm)
) innerSearch
-- Grouping by key allows us to sum each ProductID's ranks for all the columns
GROUP BY [key]) ranksGroupedByProductID
-- This join is just to get the full Product table columns
-- and is optional if you only need the ordered ProductIDs
INNER JOIN dbo.Product outerProduct
ON outerProduct.ProductID = ranksGroupedByProductID.[key]
ORDER BY WeightedRank DESC;

Resources