sql recursion: find tree given middle node - tsql

I need to get a tree of related nodes given a certain node, but not necessary top node. I've got a solution using two CTEs, since I am struggling to squeeze it all into one CTE :). Might somebody have a sleek solution to avoid using two CTEs? Here is some code that I was playing with:
DECLARE #temp AS TABLE (ID INT, ParentID INT)
INSERT INTO #temp
SELECT 1 ID, NULL AS ParentID
UNION ALL
SELECT 2, 1
UNION ALL
SELECT 3, 2
UNION ALL
SELECT 4, 3
UNION ALL
SELECT 5, 4
UNION ALL
SELECT 6, NULL
UNION ALL
SELECT 7, 6
UNION ALL
SELECT 8, 7
DECLARE #startNode INT = 4
;WITH TheTree (ID,ParentID)
AS (
SELECT ID, ParentID
FROM #temp
WHERE ID = #startNode
UNION ALL
SELECT t.id, t.ParentID
FROM #temp t
JOIN TheTree tr ON t.ParentID = tr.ID
)
SELECT * FROM TheTree
;WITH Up(ID,ParentID)
AS (
SELECT t.id, t.ParentID
FROM #temp t
WHERE t.ID = #startNode
UNION ALL
SELECT t.id, t.ParentID
FROM #temp t
JOIN Up c ON t.id = c.ParentID
)
--SELECT * FROM Up
,TheTree (ID,ParentID)
AS (
SELECT ID, ParentID
FROM Up
WHERE ParentID is null
UNION ALL
SELECT t.id, t.ParentID
FROM #temp t
JOIN TheTree tr ON t.ParentID = tr.ID
)
SELECT * FROM TheTree
thanks

Meh. This avoids using two CTEs, but the result is a brute force kludge that hardly qualifies as "sleek" as it won’t be efficient if your table is at all sizeable. It will:
Recursively build all possible hierarchies
As you build them, flag the target NodeId as you find it
Return only the targeted tree
I threw in column “TreeNumber” on the off-chance the TargetId appears in multiple hierarchies, or if you’d ever have multiple values to check in one pass. “Depth” was added to make the output a bit more legible.
A more complex solution like #John’s might do, and more and subtler tricks could be done with more detailed table sturctures.
DECLARE #startNode INT = 4
;WITH cteAllTrees (TreeNumber, Depth, ID, ParentID, ContainsTarget)
AS (
SELECT
row_number() over (order by ID) TreeNumber
,1
,ID
,ParentID
,case
when ID = #startNode then 1
else 0
end ContainsTarget
FROM #temp
WHERE ParentId is null
UNION ALL
SELECT
tr.TreeNumber
,tr.Depth + 1
,t.id
,t.ParentID
,case
when tr.ContainsTarget = 1 then 1
when t.ID = #startNode then 1
else 0
end ContainsTarget
FROM #temp t
INNER JOIN cteAllTrees tr
ON t.ParentID = tr.ID
)
SELECT
TreeNumber
,Depth
,ID
,ParentId
from cteAllTrees
where TreeNumber in (select TreeNumber from cteAllTrees where ContainsTarget = 1)
order by
TreeNumber
,Depth
,ID

Here is a technique where you can select the entire hierarchy, a specific node with all its children, and even a filtered list and how they roll.
Note: See the comments next to the DECLAREs
Declare #YourTable table (id int,pt int,name varchar(50))
Insert into #YourTable 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 2
Declare #Nest varchar(25) = '|-----' --<< Optional: Added for readability
Declare #Filter varchar(25) = '' --<< Empty for All or try 4,6
;with cteP as (
Select Seq = cast(1000+Row_Number() over (Order by name) as varchar(500))
,ID
,pt
,Lvl=1
,name
From #YourTable
Where IsNull(#Top,-1) = case when #Top is null then isnull(pt,-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.pt
,p.Lvl+1
,r.name
From #YourTable r
Join cteP p on r.pt = 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.pt
,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

Related

Delete duplicate rows with different values in columns

I didn't find my case on the Internet. Tell me how i can delete duplicates if the values are in different columns.
I have a table with a lot of values, for example:
|Id1|Id2|
|89417980|89417978|
|89417980|89417979|
|89417978|89417980|
|89417979|89417980|
I need to exclude duplicates and leave in the answer only:
|Id1|Id2|
|89417980|89417978|
|89417980|89417979|
min/max does not work here, as the values may be different.
I tried to union/join tables on a table/exclude results with temporary tables, but in the end I come to the beginning.
Assuming id1 and id2 are primary keys columns you could try this
DECLARE #tbl table (id1 int, id2 int )
INSERT INTO #tbl
SELECT 89417980, 89417978
UNION SELECT 89417980, 89417979
UNION SELECT 89417978, 89417980
UNION SELECT 89417979, 89417980
SELECT * FROM #tbl
;WITH CTE AS (--Get comparable value as "cs"
SELECT
IIF(id1 > id2, CHECKSUM(id1, id2), CHECKSUM(id2,id1)) as cs
, id1
, id2
, ROW_NUMBER() OVER (order by id1, id2) as rn
FROM #tbl
)
, CTE2 AS ( --Get rows to keep
SELECT MAX (rn) as rn
FROM CTE
GROUP BY cs
HAVING COUNT(*) > 1
)
DELETE tbl -- Delete all except the rows to keep
FROM #tbl tbl
WHERE NOT EXISTS(SELECT 1
FROM CTE2
JOIN CTE ON CTE.rn = CTE2.rn
WHERE CTE.id1 = tbl.id1
AND CTE.id2 = tbl.id2
)
SELECT * FROM #tbl

sql compare columns to get result

I have the following issue. I have products with 3 different states. Parent, Child and products which are orphans. I am setting Parents as 1, Children as 2 and Orphans as 0. I am struggling to get the Orphan to set to 0. I realise that counting the amount of Parent PLU's is where I am going wrong but I do not know how to resolve this issue. Any help would be appreciated. (As you maybe able to tell, I am a noob and constructive criticism would be appreciated)
Kind Regards,
Jason.
Picture of results from query
declare #OrderID int = 1635
declare #Store char(3) = '001'
declare #SortedBy smallint = 2
DECLARE #tbl TABLE (DetailID int, OrderID int, PLU nvarchar(35), ParentPLU nvarchar(35))
INSERT INTO #tbl (DetailID, OrderID, PLU, ParentPLU)
SELECT DetailID, OrderDetails.OrderID, OrderDetails.PLU, OrderDetails.ParentPLU
FROM OrderDetails
INNER JOIN PLU
ON PLU.PLU = OrderDetails.PLU
WHERE OrderDetails.OrderID = #OrderID
AND OrderDetails.OrderStore = #Store
SELECT DetailID, OrderID, PLU, ParentPLU,
CASE WHEN ( SELECT COUNT(DISTINCT ParentPLU)
FROM #tbl
WHERE ParentPLU IN (SELECT PLU FROM #tbl)
) > 0 AND ParentPLU = '' THEN 1
WHEN ( SELECT COUNT(DISTINCT ParentPLU)
FROM #tbl
WHERE ParentPLU IN (SELECT PLU FROM #tbl)
) > 0 THEN 2
ELSE
0
END AS ParentChild,
ROW_NUMBER() OVER (ORDER BY
CASE WHEN #SortedBy = 1 THEN OrderID END ASC,
CASE WHEN #SortedBy = 2 THEN DetailID END ASC
) AS ID
FROM #tbl
You can use coalesce to get your desired result. First subquery checks for parent state, second for children. If both are null, then it is orphan
select
DetailID, OrderID, PLU, ParentPLU
, coalesce((
select
distinct 1
from
#tbl b
where
a.PLU = b.ParentPlu
)
, (
select
distinct 2
from
#tbl b
where
b.PLU = a.ParentPlu
), 0)
from
#tbl a

postgres hierarchy - count of child levels and sort by date of children or grandchildren

I would like to know how to write a postgres subquery so that the following table example will output what I need.
id parent_id postdate
1   -1 2015-03-10
2     1 2015-03-11 (child level 1)
3     1 2015-03-12 (child level 1)
4     3 2015-03-13 (child level 2)
5    -1 2015-03-14
6    -1 2015-03-15
7     6 2015-03-16 (child level 1)
If I want to sort all the root ids by child level 1 with a count of children(s) from the parent, the output would be something like this
id count  date
6   2    2015-03-15
1   4    2015-03-10
5   1    2015-03-14
The output is sorted by postdate based on the root's child. The 'date' being outputted is the date of the root's postdate. Even though id#5 has a more recent postdate, the rootid#6's child (id#7) has the most recent postdate because it is being sorted by child's postdate. id#5 doesnt have any children so it just gets placed at the end, sorted by date. The 'count' is the number children(child level 1), grandchildren(child level 2) and itself (root). For instance, id #2,#3,#4 all belong to id#1 so for id#1, the count would be 4.
My current subquery thus far:
SELECT p1.id,count(p1.id),p1.postdate
FROM mytable p1
LEFT JOIN mytable c1 ON c1.parent_id = p1.id AND p1.parent_id = -1
LEFT JOIN mytable c2 ON c2.parent_id = c1.id AND p1.parent_id = -1
GROUP BY p1.id,c1.postdate,p1.postdate
ORDER by c1.postdate DESC,p1.postdate DESC
create table mytable ( id serial primary key, parent_id int references mytable, postdate date );
create index mytable_parent_id_idx on mytable (parent_id);
insert into mytable (id, parent_id, postdate) values (1, null, '2015-03-10');
insert into mytable (id, parent_id, postdate) values (2, 1, '2015-03-11');
insert into mytable (id, parent_id, postdate) values (3, 1, '2015-03-12');
insert into mytable (id, parent_id, postdate) values (4, 3, '2015-03-13');
insert into mytable (id, parent_id, postdate) values (5, null, '2015-03-14');
insert into mytable (id, parent_id, postdate) values (6, null, '2015-03-15');
insert into mytable (id, parent_id, postdate) values (7, 6, '2015-03-16');
with recursive recu as (
select id as parent, id as root, null::date as child_postdate
from mytable
where parent_id is null
union all
select r.parent, mytable.id, mytable.postdate
from recu r
join mytable
on parent_id = r.root
)
select m.id, c.cnt, m.postdate, c.max_child_date
from mytable m
join ( select parent, count(*) as cnt, max(child_postdate) as max_child_date
from recu
group by parent
) c on c.parent = m.id
order by c.max_child_date desc nulls last, m.postdate desc;
You'll need a recursive query to count the elements in the subtrees:
WITH RECURSIVE opa AS (
SELECT id AS par
, id AS moi
FROM the_tree
WHERE parent_id IS NULL
UNION ALL
SELECT o.par AS par
, t.id AS moi
FROM opa o
JOIN the_tree t ON t.parent_id = o.moi
)
SELECT t.id
, c.cnt
, t.postdate
FROM the_tree t
JOIN ( SELECT par, COUNT(*) AS cnt
FROM opa o
GROUP BY par
) c ON c.par = t.id
ORDER BY t.id
;
UPDATE (it appears the OP also wants the maxdate per tree)
-- The same, but also select the postdate
-- --------------------------------------
WITH RECURSIVE opa AS (
SELECT id AS par
, id AS moi
, postdate AS postdate
FROM the_tree
WHERE parent_id IS NULL
UNION ALL
SELECT o.par AS par
, t.id AS moi
-- , GREATEST(o.postdate,t.postdate) AS postdate
, t.postdate AS postdate
FROM opa o
JOIN the_tree t ON t.parent_id = o.moi
)
SELECT t.id
, c.cnt
, t.postdate
, c.maxdate
FROM the_tree t
JOIN ( SELECT par, COUNT(*) AS cnt
, MAX(o.postdate) AS maxdate -- and obtain the max()
FROM opa o
GROUP BY par
) c ON c.par = t.id
ORDER BY c.maxdate, t.id
;
After looking at everyone's code, I created the subquery I needed. I can use PHP to vary the 'case when' code depending on the user's sort selection. For instance, the code below will sort the root nodes based on child level 1's postdate.
with recursive cte as (
select id as parent, id as root, null::timestamp as child_postdate,0 as depth
from mytable
where parent_id = -1
union all
select r.parent, mytable.id, mytable.postdate,depth+1
from cte r
join mytable
on parent_id = r.root
)
select m.id, c.cnt, m.postdate
from ssf.dtb_021 m
join ( select parent, count(*) as cnt, max(child_postdate) as max_child_date,depth
from cte
group by parent,depth
) c on c.parent = m.id
order by
case
when depth=2 then 1
when depth=1 then 2
else 0
end DESC,
c.max_child_date desc nulls last, m.postdate desc;
select
p.id,
(1+c.n) as parent_post_plus_number_of_subposts,
p.postdate
from
table as p
inner join
(
select
parent_id, count(*) as n, max(postdate) as _postdate
from table
group by parent_id
) as c
on p.id = c.parent_id
where p.parent_id = -1
order by c._postdate desc

How to set the “Order” of Items in a hierarchy table in an easier and shorter way?

Refering to this post, here is the overall question and codes:
declare #tbl table (MenuItemID uniqueidentifier, PID uniqueidentifier, MenuID uniqueidentifier, SO tinyint, lvl tinyint)
;WITH
cte (MenuItemID, PID, MenuID, SO, lvl) AS
(
select MenuItemID, PID, MenuID, SO, 0 from MenuItems
where del = 0 and Perms = 1 and MenuID = #MenuID and MenuID = PID
UNION ALL
SELECT MenuItems.MenuItemID, MenuItems.PID, MenuItems.MenuID, MenuItems.SO, cte.lvl + 1 FROM MenuItems
JOIN cte ON cte.MenuItemID = MenuItems.PID
)
select * from cte
ORDER BY lvl, SO
insert into #tbl select * from cte
declare #tbl2 table (MenuItemID uniqueidentifier, PID uniqueidentifier, MenuID uniqueidentifier, SO tinyint, lvl tinyint)
;with hier (MenuItemID, PID, MenuID, SO, lvl, FullSO) as
(select l0.*, convert(varchar(max),right('000'+convert(varchar(3),SO),3)) FullSO
from #tbl l0 where lvl=0
union all
select ln.*, lp.FullSO+','+right('000'+convert(varchar(3),ln.SO),3) FullSO
from #tbl ln
join hier lp on ln.PID = lp.MenuItemID)
insert into #tbl2
select MenuItemID,
PID,
MenuID,
rank() over (partition by PID order by SO) SO,
lvl
from hier
order by FullSO, SO
update MenuItems set SO = h.SO
from MenuItems as mi
join #tbl2 h on mi.MenuItemID = h.MenuItemID and mi.MenuID = h.MenuID
I'd like to know whether there is an easier and shorter way for this code?
Thanks in advance,
Kardo
You will still need a recursive CTE to determine which top-level records for the hierarchy have del = 0 and Perms = 1, but the following should be simpler:
WITH cte AS
(select MenuItemID, PID, MenuID, SO,
rank() over (partition by PID order by SO) newSO
from MenuItems
where del = 0 and Perms = 1 and MenuID = #MenuID and MenuID = PID
UNION ALL
SELECT m.MenuItemID, m.PID, m.MenuID, m.SO,
rank() over (partition by m.PID order by m.SO) newSO
FROM MenuItems m
JOIN cte c ON c.MenuItemID = m.PID
)
update MenuItems set SO = h.newSO
from MenuItems as mi
join cte h on mi.MenuItemID = h.MenuItemID and mi.MenuID = h.MenuID;
SQLFiddle here.

t-sql WITH on WITH

I have to make query on WITH query, something like
; WITH #table1
(
SELECT id, x from ... WHERE....
UNION ALL
SELECT id, x from ... WHERE...
)
WITH #table2
(
SELECT DISTINCT tbl_x.*,ROW_NUMBER() OVER (order by id) as RowNumber
WHERE id in ( SELECT id from #table1)
)
SELECT * FROM #table2 WHERE RowNumber > ... and ...
So I have to use WITH on WITH and then SELECT on second WITH, How I can do that?
You can define multiple CTEs after the WITH keyword by separating each CTE with a comma.
WITH T1 AS
(
SELECT id, x from ... WHERE....
UNION ALL
SELECT id, x from ... WHERE...
)
, T2 AS
(
SELECT DISTINCT tbl_x.*, ROW_NUMBER() OVER (order by id) as RowNumber
WHERE id in ( SELECT id from T1 )
)
SELECT * FROM T2 WHERE RowNumber > ... and ...
https://web.archive.org/web/20210927200924/http://www.4guysfromrolla.com/webtech/071906-1.shtml