How to group hierarchical relationships together in SQL Server

Question

I have a column name Parent and Child in table Example and Below is the Table Data

|     Parent          |         


        

Answer 1

The problem with your attempt is filtering at the start. If I'm right, your want to cluster your data (group them all together) by their relationships, either ascendant or descendant, or a mix of them. For example ID 100 has child 101, which has another child 102, but 102 has a parent 103 and you want the result to be these four (100, 101, 102, 103) for any input that is in that set. This is why you can't filter at the start, since you don't have any means of knowing which relationship will be chained throughout another relationship.

Solving this isn't as simple as it seems and you won't be able to solve it with just 1 recursion.

The following is a solution I made long time ago to group all these relationships together. Keep in mind that, for large datasets (over 100k), it might take a while to calculate, since it has to identify all groups first, and select the result at the end.

CREATE PROCEDURE GetAncestors(@thingID INT)
AS
BEGIN

    SET NOCOUNT ON

    -- Load your data
    IF OBJECT_ID('tempdb..#TreeRelationship') IS NOT NULL
        DROP TABLE #TreeRelationship

    CREATE TABLE #TreeRelationship (
        RelationID INT IDENTITY(1,1) PRIMARY KEY NONCLUSTERED,
        Parent INT,
        Child INT,
        GroupID INT)

    INSERT INTO #TreeRelationship (
        Parent,
        Child)
    SELECT
        Parent = D.Parent,
        Child = D.Child
    FROM
        Example AS D
    UNION -- Data has to be loaded in both ways (direct and reverse) for algorithm to work correctly
    SELECT
        Parent = D.Child,
        Child = D.Parent
    FROM
        Example AS D   


    -- Start algorithm
    IF OBJECT_ID('tempdb..#FirstWork') IS NOT NULL
        DROP TABLE #FirstWork

    CREATE TABLE #FirstWork (
        Parent INT,
        Child INT,
        ComponentID INT)

    CREATE CLUSTERED INDEX CI_FirstWork ON #FirstWork (Parent, Child)

    INSERT INTO #FirstWork (
        Parent, 
        Child,
        ComponentID)
    SELECT DISTINCT 
        Parent = T.Parent,
        Child = T.Child, 
        ComponentID = ROW_NUMBER() OVER (ORDER BY T.Parent, T.Child)
    FROM 
        #TreeRelationship AS T


    IF OBJECT_ID('tempdb..#SecondWork') IS NOT NULL
        DROP TABLE #SecondWork

    CREATE TABLE #SecondWork (
        Component1 INT,
        Component2 INT)

    CREATE CLUSTERED INDEX CI_SecondWork ON #SecondWork (Component1)


    DECLARE @v_CurrentDepthLevel INT = 0

    WHILE @v_CurrentDepthLevel < 100 -- Relationships depth level can be controlled with this value
    BEGIN

        SET @v_CurrentDepthLevel = @v_CurrentDepthLevel + 1

        TRUNCATE TABLE #SecondWork

        INSERT INTO #SecondWork (
            Component1,
            Component2)
        SELECT DISTINCT
            Component1 = t1.ComponentID,
            Component2 = t2.ComponentID
        FROM 
            #FirstWork t1
            INNER JOIN #FirstWork t2 on 
                t1.child = t2.parent OR 
                t1.parent = t2.parent
        WHERE
            t1.ComponentID <> t2.ComponentID

        IF (SELECT COUNT(*) FROM #SecondWork) = 0
            BREAK

        UPDATE #FirstWork SET 
            ComponentID = CASE WHEN items.ComponentID < target THEN items.ComponentID ELSE target END
        FROM 
            #FirstWork items
            INNER JOIN (
                SELECT
                    Source = Component1, 
                    Target = MIN(Component2)
                FROM
                    #SecondWork
                GROUP BY
                    Component1
            ) new_components on new_components.source = ComponentID


        UPDATE #FirstWork SET
            ComponentID = target
        FROM #FirstWork items
            INNER JOIN(
                SELECT
                    source = component1, 
                    target = MIN(component2)
                FROM
                    #SecondWork
                GROUP BY
                    component1
            ) new_components ON new_components.source = ComponentID

    END

    ;WITH Groupings AS
    (
        SELECT 
            parent,
            child,
            group_id = DENSE_RANK() OVER (ORDER BY ComponentID  DESC)
        FROM
            #FirstWork
    )
    UPDATE FG SET
        GroupID = IT.group_id
    FROM
        #TreeRelationship FG
        INNER JOIN Groupings IT ON
            IT.parent = FG.parent AND
            IT.child = FG.child


    -- Select the proper result
    ;WITH IdentifiedGroup AS
    (
        SELECT TOP 1
            T.GroupID
        FROM
            #TreeRelationship AS T
        WHERE
            T.Parent = @thingID
    )
    SELECT DISTINCT
        Result = T.Parent
    FROM
        #TreeRelationship AS T
        INNER JOIN IdentifiedGroup AS I ON T.GroupID = I.GroupID

END

You will see that for @thingID of value 100, 101, 102 and 103 the result are these four, and for values 200, 201 and 202 the results are these three.

I'm pretty sure this isn't an optimal solution, but it gives the correct output and I never had the need to tune it up since it works fast for my requirements.