Searching a tree using LINQ

I have a tree created from this class.

class Node
{
    public string Key { get; }
    public List<Node> Children { get; }
}

I want t开发者_运维技巧o search in all children and all their children to get the ones matching a condition:

node.Key == SomeSpecialKey

How can I implement it?

It's a misconception that this requires recursion. It will require a stack or a queue and the easiest way is to implement it using recursion. For sake of completeness I'll provide a non-recursive answer.

static IEnumerable<Node> Descendants(this Node root)
{
    var nodes = new Stack<Node>(new[] {root});
    while (nodes.Any())
    {
        Node node = nodes.Pop();
        yield return node;
        foreach (var n in node.Children) nodes.Push(n);
    }
}

Use this expression for example to use it:

root.Descendants().Where(node => node.Key == SomeSpecialKey)

If you want to maintain Linq like syntax, you can use a method to obtain all the descendants (children + children's children etc.)

static class NodeExtensions
{
    public static IEnumerable<Node> Descendants(this Node node)
    {
        return node.Children.Concat(node.Children.SelectMany(n => n.Descendants()));
    }
}

This enumerable can then be queried like any other using where or first or whatever.

Searching a Tree of Objects with Linq

public static class TreeToEnumerableEx
{
    public static IEnumerable<T> AsDepthFirstEnumerable<T>(this T head, Func<T, IEnumerable<T>> childrenFunc)
    {
        yield return head;

        foreach (var node in childrenFunc(head))
        {
            foreach (var child in AsDepthFirstEnumerable(node, childrenFunc))
            {
                yield return child;
            }
        }

    }

    public static IEnumerable<T> AsBreadthFirstEnumerable<T>(this T head, Func<T, IEnumerable<T>> childrenFunc)
    {
        yield return head;

        var last = head;
        foreach (var node in AsBreadthFirstEnumerable(head, childrenFunc))
        {
            foreach (var child in childrenFunc(node))
            {
                yield return child;
                last = child;
            }
            if (last.Equals(node)) yield break;
        }

    }
}

You can try this extension method to enumerate the tree nodes:

static IEnumerable<Node> GetTreeNodes(this Node rootNode)
{
    yield return rootNode;
    foreach (var childNode in rootNode.Children)
    {
        foreach (var child in childNode.GetTreeNodes())
            yield return child;
    }
}

Then use that with a Where() clause:

var matchingNodes = rootNode.GetTreeNodes().Where(x => x.Key == SomeSpecialKey);

Why not use an IEnumerable<T> extension method

public static IEnumerable<TResult> SelectHierarchy<TResult>(this IEnumerable<TResult> source, Func<TResult, IEnumerable<TResult>> collectionSelector, Func<TResult, bool> predicate)
{
    if (source == null)
    {
        yield break;
    }
    foreach (var item in source)
    {
        if (predicate(item))
        {
            yield return item;
        }
        var childResults = SelectHierarchy(collectionSelector(item), collectionSelector, predicate);
        foreach (var childItem in childResults)
        {
            yield return childItem;
        }
    }
}

then just do this

var result = nodes.Children.SelectHierarchy(n => n.Children, n => n.Key.IndexOf(searchString) != -1);

Perhaps you need just

node.Children.Where(child => child.Key == SomeSpecialKey)

Or, if you need to search one level deeper,

node.Children.SelectMany(
        child => child.Children.Where(child => child.Key == SomeSpecialKey))

If you need to search on all levels, take the following:

IEnumerable<Node> FlattenAndFilter(Node source)
{
    List<Node> l = new List();
    if (source.Key == SomeSpecialKey)
        l.Add(source);
    return
        l.Concat(source.Children.SelectMany(child => FlattenAndFilter(child)));
}

public class Node
    {
        string key;
        List<Node> children;

        public Node(string key)
        {
            this.key = key;
            children = new List<Node>();
        }

        public string Key { get { return key; } }
        public List<Node> Children { get { return children; } }

        public Node Find(Func<Node, bool> myFunc)
        {
            foreach (Node node in Children)
            {
                if (myFunc(node))
                {
                    return node;
                }
                else 
                {
                    Node test = node.Find(myFunc);
                    if (test != null)
                        return test;
                }
            }

            return null;
        }
    }

And then you can search like:

    Node root = new Node("root");
    Node child1 = new Node("child1");
    Node child2 = new Node("child2");
    Node child3 = new Node("child3");
    Node child4 = new Node("child4");
    Node child5 = new Node("child5");
    Node child6 = new Node("child6");
    root.Children.Add(child1);
    root.Children.Add(child2);
    child1.Children.Add(child3);
    child2.Children.Add(child4);
    child4.Children.Add(child5);
    child5.Children.Add(child6);

    Node test = root.Find(p => p.Key == "child6");

And just for fun (almost a decade later) an answer also using Generics but with a Stack and While loop, based off the accepted answer by @vidstige.

public static class TypeExtentions
{

    public static IEnumerable<T> Descendants<T>(this T root, Func<T, IEnumerable<T>> selector)
    {
        var nodes = new Stack<T>(new[] { root });
        while (nodes.Any())
        {
            T node = nodes.Pop();
            yield return node;
            foreach (var n in selector(node)) nodes.Push(n);
        }
    }

    public static IEnumerable<T> Descendants<T>(this IEnumerable<T> encounter, Func<T, IEnumerable<T>> selector)
    {
        var nodes = new Stack<T>(encounter);
        while (nodes.Any())
        {
            T node = nodes.Pop();
            yield return node;
            if (selector(node) != null)
                foreach (var n in selector(node))
                    nodes.Push(n);
        }
    }
}

Given a collection one can use like this

        var myNode = ListNodes.Descendants(x => x.Children).Where(x => x.Key == SomeKey);

or with a root object

        var myNode = root.Descendants(x => x.Children).Where(x => x.Key == SomeKey);

A while back I wrote a codeproject article which describes how to use Linq to query tree-like structures:

http://www.codeproject.com/KB/linq/LinqToTree.aspx

This provides a linq-to-XML style API where you can search descendants, children, ancestors etc...

Probably overkill for your current problem, but might be of interest to others.

You can use this extension method to query the tree.

    public static IEnumerable<Node> InTree(this Node treeNode)
    {
        yield return treeNode;

        foreach (var childNode in treeNode.Children)
            foreach (var flattendChild in InTree(childNode))
                yield return flattendChild;
    }

I have a generic extension method that can flatten any IEnumerable<T> and from that flattened collection, you can get the node you want.

public static IEnumerable<T> FlattenHierarchy<T>(this T node, Func<T, IEnumerable<T>> getChildEnumerator)
{
    yield return node;
    if (getChildEnumerator(node) != null)
    {
        foreach (var child in getChildEnumerator(node))
        {
            foreach (var childOrDescendant in child.FlattenHierarchy(getChildEnumerator))
            {
                yield return childOrDescendant;
            }
        }
    }
}

Use this like this:

var q = from node in myTree.FlattenHierarchy(x => x.Children)
        where node.Key == "MyKey"
        select node;
var theNode = q.SingleOrDefault();

I use the following implementations for enumerating Tree items

    public static IEnumerable<Node> DepthFirstUnfold(this Node root) =>
        ObjectAsEnumerable(root).Concat(root.Children.SelectMany(DepthFirstUnfold));

    public static IEnumerable<Node> BreadthFirstUnfold(this Node root) {
        var queue = new Queue<IEnumerable<Node>>();
        queue.Enqueue(ObjectAsEnumerable(root));

        while (queue.Count != 0)
            foreach (var node in queue.Dequeue()) {
                yield return node;
                queue.Enqueue(node.Children);
            }
    }

    private static IEnumerable<T> ObjectAsEnumerable<T>(T obj) {
        yield return obj;
    }

BreadthFirstUnfold in implementation above uses queue of node sequences instead of nodes queue. This is not classic BFS algorithm way.