我有一个收藏:
List<VPair<Item, List<Item>> dependencyHierarchy;
pair 中的第一个项目是某个对象(项目),第二个项目是第一个项目所依赖的相同类型对象的集合。我想按依赖顺序获得
List<Item>
,因此不存在依赖于第一个元素的项目,依此类推(没有循环依赖!)。
输入:
Item4 依赖于 Item3 和 Item5 Item3 取决于 Item1 Item1不依赖于任何一个 项目 2 取决于项目 4 第5项不依赖于任何一项
结果:
项目1 项目5 项目3 项目4 项目2
谢谢你。
解决方案:
拓扑排序(感谢 Loïc Février 的想法)
和
在这个问题上挣扎了一段时间,这是我对 Linq 风格的 TSort 扩展方法的尝试:
public static IEnumerable<T> TSort<T>( this IEnumerable<T> source, Func<T, IEnumerable<T>> dependencies, bool throwOnCycle = false )
{
var sorted = new List<T>();
var visited = new HashSet<T>();
foreach( var item in source )
Visit( item, visited, sorted, dependencies, throwOnCycle );
return sorted;
}
private static void Visit<T>( T item, HashSet<T> visited, List<T> sorted, Func<T, IEnumerable<T>> dependencies, bool throwOnCycle )
{
if( !visited.Contains( item ) )
{
visited.Add( item );
foreach( var dep in dependencies( item ) )
Visit( dep, visited, sorted, dependencies, throwOnCycle );
sorted.Add( item );
}
else
{
if( throwOnCycle && !sorted.Contains( item ) )
throw new Exception( "Cyclic dependency found" );
}
}
使用拓扑排序的完美示例:
http://en.wikipedia.org/wiki/Topological_sorting
它将为您提供您所需要的。
您可以使用Kahn算法:
L ← Empty list that will contain the sorted elements
S ← Set of all nodes with no incoming edge
while S is not empty do
remove a node n from S
add n to L
for each node m with an edge e from n to m do
remove edge e from the graph
if m has no other incoming edges then
insert m into S
if graph has edges then
return error (graph has at least one cycle)
else
return L (a topologically sorted order)
...或者您可以使用深度优先搜索:
L ← Empty list that will contain the sorted nodes
while exists nodes without a permanent mark do
select an unmarked node n
visit(n)
function visit(node n)
if n has a permanent mark then
return
if n has a temporary mark then
stop (not a DAG)
mark n with a temporary mark
for each node m with an edge from n to m do
visit(m)
remove temporary mark from n
mark n with a permanent mark
add n to head of L
有一个要点。
对于我们这些不想重新发明轮子的人:使用 nuget 安装 QuickGraph .NET 库,其中包括多种图形算法,包括拓扑排序。
要使用它,您需要创建
AdjacencyGraph<,>
的实例,例如 AdjacencyGraph<String, SEdge<String>>
。然后,如果您包含适当的扩展名:
using QuickGraph.Algorithms;
您可以致电:
var sorted = myGraph.TopologicalSort();
获取已排序节点的列表。
我喜欢 DMM 的答案,但它假设输入节点是叶子(这可能是也可能不是预期的)。
我正在发布一个使用 LINQ 的替代解决方案,但它没有做出这种假设。此外,该解决方案使用
yield return
能够快速返回叶子(例如使用 TakeWhile
)。
public static IEnumerable<T> TopologicalSort<T>(this IEnumerable<T> nodes,
Func<T, IEnumerable<T>> connected)
{
var elems = nodes.ToDictionary(node => node,
node => new HashSet<T>(connected(node)));
while (elems.Count > 0)
{
var elem = elems.FirstOrDefault(x => x.Value.Count == 0);
if (elem.Key == null)
{
throw new ArgumentException("Cyclic connections are not allowed");
}
elems.Remove(elem.Key);
foreach (var selem in elems)
{
selem.Value.Remove(elem.Key);
}
yield return elem.Key;
}
}
这是我自己重新实现的拓扑排序,其思想基于http://tawani.blogspot.com/2009/02/topological-sorting-and-cycling.html(移植的Java源代码也消耗了很大的内存,检查 50k 对象花费 50k*50k*4 = 10GB,这是不可接受的。另外,它在某些地方仍然有 Java 编码约定)
using System.Collections.Generic;
using System.Diagnostics;
namespace Modules
{
/// <summary>
/// Provides fast-algorithm and low-memory usage to sort objects based on their dependencies.
/// </summary>
/// <remarks>
/// Definition: http://en.wikipedia.org/wiki/Topological_sorting
/// Source code credited to: http://tawani.blogspot.com/2009/02/topological-sorting-and-cyclic.html
/// Original Java source code: http://www.java2s.com/Code/Java/Collections-Data-Structure/Topologicalsorting.htm
/// </remarks>
/// <author>ThangTran</author>
/// <history>
/// 2012.03.21 - ThangTran: rewritten based on <see cref="TopologicalSorter"/>.
/// </history>
public class DependencySorter<T>
{
//**************************************************
//
// Private members
//
//**************************************************
#region Private members
/// <summary>
/// Gets the dependency matrix used by this instance.
/// </summary>
private readonly Dictionary<T, Dictionary<T, object>> _matrix = new Dictionary<T, Dictionary<T, object>>();
#endregion
//**************************************************
//
// Public methods
//
//**************************************************
#region Public methods
/// <summary>
/// Adds a list of objects that will be sorted.
/// </summary>
public void AddObjects(params T[] objects)
{
// --- Begin parameters checking code -----------------------------
Debug.Assert(objects != null);
Debug.Assert(objects.Length > 0);
// --- End parameters checking code -------------------------------
// add to matrix
foreach (T obj in objects)
{
// add to dictionary
_matrix.Add(obj, new Dictionary<T, object>());
}
}
/// <summary>
/// Sets dependencies of given object.
/// This means <paramref name="obj"/> depends on these <paramref name="dependsOnObjects"/> to run.
/// Please make sure objects given in the <paramref name="obj"/> and <paramref name="dependsOnObjects"/> are added first.
/// </summary>
public void SetDependencies(T obj, params T[] dependsOnObjects)
{
// --- Begin parameters checking code -----------------------------
Debug.Assert(dependsOnObjects != null);
// --- End parameters checking code -------------------------------
// set dependencies
Dictionary<T, object> dependencies = _matrix[obj];
dependencies.Clear();
// for each depended objects, add to dependencies
foreach (T dependsOnObject in dependsOnObjects)
{
dependencies.Add(dependsOnObject, null);
}
}
/// <summary>
/// Sorts objects based on this dependencies.
/// Note: because of the nature of algorithm and memory usage efficiency, this method can be used only one time.
/// </summary>
public T[] Sort()
{
// prepare result
List<T> result = new List<T>(_matrix.Count);
// while there are still object to get
while (_matrix.Count > 0)
{
// get an independent object
T independentObject;
if (!this.GetIndependentObject(out independentObject))
{
// circular dependency found
throw new CircularReferenceException();
}
// add to result
result.Add(independentObject);
// delete processed object
this.DeleteObject(independentObject);
}
// return result
return result.ToArray();
}
#endregion
//**************************************************
//
// Private methods
//
//**************************************************
#region Private methods
/// <summary>
/// Returns independent object or returns NULL if no independent object is found.
/// </summary>
private bool GetIndependentObject(out T result)
{
// for each object
foreach (KeyValuePair<T, Dictionary<T, object>> pair in _matrix)
{
// if the object contains any dependency
if (pair.Value.Count > 0)
{
// has dependency, skip it
continue;
}
// found
result = pair.Key;
return true;
}
// not found
result = default(T);
return false;
}
/// <summary>
/// Deletes given object from the matrix.
/// </summary>
private void DeleteObject(T obj)
{
// delete object from matrix
_matrix.Remove(obj);
// for each object, remove the dependency reference
foreach (KeyValuePair<T, Dictionary<T, object>> pair in _matrix)
{
// if current object depends on deleting object
pair.Value.Remove(obj);
}
}
#endregion
}
/// <summary>
/// Represents a circular reference exception when sorting dependency objects.
/// </summary>
public class CircularReferenceException : Exception
{
/// <summary>
/// Initializes a new instance of the <see cref="CircularReferenceException"/> class.
/// </summary>
public CircularReferenceException()
: base("Circular reference found.")
{
}
}
}
我不喜欢递归方法,所以 DMM 已经淘汰了。 Krumelur 看起来不错,但似乎占用了大量内存? 制作了一种似乎可行的替代基于堆栈的方法。使用与 DMM 相同的 DFS 逻辑,我在测试时使用此解决方案作为比较。
public static IEnumerable<T> TopogicalSequenceDFS<T>(this IEnumerable<T> source, Func<T, IEnumerable<T>> deps)
{
var yielded = new HashSet<T>();
var visited = new HashSet<T>();
var stack = new Stack<(T, IEnumerator<T>)>();
foreach (T t in source)
{
stack.Clear();
if (visited.Add(t))
stack.Push((t, deps(t).GetEnumerator()));
while (stack.Any())
{
var p = stack.Peek();
bool depPushed = false;
while (p.Item2.MoveNext())
{
var curr = p.Item2.Current;
if (visited.Add(curr))
{
stack.Push((curr, deps(curr).GetEnumerator()));
depPushed = true;
break;
}
else if (!yielded.Contains(curr))
throw new Exception("cycle");
}
if (!depPushed)
{
p = stack.Pop();
if (!yielded.Add(p.Item1))
throw new Exception("bug");
yield return p.Item1;
}
}
}
}
为了完整起见,这里还有一个基于堆栈的 BFS 变体:
public static IEnumerable<T> TopologicalSequenceBFS<T>(this IEnumerable<T> source, Func<T, IEnumerable<T>> dependencies)
{
var yielded = new HashSet<T>();
var visited = new HashSet<T>();
var stack = new Stack<(T, bool)>(source.Select(s => (s, false))); // bool signals Add to sorted
while (stack.Any())
{
var item = stack.Pop();
if (!item.Item2)
{
if (visited.Add(item.Item1))
{
stack.Push((item.Item1, true)); // To be added after processing the dependencies
foreach (var dep in dependencies(item.Item1))
stack.Push((dep, false));
}
else if (!yielded.Contains(item.Item1))
throw new Exception("cyclic");
}
else
{
if (!yielded.Add(item.Item1))
throw new Exception("bug");
yield return item.Item1;
}
}
}
我可以通过将项目的依赖关系存储在项目本身中来使这对自己来说更容易:
public class Item
{
private List<Item> m_Dependencies = new List<Item>();
protected AddDependency(Item _item) { m_Dependencies.Add(_item); }
public Item()
{
}; // eo ctor
public List<Item> Dependencies {get{return(m_Dependencies);};}
} // eo class Item
然后,鉴于此,您可以为 List 实现一个自定义排序委托,该委托根据给定 Item 是否包含在另一个依赖项列表中进行排序:
int CompareItem(Item _1, Item _2)
{
if(_2.Dependencies.Contains(_1))
return(-1);
else if(_1.Dependencies.Contains(_2))
return(1);
else
return(0);
}
对于只有一个“父母”的情况,有一个不同的想法:
您可以存储父母,而不是 deps。
所以你可以很容易地判断一个问题是否是其他问题的依赖。
然后使用
Comparable<T>
,这将声明依赖关系“较小”和依赖关系“较大”。Collections.sort( List<T>, ParentComparator<T>);
对于多父场景,需要进行树搜索,这会导致执行速度缓慢。但这可以通过 A* 排序矩阵形式的缓存来解决。
我将 DMM 的想法与维基百科上的深度优先搜索算法合并。它非常适合我的需要。
public static class TopologicalSorter
{
public static List<string> LastCyclicOrder = new List<string>(); //used to see what caused the cycle
sealed class ItemTag
{
public enum SortTag
{
NotMarked,
TempMarked,
Marked
}
public string Item { get; set; }
public SortTag Tag { get; set; }
public ItemTag(string item)
{
Item = item;
Tag = SortTag.NotMarked;
}
}
public static IEnumerable<string> TSort(this IEnumerable<string> source, Func<string, IEnumerable<string>> dependencies)
{
TopologicalSorter.LastCyclicOrder.Clear();
List<ItemTag> allNodes = new List<ItemTag>();
HashSet<string> sorted = new HashSet<string>(StringComparer.OrdinalIgnoreCase);
foreach (string item in source)
{
if (!allNodes.Where(n => string.Equals(n.Item, item, StringComparison.OrdinalIgnoreCase)).Any())
{
allNodes.Add(new ItemTag(item)); //don't insert duplicates
}
foreach (string dep in dependencies(item))
{
if (allNodes.Where(n => string.Equals(n.Item, dep, StringComparison.OrdinalIgnoreCase)).Any()) continue; //don't insert duplicates
allNodes.Add(new ItemTag(dep));
}
}
foreach (ItemTag tag in allNodes)
{
Visit(tag, allNodes, dependencies, sorted);
}
return sorted;
}
static void Visit(ItemTag tag, List<ItemTag> allNodes, Func<string, IEnumerable<string>> dependencies, HashSet<string> sorted)
{
if (tag.Tag == ItemTag.SortTag.TempMarked)
{
throw new GraphIsCyclicException();
}
else if (tag.Tag == ItemTag.SortTag.NotMarked)
{
tag.Tag = ItemTag.SortTag.TempMarked;
LastCyclicOrder.Add(tag.Item);
foreach (ItemTag dep in dependencies(tag.Item).Select(s => allNodes.Where(t => string.Equals(s, t.Item, StringComparison.OrdinalIgnoreCase)).First())) //get item tag which falls with used string
Visit(dep, allNodes, dependencies, sorted);
LastCyclicOrder.Remove(tag.Item);
tag.Tag = ItemTag.SortTag.Marked;
sorted.Add(tag.Item);
}
}
}
这是帖子中重构的代码https://stackoverflow.com/a/9991916/4805491。
// Version 1
public static class TopologicalSorter<T> where T : class {
public struct Item {
public readonly T Object;
public readonly T Dependency;
public Item(T @object, T dependency) {
Object = @object;
Dependency = dependency;
}
}
public static T[] Sort(T[] objects, Func<T, T, bool> isDependency) {
return Sort( objects.ToList(), isDependency ).ToArray();
}
public static T[] Sort(T[] objects, Item[] dependencies) {
return Sort( objects.ToList(), dependencies.ToList() ).ToArray();
}
private static List<T> Sort(List<T> objects, Func<T, T, bool> isDependency) {
return Sort( objects, GetDependencies( objects, isDependency ) );
}
private static List<T> Sort(List<T> objects, List<Item> dependencies) {
var result = new List<T>( objects.Count );
while (objects.Any()) {
var obj = GetIndependentObject( objects, dependencies );
RemoveObject( obj, objects, dependencies );
result.Add( obj );
}
return result;
}
private static List<Item> GetDependencies(List<T> objects, Func<T, T, bool> isDependency) {
var dependencies = new List<Item>();
for (var i = 0; i < objects.Count; i++) {
var obj1 = objects[i];
for (var j = i + 1; j < objects.Count; j++) {
var obj2 = objects[j];
if (isDependency( obj1, obj2 )) dependencies.Add( new Item( obj1, obj2 ) ); // obj2 is dependency of obj1
if (isDependency( obj2, obj1 )) dependencies.Add( new Item( obj2, obj1 ) ); // obj1 is dependency of obj2
}
}
return dependencies;
}
private static T GetIndependentObject(List<T> objects, List<Item> dependencies) {
foreach (var item in objects) {
if (!GetDependencies( item, dependencies ).Any()) return item;
}
throw new Exception( "Circular reference found" );
}
private static IEnumerable<Item> GetDependencies(T obj, List<Item> dependencies) {
return dependencies.Where( i => i.Object == obj );
}
private static void RemoveObject(T obj, List<T> objects, List<Item> dependencies) {
objects.Remove( obj );
dependencies.RemoveAll( i => i.Object == obj || i.Dependency == obj );
}
}
// Version 2
public class TopologicalSorter {
public static T[] Sort<T>(T[] source, Func<T, T, bool> isDependency) {
var list = new LinkedList<T>( source );
var result = new List<T>();
while (list.Any()) {
var obj = GetIndependentObject( list, isDependency );
list.Remove( obj );
result.Add( obj );
}
return result.ToArray();
}
private static T GetIndependentObject<T>(IEnumerable<T> list, Func<T, T, bool> isDependency) {
return list.First( i => !GetDependencies( i, list, isDependency ).Any() );
}
private static IEnumerable<T> GetDependencies<T>(T obj, IEnumerable<T> list, Func<T, T, bool> isDependency) {
return list.Where( i => isDependency( obj, i ) ); // i is dependency of obj
}
}