C# Dictionary, SortedDictionary, SortedList

就我个人觉得Dictionary, SortedDictionary, SortedList 这几个类的使用是比较简单的，只要稍微花点时间在网上查找一点资料，然后在阅读以下源码就理解的很清楚了。为什么要写这一片文章了，看一下code吧：

Dictionary dict = new Dictionary();
//load data to dict
int key = 1;
object obj = null;
if (dict.ContainsKey(key))
{
obj = dict[key];
}

本来程序在初始化的时候会初始化一个Dictionary，然后在程序很多地方需要读Dictionary，然后一同事刚开始就是这样写的code，后来说字典查找ContainsKey比较慢，所以就改为SortedDictionary，按照key排序的字典。 而我一般是用普通的Dictionary的 dict.TryGetValue(key, out  obj)方法就可以了。所以就有了这篇文章，先说一下 结论吧：

Dictionary泛型类提供了从一组键到一组值的映射。字典中的每个添加项都由一个值及其相关联的键组成。通过键来检索值的速度是非常快的，接近于 O(1)，这是因为Dictionary类是作为一个哈希表来实现的。检索速度取决于为 TKey 指定的类型的哈希算法的质量。
SortedDictionary泛型类是检索运算复杂度为 O(log n) 的二叉搜索树，其中n是字典中的元素数。就这一点而言，它与SortedList泛型类相似。这两个类具有相似的对象模型，并且都具有O(logn)的检索运算复杂度。这两个类的区别在于内存的使用以及插入和移除元素的速度：
SortedList使用的内存比SortedDictionary少。SortedDictionary可对未排序的数据执行更快的插入和移除操作：它的时间复杂度为O(logn)，而SortedList为 O(n)。如果使用排序数据一次性填充列表，则SortedList比SortedDictionary快。

首先来看Dictionary的实现：

 public class Dictionary: IDictionary, IDictionary, IReadOnlyDictionary, ISerializable, IDeserializationCallback  {
    {
        private struct Entry {
            public int hashCode;    // Lower 31 bits of hash code, -1 if unused
            public int next;        // Index of next entry, -1 if last
            public TKey key;           // Key of entry
            public TValue value;         // Value of entry
        }

        private int[] buckets;
        private Entry[] entries;
        private IEqualityComparer comparer;
        
        public Dictionary(int capacity): this(capacity, null) {}

        public Dictionary(IEqualityComparer comparer): this(0, comparer) {}

        public Dictionary(int capacity, IEqualityComparer comparer) {
            if (capacity < 0) ThrowHelper.ThrowArgumentOutOfRangeException(ExceptionArgument.capacity);
            if (capacity > 0) Initialize(capacity);
            this.comparer = comparer ?? EqualityComparer.Default;
        } 
        
         private void Initialize(int capacity) {
            int size = HashHelpers.GetPrime(capacity);
            buckets = new int[size];
            for (int i = 0; i < buckets.Length; i++) buckets[i] = -1;
            entries = new Entry[size];
            freeList = -1;
        }
        
        public TValue this[TKey key] {
            get {
                int i = FindEntry(key);
                if (i >= 0) return entries[i].value;
                ThrowHelper.ThrowKeyNotFoundException();
                return default(TValue);
            }
            set {
                Insert(key, value, false);
            }
        }
        
        private int FindEntry(TKey key) {
            if( key == null) {
                ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
            }

            if (buckets != null) {
                int hashCode = comparer.GetHashCode(key) & 0x7FFFFFFF;
                for (int i = buckets[hashCode % buckets.Length]; i >= 0; i = entries[i].next) {
                    if (entries[i].hashCode == hashCode && comparer.Equals(entries[i].key, key)) return i;
                }
            }
            return -1;
        }
        
        private void Insert(TKey key, TValue value, bool add) {
        
            if( key == null ) {
                ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
            }

            if (buckets == null) Initialize(0);
            int hashCode = comparer.GetHashCode(key) & 0x7FFFFFFF;
            int targetBucket = hashCode % buckets.Length;

            for (int i = buckets[targetBucket]; i >= 0; i = entries[i].next) {
                if (entries[i].hashCode == hashCode && comparer.Equals(entries[i].key, key)) {
                    if (add) { 
                        ThrowHelper.ThrowArgumentException(ExceptionResource.Argument_AddingDuplicate);
                    }
                    entries[i].value = value;
                    version++;
                    return;
                } 
            }
            int index;
            if (freeCount > 0) {
                index = freeList;
                freeList = entries[index].next;
                freeCount--;
            }
            else {
                if (count == entries.Length)
                {
                    Resize();
                    targetBucket = hashCode % buckets.Length;
                }
                index = count;
                count++;
            }

            entries[index].hashCode = hashCode;
            entries[index].next = buckets[targetBucket];
            entries[index].key = key;
            entries[index].value = value;
            buckets[targetBucket] = index;
            version++;

            if(collisionCount > HashHelpers.HashCollisionThreshold && HashHelpers.IsWellKnownEqualityComparer(comparer)) 
            {
                comparer = (IEqualityComparer) HashHelpers.GetRandomizedEqualityComparer(comparer);
                Resize(entries.Length, true);
            }
        }
    }

Dictionary的数据成员转换为Entry结构，真正保存数据的是这里的Entry[] entries 数组，第一个元素小标为0，第二个为1......,但是查找和添加Dictionary我们都是通过key来实现的，那么一个key究竟对应哪一个下标了，就需要这里的int[] buckets数组了。就如这里的FindEntry方法一样，首先获取key的哈希值获取buckets的下标（比如一个初始化为100个元素的字典，计算出来再buckets中的第50个元素），buckets 对应的值就是entries 数组的下标（buckets[50]=0,那么就应该取entries[0]的值了）。如果字典的元素个数是可以确定的话，那么建议指定capacity

int hashCode = comparer.GetHashCode(key) & 0x7FFFFFFF;
int targetBucket = hashCode % buckets.Length;

entries[index].hashCode = hashCode;
entries[index].next = buckets[targetBucket];
entries[index].key = key;
entries[index].value = value;
buckets[targetBucket] = index;

现在我们来看看SortedList的实现：

    public class SortedList : IDictionary, System.Collections.IDictionary, IReadOnlyDictionary
    {
        private TKey[] keys;
        private TValue[] values;
        private IComparer comparer;
        public SortedList(int capacity) {
            if (capacity < 0)
                ThrowHelper.ThrowArgumentOutOfRangeException(ExceptionArgument.capacity, ExceptionResource.ArgumentOutOfRange_NeedNonNegNumRequired);
            keys = new TKey[capacity];
            values = new TValue[capacity];
            comparer = Comparer.Default;
        }
        
        public SortedList(IDictionary dictionary, IComparer comparer) 
            : this((dictionary != null ? dictionary.Count : 0), comparer) {
            if (dictionary==null)
                ThrowHelper.ThrowArgumentNullException(ExceptionArgument.dictionary);

            dictionary.Keys.CopyTo(keys, 0);
            dictionary.Values.CopyTo(values, 0);
            Array.Sort(keys, values, comparer);
            _size = dictionary.Count;            
        }
        
        public TValue this[TKey key] {
            get {
                int i = IndexOfKey(key);
                if (i >= 0)
                    return values[i];

                ThrowHelper.ThrowKeyNotFoundException();
                return default(TValue);
            }
            set {
                if (((Object) key) == null) ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
                int i = Array.BinarySearch(keys, 0, _size, key, comparer);
                if (i >= 0) {
                    values[i] = value;
                    version++;
                    return;
                }
                Insert(~i, key, value);
            }
        }
        
         public int IndexOfKey(TKey key) {
            if (key == null) 
                ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
            int ret = Array.BinarySearch(keys, 0, _size, key, comparer);
            return ret >=0 ? ret : -1;
        }
        
        private void Insert(int index, TKey key, TValue value) {
            if (_size == keys.Length) EnsureCapacity(_size + 1);
            if (index < _size) {
                Array.Copy(keys, index, keys, index + 1, _size - index);
                Array.Copy(values, index, values, index + 1, _size - index);
            }
            keys[index] = key;
            values[index] = value;
            _size++;
            version++;
        }
    }

SortedList的key和value分别存在TKey[] keys和TValue[] values数组里面，但是查找key用的不是哈希算法，而是二分查找 Array.BinarySearch(keys, 0, _size, key, comparer)，但是插入的时候却有

if (index < _size) {
Array.Copy(keys, index, keys, index + 1, _size - index);
Array.Copy(values, index, values, index + 1, _size - index);
}这样的code，意思就是如果SortedList里面已经有10个值，如果新插入的值应该是第一个， 那么需要把后面10个元素依次移动一个位置。移除元素也有类似的情况。

最后我们来看SortedDictionary的实现：

    public class SortedDictionary : IDictionary, IDictionary, IReadOnlyDictionary 
     {
       public SortedDictionary(IDictionary dictionary, IComparer comparer) {
            if( dictionary == null) {
                ThrowHelper.ThrowArgumentNullException(ExceptionArgument.dictionary);
            }

            _set = new TreeSet>(new KeyValuePairComparer(comparer));

            foreach(KeyValuePair pair in dictionary) {
                _set.Add(pair);
            }            
        }

        public SortedDictionary(IComparer comparer) {
            _set = new TreeSet>(new KeyValuePairComparer(comparer));
        }
        
       public TValue this[TKey key] {
            get {
                if ( key == null) {
                    ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);                    
                }

                TreeSet>.Node node = _set.FindNode(new KeyValuePair(key, default(TValue)));
                if ( node == null) {
                    ThrowHelper.ThrowKeyNotFoundException();                    
                }

                return node.Item.Value;
            }
            set {
                if( key == null) {
                    ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
                }
            
                TreeSet>.Node node = _set.FindNode(new KeyValuePair(key, default(TValue)));
                if ( node == null) {
                    _set.Add(new KeyValuePair(key, value));                        
                } else {
                    node.Item = new KeyValuePair( node.Item.Key, value);
                    _set.UpdateVersion();
                }
            }
        }
     internal class TreeSet : SortedSet {}
         
      }
      
    public class SortedSet : ISet, ICollection, ICollection, ISerializable, IDeserializationCallback, IReadOnlyCollection 
    {
        internal virtual Node FindNode(T item) {
            Node current = root;
            while (current != null) {
                int order = comparer.Compare(item, current.Item);
                if (order == 0) {
                    return current;
                } else {
                    current = (order < 0) ? current.Left : current.Right;
                }
            }

            return null;
        }
        
        public bool Add(T item) {
            return AddIfNotPresent(item);
        }
        
        internal virtual bool AddIfNotPresent(T item) {
            if (root == null) {   // empty tree
                root = new Node(item, false);
                count = 1;
                version++;
                return true;
            }

            //
            // Search for a node at bottom to insert the new node. 
            // If we can guanratee the node we found is not a 4-node, it would be easy to do insertion.
            // We split 4-nodes along the search path.
            // 
            Node current = root;
            Node parent = null;
            Node grandParent = null;
            Node greatGrandParent = null;

            //even if we don't actually add to the set, we may be altering its structure (by doing rotations
            //and such). so update version to disable any enumerators/subsets working on it
            version++;


            int order = 0;
            while (current != null) {
                order = comparer.Compare(item, current.Item);
                if (order == 0) {
                    // We could have changed root node to red during the search process.
                    // We need to set it to black before we return.
                    root.IsRed = false;
                    return false;
                }

                // split a 4-node into two 2-nodes                
                if (Is4Node(current)) {
                    Split4Node(current);
                    // We could have introduced two consecutive red nodes after split. Fix that by rotation.
                    if (IsRed(parent)) {
                        InsertionBalance(current, ref parent, grandParent, greatGrandParent);
                    }
                }
                greatGrandParent = grandParent;
                grandParent = parent;
                parent = current;
                current = (order < 0) ? current.Left : current.Right;
            }

            Debug.Assert(parent != null, "Parent node cannot be null here!");
            // ready to insert the new node
            Node node = new Node(item);
            if (order > 0) {
                parent.Right = node;
            } else {
                parent.Left = node;
            }

            // the new node will be red, so we will need to adjust the colors if parent node is also red
            if (parent.IsRed) {
                InsertionBalance(node, ref parent, grandParent, greatGrandParent);
            }

            // Root node is always black
            root.IsRed = false;
            ++count;
            return true;
        }

    }

SortedDictionary的实现基本是靠TreeSet （SortedSet）来完成的，它的查找和添加都是在一个红黑树里面实现的。

Dictionary, SortedDictionary, SortedList 3个都有含类似IComparer comparer的构造方法，Dictionary和SortedList 里面存储是用数组，所有它俩都有int capacity的指定，然而SortedDictionary依赖于树，所以没有该参数。所以Dictionary查找，插入、修改时间复杂度为O（1）（里面主要是哈希算法的时间，建议一个哈希桶里面存放一个元素），SortedList的查找时间复杂度为O(logn)，但是插入和删除需要移动后面的元素，所以时间复杂 为O(n)，SortedDictionary依赖于红黑树，所以查找、插入和修改 时间复杂度为O(logn)。