一步一步剖析Dictionary實現原理
阿新 • • 發佈：2019-10-10
本文是對c#中Dictionary內部實現原理進行簡單的剖析。如有表述錯誤，歡迎指正。
主要對照原始碼來解析，目前對照原始碼的版本是.Net Framwork 4.8，原始碼地址。
1. 關鍵的欄位和Entry結構
struct Entry
{
public int hashCode; // key的hashCode & 0x7FFFFFFF
public int next; // 指向連結串列下一個元素的地址（實際就是entries的索引），最後一個元素為-1
public TKey key;
public TValue value;
}
Entry[] entries; //存放鍵值
int[] buckets; //儲存entries最新元素的索引,其儲存位置由取模結果決定。例：假設鍵值儲存在entries的第1元素的位置上，且hashCode和長度的取模結果為2，那麼buckets[2] = 1
int count = 0; //已儲存鍵值的個數
int version; //記錄版本，防止迭代過程中集合被更改
IEqualityComparer<TKey> _comparer;
int freeList; //entries中最新空元素的索引
int freeCount; //entries中空元素的個數2. 新增鍵值（Add）
public void Add(TKey key, TValue value) {
Insert(key, value, true);
}
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;
//取模
int targetBucket = hashCode % buckets.Length;
#if FEATURE_RANDOMIZED_STRING_HASHING
int collisionCount = 0;
#endif
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);
}
//對於已存在的Key重新賦值
entries[i].value = value;
version++;
return;
}
#if FEATURE_RANDOMIZED_STRING_HASHING
collisionCount++;
#endif
}
int index;
if (freeCount > 0) {
//存在entries中存在空元素
index = freeList;
freeList = entries[index].next;
freeCount--;
}
else {
if (count == entries.Length)
{
//擴容：取大於count * 2的最小素數作為entries和bucket的新容量（即陣列長度.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;
//存取連結串列的頭元素的索引（即entries最後存入的元素的在enties中的索引）
//便於取Key的時每次從連結串列的頭元素開始遍歷，詳細見FindEntry(TKey key)函式
buckets[targetBucket] = index;
version++;
#if FEATURE_RANDOMIZED_STRING_HASHING
#if FEATURE_CORECLR
// In case we hit the collision threshold we'll need to switch to the comparer which is using randomized string hashing
// in this case will be EqualityComparer<string>.Default.
// Note, randomized string hashing is turned on by default on coreclr so EqualityComparer<string>.Default will
// be using randomized string hashing
if (collisionCount > HashHelpers.HashCollisionThreshold && comparer == NonRandomizedStringEqualityComparer.Default)
{
comparer = (IEqualityComparer<TKey>) EqualityComparer<string>.Default;
Resize(entries.Length, true);
}
#else
if(collisionCount > HashHelpers.HashCollisionThreshold && HashHelpers.IsWellKnownEqualityComparer(comparer))
{
//如果碰撞次數（單鏈表長度）大於設定的最大碰撞閾值，需要擴容
comparer = (IEqualityComparer<TKey>) HashHelpers.GetRandomizedEqualityComparer(comparer);
Resize(entries.Length, true);
}
#endif // FEATURE_CORECLR
#endif
}
******************************************************************************************************************************************
static void Foo()
{
var dicData = new Dictionary<int, int>();
//新增鍵值
new List<int> { 1, 2, 4 }.ForEach(item => Add(item, dicData));
new List<int> { 22, 29, 36, 20 }.ForEach(item => Add(item, dicData));
}
static void Add(int key, Dictionary<int, int> dicData)
{
dicData.Add(key, key);
}
2.1 陣列entries和buckets初始化
2.2 新增鍵值{1，1}，則
hashCode = 1;
targetBucket = hasCode % buckets.Length; //targetBucket = 1
next = buckets[targetBucket]; //next = -1
buckets[targetBucket] = index; //buckets[1] = 0
2.3 新增鍵值{2，2}，則
hashCode = 2;
targetBucket = hasCode % buckets.Length; //targetBucket = 2
next = buckets[targetBucket]; //next = -1
buckets[targetBucket] = index; //buckets[2] = 1
2.4 新增鍵值{4，4}，則
hashCode = 4;
targetBucket = hasCode % buckets.Length; //targetBucket = 1
next = buckets[targetBucket]; //next = 0
buckets[targetBucket] = index; //buckets[1] = 2
接下來將entries陣列以單鏈表的形式呈現(即enteries陣列橫向)；
2.5 在繼續新增鍵值之前，需要擴容操作，因為entries陣列長度為3且都已有元素。擴容後需要對buckets和entries每個元素的Next需要重新賦值；
private void Resize(int newSize, bool forceNewHashCodes) {
Contract.Assert(newSize >= entries.Length);
//例項化buckets，並將每個元素置為-1
int[] newBuckets = new int[newSize];
for (int i = 0; i < newBuckets.Length; i++) newBuckets[i] = -1;
Entry[] newEntries = new Entry[newSize];
Array.Copy(entries, 0, newEntries, 0, count);
//如果是Hash碰撞擴容，使用新HashCode函式重新計算Hash值
if(forceNewHashCodes) {
for (int i = 0; i < count; i++) {
if(newEntries[i].hashCode != -1) {
newEntries[i].hashCode = (comparer.GetHashCode(newEntries[i].key) & 0x7FFFFFFF);
}
}
}
//重建單鏈表
for (int i = 0; i < count; i++) {
if (newEntries[i].hashCode >= 0) {
//取模重新設定next值和buckets
int bucket = newEntries[i].hashCode % newSize;
newEntries[i].next = newBuckets[bucket];
newBuckets[bucket] = i;
}
}
buckets = newBuckets;
entries = newEntries;
}
2.6 繼續新增鍵值{22，22}，{29，29}，{36，36}，{40，40}，新增完後其內部儲存結果如下
3. 取Key值（dic[22]）
public TValue this[TKey key] {
get {
//取Key對應值在entries的索引
int i = FindEntry(key);
if (i >= 0) return entries[i].value;
ThrowHelper.ThrowKeyNotFoundException();
return default(TValue);
}
set {
//更新Key對應的值
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;
//遍歷單鏈表
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;
}
*********************************************************************************************
static void Foo()
{
......
//取Key=22
var val =dicData[22];
}
簡化取Key對應值的程式碼
var hashCode =comparer.GetHashCode(key) & 0x7FFFFFFF; // 22
var targetBuget = hashCode % buckets.Length; //取模運算 1
var i = bucket[targetBuget]; //連結串列頭元素的索引 bucket[1] = 5
//遍歷單鏈表
for (; i >= 0; i = entries[i].next) {
if (entries[i].hashCode == hashCode && comparer.Equals(entries[i].key, key)) return i;
}
4. 移除鍵值（Remove）
public bool Remove(TKey key) {
if(key == null) {
ThrowHelper.ThrowArgumentNullException(ExceptionArgument.key);
}
if (buckets != null) {
int hashCode = comparer.GetHashCode(key) & 0x7FFFFFFF;
int bucket = hashCode % buckets.Length;
int last = -1;
//其原理先取出鍵值，然後記錄entries空閒的索引（freeList）和空閒個數（freeCount）
for (int i = buckets[bucket]; i >= 0; last = i, i = entries[i].next) {
if (entries[i].hashCode == hashCode && comparer.Equals(entries[i].key, key)) {
if (last < 0) {
buckets[bucket] = entries[i].next;
}
else {
entries[last].next = entries[i].next;
}
entries[i].hashCode = -1;
//建立空閒連結串列
entries[i].next = freeList;
entries[i].key = default(TKey);
entries[i].value = default(TValue);
//儲存entryies中空元素的索引
//便於插入新鍵值時，放在當前索引的位置，減少entryies空間上的浪費
freeList = i;
//空元素的個數加1
freeCount++;
version++;
return true;
}
}
}
return false;
}
*******************************************************************
static void Foo()
{
......
//移除
new List<int> { 22, 29 }.ForEach(item => dicData.Remove(item));
}
4.1 移除Key=22後，freeList = 3, freeCount = 1,
4.2 移除Key=36後，freeList = 5, freeCount = 2,
5. 再插入鍵值
如上圖，當移除掉{36，36}後，會發現又誕生一個含有兩個元素的“新連結串列”（上圖灰色框）。這個作用就是為了插入新鍵值時，按照“新連結串列”記錄的索引順序插入到entries陣列中。 例：新增鍵值{22，22}，{25，25}，此時freeList = 5，freeCount = 2;- 給entries[5]賦值，freeList = 3, freeCount = 1；
- 給entries[3]賦值，freeList = -1, freeCount = 0；
希望此文能夠讓你對於Dictionary內部實現有所認