【C++】unordered系列关联式容器及其底层结构

void test_map1()
{
	string arr[] = { "苹果", "西瓜", "苹果", "西瓜", "苹果", "苹果", "西瓜",
"苹果", "香蕉", "苹果", "香蕉","苹果","草莓", "苹果","草莓" };
	unordered_map<string, int> countMap;
	for (auto& e : arr)
	{
		countMap[e]++;
	}

	for (auto& kv : countMap)
	{
		cout << kv.first << ":" << kv.second << endl;
	}
	cout << endl;
}

void test_set1()
{
	unordered_set<int> s = { 3,1,7,8,2 };

	unordered_set<int>::iterator it = s.begin();
	while (it != s.end())
	{
		cout << *it << " ";
		++it;	
	}
	cout << endl;
}

int test_set2()
{
	const size_t N = 10000000;

	unordered_set<int> us;
	set<int> s;

	vector<int> v;
	v.reserve(N);
	srand(time(0));
	for (size_t i = 0; i < N; ++i)
	{
		//v.push_back(rand()); // N比较大时，重复值比较多
		//v.push_back(rand()+i); // 重复值相对少
		v.push_back(i); // 没有重复，有序
	}

	
	size_t begin1 = clock();
	for (auto e : v)
	{
		s.insert(e);
	}
	size_t end1 = clock();
	cout << "set insert:" << end1 - begin1 << endl;

	size_t begin2 = clock();
	for (auto e : v)
	{
		us.insert(e);
	}
	size_t end2 = clock();
	cout << "unordered_set insert:" << end2 - begin2 << endl;

	int m1 = 0;
	size_t begin3 = clock();
	for (auto e : v)
	{
		auto ret = s.find(e);
		if (ret != s.end())
		{
			++m1;
		}
	}
	size_t end3 = clock();
	cout << "set find:" << end3 - begin3 << "->" << m1 << endl;

	int m2 = 0;
	size_t begin4 = clock();
	for (auto e : v)
	{
		auto ret = us.find(e);
		if (ret != us.end())
		{
			++m2;
		}
	}
	size_t end4 = clock();
	cout << "unorered_set find:" << end4 - begin4 << "->" << m2 << endl;

	cout << "插入数据个数：" << s.size() << endl;
	cout << "插入数据个数：" << us.size() << endl << endl;

	size_t begin5 = clock();
	for (auto e : v)
	{
		s.erase(e);
	}
	size_t end5 = clock();
	cout << "set erase:" << end5 - begin5 << endl;

	size_t begin6 = clock();
	for (auto e : v)
	{
		us.erase(e);
	}
	size_t end6 = clock();
	cout << "unordered_set erase:" << end6 - begin6 << endl << endl;

	return 0;
}

enum State
{
	EMPTY,
	EXIST,
	DELETE
};

//扩容
		if (_n*10 / _tables.size() >= 7)
		{
			//size_t newsize = _tables.size() * 2;
			//vector<HashData<K, V>> newtables(newsize);

			旧表重新计算到新表
			//for (size_t i = 0; i < tables.size(); i++){}

			size_t newsize = _tables.size() * 2;
			HashTable<K, V> newHT;
			newHT._tables.resize(newsize);

			//旧表重新计算到新表
			for (size_t i = 0; i < tables.size(); i++)
			{
				if (_tables[i]._state == EXIST)
				{
					newHT.Insert(_tables[i]._kv);
				}
			}
			_tables.swap(newHT._tables)；
			
		}

template<class K>
struct HashFunc
{
	size_t operator()(const K& key)
	{
		return (size_t)key;
	}
};

template<>
struct HashFunc<string>
{

	size_t operator()(const string& key)
	{
		return key[0];
	}
};

template<>
struct HashFunc<string>
{

	size_t operator()(const string& key)
	{
		size_t hash = 0;
		for (auto ch : key)
		{
			hash += ch;
		}

		return hash;
	}
};

template<>
struct HashFunc<string>
{
	size_t operator()(const string& key)
	{
		size_t hash = 0;
		for (auto ch : key)
		{
			hash *= 131;
			hash += ch;
		}

		return hash;
	}
};

#pragma once
#include<vector>

template<class K>
struct HashFunc
{
	size_t operator()(const K& key)
	{
		return (size_t)key;
	}
};

// 特化
template<>
struct HashFunc<string>
{
	// abcd
	// bcad
	// aadd
	// BKDR
	size_t operator()(const string& key)
	{
		size_t hash = 0;
		for (auto ch : key)
		{
			hash *= 131;
			hash += ch;
		}

		return hash;
	}
};

namespace open_address
{
	enum State
	{
		EMPTY,
		EXIST,
		DELETE
	};

	template<class K, class V>
	struct HashData
	{
		pair<K, V> _kv;
		State _state = EMPTY;
	};

	struct StringHashFunc
	{
		// abcd
		// bcad
		// aadd
		// BKDR
		size_t operator()(const string& key)
		{
			size_t hash = 0;
			for (auto ch : key)
			{
				hash *= 131;
				hash += ch;
			}

			return hash;
		}
	};

	template<class K, class V, class Hash = HashFunc<K>>
	class HashTable
	{
	public:
		HashTable()
		{
			_tables.resize(10);
		}

		
		bool Insert(const pair<K,V>& kv)
		{
			if (Find(kv.first))
				return false;

			// 扩容
			if (_n * 10 / _tables.size() >= 7)
			{
				//size_t newsize = _tables.size() * 2;
				//vector<HashData<K, V>> newtables(newsize);

				 旧表重新计算负载到新表
				//for (size_t i = 0; i < _tables.size(); i++)
				//{}
				HashTable<K, V, Hash> newHT;
				newHT._tables.resize(_tables.size() * 2);

				// 旧表重新计算负载到新表
				for (size_t i = 0; i < _tables.size(); i++)
				{
					if (_tables[i]._state == EXIST)
					{
						newHT.Insert(_tables[i]._kv);
					}
				}

				_tables.swap(newHT._tables);
			}

			Hash hs;
			size_t hashi = hs(kv.first) % _tables.size();

			// 线性探测
			while (_tables[hashi]._state == EXIST)
			{
				++hashi;
				hashi %= _tables.size();
			}

			_tables[hashi]._kv = kv;
			_tables[hashi]._state = EXIST;
			++_n;

			return true;
		}

		HashData<K, V>* Find(const K& key)
		{
			Hash hs;
			size_t hashi = hs(key) % _tables.size();

			// 线性探测
			while (_tables[hashi]._state != EMPTY)
			{
				if (_tables[hashi]._state == EXIST &&
					_tables[hashi]._kv.first == key)
				{
					return &_tables[hashi];
				}

				++hashi;
				hashi %= _tables.size();
			}

			return nullptr;
		}

		bool Erase(const K& key)
		{
			HashData<K, V>* ret = Find(key);
			if (ret == nullptr)
			{
				return false;
			}
			else
			{
				ret->_state = DELETE;
				--_n;

				return true;
			}
		}

	private:
		vector <HashData<K, V>> _tables;
		size_t _n = 0;  // 有效数据个数
	};

			size_t hashi = kv.first % _tables.size();
			Node* newnode = new Node(kv);
			// 头插
			newnode->_next = _tables[hashi];
			_tables[hashi] = newnode;

	template<class K, class T, class KeyOfT, class Hash>
	class HashTable
	{
		typedef HashNode<T> Node;
	public:
		// 友元声明
		/*template<class K, class T, class KeyOfT, class Hash>
		friend struct __HTIterator;*/

		// 内部类
		template<class Ptr, class Ref>
		struct __HTIterator
		{
			typedef HashNode<T> Node;
			typedef __HTIterator Self;

			Node* _node;
			const HashTable* _pht;

			__HTIterator(Node* node, const HashTable* pht)
				:_node(node)
				, _pht(pht)
			{}

			Ref operator*()
			{
				return _node->_data;
			}

			Ptr operator->()
			{
				return &_node->_data;
			}

			Self& operator++()
			{
				if (_node->_next)
				{
					// 当前桶没走完，找当前桶的下一个节点
					_node = _node->_next;
				}
				else
				{
					// 当前桶走完了，找下一个不为空的桶的第一个节点
					KeyOfT kot;
					Hash hs;
					size_t i = hs(kot(_node->_data)) % _pht->_tables.size();
					++i;
					for (; i < _pht->_tables.size(); i++)
					{
						if (_pht->_tables[i])
							break;
					}

					if (i == _pht->_tables.size())
					{
						// 所有桶都走完了，最后一个的下一个用nullptr标记
						_node = nullptr;
					}
					else
					{
						_node = _pht->_tables[i];
					}
				}

				return *this;
			}

			bool operator!=(const Self& s)
			{
				return _node != s._node;
			}
		};

		typedef __HTIterator<T*, T&> iterator;
		typedef __HTIterator<const T*, const T&> const_iterator;

		iterator begin()
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				Node* cur = _tables[i];
				if (cur)
				{
					// this -> HashTable*
					return iterator(cur, this);
				}
			}

			return end();
		}

		iterator end()
		{
			return iterator(nullptr, this);
		}

		const_iterator begin() const
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				Node* cur = _tables[i];
				if (cur)
				{
					// this -> const HashTable*
					return const_iterator(cur, this);
				}
			}

			return end();
		}

		const_iterator end() const
		{
			return const_iterator(nullptr, this);
		}

		HashTable()
		{
			_tables.resize(10, nullptr);
			_n = 0;
		}



		~HashTable()
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				Node* cur = _tables[i];
				while (cur)
				{
					Node* next = cur->_next;
					delete cur;

					cur = next;
				}

				_tables[i] = nullptr;
			}
		}

		pair<iterator, bool> Insert(const T& data)
		{
			KeyOfT kot;
			iterator it = Find(kot(data));
			if (it != end())
				return make_pair(it, false);

			Hash hs;
			// 扩容
			// 负载因子为1时扩容
			if (_n == _tables.size())
			{
				//HashTable<K, V> newHT;
				//newHT._tables.resize(_tables.size() * 2);

				 旧表重新计算负载到新表
				//for (size_t i = 0; i < _tables.size(); i++)
				//{
				//	Node* cur = _tables[i];
				//	while (cur)
				//	{
				//		newHT.Insert(cur->_kv);
				//		cur = cur->_next;
				//	}
				//}

				//_tables.swap(newHT._tables);

				vector<Node*> newTables(_tables.size() * 2, nullptr);
				for (size_t i = 0; i < _tables.size(); i++)
				{
					Node* cur = _tables[i];
					while (cur)
					{
						Node* next = cur->_next;
						// 头插新表的位置
						size_t hashi = hs(kot(cur->_data)) % newTables.size();
						cur->_next = newTables[hashi];
						newTables[hashi] = cur;

						cur = next;
					}

					_tables[i] = nullptr;
				}

				_tables.swap(newTables);
			}

			size_t hashi = hs(kot(data)) % _tables.size();
			Node* newnode = new Node(data);
			// 头插
			newnode->_next = _tables[hashi];
			_tables[hashi] = newnode;
			++_n;

			return make_pair(iterator(newnode, this), true);
		}

		iterator Find(const K& key)
		{
			KeyOfT kot;
			Hash hs;
			size_t hashi = hs(key) % _tables.size();
			Node* cur = _tables[hashi];
			while (cur)
			{
				if (kot(cur->_data) == key)
				{
					return iterator(cur, this);
				}

				cur = cur->_next;
			}

			return end();
		}

		bool Erase(const K& key)
		{
			KeyOfT kot;
			Hash hs;
			size_t hashi = hs(key) % _tables.size();
			Node* prev = nullptr;
			Node* cur = _tables[hashi];
			while (cur)
			{
				if (kot(cur->_data) == key)
				{
					// 删除的是第一个
					if (prev == nullptr)
					{
						_tables[hashi] = cur->_next;
					}
					else
					{
						prev->_next = cur->_next;
					}

					delete cur;

					return true;
				}
				else
				{
					prev = cur;
					cur = cur->_next;
				}
			}

			return false;
		}

	private:
		vector<Node*> _tables; // 指针数组
		size_t _n;

		//vector<list<pair<K, V>>> _tables;
	};
}

template<class V>
struct HashBucketNode
{
	HashBucketNode(const V& data)
		: _pNext(nullptr), _data(data)
	{}
	HashBucketNode<V>* _pNext;
	V _data;
};
// 本文所实现的哈希桶中key是唯一的
template<class V>
class HashBucket
{
	typedef HashBucketNode<V> Node;
	typedef Node* PNode;
public:
	HashBucket(size_t capacity = 3) : _size(0)
	{
		_ht.resize(GetNextPrime(capacity), nullptr);
	}
	// 哈希桶中的元素不能重复
	PNode* Insert(const V& data)
	{
		// 确认是否需要扩容。。。
		元素(data不会重复)，返回删除元素的下一个节点
			PNode* Erase(const V & data)
		{
			size_t bucketNo = HashFunc(data);
			PNode pCur = _ht[bucketNo];
			PNode pPrev = nullptr, pRet = nullptr;
			while (pCur)
			{
				if (pCur->_data == data)
				{
					if (pCur == _ht[bucketNo])
						_ht[bucketNo] = pCur->_pNext;
					else
						pPrev->_pNext = pCur->_pNext;
					pRet = pCur->_pNext;
					delete pCur;
					_size--;
					return pRet;
				}
			}
			return nullptr;
		}
		PNode* Find(const V & data);
		size_t Size()const;
		bool Empty()const;
		void Clear();
		bool BucketCount()const;
		void Swap(HashBucket<V, HF>&ht;
		~HashBucket();
	private:
		size_t HashFunc(const V & data)
		{
			return data % _ht.capacity();
		}
	private:
		vector<PNode*> _ht;
		size_t _size; // 哈希表中有效元素的个数
	}；

void _CheckCapacity()
	{
		size_t bucketCount = BucketCount();
		if (_size == bucketCount)
		{
			HashBucket<V, HF> newHt(bucketCount);
			for (size_t bucketIdx = 0; bucketIdx < bucketCount; ++bucketIdx)
			{
				PNode pCur = _ht[bucketIdx];
				while (pCur)
				{
					// 将该节点从原哈希表中拆出来
					_ht[bucketIdx] = pCur->_pNext;
					// 将该节点插入到新哈希表中
					size_t bucketNo = newHt.HashFunc(pCur->_data);
					pCur->_pNext = newHt._ht[bucketNo];
					newHt._ht[bucketNo] = pCur;
					pCur = _ht[bucketIdx];
				}
			}
			newHt._size = _size;
			this->Swap(newHt);
		}
	}