【C++航海王：追寻罗杰的编程之路】一篇文章带你认识哈希

#define _CRT_SECURE_NO_WARNINGS 1

#include <iostream>
using namespace std;

// 哈希表每个空间给个标记
// EMPTY此位置空， EXIST此位置已经有元素， DELETE元素已经删除
enum State 
{ 
	EMPTY, EXIST, DELETE 
};

#define _CRT_SECURE_NO_WARNINGS 1

#include <iostream>
using namespace std;

// 哈希表每个空间给个标记
// EMPTY此位置空， EXIST此位置已经有元素， DELETE元素已经删除
enum State 
{ 
	EMPTY, EXIST, DELETE 
};

// 注意：假如实现的哈希表中元素唯一，即key相同的元素不再进行插入
// 为了实现简单，此哈希表中我们将比较直接与元素绑定在一起
template<class K, class V>
class HashTable
{
	struct Elem
	{
		pair<K, V> _val;
		State _state;
	};

public:
	HashTable(size_t capacity = 3)
		: _ht(capacity), _size(0)
	{
		for (size_t i = 0; i < capacity; ++i)
			_ht[i]._state = EMPTY;
	}

	bool Insert(const pair<K, V>& val)
	{
		// 检测哈希表底层空间是否充足
		// _CheckCapacity();
		size_t hashAddr = HashFunc(key);

		// size_t startAddr = hashAddr;
		while (_ht[hashAddr]._state != EMPTY)
		{
			if (_ht[hashAddr]._state == EXIST && _ht[hashAddr]._val.first
				== key)
				return false;

			hashAddr++;
			if (hashAddr == _ht.capacity())
				hashAddr = 0;
		/*
		// 转一圈也没有找到，注意：动态哈希表，该种情况可以不用考虑，哈希表中元
		素个数到达一定的数量，哈希冲突概率会增大，需要扩容来降低哈希冲突，
		因此哈希表中元素是不会存满的
			 if(hashAddr == startAddr)
			 	return false;
		*/
		}

		// 插入元素
		_ht[hashAddr]._state = EXIST;
		_ht[hashAddr]._val = val;
		_size++;

		return true;
	}

	int Find(const K& key)
	{
		size_t hashAddr = HashFunc(key);
		while (_ht[hashAddr]._state != EMPTY)
		{
			if (_ht[hashAddr]._state == EXIST && 
				_ht[hashAddr]._val.first == key)
				return hashAddr;

			hashAddr++;
		}

		return hashAddr;
	}
	bool Erase(const K & key)
	{
		int index = Find(key);
		if (-1 != index)
		{
			_ht[index]._state = DELETE;
			_size++;

			return true;
		}

		return false;
	}

	size_t Size()const;
	bool Empty() const;
	void Swap(HashTable<K, V, HF>&ht);

private:
	size_t HashFunc(const K & key)
	{
		return key % _ht.capacity();
	}

private:
	vector<Elem> _ht;
	size_t _size;
};

#define _CRT_SECURE_NO_WARNINGS 1

#include <iostream>
using namespace std;

template<class V>
struct HashBucketNode
{
	HashBucketNode(const V& data)
		: _pNext(nullptr), _data(data)
	{}
	HashBucketNode<V>* _pNext;
	V _data;
};

// 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。。。
		 // _CheckCapacity();

		// 1. 计算元素所在的桶号
		size_t bucketNo = HashFunc(data);

		// 2. 检测该元素是否在桶中
		PNode pCur = _ht[bucketNo];
		while (pCur)
		{
			if (pCur->_data == data)
				return pCur;

			pCur = pCur->_pNext;
		}

		// 3. 插入新元素
		pCur = new Node(data);
		pCur->_pNext = _ht[bucketNo];
		_ht[bucketNo] = pCur;
		_size++;

		return pCur;
	}

	// 删除哈希桶中为data的元素(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);
		}
	}

// 哈希函数采用处理余数法，被模的key必须要为整形才可以处理，此处提供将key转化为整形的方法
// 整形数据不需要转化
template<class T>
class DefHashF
{
public:
	size_t operator()(const T& val)
	{
		return val;
	}
};

// key为字符串类型，需要将其转化为整形
class Str2Int
{
public:
	size_t operator()(const string& s)
	{
		const char* str = s.c_str();
		unsigned int seed = 131; // 31 131 1313 13131 131313
		unsigned int hash = 0;
		while (*str)
		{
			hash = hash * seed + (*str++);
		}

		return (hash & 0x7FFFFFFF);
	}
};

// 为了实现简单，此哈希表中我们将比较直接与元素绑定在一起
template<class V, class HF>
class HashBucket
{
	// ……
private:
	size_t HashFunc(const V& data)
	{
		return HF()(data.first) % _ht.capacity();
	}
};

size_t GetNextPrime(size_t prime)
{
	const int PRIMECOUNT = 28;
	static const size_t primeList[PRIMECOUNT] =
	{
	53ul, 97ul, 193ul, 389ul, 769ul,
	1543ul, 3079ul, 6151ul, 12289ul, 24593ul,
	49157ul, 98317ul, 196613ul, 393241ul, 786433ul,
	1572869ul, 3145739ul, 6291469ul, 12582917ul,
   25165843ul,
	50331653ul, 100663319ul, 201326611ul, 402653189ul,
   805306457ul,
	1610612741ul, 3221225473ul, 4294967291ul
	};

	size_t i = 0;
	for (; i < PRIMECOUNT; ++i)
	{
		if (primeList[i] > prime)
			return primeList[i];
	}

	return primeList[i];
}

#pragma once

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

//HashFunc<string>
template<>
struct HashFunc<string>
{
	size_t operator()(const string& key)
	{
		// BKDR
		size_t hash = 0;
		for (auto e : key)
		{
			hash *= 31;
			hash += e;
		}

		//cout << key << ":" << hash << endl;
		return hash;
	}
};

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

	template<class K, class V>
	struct HashData
	{
		pair<K, V> _kv;
		Status _s;          //状态
	};

	//struct HashFuncString
	//{
	//	size_t operator()(const string& key)
	//	{
	//		// BKDR
	//		size_t hash = 0;
	//		for (auto e : key)
	//		{
	//			hash *= 31;
	//			hash += e;
	//		}

	//		cout << key << ":" << hash << endl;
	//		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;

			// 负载因子0.7就扩容
			if (_n * 10 / _tables.size() == 7)
			{
				size_t newSize = _tables.size() * 2;
				HashTable<K, V, Hash> newHT;
				newHT._tables.resize(newSize);

				// 遍历旧表
				for (size_t i = 0; i < _tables.size(); i++)
				{
					if (_tables[i]._s == EXIST)
					{
						newHT.Insert(_tables[i]._kv);
					}
				}

				_tables.swap(newHT._tables);
			}

			Hash hf;
			// 线性探测
			size_t hashi = hf(kv.first) % _tables.size();
			while (_tables[hashi]._s == EXIST)
			{
				hashi++;

				hashi %= _tables.size();
			}

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

			return true;
		}

		HashData<K, V>* Find(const K& key)
		{
			Hash hf;

			size_t hashi = hf(key) % _tables.size();
			while (_tables[hashi]._s != EMPTY)
			{
				if (_tables[hashi]._s == EXIST
					&& _tables[hashi]._kv.first == key)
				{
					return &_tables[hashi];
				}

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

			return NULL;
		}

		// 伪删除法
		bool Erase(const K& key)
		{
			HashData<K, V>* ret = Find(key);
			if (ret)
			{
				ret->_s = DELETE;
				--_n;

				return true;
			}
			else
			{
				return false;
			}
		}

		void Print()
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				if (_tables[i]._s == EXIST)
				{
					//printf("[%d]->%d\n", i, _tables[i]._kv.first);
					cout << "[" << i << "]->" << _tables[i]._kv.first << ":" << _tables[i]._kv.second << endl;
				}
				else if (_tables[i]._s == EMPTY)
				{
					printf("[%d]->\n", i);
				}
				else
				{
					printf("[%d]->D\n", i);
				}
			}

			cout << endl;
		}

	private:
		vector<HashData<K, V>> _tables;
		size_t _n = 0; // 存储的关键字的个数
	};

	void TestHT1()
	{
		HashTable<int, int> ht;
		int a[] = { 4,14,24,34,5,7,1 };
		for (auto e : a)
		{
			ht.Insert(make_pair(e, e));
		}

		ht.Insert(make_pair(3, 3));
		ht.Insert(make_pair(3, 3));
		ht.Insert(make_pair(-3, -3));
		ht.Print();

		ht.Erase(3);
		ht.Print();

		if (ht.Find(3))
		{
			cout << "3存在" << endl;
		}
		else
		{
			cout << "3不存在" << endl;
		}

		ht.Insert(make_pair(3, 3));
		ht.Insert(make_pair(23, 3));
		ht.Print();
	}

	void TestHT2()
	{
		string arr[] = { "香蕉", "甜瓜","苹果", "西瓜", "苹果", "西瓜", "苹果", "苹果", "西瓜", "苹果", "香蕉", "苹果", "香蕉" };
		//HashTable<string, int, HashFuncString> ht;
		HashTable<string, int> ht;
		for (auto& e : arr)
		{
			//auto ret = ht.Find(e);
			HashData<string, int>* ret = ht.Find(e);
			if (ret)
			{
				ret->_kv.second++;
			}
			else
			{
				ht.Insert(make_pair(e, 1));
			}
		}

		ht.Print();

		ht.Insert(make_pair("apple", 1));
		ht.Insert(make_pair("sort", 1));

		ht.Insert(make_pair("abc", 1));
		ht.Insert(make_pair("acb", 1));
		ht.Insert(make_pair("aad", 1));

		ht.Print();
	}
}

namespace hash_bucket
{
	template<class T>
	struct HashNode
	{
		HashNode<T>* _next;
		T _data;

		HashNode(const T& data)
			:_data(data)
			, _next(nullptr)
		{}
	};

	// 前置声明
	template<class K, class T, class KeyOfT, class Hash>
	class HashTable;

	template<class K, class T, class Ref, class Ptr, class KeyOfT, class Hash>
	struct __HTIterator
	{
		typedef HashNode<T> Node;
		typedef __HTIterator<K, T, Ref, Ptr, KeyOfT, Hash> Self;
		Node* _node;
		const HashTable<K, T, KeyOfT, Hash>* _pht;

		// vector<Node*> * _ptb;

		size_t _hashi;

		__HTIterator(Node* node, HashTable<K, T, KeyOfT, Hash>* pht, size_t hashi)
			:_node(node)
			, _pht(pht)
			, _hashi(hashi)
		{}

		__HTIterator(Node* node, const HashTable<K, T, KeyOfT, Hash>* pht, size_t hashi)
			:_node(node)
			, _pht(pht)
			, _hashi(hashi)
		{}

		Self& operator++()
		{
			if (_node->_next)
			{
				// 当前桶还有节点，走到下一个节点
				_node = _node->_next;
			}
			else
			{
				// 当前桶已经走完了，找下一个桶开始
				//KeyOfT kot;
				//Hash hf;
				//size_t hashi = hf(kot(_node->_data)) % _pht._tables.size();
				++_hashi;
				while (_hashi < _pht->_tables.size())
				{
					if (_pht->_tables[_hashi])
					{
						_node = _pht->_tables[_hashi];
						break;
					}

					++_hashi;
				}

				if (_hashi == _pht->_tables.size())
				{
					_node = nullptr;
				}
			}

			return *this;
		}

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

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

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

	// unordered_set -> Hashtable<K, K>
	// unordered_map -> Hashtable<K, pair<K, V>>
	template<class K, class T, class KeyOfT, class Hash>
	class HashTable
	{
		typedef HashNode<T> Node;

		template<class K, class T, class Ref, class Ptr, class KeyOfT, class Hash>
		friend struct __HTIterator;

	public:
		typedef __HTIterator<K, T, T&, T*, KeyOfT, Hash> iterator;
		typedef __HTIterator<K, T, const T&, const T*, KeyOfT, Hash> const_iterator;

		iterator begin()
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				if (_tables[i])
				{
					return iterator(_tables[i], this, i);
				}
			}

			return end();
		}

		iterator end()
		{
			return iterator(nullptr, this, -1);
		}

		const_iterator begin() const
		{
			for (size_t i = 0; i < _tables.size(); i++)
			{
				if (_tables[i])
				{
					return const_iterator(_tables[i], this, i);
				}
			}

			return end();
		}

		// this-> const HashTable<K, T, KeyOfT, Hash>*
		const_iterator end() const
		{
			return const_iterator(nullptr, this, -1);
		}

		HashTable()
		{
			_tables.resize(10);
		}

		~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)
		{
			Hash hf;
			KeyOfT kot;

			iterator it = Find(kot(data));
			if (it != end())
				return make_pair(it, false);

			// 负载因子最大到1
			if (_n == _tables.size())
			{
				vector<Node*> newTables;
				newTables.resize(_tables.size() * 2, nullptr);
				// 遍历旧表
				for (size_t i = 0; i < _tables.size(); i++)
				{
					Node* cur = _tables[i];
					while (cur)
					{
						Node* next = cur->_next;

						// 挪动到映射的新表
						size_t hashi = hf(kot(cur->_data)) % newTables.size();
						cur->_next = newTables[i];
						newTables[hashi] = cur;

						cur = next;
					}

					_tables[i] = nullptr;
				}

				_tables.swap(newTables);
			}

			size_t hashi = hf(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, hashi), true);
		}

		iterator Find(const K& key)
		{
			Hash hf;
			KeyOfT kot;

			size_t hashi = hf(key) % _tables.size();
			Node* cur = _tables[hashi];
			while (cur)
			{
				if (kot(cur->_data) == key)
				{
					return iterator(cur, this, hashi);
				}

				cur = cur->_next;
			}

			return end();
		}

		bool Erase(const K& key)
		{
			Hash hf;
			KeyOfT kot;

			size_t hashi = hf(key) % _tables.size();
			Node* prev = nullptr;
			Node* cur = _tables[hashi];
			while (cur)
			{
				if (kot(cur->_data) == key)
				{
					if (prev == nullptr)
					{
						_tables[hashi] = cur->_next;
					}
					else
					{
						prev->_next = cur->_next;
					}
					delete cur;

					return true;
				}

				prev = cur;
				cur = cur->_next;
			}

			return false;
		}

		void Some()
		{
			size_t bucketSize = 0;
			size_t maxBucketLen = 0;
			size_t sum = 0;
			double averageBucketLen = 0;

			for (size_t i = 0; i < _tables.size(); i++)
			{
				Node* cur = _tables[i];
				if (cur)
				{
					++bucketSize;
				}

				size_t bucketLen = 0;
				while (cur)
				{
					++bucketLen;
					cur = cur->_next;
				}

				sum += bucketLen;
				if (bucketLen > maxBucketLen)
				{
					maxBucketLen = bucketLen;
				}
			}

			averageBucketLen = (double)sum / (double)bucketSize;

			printf("all bucketSize:%d\n", _tables.size());
			printf("bucketSize:%d\n", bucketSize);
			printf("maxBucketLen:%d\n", maxBucketLen);
			printf("averageBucketLen:%lf\n\n", averageBucketLen);
		}

	private:
		vector<Node*> _tables;
		size_t _n = 0;
	};
}

#pragma once
#include"HashTable.h"

namespace fyd
{
	template<class K, class V, class Hash = HashFunc<K>>
	class unordered_map
	{
		struct MapKeyOfT
		{
			const K& operator()(const pair<K, V>& kv)
			{
				return kv.first;
			}
		};

	public:
		typedef typename hash_bucket::HashTable<K, pair<const K, V>, MapKeyOfT, Hash>::iterator iterator;

		iterator begin()
		{
			return _ht.begin();
		}

		iterator end()
		{
			return _ht.end();
		}

		pair<iterator, bool> insert(const pair<K, V>& kv)
		{
			return _ht.Insert(kv);
		}

		V& operator[](const K& key)
		{
			pair<iterator, bool> ret = _ht.Insert(make_pair(key, V()));

			return ret.first->second;
		}

		const V& operator[](const K& key) const
		{
			pair<iterator, bool> ret = _ht.Insert(make_pair(key, V()));

			return ret.first->second;
		}

		iterator find(const K& key)
		{
			return _ht.Find(key);
		}

		bool erase(const K& key)
		{
			return _ht.Erase(key);
		}

	private:
		hash_bucket::HashTable<K, pair<const K, V>, MapKeyOfT, Hash> _ht;
	};

	void test_map()
	{
		unordered_map<string, string> dict;
		dict.insert(make_pair("sort", ""));
		dict.insert(make_pair("string", "ַ"));
		dict.insert(make_pair("insert", ""));

		for (auto& kv : dict)
		{
			//kv.first += 'x';
			kv.second += 'x';

			cout << kv.first << ":" << kv.second << endl;
		}
		cout << endl;

		string arr[] = { "㽶", "","ƻ", "", "ƻ", "", "ƻ", "ƻ", "", "ƻ", "㽶", "ƻ", "㽶" };
		unordered_map<string, int> count_map;
		for (auto& e : arr)
		{
			count_map[e]++;
		}

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

#pragma once
#include"HashTable.h"

namespace fyd
{
	template<class K, class Hash = HashFunc<K>>
	class unordered_set
	{
		struct SetKeyOfT
		{
			const K& operator()(const K& key)
			{
				return key;
			}
		};
	public:
		typedef typename hash_bucket::HashTable<K, K, SetKeyOfT, Hash>::const_iterator iterator;
		typedef typename hash_bucket::HashTable<K, K, SetKeyOfT, Hash>::const_iterator const_iterator;

		/*iterator begin()
		{
			return _ht.begin();
		}

		iterator end()
		{
			return _ht.end();
		}*/

		const_iterator begin() const
		{
			return _ht.begin();
		}

		const_iterator end() const
		{
			return _ht.end();
		}

		pair<const_iterator, bool> insert(const K& key)
		{
			auto ret = _ht.Insert(key);
			return pair<const_iterator, bool>(const_iterator(ret.first._node, ret.first._pht, ret.first._hashi), ret.second);
		}

		iterator find(const K& key)
		{
			return _ht.Find(key);
		}

		bool erase(const K& key)
		{
			return _ht.Erase(key);
		}
	private:
		hash_bucket::HashTable<K, K, SetKeyOfT, Hash> _ht;
	};

	void test_set()
	{
		unordered_set<int> us;
		us.insert(5);
		us.insert(15);
		us.insert(52);
		us.insert(3);

		unordered_set<int>::iterator it = us.begin();
		while (it != us.end())
		{
			//*it += 5;
			cout << *it << " ";
			++it;
		}
		cout << endl;

		for (auto e : us)
		{
			cout << e << " ";
		}
		cout << endl;
	}
}