Bootstrap

哈希表的封装

1. 哈希表的封装

迭代器设计:不用考虑往回走,单向迭代器

image-20220911135757301

#pragma once
#include<vector>

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


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

		return hash;
	}
};

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

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

	template<class K, class T, class KeyOfT, class HashFunc>
	class HashTable;

	template<class K, class T, class KeyOfT, class HashFunc>
	class __HTIterator
	{
		typedef HashNode<T> Node;
		typedef __HTIterator<K, T, KeyOfT, HashFunc> Self;
	public:
		Node* _node;
		HashTable<K, T, KeyOfT, HashFunc>* _pht;

		__HTIterator() {}

		__HTIterator(Node* node, HashTable<K, T, KeyOfT, HashFunc>* pht)
			:_node(node)
			, _pht(pht)
		{}

		Self& operator++()
		{
			if (_node->_next)
			{
				_node = _node->_next;
			}
			else
			{
				KeyOfT kot;
				HashFunc hf;
				size_t hashi = hf(kot(_node->_data)) % _pht->_tables.size();
				++hashi;
				//找下一个不为空的桶
				for (; hashi < _pht->_tables.size(); ++hashi)
				{
					if (_pht->_tables[hashi])
					{
						_node = _pht->_tables[hashi];
						break;
					}
				}

				// 没有找到不为空的桶,用nullptr去做end标识
				if (hashi == _pht->_tables.size())
				{
					_node = nullptr;
				}
			}

			return *this;
		}

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

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

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

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

	// unordered_map ->HashTable<K, pair<K, V>, MapKeyOfT> _ht;
	// unordered_set ->HashTable<K, K, SetKeyOfT> _ht;
	template<class K, class T, class KeyOfT, class HashFunc>
	class HashTable
	{
		template<class K, class T, class KeyOfT, class HashFunc>
		friend class __HTIterator;

		typedef HashNode<T> Node;
	public:
		typedef __HTIterator<K, T, KeyOfT, HashFunc> iterator;

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

			return end();
		}

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

		~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;
			}
		}

		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
			};

			// 获取比prime大那一个素数
			size_t i = 0;
			for (; i < PRIMECOUNT; ++i)
			{
				if (primeList[i] > prime)
					return primeList[i];
			}

			return primeList[i];
		}

		pair<iterator, bool> Insert(const T& data)
		{
			HashFunc hf;
			KeyOfT kot;

			iterator pos = Find(kot(data));
			if (pos != end())
			{
				return make_pair(pos, false);
			}

			// 负载因子 == 1 扩容
			if (_tables.size() == _n)
			{
				//size_t newSize = _tables.size() == 0 ? 11 : _tables.size() * 2;
				size_t newSize = GetNextPrime(_tables.size());
				if (newSize != _tables.size())
				{
					vector<Node*> newTable;
					newTable.resize(newSize, nullptr);
					for (size_t i = 0; i < _tables.size(); ++i)
					{
						Node* cur = _tables[i];
						while (cur)
						{
							Node* next = cur->_next;

							size_t hashi = hf(kot(cur->_data)) % newSize;
							cur->_next = newTable[hashi];
							newTable[hashi] = cur;

							cur = next;
						}

						_tables[i] = nullptr;
					}

					newTable.swap(_tables);
				}
			}

			size_t hashi = hf(kot(data));
			hashi %= _tables.size();

			// 头插到对应的桶即可
			Node* newnode = new Node(data);
			newnode->_next = _tables[hashi];
			_tables[hashi] = newnode;

			++_n;

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

		iterator Find(const K& key)
		{
			if (_tables.size() == 0)
			{
				return iterator(nullptr, this);
			}

			KeyOfT kot;
			HashFunc hf;
			size_t hashi = hf(key);
			//size_t hashi = HashFunc()(key);

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

				cur = cur->_next;
			}

			return iterator(nullptr, this);
		}

		bool Erase(const K& key)
		{
			if (_tables.size() == 0)
			{
				return false;
			}

			HashFunc hf;
			KeyOfT kot;
			size_t hashi = hf(key);
			hashi %= _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;
		}

	private:
		// 指针数组
		vector<Node*> _tables;
		size_t _n = 0;
	};
}

2. unordered_set

#pragma once

#include "HashTable.h"

namespace Yuucho
{
	// 把仿函数放在各自的类模板参数中,
    // 这样当你存储的数据不支持取%时自己写一个仿函数就好了
    // 不用去改哈希表的代码
	template<class K, class HashFunc = DefaultHash<K>>
	class unordered_set
	{
        // 内部类取出key
		struct SetKeyOfT
		{
			const K& operator()(const K& key)
			{
				return key;
			}
		};
	public:
        // 提供迭代器 typename:区分内嵌类型和静态成员类型,表示这是一个内嵌类型
		typedef typename Bucket::HashTable<K, K, SetKeyOfT, HashFunc>::iterator iterator;

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

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

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

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

		bool erase(const K& key)
		{
			return _ht.Erase(key);
		}
	private:
        // 不加Bucket会不认识HashTable,报一个缺少在<前缺少;的error
		Bucket::HashTable<K, K, SetKeyOfT, HashFunc> _ht;
	};

	struct Date
	{
		Date(int year = 1, int month = 1, int day = 1)
		:_year(year)
		, _month(month)
		, _day(day)
		{}

		bool operator==(const Date& d) const
		{
			return _year == d._year
				&& _month == d._month
				&& _day == d._day;
		}

		int _year;
		int _month;
		int _day;
	};

	struct DateHash
	{
		size_t operator()(const Date& d)
		{
			//return d._year + d._month + d._day;
			size_t hash = 0;
			hash += d._year;
			hash *= 131;
			hash += d._month;
			hash *= 1313;
			hash += d._day;

			cout << hash << endl;

			return hash;
		}
	};

	void test_set()
	{
		unordered_set<int> s;
		//set<int> s;
		s.insert(2);
		s.insert(3);
		s.insert(1);
		s.insert(2);
		s.insert(5);
		s.insert(12);

		//unordered_set<int>::iterator it = s.begin();
		unordered_set<int>::iterator it;
		it = s.begin();

		//auto it = s.begin();
		while (it != s.end())
		{
			cout << *it << " ";
			++it;
		}
		cout << endl;

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

		unordered_set<Date, DateHash> sd;
		sd.insert(Date(2022, 3, 4));
		sd.insert(Date(2022, 4, 3));
	}
}

3. unordered_map

#pragma once

#include "HashTable.h"

namespace bit
{
	template<class K, class V, class HashFunc = DefaultHash<K>>
	class unordered_map
	{
		struct MapKeyOfT
		{
			const K& operator()(const pair<K, V>& kv)
			{
				return kv.first;
			}
		};
	public:
		typedef typename Bucket::HashTable<K, pair<K, V>, MapKeyOfT, HashFunc>::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);	
		}

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

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

		V& operator[](const K& key)
		{
			pair<iterator, bool> ret = insert(make_pair(key, V()));
			return ret.first->second;
		}

	private:
		Bucket::HashTable<K, pair<K, V>, MapKeyOfT, HashFunc> _ht;
	};

	void test_map()
	{
		unordered_map<string, string> dict;
		dict.insert(make_pair("sort", ""));
		dict.insert(make_pair("left", ""));
		dict.insert(make_pair("left", "ʣ"));
		dict["string"];
		dict["left"] = "ʣ";
		dict["string"] = "ַ";

		unordered_map<string, string>::iterator it = dict.begin();
		while (it != dict.end())
		{
			cout << it->first << " " << it->second << endl;
			++it;
		}

		cout << endl;

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