【C++】10.用哈希表封装myunordered_map和myunordered_set

1. 源码及框架分析

SGI-STL30版本源代码中没有unordered_map和unordered_set，SGI-STL30版本是C++11之前的STL 版本，这两个容器是C++11之后才更新的。但是SGI-STL30实现了哈希表，只容器的名字是hash_map 和hash_set，他是作为非标准的容器出现的，非标准是指非C++标准规定必须实现的，源代码在 hash_map/hash_set/stl_hash_map/stl_hash_set/stl_hashtable.h中 hash_map和hash_set的实现结构框架核心部分截取出来如下：

// stl_hash_set
template <class Value, class HashFcn = hash<Value>,class EqualKey = equal_to<Value>,class Alloc = alloc>
class hash_set
{
private:typedef hashtable<Value, Value, HashFcn, identity<Value>,EqualKey, Alloc> ht;ht rep;
public:typedef typename ht::key_type key_type;typedef typename ht::value_type value_type;typedef typename ht::hasher hasher;typedef typename ht::key_equal key_equal;typedef typename ht::const_iterator iterator;typedef typename ht::const_iterator const_iterator;hasher hash_funct() const { return rep.hash_funct(); }key_equal key_eq() const { return rep.key_eq(); }
};
// stl_hash_map
template <class Key, class T, class HashFcn = hash<Key>,class EqualKey = equal_to<Key>,class Alloc = alloc>
class hash_map
{
private:typedef hashtable<pair<const Key, T>, Key, HashFcn,select1st<pair<const Key, T> >, EqualKey, Alloc> ht;ht rep;
public:typedef typename ht::key_type key_type;typedef T data_type;typedef T mapped_type;typedef typename ht::value_type value_type;typedef typename ht::hasher hasher;typedef typename ht::key_equal key_equal;typedef typename ht::iterator iterator;typedef typename ht::const_iterator const_iterator;
};
// stl_hashtable.h
template <class Value, class Key, class HashFcn,class ExtractKey, class EqualKey,class Alloc>
class hashtable {
public:typedef Key key_type;typedef Value value_type;typedef HashFcn hasher;typedef EqualKey key_equal;
private:hasher hash;key_equal equals;ExtractKey get_key;typedef __hashtable_node<Value> node;vector<node*, Alloc> buckets;size_type num_elements;
public:typedef __hashtable_iterator<Value, Key, HashFcn, ExtractKey, EqualKey,Alloc> iterator;pair<iterator, bool> insert_unique(const value_type& obj);const_iterator find(const key_type& key) const;
};
template <class Value>
struct __hashtable_node
{__hashtable_node* next;Value val;
};

2. 模拟实现unordered_map和unordered_set

2.1 实现出复用哈希表的框架，并支持insert

我们这里相比源码调整⼀下，key参数就用K，value参数就用V，哈希表中的数据类型，我们使用T。

其次跟map和set相比而言unordered_map和unordered_set的模拟实现类结构更复杂⼀点，但是大框架和思路是完全类似的。因为HashTable实现了泛型不知道T参数导致是K，还是pair， 那么insert内部进行插入时要用K对象转换成整形取模和K比较相等，因为pair的value不参与计算取模，且默认⽀持的是key和value⼀起比较相等，我们需要时的任何时候只需要比较K对象，所以我们在unordered_map和unordered_set层分别实现⼀个MapKeyOfT和SetKeyOfT的仿函数传给 HashTable的KeyOfT，然后HashTable中通过KeyOfT仿函数取出T类型对象中的K对象，再转换成 整形取模和K比较相等，具体细节参考如下代码实现。

// MyUnorderedSet.h
namespace XiaoHai
{template<class K, class Hash = HashFunc<K>>class unordered_set{struct SetKeyOfT{const K& operator()(const K& key){return key;}};public:bool insert(const K& key){return _ht.Insert(key);}private:hash_bucket::HashTable<K, K, SetKeyOfT, Hash> _ht;};
}
// MyUnorderedMap.h
namespace XiaoHai
{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:bool insert(const pair<K, V>& kv){return _ht.Insert(kv);}private:hash_bucket::HashTable<K, pair<K, V>, MapKeyOfT, Hash> _ht;};
}
// HashTable.h
template<class K>
struct HashFunc
{size_t operator()(const K& key){return (size_t)key;}
};
namespace hash_bucket
{template<class T>struct HashNode{T _data;HashNode<T>* _next;HashNode(const T& data):_data(data), _next(nullptr){}};// 实现步骤： // 1、实现哈希表 // 2、封装unordered_map和unordered_set的框架 解决KeyOfT // 3、iterator // 4、const_iterator // 5、key不⽀持修改的问题 // 6、operator[] template<class K, class T, class KeyOfT, class Hash>class HashTable{typedef HashNode<T> Node;inline unsigned long __stl_next_prime(unsigned long n){static const int __stl_num_primes = 28;static const unsigned long __stl_prime_list[__stl_num_primes] ={53, 97, 193, 389, 769,1543, 3079, 6151, 12289, 24593,49157, 98317, 196613, 393241, 786433,1572869, 3145739, 6291469, 12582917, 25165843,50331653, 100663319, 201326611, 402653189, 805306457,1610612741, 3221225473, 4294967291};const unsigned long* first = __stl_prime_list;const unsigned long* last = __stl_prime_list + __stl_num_primes;const unsigned long* pos = lower_bound(first, last, n);return pos == last ? *(last - 1) : *pos;}public:HashTable(){_tables.resize(__stl_next_prime(_tables.size()), nullptr);}~HashTable(){// 依次把每个桶释放 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;}}bool Insert(const T& data){KeyOfT kot;if (Find(kot(data)))return false;Hash hs;size_t hashi = hs(kot(data)) % _tables.size();// 负载因⼦==1扩容 if (_n == _tables.size()){vector<Node*> newtables(__stl_next_prime(_tables.size()),nullptr);for (size_t i = 0; i < _tables.size(); i++){Node* cur = _tables[i];while (cur){Node* next = cur->_next;// 旧表中结点，挪动新表重新映射的位置 size_t hashi = hs(kot(cur->_data)) % newtables.size();// 头插到新表 cur->_next = newtables[hashi];newtables[hashi] = cur;cur = next;}_tables[i] = nullptr;}_tables.swap(newtables);}// 头插 Node* newnode = new Node(data);newnode->_next = _tables[hashi];_tables[hashi] = newnode;++_n;return true;}private:vector<Node*> _tables; // 指针数组 size_t _n = 0; // 表中存储数据个数 };
}

2.2 支持iterator的实现

iterator核心源代码

template <class Value, class Key, class HashFcn,class ExtractKey, class EqualKey, class Alloc>
struct __hashtable_iterator {typedef hashtable<Value, Key, HashFcn, ExtractKey, EqualKey, Alloc>hashtable;typedef __hashtable_iterator<Value, Key, HashFcn,ExtractKey, EqualKey, Alloc>iterator;typedef __hashtable_const_iterator<Value, Key, HashFcn,ExtractKey, EqualKey, Alloc>const_iterator;typedef __hashtable_node<Value> node;typedef forward_iterator_tag iterator_category;typedef Value value_type;node* cur;hashtable* ht;__hashtable_iterator(node* n, hashtable* tab) : cur(n), ht(tab) {}__hashtable_iterator() {}reference operator*() const { return cur->val; }
#ifndef __SGI_STL_NO_ARROW_OPERATORpointer operator->() const { return &(operator*()); }
#endif /* __SGI_STL_NO_ARROW_OPERATOR */iterator& operator++();iterator operator++(int);bool operator==(const iterator& it) const { return cur == it.cur; }bool operator!=(const iterator& it) const { return cur != it.cur; }
};
template <class V, class K, class HF, class ExK, class EqK, class A>
__hashtable_iterator<V, K, HF, ExK, EqK, A>&
__hashtable_iterator<V, K, HF, ExK, EqK, A>::operator++()
{const node* old = cur;cur = cur->next;if (!cur) {size_type bucket = ht->bkt_num(old->val);while (!cur && ++bucket < ht->buckets.size())cur = ht->buckets[bucket];}return *this;
}

iterator实现思路分析        

iterator实现的⼤框架跟list的iterator思路是⼀致的，⽤⼀个类型封装结点的指针，再通过重载运算 符实现，迭代器像指针⼀样访问的⾏为，要注意的是哈希表的迭代器是单向迭代器。

这⾥的难点是operator++的实现。iterator中有⼀个指向结点的指针，如果当前桶下⾯还有结点， 则结点的指针指向下⼀个结点即可。如果当前桶⾛完了，则需要想办法计算找到下⼀个桶。这⾥的 难点是反⽽是结构设计的问题，参考上⾯的源码，我们可以看到iterator中除了有结点的指针，还 有哈希表对象的指针，这样当前桶⾛完了，要计算下⼀个桶就相对容易多了，⽤key值计算出当前 桶位置，依次往后找下⼀个不为空的桶即可。

begin()返回第⼀个桶中第⼀个节点指针构造的迭代器，这⾥end()返回迭代器可以⽤空表⽰。

unordered_set的iterator也不⽀持修改，我们把unordered_set的第⼆个模板参数改成constK即 可， HashTableconst K, SetKeyOfT, Hash> _ht;

unordered_map的iterator不⽀持修改key但是可以修改value，我们把unordered_map的第⼆个 模板参数pair的第⼀个参数改成constK即可， HashTablepair, MapKeyOfT, Hash> _ht;

⽀持完整的迭代器还有很多细节需要修改，具体参考下⾯题的代码。

2.3 map支持[]

unordered_map要⽀持[]主要需要修改insert返回值⽀持，修改HashTable中的insert返回值为 pair Insert(const T& data)

有了insert⽀持[]实现就很简单了，具体参考下⾯代码实现

2.4 bit::unordered_map和bit::unordered_set代码实现

// MyUnorderedSet.h
namespace XiaoHai
{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, const K, SetKeyOfT,Hash>::Iterator iterator;typedef typename hash_bucket::HashTable<K, const K, SetKeyOfT,Hash>::ConstIterator 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<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:hash_bucket::HashTable<K, const K, SetKeyOfT, Hash> _ht;};void test_set(){unordered_set<int> s;int a[] = { 4, 2, 6, 1, 3, 5, 15, 7, 16, 14, 3,3,15 };for (auto e : a){s.insert(e);}for (auto e : s){cout << e << " ";}cout << endl;unordered_set<int>::iterator it = s.begin();while (it != s.end()){// 不⽀持修改 //*it += 1;cout << *it << " ";++it;}cout << endl;}
}

// MyUnorderedMap.h
namespace XiaoHai
{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;typedef typename hash_bucket::HashTable<K, pair<const K, V>,MapKeyOfT, Hash>::ConstIterator 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<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;}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({ "sort", "排序" });dict.insert({ "left", "左边" });dict.insert({ "right", "右边" });dict["left"] = "左边，剩余";dict["insert"] = "插⼊";dict["string"];unordered_map<string, string>::iterator it = dict.begin();while (it != dict.end()){// 不能修改first，可以修改second //it->first += 'x';it->second += 'x';cout << it->first << ":" << it->second << endl;++it;}cout << endl;}
}

// HashTable.h
template<class K>
struct HashFunc
{size_t operator()(const K& key){return (size_t)key;}
};
// 特化 
template<>
struct HashFunc<string>
{size_t operator()(const string& key){size_t hash = 0;for (auto e : key){hash *= 131;hash += e;}return hash;}
};
namespace hash_bucket
{template<class T>struct HashNode{T _data;HashNode<T>* _next;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 Ptr, class Ref, class KeyOfT, class Hash>struct HTIterator{typedef HashNode<T> Node;typedef HTIterator<K, T, Ptr, Ref, KeyOfT, Hash> Self;Node* _node;const HashTable<K, T, KeyOfT, Hash>* _pht;HTIterator(Node* node, const HashTable<K, T, KeyOfT, Hash>* pht):_node(node), _pht(pht){}Ref operator*(){return _node->_data;}Ptr operator->(){return &_node->_data;}bool operator!=(const Self& s){return _node != s._node;}Self& operator++(){if (_node->_next){// 当前桶还有节点 _node = _node->_next;}else{// 当前桶⾛完了，找下⼀个不为空的桶 KeyOfT kot;Hash hs;size_t hashi = hs(kot(_node->_data)) % _pht -> _tables.size();++hashi;while (hashi < _pht->_tables.size()){if (_pht->_tables[hashi]){break;}++hashi;}if (hashi == _pht->_tables.size()){_node = nullptr; // end()}else{_node = _pht->_tables[hashi];}}return *this;}};template<class K, class T, class KeyOfT, class Hash>class HashTable{// 友元声明 template<class K, class T, class Ptr, class Ref, class KeyOfT, classHash>friend struct HTIterator;typedef HashNode<T> Node;public:typedef HTIterator<K, T, T*, T&, KeyOfT, Hash> Iterator;typedef HTIterator<K, T, const T*, const T&, KeyOfT, Hash>ConstIterator;Iterator Begin(){if (_n == 0)return End();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);}ConstIterator Begin() const{if (_n == 0)return End();for (size_t i = 0; i < _tables.size(); i++){Node* cur = _tables[i];if (cur){return ConstIterator(cur, this);}}return End();}ConstIterator End() const{return ConstIterator(nullptr, this);}inline unsigned long __stl_next_prime(unsigned long n){static const int __stl_num_primes = 28;static const unsigned long __stl_prime_list[__stl_num_primes] ={53, 97, 193, 389, 769,1543, 3079, 6151, 12289, 24593,
49157, 98317, 196613, 393241, 786433,1572869, 3145739, 6291469, 12582917, 25165843,50331653, 100663319, 201326611, 402653189, 805306457,1610612741, 3221225473, 4294967291};const unsigned long* first = __stl_prime_list;const unsigned long* last = __stl_prime_list +__stl_num_primes;const unsigned long* pos = lower_bound(first, last, n);return pos == last ? *(last - 1) : *pos;}HashTable(){_tables.resize(__stl_next_prime(_tables.size()), nullptr);}~HashTable(){// 依次把每个桶释放 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;size_t hashi = hs(kot(data)) % _tables.size();// 负载因⼦==1扩容 if (_n == _tables.size()){vector<Node*>newtables(__stl_next_prime(_tables.size() + 1), nullptr);for (size_t i = 0; i < _tables.size(); i++){Node* cur = _tables[i];while (cur){Node* next = cur->_next;// 旧表中节点，挪动新表重新映射的位置 size_t hashi = hs(kot(cur->_data)) %newtables.size();// 头插到新表 cur->_next = newtables[hashi];newtables[hashi] = cur;cur = next;}_tables[i] = nullptr;}_tables.swap(newtables);}// 头插 Node* newnode = new Node(data);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){if (prev == nullptr){_tables[hashi] = cur->_next;}else{prev->_next = cur->_next;}delete cur;--_n;return true;}prev = cur;cur = cur->_next;}return false;}private:vector<Node*> _tables; // 指针数组 size_t _n = 0; // 表中存储数据个数 };
}