关联式容器-基于hash

5.7 hashtable

1、碰撞问题的解决

线性探测：负载系数在0-1之间（元素个数除以表格大小）。

二次探测：如果位置已被占用，则依序尝试H+1^2, H+2^2, ... , H+i^2，而不是像线性探测那样尝试H+1, H+2 ... , H+i。

开链法：负载系数大于1。

2、哈希表的bucket和node

template <class Value>
struct __hashtable_node{
	__hashtable_node* next;
	Value val;
};

3、哈希表的迭代器

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;
  typedef ptrdiff_t difference_type;
  typedef size_t size_type;
  typedef Value& reference;
  typedef Value* pointer;

  node* cur;       //迭代器目前所指的节点
  hashtable* ht;   //保持对容器的连结关系（因为可能需要从bucket跳到bucket）

  __hashtable_iterator(node* n, hashtable* tab) : cur(n), ht(tab) {}
  __hashtable_iterator() {}
  reference operator*() const { return cur->val; }
#ifndef __SGI_STL_NO_ARROW_OPERATOR
  pointer 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_const_iterator<V, K, HF, ExK, EqK, A>&
__hashtable_const_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);  //定位出下一个bucket
    while (!cur && ++bucket < ht->buckets.size())
      cur = ht->buckets[bucket];
  }
  return *this;
}

4、hashtable的数据结构

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;    //hash function的函数型别
  typedef EqualKey key_equal;  

  typedef size_t            size_type;
  typedef ptrdiff_t         difference_type;
  typedef value_type*       pointer;
  typedef const value_type* const_pointer;
  typedef value_type&       reference;
  typedef const value_type& const_reference;

  hasher hash_funct() const { return hash; }
  key_equal key_eq() const { return equals; }

private:
  hasher hash;
  key_equal equals;      //判断键值相同与否的方法（函数或仿函数）
  ExtractKey get_key;    //从节点中取出键值的方法（函数或仿函数）

  typedef __hashtable_node<Value> node;
  typedef simple_alloc<node, Alloc> node_allocator;

  vector<node*,Alloc> buckets;
  size_type num_elements;

public:
  typedef __hashtable_iterator<Value, Key, HashFcn, ExtractKey, EqualKey, 
                               Alloc>
  iterator;

  typedef __hashtable_const_iterator<Value, Key, HashFcn, ExtractKey, EqualKey,
                                     Alloc>
  const_iterator;

  friend struct
  __hashtable_iterator<Value, Key, HashFcn, ExtractKey, EqualKey, Alloc>;
  friend struct
  __hashtable_const_iterator<Value, Key, HashFcn, ExtractKey, EqualKey, Alloc>;
...
};

5、hashtable的构造与内存管理

hashtable(size_type n,
          const HashFcn&    hf,
          const EqualKey&   eql,
          const ExtractKey& ext)
  : hash(hf), equals(eql), get_key(ext), num_elements(0)
{
  initialize_buckets(n);
}
void initialize_buckets(size_type n)
{
  const size_type n_buckets = next_size(n);  //计算出n个元素应当分配多大的哈希表
  buckets.reserve(n_buckets);                //buckets是用vector实现的，先预留容量
  buckets.insert(buckets.end(), n_buckets, (node*) 0);
  num_elements = 0;
}

插入分为insert_unique()和insert_equal()。
注意： SGI hashtable的hash仿函数（hash<...>）只能处理short、int、long、char *、const  char*、char，不能处理string、float、double。欲处理这些型别，用户必须自行定义它们的hash function。

5.8 hash_set

由于RB-tree有自动排序功能而hashtable没有，所以set的元素有自动排序功能而hash_set没有。除此之外，hash_set的使用方式与set完全相同。

#ifndef __STL_LIMITED_DEFAULT_TEMPLATES
template <class Value, class HashFcn = hash<Value>,
          class EqualKey = equal_to<Value>,
          class Alloc = alloc>
#else
template <class Value, class HashFcn, class EqualKey, class Alloc = alloc>
#endif
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::size_type size_type;
  typedef typename ht::difference_type difference_type;
  typedef typename ht::const_pointer pointer;                 //注意不可以直接修改元素的值
  typedef typename ht::const_pointer const_pointer;      
  typedef typename ht::const_reference reference;
  typedef typename ht::const_reference const_reference;

  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(); }

public:
  hash_set() : rep(100, hasher(), key_equal()) {}    //缺省使用大小为100的表格，将被hashtable调整为最接近且较大的质数。
  explicit hash_set(size_type n) : rep(n, hasher(), key_equal()) {}
  hash_set(size_type n, const hasher& hf) : rep(n, hf, key_equal()) {}
  hash_set(size_type n, const hasher& hf, const key_equal& eql)
    : rep(n, hf, eql) {}

  void swap(hash_set& hs) { rep.swap(hs.rep); }
  friend bool operator== __STL_NULL_TMPL_ARGS (const hash_set&,
                                               const hash_set&);

  iterator begin() const { return rep.begin(); }
  iterator end() const { return rep.end(); }

public:
  pair<iterator, bool> insert(const value_type& obj)
    {
      pair<typename ht::iterator, bool> p = rep.insert_unique(obj);
      return pair<iterator, bool>(p.first, p.second);
    }
  ...
};

5.9 hash_map

同样无排序。

#ifndef __STL_LIMITED_DEFAULT_TEMPLATES
template <class Key, class T, class HashFcn = hash<Key>,
          class EqualKey = equal_to<Key>,
          class Alloc = alloc>
#else
template <class Key, class T, class HashFcn, class EqualKey, 
          class Alloc = alloc>
#endif
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::size_type size_type;
  typedef typename ht::difference_type difference_type;
  typedef typename ht::pointer pointer;
  typedef typename ht::const_pointer const_pointer;
  typedef typename ht::reference reference;
  typedef typename ht::const_reference const_reference;

  typedef typename ht::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(); }

public:
  hash_map() : rep(100, hasher(), key_equal()) {}
  explicit hash_map(size_type n) : rep(n, hasher(), key_equal()) {}
  hash_map(size_type n, const hasher& hf) : rep(n, hf, key_equal()) {}
  hash_map(size_type n, const hasher& hf, const key_equal& eql)
    : rep(n, hf, eql) {}

  T& operator[](const key_type& key) {
    return rep.find_or_insert(value_type(key, T())).second;
  }  
  ...
};

5.10 hash_multiset

采用insert_equal()。

5.11 hash_multimap

采用insert_equal()。