hash实现--开放寻址方式

原文：http://blog.csdn.net/aa2010aa/article/details/4908113

今天看了一下《算法导论》第十一章的散列表，里面有一节是关于开发寻址方式。


  下面是我的简单的实现：

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, 3221225473ul, 4294967291ul
};
unsigned int m = __stl_prime_list[0];

int Hash_Key(int key)
{
	return key % m;
}

int Hash_Key1(int key)
{
	return 1 + key % (m-1);
}
/* int Hash_Key(int key, int i)
{
	return (Hash_Key(key) + i) % m;
} */

int Hash_Key(int key, int i)
{
	return (Hash_Key(key) + i * Hash_Key1(key)) % m;
}

int Hash_Create(int *&hashTable)
{
	if(0 == m)
	{
		hashTable = NULL;
		return -1;
	}
	hashTable = new int[m];
	if (NULL == hashTable)
	{
		return -1;
	}
	for(unsigned int i = 0; i < m; i++)
		hashTable[i] = -1;
	return 1;
}

int Hash_Insert(int *hashTable, int value)
{
	int key = Hash_Key(value, 0);
	for(unsigned int i = 1; i < m; i++)
	{
		if (-1 == hashTable[key])
		{
			hashTable[key] = value;
			return key;
		}
		key = Hash_Key(value, i);
	}
	return -1;
}

int Hash_Find(int *hashTable, int value)
{
	int key = Hash_Key(value, 0);
	for(unsigned int i = 1; i < m; i++)
	{
		if(-1 == hashTable[key])
		{
			return -1;
		}
		if(value == hashTable[key])
		{
			return key;
		}
		key = Hash_Key(value, i);
	}
	return -1;
}

void Hash_Delete(int *hashTable)
{
	delete []hashTable;
}

 下面是测试：

int main()
{
	srand(time(NULL));
	unsigned int k;
	unsigned int i;
	clock_t begin, finish;
	cin >> k;
	for(i = 0; i < __stl_num_primes && k > __stl_prime_list[i]; i++);
		m = __stl_prime_list[i];
	int  *hap;
	try
	{
		Hash_Create(hap);
	}
	catch(bad_alloc &e)
	{
		cout << "create wrong" << endl;
		return -1;
	}
	begin = clock();
	for(unsigned int i = 0; i < m / 10; i++)
	{
		int d = Random32()%m;
		if( -1  == Hash_Insert(hap, d))
		{
			cout << "insert wrong" << endl;
		}
	}
	finish = clock();
	cout << "insert time";
	cout << (double)(finish - begin)/CLOCKS_PER_SEC << endl;
	begin = clock();
	for(unsigned int i = 0; i < m / 10; i++)
	{
		int d = Random32()%m;
		if( -1  == Hash_Find(hap, d))
		{
			//cout << d << "  find wrong" << endl;
		}
	}
	finish = clock();
	cout << (double)(finish - begin)/CLOCKS_PER_SEC << endl;
	Hash_Delete(hap); 
}

其中的Random32（）的实现是：

unsigned int Random32(void) {   
      
    static const unsigned long x[55] = {   
      1410651636UL, 3012776752UL, 3497475623UL, 2892145026UL, 1571949714UL,   
      3253082284UL, 3489895018UL, 387949491UL, 2597396737UL, 1981903553UL,   
      3160251843UL, 129444464UL, 1851443344UL, 4156445905UL, 224604922UL,   
      1455067070UL, 3953493484UL, 1460937157UL, 2528362617UL, 317430674UL,   
      3229354360UL, 117491133UL, 832845075UL, 1961600170UL, 1321557429UL,   
      747750121UL, 545747446UL, 810476036UL, 503334515UL, 4088144633UL,   
      2824216555UL, 3738252341UL, 3493754131UL, 3672533954UL, 29494241UL,   
      1180928407UL, 4213624418UL, 33062851UL, 3221315737UL, 1145213552UL,   
      2957984897UL, 4078668503UL, 2262661702UL, 65478801UL, 2527208841UL,   
      1960622036UL, 315685891UL, 1196037864UL, 804614524UL, 1421733266UL,   
      2017105031UL, 3882325900UL, 810735053UL, 384606609UL, 2393861397UL };   
    static int init = 1;   
    static unsigned long y[55];   
    static int j, k;   
    unsigned long ul;   
    
    if (init)   
    {   
      int i;   
      
      init = 0;   
      for (i = 0; i < 55; i++) y[i] = x[i];   
      j = 24 - 1;   
      k = 55 - 1;   
    }   
    
    ul = (y[k] += y[j]);   
    if (--j < 0) j = 55 - 1;   
    if (--k < 0) k = 55 - 1;   
    return((unsigned int)ul);   
}  

 c函数rand（）产生的数在0~RAND_MAX之间（在我的机器，RAND_MAX的大小是32767），比较小，不利于测试，Random32函数

能产生0到unsigned int最大之间的数。

   开放寻址的方式相对链表方式节省了空间（省了一个指针），但加大了插入和查找时间，特别如果插入的数重复太多的话，那么时间会有一个很大的提升。

   下面是测试结果：

   

 

  如果用rand代替Random32，测试结果是：

  

  当到了10000000，对比一下就知道，那时间是花花的上去了。