数据结构-散列

散列（hashing）：是一种以常数平均时间执行插入、删除和查找的技术。

散列表（hash table）：是包含有关键字的具有固定大小的数组。表的大小记作table-size。每个关键字被映射到从0到table-size-1这个范围中的某个数，并且被放到适当的单元中。这个映射叫作散列函数（hash function）。

散列函数：一个好的方法为保证表的大小为素数。

一个好的散列函数：

int Hash(int x, int tableSize)
{
	return x%tableSize;
}

冲突：当一个元素被插入时，另一个元素已经存在，则产生一个冲突。

冲突消除的方法：最简单的两种方法为：分离链表法和开发定址法

1. 分离链表法：将散列到同一个值的所有元素保存到一个表中。表的类型声明如下：

   struct listNode;
   typedef struct listNode* position;
   struct hashTbl;
   typedef struct hashTbl* hashTable;
   
   
   struct listNode
   {
   	int element;
   	position next;
   };
   
   
   typedef position list;
   struct hashTbl
   {
   	int tableSize;
   	list* theLists;
   };
   
   
   int Hash(int x, int tableSize);
   hashTable initializeTable(int tableSize);
   position find(int key, hashTable h);
   void insert(int key, hashTable h);
   int isPrime(int x);
   int nextPrime(int x);

   
   表的初始化：

   hashTable initializeTable(int tableSize)
   {
   	hashTable h;
   	int i;
   	h = (struct hashTbl *)malloc(sizeof(struct hashTbl));
   	if (h==NULL)
   	{
   		cout << "Out of space!" << endl;
   	}
   	h->tableSize =nextPrime( tableSize);
   	h->theLists = (list *)malloc(sizeof(list)*h->tableSize);
   	if (h->theLists==NULL)
   	{
   		cout << "Out of space!" << endl;
   	}
   	for (i = 0; i < h->tableSize; i++)
   	{
   		h->theLists[i] = (listNode *)malloc(sizeof(struct listNode));
   		if (h->theLists[i] == NULL)
   			cout << "Out of space!" << endl;
   		else
   			h->theLists[i]->next = NULL;
   	}
   	return h;
   }

   
   Find例程：

   position find(int key, hashTable h)
   {
   	position p;
   	list l;
   	l = h->theLists[Hash(key, h->tableSize)];
   	p = l->next;
   	while (p!=NULL&&p->element!=key)
   	{
   		p = p->next;
   	}
   	return p;
   }
   

   
   Insert例程：

   void insert(int key, hashTable h)
   {
   	position pos, newCell;
   	list l;
   	pos = find(key, h);
   	if (pos==NULL)
   	{
   		newCell = (listNode*)malloc(sizeof(struct listNode));
   		if (newCell==NULL)
   		{
   			cout << "Out of space!" << endl;
   		}
   		else
   		{
   			l = h->theLists[Hash(key, h->tableSize)];
   			newCell->next = l->next;
   			newCell->element = key;
   			l->next = newCell;
   		}
   	}
   }

   
   nextPrime函数的实现：求大于等于当前值的最小素数。

   int nextPrime(int x)
   {
   	if (isPrime(x))
   		return x;
   	else
   	{
   		x = x + 1;
   		while (!isPrime(x))
   		{
   			x = x + 1;
   		}
   		return x;
   	}
   }
   
   
   int isPrime(int x){
   	int i;
   	for ( i = 2; i <=sqrt(x); i++)
   	{
   		if (x%i == 0)
   			return 0;
   	}
   	return 1;
   }

   
                                                                                                                                                                                                  
   
2. 开放定址法：冲突发生后：hi(x)=(Hash(x)+F(i))mod TableSize。                                                                                                                                                                         线性探测法：F(i)=i;                                                                                                                                                                                                                                                   平方探测法：F(i)=i²;                                                                                                                                                                                                                                                双散列：F(i)=i*hash₂(x)，即选择第二个Hash函数。                                                                                                                                                                                                以平方散列为例。散列结构声明：

   typedef int position;
   struct hashTbl;
   typedef struct hashTbl *hashTable;
   enum kindOfEntry
   {
   	legitiamte,empty,deleted
   };
   struct hashEntry
   {
   	int element;
   	enum kindOfEntry info;
   };
   typedef struct hashEntry cell;
   struct hashTbl
   {
   	int tableSize;
   	cell* theCells;
   };
   
   
   int Hash(int key,int tableSize);
   hashTable initializeTable(int tableSize);
   position find(int key, hashTable h);
   void insert(int key, hashTable h);
   int nextPrime(int x);
   int isPrime(int x);

   
   初始化例程：

   hashTable initializeTable(int tableSize)
   {
   	hashTable h;
   	int i;
   	h = (hashTbl*)malloc(sizeof(struct hashTbl));
   	if (h == NULL)
   		cout << "Out of space!" << endl;
   	h->tableSize = nextPrime(tableSize);
   	h->theCells = (cell *)malloc(sizeof(cell)*h->tableSize);
   	if (h->tableSize == NULL)
   		cout << "Out of space!" << endl;
   	for (i = 0; i < h->tableSize; i++)
   		h->theCells[i].info = empty;
   	return h;
   }
   

   
   Find例程：

   position find(int key, hashTable h)
   {
   	position currentPos;
   	int collisionNum;
   	collisionNum = 0;
   	currentPos = Hash(key, h->tableSize);
   	while (h->theCells[currentPos].info!=empty&&h->theCells[currentPos].element!=key)
   	{
   		currentPos += 2 * ++collisionNum - 1;
   		if (currentPos>=h->tableSize)
   		{
   			currentPos -= h->tableSize;
   		}
   	}
   	return currentPos;
   }

   
   Insert例程：

   void insert(int key, hashTable h)
   {
   	position pos;
   	pos = find(key, h);
   	if (h->theCells[pos].info!=legitiamte)
   	{
   		h->theCells[pos].info = legitiamte;
   		h->theCells[pos].element = key;
   	}
   }

   
   nextPrime函数的实现：

   int nextPrime(int x)
   {
   		while (!isPrime(x))
   		{
   			x = x + 1;
   		}
   		return x;
   }
   
   
   int isPrime(int x)
   {
   	int i;
   	for ( i =2; i <sqrt(x); i++)
   	{
   		if (x%i == 0)
   			return 0;
   	}
   	return 1;
   }

   
   最后，对于使用平方探测法的开放定址散列法，若元素太满，那么操作的运行时间可能过长切Insert操作可能失败。此时，解决办法为：建另外一个大约两倍大的表，扫描原始散列表，计算每一个元素的新散列值并将其插入表中。