hash function比较（一）

由于工作需要，针对千万级别的数据，使用stl::map着实存在着效率问题，最后使用boost::unordered_map替代前者，发现效率上有很大的提升，但是还是无法达到我们的需求；

stl::map  底层算法：B+tree 实现

boost::unordered_map 底层算法：hash 实现

所以可能要针对不同的数据类型编写hash function来优化查找和插入的效率，自己编写，着实没有这个实力，只有在google上来寻找先辈们的精妙算法来借鉴：

常用字符串哈希函数有BKDRHash，APHash，DJBHash，JSHash，RSHash，SDBMHash，PJWHash，ELFHash等等；

有前辈做了评测：如下

其中数据1为100000个字母和数字组成的随机串哈希冲突个数。数据2为100000个有意义的英文句子哈希冲突个数。数据3为数据1的哈希值与1000003(大素数)求模后存储到线性表中冲突的个数。数据4为数据1的哈希值与10000019(更大素数)求模后存储到线性表中冲突的个数。

各种hash function的C 语言实现：

unsigned int SDBMHash(char *str)
{
	unsigned int hash = 0;
 
	while (*str)
	{
		// equivalent to: hash = 65599*hash + (*str++);
		hash = (*str++) + (hash << 6) + (hash << 16) - hash;
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// RS Hash Function
unsigned int RSHash(char *str)
{
	unsigned int b = 378551;
	unsigned int a = 63689;
	unsigned int hash = 0;
 
	while (*str)
	{
		hash = hash * a + (*str++);
		a *= b;
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// JS Hash Function
unsigned int JSHash(char *str)
{
	unsigned int hash = 1315423911;
 
	while (*str)
	{
		hash ^= ((hash << 5) + (*str++) + (hash >> 2));
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// P. J. Weinberger Hash Function
unsigned int PJWHash(char *str)
{
	unsigned int BitsInUnignedInt = (unsigned int)(sizeof(unsigned int) * 8);
	unsigned int ThreeQuarters	= (unsigned int)((BitsInUnignedInt  * 3) / 4);
	unsigned int OneEighth		= (unsigned int)(BitsInUnignedInt / 8);
	unsigned int HighBits		 = (unsigned int)(0xFFFFFFFF) << (BitsInUnignedInt - OneEighth);
	unsigned int hash			 = 0;
	unsigned int test			 = 0;
 
	while (*str)
	{
		hash = (hash << OneEighth) + (*str++);
		if ((test = hash & HighBits) != 0)
		{
			hash = ((hash ^ (test >> ThreeQuarters)) & (~HighBits));
		}
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// ELF Hash Function
unsigned int ELFHash(char *str)
{
	unsigned int hash = 0;
	unsigned int x	= 0;
 
	while (*str)
	{
		hash = (hash << 4) + (*str++);
		if ((x = hash & 0xF0000000L) != 0)
		{
			hash ^= (x >> 24);
			hash &= ~x;
		}
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// BKDR Hash Function
unsigned int BKDRHash(char *str)
{
	unsigned int seed = 131; // 31 131 1313 13131 131313 etc..
	unsigned int hash = 0;
 
	while (*str)
	{
		hash = hash * seed + (*str++);
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// DJB Hash Function
unsigned int DJBHash(char *str)
{
	unsigned int hash = 5381;
 
	while (*str)
	{
		hash += (hash << 5) + (*str++);
	}
 
	return (hash & 0x7FFFFFFF);
}
 
// AP Hash Function
unsigned int APHash(char *str)
{
	unsigned int hash = 0;
	int i;
 
	for (i=0; *str; i++)
	{
		if ((i & 1) == 0)
		{
			hash ^= ((hash << 7) ^ (*str++) ^ (hash >> 3));
		}
		else
		{
			hash ^= (~((hash << 11) ^ (*str++) ^ (hash >> 5)));
		}
	}
 
	return (hash & 0x7FFFFFFF);
}