Beyond the Void
BYVoid
各種字符串Hash函數比較
本文正體字版由OpenCC轉換

常用的字符串Hash函數還有ELFHash,APHash等等,都是十分簡單有效的方法。這些函數使用位運算使得每一個字符都對最後的函數值產生影響。另外還有以MD5和SHA1爲代表的雜湊函數,這些函數幾乎不可能找到碰撞。

常用字符串哈希函數有BKDRHash,APHash,DJBHash,JSHash,RSHash,SDBMHash,PJWHash,ELFHash等等。對於以上幾種哈希函數,我對其進行了一個小小的評測。

Hash函數 數據1 數據2 數據3 數據4 數據1得分 數據2得分 數據3得分 數據4得分 平均分
BKDRHash 2 0 4774 481 96.55 100 90.95 82.05 92.64
APHash 2 3 4754 493 96.55 88.46 100 51.28 86.28
DJBHash 2 2 4975 474 96.55 92.31 0 100 83.43
JSHash 1 4 4761 506 100 84.62 96.83 17.95 81.94
RSHash 1 0 4861 505 100 100 51.58 20.51 75.96
SDBMHash 3 2 4849 504 93.1 92.31 57.01 23.08 72.41
PJWHash 30 26 4878 513 0 0 43.89 0 21.95
ELFHash 30 26 4878 513 0 0 43.89 0 21.95

其中數據1爲100000個字母和數字組成的隨機串哈希衝突個數。數據2爲100000個有意義的英文句子哈希衝突個數。數據3爲數據1的哈希值與1000003(大素數)求模後存儲到線性表中衝突的個數。數據4爲數據1的哈希值與10000019(更大素數)求模後存儲到線性表中衝突的個數。

經過比較,得出以上平均得分。平均數爲平方平均數。可以發現,BKDRHash無論是在實際效果還是編碼實現中,效果都是最突出的。APHash也是較爲優秀的算法。DJBHash,JSHash,RSHash與SDBMHash各有千秋。PJWHash與ELFHash效果最差,但得分相似,其算法本質是相似的。

在信息修競賽中,要本着易於編碼調試的原則,個人認爲BKDRHash是最適合記憶和使用的。

BYVoid原創,歡迎建議、交流、批評和指正。

附:各種哈希函數的C語言程序代碼
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);
}

上次修改時間 2017-05-22

相關日誌