常用的字符串Hash函数还有ELFHash,APHash等等,都是十分简单有效的方法。这些函数使用位运算使得每一个字符都对最后的函数值产生影响。另外还有以MD5和SHA1为代表的杂凑函数,这些函数几乎不可能找到碰撞。
常用字符串哈希函数有BKDRHash,APHash,DJBHash,JSHash,RSHash,SDBMHash,PJWHash,ELFHash等等。对于以上几种哈希函数,我对其进行了一个小小的评测。
Hash函数 | 数据1 | 数据2 | 数据3 | 数据4 | 数据1得分 | 数据2得分 | 数据3得分 | 数据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。
经过比较,得出以上平均得分。平均数为平方平均数。可以发现,BKDRHash无论是在实际效果还是编码实现中,效果都是最突出的。APHash也是较为优秀的算法。DJBHash,JSHash,RSHash与SDBMHash各有千秋。PJWHash与ELFHash效果最差,但得分相似,其算法本质是相似的。
附1:各种哈希函数的C程序代码
#define M 249997
#define M1 1000001
#define M2 0xF0000000
// 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 % M);
}
// JS Hash Function
unsigned int JSHash(char*str)
{
unsigned int hash=1315423911 ;
while(*str)
{
hash^=((hash<<5)+(*str++)+(hash>>2));
}
return(hash % M);
}
// 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<>ThreeQuarters))&(~HighBits));
}
}
return(hash % M);
}
// 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 % M);
}
// 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 % M);
}
// SDBM Hash Function
unsigned int SDBMHash(char*str)
{
unsigned int hash=0 ;
while(*str)
{
hash=(*str++)+(hash<<6)+(hash<<16)-hash ;
}
return(hash % M);
}
// DJB Hash Function
unsigned int DJBHash(char*str)
{
unsigned int hash=5381 ;
while(*str)
{
hash+=(hash<<5)+(*str++);
}
return(hash % M);
}
// 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 % M);
}
附2:Hash算法大全
/**
* Hash算法大全
* 推荐使用FNV1算法
* @algorithm None
* @author Goodzzp 2006-11-20
* @lastEdit Goodzzp 2006-11-20
* @editDetail Create
*/
public class HashAlgorithms
{
/**
* 加法hash
* @param key 字符串
* @param prime 一个质数
* @return hash结果
*/
public static int additiveHash(String key, int prime)
{
int hash, i;
for (hash = key.length(), i = 0; i < key.length(); i++)
hash += key.charAt(i);
return (hash % prime);
}
/**
* 旋转hash
* @param key 输入字符串
* @param prime 质数
* @return hash值
*/
public static int rotatingHash(String key, int prime)
{
int hash, i;
for (hash = key.length(), i = 0; i < key.length(); ++i)
hash = (hash << 4) ^ (hash >> 28) ^ key.charAt(i);
return (hash % prime);
// return (hash ^ (hash>>10) ^ (hash>>20));
}
// 替代:
// 使用:hash = (hash ^ (hash>>10) ^ (hash>>20)) & mask;
// 替代:hash %= prime;
/**
* MASK值,随便找一个值,最好是质数
*/
static int M_MASK = 0x8765fed1;
/**
* 一次一个hash
* @param key 输入字符串
* @return 输出hash值
*/
public static int oneByOneHash(String key)
{
int hash, i;
for (hash = 0, i = 0; i < key.length(); ++i)
{
hash += key.charAt(i);
hash += (hash << 10);
hash ^= (hash >> 6);
}
hash += (hash << 3);
hash ^= (hash >> 11);
hash += (hash << 15);
// return (hash & M_MASK);
return hash;
}
/**
* Bernstein's hash
* @param key 输入字节数组
* @param level 初始hash常量
* @return 结果hash
*/
public static int bernstein(String key)
{
int hash = 0;
int i;
for (i = 0; i < key.length(); ++i) hash = 33 * hash + key.charAt(i);
return hash;
}
//
Pearson's Hash
// char pearson(char[]key, ub4 len, char tab[256])
// {
// char hash;
// ub4 i;
// for (hash=len, i=0; i> 8) ^ tab[(hash & 0xff) ^ key[i]];
// return (hash & mask);
// }
/**
* Universal Hashing
*/
public static int universal(char[] key, int mask, int[] tab)
{
int hash = key.length, i, len = key.length;
for (i = 0; i < (len << 3); i += 8)
{
char k = key[i >> 3];
if ((k & 0x01) == 0) hash ^= tab[i + 0];
if ((k & 0x02) == 0) hash ^= tab[i + 1];
if ((k & 0x04) == 0) hash ^= tab[i + 2];
if ((k & 0x08) == 0) hash ^= tab[i + 3];
if ((k & 0x10) == 0) hash ^= tab[i + 4];
if ((k & 0x20) == 0) hash ^= tab[i + 5];
if ((k & 0x40) == 0) hash ^= tab[i + 6];
if ((k & 0x80) == 0) hash ^= tab[i + 7];
}
return (hash & mask);
}
/**
* Zobrist Hashing
*/
public static int zobrist(char[] key, int mask, int[][] tab)
{
int hash, i;
for (hash = key.length, i = 0; i < key.length; ++i)
hash ^= tab[i][key[i]];
return (hash & mask);
}
// LOOKUP3
// 见Bob Jenkins(3).c文件
// 32位FNV算法
static int M_SHIFT = 0;
/**
* 32位的FNV算法
* @param data 数组
* @return int值
*/
public static int FNVHash(byte[] data)
{
int hash = (int)2166136261L;
for(byte b : data)
hash = (hash * 16777619) ^ b;
if (M_SHIFT == 0)
return hash;
return (hash ^ (hash >> M_SHIFT)) & M_MASK;
}
/**
* 改进的32位FNV算法1
* @param data 数组
* @return int值
*/
public static int FNVHash1(byte[] data)
{
final int p = 16777619;
int hash = (int)2166136261L;
for(byte b:data)
hash = (hash ^ b) * p;
hash += hash << 13;
hash ^= hash >> 7;
hash += hash << 3;
hash ^= hash >> 17;
hash += hash << 5;
return hash;
}
/**
* 改进的32位FNV算法1
* @param data 字符串
* @return int值
*/
public static int FNVHash1(String data)
{
final int p = 16777619;
int hash = (int)2166136261L;
for(int i=0;i> 7;
hash += hash << 3;
hash ^= hash >> 17;
hash += hash << 5;
return hash;
}
/**
* Thomas Wang的算法,整数hash
*/
public static int intHash(int key)
{
key += ~(key << 15);
key ^= (key >>> 10);
key += (key << 3);
key ^= (key >>> 6);
key += ~(key << 11);
key ^= (key >>> 16);
return key;
}
/**
* RS算法hash
* @param str 字符串
*/
public static int RSHash(String str)
{
int b = 378551;
int a = 63689;
int hash = 0;
for (int i = 0; i < str.length(); i++)
{
hash = hash * a + str.charAt(i);
a = a * b;
}
return (hash & 0x7FFFFFFF);
}
/* End Of RS Hash Function */
/**
* JS算法
*/
public static int JSHash(String str)
{
int hash = 1315423911;
for (int i = 0; i < str.length(); i++)
{
hash ^= ((hash << 5) + str.charAt(i) + (hash >> 2));
}
return (hash & 0x7FFFFFFF);
}
/* End Of JS Hash Function */
/**
* PJW算法
*/
public static int PJWHash(String str)
{
int BitsInUnsignedInt = 32;
int ThreeQuarters = (BitsInUnsignedInt * 3) / 4;
int OneEighth = BitsInUnsignedInt / 8;
int HighBits = 0xFFFFFFFF << (BitsInUnsignedInt - OneEighth);
int hash = 0;
int test = 0;
for (int i = 0; i < str.length(); i++)
{
hash = (hash << OneEighth) + str.charAt(i);
if ((test = hash & HighBits) != 0)
{
hash = ((hash ^ (test >> ThreeQuarters)) & (~HighBits));
}
}
return (hash & 0x7FFFFFFF);
}
/* End Of P. J. Weinberger Hash Function */
/**
* ELF算法
*/
public static int ELFHash(String str)
{
int hash = 0;
int x = 0;
for (int i = 0; i < str.length(); i++)
{
hash = (hash << 4) + str.charAt(i);
if ((x = (int)(hash & 0xF0000000L)) != 0)
{
hash ^= (x >> 24);
hash &= ~x;
}
}
return (hash & 0x7FFFFFFF);
}
/* End Of ELF Hash Function */
/**
* BKDR算法
*/
public static int BKDRHash(String str)
{
int seed = 131; // 31 131 1313 13131 131313 etc..
int hash = 0;
for (int i = 0; i < str.length(); i++)
{
hash = (hash * seed) + str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of BKDR Hash Function */
/**
* SDBM算法
*/
public static int SDBMHash(String str)
{
int hash = 0;
for (int i = 0; i < str.length(); i++)
{
hash = str.charAt(i) + (hash << 6) + (hash << 16) - hash;
}
return (hash & 0x7FFFFFFF);
}
/* End Of SDBM Hash Function */
/**
* DJB算法
*/
public static int DJBHash(String str)
{
int hash = 5381;
for (int i = 0; i < str.length(); i++)
{
hash = ((hash << 5) + hash) + str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of DJB Hash Function */
/**
* DEK算法
*/
public static int DEKHash(String str)
{
int hash = str.length();
for (int i = 0; i < str.length(); i++)
{
hash = ((hash << 5) ^ (hash >> 27)) ^ str.charAt(i);
}
return (hash & 0x7FFFFFFF);
}
/* End Of DEK Hash Function */
/**
* AP算法
*/
public static int APHash(String str)
{
int hash = 0;
for (int i = 0; i < str.length(); i++)
{
hash ^= ((i & 1) == 0) ? ((hash << 7) ^ str.charAt(i) ^ (hash >> 3)) :
(~((hash << 11) ^ str.charAt(i) ^ (hash >> 5)));
}
// return (hash & 0x7FFFFFFF);
return hash;
}
/* End Of AP Hash Function */
/**
* JAVA自己带的算法
*/
public static int java(String str)
{
int h = 0;
int off = 0;
int len = str.length();
for (int i = 0; i < len; i++)
{
h = 31 * h + str.charAt(off++);
}
return h;
}
/**
* 混合hash算法,输出64位的值
*/
public static long mixHash(String str)
{
long hash = str.hashCode();
hash <<= 32;
hash |= FNVHash1(str);
return hash;
}
}