原址链接:http://www.cmykrgb123.cn/blog/string-hash-compare/
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。
在信息修竞赛中,要本着易于编码调试的原则,个人认为BKDRHash是最适合记忆和使用的。
CmYkRgB123原创,欢迎建议、交流、批评和指正。
附:各种哈希函数的C语言程序代码
![ContractedBlock.gif](https://www.cnblogs.com/Images/OutliningIndicators/ContractedBlock.gif)
![ExpandedBlockStart.gif](https://www.cnblogs.com/Images/OutliningIndicators/ExpandedBlockStart.gif)
1 unsigned int SDBMHash(char *str)
2 {
3 unsigned int hash = 0;
4
5 while (*str)
6 {
7 // equivalent to: hash = 65599*hash + (*str++);
8 hash = (*str++) + (hash << 6) + (hash << 16) - hash;
9 }
10
11 return (hash & 0x7FFFFFFF);
12 }
13
14 // RS Hash Function
15 unsigned int RSHash(char *str)
16 {
17 unsigned int b = 378551;
18 unsigned int a = 63689;
19 unsigned int hash = 0;
20
21 while (*str)
22 {
23 hash = hash * a + (*str++);
24 a *= b;
25 }
26
27 return (hash & 0x7FFFFFFF);
28 }
29
30 // JS Hash Function
31 unsigned int JSHash(char *str)
32 {
33 unsigned int hash = 1315423911;
34
35 while (*str)
36 {
37 hash ^= ((hash << 5) + (*str++) + (hash >> 2));
38 }
39
40 return (hash & 0x7FFFFFFF);
41 }
42
43 // P. J. Weinberger Hash Function
44 unsigned int PJWHash(char *str)
45 {
46 unsigned int BitsInUnignedInt = (unsigned int)(sizeof(unsigned int) * 8);
47 unsigned int ThreeQuarters = (unsigned int)((BitsInUnignedInt * 3) / 4);
48 unsigned int OneEighth = (unsigned int)(BitsInUnignedInt / 8);
49 unsigned int HighBits = (unsigned int)(0xFFFFFFFF) << (BitsInUnignedInt - OneEighth);
50 unsigned int hash = 0;
51 unsigned int test = 0;
52
53 while (*str)
54 {
55 hash = (hash << OneEighth) + (*str++);
56 if ((test = hash & HighBits) != 0)
57 {
58 hash = ((hash ^ (test >> ThreeQuarters)) & (~HighBits));
59 }
60 }
61
62 return (hash & 0x7FFFFFFF);
63 }
64
65 // ELF Hash Function
66 unsigned int ELFHash(char *str)
67 {
68 unsigned int hash = 0;
69 unsigned int x = 0;
70
71 while (*str)
72 {
73 hash = (hash << 4) + (*str++);
74 if ((x = hash & 0xF0000000L) != 0)
75 {
76 hash ^= (x >> 24);
77 hash &= ~x;
78 }
79 }
80
81 return (hash & 0x7FFFFFFF);
82 }
83
84 // BKDR Hash Function
85 unsigned int BKDRHash(char *str)
86 {
87 unsigned int seed = 131; // 31 131 1313 13131 131313 etc..
88 unsigned int hash = 0;
89
90 while (*str)
91 {
92 hash = hash * seed + (*str++);
93 }
94
95 return (hash & 0x7FFFFFFF);
96 }
97
98 // DJB Hash Function
99 unsigned int DJBHash(char *str)
100 {
101 unsigned int hash = 5381;
102
103 while (*str)
104 {
105 hash += (hash << 5) + (*str++);
106 }
107
108 return (hash & 0x7FFFFFFF);
109 }
110
111 // AP Hash Function
112 unsigned int APHash(char *str)
113 {
114 unsigned int hash = 0;
115 int i;
116
117 for (i=0; *str; i++)
118 {
119 if ((i & 1) == 0)
120 {
121 hash ^= ((hash << 7) ^ (*str++) ^ (hash >> 3));
122 }
123 else
124 {
125 hash ^= (~((hash << 11) ^ (*str++) ^ (hash >> 5)));
126 }
127 }
128
129 return (hash & 0x7FFFFFFF);
130 }