hash function comparison

http://blog.csdn.net/kingstar158/article/details/8028635

Because of the work needs, for tens other data, the use of stl::map there is really a problem of efficiency, and finally use Boost::unordered_map replace the former, found that there is a great improvement in efficiency, but still can not meet our needs;

Stl::map underlying algorithm: B+tree implementation

Boost::unordered_map Bottom algorithm: hash implementation

So you might want to write hash function for different data types to optimize the efficiency of the search and insertion, write yourself, really do not have this strength, only on Google to find the ancestors of the ingenious algorithm to learn from:

Commonly used string hash functions have bkdrhash,aphash,djbhash,jshash,rshash,sdbmhash,pjwhash,elfhash and so on;

Have predecessors did the evaluation: the following

Ash function	Data 1	Data 2	Data 3	Data 4	Data 1 Score	Data 2 Score	Data 3 Score	Data 4 Score	Average score
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	40W	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

Where data 1 is the number of random string hash collisions consisting of 100,000 letters and numbers. Data 2 is the number of 100,000 meaningful English sentence hash collisions. Data 3 is the number of conflicts that are stored in a linear table after the hash value of data 1 is modeled with 1000003 (large prime). Data 4 is the number of conflicts that are stored in a linear table after the hash value of data 1 is modeled with 10000019 (greater prime).

C language implementations of various hash function:

[CPP]View Plaincopyprint?

2. unsigned int sdbmhash (char *str)
4. {
6. unsigned int hash = 0;
10. While (*STR)
12. {
14. //Equivalent To:hash = 65599*hash + (*str++);
16. hash = (*str++) + (hash << 6) + (hash << +)-hash;
18. }
22. return (hash & 0x7FFFFFFF);
24. }
28. RS Hash Function
30. unsigned int rshash (char *str)
32. {
34. unsigned int b = 378551;
36. unsigned int a = 63689;
38. unsigned int hash = 0;
42. While (*STR)
44. {
46. hash = hash * A + (*str++);
48. a *= b;
50. }
54. return (hash & 0x7FFFFFFF);
56. }
60. JS Hash Function
62. unsigned int jshash (char *str)
64. {
66. unsigned int hash = 1315423911;
70. While (*STR)
72. {
74. Hash ^= (Hash << 5) + (*str++) + (hash >> 2));
76. }
80. return (hash & 0x7FFFFFFF);
82. }
86. P. J. Weinberger Hash Function
88. unsigned int pjwhash (char *str)
90. {
92. unsigned int bitsinunignedint = (unsigned int) (sizeof (unsigned int) * 8);
94. unsigned int threequarters = (unsigned int) ((Bitsinunignedint * 3)/4);
96. unsigned int oneeighth = (unsigned int) (BITSINUNIGNEDINT/8);
98. unsigned int highbits = (unsigned int) (0xFFFFFFFF) << (bitsinunignedint-oneeighth);
100. unsigned int hash = 0;
102. unsigned int test = 0;
106. While (*STR)
108. {
110. hash = (hash << oneeighth) + (*str++);
112. if (test = hash & highbits)! = 0)
114. {
116. hash = ((hash ^ (test >> threequarters)) & (~highbits));
118. }
120. }
124. return (hash & 0x7FFFFFFF);
126. }
130. ELF Hash Function
132. unsigned int elfhash (char *str)
134. {
136. unsigned int hash = 0;
138. unsigned int x = 0;
142. While (*STR)
144. {
146. hash = (hash << 4) + (*str++);
148. if ((x = hash & 0xf0000000l)! = 0)
150. {
152. Hash ^= (x >> 24);
154. Hash &= ~x;
156. }
158. }
162. return (hash & 0x7FFFFFFF);
164. }
168. BKDR Hash Function
170. unsigned int bkdrhash (char *str)
172. {
174. unsigned int seed = 131;  //131 1313 13131 131313 etc..
176. unsigned int hash = 0;
180. While (*STR)
182. {
184. hash = hash * seed + (*str++);
186. }
190. return (hash & 0x7FFFFFFF);
192. }
196. DJB Hash Function
198. unsigned int djbhash (char *str)
200. {
202. unsigned int hash = 5381;
206. While (*STR)
208. {
210. Hash + = (hash << 5) + (*str++);
212. }
216. return (hash & 0x7FFFFFFF);
218. }
222. AP Hash Function
224. unsigned int aphash (char *str)
226. {
228. unsigned int hash = 0;
230. int i;
234. For (i=0; *str; i++)
236. {
238. if ((i & 1) = = 0)
240. {
242. Hash ^= (Hash << 7) ^ (*str++) ^ (hash >> 3));
244. }
246. Else
248. {
250. Hash ^= ((hash << one) ^ (*str++) ^ (hash >> 5));
252. }
254. }
258. return (hash & 0x7FFFFFFF);
260. }
262. Https://www.byvoid.com/blog/string-hash-compare/

hash function comparison