Comparison of common hash functions and its implementation in C language

Basic concepts
The so-called perfect hash function means that there is no conflicting hash function, that is, to an arbitrary key1!= Key2 has h (key1)!= H (key2).
Set the definition field to X, the range is Y, n=| x|,m=| y|, then there must be m>=n, if for different key1,key2 belong to X, there is H (key1)!=h (key2), then called H is the perfect hash function, when m=n, H is called the Minimum perfect hash function (this time is one by one mapping).

When working with large string data, you often assign an integer ID to each string. This requires a hash function of the string. How to find a perfect string hash function?

There are some commonly used string hash functions. Like Bkdrhash,aphash,djbhash,jshash,rshash,sdbmhash,pjwhash,elfhash and so on. are more classic.

Commonly used string hash functions and Elfhash,aphash and so on, are very simple and effective methods. These functions use bitwise operations to make each character have an effect on the last function value. There are also hash functions represented by MD5 and SHA1, which are almost impossible to find collisions with.

Common string hash functions are bkdrhash,aphash,djbhash,jshash,rshash,sdbmhash,pjwhash,elfhash and so on. For the above several hash functions, I have a small evaluation of it.

hash 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

The number of random string hash conflicts in which data 1 is 100,000 letters and numbers. Data 2 is the number of hash conflicts for 100,000 meaningful English sentences. The number of conflicts in the linear table is stored in data 3 after modulo the hash value of data 1 and 1000003 (large primes). Data 4 is the number of conflicts that are stored in a linear table after modulo the hash value of data 1 and 10000019 (larger primes).


After comparison, the above average score is obtained. The average is the square average. It can be found that the effect of Bkdrhash is the most outstanding in both the actual effect and the coding implementation. Aphash is also a more excellent algorithm. Djbhash,jshash,rshash and Sdbmhash. Pjwhash and Elfhash effect is the worst, but the score is similar, its algorithm essence is similar.

unsigned int sdbmhash (char *str) {unsigned int hash = 0;
        while (*STR) {//equivalent To:hash = 65599*hash + (*str++);
    hash = (*str++) + (hash << 6) + (hash <<)-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. 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 intoneeighth = (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)) & (~highbi
        TS));
} 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;//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++) ^ (ha
        SH >> 3));
        else {hash ^= ((hash << one) ^ (*str++) ^ (hash >> 5));
} return (hash & 0x7fffffff); }

A hash function in programming Zhuji

Use the nearest prime number closest to the element as the size of the hash table
#define Nhash 29989
#define mult

unsigned in hash (char *p)
{
    unsigned int h = 0;
    for (; *p; p++)
        h = mult *h + *p;
    return h% Nhash;
}