super_fast_hash_ex.c

#include <stdio.h>
#include <string.h>

// Code below is from http://www.azillionmonkeys.com/qed/hash.html
#include <stdint.h>
#undef get16bits
#if (defined(__GNUC__) && defined(__i386__)) || defined(__WATCOMC__) \
  || defined(_MSC_VER) || defined (__BORLANDC__) || defined (__TURBOC__)
#define get16bits(d) (*((const uint16_t *) (d)))
#endif

#if !defined (get16bits)
#define get16bits(d) ((((uint32_t)(((const uint8_t *)(d))[1])) << 8)\
                       +(uint32_t)(((const uint8_t *)(d))[0]) )
#endif

uint32_t SuperFastHash (const char * data, int len) {
uint32_t hash = len, tmp;
int rem;

    if (len <= 0 || data == NULL) return 0;

    rem = len & 3;
    len >>= 2;

    /* Main loop */
    for (;len > 0; len--) {
        hash  += get16bits (data);
        tmp    = (get16bits (data+2) << 11) ^ hash;
        hash   = (hash << 16) ^ tmp;
        data  += 2*sizeof (uint16_t);
        hash  += hash >> 11;
    }

    /* Handle end cases */
    switch (rem) {
        case 3: hash += get16bits (data);
                hash ^= hash << 16;
                hash ^= ((signed char)data[sizeof (uint16_t)]) << 18;
                hash += hash >> 11;
                break;
        case 2: hash += get16bits (data);
                hash ^= hash << 11;
                hash += hash >> 17;
                break;
        case 1: hash += (signed char)*data;
                hash ^= hash << 10;
                hash += hash >> 1;
    }

    /* Force "avalanching" of final 127 bits */
    hash ^= hash << 3;
    hash += hash >> 5;
    hash ^= hash << 4;
    hash += hash >> 17;
    hash ^= hash << 25;
    hash += hash >> 6;

    return hash;
}

int main() {
    FILE *file;
    ssize_t read;
    size_t len;
    char * line = NULL;

    file = fopen("all_commands.txt", "r");

    if (file == NULL) {
        printf("Could not open file.\n");
        return 1;
    }

    while (1) {
        read = getline(&line, &len, file);
        if (read == -1) {
            break;
        }

        int length = strlen(line);
        uint32_t hash = SuperFastHash(line, length - 1);
        unsigned int idx = hash % 997;
        printf("%u %u %s", hash, idx, line);
    }

    // uint32_t hash = SuperFastHash("hello", 5);
    // printf("Result: %u\n", hash);
}