How to use MurmurHash 64 in Objective-C?

I need to Hash a NSString using murmurhash i am forced to do that because the other team is doing so, I need to use the 64-bit key length on x86 platform, have anyone implemented or used murmurhash in objective-C?

Murmurhash 64 is a .cpp file and i can't get it compiled in iOS SDK 4.3, also tried to rename it to .mm but the result still the same.

Any help or Guide would be greatly appreciated.

I will post the Compilation Error Messages if someone is int开发者_JAVA技巧erested.

---

MurmurHash3:

//-----------------------------------------------------------------------------
// MurmurHash3 was written by Austin Appleby, and is placed in the public
// domain. The author hereby disclaims copyright to this source code.

// Note - The x86 and x64 versions do _not_ produce the same results, as the
// algorithms are optimized for their respective platforms. You can still
// compile and run any of them on any platform, but your performance with the
// non-native version will be less than optimal.

uint32_t rotl32 ( uint32_t x, int8_t r )
{
    return (x << r) | (x >> (32 - r));
}

uint64_t rotl64 ( uint64_t x, int8_t r )
{
    return (x << r) | (x >> (64 - r));
}

#define ROTL32(x,y)     rotl32(x,y)
#define ROTL64(x,y)     rotl64(x,y)

#define BIG_CONSTANT(x) (x##LLU)

typedef unsigned long long  uint64_t;

//-----------------------------------------------------------------------------
// Block read - if your platform needs to do endian-swapping or can only
// handle aligned reads, do the conversion here

uint32_t getblock32 ( const uint32_t * p, int i )
{
    return p[i];
}

uint64_t getblock64 ( const uint64_t * p, int i )
{
    return p[i];
}

//-----------------------------------------------------------------------------
// Finalization mix - force all bits of a hash block to avalanche

uint32_t fmix32 ( uint32_t h )
{
    h ^= h >> 16;
    h *= 0x85ebca6b;
    h ^= h >> 13;
    h *= 0xc2b2ae35;
    h ^= h >> 16;

    return h;
}

//----------

uint64_t fmix64 ( uint64_t k )
{
    k ^= k >> 33;
    k *= BIG_CONSTANT(0xff51afd7ed558ccd);
    k ^= k >> 33;
    k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53);
    k ^= k >> 33;

    return k;
}

//-----------------------------------------------------------------------------

void MurmurHash3_x86_32 ( const void * key, int len,
                         uint32_t seed, void * out )
{
    const uint8_t * data = (const uint8_t*)key;
    const int nblocks = len / 4;

    uint32_t h1 = seed;

    uint32_t c1 = 0xcc9e2d51;
    uint32_t c2 = 0x1b873593;

    //----------
    // body

    const uint32_t * blocks = (const uint32_t *)(data + nblocks*4);

    for(int i = -nblocks; i; i++)
    {
        uint32_t k1 = getblock32(blocks,i);

        k1 *= c1;
        k1 = ROTL32(k1,15);
        k1 *= c2;

        h1 ^= k1;
        h1 = ROTL32(h1,13); 
        h1 = h1*5+0xe6546b64;
    }

    //----------
    // tail

    const uint8_t * tail = (const uint8_t*)(data + nblocks*4);

    uint32_t k1 = 0;

    switch(len & 3)
    {
        case 3: k1 ^= tail[2] << 16;
        case 2: k1 ^= tail[1] << 8;
        case 1: k1 ^= tail[0];
            k1 *= c1; k1 = ROTL32(k1,16); k1 *= c2; h1 ^= k1;
    };

    //----------
    // finalization

    h1 ^= len;

    h1 = fmix32(h1);

    *(uint32_t*)out = h1;
} 

//-----------------------------------------------------------------------------

void MurmurHash3_x86_128 ( const void * key, const int len,
                          uint32_t seed, void * out )
{
    const uint8_t * data = (const uint8_t*)key;
    const int nblocks = len / 16;

    uint32_t h1 = seed;
    uint32_t h2 = seed;
    uint32_t h3 = seed;
    uint32_t h4 = seed;

    uint32_t c1 = 0x239b961b; 
    uint32_t c2 = 0xab0e9789;
    uint32_t c3 = 0x38b34ae5; 
    uint32_t c4 = 0xa1e38b93;

    //----------
    // body

    const uint32_t * blocks = (const uint32_t *)(data + nblocks*16);

    for(int i = -nblocks; i; i++)
    {
        uint32_t k1 = getblock32(blocks,i*4+0);
        uint32_t k2 = getblock32(blocks,i*4+1);
        uint32_t k3 = getblock32(blocks,i*4+2);
        uint32_t k4 = getblock32(blocks,i*4+3);

        k1 *= c1; k1  = ROTL32(k1,15); k1 *= c2; h1 ^= k1;

        h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b;

        k2 *= c2; k2  = ROTL32(k2,16); k2 *= c3; h2 ^= k2;

        h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747;

        k3 *= c3; k3  = ROTL32(k3,17); k3 *= c4; h3 ^= k3;

        h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35;

        k4 *= c4; k4  = ROTL32(k4,18); k4 *= c1; h4 ^= k4;

        h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17;
    }

    //----------
    // tail

    const uint8_t * tail = (const uint8_t*)(data + nblocks*16);

    uint32_t k1 = 0;
    uint32_t k2 = 0;
    uint32_t k3 = 0;
    uint32_t k4 = 0;

    switch(len & 15)
    {
        case 15: k4 ^= tail[14] << 16;
        case 14: k4 ^= tail[13] << 8;
        case 13: k4 ^= tail[12] << 0;
            k4 *= c4; k4  = ROTL32(k4,18); k4 *= c1; h4 ^= k4;

        case 12: k3 ^= tail[11] << 24;
        case 11: k3 ^= tail[10] << 16;
        case 10: k3 ^= tail[ 9] << 8;
        case  9: k3 ^= tail[ 8] << 0;
            k3 *= c3; k3  = ROTL32(k3,17); k3 *= c4; h3 ^= k3;

        case  8: k2 ^= tail[ 7] << 24;
        case  7: k2 ^= tail[ 6] << 16;
        case  6: k2 ^= tail[ 5] << 8;
        case  5: k2 ^= tail[ 4] << 0;
            k2 *= c2; k2  = ROTL32(k2,16); k2 *= c3; h2 ^= k2;

        case  4: k1 ^= tail[ 3] << 24;
        case  3: k1 ^= tail[ 2] << 16;
        case  2: k1 ^= tail[ 1] << 8;
        case  1: k1 ^= tail[ 0] << 0;
            k1 *= c1; k1  = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
    };

    //----------
    // finalization

    h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len;

    h1 += h2; h1 += h3; h1 += h4;
    h2 += h1; h3 += h1; h4 += h1;

    h1 = fmix32(h1);
    h2 = fmix32(h2);
    h3 = fmix32(h3);
    h4 = fmix32(h4);

    h1 += h2; h1 += h3; h1 += h4;
    h2 += h1; h3 += h1; h4 += h1;

    ((uint32_t*)out)[0] = h1;
    ((uint32_t*)out)[1] = h2;
    ((uint32_t*)out)[2] = h3;
    ((uint32_t*)out)[3] = h4;
}

//-----------------------------------------------------------------------------

void MurmurHash3_x64_128 ( const void * key, const int len,
                          const uint32_t seed, void * out )
{
    const uint8_t * data = (const uint8_t*)key;
    const int nblocks = len / 16;

    uint64_t h1 = seed;
    uint64_t h2 = seed;

    uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
    uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f);

    //----------
    // body

    const uint64_t * blocks = (const uint64_t *)(data);

    for(int i = 0; i < nblocks; i++)
    {
        uint64_t k1 = getblock64(blocks,i*2+0);
        uint64_t k2 = getblock64(blocks,i*2+1);

        k1 *= c1; k1  = ROTL64(k1,31); k1 *= c2; h1 ^= k1;

        h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;

        k2 *= c2; k2  = ROTL64(k2,33); k2 *= c1; h2 ^= k2;

        h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
    }

    //----------
    // tail

    const uint8_t * tail = (const uint8_t*)(data + nblocks*16);

    uint64_t k1 = 0;
    uint64_t k2 = 0;

    switch(len & 15)
    {
        case 15: k2 ^= ((uint64_t)tail[14]) << 48;
        case 14: k2 ^= ((uint64_t)tail[13]) << 40;
        case 13: k2 ^= ((uint64_t)tail[12]) << 32;
        case 12: k2 ^= ((uint64_t)tail[11]) << 24;
        case 11: k2 ^= ((uint64_t)tail[10]) << 16;
        case 10: k2 ^= ((uint64_t)tail[ 9]) << 8;
        case  9: k2 ^= ((uint64_t)tail[ 8]) << 0;
            k2 *= c2; k2  = ROTL64(k2,33); k2 *= c1; h2 ^= k2;

        case  8: k1 ^= ((uint64_t)tail[ 7]) << 56;
        case  7: k1 ^= ((uint64_t)tail[ 6]) << 48;
        case  6: k1 ^= ((uint64_t)tail[ 5]) << 40;
        case  5: k1 ^= ((uint64_t)tail[ 4]) << 32;
        case  4: k1 ^= ((uint64_t)tail[ 3]) << 24;
        case  3: k1 ^= ((uint64_t)tail[ 2]) << 16;
        case  2: k1 ^= ((uint64_t)tail[ 1]) << 8;
        case  1: k1 ^= ((uint64_t)tail[ 0]) << 0;
            k1 *= c1; k1  = ROTL64(k1,29); k1 *= c2; h1 ^= k1;
    };

    //----------
    // finalization

    h1 ^= len; h2 ^= len;

    h1 += h2;
    h2 += h1;

    h1 = fmix64(h1);
    h2 = fmix64(h2);

    h1 += h2;
    h2 += h1;

    ((uint64_t*)out)[0] = h1;
    ((uint64_t*)out)[1] = h2;
}

Usage example:

- (uint32_t)hash:(NSString*)string {
    const char* str = [string UTF8String];
    int len = [string length];
    uint32_t hash;
    MurmurHash3_x86_32(str,len,0,&hash);

    return hash;
}

---

For all those who will come to look for the correct answer, here is the deal:

MurmurHash64.h class
careful I have changed the typedef

// MurmurHash, by Austin Appleby

typedef unsigned long long uint64_t;

uint64_t MurmurHash64B ( const void * key, int len, unsigned int seed );

MurmurHash64.m class

#include "MurmurHash64.h"
// 64-bit hash for 32-bit platforms

uint64_t MurmurHash64B ( const void * key, int len, unsigned int seed )
{
    const unsigned int m = 0x5bd1e995;
    const int r = 24;

    unsigned int h1 = seed ^ len;
    unsigned int h2 = 0;

    const unsigned int * data = (const unsigned int *)key;

    while(len >= 8)
    {
       unsigned int k1 = *data++;
       k1 *= m; k1 ^= k1 >> r; k1 *= m;
       h1 *= m; h1 ^= k1;
       len -= 4;

       unsigned int k2 = *data++;
       k2 *= m; k2 ^= k2 >> r; k2 *= m;
       h2 *= m; h2 ^= k2;
       len -= 4;
    }

    if(len >= 4)
    {
       unsigned int k1 = *data++;
       k1 *= m; k1 ^= k1 >> r; k1 *= m;
       h1 *= m; h1 ^= k1;
       len -= 4;
    }

    switch(len)
    {
        case 3: h2 ^= ((unsigned char*)data)[2] << 16;
        case 2: h2 ^= ((unsigned char*)data)[1] << 8;
        case 1: h2 ^= ((unsigned char*)data)[0];
        h2 *= m;
    };

    h1 ^= h2 >> 18; h1 *= m;
    h2 ^= h1 >> 22; h2 *= m;
    h1 ^= h2 >> 17; h1 *= m;
    h2 ^= h1 >> 19; h2 *= m;

    uint64_t h = h1;

    h = (h << 32) | h2;

    return h;
}   

---

// Murmur.m
//-----------------------------------------------------------------------------
// MurmurHash2, by Austin Appleby

unsigned int MurmurHash2 ( const void * key, int len, unsigned int seed )
{
    // 'm' and 'r' are mixing constants generated offline.
    // They're not really 'magic', they just happen to work well.

    const unsigned int m = 0x5bd1e995;
    const int r = 24;

    // Initialize the hash to a 'random' value

    unsigned int h = seed ^ len;

    // Mix 4 bytes at a time into the hash

    const unsigned char * data = (const unsigned char *)key;

    while(len >= 4)
    {
        unsigned int k = *(unsigned int *)data;

        k *= m; 
        k ^= k >> r; 
        k *= m; 

        h *= m; 
        h ^= k;

        data += 4;
        len -= 4;
    }

    // Handle the last few bytes of the input array

    switch(len)
    {
    case 3: h ^= data[2] << 16;
    case 2: h ^= data[1] << 8;
    case 1: h ^= data[0];
            h *= m;
    };

    // Do a few final mixes of the hash to ensure the last few
    // bytes are well-incorporated.

    h ^= h >> 13;
    h *= m;
    h ^= h >> 15;

    return h;
} 

This goes to some .h:

unsigned int MurmurHash2 ( const void * key, int len, unsigned int seed );