Skip to content

Commit

Permalink
first commit
Browse files Browse the repository at this point in the history
  • Loading branch information
thekvs committed Mar 14, 2011
0 parents commit ff7c3e1
Show file tree
Hide file tree
Showing 9 changed files with 721 additions and 0 deletions.
6 changes: 6 additions & 0 deletions .gitignore
@@ -0,0 +1,6 @@
*~
.eunit
c_src/*.o
doc
ebin
priv
11 changes: 11 additions & 0 deletions README.md
@@ -0,0 +1,11 @@
## Description

The **erlang-murmurhash** library provides [MurmurHash](http://code.google.com/p/smhasher/) hash functions implemented in Erlang NIFs.

## Building and Installing

The **erlang-murmurhash** library is built with [rebar](https://github.com/basho/rebar), which must be in the command `PATH`.

## Erlang Version

The **erlang-murmurhash** library requires Erlang R14B or later.
276 changes: 276 additions & 0 deletions c_src/MurmurHash2.cpp
@@ -0,0 +1,276 @@
#include "MurmurHash2.h"

//-----------------------------------------------------------------------------
// MurmurHash2, by Austin Appleby

// Note - This code makes a few assumptions about how your machine behaves -

// 1. We can read a 4-byte value from any address without crashing
// 2. sizeof(int) == 4

// And it has a few limitations -

// 1. It will not work incrementally.
// 2. It will not produce the same results on little-endian and big-endian
// machines.

uint32_t MurmurHash2 ( const void * key, int len, uint32_t seed )
{
// 'm' and 'r' are mixing constants generated offline.
// They're not really 'magic', they just happen to work well.

const uint32_t m = 0x5bd1e995;
const int r = 24;

// Initialize the hash to a 'random' value

uint32_t h = seed ^ len;

// Mix 4 bytes at a time into the hash

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

while(len >= 4)
{
uint32_t k = *(uint32_t*)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;
}

//-----------------------------------------------------------------------------
// MurmurHash2, 64-bit versions, by Austin Appleby

// The same caveats as 32-bit MurmurHash2 apply here - beware of alignment
// and endian-ness issues if used across multiple platforms.

// 64-bit hash for 64-bit platforms

uint64_t MurmurHash64A ( const void * key, int len, uint64_t seed )
{
const uint64_t m = 0xc6a4a7935bd1e995;
const int r = 47;

uint64_t h = seed ^ (len * m);

const uint64_t * data = (const uint64_t *)key;
const uint64_t * end = data + (len/8);

while(data != end)
{
uint64_t k = *data++;

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

h ^= k;
h *= m;
}

const unsigned char * data2 = (const unsigned char*)data;

switch(len & 7)
{
case 7: h ^= uint64_t(data2[6]) << 48;
case 6: h ^= uint64_t(data2[5]) << 40;
case 5: h ^= uint64_t(data2[4]) << 32;
case 4: h ^= uint64_t(data2[3]) << 24;
case 3: h ^= uint64_t(data2[2]) << 16;
case 2: h ^= uint64_t(data2[1]) << 8;
case 1: h ^= uint64_t(data2[0]);
h *= m;
};

h ^= h >> r;
h *= m;
h ^= h >> r;

return h;
}


// 64-bit hash for 32-bit platforms

uint64_t MurmurHash64B ( const void * key, int len, uint64_t seed )
{
const uint32_t m = 0x5bd1e995;
const int r = 24;

uint32_t h1 = uint32_t(seed) ^ len;
uint32_t h2 = uint32_t(seed >> 32);

const uint32_t * data = (const uint32_t *)key;

while(len >= 8)
{
uint32_t k1 = *data++;
k1 *= m; k1 ^= k1 >> r; k1 *= m;
h1 *= m; h1 ^= k1;
len -= 4;

uint32_t k2 = *data++;
k2 *= m; k2 ^= k2 >> r; k2 *= m;
h2 *= m; h2 ^= k2;
len -= 4;
}

if(len >= 4)
{
uint32_t 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;
}

//-----------------------------------------------------------------------------
// MurmurHash2A, by Austin Appleby

// This is a variant of MurmurHash2 modified to use the Merkle-Damgard
// construction. Bulk speed should be identical to Murmur2, small-key speed
// will be 10%-20% slower due to the added overhead at the end of the hash.

// This variant fixes a minor issue where null keys were more likely to
// collide with each other than expected, and also makes the function
// more amenable to incremental implementations.

#define mmix(h,k) { k *= m; k ^= k >> r; k *= m; h *= m; h ^= k; }

uint32_t MurmurHash2A ( const void * key, int len, uint32_t seed )
{
const uint32_t m = 0x5bd1e995;
const int r = 24;
uint32_t l = len;

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

uint32_t h = seed;

while(len >= 4)
{
uint32_t k = *(uint32_t*)data;

mmix(h,k);

data += 4;
len -= 4;
}

uint32_t t = 0;

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

mmix(h,t);
mmix(h,l);

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

return h;
}

//-----------------------------------------------------------------------------
// MurmurHashNeutral2, by Austin Appleby

// Same as MurmurHash2, but endian- and alignment-neutral.
// Half the speed though, alas.

uint32_t MurmurHashNeutral2 ( const void * key, int len, uint32_t seed )
{
const uint32_t m = 0x5bd1e995;
const int r = 24;

uint32_t h = seed ^ len;

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

while(len >= 4)
{
uint32_t k;

k = data[0];
k |= data[1] << 8;
k |= data[2] << 16;
k |= data[3] << 24;

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

h *= m;
h ^= k;

data += 4;
len -= 4;
}

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

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

return h;
}

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

7 changes: 7 additions & 0 deletions c_src/MurmurHash2.h
@@ -0,0 +1,7 @@
#include <inttypes.h>

uint32_t MurmurHash2 ( const void * key, int len, uint32_t seed );
uint64_t MurmurHash64A ( const void * key, int len, uint64_t seed );
uint64_t MurmurHash64B ( const void * key, int len, uint64_t seed );
uint32_t MurmurHash2A ( const void * key, int len, uint32_t seed );
uint32_t MurmurHashNeutral2 ( const void * key, int len, uint32_t seed );

0 comments on commit ff7c3e1

Please sign in to comment.