* Add ext stuff, while I figure out how to get it working as a different project

ext/MurmurHash2.cpp

@@ -0,0 +1,523 @@
+//-----------------------------------------------------------------------------
+// MurmurHash2 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+// 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.
+
+#include "MurmurHash2.h"
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+#define BIG_CONSTANT(x) (x)
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#define BIG_CONSTANT(x) (x##LLU)
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+
+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 = BIG_CONSTANT(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;
+}
+
+//-----------------------------------------------------------------------------
+// CMurmurHash2A, by Austin Appleby
+
+// This is a sample implementation of MurmurHash2A designed to work 
+// incrementally.
+
+// Usage - 
+
+// CMurmurHash2A hasher
+// hasher.Begin(seed);
+// hasher.Add(data1,size1);
+// hasher.Add(data2,size2);
+// ...
+// hasher.Add(dataN,sizeN);
+// uint32_t hash = hasher.End()
+
+class CMurmurHash2A
+{
+public:
+
+  void Begin ( uint32_t seed = 0 )
+  {
+    m_hash  = seed;
+    m_tail  = 0;
+    m_count = 0;
+    m_size  = 0;
+  }
+
+  void Add ( const unsigned char * data, int len )
+  {
+    m_size += len;
+
+    MixTail(data,len);
+
+    while(len >= 4)
+    {
+      uint32_t k = *(uint32_t*)data;
+
+      mmix(m_hash,k);
+
+      data += 4;
+      len -= 4;
+    }
+
+    MixTail(data,len);
+  }
+
+  uint32_t End ( void )
+  {
+    mmix(m_hash,m_tail);
+    mmix(m_hash,m_size);
+
+    m_hash ^= m_hash >> 13;
+    m_hash *= m;
+    m_hash ^= m_hash >> 15;
+
+    return m_hash;
+  }
+
+private:
+
+  static const uint32_t m = 0x5bd1e995;
+  static const int r = 24;
+
+  void MixTail ( const unsigned char * & data, int & len )
+  {
+    while( len && ((len<4) || m_count) )
+    {
+      m_tail |= (*data++) << (m_count * 8);
+
+      m_count++;
+      len--;
+
+      if(m_count == 4)
+      {
+        mmix(m_hash,m_tail);
+        m_tail = 0;
+        m_count = 0;
+      }
+    }
+  }
+
+  uint32_t m_hash;
+  uint32_t m_tail;
+  uint32_t m_count;
+  uint32_t m_size;
+};
+
+//-----------------------------------------------------------------------------
+// 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;
+} 
+
+//-----------------------------------------------------------------------------
+// MurmurHashAligned2, by Austin Appleby
+
+// Same algorithm as MurmurHash2, but only does aligned reads - should be safer
+// on certain platforms. 
+
+// Performance will be lower than MurmurHash2
+
+#define MIX(h,k,m) { k *= m; k ^= k >> r; k *= m; h *= m; h ^= k; }
+
+
+uint32_t MurmurHashAligned2 ( const void * key, int len, uint32_t seed )
+{
+  const uint32_t m = 0x5bd1e995;
+  const int r = 24;
+
+  const unsigned char * data = (const unsigned char *)key;
+
+  uint32_t h = seed ^ len;
+
+  int align = (uint64_t)data & 3;
+
+  if(align && (len >= 4))
+  {
+    // Pre-load the temp registers
+
+    uint32_t t = 0, d = 0;
+
+    switch(align)
+    {
+      case 1: t |= data[2] << 16;
+      case 2: t |= data[1] << 8;
+      case 3: t |= data[0];
+    }
+
+    t <<= (8 * align);
+
+    data += 4-align;
+    len -= 4-align;
+
+    int sl = 8 * (4-align);
+    int sr = 8 * align;
+
+    // Mix
+
+    while(len >= 4)
+    {
+      d = *(uint32_t *)data;
+      t = (t >> sr) | (d << sl);
+
+      uint32_t k = t;
+
+      MIX(h,k,m);
+
+      t = d;
+
+      data += 4;
+      len -= 4;
+    }
+
+    // Handle leftover data in temp registers
+
+    d = 0;
+
+    if(len >= align)
+    {
+      switch(align)
+      {
+      case 3: d |= data[2] << 16;
+      case 2: d |= data[1] << 8;
+      case 1: d |= data[0];
+      }
+
+      uint32_t k = (t >> sr) | (d << sl);
+      MIX(h,k,m);
+
+      data += align;
+      len -= align;
+
+      //----------
+      // Handle tail bytes
+
+      switch(len)
+      {
+      case 3: h ^= data[2] << 16;
+      case 2: h ^= data[1] << 8;
+      case 1: h ^= data[0];
+          h *= m;
+      };
+    }
+    else
+    {
+      switch(len)
+      {
+      case 3: d |= data[2] << 16;
+      case 2: d |= data[1] << 8;
+      case 1: d |= data[0];
+      case 0: h ^= (t >> sr) | (d << sl);
+          h *= m;
+      }
+    }
+
+    h ^= h >> 13;
+    h *= m;
+    h ^= h >> 15;
+
+    return h;
+  }
+  else
+  {
+    while(len >= 4)
+    {
+      uint32_t k = *(uint32_t *)data;
+
+      MIX(h,k,m);
+
+      data += 4;
+      len -= 4;
+    }
+
+    //----------
+    // Handle tail bytes
+
+    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;
+  }
+}
+
+//-----------------------------------------------------------------------------
+

ext/MurmurHash2.h

@@ -0,0 +1,39 @@
+//-----------------------------------------------------------------------------
+// MurmurHash2 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH2_H_
+#define _MURMURHASH2_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+
+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 );
+uint32_t MurmurHashAligned2 ( const void * key, int len, uint32_t seed );
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH2_H_
+

ext/MurmurHash3.cpp

@@ -0,0 +1,346 @@
+//-----------------------------------------------------------------------------
+// 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.
+
+#include "MurmurHash3.h"
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+#define FORCE_INLINE	__forceinline
+
+#include <stdlib.h>
+
+#define ROTL32(x,y)	_rotl(x,y)
+#define ROTL64(x,y)	_rotl64(x,y)
+
+#define BIG_CONSTANT(x) (x)
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#if defined(GNUC) && ((GNUC > 4) || (GNUC == 4 && GNUC_MINOR >= 4))
+
+/* gcc version >= 4.4 4.1 = RHEL 5, 4.4 = RHEL 6.
+ * Don't inline for RHEL 5 gcc which is 4.1 */
+#define FORCE_INLINE attribute((always_inline))
+
+#else
+
+#define FORCE_INLINE
+
+#endif
+
+
+inline uint32_t rotl32 ( uint32_t x, int8_t r )
+{
+  return (x << r) | (x >> (32 - r));
+}
+
+inline 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)
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+// Block read - if your platform needs to do endian-swapping or can only
+// handle aligned reads, do the conversion here
+
+FORCE_INLINE uint32_t getblock ( const uint32_t * p, int i )
+{
+  return p[i];
+}
+
+FORCE_INLINE uint64_t getblock ( const uint64_t * p, int i )
+{
+  return p[i];
+}
+
+//-----------------------------------------------------------------------------
+// Finalization mix - force all bits of a hash block to avalanche
+
+FORCE_INLINE uint32_t fmix ( uint32_t h )
+{
+  h ^= h >> 16;
+  h *= 0x85ebca6b;
+  h ^= h >> 13;
+  h *= 0xc2b2ae35;
+  h ^= h >> 16;
+
+  return h;
+}
+
+//----------
+
+FORCE_INLINE uint64_t fmix ( 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 = getblock(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(k1,15); k1 *= c2; h1 ^= k1;
+  };
+
+  //----------
+  // finalization
+
+  h1 ^= len;
+
+  h1 = fmix(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 = getblock(blocks,i*4+0);
+    uint32_t k2 = getblock(blocks,i*4+1);
+    uint32_t k3 = getblock(blocks,i*4+2);
+    uint32_t k4 = getblock(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 = fmix(h1);
+  h2 = fmix(h2);
+  h3 = fmix(h3);
+  h4 = fmix(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 = getblock(blocks,i*2+0);
+    uint64_t k2 = getblock(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(k1,31); k1 *= c2; h1 ^= k1;
+  };
+
+  //----------
+  // finalization
+
+  h1 ^= len; h2 ^= len;
+
+  h1 += h2;
+  h2 += h1;
+
+  h1 = fmix(h1);
+  h2 = fmix(h2);
+
+  h1 += h2;
+  h2 += h1;
+
+  ((uint64_t*)out)[0] = h1;
+  ((uint64_t*)out)[1] = h2;
+}
+
+//-----------------------------------------------------------------------------
+

ext/MurmurHash3.h

@@ -0,0 +1,45 @@
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH3_H_
+#define _MURMURHASH3_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+void MurmurHash3_x86_32  ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out );
+
+#ifdef __cplusplus
+}
+#endif
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH3_H_

ext/murmurhash.pxd

@@ -0,0 +1,11 @@
+from libc.stdint cimport uint64_t, int64_t
+
+
+cdef extern from "../include/MurmurHash3.h":
+    void MurmurHash3_x86_32(void * key, uint64_t len, uint64_t seed, void* out)
+    void MurmurHash3_x86_128(void * key, uint64_t len, uint64_t seed, void* out)
+
+
+cdef extern from "../include/MurmurHash2.h":
+    uint64_t MurmurHash64A(void * key, uint64_t len, int64_t seed)
+    uint64_t MurmurHash64B(void * key, uint64_t len, int64_t seed)

ext/sparsehash.pxd

@@ -0,0 +1,48 @@
+from libcpp.utility cimport pair
+from libcpp.vector cimport vector
+from libc.stdint cimport uint64_t, int64_t
+
+
+cdef extern from "sparsehash/dense_hash_map" namespace "google":
+    cdef cppclass dense_hash_map[K, D]:
+        K& key_type
+        D& data_type
+        pair[K, D]& value_type
+        uint64_t size_type
+        cppclass iterator:
+            pair[K, D]& operator*() nogil
+            iterator operator++() nogil
+            iterator operator--() nogil
+            bint operator==(iterator) nogil
+            bint operator!=(iterator) nogil
+        iterator begin()
+        iterator end()
+        uint64_t size()
+        uint64_t max_size()
+        bint empty()
+        uint64_t bucket_count()
+        uint64_t bucket_size(uint64_t i)
+        uint64_t bucket(K& key)
+        double max_load_factor()
+        void max_load_vactor(double new_grow)
+        double min_load_factor()
+        double min_load_factor(double new_grow)
+        void set_resizing_parameters(double shrink, double grow)
+        void resize(uint64_t n)
+        void rehash(uint64_t n)
+        dense_hash_map()
+        dense_hash_map(uint64_t n)
+        void swap(dense_hash_map&)
+        pair[iterator, bint] insert(pair[K, D]) nogil
+        void set_empty_key(K&)
+        void set_deleted_key(K& key)
+        void clear_deleted_key()
+        void erase(iterator pos)
+        uint64_t erase(K& k)
+        void erase(iterator first, iterator last)
+        void clear()
+        void clear_no_resize()
+        pair[iterator, iterator] equal_range(K& k)
+        D& operator[](K&) nogil
+
+

include/MurmurHash2.h

@@ -0,0 +1,39 @@
+//-----------------------------------------------------------------------------
+// MurmurHash2 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH2_H_
+#define _MURMURHASH2_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+
+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 );
+uint32_t MurmurHashAligned2 ( const void * key, int len, uint32_t seed );
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH2_H_
+

include/MurmurHash3.h

@@ -0,0 +1,45 @@
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH3_H_
+#define _MURMURHASH3_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else	// defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+
+void MurmurHash3_x86_32  ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out );
+
+#ifdef __cplusplus
+}
+#endif
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH3_H_