hash-fct.C

Go to the documentation of this file.

 
/*
                          Aleph_w
 
  Data structures & Algorithms
  version 2.0.0b
  https://github.com/lrleon/Aleph-w
 
  This file is part of Aleph-w library
 
  Copyright (c) 2002-2026 Leandro Rabindranath Leon
 
  Permission is hereby granted, free of charge, to any person obtaining a copy
  of this software and associated documentation files (the "Software"), to deal
  in the Software without restriction, including without limitation the rights
  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  copies of the Software, and to permit persons to whom the Software is
  furnished to do so, subject to the following conditions:
 
  The above copyright notice and this permission notice shall be included in all
  copies or substantial portions of the Software.
 
  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  SOFTWARE.
*/
 
 
# include <time.h>
# include <gsl/gsl_rng.h>
# include <stdexcept>
# include "hash-fct.H"
 
# include <ah-errors.H>
 
namespace Aleph
{ 
 
const unsigned Default_Hash_Seed = 52679987;  
 
static long tab[256];
 
static bool init = false; 
 
void init_jsw() noexcept
{
  gsl_rng * r = gsl_rng_alloc (gsl_rng_mt19937);
  gsl_rng_set(r, time(nullptr) % gsl_rng_max(r));
 
  for (int i = 0; i < 256; ++i)
    tab[i] = gsl_rng_get(r);
 
  gsl_rng_free(r); 
 
  init = true; 
}
 
size_t jsw_hash(const void * key, size_t len)
{
  ah_domain_error_if(not init)
      << "jsw_hash: init_jsw() has not been called";
 
  const unsigned char *p = (const unsigned char*) key;
  size_t h = 16777551;
 
  for (size_t i = 0; i < len; i++)
    h = (h << 1 | h >> 31) ^ tab[p[i]];
 
  return h;
}
 
size_t jsw_hash(const char * key)
{
  ah_domain_error_if(not init)
      << "jsw_hash: init_jsw() has not been called";
 
  const unsigned char * p = (const unsigned char*) key;
  size_t h = 16777551;
  
  while (*p)
    h = (h << 1 | h >> 31) ^ tab[*p++];
  
  return h;
}
 
 
/* The following is just a exact copy of functions implemented by Peter
   Scott. They are at:
 
   https://github.com/PeterScott/murmur3
 
   They are a port of MurmurHash  by Austin Appleby. See 
 
   http://en.wikipedia.org/wiki/MurmurHash
 
   For more details
*/
 
 
#ifdef __GNUC__
#define FORCE_INLINE __attribute__((always_inline)) inline
#else
#define FORCE_INLINE inline
#endif
 
static FORCE_INLINE uint32_t rotl32 ( uint32_t x, int8_t r )
{
  return (x << r) | (x >> (32 - r));
}
 
static FORCE_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)
 
//-----------------------------------------------------------------------------
// Block read - if your platform needs to do endian-swapping or can only
// handle aligned reads, do the conversion here
 
#define getblock(p, i) (p[i])
 
//-----------------------------------------------------------------------------
// Finalization mix - force all bits of a hash block to avalanche
 
static FORCE_INLINE uint32_t fmix32 ( uint32_t h )
{
  h ^= h >> 16;
  h *= 0x85ebca6b;
  h ^= h >> 13;
  h *= 0xc2b2ae35;
  h ^= h >> 16;
 
  return h;
}
 
//----------
 
static FORCE_INLINE 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;
  int i;
 
  uint32_t h1 = seed;
 
  uint32_t c1 = 0xcc9e2d51;
  uint32_t c2 = 0x1b873593;
 
  //----------
  // body
 
  const uint32_t * blocks = (const uint32_t *)(data + nblocks*4);
 
  for(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; [[fallthrough]];
  case 2: k1 ^= tail[1] << 8;  [[fallthrough]];
  case 1: k1 ^= tail[0];
          k1 *= c1; k1 = ROTL32(k1,15); 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;
  int i;
 
  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(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; [[fallthrough]];
  case 14: k4 ^= tail[13] << 8;  [[fallthrough]];
  case 13: k4 ^= tail[12] << 0;
           k4 *= c4; k4  = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
           [[fallthrough]];
  case 12: k3 ^= tail[11] << 24; [[fallthrough]];
  case 11: k3 ^= tail[10] << 16; [[fallthrough]];
  case 10: k3 ^= tail[ 9] << 8;  [[fallthrough]];
  case  9: k3 ^= tail[ 8] << 0;
           k3 *= c3; k3  = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
           [[fallthrough]];
  case  8: k2 ^= tail[ 7] << 24; [[fallthrough]];
  case  7: k2 ^= tail[ 6] << 16; [[fallthrough]];
  case  6: k2 ^= tail[ 5] << 8;  [[fallthrough]];
  case  5: k2 ^= tail[ 4] << 0;
           k2 *= c2; k2  = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
           [[fallthrough]];
  case  4: k1 ^= tail[ 3] << 24; [[fallthrough]];
  case  3: k1 ^= tail[ 2] << 16; [[fallthrough]];
  case  2: k1 ^= tail[ 1] << 8;  [[fallthrough]];
  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;
  int i;
 
  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(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; [[fallthrough]];
  case 14: k2 ^= (uint64_t)(tail[13]) << 40; [[fallthrough]];
  case 13: k2 ^= (uint64_t)(tail[12]) << 32; [[fallthrough]];
  case 12: k2 ^= (uint64_t)(tail[11]) << 24; [[fallthrough]];
  case 11: k2 ^= (uint64_t)(tail[10]) << 16; [[fallthrough]];
  case 10: k2 ^= (uint64_t)(tail[ 9]) << 8;  [[fallthrough]];
  case  9: k2 ^= (uint64_t)(tail[ 8]) << 0;
           k2 *= c2; k2  = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
           [[fallthrough]];
  case  8: k1 ^= (uint64_t)(tail[ 7]) << 56; [[fallthrough]];
  case  7: k1 ^= (uint64_t)(tail[ 6]) << 48; [[fallthrough]];
  case  6: k1 ^= (uint64_t)(tail[ 5]) << 40; [[fallthrough]];
  case  5: k1 ^= (uint64_t)(tail[ 4]) << 32; [[fallthrough]];
  case  4: k1 ^= (uint64_t)(tail[ 3]) << 24; [[fallthrough]];
  case  3: k1 ^= (uint64_t)(tail[ 2]) << 16; [[fallthrough]];
  case  2: k1 ^= (uint64_t)(tail[ 1]) << 8;  [[fallthrough]];
  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 = fmix64(h1);
  h2 = fmix64(h2);
 
  h1 += h2;
  h2 += h1;
 
  ((uint64_t*)out)[0] = h1;
  ((uint64_t*)out)[1] = h2;
}
 
} // end namespace Aleph