来自散列函数的相同键的不同值和良好的散列值

时间:2017-07-18 14:10:36

标签: c++ algorithm sorting c++11 hash

我必须执行一个哈希函数MurmurHash3。但我得到了奇怪的结果。 而且我想知道我是否正在使用该功能:

MurmurHash3.cpp

 #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)

#define FORCE_INLINE inline __attribute__((always_inline))

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

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

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

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

  return h;
}

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

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_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;

  const uint32_t c1 = 0x239b961b; 
  const uint32_t c2 = 0xab0e9789;
  const uint32_t c3 = 0x38b34ae5; 
  const 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;

  const uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
  const 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(k1,31); 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;
}

MurmurHash3.h

#ifndef _MURMURHASH3_H_
#define _MURMURHASH3_H_

//-----------------------------------------------------------------------------
// Platform-specific functions and macros

// Microsoft Visual Studio

#if defined(_MSC_VER) && (_MSC_VER < 1600)

typedef unsigned char uint8_t;
typedef unsigned int uint32_t;
typedef unsigned __int64 uint64_t;

// Other compilers

#else   // defined(_MSC_VER)

#include <stdint.h>

#endif // !defined(_MSC_VER)

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

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 );

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

#endif // _MURMURHASH3_H_  

Testing.cpp

#include "MurmurHash3.h"
#include <time.h>
#include <string.h>
#include <iostream>

using namespace std;

int main ( int argc, char ** argv )
{
  const char * hashToTest = "murmur3a";
  char  out[128] ;
  uint32_t seed = time(0);
  MurmurHash3_x64_128( hashToTest, strlen(hashToTest) , seed, out );
  for(int i=0 ; i<128 ;i++)
  cout<<(int) out[i]<<"  ";
  cout<<endl;

}

我调用函数MurmurHash3_x64_128,因为我使用的是64位系统。 如果你是32位,你应该拨打MurmurHash3_x86_128

但是,例如,我进入 out

-34  -106  32  -60  34  44  -30  -128  -127  -10  -75  25  73  -64  -50  31  -120  32  96  0  0  0  0  0  41  116  50  -56  7  127  0  0  1  0  0  0  0  0  0  0  -32  -71  12  29  -3  127  0  0  -8  29  96  0  0  0  0  0  68  24  64  0  0  0  0  0  -8  -79  47  -56  7  127  0  0  -1  -1  0  0  1  0  0  0  -16  -71  12  29  -3  127  0  0  89  24  64  0  0  0  0  0  2  0  0  0  0  0  0  0  -83  24  64  0  0  0  0  0  1  0  0  0  -3  127  0  0  0  0  0  0  0  0  0  0  

还有负值。我不是哈希函数的专家。这种行为是正常的吗? 此外,我需要对从函数的更多调用返回的哈希值进行排序。如何有效地比较哈希值?有XOR?

让我觉得我错了的另一件事是该函数为同一个执行返回2个不同的哈希值。即查看此代码

Testing.cpp

#include "MurmurHash3.h"
#include <time.h>
#include <string.h>
#include <iostream>

using namespace std;

int main ( int argc, char ** argv )
{
  const char * hashToTest = "murmur3a";
  char  out[128] ;
  char  out2[128] ;
  uint32_t seed = time(0);
  MurmurHash3_x64_128( hashToTest, strlen(hashToTest) , seed, out );
  MurmurHash3_x64_128( hashToTest, strlen(hashToTest) , seed, out2 );
  for(int i=0 ; i<128 ;i++)
  cout<<(int) out[i]<<"  ";
  cout<<endl;

  for(int i=0 ; i<128 ;i++)
  cout<<(int) out2[i]<<"  ";
  cout<<endl;

}

我得到2个不同的哈希值:

-93  -105  98  -119  -121  125  76  -5  -48  -108  51  -50  18  -74  -72  2  -24  -68  37  32  -4  127  0  0  1  0  0  0  0  0  0  0  -80  -69  37  32  -4  127  0  0  -9  102  56  -80  99  127  0  0  1  0  0  0  99  127  0  0  0  0  0  0  0  0  0  0  -80  -81  53  -80  99  127  0  0  -40  40  -53  -81  99  127  0  0  1  0  0  0  0  0  0  0  -80  -69  37  32  -4  127  0  0  -8  29  96  0  0  0  0  0  -91  -42  56  -80  99  127  0  0  0  0  0  0  0  0  0  0  6  0  0  0  0  0  0  0  

-93  -105  98  -119  -121  125  76  -5  -48  -108  51  -50  18  -74  -72  2  -128  32  96  0  0  0  0  0  41  100  -50  -81  99  127  0  0  1  0  0  0  0  0  0  0  -80  -69  37  32  -4  127  0  0  -8  29  96  0  0  0  0  0  79  24  64  0  0  0  0  0  -8  -95  -53  -81  99  127  0  0  -1  -1  0  0  1  0  0  0  -64  -69  37  32  -4  127  0  0  100  24  64  0  0  0  0  0  2  0  0  0  0  0  0  0  -67  24  64  0  0  0  0  0  1  0  0  0  -4  127  0  0  0  0  0  0  0  0  0  0  

(我正在使用C ++ 11)

1 个答案:

答案 0 :(得分:1)

  

我得到2个不同的哈希值:

一个问题是您打印出128个字节的数据,但MurmurHash3()仅输出128个。这意味着只有输出每行的第一个(128/8)= 16个字节才是有效的哈希数据;您要打印的剩余字节是未初始化/随机数据,无意义。

MurmurHash3() Wikipedia页面提到了第二个原因:

  

使用128位时,x86和x64版本不会生成相同的版本   值,因为算法针对各自的算法进行了优化   平台。

转到下一部分......

  

还有负值。我不是哈希函数的专家。   这种行为是正常的吗?

值是否为负取决于数据打印机制如何解释字节。目前,您正在将值打印为int,并且int是签名数据类型,这意味着任何具有最高位设置的值都将打印为负值。如果你想看到打印为无符号的值,你应该将它们转换为(unsigned int),然后再将它们传递给cout。

  

如何有效地比较哈希值?

memcmp()是比较两个任意内存缓冲区内容的一种常用方法。