哈希函数

哈希函数

在设计和实现哈希函数时，通常使用的常见构建块是按位运算、数学运算和查找表。这些操作既可以应用于单个字节，也可以应用于字节块（字等），此外，它们在大多数CPU架构上都是快速，确定性和随时可用的，使其成为实现哈希函数的理想选择。以下是常用操作的列表：

• 按位运算： 不是 （！）、或 （|）、和 （&）、异或 （^）、左移/右移（<<、>>）、向左旋转/向右旋转（<<<、>>>）
• 数学运算：加法 （+）、乘法 （*）
• 查阅表格： 素数列表，幻数列表，S盒，P盒

uint32_t mix(uint32_t message_block, uint32_t internal_state)
{
   return (internal_state * message_block) ^
          ((internal_state << 3) + (message_block >> 2));
}

int32_t hash(const char* message, size_t message_length)
{
   uint32_t internal_state = 0xA5A5A5A5; // IV: A magic number
   uint32_t message_block = 0;

   // Loop over the message 32-bits at-a-time
   while (message_length >= 4)
   {
      memcpy(message_block, message, sizeof(uint32_t));

      internal_state = mix(message_block, internal_state);

      message_length -= sizeof(uint32_t);
      message        += sizeof(uint32_t);
   }

   // Are there any remaining bytes?
   if (message_length)
   {
      memcpy(message_block, message, message_length);
      internal_state = mix(message_block, internal_state);
   }

   return internal_state;
}

RS 哈希函数

unsigned int RSHash(const char* str, unsigned int length)
{
   unsigned int b    = 378551;
   unsigned int a    = 63689;
   unsigned int hash = 0;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = hash * a + (*str);
      a    = a * b;
   }

   return hash;
}

JS 哈希函数

unsigned int PJWHash(const char* str, unsigned int length)
{
   const unsigned int BitsInUnsignedInt = (unsigned int)(sizeof(unsigned int) * 8);
   const unsigned int ThreeQuarters     = (unsigned int)((BitsInUnsignedInt  * 3) / 4);
   const unsigned int OneEighth         = (unsigned int)(BitsInUnsignedInt / 8);
   const unsigned int HighBits          =
                      (unsigned int)(0xFFFFFFFF) << (BitsInUnsignedInt - OneEighth);
   unsigned int hash = 0;
   unsigned int test = 0;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = (hash << OneEighth) + (*str);

      if ((test = hash & HighBits) != 0)
      {
         hash = (( hash ^ (test >> ThreeQuarters)) & (~HighBits));
      }
   }

   return hash;
}

ELF 哈希函数

unsigned int ELFHash(const char* str, unsigned int length)
{
   unsigned int hash = 0;
   unsigned int x    = 0;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = (hash << 4) + (*str);

      if ((x = hash & 0xF0000000L) != 0)
      {
         hash ^= (x >> 24);
      }

      hash &= ~x;
   }

   return hash;
}

BKDR 哈希函数

unsigned int BKDRHash(const char* str, unsigned int length)
{
   unsigned int seed = 131; /* 31 131 1313 13131 131313 etc.. */
   unsigned int hash = 0;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = (hash * seed) + (*str);
   }

   return hash;
}

标清道夫哈希函数

unsigned int SDBMHash(const char* str, unsigned int length)
{
   unsigned int hash = 0;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = (*str) + (hash << 6) + (hash << 16) - hash;
   }

   return hash;
}

DJB 哈希函数

unsigned int DJBHash(const char* str, unsigned int length)
{
   unsigned int hash = 5381;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = ((hash << 5) + hash) + (*str);
   }

   return hash;
}

DEK 哈希函数

unsigned int DEKHash(const char* str, unsigned int length)
{
   unsigned int hash = len;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash = ((hash << 5) ^ (hash >> 27)) ^ (*str);
   }

   return hash;
}

AP 哈希函数

unsigned int APHash(const char* str, unsigned int length)
{
   unsigned int hash = 0xAAAAAAAA;
   unsigned int i    = 0;

   for (i = 0; i < length; ++str, ++i)
   {
      hash ^= ((i & 1) == 0) ? (  (hash <<  7) ^ (*str) * (hash >> 3)) :
                               (~((hash << 11) + ((*str) ^ (hash >> 5))));
   }

   return hash;
}