Robert Jenkin's hash function

        哈希表是一种常用的数据结构。它们包括一个数组（哈希表）和映射（哈希函数）。哈希函数把关键码值映射到表中一个位置。存储在哈希表中的数据必须有对应的键。哈希函数将一个项的键映射到一个哈希值，并且该哈希值被用作该项的一个索引到该项的哈希表中。这使得数据能够快速访问。

                                                          哈希算法的模型

 initialize the internal state;
  for (each block of the input)
  {
    combine (the internal state, the current input block);
    mix( the internal state);
  }
  value = postprocess( the internal state );
  return (value);

例如XORhash:

  char XORhash( char *key, int len)
  {
    char hash;
    int  i;
    for (hash=0, i=0; i<len; ++i) hash=hash^key[i];
    return (hash%101);           /* 101 is prime */
  }

                                                             32位哈希

<pre>typedef  unsigned long int  u4;   /* unsigned 4-byte type */
typedef  unsigned     char  u1;   /* unsigned 1-byte type */

/* The mixing step */
#define mix(a,b,c) \
{ \
  a=a-b;  a=a-c;  a=a^(c>>13); \
  b=b-c;  b=b-a;  b=b^(a<<8);  \
  c=c-a;  c=c-b;  c=c^(b>>13); \
  a=a-b;  a=a-c;  a=a^(c>>12); \
  b=b-c;  b=b-a;  b=b^(a<<16); \
  c=c-a;  c=c-b;  c=c^(b>>5);  \
  a=a-b;  a=a-c;  a=a^(c>>3);  \
  b=b-c;  b=b-a;  b=b^(a<<10); \
  c=c-a;  c=c-b;  c=c^(b>>15); \
}

/* The whole new hash function */
u4 hash( k, length, initval)
register u1 *k;        /* the key */
u4           length;   /* the length of the key in bytes */
u4           initval;  /* the previous hash, or an arbitrary value */
{
   register u4 a,b,c;  /* the internal state */
   u4          len;    /* how many key bytes still need mixing */

   /* Set up the internal state */
   len = length;
   a = b = 0x9e3779b9;  /* the golden ratio; an arbitrary value */
   c = initval;         /* variable initialization of internal state */

   /*---------------------------------------- handle most of the key */
   while (len >= 12)
   {
      a=a+(k[0]+((u4)k[1]<<8)+((u4)k[2]<<16) +((u4)k[3]<<24));
      b=b+(k[4]+((u4)k[5]<<8)+((u4)k[6]<<16) +((u4)k[7]<<24));
      c=c+(k[8]+((u4)k[9]<<8)+((u4)k[10]<<16)+((u4)k[11]<<24));
      mix(a,b,c);
      k = k+12; len = len-12;
   }

   /*------------------------------------- handle the last 11 bytes */
   c = c+length;
   switch(len)              /* all the case statements fall through */
   {
   case 11: c=c+((u4)k[10]<<24);
   case 10: c=c+((u4)k[9]<<16);
   case 9 : c=c+((u4)k[8]<<8);
      /* the first byte of c is reserved for the length */
   case 8 : b=b+((u4)k[7]<<24);
   case 7 : b=b+((u4)k[6]<<16);
   case 6 : b=b+((u4)k[5]<<8);
   case 5 : b=b+k[4];
   case 4 : a=a+((u4)k[3]<<24);
   case 3 : a=a+((u4)k[2]<<16);
   case 2 : a=a+((u4)k[1]<<8);
   case 1 : a=a+k[0];
     /* case 0: nothing left to add */
   }
   mix(a,b,c);
   /*-------------------------------------------- report the result */
   return c;
}

The new hash deals with blocks of 12 bytes, rather than 1 byte at a time like most hashes.The whole hash, including the mix, takes about 6m+35 instructions to hash m bytes

                                                              64位哈希

<pre>#define mix64(a,b,c) \
{ \
  a=a-b;  a=a-c;  a=a^(c>>43); \
  b=b-c;  b=b-a;  b=b^(a<<9); \
  c=c-a;  c=c-b;  c=c^(b>>8); \
  a=a-b;  a=a-c;  a=a^(c>>38); \
  b=b-c;  b=b-a;  b=b^(a<<23); \
  c=c-a;  c=c-b;  c=c^(b>>5); \
  a=a-b;  a=a-c;  a=a^(c>>35); \
  b=b-c;  b=b-a;  b=b^(a<<49); \
  c=c-a;  c=c-b;  c=c^(b>>11); \
  a=a-b;  a=a-c;  a=a^(c>>12); \
  b=b-c;  b=b-a;  b=b^(a<<18); \
  c=c-a;  c=c-b;  c=c^(b>>22); \
}

The whole 64-bit hash takes about 5 m +41 instructions to hash  m  bytes.

细究慢慢看英文吧。

http://burtleburtle.net/bob/hash/evahash.html