git.m6w6.name Git - m6w6/libmemcached/blob - libhashkit/murmur.cc

   1 /*  vim:expandtab:shiftwidth=2:tabstop=2:smarttab:
   2  *
   3  *  HashKit library
   4  *
   5  *  Copyright (C) 2011-2012 Data Differential, http://datadifferential.com/
   6  *  Copyright (C) 2006-2009 Brian Aker All rights reserved.
   7  *
   8  *  Redistribution and use in source and binary forms, with or without
   9  *  modification, are permitted provided that the following conditions are
  10  *  met:
  11  *
  12  *      * Redistributions of source code must retain the above copyright
  13  *  notice, this list of conditions and the following disclaimer.
  14  *
  15  *      * Redistributions in binary form must reproduce the above
  16  *  copyright notice, this list of conditions and the following disclaimer
  17  *  in the documentation and/or other materials provided with the
  18  *  distribution.
  19  *
  20  *      * The names of its contributors may not be used to endorse or
  21  *  promote products derived from this software without specific prior
  22  *  written permission.
  23  *
  24  *  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  25  *  "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  26  *  LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
  27  *  A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
  28  *  OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  29  *  SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  30  *  LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
  31  *  DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
  32  *  THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
  33  *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
  34  *  OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  35  *
  36  */
  37
  38 /*
  39   "Murmur" hash provided by Austin, tanjent@gmail.com
  40   http://murmurhash.googlepages.com/
  41
  42   Note - This code makes a few assumptions about how your machine behaves -
  43
  44   1. We can read a 4-byte value from any address without crashing
  45   2. sizeof(int) == 4
  46
  47   And it has a few limitations -
  48   1. It will not work incrementally.
  49   2. It will not produce the same results on little-endian and big-endian
  50   machines.
  51
  52   Updated to murmur2 hash - BP
  53 */
  54
  55 #include <libhashkit/common.h>
  56
  57 #ifdef HAVE_MURMUR_HASH
  58
  59 uint32_t hashkit_murmur(const char *key, size_t length, void *context)
  60 {
  61   /*
  62     'm' and 'r' are mixing constants generated offline.  They're not
  63     really 'magic', they just happen to work well.
  64   */
  65
  66   const unsigned int m= 0x5bd1e995;
  67   const uint32_t seed= (0xdeadbeef * (uint32_t)length);
  68   const int r= 24;
  69
  70
  71   // Initialize the hash to a 'random' value
  72
  73   uint32_t h= seed ^ (uint32_t)length;
  74
  75   // Mix 4 bytes at a time into the hash
  76
  77   const unsigned char * data= (const unsigned char *)key;
  78   (void)context;
  79
  80   while(length >= 4)
  81   {
  82     unsigned int k = *(unsigned int *)data;
  83
  84     k *= m;
  85     k ^= k >> r;
  86     k *= m;
  87
  88     h *= m;
  89     h ^= k;
  90
  91     data += 4;
  92     length -= 4;
  93   }
  94
  95   // Handle the last few bytes of the input array
  96
  97   switch(length)
  98   {
  99   case 3: h ^= ((uint32_t)data[2]) << 16;
 100   case 2: h ^= ((uint32_t)data[1]) << 8;
 101   case 1: h ^= data[0];
 102           h *= m;
 103   default: break;
 104   };
 105
 106   /*
 107     Do a few final mixes of the hash to ensure the last few bytes are
 108     well-incorporated.
 109   */
 110
 111   h ^= h >> 13;
 112   h *= m;
 113   h ^= h >> 15;
 114
 115   return h;
 116 }
 117
 118 #else
 119 uint32_t hashkit_murmur(const char *, size_t , void *)
 120 {
 121   return 0;
 122 }
 123 #endif