1  #region License Information


2  /* HeuristicLab


3  * Copyright (C) 20022018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)


4  *


5  * This file is part of HeuristicLab.


6  *


7  * HeuristicLab is free software: you can redistribute it and/or modify


8  * it under the terms of the GNU General Public License as published by


9  * the Free Software Foundation, either version 3 of the License, or


10  * (at your option) any later version.


11  *


12  * HeuristicLab is distributed in the hope that it will be useful,


13  * but WITHOUT ANY WARRANTY; without even the implied warranty of


14  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the


15  * GNU General Public License for more details.


16  *


17  * You should have received a copy of the GNU General Public License


18  * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.


19  */


20  #endregion


21 


22 


23  using System;


24  using System.Security.Cryptography;


25 


26  namespace HeuristicLab.Problems.DataAnalysis.Symbolic {


27  public static class HashUtil {


28  // This class contains some hash functions adapted from http://partow.net/programming/hashfunctions/index.html#AvailableHashFunctions


29 


30  // A simple hash function from Robert Sedgwicks Algorithms in C book.I've added some simple optimizations to the algorithm in order to speed up its hashing process.


31  public static ulong RSHash(byte[] input) {


32  const int b = 378551;


33  ulong a = 63689;


34  ulong hash = 0;


35 


36  foreach (var v in input) {


37  hash = (hash * a) + v;


38  a *= b;


39  }


40  return hash;


41  }


42 


43  // A bitwise hash function written by Justin Sobel


44  public static ulong JSHash(byte[] input) {


45  ulong hash = 1315423911;


46  for (int i = 0; i < input.Length; ++i)


47  hash ^= (hash << 5) + input[i] + (hash >> 2);


48  return hash;


49  }


50 


51  // This hash function comes from Brian Kernighan and Dennis Ritchie's book "The C Programming Language". It is a simple hash function using a strange set of possible seeds which all constitute a pattern of 31....31...31 etc, it seems to be very similar to the DJB hash function.


52  public static ulong BKDRHash(byte[] input) {


53  ulong seed = 131;


54  ulong hash = 0;


55  foreach (var v in input) {


56  hash = (hash * seed) + v;


57  }


58  return hash;


59  }


60 


61  // This is the algorithm of choice which is used in the open source SDBM project. The hash function seems to have a good overall distribution for many different data sets. It seems to work well in situations where there is a high variance in the MSBs of the elements in a data set.


62  public static ulong SDBMHash(byte[] input) {


63  ulong hash = 0;


64  foreach (var v in input) {


65  hash = v + (hash << 6) + (hash << 16)  hash;


66  }


67  return hash;


68  }


69 


70  // An algorithm produced by Professor Daniel J. Bernstein and shown first to the world on the usenet newsgroup comp.lang.c. It is one of the most efficient hash functions ever published.


71  public static ulong DJBHash(byte[] input) {


72  ulong hash = 5381;


73  foreach (var v in input) {


74  hash = (hash << 5) + hash + v;


75  }


76  return hash;


77  }


78 


79  // An algorithm proposed by Donald E.Knuth in The Art Of Computer Programming Volume 3, under the topic of sorting and search chapter 6.4.


80  public static ulong DEKHash(byte[] input) {


81  ulong hash = (ulong)input.Length;


82  foreach (var v in input) {


83  hash = (hash << 5) ^ (hash >> 27) ^ v;


84  }


85  return hash;


86  }


87 


88  public static ulong CryptoHash(HashAlgorithm ha, byte[] input) {


89  return BitConverter.ToUInt64(ha.ComputeHash(input), 0);


90  }


91  }


92  }

