Back to...

   1  --  Data_Segmentation
   2  ---------------------
   3  --
   4  --  Pure Ada 2012+ code, 100% portable: OS-, CPU- and compiler- independent.
   5  --
   6  --  The Data_Segmentation package offers tools for splitting data into more
   7  --  homogeneous blocks, with the hope of compressing those blocks better.
   8  --
   9  --  Legal licensing note:
  10  --
  11  --  Copyright (c) 2025 Gautier de Montmollin
  12  --  SWITZERLAND
  13  --
  14  --  Permission is hereby granted, free of charge, to any person obtaining a copy
  15  --  of this software and associated documentation files (the "Software"), to deal
  16  --  in the Software without restriction, including without limitation the rights
  17  --  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
  18  --  copies of the Software, and to permit persons to whom the Software is
  19  --  furnished to do so, subject to the following conditions:
  20  --
  21  --  The above copyright notice and this permission notice shall be included in
  22  --  all copies or substantial portions of the Software.
  23  --
  24  --  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
  25  --  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
  26  --  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
  27  --  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
  28  --  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
  29  --  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
  30  --  THE SOFTWARE.
  31  --
  32  --  NB: this is the MIT License, as found 21-Aug-2016 on the site
  33  --  http://www.opensource.org/licenses/mit-license.php
  34  
  35  with Ada.Containers.Vectors;
  36  
  37  generic
  38  
  39    type Index is range <>;
  40    type Alphabet is (<>);  --  Any discrete type (usually: Byte, Unsigned_8).
  41    type Buffer_Type is array (Index range <>) of Alphabet;
  42  
  43    discrepancy_threshold : Float;  --  Discrepancy detection threshold (e.g.: 1.9).
  44    index_threshold       : Index;  --  Do segmentation only above a certain distance (e.g.: 20_000).
  45    window_size           : Index;  --  Sliding window size (e.g.: 10_000).
  46  
  47  package Data_Segmentation is
  48  
  49    subtype Positive_Index is Index range 1 .. Index'Last;
  50    package Index_Vectors is new Ada.Containers.Vectors (Positive, Positive_Index);
  51    subtype Segmentation is Index_Vectors.Vector;
  52  
  53    procedure Segment_by_Entropy (buffer : in Buffer_Type; seg : out Segmentation);
  54  
  55  end Data_Segmentation;