View source with raw comments or as raw
   1/*  Part of SWI-Prolog
   2
   3    Author:        Jan Wielemaker
   4    E-mail:        J.Wielemaker@vu.nl
   5    WWW:           http://www.swi-prolog.org
   6    Copyright (c)  2011-2014, VU University Amsterdam
   7    All rights reserved.
   8
   9    Redistribution and use in source and binary forms, with or without
  10    modification, are permitted provided that the following conditions
  11    are met:
  12
  13    1. Redistributions of source code must retain the above copyright
  14       notice, this list of conditions and the following disclaimer.
  15
  16    2. Redistributions in binary form must reproduce the above copyright
  17       notice, this list of conditions and the following disclaimer in
  18       the documentation and/or other materials provided with the
  19       distribution.
  20
  21    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
  22    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
  23    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
  24    FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
  25    COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
  26    INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
  27    BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
  28    LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
  29    CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
  30    LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
  31    ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  32    POSSIBILITY OF SUCH DAMAGE.
  33*/
  34
  35:- module(isub,
  36          [ isub/4                      % +Text1, +Text2, +Normalize, -Distance
  37          ]).
  38
  39:- use_foreign_library(foreign(isub)).
  40
  41/** <module> isub: a string similarity measure
  42
  43The library(isub) implements a similarity measure between strings, i.e.,
  44something similar to the _|Levenshtein distance|_.  This method is based
  45on the length of common substrings.
  46
  47@author Giorgos Stoilos
  48@see    _|A string metric for ontology alignment|_ by Giorgos Stoilos,
  49        2005.
  50*/
  51
  52%!  isub(+Text1:atomic, +Text2:atomic, +Normalize:bool,
  53%!       -Similarity:float) is det.
  54%
  55%   Similarity is a measure for the distance between Text1 and
  56%   Text2.  E.g.
  57%
  58%     ==
  59%     ?- isub('E56.Language', 'languange', true, D).
  60%     D = 0.711348.
  61%     ==
  62%
  63%   If Normalize is =true=, isub/4   applies string normalization as
  64%   implemented by the original authors: Text1  and Text2 are mapped
  65%   to lowercase and the characters  "._   "  are removed. Lowercase
  66%   mapping is done  with  the   C-library  function  towlower(). In
  67%   general, the required normalization is   domain dependent and is
  68%   better left to the caller.  See e.g., unaccent_atom/2.
  69%
  70%   @param  Similarity is a float in the range [0.0..1.0], where 1.0
  71%           means _|most similar|_
  72
  73:- multifile sandbox:safe_primitive/1.
  74
  75sandbox:safe_primitive(isub:isub(_,_,_,_)).