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)  2009-2022, University of Amsterdam
    7                              CWI, Amsterdam
    8                              SWI-Prolog Solutions b.v.
    9    All rights reserved.
   10
   11    Redistribution and use in source and binary forms, with or without
   12    modification, are permitted provided that the following conditions
   13    are met:
   14
   15    1. Redistributions of source code must retain the above copyright
   16       notice, this list of conditions and the following disclaimer.
   17
   18    2. Redistributions in binary form must reproduce the above copyright
   19       notice, this list of conditions and the following disclaimer in
   20       the documentation and/or other materials provided with the
   21       distribution.
   22
   23    THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
   24    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
   25    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
   26    FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
   27    COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
   28    INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
   29    BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
   30    LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
   31    CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
   32    LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
   33    ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
   34    POSSIBILITY OF SUCH DAMAGE.
   35*/
   36
   37:- module(rdf_compare,
   38          [ rdf_equal_graphs/3          % +Graph1, +Graph2, -Substitutions
   39          ]).   40:- if(exists_source(library(semweb/rdf_db))).   41:- use_module(library(semweb/rdf_db),[lang_equal/2,rdf_is_bnode/1]).   42:- endif.   43:- autoload(library(apply),[partition/4,maplist/3]).   44:- use_module(library(debug),[debug/3]).   45:- autoload(library(lists),[select/3]).   46
   47/** <module> Compare RDF graphs
   48
   49This library provides predicates that compare   RDF  graphs. The current
   50version only provides one predicate:   rdf_equal_graphs/3  verifies that
   51two graphs are identical after proper labeling of the blank nodes.
   52
   53Future versions of this library may   contain  more advanced operations,
   54such as diffing two graphs.
   55*/
   56
   57
   58%!  rdf_equal_graphs(+GraphA, +GraphB, -Substition) is semidet.
   59%
   60%   True if GraphA  and  GraphB  are   the  same  under  Substition.
   61%   Substition is a list of BNodeA = BNodeB, where BNodeA is a blank
   62%   node that appears in GraphA and  BNodeB   is  a  blank node that
   63%   appears in GraphB.
   64%
   65%   @param GraphA is a list of rdf(S,P,O) terms
   66%   @param GraphB is a list of rdf(S,P,O) terms
   67%   @param Substition is a list if NodeA = NodeB terms.
   68%   @tbd    The current implementation is rather naive.  After
   69%           dealing with the subgraphs that contain no bnodes,
   70%           it performs a fully non-deterministic substitution.
   71
   72rdf_equal_graphs(A, B, Substitutions) :-
   73    sort(A, SA),
   74    sort(B, SB),
   75    partition(contains_bnodes, SA, VA, GA),
   76    partition(contains_bnodes, SB, VB, GB),
   77    (   GA == GB
   78    ->  true
   79    ;   maplist(compare_triple, GA, GB)
   80    ),
   81    compare_list(VA, VB, [], Substitutions),
   82    !.
   83
   84contains_bnodes(rdf(S,P,O)) :-
   85    (   node_id(S)
   86    ;   node_id(P)
   87    ;   node_id(O)
   88    ),
   89    !.
   90
   91compare_list([], [], S, S).
   92compare_list([H1|T1], In2, S0, S) :-
   93    select(H2, In2, T2),
   94    compare_triple(H1, H2, S0, S1),
   95    compare_list(T1, T2, S1, S).
   96
   97compare_triple(T1, T2) :-
   98    compare_triple(T1,T2,[],[]).
   99
  100compare_triple(rdf(Subj1,P1,O1), rdf(Subj2, P2, O2), S0, S) :-
  101    compare_field(Subj1, Subj2, S0, S1),
  102    compare_field(P1, P2, S1, S2),
  103    compare_field(O1, O2, S2, S).
  104
  105compare_field(X, X, S, S) :- !.
  106compare_field(literal(X), xml(X), S, S) :- !. % TBD
  107compare_field(literal(lang(L1,X)), literal(lang(L2,X)), S, S) :-
  108    !,
  109    lang_equal(L1, L2).
  110compare_field(X, Id, S, S) :-
  111    memberchk(X=Id, S),
  112    !.
  113compare_field(X, Y, S, [X=Y|S]) :-
  114    \+ memberchk(X=_, S),
  115    node_id(X),
  116    node_id(Y),
  117    debug(rdf_compare, 'Assume ~w = ~w~n', [X, Y]).
  118
  119node_id(node(_)) :- !.
  120node_id(X) :-
  121    rdf_is_bnode(X).
  122
  123:- if(\+current_predicate(rdf_is_bnode/1)).  124rdf_is_bnode(Node) :-
  125    atom(Node),
  126    sub_atom(Node, 0, _, _, '_:').
  127:- endif.  128:- if(\+current_predicate(lang_equal/2)).  129lang_equal(X, Y) :-
  130    downcase_atom(X, L),
  131    downcase_atom(Y, L).
  132:- endif.