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)  2002-2014, University of Amsterdam, 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(http_sgml_plugin, []).   36:- use_module(http_client, []).                 % library we extend
   37:- use_module(library(sgml)).   38:- use_module(library(debug)).   39
   40:- multifile
   41    http_client:http_convert_data/4.   42
   43:- multifile
   44    markup_type/2.                  % +MimeType, -ParseOptions

   59http_client:http_convert_data(In, Fields, Data, Options) :-
   60    memberchk(content_type(Type), Fields),
   61    debug(sgml_plugin, 'Content type: ~w', [Type]),
   62    (   markup_type(Type, ParseOptions)
   63    ->  true
   64    ;   type_major_props(Type, Major, Props),
   65        default_markup_type(Major, ParseOptions0),
   66        type_props(Props, ParseOptions0, ParseOptions)
   67    ),
   68    merge_options([ max_errors(-1),
   69                    syntax_errors(quiet)
   70                  | ParseOptions
   71                  ], Options, Merged),
   72    markup_options(Fields, Merged, MarkupOptions),
   73    debug(sgml_plugin, 'Markup options: ~p', [MarkupOptions]),
   74    load_structure(stream(In), Data, MarkupOptions).
   75
   76
   77type_major_props(Type0, Type, Props) :-
   78    sub_atom(Type0, B, _, A, ;),
   79    !,
   80    sub_atom(Type0, 0, B, _, Major),
   81    sub_atom(Type0, _, A, 0, Props),
   82    normalize_space(atom(Type), Major).
   83type_major_props(Type, Type, '').
   84
   85type_props('', L, L).
   86type_props(Props, L0, L) :-
   87    sub_atom(Props, _, _, A, 'charset='),
   88    sub_atom(Props, _, A, 0, CharSet0),
   89    downcase_atom(CharSet0, CharSet),
   90    known_charset(CharSet),
   91    L = [encoding(CharSet)|L0].
   92type_props(_, L, L).
   93
   94known_charset('iso-8859-1').
   95known_charset('us-ascii').
   96known_charset('utf-8').

 default_markup_type(+MimeType, -ParseOptions)

State that the HTTP contents should be parsed with load_structure/3 using the returned options. This predicate may be hooked using the multifile predicate markup_type/2.

  105default_markup_type('text/xml',
  106            [ dialect(xmlns)
  107            ]).
  108default_markup_type('text/html',
  109            [ dtd(DTD),
  110              dialect(sgml),
  111              shorttag(false)
  112            ]) :-
  113    dtd(html, DTD).
  114default_markup_type('text/x-sgml',
  115            [ dialect(sgml)
  116            ]).
  117
  118markup_options(Fields, Opt0, Options) :-
  119    (   memberchk(content_length(Bytes), Fields)
  120    ->  Options = [content_length(Bytes)|Opt0]
  121    ;   Options = Opt0
  122    ).

 merge_options(+Defaults, +GivenOptions, -Options)

If an option is not in GivenOptions, use the one from Defaults.

  129merge_options([], Options, Options).
  130merge_options([H|T], Options0, Options) :-
  131    functor(H, Name, Arity),
  132    functor(H0, Name, Arity),
  133    memberchk(H0, Options0),
  134    !,
  135    merge_options(T, Options0, Options).
  136merge_options([H|T], Options0, Options) :-
  137    merge_options(T, [H|Options0], Options)