This file is indexed.

/usr/lib/swi-prolog/library/xpath.pl is in swi-prolog-nox 5.10.4-3ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
/*  This file is part of ClioPatria.

    Author:	Jan Wielemaker <J.Wielemaker@cs.vu.nl>
    HTTP:	http://e-culture.multimedian.nl/
    Copyright:  2007, E-Culture/MultimediaN

    ClioPatria is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 2 of the License, or
    (at your option) any later version.

    ClioPatria is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with ClioPatria.  If not, see <http://www.gnu.org/licenses/>.
*/

:- module(xpath,
	  [ xpath/3,			% +DOM, +Spec, -Value
	    xpath_chk/3,		% +DOM, +Spec, -Value

	    op(400, fx, //),
	    op(400, fx, /),
	    op(200, fy, @)
	  ]).
:- use_module(library(record)).
:- use_module(library(lists)).
:- use_module(library(occurs)).
:- use_module(library(debug)).

/** <module> Select nodes in an XML DOM

The library xpath.pl provides predicates to select nodes from an XML DOM
tree as produced by library(sgml) based  on descriptions inspired by the
XPATH language.

The   predicate   xpath/3   selects   a   sub-structure   of   the   DOM
non-deterministically based on an  xpath-like   specification.  Not  all
selectors of XPATH are implemented, but the ability to mix xpath/3 calls
with arbitrary Prolog code  provides  a   powerful  tool  for extracting
information from XML parse-trees.

@see http://www.w3.org/TR/xpath
*/

:- record
	element(name, attributes, content).

%%	xpath_chk(+DOM, +Spec, ?Content) is semidet.
%
%	Semi-deterministic version of xpath/3.

xpath_chk(DOM, Spec, Content) :-
	xpath(DOM, Spec, Content), !.

%%	xpath(+DOM, +Spec, ?Content) is nondet.
%
%	Match an element in a DOM structure.   The syntax is inspired by
%	XPath, using () rather than  []   to  select  inside an element.
%	First we can construct paths using / and //:
%
%	    $ =|//|=Term :
%	    Select any node in the DOM matching term.
%	    $ =|/|=Term :
%	    Match the root against Term.
%	    $ Term :
%	    Select the immediate children of the root matching Term.
%
%	The Terms above are of type   _callable_.  The functor specifies
%	the element name. The element name   '*'  refers to any element.
%	The name =self= refers to the   top-element  itself and is often
%	used for processing matches of an  earlier xpath/3 query. A term
%	NS:Term refers to an XML  name   in  the  namespace NS. Optional
%	arguments specify additional  constraints   and  functions.  The
%	arguments are processed from left  to right. Defined conditional
%	argument values are:
%
%	    $ Integer :
%	    The N-th element with the given name
%	    $ =last= :
%	    The last element with the given name.
%	    $ =last= - IntExpr :
%	    The IntExpr-th element counting from the last (0-based)
%
%	Defined function argument values are:
%
%	    $ =self= :
%	    Evaluate to the entire element
%	    $ =text= :
%	    Evaluates to all text from the sub-tree as an atom
%	    $ =normalize_space= :
%	    As =text=, but uses normalize_space/2 to normalise
%	    white-space in the output
%	    $ =number= :
%	    Extract an integer or float from the value.  Ignores
%	    leading and trailing white-space
%	    $ =|@|=Attribute :
%	    Evaluates to the value of the given attribute
%
%	In addition, the argument-list can be _conditions_:
%
%	    $ Left = Right :
%	    Succeeds if the left-hand unifies with the right-hand.
%	    E.g. normalize_space = 'euro'
%	    $ contains(Haystack, Needle) :
%	    Succeeds if Needle is a sub-string of Haystack.
%
%	Examples:
%
%	Match each table-row in DOM:
%
%	    ==
%	    xpath(DOM, //tr, TR)
%	    ==
%
%	Match the last cell  of  each   tablerow  in  DOM.  This example
%	illustrates that a result can be the input of subsequent xpath/3
%	queries. Using multiple queries  on   the  intermediate  TR term
%	guarantee that all results come from the same table-row:
%
%	    ==
%	    xpath(DOM, //tr, TR),
%	    xpath(TR,  /td(last), TD)
%	    ==
%
%	Match each =href= attribute in an <a> element
%
%	    ==
%	    xpath(DOM, //a(@href), HREF)
%	    ==
%
%	Suppose we have a table containing  rows where each first column
%	is the name of a product with a   link to details and the second
%	is the price (a number).  The   following  predicate matches the
%	name, URL and price:
%
%	    ==
%	    product(DOM, Name, URL, Price) :-
%	    	xpath(DOM, //tr, TR),
%	    	xpath(TR, td(1), C1),
%	    	xpath(C1, /self(normalize_space), Name),
%	    	xpath(C1, a(@href), URL),
%	    	xpath(TR, td(2, number), Price).
%	    ==
%
%	Suppose we want to select  books   with  genre="thriller" from a
%	tree containing elements =|<book genre=...>|=
%
%	    ==
%	    thriller(DOM, Book) :-
%		xpath(DOM, //book(@genre=thiller), Book).
%	    ==

xpath(DOM, Spec, Content) :-
	in_dom(Spec, DOM, Content).

in_dom(//Spec, DOM, Value) :- !,
	element_spec(Spec, Name, Modifiers),
	sub_dom(I, Len, Name, E, DOM),
	modifiers(Modifiers, I, Len, E, Value).
in_dom(/Spec, E, Value) :- !,
	element_spec(Spec, Name, Modifiers),
	(   Name == self
	->  true
	;   element_name(E, Name)
	),
	modifiers(Modifiers, 1, 1, E, Value).
in_dom(A/B, DOM, Value) :- !,
	in_dom(A, DOM, Value0),
	in_dom(B, Value0, Value).
in_dom(A//B, DOM, Value) :- !,
	in_dom(A, DOM, Value0),
	in_dom(//B, Value0, Value).
in_dom(Spec, element(_, _, Content), Value) :-
	element_spec(Spec, Name, Modifiers),
	count_named_elements(Content, Name, CLen),
	CLen > 0,
	nth_element(N, Name, E, Content),
	modifiers(Modifiers, N, CLen, E, Value).

element_spec(Var, _, _) :-
	var(Var), !,
	instantiation_error(Var).
element_spec(NS:Term, NS:Name, Modifiers) :- !,
	Term =.. [Name0|Modifiers],
	star(Name0, Name).
element_spec(Term, Name, Modifiers) :- !,
	Term =.. [Name0|Modifiers],
	star(Name0, Name).

star(*, _) :- !.
star(Name, Name).


%%	sub_dom(-Index, -Count, +Name, -Sub, +DOM) is nondet.
%
%	Sub is a node in DOM with Name.
%
%	@param Count	is the total number of nodes in the content
%			list Sub appears that have the same name.
%	@param Index	is the 1-based index of Sub of nodes with
%			Name.

sub_dom(1, 1, Name, DOM, DOM) :-
	element_name(DOM, Name).
sub_dom(N, Len, Name, E, element(_,_,Content)) :- !,
	sub_dom_2(N, Len, Name, E, Content).
sub_dom(N, Len, Name, E, Content) :-
	is_list(Content),
	sub_dom_2(N, Len, Name, E, Content).

sub_dom_2(N, Len, Name, Element, Content) :-
	(   count_named_elements(Content, Name, Len),
	    nth_element(N, Name, Element, Content)
	;   member(element(_,_,C2), Content),
	    sub_dom_2(N, Len, Name, Element, C2)
	).


%%	count_named_elements(+Content, +Name, -Count) is det.
%
%	Count is the number of nodes with Name in Content.

count_named_elements(Content, Name, Count) :-
	count_named_elements(Content, Name, 0, Count).

count_named_elements([], _, Count, Count).
count_named_elements([element(Name,_,_)|T], Name, C0, C) :- !,
	C1 is C0+1,
	count_named_elements(T, Name, C1, C).
count_named_elements([_|T], Name, C0, C) :-
	count_named_elements(T, Name, C0, C).


%%	nth_element(?N, +Name, -Element, +Content:list) is nondet.
%
%	True if Element is the N-th element with name in Content.

nth_element(N, Name, Element, Content) :-
	nth_element_(1, N, Name, Element, Content).

nth_element_(I, N, Name, E, [H|T]) :-
	element_name(H, Name), !,
	(   N = I,
	    E = H
	;   I2 is I + 1,
	    (	nonvar(N), I2 > N
	    ->	!, fail
	    ;	true
	    ),
	    nth_element_(I2, N, Name, E, T)
	).
nth_element_(I, N, Name, E, [_|T]) :-
	nth_element_(I, N, Name, E, T).


%%	modifiers(+Modifiers, +I, +Clen, +DOM, -Value)
%
%

modifiers([], _, _, Value, Value).
modifiers([H|T], I, L, Value0, Value) :-
	modifier(H, I, L, Value0, Value1),
	modifiers(T, I, L, Value1, Value).

modifier(N, I, _, Value, Value) :-				% Integer
	integer(N), !,
	N =:= I.
modifier(last, I, L, Value, Value) :- !,			% last
	I =:= L.
modifier(last-Expr, I, L, Value, Value) :- !,			% last-Expr
	I =:= L-Expr.
modifier(Function, _, _, In, Out) :-
	xpath_function(Function, In, Out).
modifier(Function, _, _, In, Out) :-
	xpath_condition(Function, In),
	Out = In.

xpath_function(self, DOM, Value) :- !,				% self
	Value = DOM.
xpath_function(text, DOM, Text) :- !,				% text
	text_of_dom(DOM, Text).
xpath_function(normalize_space, DOM, Text) :- !,		% normalize_space
	text_of_dom(DOM, Text0),
	normalize_space(atom(Text), Text0).
xpath_function(number, DOM, Number) :- !,			% number
	text_of_dom(DOM, Text0),
	normalize_space(string(Text), Text0),
	catch(atom_number(Text, Number), _, fail).
xpath_function(@Name, element(_, Attrs, _), Value) :- !,	% @Name
	memberchk(Name=Value, Attrs).
xpath_function(quote(Value), _, Value).				% quote(Value)

xpath_condition(Left = Right, Value) :- !,			% =
	var_or_function(Left, Value, LeftValue),
	var_or_function(Right, Value, RightValue),
	LeftValue = RightValue.
xpath_condition(contains(Haystack, Needle), Value) :- !,	% contains(Haystack, Needle)
	val_or_function(Haystack, Value, HaystackValue),
	val_or_function(Needle, Value, NeedleValue),
	atom(HaystackValue), atom(NeedleValue),
	(   sub_atom(HaystackValue, _, _, _, NeedleValue)
	->  true
	).

var_or_function(Arg, _, Arg) :-
	var(Arg), !.
var_or_function(Func, Value0, Value) :-
	xpath_function(Func, Value0, Value), !.
var_or_function(Value, _, Value).

val_or_function(Arg, _, Arg) :-
	var(Arg), !,
	instantiation_error(Arg).
val_or_function(Func, Value0, Value) :-				% TBD
	xpath_function(Func, Value0, Value), !.
val_or_function(Value, _, Value).


%%	text_of_dom(+DOM, -Text:atom) is det.
%
%	Text is the joined textual content of DOM.

text_of_dom(DOM, Text) :-
	phrase(text_of(DOM), Tokens),
	concat_atom(Tokens, Text).

text_of(element(_,_,Content)) -->
	text_of_list(Content).
text_of([]) -->
	[].
text_of([H|T]) -->
	text_of(H),
	text_of(T).


text_of_list([]) -->
	[].
text_of_list([H|T]) -->
	text_of_1(H),
	text_of_list(T).


text_of_1(element(_,_,Content)) --> !,
	text_of_list(Content).
text_of_1(Data) -->
	{ assertion(atom(Data)) },
	[Data].