This file is indexed.

/usr/share/perl5/XML/SemanticDiff.pm is in libxml-semanticdiff-perl 1.0004-2.

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
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
package XML::SemanticDiff;

use strict;
use warnings;

use vars qw/$VERSION/;

$VERSION = '1.0004';

use XML::Parser;

=head1 NAME

XML::SemanticDiff - Perl extension for comparing XML documents.

=cut

sub new {
    my ($proto, %args) = @_;
    my $class = ref($proto) || $proto;
    my $self = \%args;

    require XML::SemanticDiff::BasicHandler unless defined $args{diffhandler};

    bless ($self, $class);
    return $self;
}

sub _is_file
{
    my ($self, $specifier) = @_;
    return $specifier !~ /\n/g && -f $specifier;
}

sub _get_pathfinder_obj {
    my $self = shift;

    return XML::SemanticDiff::PathFinder::Obj->new();
}

sub read_xml {
    my $self = shift;

    my ($xml_specifier) = @_;

    if (ref($xml_specifier) eq 'HASH')
    {
        return $xml_specifier;
    }
    else
    {
        $self->{path_finder_obj} = $self->_get_pathfinder_obj();

        my $p = XML::Parser->new(
            Style => 'Stream',
            Pkg   => 'XML::SemanticDiff::PathFinder',
            'Non-Expat-Options' => $self,
            Namespaces => 1
        );

        my $ret =
            $self->_is_file($xml_specifier)
                ? $p->parsefile($xml_specifier)
                : $p->parse($xml_specifier)
                ;
        
        $self->{path_finder_obj} = undef;

        return $ret;
    }
}

sub _same_namespace
{
    my ($self, $to, $from) = @_;
    
    my $t_e = exists($to->{NamespaceURI});
    my $f_e = exists($from->{NamespaceURI});
    if (!$t_e && !$f_e)
    {
        return 1;
    }
    elsif ($t_e && $f_e)
    {
        return ($to->{NamespaceURI} eq $from->{NamespaceURI});
    }
    else
    {
        return 0;
    }
}

sub _match_xpath {
    my $self = shift;
    my ($xpath, $flat_name) = @_;
    my @x_way = split /\//, $xpath;
    my @f_way = split /\//, $flat_name;
    for my $i (0..$#x_way) {
        $x_way[$i]=~s/.*?://g;
    }           
    for my $i (0..$#f_way) {
        $f_way[$i]=~s/\[.*?\]$//g;
    }   
    return 0 if $#x_way > $#f_way;
    for my $i (0..$#x_way) {
        if ($x_way[$i] ne $f_way[$i]) {
            return 0;
        }
    }
    return 1;
}

# Okay, it's pretty basic...
#
# We flatten each doc tree to a Perl hash where the keys are "fully qualified" 
# XPath expressions (/root[1]/element[3]) that represent the unique location
# of each XML element, then compare the two hashes. 
#
# Just loop over all the elements of the first hash- if the same key exists
# in the second, you compare the text and attributes and delete it. Any
# keys not found in the second hash are declared 'missing', and any keys leftover
# in the second hash after looping through the elements in the first are 'rogues'. 

sub compare {
    my $self = shift;
    my ($from_xml, $to_xml) = @_;

    my $from_doc = $self->read_xml($from_xml);
    my $to_doc = $self->read_xml($to_xml);

    my @warnings = ();

    my $handler = $self->{diffhandler} || XML::SemanticDiff::BasicHandler->new(%$self);

    # drop away nodes matching xpaths to be ignored
    if (defined $self->{ignorexpath}) {
        my $ignore = $self->{ignorexpath};
        for my $path (@$ignore) {
            for my $ref ($from_doc, $to_doc) {
                for my $key (keys %$ref) {
                    if ($self->_match_xpath($path, $key)) {
                        delete $ref->{$key};
                    }
                }
            }
        }
    }

    # fire the init handler
    push (@warnings, $handler->init($self)) if $handler->can('init');

    # loop the elements
    foreach my $element (sort keys (%$from_doc)) {

        # element existence check
        if (defined $to_doc->{$element}) {

            # element value test
            unless ($from_doc->{$element}->{TextChecksum} eq $to_doc->{$element}->{TextChecksum}) {
                push (@warnings, $handler->element_value($element, 
                                                         $to_doc->{$element}, 
                                                         $from_doc->{$element}))
                          if $handler->can('element_value');
            }
        
            # namespace test
            unless ($self->_same_namespace($from_doc->{$element},$to_doc->{$element})) {
                push (@warnings, $handler->namespace_uri($element, 
                                                         $to_doc->{$element}, 
                                                         $from_doc->{$element}))
                           if $handler->can('namespace_uri');
            }
    
            # attribute tests
            foreach my $attr (keys(%{$from_doc->{$element}->{Attributes}})) {
 
                 # attr existence check
                 if (defined ($to_doc->{$element}->{Attributes}->{$attr})) {

                     # attr value test
                     if ($to_doc->{$element}->{Attributes}->{$attr} ne $from_doc->{$element}->{Attributes}->{$attr}){
                        push (@warnings, $handler->attribute_value($attr, 
                                                                   $element, 
                                                                   $to_doc->{$element},
                                                                   $from_doc->{$element}))
                              if $handler->can('attribute_value');
                     }
                     delete $to_doc->{$element}->{Attributes}->{$attr};
                 }
                 else {
                     push (@warnings, $handler->missing_attribute($attr, 
                                                                  $element, 
                                                                  $to_doc->{$element}, 
                                                                  $from_doc->{$element}))
                           if $handler->can('missing_attribute'); 
                 }                
            }

            # rogue attrs
            foreach my $leftover (keys(%{$to_doc->{$element}->{Attributes}})) {
                push (@warnings, $handler->rogue_attribute($leftover, 
                                                           $element, 
                                                           $to_doc->{$element}, 
                                                           $from_doc->{$element}))
                     if $handler->can('rogue_attribute');
            }
            
            delete $to_doc->{$element};
        }
        else {  
            push (@warnings, $handler->missing_element($element, $from_doc->{$element}))
                      if $handler->can('missing_element');          
        }
    }

    # rogue elements
    foreach my $leftover ( keys (%$to_doc) ) {
        push (@warnings, $handler->rogue_element($leftover, $to_doc->{$leftover})) 
             if $handler->can('rogue_element');
    }                 

    push (@warnings, $handler->final($self)) if $handler->can('final');
            
    return @warnings;
}

1;

package XML::SemanticDiff::PathFinder;

foreach my $func (qw(StartTag EndTag Text StartDocument EndDocument PI))
{
    no strict 'refs';
    *{__PACKAGE__.'::'.$func} = sub {
        my $expat = shift;
        return $expat->{'Non-Expat-Options'}->{path_finder_obj}->$func(
            $expat, @_
        );
    };
}

package XML::SemanticDiff::PathFinder::Obj;

use strict;

use Digest::MD5  qw(md5_base64);

use Encode qw(encode_utf8);

foreach my $accessor (qw(descendents char_accumulator doc
    opts xml_context PI_position_index))
{
    no strict 'refs';
    *{__PACKAGE__.'::'.$accessor} = sub {
        my $self = shift;

        if (@_)
        {
            $self->{$accessor} = shift;
        }
        return $self->{$accessor};
    };
}

# PI_position_index is the position index for the PI's below - the processing 
# instructions.

sub new {
    my $class = shift;

    my $self = {};
    bless $self, $class;

    $self->_init(@_);

    return $self;
}

sub _init {
    return 0;
}

sub StartTag {
    my ($self, $expat, $element) = @_;


    my %attrs = %_;
            
    my @context = $expat->context;
    my $context_length = scalar (@context);
    my $parent = $context[$context_length -1];
    push (@{$self->descendents()->{$parent}}, $element) if $parent;

    my $last_ctx_elem = $self->xml_context()->[-1] || { position_index => {}};

    push @{$self->xml_context()}, 
        {
            element => "$element", 
            'index' => ++$last_ctx_elem->{position_index}->{"$element"},
            position_index => {},
        };

    my $test_context;
 
    # if (@context){
    #     $test_context = '/' . join ('/', map { $_ . '[' . $position_index->{$_} . ']' } @context);
    # }   
        
    # $test_context .= '/' . $element . '[' . $position_index->{$element} . ']';

    $test_context = $self->_calc_test_context();

    $self->doc()->{$test_context} = 
    {
        NamespaceURI => ($expat->namespace($element) || ""),
        Attributes   => \%attrs,
        ($self->opts()->{keeplinenums}
            ? ( TagStart => $expat->current_line) 
            : ()
        ),
    };
}

sub _calc_test_context
{
    my $self = shift;

    return 
        join("", 
            map { "/". $_->{'element'} . "[" . $_->{'index'} . "]" } 
            @{$self->xml_context()}
        );
}

sub EndTag {
    my ($self, $expat, $element) = @_;
    
    my @context = $expat->context;

    # if (@context){
    #    $test_context = '/' . join ('/', map { $_ . '[' . $position_index->{$_} . ']' } @context);
    #} 
    # $test_context .= '/' . $element . '[' . $position_index->{$element} . ']';

    my $test_context = $self->_calc_test_context();

    my $text;
    if ( defined( $self->char_accumulator()->{$element} )) { 
        $text = $self->char_accumulator()->{$element};
        delete $self->char_accumulator()->{$element};
    }
    $text ||= 'o';
    
#    warn "text is '$text' \n";
#    my $ctx = Digest::MD5->new;
#    $ctx->add("$text");
#    $self->doc()->{"$test_context"}->{TextChecksum} = $ctx->b64digest;

    $self->doc()->{"$test_context"}->{TextChecksum} = md5_base64(encode_utf8("$text"));
    if ($self->opts()->{keepdata}) {
        $self->doc()->{"$test_context"}->{CData} = $text;
    }
    
    
    if (defined ( $self->descendents()->{$element})) {
        my $seen = {};
        foreach my $child (@{$self->descendents()->{$element}}) {
            next if $seen->{$child};
            $seen->{$child}++;
        }
    }
    
    $self->doc()->{"$test_context"}->{TagEnd} = $expat->current_line if $self->opts()->{keeplinenums};

    pop(@{$self->xml_context()});
}

sub Text {
    my $self = shift;
    my $expat = shift;
    
    my $element = $expat->current_element;
    my $char = $_;
    
    $char =~ s/^\s*//;
    $char =~ s/\s*$//;
    $char =~ s/\s+/ /g;
    $self->char_accumulator()->{$element} .= $char if $char;
    
}
        
sub StartDocument {
    my $self = shift;
    my $expat = shift;
    $self->doc({});
    $self->descendents({});
    $self->char_accumulator({});
    $self->opts($expat->{'Non-Expat-Options'});
    $self->xml_context([]);
    $self->PI_position_index({});
}
        
sub EndDocument {
    my $self = shift;

    return $self->doc();
}


sub PI {
    my ($self, $expat, $target, $data) = @_;
    my $attrs = {};
    $self->PI_position_index()->{$target}++;

    foreach my $pair (split /\s+/, $data) {
        $attrs->{$1} = $2 if $pair =~ /^(.+?)=["'](.+?)["']$/;
    }

    my $slug = '?' . $target . '[' . $self->PI_position_index()->{$target} . ']';

    $self->doc()->{$slug} =
        {
            Attributes => ($attrs || {}),
            TextChecksum => "1",
            NamespaceURI => "", 
            ( $self->opts()->{keeplinenums} 
            ? (
                TagStart => $expat->current_line(),
                TagEnd => $expat->current_line(),
              )
            : ()
            ),
        };
}   

1;


=head1 SYNOPSIS

  use XML::SemanticDiff;
  my $diff = XML::SemanticDiff->new();

  foreach my $change ($diff->compare($file, $file2)) {
      print "$change->{message} in context $change->{context}\n";
  }

  # or, if you want line numbers:

  my $diff = XML::SemanticDiff->new(keeplinenums => 1);

  foreach my $change ($diff->compare($file, $file2)) {
      print "$change->{message} (between lines $change->{startline} and $change->{endline})\n";
  }

=head1 DESCRIPTION

XML::SematicDiff provides a way to compare the contents and structure of two XML documents. By default, it returns a list of
hashrefs where each hashref describes a single difference between the two docs.

=head1 METHODS

=head2 $obj->new([%options])

Ye olde object constructor.

The new() method recognizes the following options:

=over 4

=item * keeplinenums

When this option is enabled XML::SemanticDiff will add the 'startline' and 'endline' properties (containing the line numbers
for the reported element's start tag and end tag) to each warning. For attribute events these numbers reflect the start and
end tags of the element which contains that attribute. 

=item * keepdata

When this option is enabled XML::SemanticDiff will add the 'old_value' and 'new_value' properties to each warning. These
properties contain, surprisingly, the old and new values for the element or attribute being reported. 

In the case of missing elements or attributes (those in the first document, not in the second) only the 'old_value' property
will be defined. Similarly, in the case of rogue elements or attributes (those in the second document but not in the
first) only the 'new_value' property will be defined. 

Note that using this option will greatly increase the amount of memory used by your application.

=item * diffhandler

Taking a blessed object as it's sole argument, this option provides a way to hook the basic semantic diff engine into your own
custom handler class. 

Please see the section on 'CUSTOM HANDLERS' below.

=item  * ignorexpath

This option takes array of strings as argument. Strings are interpreted as simple xpath expressions. Nodes matching these expressions are ignored during comparison. All xpath expressions should be absolute (start with '/'). 

Current implementation ignores namespaces during comparison.

=back

=head2 @results = $differ->compare($xml1, $xml2)

Compares the XMLs $xml1 and $xml2 . $xml1 and $xml2 can be:

=over 4

=item * filenames

This will be considered if it is a string that does not contain newlines and 
exists in the filesystem.

=item * the XML text itself.

This will be considered if it's any kind of string.

=item * the results of read_xml(). (see below)

This will be considered if it's a hash reference.

=back

=head2 my $doc = read_xml($xml_location)

This will read the XML, process it for comparison and return it. See compare()
for how it is determined.

=head1 CUSTOM HANDLERS

Internally, XML::SemanticDiff uses an event-based model somewhat reminiscent of SAX where the various 'semantic diff events'
are handed off to a separate handler class to cope with the details. For most general cases where the user only cares about 
reporting the differences between two docs, the default handler, XML::SemanticDiff::BasicHandler, will probably  
suffice. However, it is often desirable to add side-effects to the diff process (updating datastores, widget callbacks,  
etc.) and a custom handler allows you to be creative with what to do about differences between two XML documents and how
those differences are reported back to the application through the compare() method.

=head1 HANDLER METHODS

The following is a list of handler methods that can be used for your custom diff-handler class.

=head2 init($self, $diff_obj)

The C<init> method is called immediately before the the two document HASHes are compared. The blessed XML::SemanticDiff object
is passed as the sole argument, so any values that you wish to pass from your application to your custom handler can safely
be added to the call to XML::SemanticDiff's constructor method.

=head2 rogue_element($self, $element_name, $todoc_element_properties)

The C<rogue_element> method handles those cases where a given element exists in the to-file but not in the from-file.

=head2 missing_element($self, $element_name, $fromdoc_element_properties)

The C<missing_element> method handles those cases where a given element exists in the from-file but not in the to-file.

=head2 element_value($self, $element, $to_element_properties, $fromdoc_element_properties)

The C<element_value> method handles those cases where the text data differs between two elements that have the same name,
namespace URI, and are at the same location in the document tree. Note that all whitespace is normalized and the text from
mixed-content elements (those containing both text and child elements mixed together) is aggregated down to a single value.

=head2 namespace_uri($self, $element, $todoc_element_properties, $fromdoc_element_properties)

The C<namespace_uri> method handles case where the XML namespace URI differs between a given element in the two
documents. Note that the namespace URI is checked, not the element prefixes since <foo:element/> <bar:element/> and <element/> 
are all considered equivalent as long as they are bound to the same namespace URI.
 

=head2 rogue_attribute($self, $attr_name, $element, $todoc_element_properties)

The C<rogue_attribute> method handles those cases where an attribute exists in a given element the to-file but not in the
from-file.

=head2 missing_attribute($self, $attr_name, $element, $todoc_element_properties, $fromdoc_element_properties)

The C<missing_attribute> method handles those cases where an attribute exists in a given element exists in the from-file but
not in the to-file.

=head2 attribute_value($self, $attr_name, $element, $todoc_element_properties, $fromdoc_element_properties)

The C<attribute_value> method handles those cases where the value of an attribute varies between the same element in both
documents.

=head2 final($self, $diff_obj)

The C<final> method is called immediately after the two document HASHes are compared. Like the C<init> handler, it is passed a
copy of the XML::SemanticDiff object as it's sole argument.

Note that if a given method is not implemented in your custom handler class, XML::SemanticDiff will not complain; but it means
that all of those events will be silently ignored. Consider yourself warned. 

=head1 AUTHOR

Originally by Kip Hampton, khampton@totalcinema.com .

Further Maintained by Shlomi Fish, L<http://www.shlomifish.org/> .

=head1 COPYRIGHT

Copyright (c) 2000 Kip Hampton. All rights reserved. This program is 
free software; you can redistribute it and/or modify it under the same terms 
as Perl itself.

Shlomi Fish hereby disclaims any implicit or explicit copyrights on this
software.

=head1 LICENSE

This program is free software; you can redistribute it and/or modify it under 
the same terms as Perl itself.

=head1 SEE ALSO

perl(1).

=cut