/usr/share/perl5/Wiki/Toolkit/Plugin/Diff.pm is in libwiki-toolkit-plugin-diff-perl 0.12-4.
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 | package Wiki::Toolkit::Plugin::Diff;
use strict;
use warnings;
our $VERSION = '0.12';
use base 'Wiki::Toolkit::Plugin';
use Algorithm::Diff;
use VCS::Lite;
use Params::Validate qw(validate validate_pos SCALAR SCALARREF ARRAYREF HASHREF UNDEF);
sub new {
my $class = shift;
my %par = validate( @_, {
metadata_separator => { type => SCALAR, default => "<br />\n"} ,
line_number_format => { type => SCALAR, default => "== Line \$_ ==\n" },
word_matcher => { type => SCALARREF, default => qr(
&.+?; #HTML special characters e.g. <
|<br\s*/> #Line breaks
|\w+\s* #Word with trailing spaces
|. #Any other single character
)xsi },
} );
bless \%par, $class;
}
sub differences {
my $self = shift;
my %args = validate( @_, {
node => { type => SCALAR},
left_version => { type => SCALAR},
right_version => { type => SCALAR},
meta_include => { type => ARRAYREF, optional => 1 },
meta_exclude => { type => ARRAYREF, optional => 1 } });
my ($node, $v1, $v2) = @args{ qw( node left_version right_version) };
my $store = $self->datastore;
my $fmt = $self->formatter;
my %ver1 = $store->retrieve_node( name => $node, version => $v1);
my %ver2 = $store->retrieve_node( name => $node, version => $v2);
my $verstring1 = "Version ".$ver1{version};
my $verstring2 = "Version ".$ver2{version};
my $el1 = VCS::Lite->new($verstring1,undef,
$self->content_escape($ver1{content}).
$self->{metadata_separator}.
$self->serialise_metadata($ver1{metadata},
@args{qw(meta_include meta_exclude)}));
my $el2 = VCS::Lite->new($verstring2,undef,
$self->content_escape($ver2{content}).
$self->{metadata_separator}.
$self->serialise_metadata($ver2{metadata},
@args{qw(meta_include meta_exclude)}));
my %pag = %ver1;
$pag{left_version} = $verstring1;
$pag{right_version} = $verstring2;
$pag{content} = $fmt->format($ver1{content});
my $dlt = $el1->delta($el2)
or return %pag;
my @out;
for ($dlt->hunks) {
my ($lin1,$lin2,$out1,$out2);
for (@$_) {
my ($ind,$line,$text) = @$_;
if ($ind ne '+') {
$lin1 ||= $line;
$out1 .= $text;
}
if ($ind ne '-') {
$lin2 ||= $line;
$out2 .= $text;
}
}
push @out,{ left => $self->line_number($lin1),
right => $self->line_number($lin2) };
my ($text1,$text2) = $self->intradiff($out1,$out2);
push @out,{left => $text1,
right => $text2};
}
$pag{diff} = \@out;
%pag;
}
sub line_number {
my $self = shift;
local ($_) = validate_pos(@_, {type => SCALAR | UNDEF, optional => 1} );
return '' unless defined $_;
my $fmt = '"'. $self->{line_number_format} . '"';
eval $fmt;
}
sub serialise_metadata {
my $self = shift;
my ($all_meta,$include,$exclude) = validate_pos ( @_,
{ type => HASHREF },
{ type => ARRAYREF | UNDEF, optional => 1 },
{ type => ARRAYREF | UNDEF, optional => 1 },
);
$include ||= [keys %$all_meta];
$exclude ||= [qw(comment username
__categories__checksum __locales__checksum)] ;
my %metadata = map {$_,$all_meta->{$_}} @$include;
delete $metadata{$_} for @$exclude;
join $self->{metadata_separator},
map {"$_='".join (',',sort @{$metadata{$_}})."'"}
sort keys %metadata;
}
sub content_escape {
my $self = shift;
my ($str) = validate_pos( @_, { type => SCALAR } );
$str =~ s/&/&/g;
$str =~ s/</</g;
$str =~ s/>/>/g;
$str =~ s!\s*?\n!<br />\n!gs;
$str;
}
sub intradiff {
my $self = shift;
my ($str1,$str2) = validate_pos( @_, {type => SCALAR|UNDEF },
{type => SCALAR|UNDEF });
return (qq{<span class="diff1">$str1</span>},"") unless $str2;
return ("",qq{<span class="diff2">$str2</span>}) unless $str1;
my $re_wordmatcher = $self->{word_matcher};
my @diffs = Algorithm::Diff::sdiff([$str1 =~ /$re_wordmatcher/sg]
,[$str2 =~ /$re_wordmatcher/sg], sub {$self->get_token(@_)});
my $out1 = '';
my $out2 = '';
my ($mode1,$mode2);
for (@diffs) {
my ($ind,$c1,$c2) = @$_;
my $newmode1 = $ind =~ /[c\-]/;
my $newmode2 = $ind =~ /[c+]/;
$out1 .= '<span class="diff1">' if $newmode1 && !$mode1;
$out2 .= '<span class="diff2">' if $newmode2 && !$mode2;
$out1 .= '</span>' if !$newmode1 && $mode1;
$out2 .= '</span>' if !$newmode2 && $mode2;
($mode1,$mode2) = ($newmode1,$newmode2);
$out1 .= $c1;
$out2 .= $c2;
}
$out1 .= '</span>' if $mode1;
$out2 .= '</span>' if $mode2;
($out1,$out2);
}
sub get_token {
my ($self,$str) = @_;
$str =~ /^(\S*)\s*$/; # Match all but trailing whitespace
$1 || $str;
}
1;
__END__
=head1 NAME
Wiki::Toolkit::Plugin::Diff - format differences between two Wiki::Toolkit pages
=head1 SYNOPSIS
use Wiki::Toolkit::Plugin::Diff;
my $plugin = Wiki::Toolkit::Plugin::Diff->new;
$wiki->register_plugin( plugin => $plugin ); # called before any node reads
my %diff = $plugin->differences( node => 'Imperial College',
left_version => 3,
right_version => 5);
=head1 DESCRIPTION
A plug-in for Wiki::Toolkit sites, which provides a nice extract of differences
between two versions of a node.
=head1 BASIC USAGE
B<differences>
my %diff_vars = $plugin->differences(
node => "Home Page",
left_version => 3,
right_version => 5
);
Takes a series of key/value pairs:
=over 4
=item *
B<left_version>
The node version whose content we're considering canonical.
=item *
B<right_version>
The node version that we're showing the differences from.
=item *
B<meta_include>
Filter the list of metadata fields to only include a certain
list in the diff output. The default is to include all metadata fields.
=item *
B<meta_exclude>
Filter the list of metadata fields to exclude certain
fields from the diff output. The default is the following list, to match
previous version (OpenGuides) behaviour:
C<qw(
username
comment
__categories__checksum
__locales__checksum )>
Agreed this list is hopelessly inadequate, especially for L<OpenGuides>.
Hopefully, future wiki designers will use the meta_include parameter to
specify exactly what metadata they want to appear on the diff.
=back
The differences method returns a list of key/value pairs, which can be
assigned to a hash:
=over 4
=item B<left_version>
The node version whose content we're considering canonical.
=item B<right_version>
The node version that we're showing the differences from.
=item B<content>
The (formatted) contents of the I<Left> version of the node.
=item B<diff>
An array of hashrefs of C<hunks> of differences between the
versions. It is assumed that the display will be rendered in HTML, and SPAN
tags are inserted with a class of diff1 or diff2, to highlight which
individual words have actually changed. Display the contents of diff using
a E<lt>tableE<gt>, with each member of the array corresponding to a row
E<lt>TRE<gt>, and keys {left} and {right} being two columns E<lt>TDE<gt>.
Usually you will want to feed this through a templating system, such as
Template Toolkit, which makes iterating the AoH very easy.
=back
=head1 ADVANCED
Wiki::Toolkit::Plugin::Diff allows for a more flexible approach than HTML only
rendering of pages. In particular, there are optional parameters to the
constructor which control fine detail of the resultant output.
If this is not sufficient, the module is also subclassable, and the
programmer can supply alternative methods.
=head2 METHODS
Most of these are called internally by the plugin, but provide hooks
for alternative code if the module is subclassed.
=over 4
=item B<new>
my $plugin = Wiki::Toolkit::Plugin::Diff->new( option => value, option => value...);
Here, I<option> can be one of the following:
=over 4
=item B<metadata_separator>
A string which is inserted between each metadata
field, and also between the contents and the metadata. This defaults to
"E<lt>br /E<gt>\n" so as to render each metadata field on a new line.
=item B<line_number_format>
Used to lay out the head line number for a
difference hunk. The string is eval'ed with $_ containing the line number.
Default is "== Line \$_ ==" .
=item B<word_matcher>
is a regular expression, used to tokenize the input
string. This is the way of grouping together atomic sequences, so as to
give a readable result. The default is the following:
&.+?; #HTML special characters e.g. <
|<br\s*/> #Line breaks
|\w+\s* #Word with trailing spaces
|. #Any other single character
=back
=item B<differences>
see above.
=item B<line_number>
This method is called to format a line number into a suitable string.
The supplied routine performs the necessary substitution of
$self->{line_number_format} using eval.
=item B<serialise_metadata>
The purpose of this method is to turn a metadata hash into a string
suitable for diffing.
=item B<content_escape>
This method is used to apply the necessary quoting or escaping of
characters that could appear in the content body, that could interfere
with the rendering of the diff text.
=item B<intradiff>
This method turns an array of hunks as returned by VCS::Lite::Delta->hunks
into a side by side diff listing, with highlights indicating different
words and punctuation.
Currently, this is hardcoded to present the differences with HTML tags.
This module is a prime candidate for migration into VCS::Lite, where this
functionality really belongs.
=item B<get_token>
This allows the "false positive" bug discovered by Earle Martin to be solved
(rt.cpan.org #6284).
Effectively, the input strings (diff1 and diff2) are tokenised using the
word_matcher regexp (see above), and turned into arrays of tokens.
The default regexp absorbs trailing whitespace, to give a more readable result.
However, if a word is followed by differing whitespace or no whitespace at
all, this was throwing up a diff.
The get_token method supplied removes trailing whitespace from the key
values before they are compared.
=back
=head1 TODO
Move intradiff functionality into VCS::Lite.
=head1 BUGS AND ENHANCEMENTS
Please use rt.cpan.org to report any bugs in this module. If you have any
ideas for how this module could be enhanced, please email the author, or
post to the Wiki::Toolkit list (cgi (hyphen) wiki (hyphen) dev (at) earth (dot) li).
=head1 AUTHOR
I. P. Williams (ivorw_openguides [at] xemaps {dot} com)
The Wiki::Toolkit team (http://www.wiki-toolkit.org/)
=head1 COPYRIGHT
Copyright (C) 2003-2004 I. P. Williams (ivorw_openguides [at] xemaps {dot} com).
Copyright (C) 2006 the Wiki::Toolkit team (http://www.wiki-toolkit.org/)
All Rights Reserved.
This module is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
=head1 SEE ALSO
L<VCS::Lite>, L<Wiki::Toolkit>, L<Wiki::Toolkit::Plugin>, L<OpenGuides>
=cut
|