/usr/share/perl5/Mojo/DOM/HTML.pm is in libmojolicious-perl 5.54+dfsg-1.
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 | package Mojo::DOM::HTML;
use Mojo::Base -base;
use Mojo::Util qw(html_unescape xml_escape);
use Scalar::Util 'weaken';
has 'xml';
has tree => sub { ['root'] };
my $ATTR_RE = qr/
([^<>=\s\/]+|\/) # Key
(?:
\s*=\s*
(?:
"([^"]*?)" # Quotation marks
|
'([^']*?)' # Apostrophes
|
([^>\s]*) # Unquoted
)
)?
\s*
/x;
my $TOKEN_RE = qr/
([^<]+)? # Text
(?:
<(?:
!(?:
DOCTYPE(
\s+\w+ # Doctype
(?:(?:\s+\w+)?(?:\s+(?:"[^"]*"|'[^']*'))+)? # External ID
(?:\s+\[.+?\])? # Int Subset
\s*)
|
--(.*?)--\s* # Comment
|
\[CDATA\[(.*?)\]\] # CDATA
)
|
\?(.*?)\? # Processing Instruction
|
(\s*[^<>\s]+ # Tag
\s*(?:(?:$ATTR_RE){0,32766})*+) # Attributes
)>
|
(<) # Runaway "<"
)??
/xis;
# HTML elements that only contain raw text
my %RAW = map { $_ => 1 } qw(script style);
# HTML elements that only contain raw text and entities
my %RCDATA = map { $_ => 1 } qw(title textarea);
# HTML elements with optional end tags
my %END = (body => 'head', optgroup => 'optgroup', option => 'option');
# HTML elements that break paragraphs
map { $END{$_} = 'p' } (
qw(address article aside blockquote dir div dl fieldset footer form h1 h2),
qw(h3 h4 h5 h6 header hr main menu nav ol p pre section table ul)
);
# HTML table elements with optional end tags
my %TABLE = map { $_ => 1 } qw(colgroup tbody td tfoot th thead tr);
# HTML elements with optional end tags and scoping rules
my %CLOSE
= (li => [{li => 1}, {ul => 1, ol => 1}], tr => [{tr => 1}, {table => 1}]);
$CLOSE{$_} = [\%TABLE, {table => 1}] for qw(colgroup tbody tfoot thead);
$CLOSE{$_} = [{dd => 1, dt => 1}, {dl => 1}] for qw(dd dt);
$CLOSE{$_} = [{rp => 1, rt => 1}, {ruby => 1}] for qw(rp rt);
$CLOSE{$_} = [{th => 1, td => 1}, {table => 1}] for qw(td th);
# HTML elements without end tags
my %EMPTY = map { $_ => 1 } (
qw(area base br col embed hr img input keygen link menuitem meta param),
qw(source track wbr)
);
# HTML elements categorized as phrasing content (and obsolete inline elements)
my @PHRASING = (
qw(a abbr area audio b bdi bdo br button canvas cite code data datalist),
qw(del dfn em embed i iframe img input ins kbd keygen label link map mark),
qw(math meta meter noscript object output picture progress q ruby s samp),
qw(script select small span strong sub sup svg template textarea time u),
qw(var video wbr)
);
my @OBSOLETE = qw(acronym applet basefont big font strike tt);
my %PHRASING = map { $_ => 1 } @OBSOLETE, @PHRASING;
# HTML elements that don't get their self-closing flag acknowledged
my %BLOCK = map { $_ => 1 } (
qw(a address applet article aside b big blockquote body button caption),
qw(center code col colgroup dd details dialog dir div dl dt em fieldset),
qw(figcaption figure font footer form frameset h1 h2 h3 h4 h5 h6 head),
qw(header hgroup html i iframe li listing main marquee menu nav nobr),
qw(noembed noframes noscript object ol optgroup option p plaintext pre rp),
qw(rt s script section select small strike strong style summary table),
qw(tbody td template textarea tfoot th thead title tr tt u ul xmp)
);
sub parse {
my ($self, $html) = @_;
my $xml = $self->xml;
my $current = my $tree = ['root'];
while ($html =~ m/\G$TOKEN_RE/gcso) {
my ($text, $doctype, $comment, $cdata, $pi, $tag, $runaway)
= ($1, $2, $3, $4, $5, $6, $11);
# Text (and runaway "<")
$text .= '<' if defined $runaway;
_node($current, 'text', html_unescape $text) if defined $text;
# Tag
if (defined $tag) {
# End
if ($tag =~ /^\s*\/\s*(.+)/) { _end($xml ? $1 : lc $1, $xml, \$current) }
# Start
elsif ($tag =~ m!([^\s/]+)([\s\S]*)!) {
my ($start, $attr) = ($xml ? $1 : lc $1, $2);
# Attributes
my (%attrs, $closing);
while ($attr =~ /$ATTR_RE/go) {
my ($key, $value) = ($xml ? $1 : lc $1, $2 // $3 // $4);
# Empty tag
++$closing and next if $key eq '/';
$attrs{$key} = defined $value ? html_unescape($value) : $value;
}
# "image" is an alias for "img"
$start = 'img' if !$xml && $start eq 'image';
_start($start, \%attrs, $xml, \$current);
# Element without end tag (self-closing)
_end($start, $xml, \$current)
if !$xml && $EMPTY{$start} || ($xml || !$BLOCK{$start}) && $closing;
# Raw text elements
next if $xml || !$RAW{$start} && !$RCDATA{$start};
next unless $html =~ m!\G(.*?)<\s*/\s*$start\s*>!gcsi;
_node($current, 'raw', $RCDATA{$start} ? html_unescape $1 : $1);
_end($start, 0, \$current);
}
}
# DOCTYPE
elsif (defined $doctype) { _node($current, 'doctype', $doctype) }
# Comment
elsif (defined $comment) { _node($current, 'comment', $comment) }
# CDATA
elsif (defined $cdata) { _node($current, 'cdata', $cdata) }
# Processing instruction (try to detect XML)
elsif (defined $pi) {
$self->xml($xml = 1) if !exists $self->{xml} && $pi =~ /xml/i;
_node($current, 'pi', $pi);
}
}
return $self->tree($tree);
}
sub render { _render($_[0]->tree, $_[0]->xml) }
sub _end {
my ($end, $xml, $current) = @_;
# Search stack for start tag
my $next = $$current;
do {
# Ignore useless end tag
return if $next->[0] eq 'root';
# Right tag
return $$current = $next->[3] if $next->[1] eq $end;
# Phrasing content can only cross phrasing content
return if !$xml && $PHRASING{$end} && !$PHRASING{$next->[1]};
} while $next = $next->[3];
}
sub _node {
my ($current, $type, $content) = @_;
push @$current, my $new = [$type, $content, $current];
weaken $new->[2];
}
sub _render {
my ($tree, $xml) = @_;
# Text (escaped)
my $type = $tree->[0];
return xml_escape $tree->[1] if $type eq 'text';
# Raw text
return $tree->[1] if $type eq 'raw';
# DOCTYPE
return '<!DOCTYPE' . $tree->[1] . '>' if $type eq 'doctype';
# Comment
return '<!--' . $tree->[1] . '-->' if $type eq 'comment';
# CDATA
return '<![CDATA[' . $tree->[1] . ']]>' if $type eq 'cdata';
# Processing instruction
return '<?' . $tree->[1] . '?>' if $type eq 'pi';
# Start tag
my $result = '';
if ($type eq 'tag') {
# Open tag
my $tag = $tree->[1];
$result .= "<$tag";
# Attributes
my @attrs;
for my $key (sort keys %{$tree->[2]}) {
# No value
push @attrs, $key and next unless defined(my $value = $tree->[2]{$key});
# Key and value
push @attrs, $key . '="' . xml_escape($value) . '"';
}
$result .= join ' ', '', @attrs if @attrs;
# Element without end tag
return $xml ? "$result />" : $EMPTY{$tag} ? "$result>" : "$result></$tag>"
unless $tree->[4];
# Close tag
$result .= '>';
}
# Render whole tree
no warnings 'recursion';
$result .= _render($tree->[$_], $xml)
for ($type eq 'root' ? 1 : 4) .. $#$tree;
# End tag
$result .= '</' . $tree->[1] . '>' if $type eq 'tag';
return $result;
}
sub _start {
my ($start, $attrs, $xml, $current) = @_;
# Autoclose optional HTML elements
if (!$xml && $$current->[0] ne 'root') {
if (my $end = $END{$start}) { _end($end, 0, $current) }
elsif (my $close = $CLOSE{$start}) {
my ($allowed, $scope) = @$close;
# Close allowed parent elements in scope
my $parent = $$current;
while ($parent->[0] ne 'root' && !$scope->{$parent->[1]}) {
_end($parent->[1], 0, $current) if $allowed->{$parent->[1]};
$parent = $parent->[3];
}
}
}
# New tag
push @$$current, my $new = ['tag', $start, $attrs, $$current];
weaken $new->[3];
$$current = $new;
}
1;
=encoding utf8
=head1 NAME
Mojo::DOM::HTML - HTML/XML engine
=head1 SYNOPSIS
use Mojo::DOM::HTML;
# Turn HTML into DOM tree
my $html = Mojo::DOM::HTML->new;
$html->parse('<div><p id="a">Test</p><p id="b">123</p></div>');
my $tree = $html->tree;
=head1 DESCRIPTION
L<Mojo::DOM::HTML> is the HTML/XML engine used by L<Mojo::DOM> and based on
the L<HTML Living Standard|https://html.spec.whatwg.org> as well as the
L<Extensible Markup Language (XML) 1.0|http://www.w3.org/TR/xml/>.
=head1 ATTRIBUTES
L<Mojo::DOM::HTML> implements the following attributes.
=head2 tree
my $tree = $html->tree;
$html = $html->tree(['root']);
Document Object Model. Note that this structure should only be used very
carefully since it is very dynamic.
=head2 xml
my $bool = $html->xml;
$html = $html->xml($bool);
Disable HTML semantics in parser and activate case sensitivity, defaults to
auto detection based on processing instructions.
=head1 METHODS
L<Mojo::DOM::HTML> inherits all methods from L<Mojo::Base> and implements the
following new ones.
=head2 parse
$html = $html->parse('<foo bar="baz">I ♥ Mojolicious!</foo>');
Parse HTML/XML fragment.
=head2 render
my $str = $html->render;
Render DOM to HTML/XML.
=head1 SEE ALSO
L<Mojolicious>, L<Mojolicious::Guides>, L<http://mojolicio.us>.
=cut
|