view release on metacpan or  search on metacpan

lib/Aion/Format/Html.pm  view on Meta::CPAN

noembed
noframes
noscript

ol

p
pre
progress

q

rp
rt
ruby

s
samp
section
small
span
strike
strong
   sub
summary
sup

table
tbody
td
tfoot
th
thead
time

tr
tt

u
ul

var

wbr
/;

my %SAFE_ATTR = map {$_=>1} qw/
pubdate datetime
open optimum

dir lang language style tabindex title high low hreflang icon

max min

href media ping rel rev name type

class

src

alt crossorigin decoding height width importance  intrinsicsize loading sizes srcset

align border hspace vspace longdesc  axis  char charoff summary

colspan rowspan

border cite bgcolor color

coords
/;

# срезает у html-я опасные, а так же неведомые теги
sub safe_html($;$) {
	(local $_, my $link) = @_;

	my $f = sub {
		return "" if !exists $SAFE_TAG{lc $2};
		return "</$2>" if $1 ne "";
		my $tag = $2;
		my $x = $3;
		my @attrs;
		while($x =~ /
			\b (?<attr> [a-z][a-z\d]*) ( \s*=\s* ( (?<quot> ") (?<val> [^"]*)" | (?<quot> ') (?<val> [^']*)' | (?<val> \S*) ) )?
		/gixn) {
			push @attrs, $+{val} eq ""? " $+{attr}"
				: join "", " ", $+{attr}, "=", $+{quot},
					lc $+{attr} ~~ [qw/src href/]
						? Aion::Format::Url::normalize_url($+{val}, $link)
						: $+{val},
					$+{quot}
				if exists $SAFE_ATTR{lc $+{attr}};
		}

		push @attrs, " target=_blank" if lc $tag eq "a";

		"<$tag@attrs>"
	};

	s{<(/\s*)?([a-z][a-z\d:-]*)([^<>]*)>|<!--(?:.*?)-->}{ $f->() }igse;

	$_
}

1;

__END__

=encoding utf-8

=head1 NAME

Aion::Format::Html - library for HTML formatting

=head1 SYNOPSIS

	use Aion::Format::Html;
	
	from_html "<b>&excl;</b>" # => !
	to_html "<a>"             # => &lt;a&gt;

=head1 DESCRIPION