use strict;
use bytes;
package Mail::SpamAssassin::HTML;
require Exporter;
my @ISA = qw(Exporter);
my @EXPORT = qw($re_start $re_loose $re_strict get_results);
my @EXPORT_OK = qw();
use HTML::Parser 3.24 ();
use vars qw($re_start $re_loose $re_strict $re_other);
$re_start = 'body|head|html|img|pre|table|title';
$re_loose = 'applet|basefont|center|dir|font|frame|frameset|iframe|isindex|menu|noframes|s|strike|u';
$re_strict = 'a|abbr|acronym|address|area|b|base|bdo|big|blockquote|body|br|button|caption|cite|code|col|colgroup|dd|del|dfn|div|dl|dt|em|fieldset|form|h1|h2|h3|h4|h5|h6|head|hr|html|i|img|input|ins|kbd|label|legend|li|link|map|meta|noscript|object|ol|optgroup|option|p|param|pre|q|samp|script|select|small|span|strong|style|sub|sup|table|tbody|td|textarea|tfoot|th|thead|title|tr|tt|ul|var';
my $events = 'on(?:activate|afterupdate|beforeactivate|beforecopy|beforecut|beforedeactivate|beforeeditfocus|beforepaste|beforeupdate|blur|change|click|contextmenu|controlselect|copy|cut|dblclick|deactivate|errorupdate|focus|focusin|focusout|help|keydown|keypress|keyup|load|losecapture|mousedown|mouseenter|mouseleave|mousemove|mouseout|mouseover|mouseup|mousewheel|move|moveend|movestart|paste|propertychange|readystatechange|reset|resize|resizeend|resizestart|select|submit|timeerror|unload)';
$re_other = 'o:\w+/?|x-sigsep|x-tab';
my $re_attr = 'abbr|accept-charset|accept|accesskey|action|align|alink|alt|archive|axis|background|bgcolor|border|cellpadding|cellspacing|char|charoff|charset|checked|cite|class|classid|clear|code|codebase|codetype|color|cols|colspan|compact|content|coords|data|datetime|declare|defer|dir|disabled|enctype|face|for|frame|frameborder|headers|height|href|hreflang|hspace|http-equiv|id|ismap|label|lang|language|link|longdesc|marginheight|marginwidth|maxlength|media|method|multiple|name|nohref|noresize|noshade|nowrap|object|onblur|onchange|onclick|ondblclick|onfocus|onkeydown|onkeypress|onkeyup|onload|onmousedown|onmousemove|onmouseout|onmouseover|onmouseup|onreset|onselect|onsubmit|onunload|profile|prompt|readonly|rel|rev|rows|rowspan|rules|scheme|scope|scrolling|selected|shape|size|span|src|standby|start|style|summary|tabindex|target|text|title|type|usemap|valign|value|valuetype|version|vlink|vspace|width';
my $re_attr_extra = 'family|wrap|/';
my $re_attr_no_style = 'base|basefont|head|html|meta|param|script|style|title';
my %ok_attribute = (
text => [qw(body)],
color => [qw(basefont font)],
bgcolor => [qw(body table tr td th marquee)],
face => [qw(basefont font)],
size => [qw(basefont font)],
link => [qw(body)],
alink => [qw(body)],
vlink => [qw(body)],
background => [qw(body marquee)],
);
my %tested_colors;
sub new {
my $this = shift;
my $class = ref($this) || $this;
my $self = {};
bless($self, $class);
$self->html_start();
return $self;
}
sub html_start {
my ($self) = @_;
$self->{basefont} = 3;
undef $self->{text_style};
my %default = (tag => "default",
fgcolor => "#000000",
bgcolor => "#ffffff",
size => $self->{basefont});
push @{ $self->{text_style} }, \%default;
}
sub html_end {
my ($self) = @_;
$self->display_text();
}
sub get_results {
my ($self) = @_;
return $self->{html};
}
sub html_render {
my ($self, $text) = @_;
for my $key (keys %{ $self->{html} }) {
delete $self->{html}{$key};
}
$self->{html}{ratio} = 0;
$self->{html}{image_area} = 0;
$self->{html}{shouting} = 0;
$self->{html}{max_shouting} = 0;
$self->{html}{anchor_index} = -1;
$self->{html}{title_index} = -1;
$self->{html}{max_size} = 3; $self->{html}{min_size} = 3;
$self->{html_text} = [];
$self->{html_visible_text} = [];
$self->{html_invisible_text} = [];
$self->{last_text} = "";
$self->{last_visible_text} = "";
$self->{last_invisible_text} = "";
$self->{html_last_tag} = 0;
$self->{html}{closed_html} = 0;
$self->{html}{closed_body} = 0;
$self->{html}{length} += $1 if (length($text) =~ m/^(\d+)$/);
if ($HTML::Parser::VERSION < 3.28) {
$text =~ s/<!((?!--|doctype)[^>]*)>/<!--$1-->/gsi;
}
if ($HTML::Parser::VERSION < 3.29) {
$text =~ s/<\/(?:\s.*?)?>//gs;
}
$text =~ s/ / /g;
my $hp = HTML::Parser->new(
api_version => 3,
handlers => [
start_document => [sub { $self->html_start(@_) }],
start => [sub { $self->html_tag(@_) }, "tagname,attr,'+1'"],
end_document => [sub { $self->html_end(@_) }],
end => [sub { $self->html_tag(@_) }, "tagname,attr,'-1'"],
text => [sub { $self->html_text(@_) }, "dtext"],
comment => [sub { $self->html_comment(@_) }, "text"],
declaration => [sub { $self->html_declaration(@_) }, "text"],
],
marked_sections => 1);
$hp->parse(pack ('C0A*', $text));
$hp->eof;
delete $self->{html_last_tag};
return $self->{html_text};
}
sub html_tag {
my ($self, $tag, $attr, $num) = @_;
my $is_element = ($tag =~ /^(?:$re_strict|$re_loose|$re_other)$/io);
if ($is_element) {
$self->{html}{elements}++;
$self->{html}{elements_seen}++ if !exists $self->{html}{"inside_$tag"};
}
$self->{html}{tags}++;
$self->{html}{tags_seen}++ if !exists $self->{html}{"inside_$tag"};
$self->{html}{"inside_$tag"} += $num;
$self->{html}{"inside_$tag"} = 0 if $self->{html}{"inside_$tag"} < 0;
for my $name (keys %$attr) {
if ($name !~ /^(?:$re_attr|$re_attr_extra)$/io) {
$self->{html}{attr_bad}++;
$self->{html}{attr_unique_bad}++ if !exists $self->{"attr_seen_$name"};
}
$self->{html}{attr_all}++;
$self->{html}{attr_unique_all}++ if !exists $self->{"attr_seen_$name"};
$self->{"attr_seen_$name"} = 1;
}
if ($is_element) {
if ($tag =~ /^(?:body|font|table|tr|th|td|big|small|basefont|marquee)$/) {
$self->text_style($tag, $attr, $num);
}
if ($tag !~ /^(?:$re_attr_no_style)$/ && exists $attr->{style}) {
$self->css_style($tag, $attr, $num);
}
if ($num == 1) {
$self->html_format($tag, $attr, $num);
$self->html_uri($tag, $attr, $num);
$self->html_tests($tag, $attr, $num);
}
elsif ($num == -1) {
$self->{html}{closed_html} = 1 if $tag eq "html";
$self->{html}{closed_body} = 1 if $tag eq "body";
}
if ($tag =~ /^(?:b|i|u|strong|em|big|center|h\d)$/) {
$self->{html}{shouting} += $num;
if ($self->{html}{shouting} > $self->{html}{max_shouting}) {
$self->{html}{max_shouting} = $self->{html}{shouting};
}
}
$self->{html_last_tag} = (($num < 0) ? "/" : "") . $tag;
}
}
sub html_format {
my ($self, $tag, $attr, $num) = @_;
if ($tag eq "br" || $tag eq "div") {
$self->display_text();
push @{$self->{html_visible_text}}, "\n";
push @{$self->{html_invisible_text}}, "\n";
push @{$self->{html_text}}, "\n";
}
elsif ($tag =~ /^(?:li|t[hd]|d[td])$/) {
$self->display_text();
push @{$self->{html_visible_text}}, " ";
push @{$self->{html_invisible_text}}, " ";
push @{$self->{html_text}}, " ";
}
elsif ($tag =~ /^(?:p|hr|blockquote|pre)$/) {
$self->display_text();
push @{$self->{html_visible_text}}, "\n\n";
push @{$self->{html_invisible_text}}, "\n\n";
push @{$self->{html_text}}, "\n\n";
}
}
use constant URI_STRICT => 0;
sub parse_uri {
my ($u) = @_;
my %u;
($u{scheme}, $u{authority}, $u{path}, $u{query}, $u{fragment}) =
$u =~ m|^(?:([^:/? return %u;
}
sub remove_dot_segments {
my ($input) = @_;
my $output = "";
$input =~ s@^(?:\.\.?/)@/@;
while ($input) {
if ($input =~ s@^/\.(?:$|/)@/@) {
}
elsif ($input =~ s@^/\.\.(?:$|/)@/@) {
$output =~ s@/?[^/]*$@@;
}
elsif ($input =~ s@(/?[^/]*)@@) {
$output .= $1;
}
}
return $output;
}
sub merge_uri {
my ($base_authority, $base_path, $r_path) = @_;
if (defined $base_authority && !$base_path) {
return "/" . $r_path;
}
else {
if ($base_path =~ m|/|) {
$base_path =~ s|(?<=/)[^/]*$||;
}
else {
$base_path = "";
}
return $base_path . $r_path;
}
}
sub target_uri {
my ($base, $r) = @_;
my %r = parse_uri($r); my %base = parse_uri($base); my %t;
if ((not URI_STRICT) and
(defined $r{scheme} && defined $base{scheme}) and
($r{scheme} eq $base{scheme}))
{
undef $r{scheme};
}
if (defined $r{scheme}) {
$t{scheme} = $r{scheme};
$t{authority} = $r{authority};
$t{path} = remove_dot_segments($r{path});
$t{query} = $r{query};
}
else {
if (defined $r{authority}) {
$t{authority} = $r{authority};
$t{path} = remove_dot_segments($r{path});
$t{query} = $r{query};
}
else {
if ($r{path} eq "") {
$t{path} = $base{path};
if (defined $r{query}) {
$t{query} = $r{query};
}
else {
$t{query} = $base{query};
}
}
else {
if ($r{path} =~ m|^/|) {
$t{path} = remove_dot_segments($r{path});
}
else {
$t{path} = merge_uri($base{authority}, $base{path}, $r{path});
$t{path} = remove_dot_segments($t{path});
}
$t{query} = $r{query};
}
$t{authority} = $base{authority};
}
$t{scheme} = $base{scheme};
}
$t{fragment} = $r{fragment};
my $result = "";
if ($t{scheme}) {
$result .= $t{scheme} . ":";
}
elsif (defined $t{authority}) {
if ($t{authority} =~ /^www\d*\./i) {
$result .= "http:";
}
elsif ($t{authority} =~ /^ftp\d*\./i) {
$result .= "ftp:";
}
}
if ($t{authority}) {
$result .= "//" . $t{authority};
}
$result .= $t{path};
if ($t{query}) {
$result .= "?" . $t{query};
}
if ($t{fragment}) {
$result .= "#" . $t{fragment};
}
return $result;
}
sub push_uri {
my ($self, $uri) = @_;
$uri ||= '';
$uri =~ s/^\s+//;
$uri =~ s/\s+$//;
my $target = target_uri($self->{html}{base_href} || "", $uri);
push @{$self->{html}{uri}}, $target if $target;
}
sub html_uri {
my ($self, $tag, $attr, $num) = @_;
if ($tag =~ /^(?:body|table|tr|td)$/) {
$self->push_uri($attr->{background});
}
elsif ($tag =~ /^(?:a|area|link)$/) {
$self->push_uri($attr->{href});
}
elsif ($tag =~ /^(?:img|frame|iframe|embed|script)$/) {
$self->push_uri($attr->{src});
}
elsif ($tag eq "form") {
$self->push_uri($attr->{action});
}
elsif ($tag eq "base") {
if (my $uri = $attr->{href}) {
push @{$self->{html}{uri}}, $uri;
if ($uri =~ m@^(?:https?|ftp):/{0,2}@i) {
$uri =~ s@^([a-z]+:/{0,2}[^/]+/.*?)[^/\.]+\.[^/\.]{2,4}$@$1@i;
$uri .= "/" unless $uri =~ m@/$@;
$self->{html}{base_href} = $uri;
}
}
}
}
my %html_color = (
aqua => 0x00ffff,
black => 0x000000,
blue => 0x0000ff,
fuchsia => 0xff00ff,
gray => 0x808080,
green => 0x008000,
lime => 0x00ff00,
maroon => 0x800000,
navy => 0x000080,
olive => 0x808000,
purple => 0x800080,
red => 0xff0000,
silver => 0xc0c0c0,
teal => 0x008080,
white => 0xffffff,
yellow => 0xffff00,
aliceblue => 0xf0f8ff,
antiquewhite => 0xfaebd7,
aqua => 0x00ffff,
aquamarine => 0x7fffd4,
azure => 0xf0ffff,
beige => 0xf5f5dc,
bisque => 0xffe4c4,
black => 0x000000,
blanchedalmond => 0xffebcd,
blue => 0x0000ff,
blueviolet => 0x8a2be2,
brown => 0xa52a2a,
burlywood => 0xdeb887,
cadetblue => 0x5f9ea0,
chartreuse => 0x7fff00,
chocolate => 0xd2691e,
coral => 0xff7f50,
cornflowerblue => 0x6495ed,
cornsilk => 0xfff8dc,
crimson => 0xdc143c,
cyan => 0x00ffff,
darkblue => 0x00008b,
darkcyan => 0x008b8b,
darkgoldenrod => 0xb8860b,
darkgray => 0xa9a9a9,
darkgreen => 0x006400,
darkgrey => 0xa9a9a9,
darkkhaki => 0xbdb76b,
darkmagenta => 0x8b008b,
darkolivegreen => 0x556b2f,
darkorange => 0xff8c00,
darkorchid => 0x9932cc,
darkred => 0x8b0000,
darksalmon => 0xe9967a,
darkseagreen => 0x8fbc8f,
darkslateblue => 0x483d8b,
darkslategray => 0x2f4f4f,
darkslategrey => 0x2f4f4f,
darkturquoise => 0x00ced1,
darkviolet => 0x9400d3,
deeppink => 0xff1493,
deepskyblue => 0x00bfff,
dimgray => 0x696969,
dimgrey => 0x696969,
dodgerblue => 0x1e90ff,
firebrick => 0xb22222,
floralwhite => 0xfffaf0,
forestgreen => 0x228b22,
fuchsia => 0xff00ff,
gainsboro => 0xdcdcdc,
ghostwhite => 0xf8f8ff,
gold => 0xffd700,
goldenrod => 0xdaa520,
gray => 0x808080,
green => 0x008000,
greenyellow => 0xadff2f,
grey => 0x808080,
honeydew => 0xf0fff0,
hotpink => 0xff69b4,
indianred => 0xcd5c5c,
indigo => 0x4b0082,
ivory => 0xfffff0,
khaki => 0xf0e68c,
lavender => 0xe6e6fa,
lavenderblush => 0xfff0f5,
lawngreen => 0x7cfc00,
lemonchiffon => 0xfffacd,
lightblue => 0xadd8e6,
lightcoral => 0xf08080,
lightcyan => 0xe0ffff,
lightgoldenrodyellow => 0xfafad2,
lightgray => 0xd3d3d3,
lightgreen => 0x90ee90,
lightgrey => 0xd3d3d3,
lightpink => 0xffb6c1,
lightsalmon => 0xffa07a,
lightseagreen => 0x20b2aa,
lightskyblue => 0x87cefa,
lightslategray => 0x778899,
lightslategrey => 0x778899,
lightsteelblue => 0xb0c4de,
lightyellow => 0xffffe0,
lime => 0x00ff00,
limegreen => 0x32cd32,
linen => 0xfaf0e6,
magenta => 0xff00ff,
maroon => 0x800000,
mediumaquamarine => 0x66cdaa,
mediumblue => 0x0000cd,
mediumorchid => 0xba55d3,
mediumpurple => 0x9370db,
mediumseagreen => 0x3cb371,
mediumslateblue => 0x7b68ee,
mediumspringgreen => 0x00fa9a,
mediumturquoise => 0x48d1cc,
mediumvioletred => 0xc71585,
midnightblue => 0x191970,
mintcream => 0xf5fffa,
mistyrose => 0xffe4e1,
moccasin => 0xffe4b5,
navajowhite => 0xffdead,
navy => 0x000080,
oldlace => 0xfdf5e6,
olive => 0x808000,
olivedrab => 0x6b8e23,
orange => 0xffa500,
orangered => 0xff4500,
orchid => 0xda70d6,
palegoldenrod => 0xeee8aa,
palegreen => 0x98fb98,
paleturquoise => 0xafeeee,
palevioletred => 0xdb7093,
papayawhip => 0xffefd5,
peachpuff => 0xffdab9,
peru => 0xcd853f,
pink => 0xffc0cb,
plum => 0xdda0dd,
powderblue => 0xb0e0e6,
purple => 0x800080,
red => 0xff0000,
rosybrown => 0xbc8f8f,
royalblue => 0x4169e1,
saddlebrown => 0x8b4513,
salmon => 0xfa8072,
sandybrown => 0xf4a460,
seagreen => 0x2e8b57,
seashell => 0xfff5ee,
sienna => 0xa0522d,
silver => 0xc0c0c0,
skyblue => 0x87ceeb,
slateblue => 0x6a5acd,
slategray => 0x708090,
slategrey => 0x708090,
snow => 0xfffafa,
springgreen => 0x00ff7f,
steelblue => 0x4682b4,
tan => 0xd2b48c,
teal => 0x008080,
thistle => 0xd8bfd8,
tomato => 0xff6347,
turquoise => 0x40e0d0,
violet => 0xee82ee,
wheat => 0xf5deb3,
white => 0xffffff,
whitesmoke => 0xf5f5f5,
yellow => 0xffff00,
yellowgreen => 0x9acd32,
);
sub name_to_rgb {
my $color = lc $_[0];
if (my $hex = $html_color{$color}) {
return sprintf("#%06x", $hex);
}
return $color;
}
sub close_table_tag {
my ($self, $tag) = @_;
return unless grep { $_->{tag} eq $tag } @{ $self->{text_style} };
my $top;
while (@{ $self->{text_style} } && ($top = $self->{text_style}[-1]->{tag})) {
if (($tag eq "td" && $top =~ /^(?:font|td)$/) ||
($tag eq "tr" && $top =~ /^(?:font|td|tr)$/))
{
pop @{ $self->{text_style} };
}
else {
last;
}
}
}
sub close_tag {
my ($self, $tag) = @_;
return if !grep { $_->{tag} eq $tag } @{ $self->{text_style} };
while (my %current = %{ pop @{ $self->{text_style} } }) {
last if $current{tag} eq $tag;
}
}
sub css_style {
my ($self, $tag, $attr, $num) = @_;
}
sub text_style {
my ($self, $tag, $attr, $num) = @_;
$tag = "td" if $tag eq "th";
if ($num == 1) {
if ($tag eq "body") {
}
if ($tag eq "basefont" &&
exists $attr->{size} && $attr->{size} =~ /^\s*(\d+)/)
{
$self->{basefont} = $1;
return;
}
$self->close_table_tag($tag) if ($tag eq "td" || $tag eq "tr");
my %new = %{ $self->{text_style}[-1] };
$new{tag} = $tag;
if ($tag eq "big") {
$new{size} += 1;
push @{ $self->{text_style} }, \%new;
return;
}
if ($tag eq "small") {
$new{size} -= 1;
push @{ $self->{text_style} }, \%new;
return;
}
for my $name (keys %$attr) {
next unless (grep { $_ eq $tag } @{ $ok_attribute{$name} });
if ($name =~ /^(?:text|color)$/) {
$new{fgcolor} = name_to_rgb(lc($attr->{$name}));
}
elsif ($name eq "size" && $attr->{size} =~ /^\s*([+-]\d+)/) {
$new{size} = $self->{basefont} + $1;
}
else {
if ($name eq "bgcolor") {
$attr->{bgcolor} = name_to_rgb(lc($attr->{bgcolor}));
}
if ($name eq "size" && $attr->{size} !~ /^\s*([+-])(\d+)/) {
}
else {
$new{$name} = $attr->{$name};
}
}
if ($new{size} > $self->{html}{max_size}) {
$self->{html}{max_size} = $new{size};
}
elsif ($new{size} < $self->{html}{min_size}) {
$self->{html}{min_size} = $new{size};
}
}
push @{ $self->{text_style} }, \%new;
}
else {
if ($tag ne "body") {
$self->close_tag($tag);
}
}
}
sub html_font_invisible {
my ($self, $text) = @_;
my $fg = $self->{text_style}[-1]->{fgcolor};
my $bg = $self->{text_style}[-1]->{bgcolor};
my $visible_for_bayes = 1;
if (substr($fg,-6) eq substr($bg,-6)) {
$self->{html}{font_invisible} = 1;
$visible_for_bayes = 0;
}
elsif ($fg =~ /^\ my ($r1, $g1, $b1) = (hex($1), hex($2), hex($3));
if ($bg =~ /^\ my ($r2, $g2, $b2) = (hex($1), hex($2), hex($3));
my $r = ($r1 - $r2);
my $g = ($g1 - $g2);
my $b = ($b1 - $b2);
my $distance = ((0.2126*$r)**2 + (0.7152*$g)**2 + (0.0722*$b)**2)**0.5;
if ($distance < 12) {
$self->{html}{"font_low_contrast"} = 1;
$visible_for_bayes = 0;
}
}
}
return $visible_for_bayes;
}
sub html_tests {
my ($self, $tag, $attr, $num) = @_;
local ($_);
if ($tag eq "table" && exists $attr->{border} && $attr->{border} =~ /(\d+)/)
{
$self->{html}{thick_border} = 1 if $1 > 1;
}
if ($tag =~ /^(?:a|body|div|input|form|td|layer|area|img)$/i) {
for (keys %$attr) {
if (/\b(?:$events)\b/io)
{
$self->{html}{html_event} = 1;
}
if (/\bon(?:contextmenu|load|resize|submit|unload)\b/i &&
$attr->{$_})
{
$self->{html}{html_event_unsafe} = 1;
}
}
}
if ($tag eq "font" && exists $attr->{size}) {
my $size = $attr->{size};
$self->{html}{tiny_font} = 1 if (($size =~ /^\s*(\d+)/ && $1 < 1) ||
($size =~ /\-(\d+)/ && $1 >= 3));
$self->{html}{big_font} = 1 if (($size =~ /^\s*(\d+)/ && $1 > 3) ||
($size =~ /\+(\d+)/ && $1 >= 1));
}
if ($tag eq "font" && exists $attr->{face}) {
if ($attr->{face} =~ /[A-Z]{3}/ && $attr->{face} !~ /M[ST][A-Z]|ITC/) {
$self->{html}{font_face_caps} = 1;
}
if ($attr->{face} !~ /^[a-z][a-z -]*[a-z](?:,\s*[a-z][a-z -]*[a-z])*$/i) {
$self->{html}{font_face_bad} = 1;
}
}
if (exists($attr->{style})) {
if ($attr->{style} =~ /font(?:-size)?:\s*(\d+(?:\.\d*)?|\.\d+)(p[tx])/i) {
$self->examine_text_style ($1, $2);
}
}
if ($tag eq "img") {
push @{ $self->{html}{img_src} }, $attr->{src} if exists $attr->{src};
}
if ($tag eq "img" && exists $attr->{width} && exists $attr->{height}) {
my $width = 0;
my $height = 0;
my $area = 0;
if ($attr->{width} =~ /^(\d+)(\%)?$/) {
$width = $1;
$width *= 8 if (defined $2 && $2 eq "%");
}
if ($attr->{height} =~ /^(\d+)(\%)?$/) {
$height = $1;
$height *= 6 if (defined $2 && $2 eq "%");
}
$width = 200 if $width <= 0;
$height = 200 if $height <= 0;
if ($width > 0 && $height > 0) {
$area = $width * $height;
$self->{html}{image_area} += $area;
}
if (exists $attr->{src} &&
$attr->{src} =~ /\.(?:pl|cgi|php|asp|jsp|cfm)\b/i)
{
$self->{html}{web_bugs} = 1;
}
}
if ($tag eq "form" && exists $attr->{action}) {
$self->{html}{form_action_mailto} = 1 if $attr->{action} =~ /mailto:/i
}
if ($tag =~ /^(?:object|embed)$/) {
$self->{html}{embeds} = 1;
}
if ($tag eq "a") {
$self->{html}{anchor_index}++;
$self->{html}{anchor}->[$self->{html}{anchor_index}] = "";
}
if ($tag eq "title") {
$self->{html}{title_index}++;
$self->{html}{title}->[$self->{html}{title_index}] = "";
}
if ($tag eq "meta" &&
exists $attr->{'http-equiv'} &&
exists $attr->{content} &&
$attr->{'http-equiv'} =~ /Content-Type/i &&
$attr->{content} =~ /\bcharset\s*=\s*["']?([^"']+)/i)
{
$self->{html}{charsets} .= exists $self->{html}{charsets} ? " $1" : $1;
}
}
sub examine_text_style {
my ($self, $size, $type) = @_;
$type = lc $type;
$self->{html}{tiny_font} = 1 if ($type eq "pt" && $size < 4);
$self->{html}{tiny_font} = 1 if ($type eq "pt" && $size < 4);
$self->{html}{big_font} = 1 if ($type eq "pt" && $size > 14);
$self->{html}{big_font} = 1 if ($type eq "px" && $size > 18);
}
sub display_text {
my ($self) = @_;
for my $type ('text', 'visible_text', 'invisible_text') {
my $text = $self->{"last_$type"};
$text =~ s/[ \t\n\r\f\x0b\xa0]+/ /g;
$text =~ s/^ //;
$text =~ s/ $//;
push @{$self->{"html_$type"}}, $text;
$self->{"last_$type"} = "";
}
}
sub html_text {
my ($self, $text) = @_;
# note: this comes back from HTML::Parser as UTF-8-tainted. Enforce byte
# mode by repacking the string in byte mode, to avoid 'Malformed UTF-8
$text = pack ("C0A*", $text);
if (exists $self->{html}{inside_script} && $self->{html}{inside_script} > 0)
{
if ($text =~ /\bon(?:blur|contextmenu|focus|load|resize|submit|unload)\b/i)
{
$self->{html}{html_event_unsafe} = 1;
}
if ($text =~ /\b(?:$events)\b/io) { $self->{html}{html_event} = 1; }
return;
}
if (exists $self->{html}{inside_style} && $self->{html}{inside_style} > 0) {
if ($text =~ /font(?:-size)?:\s*(\d+(?:\.\d*)?|\.\d+)(p[tx])/i) {
$self->examine_text_style ($1, $2);
}
return;
}
if (exists $self->{html}{inside_a} && $self->{html}{inside_a} > 0) {
$self->{html}{anchor}->[$self->{html}{anchor_index}] .= $text;
}
if (exists $self->{html}{inside_title} && $self->{html}{inside_title} > 0) {
$self->{html}{title}->[$self->{html}{title_index}] .= $text;
}
my $visible_for_bayes = 1;
if ($text =~ /[^ \t\n\r\f\x0b\xa0]/) {
$visible_for_bayes = $self->html_font_invisible($text);
$self->{html}{text_after_body} = 1 if $self->{html}{closed_body};
$self->{html}{text_after_html} = 1 if $self->{html}{closed_html};
}
if ($self->{last_text}) {
if ($text =~ /^[^\s\x21-\x2f\x3a-\x40\x5b-\x60\x7b-\x7e]/s &&
$self->{last_text} =~ /[^\s\x21-\x2f\x3a-\x40\x5b-\x60\x7b-\x7e]\z/s)
{
$self->{html}{obfuscation}++;
}
if ($self->{last_text} =~
/\b([^\s\x21-\x2f\x3a-\x40\x5b-\x60\x7b-\x7e]{1,7})\z/s)
{
my $start = length($1);
if ($text =~ /^([^\s\x21-\x2f\x3a-\x40\x5b-\x60\x7b-\x7e]{1,7})\b/s) {
my $backhair = $start . "_" . length($1);
$self->{html}{backhair}->{$backhair}++;
$self->{html}{backhair_count} = keys %{ $self->{html}{backhair} };
}
}
}
if ($visible_for_bayes) {
$self->{last_visible_text} .= $text;
}
else {
$self->{last_invisible_text} .= $text;
}
$self->{last_text} .= $text;
}
sub html_comment {
my ($self, $text) = @_;
push @{ $self->{html}{comment} }, $text;
if ($self->{html_last_tag} eq "div" &&
$text =~ /Converted from text\/plain format/)
{
$self->{html}{div_converted} = 1;
}
if (exists $self->{html}{inside_script} && $self->{html}{inside_script} > 0)
{
if ($text =~ /\b(?:$events)\b/io)
{
$self->{html}{html_event} = 1;
}
if ($text =~ /\bon(?:blur|contextmenu|focus|load|resize|submit|unload)\b/i)
{
$self->{html}{html_event_unsafe} = 1;
}
return;
}
if (exists $self->{html}{inside_style} && $self->{html}{inside_style} > 0) {
if ($text =~ /font(?:-size)?:\s*(\d+(?:\.\d*)?|\.\d+)(p[tx])/i) {
$self->examine_text_style ($1, $2);
}
}
if (exists $self->{html}{shouting} && $self->{html}{shouting} > 1) {
$self->{html}{comment_shouting} = 1;
}
}
sub html_declaration {
my ($self, $text) = @_;
if ($text =~ /^<!doctype/i) {
my $tag = "!doctype";
$self->{html}{elements}++;
$self->{html}{tags}++;
$self->{html}{"inside_$tag"} = 0;
}
}
1;
__END__