Module: Loofah::HTML5::Scrub

Defined in:
lib/loofah/html5/scrub.rb

Constant Summary collapse

CONTROL_CHARACTERS =
/[`\u0000-\u0020\u007f\u0080-\u0101]/
CSS_KEYWORDISH =
/\A(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|-?\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)\z/
CRASS_SEMICOLON =
{:node => :semicolon, :raw => ";"}

Class Method Summary collapse

Class Method Details

.allowed_element?(element_name) ⇒ Boolean

Returns:

  • (Boolean)


16
17
18
# File 'lib/loofah/html5/scrub.rb', line 16

def allowed_element? element_name
  ::Loofah::HTML5::WhiteList::ALLOWED_ELEMENTS_WITH_LIBXML2.include? element_name
end

.scrub_attributes(node) ⇒ Object

alternative implementation of the html5lib attribute scrubbing algorithm



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
# File 'lib/loofah/html5/scrub.rb', line 21

def scrub_attributes node
  node.attribute_nodes.each do |attr_node|
    attr_name = if attr_node.namespace
                  "#{attr_node.namespace.prefix}:#{attr_node.node_name}"
                else
                  attr_node.node_name
                end

    if attr_name =~ /\Adata-[\w-]+\z/
      next
    end

    unless WhiteList::ALLOWED_ATTRIBUTES.include?(attr_name)
      attr_node.remove
      next
    end

    if WhiteList::ATTR_VAL_IS_URI.include?(attr_name)
      # this block lifted nearly verbatim from HTML5 sanitization
      val_unescaped = CGI.unescapeHTML(attr_node.value).gsub(CONTROL_CHARACTERS,'').downcase
      if val_unescaped =~ /^[a-z0-9][-+.a-z0-9]*:/ && ! WhiteList::ALLOWED_PROTOCOLS.include?(val_unescaped.split(WhiteList::PROTOCOL_SEPARATOR)[0])
        attr_node.remove
        next
      elsif val_unescaped.split(WhiteList::PROTOCOL_SEPARATOR)[0] == 'data'
        # permit only allowed data mediatypes
        mediatype = val_unescaped.split(WhiteList::PROTOCOL_SEPARATOR)[1]
        mediatype, _ = mediatype.split(';')[0..1] if mediatype
        if mediatype && !WhiteList::ALLOWED_URI_DATA_MEDIATYPES.include?(mediatype)
          attr_node.remove
          next
        end
      end
    end
    if WhiteList::SVG_ATTR_VAL_ALLOWS_REF.include?(attr_name)
      attr_node.value = attr_node.value.gsub(/url\s*\(\s*[^#\s][^)]+?\)/m, ' ') if attr_node.value
    end
    if WhiteList::SVG_ALLOW_LOCAL_HREF.include?(node.name) && attr_name == 'xlink:href' && attr_node.value =~ /^\s*[^#\s].*/m
      attr_node.remove
      next
    end
  end

  scrub_css_attribute node

  node.attribute_nodes.each do |attr_node|
    node.remove_attribute(attr_node.name) if attr_node.value !~ /[^[:space:]]/
  end
end

.scrub_css(style) ⇒ Object



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
# File 'lib/loofah/html5/scrub.rb', line 75

def scrub_css style
  style_tree = Crass.parse_properties style
  sanitized_tree = []

  style_tree.each do |node|
    next unless node[:node] == :property
    next if node[:children].any? do |child|
      [:url, :bad_url].include?(child[:node]) || (child[:node] == :function && !WhiteList::ALLOWED_CSS_FUNCTIONS.include?(child[:name].downcase))
    end
    name = node[:name].downcase
    if WhiteList::ALLOWED_CSS_PROPERTIES.include?(name) || WhiteList::ALLOWED_SVG_PROPERTIES.include?(name)
      sanitized_tree << node << CRASS_SEMICOLON
    elsif WhiteList::SHORTHAND_CSS_PROPERTIES.include?(name.split('-').first)
      value = node[:value].split.map do |keyword|
        if WhiteList::ALLOWED_CSS_KEYWORDS.include?(keyword) || keyword =~ CSS_KEYWORDISH
          keyword
        end
      end.compact
      unless value.empty?
        propstring = sprintf "%s:%s", name, value.join(" ")
        sanitized_node = Crass.parse_properties(propstring).first
        sanitized_tree << sanitized_node << CRASS_SEMICOLON
      end
    end
  end

  Crass::Parser.stringify sanitized_tree
end

.scrub_css_attribute(node) ⇒ Object



70
71
72
73
# File 'lib/loofah/html5/scrub.rb', line 70

def scrub_css_attribute node
  style = node.attributes['style']
  style.value = scrub_css(style.value) if style
end