Class: Sanitize
- Inherits:
-
Object
- Object
- Sanitize
- Defined in:
- lib/sanitize/config.rb,
lib/sanitize.rb,
lib/sanitize/version.rb,
lib/sanitize/config/basic.rb,
lib/sanitize/config/relaxed.rb,
lib/sanitize/config/restricted.rb
Overview
– Copyright © 2009 Ryan Grove <[email protected]>
Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the ‘Software’), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED ‘AS IS’, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. ++
Defined Under Namespace
Modules: Config
Constant Summary collapse
- REGEX_PROTOCOL =
Matches an attribute value that could be treated by a browser as a URL with a protocol prefix, such as “http:” or “javascript:”. Any string of zero or more characters followed by a colon is considered a match, even if the colon is encoded as an entity and even if it’s an incomplete entity (which IE6 and Opera will still parse).
/^([A-Za-z0-9\+\-\.\&\;\#\s]*?)(?:\:|�*58|�*3a)/i
- VERSION =
'1.1.1'
Class Method Summary collapse
-
.clean(html, config = {}) ⇒ Object
Returns a sanitized copy of html, using the settings in config if specified.
-
.clean!(html, config = {}) ⇒ Object
Performs Sanitize#clean in place, returning html, or
nil
if no changes were made.
Instance Method Summary collapse
-
#clean(html) ⇒ Object
Returns a sanitized copy of html.
-
#clean!(html) ⇒ Object
Performs clean in place, returning html, or
nil
if no changes were made. -
#initialize(config = {}) ⇒ Sanitize
constructor
Returns a new Sanitize object initialized with the settings in config.
Constructor Details
Class Method Details
Instance Method Details
#clean(html) ⇒ Object
Returns a sanitized copy of html.
50 51 52 53 |
# File 'lib/sanitize.rb', line 50 def clean(html) dupe = html.dup clean!(dupe) || dupe end |
#clean!(html) ⇒ Object
Performs clean in place, returning html, or nil
if no changes were made.
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 |
# File 'lib/sanitize.rb', line 57 def clean!(html) fragment = Nokogiri::HTML::DocumentFragment.parse(html) fragment.traverse do |node| if node.comment? node.unlink unless @config[:allow_comments] elsif node.element? name = node.name.to_s.downcase parent_name = node.parent ? node.parent.name.to_s.downcase : nil # Special handling of objects is necessary to limit by specific domains. if @config[:object_urls].any? && [name, parent_name].include?('object') unless @config[:object_config][:elements].include?(name) node.unlink next end attr_whitelist = @config[:object_config][:attributes][name] || [] # Remove non-whitelisted object interior tag attributes node.attribute_nodes.each do |attr| attr.unlink unless attr_whitelist.include?(attr.name.downcase) end # Remove non-whitelisted object URLs. object_url = if name == 'param' && node['name'] == 'movie' node['value'] elsif name == 'embed' node['src'] end if object_url && !@config[:object_urls].any?{|good| object_url.index(good) == 0} node.parent.unlink end next end # Delete any element that isn't in the whitelist. unless @config[:elements].include?(name) node.children.each { |n| node.add_previous_sibling(n) } node.unlink next end attr_whitelist = ((@config[:attributes][name] || []) + (@config[:attributes][:all] || [])).uniq if attr_whitelist.empty? # Delete all attributes from elements with no whitelisted # attributes. node.attribute_nodes.each { |attr| attr.remove } else # Delete any attribute that isn't in the whitelist for this element. node.attribute_nodes.each do |attr| attr.unlink unless attr_whitelist.include?(attr.name.downcase) end # Delete remaining attributes that use unacceptable protocols. if @config[:protocols].has_key?(name) protocol = @config[:protocols][name] node.attribute_nodes.each do |attr| attr_name = attr.name.downcase next false unless protocol.has_key?(attr_name) del = if attr.value.to_s.downcase =~ REGEX_PROTOCOL !protocol[attr_name].include?($1.downcase) else !protocol[attr_name].include?(:relative) end attr.unlink if del end end end # Add required attributes. if @config[:add_attributes].has_key?(name) @config[:add_attributes][name].each do |key, val| node[key] = val end end elsif node.cdata? node.replace(Nokogiri::XML::Text.new(node.text, node.document)) end end # Nokogiri 1.3.3 (and possibly earlier versions) always returns a US-ASCII # string no matter what we ask for. This will be fixed in 1.4.0, but for # now we have to hack around it to prevent errors. output_method_params = {:encoding => 'utf-8', :indent => 0} if @config[:output] == :xhtml output_method = fragment.method(:to_xhtml) output_method_params.merge!(:save_with => Nokogiri::XML::Node::SaveOptions::AS_XHTML) elsif @config[:output] == :html output_method = fragment.method(:to_html) else raise Error, "unsupported output format: #{@config[:output]}" end result = output_method.call(output_method_params) result.force_encoding('utf-8') if RUBY_VERSION >= '1.9' return result == html ? nil : html[0, html.length] = result end |