From 6637f9069c8bd819edc175cca13b667861aa3a0b Mon Sep 17 00:00:00 2001 From: David Heinemeier Hansson Date: Wed, 10 Oct 2007 17:35:10 +0000 Subject: Extracted sanitization methods from TextHelper to SanitizeHelper [DHH] Changed SanitizeHelper#sanitize to only allow the custom attributes and tags when specified in the call [DHH] git-svn-id: http://svn-commit.rubyonrails.org/rails/trunk@7825 5ecf4fe2-1ee6-0310-87b1-e25e094e27de --- actionpack/CHANGELOG | 4 + .../lib/action_view/helpers/sanitize_helper.rb | 325 +++++++++++++++++++++ actionpack/lib/action_view/helpers/text_helper.rb | 309 +------------------- actionpack/test/template/sanitize_helper_test.rb | 234 +++++++++++++++ actionpack/test/template/text_helper_test.rb | 222 -------------- 5 files changed, 564 insertions(+), 530 deletions(-) create mode 100644 actionpack/lib/action_view/helpers/sanitize_helper.rb create mode 100644 actionpack/test/template/sanitize_helper_test.rb (limited to 'actionpack') diff --git a/actionpack/CHANGELOG b/actionpack/CHANGELOG index 504eca371e..28c5556d81 100644 --- a/actionpack/CHANGELOG +++ b/actionpack/CHANGELOG @@ -1,5 +1,9 @@ *SVN* +* Changed SanitizeHelper#sanitize to only allow the custom attributes and tags when specified in the call [DHH] + +* Extracted sanitization methods from TextHelper to SanitizeHelper [DHH] + * rescue_from accepts :with => lambda { |exception| ... } or a normal block. #9827 [lifofifo] * Add :status to redirect_to allowing users to choose their own response code without manually setting headers. #8297 [codahale, chasgrundy] diff --git a/actionpack/lib/action_view/helpers/sanitize_helper.rb b/actionpack/lib/action_view/helpers/sanitize_helper.rb new file mode 100644 index 0000000000..e67abd9f67 --- /dev/null +++ b/actionpack/lib/action_view/helpers/sanitize_helper.rb @@ -0,0 +1,325 @@ +require 'action_view/helpers/tag_helper' +require 'html/document' + +module ActionView + module Helpers #:nodoc: + # The SanitizeHelper module provides a set of methods for scrubbing text of undesired HTML elements. + # These helper methods extend ActionView making them callable within your template files. + module SanitizeHelper + def self.included(base) + base.extend(ClassMethods) + end + + # This #sanitize helper will html encode all tags and strip all attributes that aren't specifically allowed. + # It also strips href/src tags with invalid protocols, like javascript: especially. It does its best to counter any + # tricks that hackers may use, like throwing in unicode/ascii/hex values to get past the javascript: filters. Check out + # the extensive test suite. + # + # <%= sanitize @article.body %> + # + # You can add or remove tags/attributes if you want to customize it a bit. See ActionView::Base for full docs on the + # available options. You can add tags/attributes for single uses of #sanitize by passing either the :attributes or :tags options: + # + # Normal Use + # + # <%= sanitize @article.body %> + # + # Custom Use (only the mentioned tags and attributes are allowed, nothing else) + # + # <%= sanitize @article.body, :tags => %w(table tr td), :attributes => %w(id class style) + # + # Add table tags to the default allowed tags + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_tags = 'table', 'tr', 'td' + # end + # + # Remove tags to the default allowed tags + # + # Rails::Initializer.run do |config| + # config.after_initialize do + # ActionView::Base.sanitized_allowed_tags.delete 'div' + # end + # end + # + # Change allowed default attributes + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_attributes = 'id', 'class', 'style' + # end + # + def sanitize(html, options = {}) + return html if html.blank? || !html.include?('<') + + attrs = options[:attributes] || sanitized_allowed_attributes + tags = options[:tags] || sanitized_allowed_tags + + returning [] do |new_text| + tokenizer = HTML::Tokenizer.new(html) + parent = [] + + while token = tokenizer.next + node = HTML::Node.parse(nil, 0, 0, token, false) + + new_text << case node + when HTML::Tag + if node.closing == :close + parent.shift + else + parent.unshift node.name + end + + node.attributes.keys.each do |attr_name| + value = node.attributes[attr_name].to_s + + if !attrs.include?(attr_name) || contains_bad_protocols?(attr_name, value) + node.attributes.delete(attr_name) + else + node.attributes[attr_name] = attr_name == 'style' ? sanitize_css(value) : CGI::escapeHTML(value) + end + end if node.attributes + + tags.include?(node.name) ? node : nil + else + sanitized_bad_tags.include?(parent.first) ? nil : node.to_s.gsub(/these tags!") + # # => Strip these tags! + # + # strip_tags("Bold no more! See more here...") + # # => Bold no more! See more here... + # + # strip_tags("
Welcome to my website!
") + # # => Welcome to my website! + def strip_tags(html) + return html if html.blank? || !html.index("<") + tokenizer = HTML::Tokenizer.new(html) + + text = returning [] do |text| + while token = tokenizer.next + node = HTML::Node.parse(nil, 0, 0, token, false) + # result is only the content of any Text nodes + text << node.to_s if node.class == HTML::Text + end + end + + # strip any comments, and if they have a newline at the end (ie. line with + # only a comment) strip that too + result = text.join.gsub(/[\n]?/m, "") + + # Recurse - handle all dirty nested tags + result == html ? result : strip_tags(result) + end + + # Strips all link tags from +text+ leaving just the link text. + # + # ==== Examples + # strip_links('Ruby on Rails') + # # => Ruby on Rails + # + # strip_links('Please e-mail me at me@email.com.') + # # => Please e-mail me at me@email.com. + # + # strip_links('Blog: Visit.') + # # => Blog: Visit + def strip_links(html) + if !html.blank? && (html.index("") + tokenizer = HTML::Tokenizer.new(html) + result = returning [] do |result| + while token = tokenizer.next + node = HTML::Node.parse(nil, 0, 0, token, false) + result << node.to_s unless node.is_a?(HTML::Tag) && ["a", "href"].include?(node.name) + end + end.join + result == html ? result : strip_links(result) # Recurse - handle all dirty nested links + else + html + end + end + + # A regular expression of the valid characters used to separate protocols like + # the ':' in 'http://foo.com' + @@sanitized_protocol_separator = /:|(�*58)|(p)|(%|%)3A/ + mattr_accessor :sanitized_protocol_separator, :instance_writer => false + + # Specifies a Set of HTML attributes that can have URIs. + @@sanitized_uri_attributes = Set.new(%w(href src cite action longdesc xlink:href lowsrc)) + mattr_reader :sanitized_uri_attributes + + # Specifies a Set of 'bad' tags that the #sanitize helper will remove completely, as opposed + # to just escaping harmless tags like <font> + @@sanitized_bad_tags = Set.new(%w(script)) + mattr_reader :sanitized_bad_tags + + # Specifies the default Set of tags that the #sanitize helper will allow unscathed. + @@sanitized_allowed_tags = Set.new(%w(strong em b i p code pre tt output samp kbd var sub + sup dfn cite big small address hr br div span h1 h2 h3 h4 h5 h6 ul ol li dt dd abbr + acronym a img blockquote del ins fieldset legend)) + mattr_reader :sanitized_allowed_tags + + # Specifies the default Set of html attributes that the #sanitize helper will leave + # in the allowed tag. + @@sanitized_allowed_attributes = Set.new(%w(href src width height alt cite datetime title class name xml:lang abbr)) + mattr_reader :sanitized_allowed_attributes + + # Specifies the default Set of acceptable css properties that #sanitize and #sanitize_css will accept. + @@sanitized_allowed_css_properties = Set.new(%w(azimuth background-color border-bottom-color border-collapse + border-color border-left-color border-right-color border-top-color clear color cursor direction display + elevation float font font-family font-size font-style font-variant font-weight height letter-spacing line-height + overflow pause pause-after pause-before pitch pitch-range richness speak speak-header speak-numeral speak-punctuation + speech-rate stress text-align text-decoration text-indent unicode-bidi vertical-align voice-family volume white-space + width)) + mattr_reader :sanitized_allowed_css_properties + + # Specifies the default Set of acceptable css keywords that #sanitize and #sanitize_css will accept. + @@sanitized_allowed_css_keywords = Set.new(%w(auto aqua black block blue bold both bottom brown center + collapse dashed dotted fuchsia gray green !important italic left lime maroon medium none navy normal + nowrap olive pointer purple red right solid silver teal top transparent underline white yellow)) + mattr_reader :sanitized_allowed_css_keywords + + # Specifies the default Set of allowed shorthand css properties for the #sanitize and #sanitize_css helpers. + @@sanitized_shorthand_css_properties = Set.new(%w(background border margin padding)) + mattr_reader :sanitized_shorthand_css_properties + + # Specifies the default Set of protocols that the #sanitize helper will leave in + # protocol attributes. + @@sanitized_allowed_protocols = Set.new(%w(ed2k ftp http https irc mailto news gopher nntp telnet webcal xmpp callto feed svn urn aim rsync tag ssh sftp rtsp afs)) + mattr_reader :sanitized_allowed_protocols + + module ClassMethods #:nodoc: + def self.extended(base) + class << base + # we want these to be class methods on ActionView::Base, they'll get mattr_readers for these below. + [:sanitized_protocol_separator, :sanitized_uri_attributes, :sanitized_bad_tags, :sanitized_allowed_tags, + :sanitized_allowed_attributes, :sanitized_allowed_css_properties, :sanitized_allowed_css_keywords, + :sanitized_shorthand_css_properties, :sanitized_allowed_protocols, :sanitized_protocol_separator=].each do |prop| + delegate prop, :to => SanitizeHelper + end + end + end + + # Adds valid HTML attributes that the #sanitize helper checks for URIs. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_uri_attributes = 'lowsrc', 'target' + # end + # + def sanitized_uri_attributes=(attributes) + Helpers::SanitizeHelper.sanitized_uri_attributes.merge(attributes) + end + + # Adds to the Set of 'bad' tags for the #sanitize helper. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_bad_tags = 'embed', 'object' + # end + # + def sanitized_bad_tags=(attributes) + Helpers::SanitizeHelper.sanitized_bad_tags.merge(attributes) + end + # Adds to the Set of allowed tags for the #sanitize helper. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_tags = 'table', 'tr', 'td' + # end + # + def sanitized_allowed_tags=(attributes) + Helpers::SanitizeHelper.sanitized_allowed_tags.merge(attributes) + end + + # Adds to the Set of allowed html attributes for the #sanitize helper. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_attributes = 'onclick', 'longdesc' + # end + # + def sanitized_allowed_attributes=(attributes) + Helpers::SanitizeHelper.sanitized_allowed_attributes.merge(attributes) + end + + # Adds to the Set of allowed css properties for the #sanitize and #sanitize_css heleprs. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_css_properties = 'expression' + # end + # + def sanitized_allowed_css_properties=(attributes) + Helpers::SanitizeHelper.sanitized_allowed_css_properties.merge(attributes) + end + + # Adds to the Set of allowed css keywords for the #sanitize and #sanitize_css helpers. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_css_keywords = 'expression' + # end + # + def sanitized_allowed_css_keywords=(attributes) + Helpers::SanitizeHelper.sanitized_allowed_css_keywords.merge(attributes) + end + + # Adds to the Set of allowed shorthand css properties for the #sanitize and #sanitize_css helpers. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_shorthand_css_properties = 'expression' + # end + # + def sanitized_shorthand_css_properties=(attributes) + Helpers::SanitizeHelper.sanitized_shorthand_css_properties.merge(attributes) + end + + # Adds to the Set of allowed protocols for the #sanitize helper. + # + # Rails::Initializer.run do |config| + # config.action_view.sanitized_allowed_protocols = 'ssh', 'feed' + # end + # + def sanitized_allowed_protocols=(attributes) + Helpers::SanitizeHelper.sanitized_allowed_protocols.merge(attributes) + end + end + + private + def contains_bad_protocols?(attr_name, value) + sanitized_uri_attributes.include?(attr_name) && + (value =~ /(^[^\/:]*):|(�*58)|(p)|(%|%)3A/ && !sanitized_allowed_protocols.include?(value.split(sanitized_protocol_separator).first)) + end + end + end +end diff --git a/actionpack/lib/action_view/helpers/text_helper.rb b/actionpack/lib/action_view/helpers/text_helper.rb index adb0e1fa1b..d0c8f155ea 100644 --- a/actionpack/lib/action_view/helpers/text_helper.rb +++ b/actionpack/lib/action_view/helpers/text_helper.rb @@ -7,11 +7,7 @@ module ActionView # and transforming strings, which can reduce the amount of inline Ruby code in # your views. These helper methods extend ActionView making them callable # within your template files. - module TextHelper - def self.included(base) - base.extend(ClassMethods) - end - + module TextHelper # The preferred method of outputting text in your views is to use the # <%= "text" %> eRuby syntax. The regular _puts_ and _print_ methods # do not operate as expected in an eRuby code block. If you absolutely must @@ -316,163 +312,6 @@ module ActionView when :urls then auto_link_urls(text, href_options, &block) end end - - # Strips all link tags from +text+ leaving just the link text. - # - # ==== Examples - # strip_links('Ruby on Rails') - # # => Ruby on Rails - # - # strip_links('Please e-mail me at me@email.com.') - # # => Please e-mail me at me@email.com. - # - # strip_links('Blog: Visit.') - # # => Blog: Visit - def strip_links(html) - if !html.blank? && (html.index("") - tokenizer = HTML::Tokenizer.new(html) - result = returning [] do |result| - while token = tokenizer.next - node = HTML::Node.parse(nil, 0, 0, token, false) - result << node.to_s unless node.is_a?(HTML::Tag) && ["a", "href"].include?(node.name) - end - end.join - result == html ? result : strip_links(result) # Recurse - handle all dirty nested links - else - html - end - end - - # This #sanitize helper will html encode all tags and strip all attributes that aren't specifically allowed. - # It also strips href/src tags with invalid protocols, like javascript: especially. It does its best to counter any - # tricks that hackers may use, like throwing in unicode/ascii/hex values to get past the javascript: filters. Check out - # the extensive test suite. - # - # <%= sanitize @article.body %> - # - # You can add or remove tags/attributes if you want to customize it a bit. See ActionView::Base for full docs on the - # available options. You can add tags/attributes for single uses of #sanitize by passing either the :attributes or :tags options: - # - # Normal Use - # - # <%= sanitize @article.body %> - # - # Custom Use - # - # <%= sanitize @article.body, :tags => %w(table tr td), :attributes => %w(id class style) - # - # Add table tags - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_tags = 'table', 'tr', 'td' - # end - # - # Remove tags - # - # Rails::Initializer.run do |config| - # config.after_initialize do - # ActionView::Base.sanitized_allowed_tags.delete 'div' - # end - # end - # - # Change allowed attributes - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_attributes = 'id', 'class', 'style' - # end - # - def sanitize(html, options = {}) - return html if html.blank? || !html.include?('<') - attrs = options.key?(:attributes) ? Set.new(options[:attributes]).merge(sanitized_allowed_attributes) : sanitized_allowed_attributes - tags = options.key?(:tags) ? Set.new(options[:tags] ).merge(sanitized_allowed_tags) : sanitized_allowed_tags - returning [] do |new_text| - tokenizer = HTML::Tokenizer.new(html) - parent = [] - while token = tokenizer.next - node = HTML::Node.parse(nil, 0, 0, token, false) - new_text << case node - when HTML::Tag - if node.closing == :close - parent.shift - else - parent.unshift node.name - end - node.attributes.keys.each do |attr_name| - value = node.attributes[attr_name].to_s - if !attrs.include?(attr_name) || contains_bad_protocols?(attr_name, value) - node.attributes.delete(attr_name) - else - node.attributes[attr_name] = attr_name == 'style' ? sanitize_css(value) : CGI::escapeHTML(value) - end - end if node.attributes - tags.include?(node.name) ? node : nil - else - sanitized_bad_tags.include?(parent.first) ? nil : node.to_s.gsub(/these tags!") - # # => Strip these tags! - # - # strip_tags("Bold no more! See more here...") - # # => Bold no more! See more here... - # - # strip_tags("
Welcome to my website!
") - # # => Welcome to my website! - def strip_tags(html) - return html if html.blank? || !html.index("<") - tokenizer = HTML::Tokenizer.new(html) - - text = returning [] do |text| - while token = tokenizer.next - node = HTML::Node.parse(nil, 0, 0, token, false) - # result is only the content of any Text nodes - text << node.to_s if node.class == HTML::Text - end - end - - # strip any comments, and if they have a newline at the end (ie. line with - # only a comment) strip that too - result = text.join.gsub(/[\n]?/m, "") - - # Recurse - handle all dirty nested tags - result == html ? result : strip_tags(result) - end # Creates a Cycle object whose _to_s_ method cycles through elements of an # array every time it is called. This can be used for example, to alternate @@ -569,147 +408,6 @@ module ActionView end end - # A regular expression of the valid characters used to separate protocols like - # the ':' in 'http://foo.com' - @@sanitized_protocol_separator = /:|(�*58)|(p)|(%|%)3A/ - mattr_accessor :sanitized_protocol_separator, :instance_writer => false - - # Specifies a Set of HTML attributes that can have URIs. - @@sanitized_uri_attributes = Set.new(%w(href src cite action longdesc xlink:href lowsrc)) - mattr_reader :sanitized_uri_attributes - - # Specifies a Set of 'bad' tags that the #sanitize helper will remove completely, as opposed - # to just escaping harmless tags like <font> - @@sanitized_bad_tags = Set.new(%w(script)) - mattr_reader :sanitized_bad_tags - - # Specifies the default Set of tags that the #sanitize helper will allow unscathed. - @@sanitized_allowed_tags = Set.new(%w(strong em b i p code pre tt output samp kbd var sub - sup dfn cite big small address hr br div span h1 h2 h3 h4 h5 h6 ul ol li dt dd abbr - acronym a img blockquote del ins fieldset legend)) - mattr_reader :sanitized_allowed_tags - - # Specifies the default Set of html attributes that the #sanitize helper will leave - # in the allowed tag. - @@sanitized_allowed_attributes = Set.new(%w(href src width height alt cite datetime title class name xml:lang abbr)) - mattr_reader :sanitized_allowed_attributes - - # Specifies the default Set of acceptable css properties that #sanitize and #sanitize_css will accept. - @@sanitized_allowed_css_properties = Set.new(%w(azimuth background-color border-bottom-color border-collapse - border-color border-left-color border-right-color border-top-color clear color cursor direction display - elevation float font font-family font-size font-style font-variant font-weight height letter-spacing line-height - overflow pause pause-after pause-before pitch pitch-range richness speak speak-header speak-numeral speak-punctuation - speech-rate stress text-align text-decoration text-indent unicode-bidi vertical-align voice-family volume white-space - width)) - mattr_reader :sanitized_allowed_css_properties - - # Specifies the default Set of acceptable css keywords that #sanitize and #sanitize_css will accept. - @@sanitized_allowed_css_keywords = Set.new(%w(auto aqua black block blue bold both bottom brown center - collapse dashed dotted fuchsia gray green !important italic left lime maroon medium none navy normal - nowrap olive pointer purple red right solid silver teal top transparent underline white yellow)) - mattr_reader :sanitized_allowed_css_keywords - - # Specifies the default Set of allowed shorthand css properties for the #sanitize and #sanitize_css helpers. - @@sanitized_shorthand_css_properties = Set.new(%w(background border margin padding)) - mattr_reader :sanitized_shorthand_css_properties - - # Specifies the default Set of protocols that the #sanitize helper will leave in - # protocol attributes. - @@sanitized_allowed_protocols = Set.new(%w(ed2k ftp http https irc mailto news gopher nntp telnet webcal xmpp callto feed svn urn aim rsync tag ssh sftp rtsp afs)) - mattr_reader :sanitized_allowed_protocols - - module ClassMethods #:nodoc: - def self.extended(base) - class << base - # we want these to be class methods on ActionView::Base, they'll get mattr_readers for these below. - [:sanitized_protocol_separator, :sanitized_uri_attributes, :sanitized_bad_tags, :sanitized_allowed_tags, - :sanitized_allowed_attributes, :sanitized_allowed_css_properties, :sanitized_allowed_css_keywords, - :sanitized_shorthand_css_properties, :sanitized_allowed_protocols, :sanitized_protocol_separator=].each do |prop| - delegate prop, :to => TextHelper - end - end - end - - # Adds valid HTML attributes that the #sanitize helper checks for URIs. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_uri_attributes = 'lowsrc', 'target' - # end - # - def sanitized_uri_attributes=(attributes) - Helpers::TextHelper.sanitized_uri_attributes.merge(attributes) - end - - # Adds to the Set of 'bad' tags for the #sanitize helper. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_bad_tags = 'embed', 'object' - # end - # - def sanitized_bad_tags=(attributes) - Helpers::TextHelper.sanitized_bad_tags.merge(attributes) - end - # Adds to the Set of allowed tags for the #sanitize helper. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_tags = 'table', 'tr', 'td' - # end - # - def sanitized_allowed_tags=(attributes) - Helpers::TextHelper.sanitized_allowed_tags.merge(attributes) - end - - # Adds to the Set of allowed html attributes for the #sanitize helper. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_attributes = 'onclick', 'longdesc' - # end - # - def sanitized_allowed_attributes=(attributes) - Helpers::TextHelper.sanitized_allowed_attributes.merge(attributes) - end - - # Adds to the Set of allowed css properties for the #sanitize and #sanitize_css heleprs. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_css_properties = 'expression' - # end - # - def sanitized_allowed_css_properties=(attributes) - Helpers::TextHelper.sanitized_allowed_css_properties.merge(attributes) - end - - # Adds to the Set of allowed css keywords for the #sanitize and #sanitize_css helpers. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_css_keywords = 'expression' - # end - # - def sanitized_allowed_css_keywords=(attributes) - Helpers::TextHelper.sanitized_allowed_css_keywords.merge(attributes) - end - - # Adds to the Set of allowed shorthand css properties for the #sanitize and #sanitize_css helpers. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_shorthand_css_properties = 'expression' - # end - # - def sanitized_shorthand_css_properties=(attributes) - Helpers::TextHelper.sanitized_shorthand_css_properties.merge(attributes) - end - - # Adds to the Set of allowed protocols for the #sanitize helper. - # - # Rails::Initializer.run do |config| - # config.action_view.sanitized_allowed_protocols = 'ssh', 'feed' - # end - # - def sanitized_allowed_protocols=(attributes) - Helpers::TextHelper.sanitized_allowed_protocols.merge(attributes) - end - end - private # The cycle helpers need to store the cycles in a place that is # guaranteed to be reset every time a page is rendered, so it @@ -776,11 +474,6 @@ module ActionView end end end - - def contains_bad_protocols?(attr_name, value) - sanitized_uri_attributes.include?(attr_name) && - (value =~ /(^[^\/:]*):|(�*58)|(p)|(%|%)3A/ && !sanitized_allowed_protocols.include?(value.split(sanitized_protocol_separator).first)) - end end end end diff --git a/actionpack/test/template/sanitize_helper_test.rb b/actionpack/test/template/sanitize_helper_test.rb new file mode 100644 index 0000000000..9f039e287f --- /dev/null +++ b/actionpack/test/template/sanitize_helper_test.rb @@ -0,0 +1,234 @@ +require "#{File.dirname(__FILE__)}/../abstract_unit" +require "#{File.dirname(__FILE__)}/../testing_sandbox" + +class SanitizeHelperTest < Test::Unit::TestCase + include ActionView::Helpers::SanitizeHelper + include ActionView::Helpers::TagHelper + include TestingSandbox + + def test_strip_links + assert_equal "Dont touch me", strip_links("Dont touch me") + assert_equal "on my mind\nall day long") + assert_equal "0wn3d", strip_links("0wn3d") + assert_equal "Magic", strip_links("Magic") + assert_equal "FrrFox", strip_links("FrrFox") + assert_equal "My mind\nall day long", strip_links("My mind\nall day long") + assert_equal "all day long", strip_links("<a href='hello'>all day long</a>") + end + + def test_sanitize_form + assert_sanitized "
", '' + end + + def test_sanitize_plaintext + raw = "<span>foo</span></plaintext>" + assert_sanitized raw, "<span>foo</span>" + end + + def test_sanitize_script + raw = "a b c<script language=\"Javascript\">blah blah blah</script>d e f" + assert_sanitized raw, "a b cd e f" + end + + def test_sanitize_js_handlers + raw = %{onthis="do that" <a href="#" onclick="hello" name="foo" onbogus="remove me">hello</a>} + assert_sanitized raw, %{onthis="do that" <a name="foo" href="#">hello</a>} + end + + def test_sanitize_javascript_href + raw = %{href="javascript:bang" <a href="javascript:bang" name="hello">foo</a>, <span href="javascript:bang">bar</span>} + assert_sanitized raw, %{href="javascript:bang" <a name="hello">foo</a>, <span>bar</span>} + end + + def test_sanitize_image_src + raw = %{src="javascript:bang" <img src="javascript:bang" width="5">foo</img>, <span src="javascript:bang">bar</span>} + assert_sanitized raw, %{src="javascript:bang" <img width="5">foo</img>, <span>bar</span>} + end + + ActionView::Helpers::SanitizeHelper.sanitized_allowed_tags.each do |tag_name| + define_method "test_should_allow_#{tag_name}_tag" do + assert_sanitized "start <#{tag_name} title=\"1\" onclick=\"foo\">foo <bad>bar</bad> baz</#{tag_name}> end", %(start <#{tag_name} title="1">foo bar baz</#{tag_name}> end) + end + end + + def test_should_allow_anchors + assert_sanitized %(<a href="foo" onclick="bar"><script>baz</script></a>), %(<a href="foo"></a>) + end + + # RFC 3986, sec 4.2 + def test_allow_colons_in_path_component + assert_sanitized("<a href=\"./this:that\">foo</a>") + end + + %w(src width height alt).each do |img_attr| + define_method "test_should_allow_image_#{img_attr}_attribute" do + assert_sanitized %(<img #{img_attr}="foo" onclick="bar" />), %(<img #{img_attr}="foo" />) + end + end + + def test_should_handle_non_html + assert_sanitized 'abc' + end + + def test_should_handle_blank_text + assert_sanitized nil + assert_sanitized '' + end + + def test_should_allow_custom_tags + text = "<u>foo</u>" + assert_equal(text, sanitize(text, :tags => %w(u))) + end + + def test_should_allow_only_custom_tags + text = "<u>foo</u> with <i>bar</i>" + assert_equal("<u>foo</u> with bar", sanitize(text, :tags => %w(u))) + end + + def test_should_allow_custom_tags_with_attributes + text = %(<fieldset foo="bar">foo</fieldset>) + assert_equal(text, sanitize(text, :attributes => ['foo'])) + end + + [%w(img src), %w(a href)].each do |(tag, attr)| + define_method "test_should_strip_#{attr}_attribute_in_#{tag}_with_bad_protocols" do + assert_sanitized %(<#{tag} #{attr}="javascript:bang" title="1">boo</#{tag}>), %(<#{tag} title="1">boo</#{tag}>) + end + end + + def test_should_flag_bad_protocols + %w(about chrome data disk hcp help javascript livescript lynxcgi lynxexec ms-help ms-its mhtml mocha opera res resource shell vbscript view-source vnd.ms.radio wysiwyg).each do |proto| + assert contains_bad_protocols?('src', "#{proto}://bad") + end + end + + def test_should_accept_good_protocols + sanitized_allowed_protocols.each do |proto| + assert !contains_bad_protocols?('src', "#{proto}://good") + end + end + + def test_should_reject_hex_codes_in_protocol + assert contains_bad_protocols?('src', "%6A%61%76%61%73%63%72%69%70%74%3A%61%6C%65%72%74%28%22%58%53%53%22%29") + assert_sanitized %(<a href="&#37;6A&#37;61&#37;76&#37;61&#37;73&#37;63&#37;72&#37;69&#37;70&#37;74&#37;3A&#37;61&#37;6C&#37;65&#37;72&#37;74&#37;28&#37;22&#37;58&#37;53&#37;53&#37;22&#37;29">1</a>), "<a>1</a>" + end + + def test_should_block_script_tag + assert_sanitized %(<SCRIPT\nSRC=http://ha.ckers.org/xss.js></SCRIPT>), "" + end + + [%(<IMG SRC="javascript:alert('XSS');">), + %(<IMG SRC=javascript:alert('XSS')>), + %(<IMG SRC=JaVaScRiPt:alert('XSS')>), + %(<IMG """><SCRIPT>alert("XSS")</SCRIPT>">), + %(<IMG SRC=javascript:alert(&quot;XSS&quot;)>), + %(<IMG SRC=javascript:alert(String.fromCharCode(88,83,83))>), + %(<IMG SRC=&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;&#108;&#101;&#114;&#116;&#40;&#39;&#88;&#83;&#83;&#39;&#41;>), + %(<IMG SRC=&#0000106&#0000097&#0000118&#0000097&#0000115&#0000099&#0000114&#0000105&#0000112&#0000116&#0000058&#0000097&#0000108&#0000101&#0000114&#0000116&#0000040&#0000039&#0000088&#0000083&#0000083&#0000039&#0000041>), + %(<IMG SRC=&#x6A&#x61&#x76&#x61&#x73&#x63&#x72&#x69&#x70&#x74&#x3A&#x61&#x6C&#x65&#x72&#x74&#x28&#x27&#x58&#x53&#x53&#x27&#x29>), + %(<IMG SRC="jav\tascript:alert('XSS');">), + %(<IMG SRC="jav&#x09;ascript:alert('XSS');">), + %(<IMG SRC="jav&#x0A;ascript:alert('XSS');">), + %(<IMG SRC="jav&#x0D;ascript:alert('XSS');">), + %(<IMG SRC=" &#14; javascript:alert('XSS');">), + %(<IMG SRC=`javascript:alert("RSnake says, 'XSS'")`>)].each_with_index do |img_hack, i| + define_method "test_should_not_fall_for_xss_image_hack_#{i+1}" do + assert_sanitized img_hack, "<img>" + end + end + + def test_should_sanitize_tag_broken_up_by_null + assert_sanitized %(<SCR\0IPT>alert(\"XSS\")</SCR\0IPT>), "alert(\"XSS\")" + end + + def test_should_sanitize_invalid_script_tag + assert_sanitized %(<SCRIPT/XSS SRC="http://ha.ckers.org/xss.js"></SCRIPT>), "" + end + + def test_should_sanitize_script_tag_with_multiple_open_brackets + assert_sanitized %(<<SCRIPT>alert("XSS");//<</SCRIPT>), "&lt;" + assert_sanitized %(<iframe src=http://ha.ckers.org/scriptlet.html\n<a), %(&lt;a) + end + + def test_should_sanitize_unclosed_script + assert_sanitized %(<SCRIPT SRC=http://ha.ckers.org/xss.js?<B>), "<b>" + end + + def test_should_sanitize_half_open_scripts + assert_sanitized %(<IMG SRC="javascript:alert('XSS')"), "<img>" + end + + def test_should_not_fall_for_ridiculous_hack + img_hack = %(<IMG\nSRC\n=\n"\nj\na\nv\na\ns\nc\nr\ni\np\nt\n:\na\nl\ne\nr\nt\n(\n'\nX\nS\nS\n'\n)\n"\n>) + assert_sanitized img_hack, "<img>" + end + + def test_should_sanitize_attributes + assert_sanitized %(<SPAN title="'><script>alert()</script>">blah</SPAN>), %(<span title="'&gt;&lt;script&gt;alert()&lt;/script&gt;">blah</span>) + end + + def test_should_sanitize_illegal_style_properties + raw = %(display:block; position:absolute; left:0; top:0; width:100%; height:100%; z-index:1; background-color:black; background-image:url(http://www.ragingplatypus.com/i/cam-full.jpg); background-x:center; background-y:center; background-repeat:repeat;) + expected = %(display: block; width: 100%; height: 100%; background-color: black; background-image: ; background-x: center; background-y: center;) + assert_equal expected, sanitize_css(raw) + end + + def test_should_sanitize_xul_style_attributes + raw = %(-moz-binding:url('http://ha.ckers.org/xssmoz.xml#xss')) + assert_equal '', sanitize_css(raw) + end + + def test_should_sanitize_invalid_tag_names + assert_sanitized(%(a b c<script/XSS src="http://ha.ckers.org/xss.js"></script>d e f), "a b cd e f") + end + + def test_should_sanitize_non_alpha_and_non_digit_characters_in_tags + assert_sanitized('<a onclick!#$%&()*~+-_.,:;?@[/|\]^`=alert("XSS")>foo</a>', "<a>foo</a>") + end + + def test_should_sanitize_invalid_tag_names_in_single_tags + assert_sanitized('<img/src="http://ha.ckers.org/xss.js"/>', "<img />") + end + + def test_should_sanitize_img_dynsrc_lowsrc + assert_sanitized(%(<img lowsrc="javascript:alert('XSS')" />), "<img />") + end + + def test_should_sanitize_div_background_image_unicode_encoded + raw = %(background-image:\0075\0072\006C\0028'\006a\0061\0076\0061\0073\0063\0072\0069\0070\0074\003a\0061\006c\0065\0072\0074\0028.1027\0058.1053\0053\0027\0029'\0029) + assert_equal '', sanitize_css(raw) + end + + def test_should_sanitize_div_style_expression + raw = %(width: expression(alert('XSS'));) + assert_equal '', sanitize_css(raw) + end + + def test_should_sanitize_style_attribute + raw = %(<div style="display:block; background:url(http://rubyonrails.com); background-image: url(rubyonrails)">foo</div>) + assert_equal %(<div style="display: block; background: ; background-image: ;">foo</div>), sanitize(raw, :attributes => 'style') + end + + def test_should_sanitize_img_vbscript + assert_sanitized %(<img src='vbscript:msgbox("XSS")' />), '<img />' + end + + def test_strip_tags + assert_equal("<<<bad html", strip_tags("<<<bad html")) + assert_equal("<<", strip_tags("<<<bad html>")) + assert_equal("Dont touch me", strip_tags("Dont touch me")) + assert_equal("This is a test.", strip_tags("<p>This <u>is<u> a <a href='test.html'><strong>test</strong></a>.</p>")) + assert_equal("Weirdos", strip_tags("Wei<<a>a onclick='alert(document.cookie);'</a>/>rdos")) + assert_equal("This is a test.", strip_tags("This is a test.")) + assert_equal( + %{This is a test.\n\n\nIt no longer contains any HTML.\n}, strip_tags( + %{<title>This is <b>a <a href="" target="_blank">test</a></b>.</title>\n\n<!-- it has a comment -->\n\n<p>It no <b>longer <strong>contains <em>any <strike>HTML</strike></em>.</strong></b></p>\n})) + assert_equal "This has a here.", strip_tags("This has a <!-- comment --> here.") + [nil, '', ' '].each { |blank| assert_equal blank, strip_tags(blank) } + end + + def assert_sanitized(text, expected = nil) + assert_equal((expected || text), sanitize(text)) + end +end \ No newline at end of file diff --git a/actionpack/test/template/text_helper_test.rb b/actionpack/test/template/text_helper_test.rb index 7520e49779..92d6bc3ae2 100644 --- a/actionpack/test/template/text_helper_test.rb +++ b/actionpack/test/template/text_helper_test.rb @@ -46,17 +46,6 @@ class TextHelperTest < Test::Unit::TestCase end end - def test_strip_links - assert_equal "Dont touch me", strip_links("Dont touch me") - assert_equal "<a<a", strip_links("<a<a") - assert_equal "on my mind\nall day long", strip_links("<a href='almost'>on my mind</a>\n<A href='almost'>all day long</A>") - assert_equal "0wn3d", strip_links("<a href='http://www.rubyonrails.com/'><a href='http://www.rubyonrails.com/' onlclick='steal()'>0wn3d</a></a>") - assert_equal "Magic", strip_links("<a href='http://www.rubyonrails.com/'>Mag<a href='http://www.ruby-lang.org/'>ic") - assert_equal "FrrFox", strip_links("<href onlclick='steal()'>FrrFox</a></href>") - assert_equal "My mind\nall <b>day</b> long", strip_links("<a href='almost'>My mind</a>\n<A href='almost'>all <b>day</b> long</A>") - assert_equal "all <b>day</b> long", strip_links("<<a>a href='hello'>all <b>day</b> long<</A>/a>") - end - def test_highlighter assert_equal( "This is a <strong class=\"highlight\">beautiful</strong> morning", @@ -261,199 +250,6 @@ class TextHelperTest < Test::Unit::TestCase assert_equal %(<p><a href="#{url}">#{url[0...7]}...</a><br /><a href="mailto:#{email}">#{email[0...7]}...</a><br /></p>), auto_link("<p>#{url}<br />#{email}<br /></p>") { |url| truncate(url, 10) } end - def test_sanitize_form - assert_sanitized "<form action=\"/foo/bar\" method=\"post\"><input></form>", '' - end - - def test_sanitize_plaintext - raw = "<plaintext><span>foo</span></plaintext>" - assert_sanitized raw, "<span>foo</span>" - end - - def test_sanitize_script - raw = "a b c<script language=\"Javascript\">blah blah blah</script>d e f" - assert_sanitized raw, "a b cd e f" - end - - def test_sanitize_js_handlers - raw = %{onthis="do that" <a href="#" onclick="hello" name="foo" onbogus="remove me">hello</a>} - assert_sanitized raw, %{onthis="do that" <a name="foo" href="#">hello</a>} - end - - def test_sanitize_javascript_href - raw = %{href="javascript:bang" <a href="javascript:bang" name="hello">foo</a>, <span href="javascript:bang">bar</span>} - assert_sanitized raw, %{href="javascript:bang" <a name="hello">foo</a>, <span>bar</span>} - end - - def test_sanitize_image_src - raw = %{src="javascript:bang" <img src="javascript:bang" width="5">foo</img>, <span src="javascript:bang">bar</span>} - assert_sanitized raw, %{src="javascript:bang" <img width="5">foo</img>, <span>bar</span>} - end - - ActionView::Helpers::TextHelper.sanitized_allowed_tags.each do |tag_name| - define_method "test_should_allow_#{tag_name}_tag" do - assert_sanitized "start <#{tag_name} title=\"1\" onclick=\"foo\">foo <bad>bar</bad> baz</#{tag_name}> end", %(start <#{tag_name} title="1">foo bar baz</#{tag_name}> end) - end - end - - def test_should_allow_anchors - assert_sanitized %(<a href="foo" onclick="bar"><script>baz</script></a>), %(<a href="foo"></a>) - end - - # RFC 3986, sec 4.2 - def test_allow_colons_in_path_component - assert_sanitized("<a href=\"./this:that\">foo</a>") - end - - %w(src width height alt).each do |img_attr| - define_method "test_should_allow_image_#{img_attr}_attribute" do - assert_sanitized %(<img #{img_attr}="foo" onclick="bar" />), %(<img #{img_attr}="foo" />) - end - end - - def test_should_handle_non_html - assert_sanitized 'abc' - end - - def test_should_handle_blank_text - assert_sanitized nil - assert_sanitized '' - end - - def test_should_allow_custom_tags - text = "<u>foo</u>" - assert_equal(text, sanitize(text, :tags => %w(u))) - end - - def test_should_allow_custom_tags_with_attributes - text = %(<fieldset foo="bar">foo</fieldset>) - assert_equal(text, sanitize(text, :attributes => ['foo'])) - end - - [%w(img src), %w(a href)].each do |(tag, attr)| - define_method "test_should_strip_#{attr}_attribute_in_#{tag}_with_bad_protocols" do - assert_sanitized %(<#{tag} #{attr}="javascript:bang" title="1">boo</#{tag}>), %(<#{tag} title="1">boo</#{tag}>) - end - end - - def test_should_flag_bad_protocols - %w(about chrome data disk hcp help javascript livescript lynxcgi lynxexec ms-help ms-its mhtml mocha opera res resource shell vbscript view-source vnd.ms.radio wysiwyg).each do |proto| - assert contains_bad_protocols?('src', "#{proto}://bad") - end - end - - def test_should_accept_good_protocols - sanitized_allowed_protocols.each do |proto| - assert !contains_bad_protocols?('src', "#{proto}://good") - end - end - - def test_should_reject_hex_codes_in_protocol - assert contains_bad_protocols?('src', "%6A%61%76%61%73%63%72%69%70%74%3A%61%6C%65%72%74%28%22%58%53%53%22%29") - assert_sanitized %(<a href="&#37;6A&#37;61&#37;76&#37;61&#37;73&#37;63&#37;72&#37;69&#37;70&#37;74&#37;3A&#37;61&#37;6C&#37;65&#37;72&#37;74&#37;28&#37;22&#37;58&#37;53&#37;53&#37;22&#37;29">1</a>), "<a>1</a>" - end - - def test_should_block_script_tag - assert_sanitized %(<SCRIPT\nSRC=http://ha.ckers.org/xss.js></SCRIPT>), "" - end - - [%(<IMG SRC="javascript:alert('XSS');">), - %(<IMG SRC=javascript:alert('XSS')>), - %(<IMG SRC=JaVaScRiPt:alert('XSS')>), - %(<IMG """><SCRIPT>alert("XSS")</SCRIPT>">), - %(<IMG SRC=javascript:alert(&quot;XSS&quot;)>), - %(<IMG SRC=javascript:alert(String.fromCharCode(88,83,83))>), - %(<IMG SRC=&#106;&#97;&#118;&#97;&#115;&#99;&#114;&#105;&#112;&#116;&#58;&#97;&#108;&#101;&#114;&#116;&#40;&#39;&#88;&#83;&#83;&#39;&#41;>), - %(<IMG SRC=&#0000106&#0000097&#0000118&#0000097&#0000115&#0000099&#0000114&#0000105&#0000112&#0000116&#0000058&#0000097&#0000108&#0000101&#0000114&#0000116&#0000040&#0000039&#0000088&#0000083&#0000083&#0000039&#0000041>), - %(<IMG SRC=&#x6A&#x61&#x76&#x61&#x73&#x63&#x72&#x69&#x70&#x74&#x3A&#x61&#x6C&#x65&#x72&#x74&#x28&#x27&#x58&#x53&#x53&#x27&#x29>), - %(<IMG SRC="jav\tascript:alert('XSS');">), - %(<IMG SRC="jav&#x09;ascript:alert('XSS');">), - %(<IMG SRC="jav&#x0A;ascript:alert('XSS');">), - %(<IMG SRC="jav&#x0D;ascript:alert('XSS');">), - %(<IMG SRC=" &#14; javascript:alert('XSS');">), - %(<IMG SRC=`javascript:alert("RSnake says, 'XSS'")`>)].each_with_index do |img_hack, i| - define_method "test_should_not_fall_for_xss_image_hack_#{i+1}" do - assert_sanitized img_hack, "<img>" - end - end - - def test_should_sanitize_tag_broken_up_by_null - assert_sanitized %(<SCR\0IPT>alert(\"XSS\")</SCR\0IPT>), "alert(\"XSS\")" - end - - def test_should_sanitize_invalid_script_tag - assert_sanitized %(<SCRIPT/XSS SRC="http://ha.ckers.org/xss.js"></SCRIPT>), "" - end - - def test_should_sanitize_script_tag_with_multiple_open_brackets - assert_sanitized %(<<SCRIPT>alert("XSS");//<</SCRIPT>), "&lt;" - assert_sanitized %(<iframe src=http://ha.ckers.org/scriptlet.html\n<a), %(&lt;a) - end - - def test_should_sanitize_unclosed_script - assert_sanitized %(<SCRIPT SRC=http://ha.ckers.org/xss.js?<B>), "<b>" - end - - def test_should_sanitize_half_open_scripts - assert_sanitized %(<IMG SRC="javascript:alert('XSS')"), "<img>" - end - - def test_should_not_fall_for_ridiculous_hack - img_hack = %(<IMG\nSRC\n=\n"\nj\na\nv\na\ns\nc\nr\ni\np\nt\n:\na\nl\ne\nr\nt\n(\n'\nX\nS\nS\n'\n)\n"\n>) - assert_sanitized img_hack, "<img>" - end - - def test_should_sanitize_attributes - assert_sanitized %(<SPAN title="'><script>alert()</script>">blah</SPAN>), %(<span title="'&gt;&lt;script&gt;alert()&lt;/script&gt;">blah</span>) - end - - def test_should_sanitize_illegal_style_properties - raw = %(display:block; position:absolute; left:0; top:0; width:100%; height:100%; z-index:1; background-color:black; background-image:url(http://www.ragingplatypus.com/i/cam-full.jpg); background-x:center; background-y:center; background-repeat:repeat;) - expected = %(display: block; width: 100%; height: 100%; background-color: black; background-image: ; background-x: center; background-y: center;) - assert_equal expected, sanitize_css(raw) - end - - def test_should_sanitize_xul_style_attributes - raw = %(-moz-binding:url('http://ha.ckers.org/xssmoz.xml#xss')) - assert_equal '', sanitize_css(raw) - end - - def test_should_sanitize_invalid_tag_names - assert_sanitized(%(a b c<script/XSS src="http://ha.ckers.org/xss.js"></script>d e f), "a b cd e f") - end - - def test_should_sanitize_non_alpha_and_non_digit_characters_in_tags - assert_sanitized('<a onclick!#$%&()*~+-_.,:;?@[/|\]^`=alert("XSS")>foo</a>', "<a>foo</a>") - end - - def test_should_sanitize_invalid_tag_names_in_single_tags - assert_sanitized('<img/src="http://ha.ckers.org/xss.js"/>', "<img />") - end - - def test_should_sanitize_img_dynsrc_lowsrc - assert_sanitized(%(<img lowsrc="javascript:alert('XSS')" />), "<img />") - end - - def test_should_sanitize_div_background_image_unicode_encoded - raw = %(background-image:\0075\0072\006C\0028'\006a\0061\0076\0061\0073\0063\0072\0069\0070\0074\003a\0061\006c\0065\0072\0074\0028.1027\0058.1053\0053\0027\0029'\0029) - assert_equal '', sanitize_css(raw) - end - - def test_should_sanitize_div_style_expression - raw = %(width: expression(alert('XSS'));) - assert_equal '', sanitize_css(raw) - end - - def test_should_sanitize_style_attribute - raw = %(<div style="display:block; background:url(http://rubyonrails.com); background-image: url(rubyonrails)">foo</div>) - assert_equal %(<div style="display: block; background: ; background-image: ;">foo</div>), sanitize(raw, :attributes => 'style') - end - - def test_should_sanitize_img_vbscript - assert_sanitized %(<img src='vbscript:msgbox("XSS")' />), '<img />' - end - - def test_cycle_class value = Cycle.new("one", 2, "3") assert_equal("one", value.to_s) @@ -536,22 +332,4 @@ class TextHelperTest < Test::Unit::TestCase assert_equal("red", cycle("red", "blue")) assert_equal(%w{Specialized Fuji Giant}, @cycles) end - - def test_strip_tags - assert_equal("<<<bad html", strip_tags("<<<bad html")) - assert_equal("<<", strip_tags("<<<bad html>")) - assert_equal("Dont touch me", strip_tags("Dont touch me")) - assert_equal("This is a test.", strip_tags("<p>This <u>is<u> a <a href='test.html'><strong>test</strong></a>.</p>")) - assert_equal("Weirdos", strip_tags("Wei<<a>a onclick='alert(document.cookie);'</a>/>rdos")) - assert_equal("This is a test.", strip_tags("This is a test.")) - assert_equal( - %{This is a test.\n\n\nIt no longer contains any HTML.\n}, strip_tags( - %{<title>This is <b>a <a href="" target="_blank">test</a></b>.</title>\n\n<!-- it has a comment -->\n\n<p>It no <b>longer <strong>contains <em>any <strike>HTML</strike></em>.</strong></b></p>\n})) - assert_equal "This has a here.", strip_tags("This has a <!-- comment --> here.") - [nil, '', ' '].each { |blank| assert_equal blank, strip_tags(blank) } - end - - def assert_sanitized(text, expected = nil) - assert_equal((expected || text), sanitize(text)) - end end -- cgit v1.2.3