Merge branch 'jf.safelist'

Author: flavorjones

CHANGELOG.md

@@ -17,6 +17,17 @@
 * CSS hex values are no longer limited to lowercase hex. Previously uppercase hex were scrubbed. [#165] (Thanks, @asok!)
 
 
+### Deprecations / Name Changes
+
+The following method and constants are hereby deprecated, and will be completely removed in a future release:
+
+* Deprecate `Loofah::Helpers::ActionView.white_list_sanitizer`, please use `Loofah::Helpers::ActionView.safe_list_sanitizer` instead.
+* Deprecate `Loofah::Helpers::ActionView::WhiteListSanitizer`, please use `Loofah::Helpers::ActionView::SafeListSanitizer` instead.
+* Deprecate `Loofah::HTML5::WhiteList`, please use `Loofah::HTML5::SafeList` instead.
+
+Thanks to @JuanitoFatas for submitting these changes in #164 and for making the language used in Loofah more inclusive.
+
+
 ## 2.2.3 / 2018-10-30
 
 ### Security

Manifest.txt

@@ -17,7 +17,7 @@ lib/loofah/html/document.rb
 lib/loofah/html/document_fragment.rb
 lib/loofah/html5/libxml2_workarounds.rb
 lib/loofah/html5/scrub.rb
-lib/loofah/html5/whitelist.rb
+lib/loofah/html5/safelist.rb
 lib/loofah/instance_methods.rb
 lib/loofah/metahelpers.rb
 lib/loofah/scrubber.rb

README.md

@@ -19,7 +19,7 @@ documents and fragments. It's built on top of Nokogiri and libxml2, so
 it's fast and has a nice API.
 
 Loofah excels at HTML sanitization (XSS prevention). It includes some
-nice HTML sanitizers, which are based on HTML5lib's whitelist, so it
+nice HTML sanitizers, which are based on HTML5lib's safelist, so it
 most likely won't make your codes less secure. (These statements have
 not been evaluated by Netexperts.)
 
@@ -29,7 +29,7 @@ ActiveRecord extensions for sanitization are available in the
 
 ## Features
 
-* Easily write custom scrubbers for HTML/XML leveraging the sweetness of Nokogiri (and HTML5lib's whitelists).
+* Easily write custom scrubbers for HTML/XML leveraging the sweetness of Nokogiri (and HTML5lib's safelists).
 * Common HTML sanitizing tasks are built-in:
   * _Strip_ unsafe tags, leaving behind only the inner text.
   * _Prune_ unsafe tags and their subtrees, removing all traces that they ever existed.
@@ -221,7 +221,7 @@ Loofah.xml_document(File.read('plague.xml')).scrub!(bring_out_your_dead)
 === Built-In HTML Scrubbers
 
 Loofah comes with a set of sanitizing scrubbers that use HTML5lib's
-whitelist algorithm:
+safelist algorithm:
 
 ``` ruby
 doc.scrub!(:strip)       # replaces unknown/unsafe tags with their inner text

Rakefile

@@ -70,9 +70,9 @@ task :doc_upload_to_rubyforge => :docs do
   end
 end
 
-desc "generate whitelists from W3C specifications"
-task :generate_whitelists do
-  load "tasks/generate-whitelists"
+desc "generate safelists from W3C specifications"
+task :generate_safelists do
+  load "tasks/generate-safelists"
 end
 
 Concourse.new("loofah", fly_target: "ci") do |c|

lib/loofah.rb

@@ -5,7 +5,7 @@
 require 'loofah/metahelpers'
 require 'loofah/elements'
 
-require 'loofah/html5/whitelist'
+require 'loofah/html5/safelist'
 require 'loofah/html5/libxml2_workarounds'
 require 'loofah/html5/scrub'
 

lib/loofah/helpers.rb

@@ -46,8 +46,13 @@ def full_sanitizer
           @full_sanitizer ||= ::Loofah::Helpers::ActionView::FullSanitizer.new
         end
 
+        def safe_list_sanitizer
+          @safe_list_sanitizer ||= ::Loofah::Helpers::ActionView::SafeListSanitizer.new
+        end
+
         def white_list_sanitizer
-          @white_list_sanitizer ||= ::Loofah::Helpers::ActionView::WhiteListSanitizer.new
+          warn "warning: white_list_sanitizer is deprecated, please use safe_list_sanitizer instead."
+          safe_list_sanitizer
         end
       end
 
@@ -73,13 +78,13 @@ def sanitize html, *args
       #
       #  To use by default, call this in an application initializer:
       #
-      #    ActionView::Helpers::SanitizeHelper.white_list_sanitizer = ::Loofah::Helpers::ActionView::WhiteListSanitizer.new
+      #    ActionView::Helpers::SanitizeHelper.safe_list_sanitizer = ::Loofah::Helpers::ActionView::SafeListSanitizer.new
       #
       #  Or, to generally opt-in to Loofah's view sanitizers:
       #
       #    Loofah::Helpers::ActionView.set_as_default_sanitizer
       #
-      class WhiteListSanitizer
+      class SafeListSanitizer
         def sanitize html, *args
           Loofah::Helpers.sanitize html
         end
@@ -88,6 +93,11 @@ def sanitize_css style_string, *args
           Loofah::Helpers.sanitize_css style_string
         end
       end
+
+      WhiteListSanitizer = SafeListSanitizer
+      if Object.respond_to?(:deprecate_constant)
+        deprecate_constant :WhiteListSanitizer
+      end
     end
   end
 end

lib/loofah/html5/whitelist.rb lib/loofah/html5/safelist.rblib/loofah/html5/whitelist.rb renamed to lib/loofah/html5/safelist.rb

@@ -3,7 +3,7 @@
 module Loofah
   module HTML5 # :nodoc:
     #
-    #  HTML whitelist lifted from HTML5lib sanitizer code:
+    #  HTML safelist lifted from HTML5lib sanitizer code:
     #
     #    http://code.google.com/p/html5lib/
     #
@@ -44,7 +44,7 @@ module HTML5 # :nodoc:
     #   DEALINGS IN THE SOFTWARE.
     #
     # </html5_license>
-    module WhiteList
+    module SafeList
 
       ACCEPTABLE_ELEMENTS = Set.new([
                                       "a",
@@ -790,6 +790,11 @@ module WhiteList
       ALLOWED_ELEMENTS_WITH_LIBXML2 = ALLOWED_ELEMENTS + TAGS_SAFE_WITH_LIBXML2
     end
 
-    ::Loofah::MetaHelpers.add_downcased_set_members_to_all_set_constants ::Loofah::HTML5::WhiteList
+    WhiteList = SafeList
+    if Object.respond_to?(:deprecate_constant)
+      deprecate_constant :WhiteList
+    end
+
+    ::Loofah::MetaHelpers.add_downcased_set_members_to_all_set_constants ::Loofah::HTML5::SafeList
   end
 end

lib/loofah/html5/scrub.rb

@@ -12,7 +12,7 @@ module Scrub
       class << self
 
         def allowed_element? element_name
-          ::Loofah::HTML5::WhiteList::ALLOWED_ELEMENTS_WITH_LIBXML2.include? element_name
+          ::Loofah::HTML5::SafeList::ALLOWED_ELEMENTS_WITH_LIBXML2.include? element_name
         end
 
         #  alternative implementation of the html5lib attribute scrubbing algorithm
@@ -28,31 +28,31 @@ def scrub_attributes node
               next
             end
 
-            unless WhiteList::ALLOWED_ATTRIBUTES.include?(attr_name)
+            unless SafeList::ALLOWED_ATTRIBUTES.include?(attr_name)
               attr_node.remove
               next
             end
 
-            if WhiteList::ATTR_VAL_IS_URI.include?(attr_name)
+            if SafeList::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])
+              if val_unescaped =~ /^[a-z0-9][-+.a-z0-9]*:/ && ! SafeList::ALLOWED_PROTOCOLS.include?(val_unescaped.split(SafeList::PROTOCOL_SEPARATOR)[0])
                 attr_node.remove
                 next
-              elsif val_unescaped.split(WhiteList::PROTOCOL_SEPARATOR)[0] == 'data'
+              elsif val_unescaped.split(SafeList::PROTOCOL_SEPARATOR)[0] == 'data'
                 # permit only allowed data mediatypes
-                mediatype = val_unescaped.split(WhiteList::PROTOCOL_SEPARATOR)[1]
+                mediatype = val_unescaped.split(SafeList::PROTOCOL_SEPARATOR)[1]
                 mediatype, _ = mediatype.split(';')[0..1] if mediatype
-                if mediatype && !WhiteList::ALLOWED_URI_DATA_MEDIATYPES.include?(mediatype)
+                if mediatype && !SafeList::ALLOWED_URI_DATA_MEDIATYPES.include?(mediatype)
                   attr_node.remove
                   next
                 end
               end
             end
-            if WhiteList::SVG_ATTR_VAL_ALLOWS_REF.include?(attr_name)
+            if SafeList::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
+            if SafeList::SVG_ALLOW_LOCAL_HREF.include?(node.name) && attr_name == 'xlink:href' && attr_node.value =~ /^\s*[^#\s].*/m
               attr_node.remove
               next
             end
@@ -79,14 +79,14 @@ def scrub_css style
           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))
+              [:url, :bad_url].include?(child[:node]) || (child[:node] == :function && !SafeList::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)
+            if SafeList::ALLOWED_CSS_PROPERTIES.include?(name) || SafeList::ALLOWED_SVG_PROPERTIES.include?(name)
               sanitized_tree << node << CRASS_SEMICOLON
-            elsif WhiteList::SHORTHAND_CSS_PROPERTIES.include?(name.split('-').first)
+            elsif SafeList::SHORTHAND_CSS_PROPERTIES.include?(name.split('-').first)
               value = node[:value].split.map do |keyword|
-                if WhiteList::ALLOWED_CSS_KEYWORDS.include?(keyword) || keyword =~ CSS_KEYWORDISH
+                if SafeList::ALLOWED_CSS_KEYWORDS.include?(keyword) || keyword =~ CSS_KEYWORDISH
                   keyword
                 end
               end.compact

lib/loofah/scrubbers.rb

@@ -1,7 +1,7 @@
 module Loofah
   #
   #  Loofah provides some built-in scrubbers for sanitizing with
-  #  HTML5lib's whitelist and for accomplishing some common
+  #  HTML5lib's safelist and for accomplishing some common
   #  transformation tasks.
   #
   #

loofah.gemspec

@@ -9,10 +9,10 @@ Gem::Specification.new do |s|
   s.require_paths = ["lib".freeze]
   s.authors = ["Mike Dalessio".freeze, "Bryan Helmkamp".freeze]
   s.date = "2018-02-12"
-  s.description = "Loofah is a general library for manipulating and transforming HTML/XML\ndocuments and fragments. It's built on top of Nokogiri and libxml2, so\nit's fast and has a nice API.\n\nLoofah excels at HTML sanitization (XSS prevention). It includes some\nnice HTML sanitizers, which are based on HTML5lib's whitelist, so it\nmost likely won't make your codes less secure. (These statements have\nnot been evaluated by Netexperts.)\n\nActiveRecord extensions for sanitization are available in the\n[`loofah-activerecord` gem](https://github.com/flavorjones/loofah-activerecord).".freeze
+  s.description = "Loofah is a general library for manipulating and transforming HTML/XML\ndocuments and fragments. It's built on top of Nokogiri and libxml2, so\nit's fast and has a nice API.\n\nLoofah excels at HTML sanitization (XSS prevention). It includes some\nnice HTML sanitizers, which are based on HTML5lib's safelist, so it\nmost likely won't make your codes less secure. (These statements have\nnot been evaluated by Netexperts.)\n\nActiveRecord extensions for sanitization are available in the\n[`loofah-activerecord` gem](https://github.com/flavorjones/loofah-activerecord).".freeze
   s.email = ["mike.dalessio@gmail.com".freeze, "bryan@brynary.com".freeze]
   s.extra_rdoc_files = ["CHANGELOG.md".freeze, "MIT-LICENSE.txt".freeze, "Manifest.txt".freeze, "README.md".freeze, "CHANGELOG.md".freeze, "README.md".freeze]
-  s.files = [".gemtest".freeze, "CHANGELOG.md".freeze, "Gemfile".freeze, "MIT-LICENSE.txt".freeze, "Manifest.txt".freeze, "README.md".freeze, "Rakefile".freeze, "benchmark/benchmark.rb".freeze, "benchmark/fragment.html".freeze, "benchmark/helper.rb".freeze, "benchmark/www.slashdot.com.html".freeze, "lib/loofah.rb".freeze, "lib/loofah/elements.rb".freeze, "lib/loofah/helpers.rb".freeze, "lib/loofah/html/document.rb".freeze, "lib/loofah/html/document_fragment.rb".freeze, "lib/loofah/html5/scrub.rb".freeze, "lib/loofah/html5/whitelist.rb".freeze, "lib/loofah/instance_methods.rb".freeze, "lib/loofah/metahelpers.rb".freeze, "lib/loofah/scrubber.rb".freeze, "lib/loofah/scrubbers.rb".freeze, "lib/loofah/xml/document.rb".freeze, "lib/loofah/xml/document_fragment.rb".freeze, "test/assets/testdata_sanitizer_tests1.dat".freeze, "test/helper.rb".freeze, "test/html5/test_sanitizer.rb".freeze, "test/integration/test_ad_hoc.rb".freeze, "test/integration/test_helpers.rb".freeze, "test/integration/test_html.rb".freeze, "test/integration/test_scrubbers.rb".freeze, "test/integration/test_xml.rb".freeze, "test/unit/test_api.rb".freeze, "test/unit/test_encoding.rb".freeze, "test/unit/test_helpers.rb".freeze, "test/unit/test_scrubber.rb".freeze, "test/unit/test_scrubbers.rb".freeze]
+  s.files = [".gemtest".freeze, "CHANGELOG.md".freeze, "Gemfile".freeze, "MIT-LICENSE.txt".freeze, "Manifest.txt".freeze, "README.md".freeze, "Rakefile".freeze, "benchmark/benchmark.rb".freeze, "benchmark/fragment.html".freeze, "benchmark/helper.rb".freeze, "benchmark/www.slashdot.com.html".freeze, "lib/loofah.rb".freeze, "lib/loofah/elements.rb".freeze, "lib/loofah/helpers.rb".freeze, "lib/loofah/html/document.rb".freeze, "lib/loofah/html/document_fragment.rb".freeze, "lib/loofah/html5/scrub.rb".freeze, "lib/loofah/html5/safelist.rb".freeze, "lib/loofah/instance_methods.rb".freeze, "lib/loofah/metahelpers.rb".freeze, "lib/loofah/scrubber.rb".freeze, "lib/loofah/scrubbers.rb".freeze, "lib/loofah/xml/document.rb".freeze, "lib/loofah/xml/document_fragment.rb".freeze, "test/assets/testdata_sanitizer_tests1.dat".freeze, "test/helper.rb".freeze, "test/html5/test_sanitizer.rb".freeze, "test/integration/test_ad_hoc.rb".freeze, "test/integration/test_helpers.rb".freeze, "test/integration/test_html.rb".freeze, "test/integration/test_scrubbers.rb".freeze, "test/integration/test_xml.rb".freeze, "test/unit/test_api.rb".freeze, "test/unit/test_encoding.rb".freeze, "test/unit/test_helpers.rb".freeze, "test/unit/test_scrubber.rb".freeze, "test/unit/test_scrubbers.rb".freeze]
   s.homepage = "https://github.com/flavorjones/loofah".freeze
   s.licenses = ["MIT".freeze]
   s.rdoc_options = ["--main".freeze, "README.md".freeze]