Merge pull request #48293 from flavorjones/flavorjones-support-html5-…

…sanitizer Update Action View to use HTML5 standards-compliant sanitizers
rails · May 30, 2023 · 54de0cb · 54de0cb
2 parents ae02cd6 + ce43ac6
commit 54de0cb
Show file tree

Hide file tree

Showing 10 changed files with 467 additions and 54 deletions.
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -52,7 +52,7 @@ PATH
       rack-session (>= 1.0.1)
       rack-test (>= 0.6.3)
       rails-dom-testing (~> 2.0)
-      rails-html-sanitizer (~> 1.0, >= 1.2.0)
+      rails-html-sanitizer (~> 1.6)
     actiontext (7.1.0.alpha)
       actionpack (= 7.1.0.alpha)
       activerecord (= 7.1.0.alpha)
@@ -65,7 +65,7 @@ PATH
       builder (~> 3.1)
       erubi (~> 1.11)
       rails-dom-testing (~> 2.0)
-      rails-html-sanitizer (~> 1.1, >= 1.2.0)
+      rails-html-sanitizer (~> 1.6)
     activejob (7.1.0.alpha)
       activesupport (= 7.1.0.alpha)
       globalid (>= 0.3.6)
@@ -292,9 +292,9 @@ GEM
     listen (3.8.0)
       rb-fsevent (~> 0.10, >= 0.10.3)
       rb-inotify (~> 0.9, >= 0.9.10)
-    loofah (2.19.1)
+    loofah (2.21.3)
       crass (~> 1.0.2)
-      nokogiri (>= 1.5.9)
+      nokogiri (>= 1.12.0)
     mail (2.8.0.1)
       mini_mime (>= 0.1.1)
       net-imap
@@ -311,7 +311,7 @@ GEM
     memoist (0.16.2)
     mini_magick (4.12.0)
     mini_mime (1.1.2)
-    mini_portile2 (2.8.1)
+    mini_portile2 (2.8.2)
     minitest (5.17.0)
     minitest-bisect (1.6.0)
       minitest-server (~> 1.0)
@@ -346,12 +346,12 @@ GEM
     net-smtp (0.3.3)
       net-protocol
     nio4r (2.5.8)
-    nokogiri (1.14.3)
-      mini_portile2 (~> 2.8.0)
+    nokogiri (1.15.2)
+      mini_portile2 (~> 2.8.2)
       racc (~> 1.4)
-    nokogiri (1.14.3-x86_64-darwin)
+    nokogiri (1.15.2-x86_64-darwin)
       racc (~> 1.4)
-    nokogiri (1.14.3-x86_64-linux)
+    nokogiri (1.15.2-x86_64-linux)
       racc (~> 1.4)
     os (1.1.4)
     parallel (1.22.1)
@@ -388,8 +388,9 @@ GEM
     rails-dom-testing (2.0.3)
       activesupport (>= 4.2.0)
       nokogiri (>= 1.6)
-    rails-html-sanitizer (1.4.4)
-      loofah (~> 2.19, >= 2.19.1)
+    rails-html-sanitizer (1.6.0)
+      loofah (~> 2.21)
+      nokogiri (~> 1.14)
     rainbow (3.1.1)
     rake (13.0.6)
     rb-fsevent (0.11.2)

diff --git a/actionpack/actionpack.gemspec b/actionpack/actionpack.gemspec
@@ -39,7 +39,7 @@ Gem::Specification.new do |s|
   s.add_dependency "rack",      ">= 2.2.4"
   s.add_dependency "rack-session", ">= 1.0.1"
   s.add_dependency "rack-test", ">= 0.6.3"
-  s.add_dependency "rails-html-sanitizer", "~> 1.0", ">= 1.2.0"
+  s.add_dependency "rails-html-sanitizer", "~> 1.6"
   s.add_dependency "rails-dom-testing", "~> 2.0"
   s.add_dependency "actionview", version
 

diff --git a/actionview/CHANGELOG.md b/actionview/CHANGELOG.md
@@ -1,3 +1,16 @@
+*   Add support for HTML5 standards-compliant sanitizers, and default to `Rails::HTML5::Sanitizer`
+    in the Rails 7.1 configuration if it is supported.
+
+    Action View's HTML sanitizers can be configured by setting
+    `config.action_view.sanitizer_vendor`. Supported values are `Rails::HTML4::Sanitizer` or
+    `Rails::HTML5::Sanitizer`.
+
+    The Rails 7.1 configuration will set this to `Rails::HTML5::Sanitizer` when it is supported, and
+    fall back to `Rails::HTML4::Sanitizer`. Previous configurations default to
+    `Rails::HTML4::Sanitizer`.
+
+    *Mike Dalessio*
+
 *   Add support for the HTML picture tag. It supports passing a String, an Array or a Block.
     Supports passing properties directly to the img tag via the `:image` key.
     Since the picture tag requires an img tag, the last element you provide will be used for the img tag.

diff --git a/actionview/actionview.gemspec b/actionview/actionview.gemspec
@@ -37,7 +37,7 @@ Gem::Specification.new do |s|
 
   s.add_dependency "builder",       "~> 3.1"
   s.add_dependency "erubi",         "~> 1.11"
-  s.add_dependency "rails-html-sanitizer", "~> 1.1", ">= 1.2.0"
+  s.add_dependency "rails-html-sanitizer", "~> 1.6"
   s.add_dependency "rails-dom-testing", "~> 2.0"
 
   s.add_development_dependency "actionpack",  version

diff --git a/actionview/lib/action_view/helpers/sanitize_helper.rb b/actionview/lib/action_view/helpers/sanitize_helper.rb
@@ -9,15 +9,17 @@ module Helpers # :nodoc:
     # The SanitizeHelper module provides a set of methods for scrubbing text of undesired HTML elements.
     # These helper methods extend Action View making them callable within your template files.
     module SanitizeHelper
+      mattr_accessor :sanitizer_vendor, default: Rails::HTML4::Sanitizer
+
       extend ActiveSupport::Concern
+
       # Sanitizes HTML input, stripping all but known-safe tags and attributes.
       #
-      # It also strips href/src attributes with unsafe protocols like
-      # <tt>javascript:</tt>, while also protecting against attempts to use Unicode,
-      # ASCII, and hex character references to work around these protocol filters.
-      # All special characters will be escaped.
+      # It also strips href/src attributes with unsafe protocols like <tt>javascript:</tt>, while
+      # also protecting against attempts to use Unicode, ASCII, and hex character references to work
+      # around these protocol filters.
       #
-      # The default sanitizer is Rails::Html::SafeListSanitizer. See {Rails HTML
+      # The default sanitizer is Rails::HTML5::SafeListSanitizer. See {Rails HTML
       # Sanitizers}[https://github.com/rails/rails-html-sanitizer] for more information.
       #
       # Custom sanitization rules can also be provided.
@@ -29,7 +31,7 @@ module SanitizeHelper
       #
       # * <tt>:tags</tt> - An array of allowed tags.
       # * <tt>:attributes</tt> - An array of allowed attributes.
-      # * <tt>:scrubber</tt> - A {Rails::Html scrubber}[https://github.com/rails/rails-html-sanitizer]
+      # * <tt>:scrubber</tt> - A {Rails::HTML scrubber}[https://github.com/rails/rails-html-sanitizer]
       #   or {Loofah::Scrubber}[https://github.com/flavorjones/loofah] object that
       #   defines custom sanitization rules. A custom scrubber takes precedence over
       #   custom tags and attributes.
@@ -44,9 +46,9 @@ module SanitizeHelper
       #
       #   <%= sanitize @comment.body, tags: %w(strong em a), attributes: %w(href) %>
       #
-      # Providing a custom Rails::Html scrubber:
+      # Providing a custom Rails::HTML scrubber:
       #
-      #   class CommentScrubber < Rails::Html::PermitScrubber
+      #   class CommentScrubber < Rails::HTML::PermitScrubber
       #     def initialize
       #       super
       #       self.tags = %w( form script comment blockquote )
@@ -61,7 +63,7 @@ module SanitizeHelper
       #   <%= sanitize @comment.body, scrubber: CommentScrubber.new %>
       #
       # See {Rails HTML Sanitizer}[https://github.com/rails/rails-html-sanitizer] for
-      # documentation about Rails::Html scrubbers.
+      # documentation about Rails::HTML scrubbers.
       #
       # Providing a custom Loofah::Scrubber:
       #
@@ -79,6 +81,22 @@ module SanitizeHelper
       #   # In config/application.rb
       #   config.action_view.sanitized_allowed_tags = ['strong', 'em', 'a']
       #   config.action_view.sanitized_allowed_attributes = ['href', 'title']
+      #
+      # The default, starting in \Rails 7.1, is to use an HTML5 parser for sanitization (if it is
+      # available, see NOTE below). If you wish to revert back to the previous HTML4 behavior, you
+      # can do so by setting the following in your application configuration:
+      #
+      #   # In config/application.rb
+      #   config.action_view.sanitizer_vendor = Rails::HTML4::Sanitizer
+      #
+      # Or, if you're upgrading from a previous version of \Rails and wish to opt into the HTML5
+      # behavior:
+      #
+      #   # In config/application.rb
+      #   config.action_view.sanitizer_vendor = Rails::HTML5::Sanitizer
+      #
+      # NOTE: Rails::HTML5::Sanitizer is not supported on JRuby, so on JRuby platforms \Rails will
+      # fall back to use Rails::HTML4::Sanitizer.
       def sanitize(html, options = {})
         self.class.safe_list_sanitizer.sanitize(html, options)&.html_safe
       end
@@ -126,7 +144,7 @@ module ClassMethods # :nodoc:
         attr_writer :full_sanitizer, :link_sanitizer, :safe_list_sanitizer
 
         def sanitizer_vendor
-          Rails::Html::Sanitizer
+          ActionView::Helpers::SanitizeHelper.sanitizer_vendor
         end
 
         def sanitized_allowed_tags
@@ -137,7 +155,7 @@ def sanitized_allowed_attributes
           sanitizer_vendor.safe_list_sanitizer.allowed_attributes
         end
 
-        # Gets the Rails::Html::FullSanitizer instance used by +strip_tags+. Replace with
+        # Gets the Rails::HTML::FullSanitizer instance used by +strip_tags+. Replace with
         # any object that responds to +sanitize+.
         #
         #   class Application < Rails::Application
@@ -147,7 +165,7 @@ def full_sanitizer
           @full_sanitizer ||= sanitizer_vendor.full_sanitizer.new
         end
 
-        # Gets the Rails::Html::LinkSanitizer instance used by +strip_links+.
+        # Gets the Rails::HTML::LinkSanitizer instance used by +strip_links+.
         # Replace with any object that responds to +sanitize+.
         #
         #   class Application < Rails::Application
@@ -157,7 +175,7 @@ def link_sanitizer
           @link_sanitizer ||= sanitizer_vendor.link_sanitizer.new
         end
 
-        # Gets the Rails::Html::SafeListSanitizer instance used by sanitize and +sanitize_css+.
+        # Gets the Rails::HTML::SafeListSanitizer instance used by sanitize and +sanitize_css+.
         # Replace with any object that responds to +sanitize+.
         #
         #   class Application < Rails::Application

diff --git a/actionview/lib/action_view/railtie.rb b/actionview/lib/action_view/railtie.rb
@@ -46,6 +46,12 @@ class Railtie < Rails::Engine # :nodoc:
       ActionView::Helpers::ContentExfiltrationPreventionHelper.prepend_content_exfiltration_prevention = prepend_content_exfiltration_prevention
     end
 
+    initializer "action_view.sanitizer_vendor" do |app|
+      if klass = app.config.action_view.delete(:sanitizer_vendor)
+        ActionView::Helpers::SanitizeHelper.sanitizer_vendor = klass
+      end
+    end
+
     config.after_initialize do |app|
       button_to_generates_button_tag = app.config.action_view.delete(:button_to_generates_button_tag)
       unless button_to_generates_button_tag.nil?