Merge remote-tracking branch 'origin/master' into require-gemoji-2

CHANGELOG.md

@@ -3,7 +3,7 @@
 ## 1.11.0
 
   * Search for text nodes on DocumentFragments without root tags #146 Razer6
-  * Don't filter @mentions in <style> tags #145 jch
+  * Don't filter @mentions in `<style>` tags #145 jch
   * Prefer `http_url` in HttpsFilter. `base_url` still works. #142 bkeepers
   * Remove duplicate check in EmojiFilter #141 Razer6
 

README.md

@@ -1,4 +1,4 @@
-# HTML::Pipeline [![Build Status](https://secure.travis-ci.org/jch/html-pipeline.png)](http://travis-ci.org/jch/html-pipeline)
+# HTML::Pipeline [![Build Status](https://travis-ci.org/jch/html-pipeline.svg?branch=master)](https://travis-ci.org/jch/html-pipeline)
 
 GitHub HTML processing filters and utilities. This module includes a small
 framework for defining DOM based content filters and applying them to user
@@ -243,6 +243,8 @@ Here are some extensions people have built:
 * [html-pipeline-cite](https://github.com/lifted-studios/html-pipeline-cite)
 * [tilt-html-pipeline](https://github.com/bradgessler/tilt-html-pipeline)
 * [html-pipeline-wiki-link'](https://github.com/lifted-studios/html-pipeline-wiki-link) - WikiMedia-style wiki links
+* [task_list](https://github.com/github/task_list) - GitHub flavor Markdown Task List
+* [html-pipeline-rouge_filter](https://github.com/JuanitoFatas/html-pipeline-rouge_filter) - Syntax highlight with [Rouge](https://github.com/jneen/rouge/)
 
 ## Instrumenting
 

html-pipeline.gemspec

@@ -15,7 +15,7 @@ Gem::Specification.new do |gem|
   gem.test_files    = gem.files.grep(%r{^test})
   gem.require_paths = ["lib"]
 
-  gem.add_dependency "nokogiri", "~> 1.4"
+  gem.add_dependency "nokogiri", [">= 1.4", "<= 1.6.5"]
   gem.add_dependency "activesupport", ">= 2"
 
   gem.post_install_message = <<msg

lib/html/pipeline/@mention_filter.rb

@@ -125,11 +125,13 @@ def link_to_mention_info(text, info_url=nil)
 
       def link_to_mentioned_user(login)
         result[:mentioned_usernames] |= [login]
-        url = File.join(base_url, login)
-        "<a href='#{url}' class='user-mention'>" +
+
+        base_url << "/" unless base_url =~ /[\/~]\z/
+
+        "<a href='#{base_url << login}' class='user-mention'>" +
         "@#{login}" +
         "</a>"
       end
     end
   end
-end
+end

lib/html/pipeline/emoji_filter.rb

@@ -13,12 +13,16 @@ class Pipeline
     # Context:
     #   :asset_root (required) - base url to link to emoji sprite
     #   :asset_path (optional) - url path to link to emoji sprite. :file_name can be used as a placeholder for the sprite file name. If no asset_path is set "emoji/:file_name" is used.
+    #   :ignored_ancestor_tags (optional) - Tags to stop the emojification. Node has matched ancestor HTML tags will not be emojified. Default to pre, code, and tt tags. Extra tags please pass in the form of array, e.g., %w(blockquote summary).
     class EmojiFilter < Filter
+
+      DEFAULT_IGNORED_ANCESTOR_TAGS = %w(pre code tt).freeze
+
       def call
         doc.search('text()').each do |node|
           content = node.to_html
           next unless content.include?(':')
-          next if has_ancestor?(node, %w(pre code tt))
+          next if has_ancestor?(node, ignored_ancestor_tags)
           html = emoji_image_filter(content)
           next if html == content
           node.replace(html)
@@ -86,6 +90,17 @@ def self.emoji_names
       def emoji_filename(name)
         Emoji.find_by_alias(name).image_filename
       end
+
+      # Return ancestor tags to stop the emojification.
+      #
+      # @return [Array<String>] Ancestor tags.
+      def ignored_ancestor_tags
+        if context[:ignored_ancestor_tags]
+          DEFAULT_IGNORED_ANCESTOR_TAGS | context[:ignored_ancestor_tags]
+        else
+          DEFAULT_IGNORED_ANCESTOR_TAGS
+        end
+      end
     end
   end
 end

lib/html/pipeline/sanitization_filter.rb

@@ -45,7 +45,7 @@ class SanitizationFilter < Filter
         :elements => %w(
           h1 h2 h3 h4 h5 h6 h7 h8 br b i strong em a pre code img tt
           div ins del sup sub p ol ul table thead tbody tfoot blockquote
-          dl dt dd kbd q samp var hr ruby rt rp li tr td th s strike
+          dl dt dd kbd q samp var hr ruby rt rp li tr td th s strike summary details
         ),
         :remove_contents => ['script'],
         :attributes => {
@@ -57,13 +57,13 @@ class SanitizationFilter < Filter
                     'border', 'cellpadding', 'cellspacing', 'char',
                     'charoff', 'charset', 'checked', 'cite',
                     'clear', 'cols', 'colspan', 'color',
-                    'compact', 'coords', 'datetime', 'details', 'dir',
+                    'compact', 'coords', 'datetime', 'dir',
                     'disabled', 'enctype', 'for', 'frame',
                     'headers', 'height', 'hreflang',
                     'hspace', 'ismap', 'label', 'lang',
                     'longdesc', 'maxlength', 'media', 'method',
                     'multiple', 'name', 'nohref', 'noshade',
-                    'nowrap', 'prompt', 'readonly', 'rel', 'rev',
+                    'nowrap', 'open', 'prompt', 'readonly', 'rel', 'rev',
                     'rows', 'rowspan', 'rules', 'scope',
                     'selected', 'shape', 'size', 'span',
                     'start', 'summary', 'tabindex', 'target',

test/html/pipeline/emoji_filter_test.rb

@@ -48,4 +48,18 @@ def test_not_emojify_in_pre_tags
     doc = filter.call
     assert_equal body, doc.to_html
   end
+
+  def test_not_emojify_in_custom_single_tag_foo
+    body = "<foo>:shipit:</foo>"
+    filter = EmojiFilter.new(body, {:asset_root => 'https://foo.com', ignored_ancestor_tags: %w(foo)})
+    doc = filter.call
+    assert_equal body, doc.to_html
+  end
+
+  def test_not_emojify_in_custom_multiple_tags_foo_and_bar
+    body = "<bar>:shipit:</bar>"
+    filter = EmojiFilter.new(body, {:asset_root => 'https://foo.com', ignored_ancestor_tags: %w(foo bar)})
+    doc = filter.call
+    assert_equal body, doc.to_html
+  end
 end

test/html/pipeline/mention_filter_test.rb

@@ -72,6 +72,27 @@ def test_links_to_more_info_when_info_url_given
       filter(body, '/', 'https://github.com/blog/821').to_html
   end
 
+  def test_base_url_slash
+    body = "<p>Hi, @jch!</p>"
+    link = "<a href=\"/jch\" class=\"user-mention\">@jch</a>"
+    assert_equal "<p>Hi, #{link}!</p>",
+      filter(body, '/').to_html
+  end
+
+  def test_base_url_under_custom_route
+    body = "<p>Hi, @jch!</p>"
+    link = "<a href=\"/userprofile/jch\" class=\"user-mention\">@jch</a>"
+    assert_equal "<p>Hi, #{link}!</p>",
+      filter(body, '/userprofile').to_html
+  end
+
+  def test_base_url_slash_with_tilde
+    body = "<p>Hi, @jch!</p>"
+    link = "<a href=\"/~jch\" class=\"user-mention\">@jch</a>"
+    assert_equal "<p>Hi, #{link}!</p>",
+      filter(body, '/~').to_html
+  end
+
   MarkdownPipeline =
     HTML::Pipeline.new [
       HTML::Pipeline::MarkdownFilter,

test/html/pipeline/sanitization_filter_test.rb

@@ -127,4 +127,28 @@ def test_table_sections_are_not_removed
 </table>)
     assert_equal orig, SanitizationFilter.call(orig).to_s
   end
+
+  def test_summary_tag_are_not_removed
+    orig = %(<summary>Foo</summary>)
+    assert_equal orig, SanitizationFilter.call(orig).to_s
+  end
+
+  def test_details_tag_and_open_attribute_are_not_removed
+    orig = %(<details open>Foo</details>)
+    assert_equal orig, SanitizationFilter.call(orig).to_s
+  end
+
+  def test_nested_details_tag_are_not_removed
+    orig = <<-NESTED
+      <details>
+        <summary>Foo</summary>
+        <details>
+          Bar
+          <summary>Baz</summary>
+        </details>
+        Qux
+      </details>
+    NESTED
+    assert_equal orig, SanitizationFilter.call(orig).to_s
+  end
 end