devcenter-parser 2.2.5 → 2.2.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b1ecce7a41e0f3665dce79c95b6936d1dd530ed1548055ebe602ede352583192
-  data.tar.gz: 06a10cc3bb0f7932b79b20bfc481a3408be0996f1e0b8a1ef65d60fe93757dc5
+  metadata.gz: dfd75f1b30669185f61feb1051ca91a23a19e6552b4a8f14c6ec60a57205f858
+  data.tar.gz: 13929cf26ab3771a28e7f887f0a70dd2e6bf79a922259284c5874da8bff65816
 SHA512:
-  metadata.gz: 6b12389bc38dd0bf4d1125e16d10040121b34f55f10065cb891f04b5f23eae1e5129328a31e5e4fb27a2f278f9f120125caf2e753e59c619aa56e5691659113c
-  data.tar.gz: 0e27a7fdc0f13a3d1a41d1ae8ddddbc38bb02fb7e7c6d26187f3a77e9994b7c4b7bd7787aa391f76998eae8e567542f93994d22cbadd83a8d74fcdf3644ddff6
+  metadata.gz: 699004a8938e09580e9f3a3d5f355d88dbea868b207992400d299e1ec073d29ebd3ccf2ff7fb3b42d00ea9da8aa5386d268c8b05a028ea50635f18afec04922b
+  data.tar.gz: 1c0a5f037d378b78315e1497cac388074aae7fa3c391b510768eb0ee683b35ac10aec7936bb0b212df15f275727cf4b265ef43eb48c2cc04b1b6b3c056f880f2

data/Gemfile.lock

@@ -1,27 +1,27 @@
 PATH
   remote: .
   specs:
-    devcenter-parser (2.2.5)
+    devcenter-parser (2.2.10)
       nokogiri (>= 1.7.1)
-      redcarpet (= 3.3.4)
-      sanitize (~> 4.6.3)
+      redcarpet (= 3.5.0)
+      sanitize (~> 5.2.1)
 
 GEM
   remote: http://rubygems.org/
   specs:
-    crass (1.0.4)
-    mini_portile2 (2.3.0)
+    crass (1.0.6)
+    mini_portile2 (2.4.0)
     minitest (5.10.1)
-    nokogiri (1.8.5)
-      mini_portile2 (~> 2.3.0)
-    nokogumbo (1.5.0)
-      nokogiri
+    nokogiri (1.10.10)
+      mini_portile2 (~> 2.4.0)
+    nokogumbo (2.0.2)
+      nokogiri (~> 1.8, >= 1.8.4)
     rake (12.0.0)
-    redcarpet (3.3.4)
-    sanitize (4.6.6)
+    redcarpet (3.5.0)
+    sanitize (5.2.1)
       crass (~> 1.0.2)
-      nokogiri (>= 1.4.4)
-      nokogumbo (~> 1.4)
+      nokogiri (>= 1.8.0)
+      nokogumbo (~> 2.0)
 
 PLATFORMS
   ruby
@@ -32,4 +32,4 @@ DEPENDENCIES
   rake
 
 BUNDLED WITH
-   1.16.4
+   1.17.2

data/devcenter-parser.gemspec

@@ -15,8 +15,8 @@ Gem::Specification.new do |gem|
   gem.require_paths = %w{ lib }
 
   gem.add_runtime_dependency 'nokogiri', '>= 1.7.1'
-  gem.add_runtime_dependency 'redcarpet', '3.3.4'
-  gem.add_runtime_dependency 'sanitize', '~>4.6.3'
+  gem.add_runtime_dependency 'redcarpet', '3.5.0'
+  gem.add_runtime_dependency 'sanitize', '~>5.2.1'
 
   gem.add_development_dependency 'minitest', '>2.0'
   gem.add_development_dependency 'rake'

data/lib/devcenter-parser.rb

@@ -10,14 +10,14 @@ module DevcenterParser
   class InvalidMarkdownError < Exception; end
   class InvalidRawHTMLError < Exception; end
 
-  def self.to_html(markdown)
-    sanitize to_unsanitized_html(markdown)
+  def self.to_html(markdown, options = {})
+    sanitize to_unsanitized_html(markdown, options)
   end
 
-  def self.to_unsanitized_html(markdown)
+  def self.to_unsanitized_html(markdown, options = {})
     markdown = normalize_markdown(markdown)
     doc = GitHubParser.parse(markdown)
-    doc_to_html(doc)
+    doc_to_html(doc, options)
   rescue InvalidRawHTMLError => e
     raise InvalidMarkdownError, e.message
   end
@@ -28,9 +28,9 @@ module DevcenterParser
 
   private
 
-  def self.doc_to_html(doc)
+  def self.doc_to_html(doc, options = {})
     HeaderIdGenerator.apply!(doc)
-    convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc)
+    convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc, options)
     html = doc.to_html(:encoding => 'utf-8')
     verify_raw_html(html)
     html
@@ -92,10 +92,15 @@ module DevcenterParser
     @@sanitize_config = config.merge({remove_contents: true, allow_comments: true})
   end
 
-  def self.convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc)
+  def self.convert_to_article_links_all_relative_links_with_missing_initial_slashes(doc, options = {})
+    link_prefix = options[:link_prefix] || '/articles'
     doc.css('a').each do |node|
-      unless node['href'].nil? || node['href'] =~ /\Ahttp|\A\/|\Amailto\:|\A#/
-        node['href'] = "/articles/#{node['href']}".gsub('/articles/articles/', '/articles/')
+      next if node['href'].nil? || node['href'] =~ /\Ahttp|\A\/|\Amailto\:|\A#/
+
+      if node['href'].start_with? 'categories/'
+        node['href'] = "/#{node['href']}"
+      else
+        node['href'] = "#{link_prefix}/#{node['href']}".gsub('/articles/articles/', '/articles/')
       end
     end
   end
@@ -124,7 +129,7 @@ module DevcenterParser
   end
 
   def self.iframe_has_invalid_src?(node)
-    node.attributes['src'].value !~ /\Ahttps:\/\/player.vimeo.com\//i && node.attributes['src'].value !~ /\Ahttps:\/\/www.youtube.com\/embed/i
+    node.attributes['src'].value !~ /https:\/\/player.vimeo.com(.+)(&|\?)dnt=true/i && node.attributes['src'].value !~ /\Ahttps:\/\/www\.youtube-nocookie\.com\/embed/i
   end
 
   def self.iframe?(node)

data/lib/devcenter-parser/github_parser.rb

@@ -34,7 +34,7 @@ module GitHubParser
 
   def self.parse(markdown)
     html = github_parser.render(markdown.to_s)
-    doc = Nokogiri::HTML::DocumentFragment.parse(html)
+    doc = Nokogiri::HTML5::DocumentFragment.parse(html)
     special_blocks(doc)
     doc
   end

data/lib/devcenter-parser/header_id_generator.rb

@@ -72,7 +72,13 @@ class HeaderIdGenerator
   end
 
   def add_default_ids
-    @nodes_ids.each{ |node, id| @nodes_ids[node] = subheader_id(node.content) }
+    @nodes_ids.each do |node, _|
+      if node['id'].to_s.empty?
+        @nodes_ids[node] = subheader_id(node.content)
+      else
+        @nodes_ids[node] = node['id']
+      end
+    end
   end
 
   def subheader_id(content)

data/lib/devcenter-parser/version.rb

@@ -1,3 +1,3 @@
 module DevcenterParser
-  VERSION = '2.2.5'.freeze
+  VERSION = '2.2.11'.freeze
 end

data/test/devcenter-parser_test.rb

@@ -18,6 +18,10 @@ describe 'DevcenterParser' do
       assert_parsing_unsanitized_result '<toolbelt />', '<p><toolbelt></toolbelt></p>'
     end
 
+    it 'keeps html entities' do
+      assert_parsing_unsanitized_result '<p>&nbsp;</p>', '<p>&nbsp;</p>'
+    end
+
   end
 
   describe '.to_html' do
@@ -26,6 +30,10 @@ describe 'DevcenterParser' do
       assert_parsing_result nil, ''
     end
 
+    it 'keeps html entities' do
+      assert_parsing_result '<p>&nbsp;</p>', '<p>&nbsp;</p>'
+    end
+
     it 'does not create <em>s inside words' do
       assert_parsing_result 'foo_bar_baz', '<p>foo_bar_baz</p>'
     end
@@ -42,11 +50,31 @@ describe 'DevcenterParser' do
       assert_parsing_result md, html
     end
 
-    it 'allows embedding vimeo videos' do
-      src = '<iframe src="https://player.vimeo.com/video/61044807?title=0&amp;byline=0&amp;portrait=0&amp;color=a086ee" width="50" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe>'
+    it 'allows embedding vimeo videos when their do-no-track param is set to true' do
+      src = '<iframe src="https://player.vimeo.com/video/143343818?api=1&amp;dnt=true&amp;title=foo" width="50" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe>'
+      assert_parsing_result src, src
+    end
+
+    it 'allows embedding youtube videos from its no-cookies domain' do
+      src = '<iframe width="560" height="315" src="https://www.youtube-nocookie.com/embed/123456ABCDEF" frameborder="0" allowfullscreen=""></iframe>'
       assert_parsing_result src, src
     end
 
+    it 'removes youtube videos embedded from the with-cookies domain' do
+      src = '<iframe width="560" height="315" src="https://www.youtube.com/embed/123456ABCDEF" frameborder="0" allowfullscreen=""></iframe>'
+      assert_parsing_result src, ''
+    end
+      
+    it 'does not allow embedding vimeo videos when their do-no-track param is set to something different than true' do
+      src = '<iframe src="https://player.vimeo.com/video/143343818?api=1&amp;dnt=foo&amp;title=foo" width="50" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe>'
+      assert_parsing_result src, ''
+    end
+
+    it 'does not allow embedding vimeo videos when their do-no-track param is not passed' do
+      src = '<iframe src="https://player.vimeo.com/video/143343818?api=1&&amp;title=foo" width="50" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe>'
+      assert_parsing_result src, ''
+    end
+
     it 'allows images' do
       src = '<p><img src="http://nav.heroku.com/images/logos/logo.png" alt="image"></p>'
       assert_parsing_result src, src
@@ -234,7 +262,7 @@ And that's it.
 more callout</p>
 </div>
 
-<p class="devcenter-parser-special-block-separator" style="display:none"> </p>
+<p class="devcenter-parser-special-block-separator" style="display:none">&nbsp;</p>
 
 <blockquote>
 <p>normal</p>
@@ -263,7 +291,7 @@ more callout</p>
 <p>foo</p>
 </div>
 
-<p class="devcenter-parser-special-block-separator" style="display:none"> </p>
+<p class="devcenter-parser-special-block-separator" style="display:none">&nbsp;</p>
 
 <div class="note">
 <p>bar</p>
@@ -282,14 +310,12 @@ more callout</p>
       MARKDOWN
 
       html = <<-HTML
-<table>
-<thead>
+<table><thead>
 <tr>
 <th>A</th>
 <th>B</th>
 </tr>
-</thead>
-<tbody>
+</thead><tbody>
 <tr>
 <td>1</td>
 <td>2</td>
@@ -298,8 +324,7 @@ more callout</p>
 <td>3</td>
 <td>4</td>
 </tr>
-</tbody>
-</table>
+</tbody></table>
       HTML
 
       assert_parsing_result md, html
@@ -336,13 +361,21 @@ HTML
     end
 
     it 'converts relative links with missing initial slashes to article links' do
-      ['foo', 'foo/bar', 'foo#bar', '123'].each do |href|
+      ['foo', 'foo/bar', 'foo#bar', '123', 'categories'].each do |href|
         md = "[link](#{href})"
         html = "<p><a href=\"/articles/#{href}\">link</a></p>"
         assert_parsing_result md, html
       end
     end
 
+    it 'ignores links with missing initial slashes IFF they start with `categories/`' do
+      ['categories/foo', 'categories/foo/bar', 'categories/foo#bar', 'categories/123'].each do |href|
+        md = "[link](#{href})"
+        html = "<p><a href=\"/#{href}\">link</a></p>"
+        assert_parsing_result md, html
+      end
+    end
+
     it 'converts "articles/foo relative links with missing initial slashes to article links' do
       md = '[link](articles/foo)'
       html = '<p><a href="/articles/foo">link</a></p>'
@@ -353,6 +386,14 @@ HTML
       assert_parsing_result md, html
     end
 
+    it 'adds a link prefix from options for relative dev center links' do
+      md = '[link](foo)'
+      expected = '<p><a href="/ja/articles/foo">link</a></p>'
+
+      result = DevcenterParser.to_html(md, { link_prefix: '/ja/articles' })
+      assert_equal expected.strip, result.strip, "Failed when parsing\n#{md}\n.\n\nExpected:\n#{expected}\n\nActual result:\n#{result}\n\n"
+    end
+
     it 'does not alter relative links with initial slashes nor absolute links nor anchor links to the same doc' do
       ['http://foo.com', 'https://foo.com', '/foo', '/foo/bar', '/foo#bar', '#foo', '/123', 'mailto:foo@foobar.com'].each do |href|
         md = "[link](#{href})"
@@ -380,7 +421,7 @@ HTML
 <p>foo</p>
 </blockquote>
 
-<p class="devcenter-parser-special-block-separator" style="display:none"> </p>
+<p class="devcenter-parser-special-block-separator" style="display:none">&nbsp;</p>
 
 <blockquote>
 <p>bar</p>

data/test/header_id_generator_test.rb

@@ -13,6 +13,12 @@ describe 'HeaderIdGeneratorTest' do
     assert_id result(html), 'h2', 'foo-bar-header-123'
   end
 
+  it 'does not replace existing ids' do
+    html = '<h2 id="foo">Foo Bar</h2><p>Content</p><h3>Baz</h3>'
+    assert_id result(html), 'h2', 'foo'
+    assert_id result(html), 'h3', 'baz'
+  end
+
   it 'generates ids replacing inner non-alphanum chars with dashes' do
     ['Foo Bar', 'Foo-Bar', 'Foo#bar', 'Foo##Bar', 'Foo##Bar', '-$Foo##Bar$-'].each do |title|
       html = "<h2>#{title}</h2>"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: devcenter-parser
 version: !ruby/object:Gem::Version
-  version: 2.2.5
+  version: 2.2.11
 platform: ruby
 authors:
 - Heroku
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2018-10-31 00:00:00.000000000 Z
+date: 2020-12-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -30,28 +30,28 @@ dependencies:
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 3.3.4
+        version: 3.5.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - '='
       - !ruby/object:Gem::Version
-        version: 3.3.4
+        version: 3.5.0
 - !ruby/object:Gem::Dependency
   name: sanitize
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 4.6.3
+        version: 5.2.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 4.6.3
+        version: 5.2.1
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -103,7 +103,7 @@ files:
 homepage: https://devcenter.heroku.com
 licenses: []
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -118,9 +118,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.7
-signing_key: 
+rubygems_version: 3.1.4
+signing_key:
 specification_version: 4
 summary: Parser for Heroku Dev Center's content
 test_files: