motion-html-pipeline 0.1

data/spec/motion-html-pipeline/pipeline/disabled/markdown_filter_spec.rb

@@ -0,0 +1,112 @@
+# describe 'MotionHTMLPipeline::Pipeline::MarkdownFilterTest' do
+#   MarkdownFilter = MotionHTMLPipeline::Pipeline::MarkdownFilter
+#
+#   def setup
+#     @haiku =
+#       "Pointing at the moon\n" \
+#       "Reminded of simple things\n" \
+#       'Moments matter most'
+#     @links =
+#       'See http://example.org/ for more info'
+#     @code =
+#       "```\n" \
+#       'def hello()' \
+#       "  'world'" \
+#       'end' \
+#       '```'
+#   end
+#
+#   def test_fails_when_given_a_documentfragment
+#     body = '<p>heyo</p>'
+#     doc  = HTML::Pipeline.parse(body)
+#     assert_raises(TypeError) { MarkdownFilter.call(doc, {}) }
+#   end
+#
+#   def test_gfm_enabled_by_default
+#     doc = MarkdownFilter.to_document(@haiku, {})
+#     assert doc.is_a?(HTML::Pipeline::DocumentFragment)
+#     assert_equal 2, doc.search('br').size
+#   end
+#
+#   def test_disabling_gfm
+#     doc = MarkdownFilter.to_document(@haiku, gfm: false)
+#     assert doc.is_a?(HTML::Pipeline::DocumentFragment)
+#     assert_equal 0, doc.search('br').size
+#   end
+#
+#   def test_fenced_code_blocks
+#     doc = MarkdownFilter.to_document(@code)
+#     assert doc.is_a?(HTML::Pipeline::DocumentFragment)
+#     assert_equal 1, doc.search('pre').size
+#   end
+#
+#   def test_fenced_code_blocks_with_language
+#     doc = MarkdownFilter.to_document(@code.sub('```', '``` ruby'))
+#     assert doc.is_a?(HTML::Pipeline::DocumentFragment)
+#     assert_equal 1, doc.search('pre').size
+#     assert_equal 'ruby', doc.search('pre').first['lang']
+#   end
+#
+#   def test_standard_extensions
+#     iframe = "<iframe src='http://www.google.com'></iframe>"
+#     iframe_escaped = "&lt;iframe src='http://www.google.com'>&lt;/iframe>"
+#     doc = MarkdownFilter.new(iframe, unsafe: true).call
+#     assert_equal(doc, iframe_escaped)
+#   end
+#
+#   def test_changing_extensions
+#     iframe = "<iframe src='http://www.google.com'></iframe>"
+#     doc = MarkdownFilter.new(iframe, commonmarker_extensions: [], unsafe: true).call
+#     assert_equal(doc, iframe)
+#   end
+# end
+#
+# class GFMTest < Minitest::Test
+#   def gfm(text)
+#     MarkdownFilter.call(text, gfm: true, unsafe: true)
+#   end
+#
+#   def test_not_touch_single_underscores_inside_words
+#     assert_equal '<p>foo_bar</p>',
+#                  gfm('foo_bar')
+#   end
+#
+#   def test_not_touch_underscores_in_code_blocks
+#     assert_equal "<pre><code>foo_bar_baz\n</code></pre>",
+#                  gfm('    foo_bar_baz')
+#   end
+#
+#   def test_not_touch_underscores_in_pre_blocks
+#     assert_equal "<pre>\nfoo_bar_baz\n</pre>",
+#                  gfm("<pre>\nfoo_bar_baz\n</pre>")
+#   end
+#
+#   def test_not_touch_two_or_more_underscores_inside_words
+#     assert_equal '<p>foo_bar_baz</p>',
+#                  gfm('foo_bar_baz')
+#   end
+#
+#   def test_turn_newlines_into_br_tags_in_simple_cases
+#     assert_equal "<p>foo<br />\nbar</p>",
+#                  gfm("foo\nbar")
+#   end
+#
+#   def test_convert_newlines_in_all_groups
+#     assert_equal "<p>apple<br />\npear<br />\norange</p>\n" \
+#                  "<p>ruby<br />\npython<br />\nerlang</p>",
+#                  gfm("apple\npear\norange\n\nruby\npython\nerlang")
+#   end
+#
+#   def test_convert_newlines_in_even_long_groups
+#     assert_equal "<p>apple<br />\npear<br />\norange<br />\nbanana</p>\n" \
+#                  "<p>ruby<br />\npython<br />\nerlang</p>",
+#                  gfm("apple\npear\norange\nbanana\n\nruby\npython\nerlang")
+#   end
+#
+#   def test_not_convert_newlines_in_lists
+#     assert_equal "<h1>foo</h1>\n<h1>bar</h1>",
+#                  gfm("# foo\n# bar")
+#     assert_equal "<ul>\n<li>foo</li>\n<li>bar</li>\n</ul>",
+#                  gfm("* foo\n* bar")
+#   end
+# end

data/spec/motion-html-pipeline/pipeline/disabled/plain_text_input_filter_spec.rb

@@ -0,0 +1,20 @@
+# describe 'MotionHTMLPipeline::Pipeline::PlainTextInputFilterTest' do
+#   PlainTextInputFilter = MotionHTMLPipeline::Pipeline::PlainTextInputFilter
+#
+#   def test_fails_when_given_a_documentfragment
+#     body = '<p>heyo</p>'
+#     doc  = Nokogiri::HTML::DocumentFragment.parse(body)
+#     assert_raises(TypeError) { PlainTextInputFilter.call(doc, {}) }
+#   end
+#
+#   def test_wraps_input_in_a_div_element
+#     doc = PlainTextInputFilter.call('howdy pahtner', {})
+#     assert_equal '<div>howdy pahtner</div>', doc.to_s
+#   end
+#
+#   def test_html_escapes_plain_text_input
+#     doc = PlainTextInputFilter.call('See: <http://example.org>', {})
+#     assert_equal '<div>See: &lt;http://example.org&gt;</div>',
+#                  doc.to_s
+#   end
+# end

data/spec/motion-html-pipeline/pipeline/disabled/sanitization_filter_spec.rb

@@ -0,0 +1,164 @@
+# describe 'MotionHTMLPipeline::Pipeline::SanitizationFilterTest' do
+#   SanitizationFilter = MotionHTMLPipeline::Pipeline::SanitizationFilter
+#
+#   def test_removing_script_tags
+#     orig = %(<p><img src="http://github.com/img.png" /><script></script></p>)
+#     html = SanitizationFilter.call(orig).to_s
+#     refute_match /script/, html
+#   end
+#
+#   def test_removing_style_tags
+#     orig = %(<p><style>hey now</style></p>)
+#     html = SanitizationFilter.call(orig).to_s
+#     refute_match /style/, html
+#   end
+#
+#   def test_removing_style_attributes
+#     orig = %(<p style='font-size:1000%'>YO DAWG</p>)
+#     html = SanitizationFilter.call(orig).to_s
+#     refute_match /font-size/, html
+#     refute_match /style/, html
+#   end
+#
+#   def test_removing_script_event_handler_attributes
+#     orig = %(<a onclick='javascript:alert(0)'>YO DAWG</a>)
+#     html = SanitizationFilter.call(orig).to_s
+#     refute_match /javscript/, html
+#     refute_match /onclick/, html
+#   end
+#
+#   def test_sanitizes_li_elements_not_contained_in_ul_or_ol
+#     stuff = "a\n<li>b</li>\nc"
+#     html  = SanitizationFilter.call(stuff).to_s
+#     assert_equal "a\nb\nc", html
+#   end
+#
+#   def test_does_not_sanitize_li_elements_contained_in_ul_or_ol
+#     stuff = "a\n<ul><li>b</li></ul>\nc"
+#     assert_equal stuff, SanitizationFilter.call(stuff).to_s
+#   end
+#
+#   def test_github_specific_protocols_are_not_removed
+#     stuff = '<a href="github-windows://spillthelog">Spill this yo</a> and so on'
+#     assert_equal stuff, SanitizationFilter.call(stuff).to_s
+#   end
+#
+#   def test_unknown_schemes_are_removed
+#     stuff = '<a href="something-weird://heyyy">Wat</a> is this'
+#     html  = SanitizationFilter.call(stuff).to_s
+#     assert_equal '<a>Wat</a> is this', html
+#   end
+#
+#   def test_whitelisted_longdesc_schemes_are_allowed
+#     stuff = '<img src="./foo.jpg" longdesc="http://longdesc.com">'
+#     html  = SanitizationFilter.call(stuff).to_s
+#     assert_equal '<img src="./foo.jpg" longdesc="http://longdesc.com">', html
+#   end
+#
+#   def test_weird_longdesc_schemes_are_removed
+#     stuff = '<img src="./foo.jpg" longdesc="javascript:alert(1)">'
+#     html  = SanitizationFilter.call(stuff).to_s
+#     assert_equal '<img src="./foo.jpg">', html
+#   end
+#
+#   def test_standard_schemes_are_removed_if_not_specified_in_anchor_schemes
+#     stuff  = '<a href="http://www.example.com/">No href for you</a>'
+#     filter = SanitizationFilter.new(stuff, anchor_schemes: [])
+#     html   = filter.call.to_s
+#     assert_equal '<a>No href for you</a>', html
+#   end
+#
+#   def test_custom_anchor_schemes_are_not_removed
+#     stuff  = '<a href="something-weird://heyyy">Wat</a> is this'
+#     filter = SanitizationFilter.new(stuff, anchor_schemes: ['something-weird'])
+#     html   = filter.call.to_s
+#     assert_equal stuff, html
+#   end
+#
+#   def test_anchor_schemes_are_merged_with_other_anchor_restrictions
+#     stuff = '<a href="something-weird://heyyy" ping="more-weird://hiii">Wat</a> is this'
+#     whitelist = {
+#       elements: ['a'],
+#       attributes: { 'a' => %w[href ping] },
+#       protocols: { 'a' => { 'ping' => ['http'] } }
+#     }
+#     filter = SanitizationFilter.new(stuff, whitelist: whitelist, anchor_schemes: ['something-weird'])
+#     html   = filter.call.to_s
+#     assert_equal '<a href="something-weird://heyyy">Wat</a> is this', html
+#   end
+#
+#   def test_uses_anchor_schemes_from_whitelist_when_not_separately_specified
+#     stuff = '<a href="something-weird://heyyy">Wat</a> is this'
+#     whitelist = {
+#       elements: ['a'],
+#       attributes: { 'a' => ['href'] },
+#       protocols: { 'a' => { 'href' => ['something-weird'] } }
+#     }
+#     filter = SanitizationFilter.new(stuff, whitelist: whitelist)
+#     html   = filter.call.to_s
+#     assert_equal stuff, html
+#   end
+#
+#   def test_whitelist_contains_default_anchor_schemes
+#     assert_equal SanitizationFilter::WHITELIST[:protocols]['a']['href'], ['http', 'https', 'mailto', 'xmpp', :relative, 'github-windows', 'github-mac', 'irc', 'ircs']
+#   end
+#
+#   def test_whitelist_from_full_constant
+#     stuff  = '<a href="something-weird://heyyy" ping="more-weird://hiii">Wat</a> is this'
+#     filter = SanitizationFilter.new(stuff, whitelist: SanitizationFilter::FULL)
+#     html   = filter.call.to_s
+#     assert_equal 'Wat is this', html
+#   end
+#
+#   def test_exports_default_anchor_schemes
+#     assert_equal SanitizationFilter::ANCHOR_SCHEMES, ['http', 'https', 'mailto', 'xmpp', :relative, 'github-windows', 'github-mac', 'irc', 'ircs']
+#   end
+#
+#   def test_script_contents_are_removed
+#     orig = '<script>JavaScript!</script>'
+#     assert_equal '', SanitizationFilter.call(orig).to_s
+#   end
+#
+#   def test_table_rows_and_cells_removed_if_not_in_table
+#     orig = %(<tr><td>Foo</td></tr><td>Bar</td>)
+#     assert_equal 'FooBar', SanitizationFilter.call(orig).to_s
+#   end
+#
+#   def test_table_sections_removed_if_not_in_table
+#     orig = %(<thead><tr><td>Foo</td></tr></thead>)
+#     assert_equal 'Foo', SanitizationFilter.call(orig).to_s
+#   end
+#
+#   def test_table_sections_are_not_removed
+#     orig = %(<table>
+# <thead><tr><th>Column 1</th></tr></thead>
+# <tfoot><tr><td>Sum</td></tr></tfoot>
+# <tbody><tr><td>1</td></tr></tbody>
+# </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

data/spec/motion-html-pipeline/pipeline/disabled/syntax_highlighting_filter_spec.rb

@@ -0,0 +1,59 @@
+# describe 'MotionHTMLPipeline::Pipeline::SyntaxHighlightFilterTest' do
+#   SyntaxHighlightFilter = MotionHTMLPipeline::Pipeline::SyntaxHighlightFilter
+#
+#   def test_highlight_default
+#     filter = SyntaxHighlightFilter.new \
+#       '<pre>hello</pre>', highlight: 'coffeescript'
+#
+#     doc = filter.call
+#     assert !doc.css('.highlight-coffeescript').empty?
+#   end
+#
+#   def test_highlight_default_will_not_override
+#     filter = SyntaxHighlightFilter.new \
+#       "<pre lang='c'>hello</pre>", highlight: 'coffeescript'
+#
+#     doc = filter.call
+#     assert doc.css('.highlight-coffeescript').empty?
+#     assert !doc.css('.highlight-c').empty?
+#   end
+#
+#   def test_highlight_does_not_remove_pre_tag
+#     filter = SyntaxHighlightFilter.new \
+#       "<pre lang='c'>hello</pre>", highlight: 'coffeescript'
+#
+#     doc = filter.call
+#
+#     assert !doc.css('pre').empty?
+#   end
+#
+#   def test_highlight_allows_optional_scope
+#     filter = SyntaxHighlightFilter.new \
+#       "<pre lang='c'>hello</pre>", highlight: 'coffeescript', scope: 'test-scope'
+#
+#     doc = filter.call
+#
+#     assert !doc.css('pre.test-scope').empty?
+#   end
+#
+#   def test_highlight_keeps_the_pre_tags_lang
+#     filter = SyntaxHighlightFilter.new \
+#       "<pre lang='c'>hello</pre>", highlight: 'coffeescript'
+#
+#     doc = filter.call
+#
+#     assert !doc.css('pre[lang=c]').empty?
+#   end
+#
+#   def test_highlight_handles_nested_pre_tags
+#     inner_code = "<pre>console.log('i am nested!')</pre>"
+#     escaped = EscapeUtils.escape_html(inner_code)
+#     html = "<pre lang='html'>#{escaped}</pre>"
+#     filter = SyntaxHighlightFilter.new html, highlight: 'html'
+#
+#     doc = filter.call
+#
+#     assert_equal 2, doc.css('span[class=nt]').length
+#     assert_equal EscapeUtils.unescape_html(escaped), doc.inner_text
+#   end
+# end

data/spec/motion-html-pipeline/pipeline/disabled/toc_filter_spec.rb

@@ -0,0 +1,137 @@
+# describe 'MotionHTMLPipeline::Pipeline::TableOfContentsFilterTest' do
+#   TocFilter = MotionHTMLPipeline::Pipeline::TableOfContentsFilter
+#
+#   TocPipeline =
+#     HTML::Pipeline.new [
+#       HTML::Pipeline::TableOfContentsFilter
+#     ]
+#
+#   def toc
+#     result = {}
+#     TocPipeline.call(@orig, {}, result)
+#     result[:toc]
+#   end
+#
+#   def test_anchors_are_added_properly
+#     orig = %(<h1>Ice cube</h1><p>Will swarm on any motherfucker in a blue uniform</p>)
+#     assert_includes TocFilter.call(orig).to_s, '<a id='
+#   end
+#
+#   def test_custom_anchor_icons_added_properly
+#     orig = %(<h1>Ice cube</h1>)
+#     expected = %(<h1>\n<a id="ice-cube" class="anchor" href="#ice-cube" aria-hidden="true">#</a>Ice cube</h1>)
+#
+#     assert_equal expected, TocFilter.call(orig, anchor_icon: '#').to_s
+#   end
+#
+#   def test_toc_list_added_properly
+#     @orig = %(<h1>Ice cube</h1><p>Will swarm on any motherfucker in a blue uniform</p>)
+#     assert_includes toc, %(<ul class="section-nav">\n<li><a href=")
+#   end
+#
+#   def test_anchors_have_sane_names
+#     orig = %(<h1>Dr Dre</h1><h1>Ice Cube</h1><h1>Eazy-E</h1><h1>MC Ren</h1>)
+#     result = TocFilter.call(orig).to_s
+#
+#     assert_includes result, '"dr-dre"'
+#     assert_includes result, '"ice-cube"'
+#     assert_includes result, '"eazy-e"'
+#     assert_includes result, '"mc-ren"'
+#   end
+#
+#   def test_anchors_have_aria_hidden
+#     orig = '<h1>Straight Outta Compton</h1>'
+#     result = TocFilter.call(orig).to_s
+#     assert_includes result, 'aria-hidden="true"'
+#   end
+#
+#   def test_toc_hrefs_have_sane_values
+#     @orig = %(<h1>Dr Dre</h1><h1>Ice Cube</h1><h1>Eazy-E</h1><h1>MC Ren</h1>)
+#     assert_includes toc, '"#dr-dre"'
+#     assert_includes toc, '"#ice-cube"'
+#     assert_includes toc, '"#eazy-e"'
+#     assert_includes toc, '"#mc-ren"'
+#   end
+#
+#   def test_dupe_headers_have_unique_trailing_identifiers
+#     orig = %(<h1>Straight Outta Compton</h1>
+#              <h2>Dopeman</h2>
+#              <h3>Express Yourself</h3>
+#              <h1>Dopeman</h1>)
+#
+#     result = TocFilter.call(orig).to_s
+#
+#     assert_includes result, '"dopeman"'
+#     assert_includes result, '"dopeman-1"'
+#   end
+#
+#   def test_dupe_headers_have_unique_toc_anchors
+#     @orig = %(<h1>Straight Outta Compton</h1>
+#               <h2>Dopeman</h2>
+#               <h3>Express Yourself</h3>
+#               <h1>Dopeman</h1>)
+#
+#     assert_includes toc, '"#dopeman"'
+#     assert_includes toc, '"#dopeman-1"'
+#   end
+#
+#   def test_all_header_tags_are_found_when_adding_anchors
+#     orig = %(<h1>"Funky President" by James Brown</h1>
+#              <h2>"It's My Thing" by Marva Whitney</h2>
+#              <h3>"Boogie Back" by Roy Ayers</h3>
+#              <h4>"Feel Good" by Fancy</h4>
+#              <h5>"Funky Drummer" by James Brown</h5>
+#              <h6>"Ruthless Villain" by Eazy-E</h6>
+#              <h7>"Be Thankful for What You Got" by William DeVaughn</h7>)
+#
+#     doc = TocFilter.call(orig)
+#
+#     assert_equal 6, doc.search('a').size
+#   end
+#
+#   def test_toc_outputs_escaped_html
+#     @orig = %(<h1>&lt;img src="x" onerror="alert(42)"&gt;</h1>)
+#
+#     refute_includes toc, %(<img src="x" onerror="alert(42)">)
+#   end
+#
+#   def test_toc_is_complete
+#     @orig = %(<h1>"Funky President" by James Brown</h1>
+#               <h2>"It's My Thing" by Marva Whitney</h2>
+#               <h3>"Boogie Back" by Roy Ayers</h3>
+#               <h4>"Feel Good" by Fancy</h4>
+#               <h5>"Funky Drummer" by James Brown</h5>
+#               <h6>"Ruthless Villain" by Eazy-E</h6>
+#               <h7>"Be Thankful for What You Got" by William DeVaughn</h7>)
+#
+#     expected = %(<ul class="section-nav">\n<li><a href="#funky-president-by-james-brown">&quot;Funky President&quot; by James Brown</a></li>\n<li><a href="#its-my-thing-by-marva-whitney">&quot;It&#39;s My Thing&quot; by Marva Whitney</a></li>\n<li><a href="#boogie-back-by-roy-ayers">&quot;Boogie Back&quot; by Roy Ayers</a></li>\n<li><a href="#feel-good-by-fancy">&quot;Feel Good&quot; by Fancy</a></li>\n<li><a href="#funky-drummer-by-james-brown">&quot;Funky Drummer&quot; by James Brown</a></li>\n<li><a href="#ruthless-villain-by-eazy-e">&quot;Ruthless Villain&quot; by Eazy-E</a></li>\n</ul>)
+#
+#     assert_equal expected, toc
+#   end
+#
+#   if RUBY_VERSION > '1.9' # not sure how to make this work on 1.8.7
+#
+#     def test_anchors_with_utf8_characters
+#       orig = %(<h1>日本語</h1>
+#                <h1>Русский</h1)
+#
+#       rendered_h1s = TocFilter.call(orig).search('h1').map(&:to_s)
+#
+#       assert_equal "<h1>\n<a id=\"日本語\" class=\"anchor\" href=\"#%E6%97%A5%E6%9C%AC%E8%AA%9E\" aria-hidden=\"true\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a>日本語</h1>",
+#                    rendered_h1s[0]
+#       assert_equal "<h1>\n<a id=\"Русский\" class=\"anchor\" href=\"#%D0%A0%D1%83%D1%81%D1%81%D0%BA%D0%B8%D0%B9\" aria-hidden=\"true\"><span aria-hidden=\"true\" class=\"octicon octicon-link\"></span></a>Русский</h1>",
+#                    rendered_h1s[1]
+#     end
+#
+#     def test_toc_with_utf8_characters
+#       @orig = %(<h1>日本語</h1>
+#                 <h1>Русский</h1)
+#
+#       rendered_toc = Nokogiri::HTML::DocumentFragment.parse(toc).to_s
+#
+#       expected = %(<ul class="section-nav">\n<li><a href="#%E6%97%A5%E6%9C%AC%E8%AA%9E">日本語</a></li>\n<li><a href="#%D0%A0%D1%83%D1%81%D1%81%D0%BA%D0%B8%D0%B9">Русский</a></li>\n</ul>)
+#
+#       assert_equal expected, rendered_toc
+#     end
+#   end
+# end