html-pipeline 2.4.1 → 2.4.2

data/test/html/pipeline/mention_filter_test.rb

@@ -1,212 +0,0 @@
-require "test_helper"
-
-class HTML::Pipeline::MentionFilterTest < Minitest::Test
-  def filter(html, base_url='/', info_url=nil, username_pattern=nil)
-    HTML::Pipeline::MentionFilter.call(html, :base_url => base_url, :info_url => info_url, :username_pattern => username_pattern)
-  end
-
-  def test_filtering_a_documentfragment
-    body = "<p>@kneath: check it out.</p>"
-    doc  = Nokogiri::HTML::DocumentFragment.parse(body)
-
-    res  = filter(doc, '/')
-    assert_same doc, res
-
-    link = "<a href=\"/kneath\" class=\"user-mention\">@kneath</a>"
-    assert_equal "<p>#{link}: check it out.</p>",
-      res.to_html
-  end
-
-  def test_filtering_plain_text
-    body = "<p>@kneath: check it out.</p>"
-    res  = filter(body, '/')
-
-    link = "<a href=\"/kneath\" class=\"user-mention\">@kneath</a>"
-    assert_equal "<p>#{link}: check it out.</p>",
-      res.to_html
-  end
-
-  def test_not_replacing_mentions_in_pre_tags
-    body = "<pre>@kneath: okay</pre>"
-    assert_equal body, filter(body).to_html
-  end
-
-  def test_not_replacing_mentions_in_code_tags
-    body = "<p><code>@kneath:</code> okay</p>"
-    assert_equal body, filter(body).to_html
-  end
-
-  def test_not_replacing_mentions_in_style_tags
-    body = "<style>@media (min-width: 768px) { color: red; }</style>"
-    assert_equal body, filter(body).to_html
-  end
-
-  def test_not_replacing_mentions_in_links
-    body = "<p><a>@kneath</a> okay</p>"
-    assert_equal body, filter(body).to_html
-  end
-
-  def test_entity_encoding_and_whatnot
-    body = "<p>@&#x6b;neath what's up</p>"
-    link = "<a href=\"/kneath\" class=\"user-mention\">@kneath</a>"
-    assert_equal "<p>#{link} what's up</p>", filter(body, '/').to_html
-  end
-
-  def test_html_injection
-    body = "<p>@kneath &lt;script>alert(0)&lt;/script></p>"
-    link = "<a href=\"/kneath\" class=\"user-mention\">@kneath</a>"
-    assert_equal "<p>#{link} &lt;script&gt;alert(0)&lt;/script&gt;</p>",
-      filter(body, '/').to_html
-  end
-
-  def test_links_to_nothing_when_no_info_url_given
-    body = "<p>How do I @mention someone?</p>"
-    assert_equal "<p>How do I @mention someone?</p>",
-      filter(body, '/').to_html
-  end
-
-  def test_links_to_more_info_when_info_url_given
-    body = "<p>How do I @mention someone?</p>"
-    link = "<a href=\"https://github.com/blog/821\" class=\"user-mention\">@mention</a>"
-    assert_equal "<p>How do I #{link} someone?</p>",
-      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,
-      HTML::Pipeline::MentionFilter
-    ]
-
-  def mentioned_usernames
-    result = {}
-    MarkdownPipeline.call(@body, {}, result)
-    result[:mentioned_usernames]
-  end
-
-  def test_matches_usernames_in_body
-    @body = "@test how are you?"
-    assert_equal %w[test], mentioned_usernames
-  end
-
-  def test_matches_usernames_with_dashes
-    @body = "hi @some-user"
-    assert_equal %w[some-user], mentioned_usernames
-  end
-
-  def test_matches_usernames_followed_by_a_single_dot
-    @body = "okay @some-user."
-    assert_equal %w[some-user], mentioned_usernames
-  end
-
-  def test_matches_usernames_followed_by_multiple_dots
-    @body = "okay @some-user..."
-    assert_equal %w[some-user], mentioned_usernames
-  end
-
-  def test_does_not_match_email_addresses
-    @body = "aman@tmm1.net"
-    assert_equal [], mentioned_usernames
-  end
-
-  def test_does_not_match_domain_name_looking_things
-    @body = "we need a @github.com email"
-    assert_equal [], mentioned_usernames
-  end
-
-  def test_does_not_match_organization_team_mentions
-    @body = "we need to @github/enterprise know"
-    assert_equal [], mentioned_usernames
-  end
-
-  def test_matches_colon_suffixed_names
-    @body = "@tmm1: what do you think?"
-    assert_equal %w[tmm1], mentioned_usernames
-  end
-
-  def test_matches_list_of_names
-    @body = "@defunkt @atmos @kneath"
-    assert_equal %w[defunkt atmos kneath], mentioned_usernames
-  end
-
-  def test_matches_list_of_names_with_commas
-    @body = "/cc @defunkt, @atmos, @kneath"
-    assert_equal %w[defunkt atmos kneath], mentioned_usernames
-  end
-
-  def test_matches_inside_brackets
-    @body = "(@mislav) and [@rtomayko]"
-    assert_equal %w[mislav rtomayko], mentioned_usernames
-  end
-
-  def test_doesnt_ignore_invalid_users
-    @body = "@defunkt @mojombo and @somedude"
-    assert_equal ['defunkt', 'mojombo', 'somedude'], mentioned_usernames
-  end
-
-  def test_returns_distinct_set
-    @body = "/cc @defunkt, @atmos, @kneath, @defunkt, @defunkt"
-    assert_equal %w[defunkt atmos kneath], mentioned_usernames
-  end
-
-  def test_does_not_match_inline_code_block_with_multiple_code_blocks
-    @body = "something\n\n`/cc @defunkt @atmos @kneath` `/cc @atmos/atmos`"
-    assert_equal %w[], mentioned_usernames
-  end
-
-  def test_mention_at_end_of_parenthetical_sentence
-    @body = "(We're talking 'bout @ymendel.)"
-    assert_equal %w[ymendel], mentioned_usernames
-  end
-
-  def test_username_pattern_can_be_customized
-    body = "<p>@_abc: test.</p>"
-    doc  = Nokogiri::HTML::DocumentFragment.parse(body)
-
-    res  = filter(doc, '/', nil, /(_[a-z]{3})/)
-
-    link = "<a href=\"/_abc\" class=\"user-mention\">@_abc</a>"
-    assert_equal "<p>#{link}: test.</p>",
-      res.to_html
-  end
-
-  def test_filter_does_not_create_a_new_object_for_default_username_pattern
-    body = "<div>@test</div>"
-    doc = Nokogiri::HTML::DocumentFragment.parse(body)
-
-    filter(doc.clone, '/', nil)
-    pattern_count = HTML::Pipeline::MentionFilter::MentionPatterns.length
-    filter(doc.clone, '/', nil)
-
-    assert_equal pattern_count, HTML::Pipeline::MentionFilter::MentionPatterns.length
-    filter(doc.clone, '/', nil, /test/)
-    assert_equal pattern_count + 1, HTML::Pipeline::MentionFilter::MentionPatterns.length
-  end
-
-  def test_mention_link_filter
-    filter = HTML::Pipeline::MentionFilter.new nil
-    expected = "<a href='/hubot' class='user-mention'>@hubot</a>"
-    assert_equal expected, filter.mention_link_filter("@hubot")
-  end
-end

data/test/html/pipeline/plain_text_input_filter_test.rb

@@ -1,22 +0,0 @@
-require "test_helper"
-
-class HTML::Pipeline::PlainTextInputFilterTest < Minitest::Test
-  PlainTextInputFilter = HTML::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/test/html/pipeline/sanitization_filter_test.rb

@@ -1,166 +0,0 @@
-require "test_helper"
-
-class HTML::Pipeline::SanitizationFilterTest < Minitest::Test
-  SanitizationFilter = HTML::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' => ['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', :relative, 'github-windows', 'github-mac']
-  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', :relative, 'github-windows', 'github-mac']
-  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/test/html/pipeline/syntax_highlight_filter_test.rb

@@ -1,22 +0,0 @@
-require "test_helper"
-
-SyntaxHighlightFilter = HTML::Pipeline::SyntaxHighlightFilter
-
-class HTML::Pipeline::SyntaxHighlightFilterTest < Minitest::Test
-  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
-end

data/test/html/pipeline/toc_filter_test.rb

@@ -1,134 +0,0 @@
-# encoding: utf-8
-require "test_helper"
-
-class HTML::Pipeline::TableOfContentsFilterTest < Minitest::Test
-  TocFilter = HTML::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 = %Q{<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, %Q{<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_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 = %Q{<ul class="section-nav">\n<li><a href="#funky-president-by-james-brown">"Funky President" by James Brown</a></li>\n<li><a href="#its-my-thing-by-marva-whitney">"It's My Thing" by Marva Whitney</a></li>\n<li><a href="#boogie-back-by-roy-ayers">"Boogie Back" by Roy Ayers</a></li>\n<li><a href="#feel-good-by-fancy">"Feel Good" by Fancy</a></li>\n<li><a href="#funky-drummer-by-james-brown">"Funky Drummer" by James Brown</a></li>\n<li><a href="#ruthless-villain-by-eazy-e">"Ruthless Villain" 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 = %Q{<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