summaryrefslogtreecommitdiff
path: root/spec/features/markdown/markdown_spec.rb
blob: 9ebd85acb81ca85058ab402149a189c9418e19b1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
# frozen_string_literal: true

require 'spec_helper'
require 'erb'

# This feature spec is intended to be a comprehensive exercising of all of
# GitLab's non-standard Markdown parsing and the integration thereof.
#
# These tests should be very high-level. Anything low-level belongs in the specs
# for the corresponding HTML::Pipeline filter or helper method.
#
# The idea is to pass a Markdown document through our entire processing stack.
#
# The process looks like this:
#
#   Raw Markdown
#   -> `markdown` helper
#     -> CommonMark::Render::GitlabHTML converts Markdown to HTML
#       -> Post-process HTML
#         -> `gfm` helper
#           -> HTML::Pipeline
#             -> SanitizationFilter
#             -> Other filters, depending on pipeline
#           -> `html_safe`
#           -> Template
#
# See the MarkdownFeature class for setup details.

describe 'GitLab Markdown', :aggregate_failures do
  include Capybara::Node::Matchers
  include MarkupHelper
  include MarkdownMatchers

  # Sometimes it can be useful to see the parsed output of the Markdown document
  # for debugging. Call this method to write the output to
  # `tmp/capybara/<filename>.html`.
  def write_markdown(filename = 'markdown_spec')
    File.open(Rails.root.join("tmp/capybara/#{filename}.html"), 'w') do |file|
      file.puts @html
    end
  end

  def doc(html = @html)
    @doc ||= Nokogiri::HTML::DocumentFragment.parse(html)
  end

  # Shared behavior that all pipelines should exhibit
  shared_examples 'all pipelines' do
    it 'includes extensions' do
      aggregate_failures 'does not parse emphasis inside of words' do
        expect(doc.to_html).not_to match('foo<em>bar</em>baz')
      end

      aggregate_failures 'parses table Markdown' do
        expect(doc).to have_selector('th:contains("Header")')
        expect(doc).to have_selector('th:contains("Row")')
        expect(doc).to have_selector('th:contains("Example")')
      end

      aggregate_failures 'allows Markdown in tables' do
        expect(doc.at_css('td:contains("Baz")').children.to_html)
          .to eq '<strong>Baz</strong>'
      end

      aggregate_failures 'parses fenced code blocks' do
        expect(doc).to have_selector('pre.code.highlight.js-syntax-highlight.c')
        expect(doc).to have_selector('pre.code.highlight.js-syntax-highlight.python')
      end

      aggregate_failures 'parses mermaid code block' do
        expect(doc).to have_selector('pre[lang=mermaid] > code.js-render-mermaid')
      end

      aggregate_failures 'parses strikethroughs' do
        expect(doc).to have_selector(%{del:contains("and this text doesn't")})
      end
    end

    it 'includes SanitizationFilter' do
      aggregate_failures 'permits b elements' do
        expect(doc).to have_selector('b:contains("b tag")')
      end

      aggregate_failures 'permits em elements' do
        expect(doc).to have_selector('em:contains("em tag")')
      end

      aggregate_failures 'permits code elements' do
        expect(doc).to have_selector('code:contains("code tag")')
      end

      aggregate_failures 'permits kbd elements' do
        expect(doc).to have_selector('kbd:contains("s")')
      end

      aggregate_failures 'permits strike elements' do
        expect(doc).to have_selector('strike:contains(Emoji)')
      end

      aggregate_failures 'permits img elements' do
        expect(doc).to have_selector('img[data-src*="smile.png"]')
      end

      aggregate_failures 'permits br elements' do
        expect(doc).to have_selector('br')
      end

      aggregate_failures 'permits hr elements' do
        expect(doc).to have_selector('hr')
      end

      aggregate_failures 'permits span elements' do
        expect(doc).to have_selector('span:contains("span tag")')
      end

      aggregate_failures 'permits details elements' do
        expect(doc).to have_selector('details:contains("Hiding the details")')
      end

      aggregate_failures 'permits summary elements' do
        expect(doc).to have_selector('details summary:contains("collapsible")')
      end

      aggregate_failures 'permits align attribute in th elements' do
        expect(doc.at_css('th:contains("Header")')['align']).to eq 'center'
        expect(doc.at_css('th:contains("Row")')['align']).to eq 'right'
        expect(doc.at_css('th:contains("Example")')['align']).to eq 'left'
      end

      aggregate_failures 'permits align attribute in td elements' do
        expect(doc.at_css('td:contains("Foo")')['align']).to eq 'center'
        expect(doc.at_css('td:contains("Bar")')['align']).to eq 'right'
        expect(doc.at_css('td:contains("Baz")')['align']).to eq 'left'
      end

      aggregate_failures 'permits superscript elements' do
        expect(doc).to have_selector('sup', count: 2)
      end

      aggregate_failures 'permits subscript elements' do
        expect(doc).to have_selector('sub', count: 3)
      end

      aggregate_failures 'removes `rel` attribute from links' do
        expect(doc).not_to have_selector('a[rel="bookmark"]')
      end

      aggregate_failures "removes `href` from `a` elements if it's fishy" do
        expect(doc).not_to have_selector('a[href*="javascript"]')
      end
    end

    describe 'Escaping' do
      it 'escapes non-tag angle brackets' do
        table = doc.css('table').last.at_css('tbody')
        expect(table.at_xpath('.//tr[1]/td[3]').inner_html).to eq '1 &lt; 3 &amp; 5'
      end
    end

    describe 'Edge Cases' do
      it 'allows markup inside link elements' do
        aggregate_failures do
          expect(doc.at_css('a[href="#link-emphasis"]').to_html)
            .to eq %{<a href="#link-emphasis"><em>text</em></a>}

          expect(doc.at_css('a[href="#link-strong"]').to_html)
            .to eq %{<a href="#link-strong"><strong>text</strong></a>}

          expect(doc.at_css('a[href="#link-code"]').to_html)
            .to eq %{<a href="#link-code"><code>text</code></a>}
        end
      end
    end

    it 'includes ExternalLinkFilter' do
      aggregate_failures 'adds nofollow to external link' do
        link = doc.at_css('a:contains("Google")')

        expect(link.attr('rel')).to include('nofollow')
      end

      aggregate_failures 'adds noreferrer to external link' do
        link = doc.at_css('a:contains("Google")')

        expect(link.attr('rel')).to include('noreferrer')
      end

      aggregate_failures 'adds _blank to target attribute for external links' do
        link = doc.at_css('a:contains("Google")')

        expect(link.attr('target')).to match('_blank')
      end

      aggregate_failures 'ignores internal link' do
        link = doc.at_css('a:contains("GitLab Root")')

        expect(link.attr('rel')).not_to match 'nofollow'
        expect(link.attr('target')).not_to match '_blank'
      end
    end
  end

  before do
    @feat = MarkdownFeature.new

    # `markdown` helper expects a `@project` and `@group` variable
    @project = @feat.project
    @group = @feat.group
  end

  let(:project) { @feat.project } # Shadow this so matchers can use it

  context 'default pipeline' do
    before do
      @html = markdown(@feat.raw_markdown)
    end

    it_behaves_like 'all pipelines'

    it 'includes custom filters' do
      aggregate_failures 'UploadLinkFilter' do
        expect(doc).to parse_upload_links
      end

      aggregate_failures 'RepositoryLinkFilter' do
        expect(doc).to parse_repository_links
      end

      aggregate_failures 'EmojiFilter' do
        expect(doc).to parse_emoji
      end

      aggregate_failures 'TableOfContentsFilter' do
        expect(doc).to create_header_links
      end

      aggregate_failures 'AutolinkFilter' do
        expect(doc).to create_autolinks
      end

      aggregate_failures 'all reference filters' do
        expect(doc).to reference_users
        expect(doc).to reference_issues
        expect(doc).to reference_merge_requests
        expect(doc).to reference_snippets
        expect(doc).to reference_commit_ranges
        expect(doc).to reference_commits
        expect(doc).to reference_labels
        expect(doc).to reference_milestones
      end

      aggregate_failures 'TaskListFilter' do
        expect(doc).to parse_task_lists
      end

      aggregate_failures 'InlineDiffFilter' do
        expect(doc).to parse_inline_diffs
      end

      aggregate_failures 'VideoLinkFilter' do
        expect(doc).to parse_video_links
      end

      aggregate_failures 'ColorFilter' do
        expect(doc).to parse_colors
      end
    end
  end

  context 'wiki pipeline' do
    before do
      @project_wiki = @feat.project_wiki
      @project_wiki_page = @feat.project_wiki_page

      path = 'images/example.jpg'
      gitaly_wiki_file = Gitlab::GitalyClient::WikiFile.new(path: path)
      expect(@project_wiki).to receive(:find_file).with(path).and_return(Gitlab::Git::WikiFile.new(gitaly_wiki_file))
      allow(@project_wiki).to receive(:wiki_base_path) { '/namespace1/gitlabhq/wikis' }

      @html = markdown(@feat.raw_markdown, { pipeline: :wiki, project_wiki: @project_wiki, page_slug: @project_wiki_page.slug })
    end

    it_behaves_like 'all pipelines'

    it 'includes custom filters' do
      aggregate_failures 'UploadLinkFilter' do
        expect(doc).to parse_upload_links
      end

      aggregate_failures 'RepositoryLinkFilter' do
        expect(doc).not_to parse_repository_links
      end

      aggregate_failures 'EmojiFilter' do
        expect(doc).to parse_emoji
      end

      aggregate_failures 'TableOfContentsFilter' do
        expect(doc).to create_header_links
      end

      aggregate_failures 'AutolinkFilter' do
        expect(doc).to create_autolinks
      end

      aggregate_failures 'all reference filters' do
        expect(doc).to reference_users
        expect(doc).to reference_issues
        expect(doc).to reference_merge_requests
        expect(doc).to reference_snippets
        expect(doc).to reference_commit_ranges
        expect(doc).to reference_commits
        expect(doc).to reference_labels
        expect(doc).to reference_milestones
      end

      aggregate_failures 'TaskListFilter' do
        expect(doc).to parse_task_lists
      end

      aggregate_failures 'GollumTagsFilter' do
        expect(doc).to parse_gollum_tags
      end

      aggregate_failures 'InlineDiffFilter' do
        expect(doc).to parse_inline_diffs
      end

      aggregate_failures 'VideoLinkFilter' do
        expect(doc).to parse_video_links
      end

      aggregate_failures 'AudioLinkFilter' do
        expect(doc).to parse_audio_links
      end

      aggregate_failures 'ColorFilter' do
        expect(doc).to parse_colors
      end
    end
  end

  # Fake a `current_user` helper
  def current_user
    @feat.user
  end
end