about summary refs log tree commit diff
path: root/spec/lib/text_formatter_spec.rb
blob: 3417b450c60cab8a44ae71e11902823c7d82a26a (plain) (blame)
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
# frozen_string_literal: true

require 'rails_helper'

RSpec.describe TextFormatter do
  describe '#to_s' do
    subject { described_class.new(text, preloaded_accounts: preloaded_accounts).to_s }

    let(:preloaded_accounts) { nil }

    context 'given text containing plain text' do
      let(:text) { 'text' }

      it 'paragraphizes the text' do
        expect(subject).to eq '<p>text</p>'
      end
    end

    context 'given text containing line feeds' do
      let(:text) { "line\nfeed" }

      it 'removes line feeds' do
        expect(subject).to_not include "\n"
      end
    end

    context 'given text containing linkable mentions' do
      let(:preloaded_accounts) { [Fabricate(:account, username: 'alice')] }
      let(:text) { '@alice' }

      it 'creates a mention link' do
        expect(subject).to include '<a href="https://cb6e6126.ngrok.io/@alice" class="u-url mention">@<span>alice</span></a></span>'
      end
    end

    context 'given text containing unlinkable mentions' do
      let(:preloaded_accounts) { [] }
      let(:text) { '@alice' }

      it 'does not create a mention link' do
        expect(subject).to include '@alice'
      end
    end

    context 'given a stand-alone medium URL' do
      let(:text) { 'https://hackernoon.com/the-power-to-build-communities-a-response-to-mark-zuckerberg-3f2cac9148a4' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://hackernoon.com/the-power-to-build-communities-a-response-to-mark-zuckerberg-3f2cac9148a4"'
      end
    end

    context 'given a stand-alone google URL' do
      let(:text) { 'http://google.com' }

      it 'matches the full URL' do
        expect(subject).to include 'href="http://google.com"'
      end
    end

    context 'given a stand-alone URL with a newer TLD' do
      let(:text) { 'http://example.gay' }

      it 'matches the full URL' do
        expect(subject).to include 'href="http://example.gay"'
      end
    end

    context 'given a stand-alone IDN URL' do
      let(:text) { 'https://nic.みんな/' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://nic.みんな/"'
      end

      it 'has display URL' do
        expect(subject).to include '<span class="">nic.みんな/</span>'
      end
    end

    context 'given a URL with a trailing period' do
      let(:text) { 'http://www.mcmansionhell.com/post/156408871451/50-states-of-mcmansion-hell-scottsdale-arizona. ' }

      it 'matches the full URL but not the period' do
        expect(subject).to include 'href="http://www.mcmansionhell.com/post/156408871451/50-states-of-mcmansion-hell-scottsdale-arizona"'
      end
    end

    context 'given a URL enclosed with parentheses' do
      let(:text) { '(http://google.com/)' }

      it 'matches the full URL but not the parentheses' do
        expect(subject).to include 'href="http://google.com/"'
      end
    end

    context 'given a URL with a trailing exclamation point' do
      let(:text) { 'http://www.google.com!' }

      it 'matches the full URL but not the exclamation point' do
        expect(subject).to include 'href="http://www.google.com"'
      end
    end

    context 'given a URL with a trailing single quote' do
      let(:text) { "http://www.google.com'" }

      it 'matches the full URL but not the single quote' do
        expect(subject).to include 'href="http://www.google.com"'
      end
    end

    context 'given a URL with a trailing angle bracket' do
      let(:text) { 'http://www.google.com>' }

      it 'matches the full URL but not the angle bracket' do
        expect(subject).to include 'href="http://www.google.com"'
      end
    end

    context 'given a URL with a query string' do
      context 'with escaped unicode character' do
        let(:text) { 'https://www.ruby-toolbox.com/search?utf8=%E2%9C%93&q=autolink' }

        it 'matches the full URL' do
          expect(subject).to include 'href="https://www.ruby-toolbox.com/search?utf8=%E2%9C%93&amp;q=autolink"'
        end
      end

      context 'with unicode character' do
        let(:text) { 'https://www.ruby-toolbox.com/search?utf8=✓&q=autolink' }

        it 'matches the full URL' do
          expect(subject).to include 'href="https://www.ruby-toolbox.com/search?utf8=✓&amp;q=autolink"'
        end
      end

      context 'with unicode character at the end' do
        let(:text) { 'https://www.ruby-toolbox.com/search?utf8=✓' }

        it 'matches the full URL' do
          expect(subject).to include 'href="https://www.ruby-toolbox.com/search?utf8=✓"'
        end
      end

      context 'with escaped and not escaped unicode characters' do
        let(:text) { 'https://www.ruby-toolbox.com/search?utf8=%E2%9C%93&utf81=✓&q=autolink' }

        it 'preserves escaped unicode characters' do
          expect(subject).to include 'href="https://www.ruby-toolbox.com/search?utf8=%E2%9C%93&amp;utf81=✓&amp;q=autolink"'
        end
      end
    end

    context 'given a URL with parentheses in it' do
      let(:text) { 'https://en.wikipedia.org/wiki/Diaspora_(software)' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://en.wikipedia.org/wiki/Diaspora_(software)"'
      end
    end

    context 'given a URL in quotation marks' do
      let(:text) { '"https://example.com/"' }

      it 'does not match the quotation marks' do
        expect(subject).to include 'href="https://example.com/"'
      end
    end

    context 'given a URL in angle brackets' do
      let(:text) { '<https://example.com/>' }

      it 'does not match the angle brackets' do
        expect(subject).to include 'href="https://example.com/"'
      end
    end

    context 'given a URL with Japanese path string' do
      let(:text) { 'https://ja.wikipedia.org/wiki/日本' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://ja.wikipedia.org/wiki/日本"'
      end
    end

    context 'given a URL with Korean path string' do
      let(:text) { 'https://ko.wikipedia.org/wiki/대한민국' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://ko.wikipedia.org/wiki/대한민국"'
      end
    end

    context 'given a URL with a full-width space' do
      let(:text) { 'https://example.com/ abc123' }

      it 'does not match the full-width space' do
        expect(subject).to include 'href="https://example.com/"'
      end
    end

    context 'given a URL in Japanese quotation marks' do
      let(:text) { '「[https://example.org/」' }

      it 'does not match the quotation marks' do
        expect(subject).to include 'href="https://example.org/"'
      end
    end

    context 'given a URL with Simplified Chinese path string' do
      let(:text) { 'https://baike.baidu.com/item/中华人民共和国' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://baike.baidu.com/item/中华人民共和国"'
      end
    end

    context 'given a URL with Traditional Chinese path string' do
      let(:text) { 'https://zh.wikipedia.org/wiki/臺灣' }

      it 'matches the full URL' do
        expect(subject).to include 'href="https://zh.wikipedia.org/wiki/臺灣"'
      end
    end

    context 'given a URL containing unsafe code (XSS attack, visible part)' do
      let(:text) { 'http://example.com/b<del>b</del>' }

      it 'does not include the HTML in the URL' do
        expect(subject).to include '"http://example.com/b"'
      end

      it 'escapes the HTML' do
        expect(subject).to include '&lt;del&gt;b&lt;/del&gt;'
      end
    end

    context 'given a URL containing unsafe code (XSS attack, invisible part)' do
      let(:text) { 'http://example.com/blahblahblahblah/a<script>alert("Hello")</script>' }

      it 'does not include the HTML in the URL' do
        expect(subject).to include '"http://example.com/blahblahblahblah/a"'
      end

      it 'escapes the HTML' do
        expect(subject).to include '&lt;script&gt;alert(&quot;Hello&quot;)&lt;/script&gt;'
      end
    end

    context 'given text containing HTML code (script tag)' do
      let(:text) { '<script>alert("Hello")</script>' }

      it 'escapes the HTML' do
        expect(subject).to include '<p>&lt;script&gt;alert(&quot;Hello&quot;)&lt;/script&gt;</p>'
      end
    end

    context 'given text containing HTML (XSS attack)' do
      let(:text) { %q{<img src="javascript:alert('XSS');">} }

      it 'escapes the HTML' do
        expect(subject).to include '<p>&lt;img src=&quot;javascript:alert(&#39;XSS&#39;);&quot;&gt;</p>'
      end
    end

    context 'given an invalid URL' do
      let(:text) { 'http://www\.google\.com' }

      it 'outputs the raw URL' do
        expect(subject).to eq '<p>http://www\.google\.com</p>'
      end
    end

    context 'given text containing a hashtag' do
      let(:text)  { '#hashtag' }

      it 'creates a hashtag link' do
        expect(subject).to include '/tags/hashtag" class="mention hashtag" rel="tag">#<span>hashtag</span></a>'
      end
    end

    context 'given text containing a hashtag with Unicode chars' do
      let(:text)  { '#hashtagタグ' }

      it 'creates a hashtag link' do
        expect(subject).to include '/tags/hashtag%E3%82%BF%E3%82%B0" class="mention hashtag" rel="tag">#<span>hashtagタグ</span></a>'
      end
    end

    context 'given text with a stand-alone xmpp: URI' do
      let(:text) { 'xmpp:user@instance.com' }

      it 'matches the full URI' do
        expect(subject).to include 'href="xmpp:user@instance.com"'
      end
    end

    context 'given text with an xmpp: URI with a query-string' do
      let(:text) { 'please join xmpp:muc@instance.com?join right now' }

      it 'matches the full URI' do
        expect(subject).to include 'href="xmpp:muc@instance.com?join"'
      end
    end

    context 'given text containing a magnet: URI' do
      let(:text) { 'wikipedia gives this example of a magnet uri: magnet:?xt=urn:btih:c12fe1c06bba254a9dc9f519b335aa7c1367a88a' }

      it 'matches the full URI' do
        expect(subject).to include 'href="magnet:?xt=urn:btih:c12fe1c06bba254a9dc9f519b335aa7c1367a88a"'
      end
    end
  end
end