twitter-text 1.4.8 → 1.4.9
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile.lock +1 -27
- data/README.rdoc +1 -0
- data/lib/autolink.rb +55 -47
- data/lib/extractor.rb +36 -2
- data/lib/regex.rb +49 -24
- data/lib/rewriter.rb +63 -0
- data/lib/twitter-text.rb +7 -4
- data/lib/validation.rb +5 -5
- data/spec/autolinking_spec.rb +41 -3
- data/spec/extractor_spec.rb +2 -2
- data/spec/rewriter_spec.rb +558 -0
- data/spec/spec_helper.rb +10 -4
- data/test/conformance_test.rb +18 -5
- data/twitter-text.gemspec +6 -4
- metadata +12 -7
data/lib/twitter-text.rb
CHANGED
@@ -1,15 +1,18 @@
|
|
1
1
|
major, minor, patch = RUBY_VERSION.split('.')
|
2
2
|
|
3
|
-
if major.to_i == 1 && minor.to_i < 9
|
3
|
+
$RUBY_1_9 = if major.to_i == 1 && minor.to_i < 9
|
4
4
|
# Ruby 1.8 KCODE check. Not needed on 1.9 and later.
|
5
5
|
raise("twitter-text requires the $KCODE variable be set to 'UTF8' or 'u'") unless $KCODE[0].chr =~ /u/i
|
6
|
+
false
|
7
|
+
else
|
8
|
+
true
|
6
9
|
end
|
7
10
|
|
8
|
-
|
9
|
-
require '
|
10
|
-
require 'action_view'
|
11
|
+
require 'active_support'
|
12
|
+
require 'active_support/core_ext/string/multibyte.rb'
|
11
13
|
|
12
14
|
require File.join(File.dirname(__FILE__), 'regex')
|
15
|
+
require File.join(File.dirname(__FILE__), 'rewriter')
|
13
16
|
require File.join(File.dirname(__FILE__), 'autolink')
|
14
17
|
require File.join(File.dirname(__FILE__), 'extractor')
|
15
18
|
require File.join(File.dirname(__FILE__), 'unicode')
|
data/lib/validation.rb
CHANGED
@@ -35,7 +35,7 @@ module Twitter
|
|
35
35
|
# <tt>:empty</tt>:: if the <tt>text</tt> is nil or empty
|
36
36
|
# <tt>:invalid_characters</tt>:: if the <tt>text</tt> contains non-Unicode or any of the disallowed Unicode characters
|
37
37
|
def tweet_invalid?(text)
|
38
|
-
return :empty if text.
|
38
|
+
return :empty if !text || text.empty?
|
39
39
|
begin
|
40
40
|
return :too_long if tweet_length(text) > MAX_LENGTH
|
41
41
|
return :invalid_characters if INVALID_CHARACTERS.any?{|invalid_char| text.include?(invalid_char) }
|
@@ -52,7 +52,7 @@ module Twitter
|
|
52
52
|
end
|
53
53
|
|
54
54
|
def valid_username?(username)
|
55
|
-
return false if username.
|
55
|
+
return false if !username || username.empty?
|
56
56
|
|
57
57
|
extracted = Twitter::Extractor.extract_mentioned_screen_names(username)
|
58
58
|
# Should extract the username minus the @ sign, hence the [1..-1]
|
@@ -63,11 +63,11 @@ module Twitter
|
|
63
63
|
def valid_list?(username_list)
|
64
64
|
match = username_list.match(VALID_LIST_RE)
|
65
65
|
# Must have matched and had nothing before or after
|
66
|
-
!!(match && match[1] == "" && !match[4].
|
66
|
+
!!(match && match[1] == "" && match[4] && !match[4].empty?)
|
67
67
|
end
|
68
68
|
|
69
69
|
def valid_hashtag?(hashtag)
|
70
|
-
return false if hashtag.
|
70
|
+
return false if !hashtag || hashtag.empty?
|
71
71
|
|
72
72
|
extracted = Twitter::Extractor.extract_hashtags(hashtag)
|
73
73
|
# Should extract the hashtag minus the # sign, hence the [1..-1]
|
@@ -75,7 +75,7 @@ module Twitter
|
|
75
75
|
end
|
76
76
|
|
77
77
|
def valid_url?(url, unicode_domains=true)
|
78
|
-
return false if url.
|
78
|
+
return false if !url || url.empty?
|
79
79
|
|
80
80
|
url_parts = url.match(Twitter::Regex[:validate_url_unencoded])
|
81
81
|
return false unless (url_parts && url_parts.to_s == url)
|
data/spec/autolinking_spec.rb
CHANGED
@@ -36,7 +36,7 @@ describe Twitter::Autolink do
|
|
36
36
|
def original_text; "meet@the beach"; end
|
37
37
|
|
38
38
|
it "should not be linked" do
|
39
|
-
Nokogiri::HTML(@autolinked_text).search('a').should
|
39
|
+
Nokogiri::HTML(@autolinked_text).search('a').should be_empty
|
40
40
|
end
|
41
41
|
end
|
42
42
|
|
@@ -133,7 +133,7 @@ describe Twitter::Autolink do
|
|
133
133
|
def original_text; "hello @/my-list"; end
|
134
134
|
|
135
135
|
it "should NOT be linked" do
|
136
|
-
Nokogiri::HTML(@autolinked_text).search('a').should
|
136
|
+
Nokogiri::HTML(@autolinked_text).search('a').should be_empty
|
137
137
|
end
|
138
138
|
end
|
139
139
|
|
@@ -149,7 +149,7 @@ describe Twitter::Autolink do
|
|
149
149
|
def original_text; "meet@the/beach"; end
|
150
150
|
|
151
151
|
it "should not be linked" do
|
152
|
-
Nokogiri::HTML(@autolinked_text).search('a').should
|
152
|
+
Nokogiri::HTML(@autolinked_text).search('a').should be_empty
|
153
153
|
end
|
154
154
|
end
|
155
155
|
|
@@ -505,6 +505,24 @@ describe Twitter::Autolink do
|
|
505
505
|
end
|
506
506
|
end
|
507
507
|
|
508
|
+
context "regex engine quirks" do
|
509
|
+
context "does not spiral out of control on repeated periods" do
|
510
|
+
def original_text; "Test a ton of periods http://example.com/path.........................................."; end
|
511
|
+
|
512
|
+
it "should autolink" do
|
513
|
+
@autolinked_text.should have_autolinked_url('http://example.com/path')
|
514
|
+
end
|
515
|
+
end
|
516
|
+
|
517
|
+
context "does not spiral out of control on repeated dashes" do
|
518
|
+
def original_text; "Single char file ext http://www.bestbuy.com/site/Currie+Technologies+-+Ezip+400+Scooter/9885188.p?id=1218189013070&skuId=9885188"; end
|
519
|
+
|
520
|
+
it "should autolink" do
|
521
|
+
@autolinked_text.should have_autolinked_url('http://www.bestbuy.com/site/Currie+Technologies+-+Ezip+400+Scooter/9885188.p?id=1218189013070&skuId=9885188')
|
522
|
+
end
|
523
|
+
end
|
524
|
+
end
|
525
|
+
|
508
526
|
end
|
509
527
|
|
510
528
|
describe "Autolink all" do
|
@@ -558,6 +576,26 @@ describe Twitter::Autolink do
|
|
558
576
|
linked.should have_autolinked_url('http://example.com/')
|
559
577
|
linked.should match(/target="mywindow"/)
|
560
578
|
end
|
579
|
+
|
580
|
+
it "should customize href by username_url_block option" do
|
581
|
+
linked = TestAutolink.new.auto_link("@test", :username_url_block => lambda{|a| "dummy"})
|
582
|
+
linked.should have_autolinked_url('dummy', 'test')
|
583
|
+
end
|
584
|
+
|
585
|
+
it "should customize href by list_url_block option" do
|
586
|
+
linked = TestAutolink.new.auto_link("@test/list", :list_url_block => lambda{|a| "dummy"})
|
587
|
+
linked.should have_autolinked_url('dummy', 'test/list')
|
588
|
+
end
|
589
|
+
|
590
|
+
it "should customize href by hashtag_url_block option" do
|
591
|
+
linked = TestAutolink.new.auto_link("#hashtag", :hashtag_url_block => lambda{|a| "dummy"})
|
592
|
+
linked.should have_autolinked_url('dummy', '#hashtag')
|
593
|
+
end
|
594
|
+
|
595
|
+
it "should customize href by link_url_block option" do
|
596
|
+
linked = TestAutolink.new.auto_link("http://example.com/", :link_url_block => lambda{|a| "dummy"})
|
597
|
+
linked.should have_autolinked_url('dummy', 'http://example.com/')
|
598
|
+
end
|
561
599
|
end
|
562
600
|
|
563
601
|
describe "html_escape" do
|
data/spec/extractor_spec.rb
CHANGED
@@ -228,11 +228,11 @@ describe Twitter::Extractor do
|
|
228
228
|
end
|
229
229
|
|
230
230
|
it "should not allow the multiplication character" do
|
231
|
-
@extractor.extract_hashtags("#pre#{
|
231
|
+
@extractor.extract_hashtags("#pre#{Twitter::Unicode::U00D7}post").should == []
|
232
232
|
end
|
233
233
|
|
234
234
|
it "should not allow the division character" do
|
235
|
-
@extractor.extract_hashtags("#pre#{
|
235
|
+
@extractor.extract_hashtags("#pre#{Twitter::Unicode::U00F7}post").should == []
|
236
236
|
end
|
237
237
|
end
|
238
238
|
|
@@ -0,0 +1,558 @@
|
|
1
|
+
# encoding: UTF-8
|
2
|
+
|
3
|
+
require 'spec_helper'
|
4
|
+
|
5
|
+
describe Twitter::Rewriter do
|
6
|
+
def original_text; end
|
7
|
+
def url; end
|
8
|
+
|
9
|
+
def block(*args)
|
10
|
+
if Array === @block_args
|
11
|
+
unless Array === @block_args.first
|
12
|
+
@block_args = [@block_args]
|
13
|
+
end
|
14
|
+
@block_args << args
|
15
|
+
else
|
16
|
+
@block_args = args
|
17
|
+
end
|
18
|
+
"[rewritten]"
|
19
|
+
end
|
20
|
+
|
21
|
+
describe "rewrite usernames" do #{{{
|
22
|
+
before do
|
23
|
+
@rewritten_text = Twitter::Rewriter.rewrite_usernames_or_lists(original_text, &method(:block))
|
24
|
+
end
|
25
|
+
|
26
|
+
context "username preceded by a space" do
|
27
|
+
def original_text; "hello @jacob"; end
|
28
|
+
|
29
|
+
it "should be rewritten" do
|
30
|
+
@block_args.should == ["@", "jacob", nil]
|
31
|
+
@rewritten_text.should == "hello [rewritten]"
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
context "username at beginning of line" do
|
36
|
+
def original_text; "@jacob you're cool"; end
|
37
|
+
|
38
|
+
it "should be rewritten" do
|
39
|
+
@block_args.should == ["@", "jacob", nil]
|
40
|
+
@rewritten_text.should == "[rewritten] you're cool"
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
context "username preceded by word character" do
|
45
|
+
def original_text; "meet@the beach"; end
|
46
|
+
|
47
|
+
it "should not be rewritten" do
|
48
|
+
@block_args.should be_nil
|
49
|
+
@rewritten_text.should == "meet@the beach"
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
context "username preceded by non-word character" do
|
54
|
+
def original_text; "great.@jacob"; end
|
55
|
+
|
56
|
+
it "should be rewritten" do
|
57
|
+
@block_args.should == ["@", "jacob", nil]
|
58
|
+
@rewritten_text.should == "great.[rewritten]"
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
context "username containing non-word characters" do
|
63
|
+
def original_text; "@jacob&^$%^"; end
|
64
|
+
|
65
|
+
it "should be rewritten" do
|
66
|
+
@block_args.should == ["@", "jacob", nil]
|
67
|
+
@rewritten_text.should == "[rewritten]&^$%^"
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
context "username over twenty characters" do
|
72
|
+
def original_text
|
73
|
+
@twenty_character_username = "zach" * 5
|
74
|
+
"@" + @twenty_character_username + "1"
|
75
|
+
end
|
76
|
+
|
77
|
+
it "should be rewritten" do
|
78
|
+
@block_args.should == ["@", @twenty_character_username, nil]
|
79
|
+
@rewritten_text.should == "[rewritten]1"
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
context "username followed by japanese" do
|
84
|
+
def original_text; "@jacobの"; end
|
85
|
+
|
86
|
+
it "should be rewritten" do
|
87
|
+
@block_args.should == ["@", "jacob", nil]
|
88
|
+
@rewritten_text.should == "[rewritten]の"
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
context "username preceded by japanese" do
|
93
|
+
def original_text; "あ@jacob"; end
|
94
|
+
|
95
|
+
it "should be rewritten" do
|
96
|
+
@block_args.should == ["@", "jacob", nil]
|
97
|
+
@rewritten_text.should == "あ[rewritten]"
|
98
|
+
end
|
99
|
+
end
|
100
|
+
|
101
|
+
context "username surrounded by japanese" do
|
102
|
+
def original_text; "あ@jacobの"; end
|
103
|
+
|
104
|
+
it "should be rewritten" do
|
105
|
+
@block_args.should == ["@", "jacob", nil]
|
106
|
+
@rewritten_text.should == "あ[rewritten]の"
|
107
|
+
end
|
108
|
+
end
|
109
|
+
|
110
|
+
context "username using full-width at-sign" do
|
111
|
+
def original_text
|
112
|
+
"#{[0xFF20].pack('U')}jacob"
|
113
|
+
end
|
114
|
+
|
115
|
+
it "should be rewritten" do
|
116
|
+
@block_args.should == ["@", "jacob", nil]
|
117
|
+
@rewritten_text.should == "[rewritten]"
|
118
|
+
end
|
119
|
+
end
|
120
|
+
end #}}}
|
121
|
+
|
122
|
+
describe "rewrite lists" do #{{{
|
123
|
+
before do
|
124
|
+
@rewritten_text = Twitter::Rewriter.rewrite_usernames_or_lists(original_text, &method(:block))
|
125
|
+
end
|
126
|
+
|
127
|
+
context "slug preceded by a space" do
|
128
|
+
def original_text; "hello @jacob/my-list"; end
|
129
|
+
|
130
|
+
it "should be rewritten" do
|
131
|
+
@block_args.should == ["@", "jacob", "/my-list"]
|
132
|
+
@rewritten_text.should == "hello [rewritten]"
|
133
|
+
end
|
134
|
+
end
|
135
|
+
|
136
|
+
context "username followed by a slash but no list" do
|
137
|
+
def original_text; "hello @jacob/ my-list"; end
|
138
|
+
|
139
|
+
it "should not be rewritten" do
|
140
|
+
@block_args.should == ["@", "jacob", nil]
|
141
|
+
@rewritten_text.should == "hello [rewritten]/ my-list"
|
142
|
+
end
|
143
|
+
end
|
144
|
+
|
145
|
+
context "empty username followed by a list" do
|
146
|
+
def original_text; "hello @/my-list"; end
|
147
|
+
|
148
|
+
it "should not be rewritten" do
|
149
|
+
@block_args.should be_nil
|
150
|
+
@rewritten_text.should == "hello @/my-list"
|
151
|
+
end
|
152
|
+
end
|
153
|
+
|
154
|
+
context "list slug at beginning of line" do
|
155
|
+
def original_text; "@jacob/my-list"; end
|
156
|
+
|
157
|
+
it "should be rewritten" do
|
158
|
+
@block_args.should == ["@", "jacob", "/my-list"]
|
159
|
+
@rewritten_text.should == "[rewritten]"
|
160
|
+
end
|
161
|
+
end
|
162
|
+
|
163
|
+
context "username preceded by alpha-numeric character" do
|
164
|
+
def original_text; "meet@jacob/my-list"; end
|
165
|
+
|
166
|
+
it "should not be rewritten" do
|
167
|
+
@block_args.should be_nil
|
168
|
+
@rewritten_text.should == "meet@jacob/my-list"
|
169
|
+
end
|
170
|
+
end
|
171
|
+
|
172
|
+
context "username preceded by non-word character" do
|
173
|
+
def original_text; "great.@jacob/my-list"; end
|
174
|
+
|
175
|
+
it "should be rewritten" do
|
176
|
+
@block_args.should == ["@", "jacob", "/my-list"]
|
177
|
+
@rewritten_text.should == "great.[rewritten]"
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
context "username containing non-word characters" do
|
182
|
+
def original_text; "@jacob/my-list&^$%^"; end
|
183
|
+
|
184
|
+
it "should be rewritten" do
|
185
|
+
@block_args.should == ["@", "jacob", "/my-list"]
|
186
|
+
@rewritten_text.should == "[rewritten]&^$%^"
|
187
|
+
end
|
188
|
+
end
|
189
|
+
|
190
|
+
context "username over twenty characters" do
|
191
|
+
def original_text
|
192
|
+
@twentyfive_character_list = "a" * 25
|
193
|
+
"@jacob/#{@twentyfive_character_list}12345"
|
194
|
+
end
|
195
|
+
|
196
|
+
it "should be rewritten" do
|
197
|
+
@block_args.should == ["@", "jacob", "/#{@twentyfive_character_list}"]
|
198
|
+
@rewritten_text.should == "[rewritten]12345"
|
199
|
+
end
|
200
|
+
end
|
201
|
+
end #}}}
|
202
|
+
|
203
|
+
describe "rewrite hashtags" do #{{{
|
204
|
+
before do
|
205
|
+
@rewritten_text = Twitter::Rewriter.rewrite_hashtags(original_text, &method(:block))
|
206
|
+
end
|
207
|
+
|
208
|
+
context "with an all numeric hashtag" do
|
209
|
+
def original_text; "#123"; end
|
210
|
+
|
211
|
+
it "should not be rewritten" do
|
212
|
+
@block_args.should be_nil
|
213
|
+
@rewritten_text.should == "#123"
|
214
|
+
end
|
215
|
+
end
|
216
|
+
|
217
|
+
context "with a hashtag with alphanumeric characters" do
|
218
|
+
def original_text; "#ab1d"; end
|
219
|
+
|
220
|
+
it "should be rewritten" do
|
221
|
+
@block_args.should == ["#", "ab1d"]
|
222
|
+
@rewritten_text.should == "[rewritten]"
|
223
|
+
end
|
224
|
+
end
|
225
|
+
|
226
|
+
context "with a hashtag with underscores" do
|
227
|
+
def original_text; "#a_b_c_d"; end
|
228
|
+
|
229
|
+
it "should be rewritten" do
|
230
|
+
@block_args.should == ["#", "a_b_c_d"]
|
231
|
+
@rewritten_text.should == "[rewritten]"
|
232
|
+
end
|
233
|
+
end
|
234
|
+
|
235
|
+
context "with a hashtag that is preceded by a word character" do
|
236
|
+
def original_text; "ab#cd"; end
|
237
|
+
|
238
|
+
it "should not be rewritten" do
|
239
|
+
@block_args.should be_nil
|
240
|
+
@rewritten_text.should == "ab#cd"
|
241
|
+
end
|
242
|
+
end
|
243
|
+
|
244
|
+
context "with a page anchor in a url" do
|
245
|
+
def original_text; "Here's my url: http://foobar.com/#home"; end
|
246
|
+
|
247
|
+
it "should not link the hashtag" do
|
248
|
+
@block_args.should be_nil
|
249
|
+
@rewritten_text.should == "Here's my url: http://foobar.com/#home"
|
250
|
+
end
|
251
|
+
end
|
252
|
+
|
253
|
+
context "with a hashtag that starts with a number but has word characters" do
|
254
|
+
def original_text; "#2ab"; end
|
255
|
+
|
256
|
+
it "should be rewritten" do
|
257
|
+
@block_args.should == ["#", "2ab"]
|
258
|
+
@rewritten_text.should == "[rewritten]"
|
259
|
+
end
|
260
|
+
end
|
261
|
+
|
262
|
+
context "with multiple valid hashtags" do
|
263
|
+
def original_text; "I'm frickin' awesome #ab #cd #ef"; end
|
264
|
+
|
265
|
+
it "rewrites each hashtag" do
|
266
|
+
@block_args.should == [["#", "ab"], ["#", "cd"], ["#", "ef"]]
|
267
|
+
@rewritten_text.should == "I'm frickin' awesome [rewritten] [rewritten] [rewritten]"
|
268
|
+
end
|
269
|
+
end
|
270
|
+
|
271
|
+
context "with a hashtag preceded by a ." do
|
272
|
+
def original_text; "ok, great.#abc"; end
|
273
|
+
|
274
|
+
it "should be rewritten" do
|
275
|
+
@block_args.should == ["#", "abc"]
|
276
|
+
@rewritten_text.should == "ok, great.[rewritten]"
|
277
|
+
end
|
278
|
+
end
|
279
|
+
|
280
|
+
context "with a hashtag preceded by a &" do
|
281
|
+
def original_text; "&#nbsp;"; end
|
282
|
+
|
283
|
+
it "should not be rewritten" do
|
284
|
+
@block_args.should be_nil
|
285
|
+
@rewritten_text.should == "&#nbsp;"
|
286
|
+
end
|
287
|
+
end
|
288
|
+
|
289
|
+
context "with a hashtag that ends in an !" do
|
290
|
+
def original_text; "#great!"; end
|
291
|
+
|
292
|
+
it "should be rewritten, but should not include the !" do
|
293
|
+
@block_args.should == ["#", "great"];
|
294
|
+
@rewritten_text.should == "[rewritten]!"
|
295
|
+
end
|
296
|
+
end
|
297
|
+
|
298
|
+
context "with a hashtag followed by Japanese" do
|
299
|
+
def original_text; "#twj_devの"; end
|
300
|
+
|
301
|
+
it "should be rewritten" do
|
302
|
+
@block_args.should == ["#", "twj_devの"];
|
303
|
+
@rewritten_text.should == "[rewritten]"
|
304
|
+
end
|
305
|
+
end
|
306
|
+
|
307
|
+
context "with a hashtag preceded by a full-width space" do
|
308
|
+
def original_text; "#{[0x3000].pack('U')}#twj_dev"; end
|
309
|
+
|
310
|
+
it "should be rewritten" do
|
311
|
+
@block_args.should == ["#", "twj_dev"];
|
312
|
+
@rewritten_text.should == " [rewritten]"
|
313
|
+
end
|
314
|
+
end
|
315
|
+
|
316
|
+
context "with a hashtag followed by a full-width space" do
|
317
|
+
def original_text; "#twj_dev#{[0x3000].pack('U')}"; end
|
318
|
+
|
319
|
+
it "should be rewritten" do
|
320
|
+
@block_args.should == ["#", "twj_dev"];
|
321
|
+
@rewritten_text.should == "[rewritten] "
|
322
|
+
end
|
323
|
+
end
|
324
|
+
|
325
|
+
context "with a hashtag using full-width hash" do
|
326
|
+
def original_text; "#{[0xFF03].pack('U')}twj_dev"; end
|
327
|
+
|
328
|
+
it "should be rewritten" do
|
329
|
+
@block_args.should == ["#", "twj_dev"];
|
330
|
+
@rewritten_text.should == "[rewritten]"
|
331
|
+
end
|
332
|
+
end
|
333
|
+
|
334
|
+
context "with a hashtag containing an accented latin character" do
|
335
|
+
def original_text
|
336
|
+
# the hashtag is #éhashtag
|
337
|
+
"##{[0x00e9].pack('U')}hashtag"
|
338
|
+
end
|
339
|
+
|
340
|
+
it "should be rewritten" do
|
341
|
+
@block_args.should == ["#", "éhashtag"];
|
342
|
+
@rewritten_text.should == "[rewritten]"
|
343
|
+
end
|
344
|
+
end
|
345
|
+
end #}}}
|
346
|
+
|
347
|
+
describe "rewrite urls" do #{{{
|
348
|
+
def url; "http://www.google.com"; end
|
349
|
+
|
350
|
+
before do
|
351
|
+
@rewritten_text = Twitter::Rewriter.rewrite_urls(original_text, &method(:block))
|
352
|
+
end
|
353
|
+
|
354
|
+
context "when embedded in plain text" do
|
355
|
+
def original_text; "On my search engine #{url} I found good links."; end
|
356
|
+
|
357
|
+
it "should be rewritten" do
|
358
|
+
@block_args.should == [url];
|
359
|
+
@rewritten_text.should == "On my search engine [rewritten] I found good links."
|
360
|
+
end
|
361
|
+
end
|
362
|
+
|
363
|
+
context "when surrounded by Japanese;" do
|
364
|
+
def original_text; "いまなにしてる#{url}いまなにしてる"; end
|
365
|
+
|
366
|
+
it "should be rewritten" do
|
367
|
+
@block_args.should == [url];
|
368
|
+
@rewritten_text.should == "いまなにしてる[rewritten]いまなにしてる"
|
369
|
+
end
|
370
|
+
end
|
371
|
+
|
372
|
+
context "with a path surrounded by parentheses;" do
|
373
|
+
def original_text; "I found a neatness (#{url})"; end
|
374
|
+
|
375
|
+
it "should be rewritten" do
|
376
|
+
@block_args.should == [url];
|
377
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
378
|
+
end
|
379
|
+
|
380
|
+
context "when the URL ends with a slash;" do
|
381
|
+
def url; "http://www.google.com/"; end
|
382
|
+
|
383
|
+
it "should be rewritten" do
|
384
|
+
@block_args.should == [url];
|
385
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
386
|
+
end
|
387
|
+
end
|
388
|
+
|
389
|
+
context "when the URL has a path;" do
|
390
|
+
def url; "http://www.google.com/fsdfasdf"; end
|
391
|
+
|
392
|
+
it "should be rewritten" do
|
393
|
+
@block_args.should == [url];
|
394
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
395
|
+
end
|
396
|
+
end
|
397
|
+
end
|
398
|
+
|
399
|
+
context "when path contains parens" do
|
400
|
+
def original_text; "I found a neatness (#{url})"; end
|
401
|
+
|
402
|
+
it "should be rewritten" do
|
403
|
+
@block_args.should == [url];
|
404
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
405
|
+
end
|
406
|
+
|
407
|
+
context "wikipedia" do
|
408
|
+
def url; "http://en.wikipedia.org/wiki/Madonna_(artist)"; end
|
409
|
+
|
410
|
+
it "should be rewritten" do
|
411
|
+
@block_args.should == [url];
|
412
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
413
|
+
end
|
414
|
+
end
|
415
|
+
|
416
|
+
context "IIS session" do
|
417
|
+
def url; "http://msdn.com/S(deadbeef)/page.htm"; end
|
418
|
+
|
419
|
+
it "should be rewritten" do
|
420
|
+
@block_args.should == [url];
|
421
|
+
@rewritten_text.should == "I found a neatness ([rewritten])"
|
422
|
+
end
|
423
|
+
end
|
424
|
+
|
425
|
+
context "unbalanced parens" do
|
426
|
+
def url; "http://example.com/i_has_a_("; end
|
427
|
+
|
428
|
+
it "should be rewritten" do
|
429
|
+
@block_args.should == ["http://example.com/i_has_a_"];
|
430
|
+
@rewritten_text.should == "I found a neatness ([rewritten]()"
|
431
|
+
end
|
432
|
+
end
|
433
|
+
|
434
|
+
context "balanced parens with a double quote inside" do
|
435
|
+
def url; "http://foo.bar/foo_(\")_bar" end
|
436
|
+
|
437
|
+
it "should be rewritten" do
|
438
|
+
@block_args.should == ["http://foo.bar/foo_"];
|
439
|
+
@rewritten_text.should == "I found a neatness ([rewritten](\")_bar)"
|
440
|
+
end
|
441
|
+
end
|
442
|
+
|
443
|
+
context "balanced parens hiding XSS" do
|
444
|
+
def url; 'http://x.xx/("style="color:red"onmouseover="alert(1)' end
|
445
|
+
|
446
|
+
it "should be rewritten" do
|
447
|
+
@block_args.should == ["http://x.xx/"];
|
448
|
+
@rewritten_text.should == 'I found a neatness ([rewritten]("style="color:red"onmouseover="alert(1))'
|
449
|
+
end
|
450
|
+
end
|
451
|
+
end
|
452
|
+
|
453
|
+
context "when preceded by a :" do
|
454
|
+
def original_text; "Check this out @hoverbird:#{url}"; end
|
455
|
+
|
456
|
+
it "should be rewritten" do
|
457
|
+
@block_args.should == [url];
|
458
|
+
@rewritten_text.should == "Check this out @hoverbird:[rewritten]"
|
459
|
+
end
|
460
|
+
end
|
461
|
+
|
462
|
+
context "with a URL ending in allowed punctuation" do
|
463
|
+
it "does not consume ending punctuation" do
|
464
|
+
%w| ? ! , . : ; ] ) } = \ ' |.each do |char|
|
465
|
+
Twitter::Rewriter.rewrite_urls("#{url}#{char}") do |url|
|
466
|
+
url.should == url; "[rewritten]"
|
467
|
+
end.should == "[rewritten]#{char}"
|
468
|
+
end
|
469
|
+
end
|
470
|
+
end
|
471
|
+
|
472
|
+
context "with a URL preceded in forbidden characters" do
|
473
|
+
it "should not be rewritten" do
|
474
|
+
%w| \ ' / ! = |.each do |char|
|
475
|
+
Twitter::Rewriter.rewrite_urls("#{char}#{url}") do |url|
|
476
|
+
"[rewritten]" # should not be called here.
|
477
|
+
end.should == "#{char}#{url}"
|
478
|
+
end
|
479
|
+
end
|
480
|
+
end
|
481
|
+
|
482
|
+
context "when embedded in a link tag" do
|
483
|
+
def original_text; "<link rel='true'>#{url}</link>"; end
|
484
|
+
|
485
|
+
it "should be rewritten" do
|
486
|
+
@block_args.should == [url];
|
487
|
+
@rewritten_text.should == "<link rel='true'>[rewritten]</link>"
|
488
|
+
end
|
489
|
+
end
|
490
|
+
|
491
|
+
context "with multiple URLs" do
|
492
|
+
def original_text; "http://www.links.org link at start of page, link at end http://www.foo.org"; end
|
493
|
+
|
494
|
+
it "should autolink each one" do
|
495
|
+
@block_args.should == [["http://www.links.org"], ["http://www.foo.org"]];
|
496
|
+
@rewritten_text.should == "[rewritten] link at start of page, link at end [rewritten]"
|
497
|
+
end
|
498
|
+
end
|
499
|
+
|
500
|
+
context "with multiple URLs in different formats" do
|
501
|
+
def original_text; "http://foo.com https://bar.com http://mail.foobar.org"; end
|
502
|
+
|
503
|
+
it "should autolink each one, in the proper order" do
|
504
|
+
@block_args.should == [["http://foo.com"], ["https://bar.com"], ["http://mail.foobar.org"]];
|
505
|
+
@rewritten_text.should == "[rewritten] [rewritten] [rewritten]"
|
506
|
+
end
|
507
|
+
end
|
508
|
+
|
509
|
+
context "with a URL having a long TLD" do
|
510
|
+
def original_text; "Yahoo integriert Facebook http://golem.mobi/0912/71607.html"; end
|
511
|
+
|
512
|
+
it "should autolink it" do
|
513
|
+
@block_args.should == ["http://golem.mobi/0912/71607.html"]
|
514
|
+
@rewritten_text.should == "Yahoo integriert Facebook [rewritten]"
|
515
|
+
end
|
516
|
+
end
|
517
|
+
|
518
|
+
context "with a url lacking the protocol" do
|
519
|
+
def original_text; "I like www.foobar.com dudes"; end
|
520
|
+
|
521
|
+
it "does not link at all" do
|
522
|
+
@block_args.should be_nil
|
523
|
+
@rewritten_text.should == "I like www.foobar.com dudes"
|
524
|
+
end
|
525
|
+
end
|
526
|
+
|
527
|
+
context "with a @ in a URL" do
|
528
|
+
context "with XSS attack" do
|
529
|
+
def original_text; 'http://x.xx/@"style="color:pink"onmouseover=alert(1)//'; end
|
530
|
+
|
531
|
+
it "should not allow XSS follwing @" do
|
532
|
+
@block_args.should == ["http://x.xx/"]
|
533
|
+
@rewritten_text.should == '[rewritten]@"style="color:pink"onmouseover=alert(1)//'
|
534
|
+
end
|
535
|
+
end
|
536
|
+
|
537
|
+
context "with a username not followed by a /" do
|
538
|
+
def original_text; "http://example.com/@foobar"; end
|
539
|
+
|
540
|
+
it "should link small url and username" do
|
541
|
+
@block_args.should == ["http://example.com/"]
|
542
|
+
@rewritten_text.should == "[rewritten]@foobar"
|
543
|
+
end
|
544
|
+
end
|
545
|
+
|
546
|
+
context "with a username followed by a /" do
|
547
|
+
def original_text; "http://example.com/@foobar/"; end
|
548
|
+
|
549
|
+
it "should not link the username but link full url" do
|
550
|
+
@block_args.should == ["http://example.com/@foobar/"]
|
551
|
+
@rewritten_text.should == "[rewritten]"
|
552
|
+
end
|
553
|
+
end
|
554
|
+
end
|
555
|
+
end #}}}
|
556
|
+
end
|
557
|
+
|
558
|
+
# vim: foldmethod=marker
|