chupa-text-decomposer-html 1.0.1 → 1.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (7) hide show
  1. checksums.yaml +4 -4
  2. data/Rakefile +4 -2
  3. data/chupa-text-decomposer-html.gemspec +4 -4
  4. data/doc/text/news.md +6 -0
  5. data/lib/chupa-text/decomposers/html.rb +121 -8
  6. data/test/test-html.rb +251 -3
  7. metadata +25 -26
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA1:
3
- metadata.gz: 75be13613ba030b332f565e1e569c9e15a75e111
4
- data.tar.gz: 0ad922b353bffb19819340d6ffb70ce739e51fc0
3
+ metadata.gz: '068db7f654ca70a8f65209c3d2f0d2fa1edf45ff'
4
+ data.tar.gz: 715d8630a7e69c100ed38a8bb090c5282b62fe2d
5
5
  SHA512:
6
- metadata.gz: 5f00a62cb2156eab85ab87e4a1f50aee301fe17d831965cc1a2b7fe0b6bbde6b67f8b108a16999d6ecad3df7349b84a1d8ef7103901cfdfde0ba1ad45c5c8235
7
- data.tar.gz: 975b69746801761f2872921e83c95bd1c309f01a6ae9703be404ec81b1b92cb359049dab3aa74cc37d603d0c71734fa30ed29715489298c0c70514f8b7534e6f
6
+ metadata.gz: ab46f697f57427a940bd7968391648f54e2edbfab77974bc651ebe155f8dbfb6bbb9f8922d7153ee306ccb0402d30957a05fefe839437ba3ff28037f9a9e6ab0
7
+ data.tar.gz: 932251f709b54256f6478d4e7103f1b483c9c83166a277c6ee4b67b24c1528389ef1602ec960536de9b727cfcfa771e323d3467e9573911486f752e715ca5fcb
data/Rakefile CHANGED
@@ -1,6 +1,6 @@
1
1
  # -*- mode: ruby; coding: utf-8 -*-
2
2
  #
3
- # Copyright (C) 2013 Kouhei Sutou <kou@clear-code.com>
3
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
4
4
  #
5
5
  # This library is free software; you can redistribute it and/or
6
6
  # modify it under the terms of the GNU Lesser General Public
@@ -34,7 +34,9 @@ end
34
34
  helper.install
35
35
  spec = helper.gemspec
36
36
 
37
- Packnga::DocumentTask.new(spec) do
37
+ Packnga::DocumentTask.new(spec) do |task|
38
+ task.original_language = "en"
39
+ task.translate_language = "ja"
38
40
  end
39
41
 
40
42
  Packnga::ReleaseTask.new(spec) do
data/chupa-text-decomposer-html.gemspec CHANGED
@@ -1,6 +1,6 @@
1
- # -*- mode: ruby; coding: utf-8 -*-
1
+ # -*- ruby -*-
2
2
  #
3
- # Copyright (C) 2013 Kouhei Sutou <kou@clear-code.com>
3
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
4
4
  #
5
5
  # This library is free software; you can redistribute it and/or
6
6
  # modify it under the terms of the GNU Lesser General Public
@@ -22,7 +22,7 @@ end
22
22
 
23
23
  Gem::Specification.new do |spec|
24
24
  spec.name = "chupa-text-decomposer-html"
25
- spec.version = "1.0.1"
25
+ spec.version = "1.0.2"
26
26
  spec.homepage = "https://github.com/ranguba/chupa-text-decomposer-html"
27
27
  spec.authors = ["Kouhei Sutou"]
28
28
  spec.email = ["kou@clear-code.com"]
@@ -31,7 +31,7 @@ Gem::Specification.new do |spec|
31
31
  description = clean_white_space.call(entries[entries.index("Description") + 1])
32
32
  spec.summary = description.split(/\n\n+/, 2).first
33
33
  spec.description = description
34
- spec.license = "LGPLv2.1 or later"
34
+ spec.license = "LGPL-2.1+"
35
35
  spec.files = ["#{spec.name}.gemspec"]
36
36
  spec.files += ["README.md", "LICENSE.txt", "Rakefile", "Gemfile"]
37
37
  spec.files += [".yardopts"]
data/doc/text/news.md CHANGED
@@ -1,5 +1,11 @@
1
1
  # News
2
2
 
3
+ ## 1.0.2: 2017-07-05
4
+
5
+ * Support content based HTML detection.
6
+
7
+ * Ignore common contents.
8
+
3
9
  ## 1.0.1: 2014-02-18
4
10
 
5
11
  * Support chupa-text 1.0.4.
data/lib/chupa-text/decomposers/html.rb CHANGED
@@ -1,4 +1,4 @@
1
- # Copyright (C) 2013 Kouhei Sutou <kou@clear-code.com>
1
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
2
2
  #
3
3
  # This library is free software; you can redistribute it and/or
4
4
  # modify it under the terms of the GNU Lesser General Public
@@ -28,8 +28,16 @@ module ChupaText
28
28
  "application/xhtml+xml",
29
29
  ]
30
30
  def target?(data)
31
- TARGET_EXTENSIONS.include?(data.extension) or
32
- TARGET_MIME_TYPES.include?(data.mime_type)
31
+ return true if TARGET_EXTENSIONS.include?(data.extension)
32
+ return true if TARGET_MIME_TYPES.include?(data.mime_type)
33
+
34
+ body = data.body
35
+ return false if body.nil?
36
+
37
+ return true if body.start_with?("<!DOCTYPE html ")
38
+ return true if body.start_with?("<html")
39
+
40
+ false
33
41
  end
34
42
 
35
43
  def decompose(data)
@@ -37,13 +45,11 @@ module ChupaText
37
45
  doc = Nokogiri::HTML.parse(html, nil, guess_encoding(html))
38
46
  body_element = (doc % "body")
39
47
  if body_element
40
- body = body_element.text.gsub(/^\s+|\s+$/, '')
48
+ body = extract_text(body_element, "").scrub.gsub(/^\s+|\s+$/, '')
41
49
  else
42
50
  body = ""
43
51
  end
44
- decomposed_data = TextData.new(body)
45
- decomposed_data.uri = data.uri
46
-
52
+ decomposed_data = TextData.new(body, :source_data => data)
47
53
  attributes = decomposed_data.attributes
48
54
  title_element = (doc % "head/title")
49
55
  attributes.title = title_element.text if title_element
@@ -55,6 +61,10 @@ module ChupaText
55
61
 
56
62
  private
57
63
  def guess_encoding(text)
64
+ unless text.encoding.ascii_compatible?
65
+ return text.encoding.name
66
+ end
67
+
58
68
  case text
59
69
  when /\A<\?xml.+?encoding=(['"])([a-zA-Z0-9_-]+)\1/
60
70
  $2
@@ -72,7 +82,11 @@ module ChupaText
72
82
  charset = $2
73
83
  normalize_charset(charset)
74
84
  else
75
- guess_encoding_nkf(text)
85
+ if text.encoding != Encoding::ASCII_8BIT and text.valid_encoding?
86
+ text.encoding.to_s
87
+ else
88
+ guess_encoding_nkf(text)
89
+ end
76
90
  end
77
91
  end
78
92
 
@@ -90,6 +104,105 @@ module ChupaText
90
104
  def guess_encoding_nkf(text)
91
105
  NKF.guess(text).name
92
106
  end
107
+
108
+ def extract_text(element, text)
109
+ name = element.name.downcase
110
+ classes = (element["class"] || "").split
111
+ return text if noindex_element?(element, name, classes)
112
+ return text if header_element?(element, name, classes)
113
+ return text if footer_element?(element, name, classes)
114
+ return text if navigation_element?(element, name, classes)
115
+
116
+ element.children.each do |child|
117
+ case child
118
+ when Nokogiri::XML::Text
119
+ text << child.text
120
+ when Nokogiri::XML::Element
121
+ extract_text(child, text)
122
+ end
123
+ end
124
+
125
+ text
126
+ end
127
+
128
+ def noindex_element?(element, name, classes)
129
+ case name
130
+ when "script", "noscript", "link", "style"
131
+ return true
132
+ end
133
+
134
+ classes.each do |klass|
135
+ case klass
136
+ when "noindex", "robots-noindex"
137
+ return true
138
+ end
139
+ end
140
+
141
+ false
142
+ end
143
+
144
+ def header_element?(element, name, classes)
145
+ case name
146
+ when "header", "nav"
147
+ return true
148
+ end
149
+
150
+ classes.each do |klass|
151
+ case klass
152
+ when "header"
153
+ return true
154
+ end
155
+ end
156
+
157
+ case element["id"]
158
+ when "header"
159
+ return true
160
+ end
161
+
162
+ false
163
+ end
164
+
165
+ def footer_element?(element, name, classes)
166
+ case name
167
+ when "footer"
168
+ return true
169
+ end
170
+
171
+ classes.each do |klass|
172
+ case klass
173
+ when "footer"
174
+ return true
175
+ end
176
+ end
177
+
178
+ case element["id"]
179
+ when "footer"
180
+ return true
181
+ end
182
+
183
+ false
184
+ end
185
+
186
+ def navigation_element?(element, name, classes)
187
+ case name
188
+ when "nav"
189
+ return true
190
+ end
191
+
192
+ classes.each do |klass|
193
+ case klass
194
+ when "nav", "menu"
195
+ return true
196
+ end
197
+ end
198
+
199
+ case element["id"]
200
+ when "nav", "menu"
201
+ return true
202
+ end
203
+
204
+ false
205
+ end
93
206
  end
94
207
  end
95
208
  end
data/test/test-html.rb CHANGED
@@ -1,4 +1,4 @@
1
- # Copyright (C) 2013-2014 Kouhei Sutou <kou@clear-code.com>
1
+ # Copyright (C) 2013-2017 Kouhei Sutou <kou@clear-code.com>
2
2
  #
3
3
  # This library is free software; you can redistribute it and/or
4
4
  # modify it under the terms of the GNU Lesser General Public
@@ -51,6 +51,12 @@ class TestHTML < Test::Unit::TestCase
51
51
  def test_txt
52
52
  assert_false(@decomposer.target?(create_data("index.txt")))
53
53
  end
54
+
55
+ def test_php
56
+ assert do
57
+ not @decomposer.target?(create_data("index.php"))
58
+ end
59
+ end
54
60
  end
55
61
 
56
62
  sub_test_case("mime-type") do
@@ -72,6 +78,26 @@ class TestHTML < Test::Unit::TestCase
72
78
  assert_false(@decomposer.target?(create_data("text/plain")))
73
79
  end
74
80
  end
81
+
82
+ sub_test_case("content") do
83
+ def create_data(body)
84
+ data = ChupaText::Data.new
85
+ data.body = body
86
+ data
87
+ end
88
+
89
+ def test_doctype_html
90
+ assert do
91
+ @decomposer.target?(create_data("<!DOCTYPE html "))
92
+ end
93
+ end
94
+
95
+ def test_html
96
+ assert do
97
+ @decomposer.target?(create_data("<html"))
98
+ end
99
+ end
100
+ end
75
101
  end
76
102
 
77
103
  sub_test_case("decompose") do
@@ -138,12 +164,12 @@ class TestHTML < Test::Unit::TestCase
138
164
 
139
165
  sub_test_case("detect") do
140
166
  def test_nothing
141
- @data.body = <<-HTML
167
+ @data.body = <<-HTML.force_encoding("UTF-8")
142
168
  <html>
143
169
  <body>Hello</body>
144
170
  </html>
145
171
  HTML
146
- assert_equal([Encoding::US_ASCII], decompose(@data))
172
+ assert_equal([Encoding::UTF_8], decompose(@data))
147
173
  end
148
174
 
149
175
  def test_xml_declaration
@@ -181,6 +207,44 @@ class TestHTML < Test::Unit::TestCase
181
207
  HTML5
182
208
  assert_equal([Encoding::EUC_JP], decompose(@data))
183
209
  end
210
+
211
+ sub_test_case("not ascii_compatible?") do
212
+ def test_iso_2022_jp
213
+ @data.body = <<-ISO_2022_JP_HTML.encode("ISO-2022-JP")
214
+ <html>
215
+ <head>
216
+ <title>タイトル</title>
217
+ </head>
218
+ <body>Hello</body>
219
+ </html>
220
+ ISO_2022_JP_HTML
221
+ assert_equal([Encoding::ISO_2022_JP], decompose(@data))
222
+ end
223
+
224
+ def test_utf_32
225
+ @data.body = <<-UTF_32_HTML.encode("UTF-32")
226
+ <html>
227
+ <head>
228
+ <title>タイトル</title>
229
+ </head>
230
+ <body>Hello</body>
231
+ </html>
232
+ UTF_32_HTML
233
+ assert_equal([Encoding::UTF_32], decompose(@data))
234
+ end
235
+
236
+ def test_koi8_r
237
+ @data.body = <<-KOI8_R_HTML.encode("KOI8-R")
238
+ <html>
239
+ <head>
240
+ <title>название</title>
241
+ </head>
242
+ <body>Hello</body>
243
+ </html>
244
+ KOI8_R_HTML
245
+ assert_equal([Encoding::KOI8_R], decompose(@data))
246
+ end
247
+ end
184
248
  end
185
249
 
186
250
  sub_test_case("normalize") do
@@ -209,5 +273,189 @@ class TestHTML < Test::Unit::TestCase
209
273
  end
210
274
  end
211
275
  end
276
+
277
+ sub_test_case("body") do
278
+ def normalize_decomposed_data(decomposed_data)
279
+ decomposed_data.body
280
+ end
281
+
282
+ sub_test_case("noindex") do
283
+ def test_script
284
+ @data.body = <<-HTML
285
+ <html>
286
+ <body>Before<script>var x;</script>After</body>
287
+ </html>
288
+ HTML
289
+ assert_equal(["BeforeAfter"],
290
+ decompose(@data))
291
+ end
292
+
293
+ def test_noscript
294
+ @data.body = <<-HTML
295
+ <html>
296
+ <body>Before<noscript>Enable JavaScript!</noscript>After</body>
297
+ </html>
298
+ HTML
299
+ assert_equal(["BeforeAfter"],
300
+ decompose(@data))
301
+ end
302
+
303
+ def test_link
304
+ @data.body = <<-HTML
305
+ <html>
306
+ <body>Before<link rel="stylehseet">After</body>
307
+ </html>
308
+ HTML
309
+ assert_equal(["BeforeAfter"],
310
+ decompose(@data))
311
+ end
312
+
313
+ def test_style
314
+ @data.body = <<-HTML
315
+ <html>
316
+ <body>Before<style>a {color: "red";}</style>After</body>
317
+ </html>
318
+ HTML
319
+ assert_equal(["BeforeAfter"],
320
+ decompose(@data))
321
+ end
322
+
323
+ def test_noindex
324
+ @data.body = <<-HTML
325
+ <html>
326
+ <body>Before<div class="noindex">header</div>After</body>
327
+ </html>
328
+ HTML
329
+ assert_equal(["BeforeAfter"],
330
+ decompose(@data))
331
+ end
332
+
333
+ def test_robots_noindex
334
+ @data.body = <<-HTML
335
+ <html>
336
+ <body>Before<div class="robots-noindex">header</div>After</body>
337
+ </html>
338
+ HTML
339
+ assert_equal(["BeforeAfter"],
340
+ decompose(@data))
341
+ end
342
+ end
343
+
344
+ sub_test_case("header") do
345
+ def test_tag
346
+ @data.body = <<-HTML
347
+ <html>
348
+ <body>Before<header>header</header>After</body>
349
+ </html>
350
+ HTML
351
+ assert_equal(["BeforeAfter"],
352
+ decompose(@data))
353
+ end
354
+
355
+ def test_class
356
+ @data.body = <<-HTML
357
+ <html>
358
+ <body>Before<div class="header">header</div>After</body>
359
+ </html>
360
+ HTML
361
+ assert_equal(["BeforeAfter"],
362
+ decompose(@data))
363
+ end
364
+
365
+ def test_id
366
+ @data.body = <<-HTML
367
+ <html>
368
+ <body>Before<div id="header">header</div>After</body>
369
+ </html>
370
+ HTML
371
+ assert_equal(["BeforeAfter"],
372
+ decompose(@data))
373
+ end
374
+ end
375
+
376
+ sub_test_case("footer") do
377
+ def test_tag
378
+ @data.body = <<-HTML
379
+ <html>
380
+ <body>Before<footer>footer</footer>After</body>
381
+ </html>
382
+ HTML
383
+ assert_equal(["BeforeAfter"],
384
+ decompose(@data))
385
+ end
386
+
387
+ def test_class
388
+ @data.body = <<-HTML
389
+ <html>
390
+ <body>Before<div class="footer">footer</div>After</body>
391
+ </html>
392
+ HTML
393
+ assert_equal(["BeforeAfter"],
394
+ decompose(@data))
395
+ end
396
+
397
+ def test_id
398
+ @data.body = <<-HTML
399
+ <html>
400
+ <body>Before<div id="footer">footer</div>After</body>
401
+ </html>
402
+ HTML
403
+ assert_equal(["BeforeAfter"],
404
+ decompose(@data))
405
+ end
406
+ end
407
+
408
+ sub_test_case("navigation") do
409
+ def test_nav_tag
410
+ @data.body = <<-HTML
411
+ <html>
412
+ <body>Before<nav>nav</nav>After</body>
413
+ </html>
414
+ HTML
415
+ assert_equal(["BeforeAfter"],
416
+ decompose(@data))
417
+ end
418
+
419
+ def test_nav_class
420
+ @data.body = <<-HTML
421
+ <html>
422
+ <body>Before<div class="nav">nav</div>After</body>
423
+ </html>
424
+ HTML
425
+ assert_equal(["BeforeAfter"],
426
+ decompose(@data))
427
+ end
428
+
429
+ def test_menu_class
430
+ @data.body = <<-HTML
431
+ <html>
432
+ <body>Before<div class="menu">nav</div>After</body>
433
+ </html>
434
+ HTML
435
+ assert_equal(["BeforeAfter"],
436
+ decompose(@data))
437
+ end
438
+
439
+ def test_nav_id
440
+ @data.body = <<-HTML
441
+ <html>
442
+ <body>Before<div id="nav">nav</div>After</body>
443
+ </html>
444
+ HTML
445
+ assert_equal(["BeforeAfter"],
446
+ decompose(@data))
447
+ end
448
+
449
+ def test_menu_id
450
+ @data.body = <<-HTML
451
+ <html>
452
+ <body>Before<div id="menu">nav</div>After</body>
453
+ </html>
454
+ HTML
455
+ assert_equal(["BeforeAfter"],
456
+ decompose(@data))
457
+ end
458
+ end
459
+ end
212
460
  end
213
461
  end
metadata CHANGED
@@ -1,111 +1,111 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: chupa-text-decomposer-html
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.1
4
+ version: 1.0.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Kouhei Sutou
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2014-02-17 00:00:00.000000000 Z
11
+ date: 2017-07-05 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: chupa-text
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
- - - '>='
17
+ - - ">="
18
18
  - !ruby/object:Gem::Version
19
19
  version: '0'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
- - - '>='
24
+ - - ">="
25
25
  - !ruby/object:Gem::Version
26
26
  version: '0'
27
27
  - !ruby/object:Gem::Dependency
28
28
  name: nokogiri
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
- - - '>='
31
+ - - ">="
32
32
  - !ruby/object:Gem::Version
33
33
  version: '0'
34
34
  type: :runtime
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
- - - '>='
38
+ - - ">="
39
39
  - !ruby/object:Gem::Version
40
40
  version: '0'
41
41
  - !ruby/object:Gem::Dependency
42
42
  name: bundler
43
43
  requirement: !ruby/object:Gem::Requirement
44
44
  requirements:
45
- - - '>='
45
+ - - ">="
46
46
  - !ruby/object:Gem::Version
47
47
  version: '0'
48
48
  type: :development
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
- - - '>='
52
+ - - ">="
53
53
  - !ruby/object:Gem::Version
54
54
  version: '0'
55
55
  - !ruby/object:Gem::Dependency
56
56
  name: rake
57
57
  requirement: !ruby/object:Gem::Requirement
58
58
  requirements:
59
- - - '>='
59
+ - - ">="
60
60
  - !ruby/object:Gem::Version
61
61
  version: '0'
62
62
  type: :development
63
63
  prerelease: false
64
64
  version_requirements: !ruby/object:Gem::Requirement
65
65
  requirements:
66
- - - '>='
66
+ - - ">="
67
67
  - !ruby/object:Gem::Version
68
68
  version: '0'
69
69
  - !ruby/object:Gem::Dependency
70
70
  name: test-unit
71
71
  requirement: !ruby/object:Gem::Requirement
72
72
  requirements:
73
- - - '>='
73
+ - - ">="
74
74
  - !ruby/object:Gem::Version
75
75
  version: '0'
76
76
  type: :development
77
77
  prerelease: false
78
78
  version_requirements: !ruby/object:Gem::Requirement
79
79
  requirements:
80
- - - '>='
80
+ - - ">="
81
81
  - !ruby/object:Gem::Version
82
82
  version: '0'
83
83
  - !ruby/object:Gem::Dependency
84
84
  name: packnga
85
85
  requirement: !ruby/object:Gem::Requirement
86
86
  requirements:
87
- - - '>='
87
+ - - ">="
88
88
  - !ruby/object:Gem::Version
89
89
  version: '0'
90
90
  type: :development
91
91
  prerelease: false
92
92
  version_requirements: !ruby/object:Gem::Requirement
93
93
  requirements:
94
- - - '>='
94
+ - - ">="
95
95
  - !ruby/object:Gem::Version
96
96
  version: '0'
97
97
  - !ruby/object:Gem::Dependency
98
98
  name: redcarpet
99
99
  requirement: !ruby/object:Gem::Requirement
100
100
  requirements:
101
- - - '>='
101
+ - - ">="
102
102
  - !ruby/object:Gem::Version
103
103
  version: '0'
104
104
  type: :development
105
105
  prerelease: false
106
106
  version_requirements: !ruby/object:Gem::Requirement
107
107
  requirements:
108
- - - '>='
108
+ - - ">="
109
109
  - !ruby/object:Gem::Version
110
110
  version: '0'
111
111
  description: |
@@ -119,19 +119,19 @@ executables: []
119
119
  extensions: []
120
120
  extra_rdoc_files: []
121
121
  files:
122
- - chupa-text-decomposer-html.gemspec
123
- - README.md
122
+ - ".yardopts"
123
+ - Gemfile
124
124
  - LICENSE.txt
125
+ - README.md
125
126
  - Rakefile
126
- - Gemfile
127
- - .yardopts
128
- - lib/chupa-text/decomposers/html.rb
127
+ - chupa-text-decomposer-html.gemspec
129
128
  - doc/text/news.md
129
+ - lib/chupa-text/decomposers/html.rb
130
130
  - test/run-test.rb
131
131
  - test/test-html.rb
132
132
  homepage: https://github.com/ranguba/chupa-text-decomposer-html
133
133
  licenses:
134
- - LGPLv2.1 or later
134
+ - LGPL-2.1+
135
135
  metadata: {}
136
136
  post_install_message:
137
137
  rdoc_options: []
@@ -139,20 +139,19 @@ require_paths:
139
139
  - lib
140
140
  required_ruby_version: !ruby/object:Gem::Requirement
141
141
  requirements:
142
- - - '>='
142
+ - - ">="
143
143
  - !ruby/object:Gem::Version
144
144
  version: '0'
145
145
  required_rubygems_version: !ruby/object:Gem::Requirement
146
146
  requirements:
147
- - - '>='
147
+ - - ">="
148
148
  - !ruby/object:Gem::Version
149
149
  version: '0'
150
150
  requirements: []
151
151
  rubyforge_project:
152
- rubygems_version: 2.0.14
152
+ rubygems_version: 2.5.2
153
153
  signing_key:
154
154
  specification_version: 4
155
155
  summary: This is a ChupaText decomposer plugin for to extract text and meta-data from
156
156
  HTML.
157
157
  test_files: []
158
- has_rdoc: