govuk-diff-pages 0.1.0

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 (34) hide show
  1. checksums.yaml +7 -0
  2. data/.gitignore +33 -0
  3. data/.rspec +2 -0
  4. data/.ruby-version +1 -0
  5. data/Gemfile +5 -0
  6. data/LICENSE.txt +21 -0
  7. data/README.md +75 -0
  8. data/Rakefile +14 -0
  9. data/config/settings.yml +53 -0
  10. data/docs/screenshots/gallery.png +0 -0
  11. data/govuk-diff-pages.gemspec +30 -0
  12. data/lib/govuk/diff/pages.rb +30 -0
  13. data/lib/govuk/diff/pages/app_config.rb +61 -0
  14. data/lib/govuk/diff/pages/format_searcher.rb +37 -0
  15. data/lib/govuk/diff/pages/html_diff.rb +10 -0
  16. data/lib/govuk/diff/pages/html_diff/assets/gallery_template.erb +30 -0
  17. data/lib/govuk/diff/pages/html_diff/assets/html_diff_styles.css +59 -0
  18. data/lib/govuk/diff/pages/html_diff/assets/html_diff_template.erb +31 -0
  19. data/lib/govuk/diff/pages/html_diff/differ.rb +84 -0
  20. data/lib/govuk/diff/pages/html_diff/runner.rb +44 -0
  21. data/lib/govuk/diff/pages/link_checker.rb +47 -0
  22. data/lib/govuk/diff/pages/page_indexer.rb +27 -0
  23. data/lib/govuk/diff/pages/page_searcher.rb +46 -0
  24. data/lib/govuk/diff/pages/tasks/rakefile.rake +93 -0
  25. data/lib/govuk/diff/pages/text_diff.rb +13 -0
  26. data/lib/govuk/diff/pages/text_diff/differ.rb +15 -0
  27. data/lib/govuk/diff/pages/text_diff/formatter.rb +15 -0
  28. data/lib/govuk/diff/pages/text_diff/renderer.rb +23 -0
  29. data/lib/govuk/diff/pages/text_diff/retriever.rb +13 -0
  30. data/lib/govuk/diff/pages/text_diff/runner.rb +41 -0
  31. data/lib/govuk/diff/pages/url_checker.rb +36 -0
  32. data/lib/govuk/diff/pages/version.rb +7 -0
  33. data/lib/govuk/diff/pages/wraith_config_generator.rb +79 -0
  34. metadata +189 -0
@@ -0,0 +1,13 @@
1
+ module Govuk
2
+ module Diff
3
+ module Pages
4
+ module TextDiff
5
+ class Retriever
6
+ def call(url)
7
+ `curl -s #{url}`
8
+ end
9
+ end
10
+ end
11
+ end
12
+ end
13
+ end
@@ -0,0 +1,41 @@
1
+ module Govuk
2
+ module Diff
3
+ module Pages
4
+ module TextDiff
5
+ class Runner
6
+ def initialize(
7
+ pages: Array.new,
8
+ differ: Differ.new,
9
+ retriever: Retriever.new,
10
+ formatter: Formatter.new,
11
+ renderer: Renderer.new,
12
+ left_domain: "www-origin.staging.publishing.service.gov.uk",
13
+ right_domain: "www-origin.publishing.service.gov.uk"
14
+ )
15
+ @pages = pages
16
+ @differ = differ
17
+ @retriever = retriever
18
+ @formatter = formatter
19
+ @renderer = renderer
20
+ @left_domain = left_domain
21
+ @right_domain = right_domain
22
+ end
23
+
24
+ def run
25
+ responses = @pages.inject([]) do |response, page|
26
+ left = @retriever.call("https://#{@left_domain}/#{page}")
27
+ right = @retriever.call("https://#{@right_domain}/#{page}")
28
+
29
+ response << @differ.diff(
30
+ @formatter.call(left),
31
+ @formatter.call(right)
32
+ )
33
+ end
34
+
35
+ @renderer.call(responses)
36
+ end
37
+ end
38
+ end
39
+ end
40
+ end
41
+ end
@@ -0,0 +1,36 @@
1
+ module Govuk
2
+ module Diff
3
+ module Pages
4
+ class UrlChecker
5
+ def initialize(config)
6
+ @config = config
7
+ @govuk_regex = /^#{@config.domains.production}/
8
+ @parameterised_url_regex = /\?/
9
+ @relative_path_regex = /^\//
10
+ end
11
+
12
+ # returns true if non parameterised and a relative or govuk url
13
+ def valid?(url)
14
+ if url =~ @parameterised_url_regex # question mark denotes it has parameters - we don't want those
15
+ false
16
+ elsif url =~ @relative_path_regex # starts with slash - so is a path on govuk website
17
+ true
18
+ elsif url =~ @govuk_regex # gov uk full link
19
+ true
20
+ else
21
+ false
22
+ end
23
+ end
24
+
25
+ def normalize(url)
26
+ raise "Not GOVUK url: #{url}" unless valid?(url)
27
+ url.sub(@govuk_regex, '')
28
+ end
29
+
30
+ def production_url(url)
31
+ "#{@config.domains.production}#{normalize(url)}"
32
+ end
33
+ end
34
+ end
35
+ end
36
+ end
@@ -0,0 +1,7 @@
1
+ module Govuk
2
+ module Diff
3
+ module Pages
4
+ VERSION = "0.1.0"
5
+ end
6
+ end
7
+ end
@@ -0,0 +1,79 @@
1
+ require 'yaml'
2
+ require 'securerandom'
3
+
4
+ module Govuk
5
+ module Diff
6
+ module Pages
7
+ class WraithConfigGenerator
8
+ def initialize
9
+ @config = AppConfig.new
10
+ unless File.exist?(Govuk::Diff::Pages.govuk_pages_file)
11
+ raise "Cannot find file #{Govuk::Diff::Pages.govuk_pages_file}: run 'rake update_page_list' to generate."
12
+ end
13
+ @govuk_pages = YAML.load_file(Govuk::Diff::Pages.govuk_pages_file)
14
+ @url_checker = UrlChecker.new(@config)
15
+ puts "Generating wraith.yaml" if verbose?
16
+ validate_hard_coded_pages
17
+ end
18
+
19
+ def run
20
+ @wraith_config = @config.wraith.to_h
21
+ @wraith_config['paths'] = generate_path_list
22
+ @wraith_config['domains'] = @config.domains.to_h
23
+ @wraith_config['browser'] = { 'phantomjs' => 'phantomjs' }
24
+ @wraith_config['phantomjs_options'] = "--ssl-protocol=tlsv1 --ignore-ssl-errors=true"
25
+ end
26
+
27
+ def save
28
+ File.open(WRAITH_CONFIG_FILE, 'w') do |fp|
29
+ fp.puts YAML.dump(@wraith_config)
30
+ end
31
+ end
32
+
33
+ def verbose?
34
+ @config.verbose
35
+ end
36
+
37
+ private
38
+ def validate_hard_coded_pages
39
+ errors = []
40
+ @config.hard_coded_pages.to_h.each do |_key, url|
41
+ next if @url_checker.valid?(url)
42
+ errors << "ERROR: Invalid url specified in hard coded pages: '#{url}'"
43
+ end
44
+ print_errors_and_exit(errors) unless errors.empty?
45
+ end
46
+
47
+ def print_errors_and_exit(errors)
48
+ raise ArgumentError.new %[Invalid config:\n #{errors.join("\n ")}]
49
+ end
50
+
51
+ def generate_path_list
52
+ paths = generate_paths_from_govuk_pages_file
53
+ paths.merge(@config.hard_coded_pages.to_h)
54
+ end
55
+
56
+ def generate_paths_from_govuk_pages_file
57
+ paths = {}
58
+ @govuk_pages.each do |path|
59
+ next unless @url_checker.valid?(path)
60
+ normalized_path = @url_checker.normalize(path)
61
+ paths[keyify_path(normalized_path)] = normalized_path
62
+ end
63
+ paths
64
+ end
65
+
66
+ def normalize_path(path)
67
+ path.sub(/^#{@config.domains.production}/, '')
68
+ end
69
+
70
+ def keyify_path(path)
71
+ key = path.sub(/^\//, '').tr("/", "_")
72
+ # YAML DUMP doesn't work with very long keys
73
+ key = SecureRandom.uuid if key.size > 100
74
+ key
75
+ end
76
+ end
77
+ end
78
+ end
79
+ end
metadata ADDED
@@ -0,0 +1,189 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: govuk-diff-pages
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Ben Lovell
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2016-03-16 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: diffy
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - "~>"
18
+ - !ruby/object:Gem::Version
19
+ version: '3.1'
20
+ type: :runtime
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - "~>"
25
+ - !ruby/object:Gem::Version
26
+ version: '3.1'
27
+ - !ruby/object:Gem::Dependency
28
+ name: rest-client
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - "~>"
32
+ - !ruby/object:Gem::Version
33
+ version: '1.8'
34
+ type: :runtime
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - "~>"
39
+ - !ruby/object:Gem::Version
40
+ version: '1.8'
41
+ - !ruby/object:Gem::Dependency
42
+ name: nokogiri
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ">="
46
+ - !ruby/object:Gem::Version
47
+ version: '0'
48
+ type: :runtime
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - ">="
53
+ - !ruby/object:Gem::Version
54
+ version: '0'
55
+ - !ruby/object:Gem::Dependency
56
+ name: bundler
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - "~>"
60
+ - !ruby/object:Gem::Version
61
+ version: '1.10'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - "~>"
67
+ - !ruby/object:Gem::Version
68
+ version: '1.10'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rake
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - "~>"
74
+ - !ruby/object:Gem::Version
75
+ version: '10.0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '10.0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: rspec
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - "~>"
88
+ - !ruby/object:Gem::Version
89
+ version: '3.0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - "~>"
95
+ - !ruby/object:Gem::Version
96
+ version: '3.0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: pry-byebug
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: gem_publisher
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - "~>"
116
+ - !ruby/object:Gem::Version
117
+ version: '1.1'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - "~>"
123
+ - !ruby/object:Gem::Version
124
+ version: '1.1'
125
+ description: Diffs web pages both visually and textually.
126
+ email:
127
+ - benjamin.lovell@gmail.com
128
+ executables: []
129
+ extensions: []
130
+ extra_rdoc_files: []
131
+ files:
132
+ - ".gitignore"
133
+ - ".rspec"
134
+ - ".ruby-version"
135
+ - Gemfile
136
+ - Gemfile.lock
137
+ - LICENSE.txt
138
+ - README.md
139
+ - Rakefile
140
+ - config/settings.yml
141
+ - docs/screenshots/gallery.png
142
+ - govuk-diff-pages.gemspec
143
+ - lib/govuk/diff/pages.rb
144
+ - lib/govuk/diff/pages/app_config.rb
145
+ - lib/govuk/diff/pages/format_searcher.rb
146
+ - lib/govuk/diff/pages/html_diff.rb
147
+ - lib/govuk/diff/pages/html_diff/assets/gallery_template.erb
148
+ - lib/govuk/diff/pages/html_diff/assets/html_diff_styles.css
149
+ - lib/govuk/diff/pages/html_diff/assets/html_diff_template.erb
150
+ - lib/govuk/diff/pages/html_diff/differ.rb
151
+ - lib/govuk/diff/pages/html_diff/runner.rb
152
+ - lib/govuk/diff/pages/link_checker.rb
153
+ - lib/govuk/diff/pages/page_indexer.rb
154
+ - lib/govuk/diff/pages/page_searcher.rb
155
+ - lib/govuk/diff/pages/tasks/rakefile.rake
156
+ - lib/govuk/diff/pages/text_diff.rb
157
+ - lib/govuk/diff/pages/text_diff/differ.rb
158
+ - lib/govuk/diff/pages/text_diff/formatter.rb
159
+ - lib/govuk/diff/pages/text_diff/renderer.rb
160
+ - lib/govuk/diff/pages/text_diff/retriever.rb
161
+ - lib/govuk/diff/pages/text_diff/runner.rb
162
+ - lib/govuk/diff/pages/url_checker.rb
163
+ - lib/govuk/diff/pages/version.rb
164
+ - lib/govuk/diff/pages/wraith_config_generator.rb
165
+ homepage: https://github.com/alphagov/govuk-diff-pages
166
+ licenses:
167
+ - MIT
168
+ metadata: {}
169
+ post_install_message:
170
+ rdoc_options: []
171
+ require_paths:
172
+ - lib
173
+ required_ruby_version: !ruby/object:Gem::Requirement
174
+ requirements:
175
+ - - ">="
176
+ - !ruby/object:Gem::Version
177
+ version: '0'
178
+ required_rubygems_version: !ruby/object:Gem::Requirement
179
+ requirements:
180
+ - - ">="
181
+ - !ruby/object:Gem::Version
182
+ version: '0'
183
+ requirements: []
184
+ rubyforge_project:
185
+ rubygems_version: 2.4.5.1
186
+ signing_key:
187
+ specification_version: 4
188
+ summary: Visual and textual page diffing.
189
+ test_files: []