validate-website 1.8.1 → 1.10.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (29) hide show
  1. checksums.yaml +4 -4
  2. data/History.md +37 -0
  3. data/LICENSE +1 -1
  4. data/README.md +38 -25
  5. data/Rakefile +5 -1
  6. data/bin/validate-website +1 -1
  7. data/bin/validate-website-static +1 -1
  8. data/lib/validate_website.rb +2 -0
  9. data/lib/validate_website/colorful_messages.rb +3 -0
  10. data/lib/validate_website/core.rb +14 -6
  11. data/lib/validate_website/crawl.rb +8 -1
  12. data/lib/validate_website/option_parser.rb +58 -54
  13. data/lib/validate_website/runner.rb +3 -1
  14. data/lib/validate_website/static.rb +19 -9
  15. data/lib/validate_website/static_link.rb +4 -2
  16. data/lib/validate_website/utils.rb +3 -0
  17. data/lib/validate_website/validator.rb +24 -27
  18. data/lib/validate_website/validator_class_methods.rb +3 -0
  19. data/lib/validate_website/version.rb +1 -1
  20. data/man/man1/validate-website-static.1 +17 -8
  21. data/man/man1/validate-website.1 +17 -8
  22. data/test/core_test.rb +4 -2
  23. data/test/crawler_test.rb +36 -17
  24. data/test/data/html5-fail.html +0 -337
  25. data/test/static_test.rb +26 -6
  26. data/test/test_helper.rb +9 -2
  27. data/test/validator_test.rb +26 -24
  28. data/test/webmock_helper.rb +4 -2
  29. metadata +34 -35
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: b148e551f237891330dc1ebbbdb8b2c1d60217d41aac7d682293f9b85f7e3d45
4
- data.tar.gz: '068a9f8dde45e751498d69a903d9e23b8f38a68748ef7416863b8a1c73feacec'
3
+ metadata.gz: 4a5b0553089c9d66d3622781fe6c4ab5ca68ac6a198fe36c53c84c8d34e14adb
4
+ data.tar.gz: f3f0cc4aef203f85ebb9868e793b7cd0312db8c4b6f7fb0d15beefeaaef1cc83
5
5
  SHA512:
6
- metadata.gz: 8cba9a25bc027cf5d9a309e6077b3228b8668a8f473b89113d518ddcccca7e86a486a3059d3b74401bd5e7130a28213a4bfa02117de24918d396838d51418672
7
- data.tar.gz: 9d99666a222c2c2dd1de6aa551c9d572d8ef68f30e13bb809924a14502032bd0698ba10ef128acb48a11571bcad8ec41234dac7eb06968e0f8c091bca97643ce
6
+ metadata.gz: c9a8fae92bcb19d5f92466a7b77f3e40cca59643c946c15563885d9e65a1d2793271dee2b723a296fe487d57634fdd88f4440a60d2fac625a6a7208c8105159d
7
+ data.tar.gz: e7a78f899b42d5f27cb41e99472e37499389bf39c567dd9f16ab064fce38927a43de89c00411c25697c622ad76f59b8d4b9836d898249822cf9bc0d37591c3bf
data/History.md CHANGED
@@ -1,4 +1,41 @@
1
1
 
2
+ 1.10.0 / 2020-07-03
3
+ ==================
4
+
5
+ * Fix build for Ruby 2.3 and 2.4
6
+ * Remove rbx-3 from build
7
+ * Remove minitest-focus and fix minitest 6 warnings
8
+ * Fix html5_validator option and change html5_validator_service_url
9
+ * Add Ruby 2.7 to CI and update jruby
10
+ * Update rubocop and fix offences
11
+ * Remove Ruby 2.2 support and update rubocop
12
+
13
+ 1.9.3 / 2019-04-11
14
+ ==================
15
+
16
+ * Update tidy_ffi to 1.0
17
+ * Avoid testing tidy bug with js
18
+
19
+ 1.9.2 / 2019-03-09
20
+ ==================
21
+
22
+ * Load schema when needed instead of boot
23
+
24
+ 1.9.1 / 2019-03-05
25
+ ==================
26
+
27
+ * Improve start message for static validator
28
+ * Update travis config
29
+ * Fix bundler to <2 on travis (dropped support Ruby < 2.3)
30
+
31
+ 1.9.0 / 2018-12-25
32
+ ==================
33
+
34
+ * Update deps paint; slop; webmock
35
+ * Remove Ruby 2.1 support
36
+ * Force nonet and disable substitute entities on xhtml parse
37
+ * Use coveralls for code coverage
38
+
2
39
  v1.8.1 / 2018-03-25
3
40
  ===================
4
41
 
data/LICENSE CHANGED
@@ -1,6 +1,6 @@
1
1
  The MIT License
2
2
 
3
- Copyright (c) 2009-2018 Laurent Arnoud <laurent@spkdev.net>
3
+ Copyright (c) 2009-2020 Laurent Arnoud <laurent@spkdev.net>
4
4
 
5
5
  Permission is hereby granted, free of charge, to any person obtaining
6
6
  a copy of this software and associated documentation files (the
data/README.md CHANGED
@@ -10,22 +10,34 @@ Web crawler for checking the validity of your documents
10
10
 
11
11
  ### Debian
12
12
 
13
- ~~~ console
14
- apt install ruby-dev libxslt-dev libxml2-dev libtidy5
15
- ~~~
13
+ ```
14
+ apt install ruby-dev libxslt1-dev libxml2-dev
15
+ ```
16
+
17
+ If you want complete local validation look [tidy
18
+ packages](https://binaries.html-tidy.org/)
16
19
 
17
20
  ### RubyGems
18
21
 
19
- ~~~ console
22
+ ```
20
23
  gem install validate-website
21
- ~~~
24
+ ```
22
25
 
23
26
  ## Synopsis
24
27
 
25
- ~~~ console
28
+ ```
26
29
  validate-website [OPTIONS]
27
30
  validate-website-static [OPTIONS]
28
- ~~~
31
+ ```
32
+
33
+ ## Examples
34
+
35
+ ```
36
+ validate-website -v -s https://www.ruby-lang.org/
37
+ validate-website -v -x tidy -s https://www.ruby-lang.org/
38
+ validate-website -v -x nu -s https://www.ruby-lang.org/
39
+ validate-website -h
40
+ ```
29
41
 
30
42
  ## Description
31
43
 
@@ -47,30 +59,31 @@ Service](https://checker.html5.org/).
47
59
 
48
60
  ## On your application
49
61
 
50
- ~~~ ruby
62
+ ``` ruby
51
63
  require 'validate_website/validator'
52
64
  body = '<!DOCTYPE html><html></html>'
53
65
  v = ValidateWebsite::Validator.new(Nokogiri::HTML(body), body)
54
66
  v.valid? # => false
55
- ~~~
67
+ ```
56
68
 
57
69
  ## Jekyll static site validation
58
70
 
59
71
  You can add this Rake task to validate a
60
72
  [jekyll](https://github.com/jekyll/jekyll) site:
61
73
 
62
- ~~~ ruby
74
+ ``` ruby
63
75
  desc 'validate _site with validate website'
64
76
  task validate: :build do
65
- Dir.chdir('_site') do
66
- sh("validate-website-static --site '<CONFIG_URL>'") do |ok, res|
67
- unless ok
68
- puts "validate error (status = #{res.exitstatus})"
69
- end
77
+ Dir.chdir("_site") do
78
+ system("validate-website-static",
79
+ "--verbose",
80
+ "--exclude", "examples",
81
+ "--site", HTTP_URL)
82
+ exit($?.exitstatus)
70
83
  end
71
84
  end
72
85
  end
73
- ~~~
86
+ ```
74
87
 
75
88
  ## More info
76
89
 
@@ -97,17 +110,17 @@ validation service.
97
110
  You can download [validator](https://github.com/validator/validator) jar and
98
111
  start it with:
99
112
 
100
- ~~~
113
+ ```
101
114
  java -cp PATH_TO/vnu.jar nu.validator.servlet.Main 8888
102
- ~~~
115
+ ```
103
116
 
104
117
  Then you can use validate-website option:
105
118
 
106
- ~~~
119
+ ```
107
120
  --html5-validator-service-url http://localhost:8888/
108
121
  # or
109
122
  export VALIDATOR_NU_URL="http://localhost:8888/"
110
- ~~~
123
+ ```
111
124
 
112
125
  This will prevent you to be blacklisted from validator webservice.
113
126
 
@@ -115,9 +128,9 @@ This will prevent you to be blacklisted from validator webservice.
115
128
 
116
129
  With standard environment:
117
130
 
118
- ~~~ console
131
+ ```
119
132
  bundle exec rake
120
- ~~~
133
+ ```
121
134
 
122
135
  ## Credits
123
136
 
@@ -132,12 +145,12 @@ See [GitHub](https://github.com/spk/validate-website/graphs/contributors).
132
145
 
133
146
  The MIT License
134
147
 
135
- Copyright (c) 2009-2018 Laurent Arnoud <laurent@spkdev.net>
148
+ Copyright (c) 2009-2020 Laurent Arnoud <laurent@spkdev.net>
136
149
 
137
150
  ---
138
- [![Build](https://img.shields.io/travis-ci/spk/validate-website.svg)](https://travis-ci.org/spk/validate-website)
151
+ [![Build](https://img.shields.io/travis/spk/validate-website.svg)](https://travis-ci.org/spk/validate-website)
139
152
  [![Version](https://img.shields.io/gem/v/validate-website.svg)](https://rubygems.org/gems/validate-website)
140
153
  [![Documentation](https://img.shields.io/badge/doc-rubydoc-blue.svg)](http://www.rubydoc.info/gems/validate-website)
141
154
  [![License](https://img.shields.io/badge/license-MIT-blue.svg)](http://opensource.org/licenses/MIT "MIT")
142
- [![Code Climate](https://img.shields.io/codeclimate/github/spk/validate-website.svg)](https://codeclimate.com/github/spk/validate-website)
155
+ [![Coverage Status](https://img.shields.io/coveralls/github/spk/validate-website.svg)](https://coveralls.io/github/spk/validate-website?branch=master)
143
156
  [![Inline docs](https://inch-ci.org/github/spk/validate-website.svg?branch=master)](http://inch-ci.org/github/spk/validate-website)
data/Rakefile CHANGED
@@ -1,8 +1,12 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'rake/testtask'
2
4
  require 'rubocop/rake_task'
3
5
  require 'asciidoctor'
4
6
 
5
- task default: %i[test rubocop]
7
+ default = %i[test]
8
+ default << :rubocop unless RUBY_ENGINE == 'rbx'
9
+ task default: default
6
10
 
7
11
  desc 'Update manpage from asciidoc file'
8
12
  task :manpage do
data/bin/validate-website CHANGED
@@ -1,5 +1,5 @@
1
1
  #!/usr/bin/env ruby
2
- # encoding: utf-8
2
+ # frozen_string_literal: true
3
3
 
4
4
  require 'validate_website/runner'
5
5
  exit_status = ValidateWebsite::Runner.run_crawl(ARGV)
data/bin/validate-website-static CHANGED
@@ -1,5 +1,5 @@
1
1
  #!/usr/bin/env ruby
2
- # encoding: utf-8
2
+ # frozen_string_literal: true
3
3
 
4
4
  require 'validate_website/runner'
5
5
  exit_status = ValidateWebsite::Runner.run_static(ARGV)
data/lib/validate_website.rb CHANGED
@@ -1,2 +1,4 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'validate_website/core'
2
4
  require 'validate_website/version'
data/lib/validate_website/colorful_messages.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'paint'
2
4
 
3
5
  module ValidateWebsite
@@ -5,6 +7,7 @@ module ValidateWebsite
5
7
  module ColorfulMessages
6
8
  def color(type, message, colored = true)
7
9
  return message unless colored
10
+
8
11
  send(type, message)
9
12
  end
10
13
 
data/lib/validate_website/core.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'set'
2
4
  require 'open-uri'
3
5
  require 'webrick/cookie'
@@ -26,6 +28,7 @@ module ValidateWebsite
26
28
  EXIT_FAILURE_MARKUP = 64
27
29
  EXIT_FAILURE_NOT_FOUND = 65
28
30
  EXIT_FAILURE_MARKUP_NOT_FOUND = 66
31
+ START_MESSAGE = 'Validating'
29
32
 
30
33
  # Initialize core ValidateWebsite class
31
34
  # @example
@@ -39,15 +42,14 @@ module ValidateWebsite
39
42
  @site = @options[:site]
40
43
  @service_url = @options[:html5_validator_service_url]
41
44
  Validator.html5_validator_service_url = @service_url if @service_url
42
- puts color(:note, "validating #{@site}\n", @options[:color])
43
45
  end
44
46
 
45
47
  def errors?
46
- @errors_count > 0
48
+ @errors_count.positive?
47
49
  end
48
50
 
49
51
  def not_founds?
50
- @not_founds_count > 0
52
+ @not_founds_count.positive?
51
53
  end
52
54
 
53
55
  def exit_status
@@ -71,9 +73,14 @@ module ValidateWebsite
71
73
 
72
74
  private
73
75
 
76
+ def start_message(type)
77
+ puts color(:note, "#{START_MESSAGE} #{type}\n", @options[:color])
78
+ end
79
+
74
80
  def check_css_syntax(page)
75
81
  nodes = Crass::Parser.parse_stylesheet(page.body)
76
82
  return unless any_css_errors?(nodes)
83
+
77
84
  handle_validation_error(page.url)
78
85
  end
79
86
 
@@ -107,10 +114,10 @@ module ValidateWebsite
107
114
  # @param [Nokogiri::HTML::Document] original_doc
108
115
  # @param [String] The raw HTTP response body of the page
109
116
  # @param [String] url
110
- # @param [Regexp] Errors to ignore
117
+ # @param [Hash] Validator options
111
118
  #
112
- def validate(doc, body, url, ignore = nil)
113
- validator = Validator.new(doc, body, ignore: ignore)
119
+ def validate(doc, body, url, options)
120
+ validator = Validator.new(doc, body, options)
114
121
  if validator.valid?
115
122
  print color(:success, '.', options[:color]) # rspec style
116
123
  else
@@ -121,6 +128,7 @@ module ValidateWebsite
121
128
  def handle_html_validation_error(validator, url)
122
129
  handle_validation_error(url)
123
130
  return unless options[:verbose]
131
+
124
132
  puts color(:error, validator.errors.join(', '), options[:color])
125
133
  end
126
134
 
data/lib/validate_website/crawl.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'validate_website/core'
2
4
  require 'validate_website/utils'
3
5
 
@@ -8,6 +10,7 @@ module ValidateWebsite
8
10
 
9
11
  def initialize(options = {}, validation_type = :crawl)
10
12
  super
13
+ start_message(@site)
11
14
  end
12
15
 
13
16
  def history_count
@@ -40,6 +43,7 @@ module ValidateWebsite
40
43
  #
41
44
  def extract_imgs_from_page(page)
42
45
  return Set[] if page.is_redirect?
46
+
43
47
  page.doc.search('//img[@src]').reduce(Set[]) do |result, elem|
44
48
  u = elem.attributes['src'].content
45
49
  result << page.to_absolute(URI.parse(URI.encode(u)))
@@ -76,7 +80,10 @@ module ValidateWebsite
76
80
  end
77
81
 
78
82
  if validate?(page)
79
- validate(page.doc, page.body, page.url, options[:ignore])
83
+ keys = %i[ignore html5_validator]
84
+ # slice does not exists on Ruby <= 2.4
85
+ slice = Hash[[keys, options.values_at(*keys)].transpose]
86
+ validate(page.doc, page.body, page.url, slice)
80
87
  end
81
88
  end
82
89
  end
data/lib/validate_website/option_parser.rb CHANGED
@@ -1,4 +1,7 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'slop'
4
+ require File.expand_path('version', __dir__)
2
5
 
3
6
  module ValidateWebsite
4
7
  # Internal class for parse command line args
@@ -28,6 +31,7 @@ module ValidateWebsite
28
31
  # Generic parse method for crawl or static options
29
32
  def self.parse(options, type)
30
33
  raise ArgumentError unless VALID_TYPES.include?(type)
34
+
31
35
  # We are in command line (ARGV)
32
36
  if options.is_a?(Array)
33
37
  send("command_line_parse_#{type}", options)
@@ -38,57 +42,57 @@ module ValidateWebsite
38
42
  end
39
43
 
40
44
  def self.default_args
41
- Slop.parse do |o|
42
- yield o if block_given?
43
- markup_syntax(o)
44
- boolean_options(o)
45
- ignore_html5_options(o)
46
- verbose_option(o)
47
- version_help(o)
45
+ Slop.parse do |opt|
46
+ yield opt if block_given?
47
+ markup_syntax(opt)
48
+ boolean_options(opt)
49
+ ignore_html5_options(opt)
50
+ verbose_option(opt)
51
+ version_help(opt)
48
52
  end
49
53
  end
50
54
 
51
- def self.ignore_html5_options(o)
52
- o.regexp('-i', '--ignore',
53
- 'Validation errors to ignore (ex: "valign|autocorrect")')
54
- o.string('-x', '--html5-validator',
55
- 'Change default html5 validator engine (ex: tidy or nu)',
56
- default: DEFAULT_OPTIONS[:html5_validator])
57
- o.string('-5', '--html5-validator-service-url',
58
- 'Change default html5 validator service URL for "nu" engine')
55
+ def self.ignore_html5_options(opt)
56
+ opt.regexp('-i', '--ignore',
57
+ 'Validation errors to ignore (ex: "valign|autocorrect")')
58
+ opt.string('-x', '--html5-validator',
59
+ 'Change default html5 validator engine (ex: tidy or nu)',
60
+ default: DEFAULT_OPTIONS[:html5_validator])
61
+ opt.string('-5', '--html5-validator-service-url',
62
+ 'Change default html5 validator service URL for "nu" engine')
59
63
  end
60
64
 
61
- def self.markup_syntax(o)
62
- o.bool('-m', '--markup',
63
- "Markup validation (default: #{DEFAULT_OPTIONS[:markup]})",
64
- default: DEFAULT_OPTIONS[:markup])
65
- o.bool('--css-syntax',
66
- "Css validation (default: #{DEFAULT_OPTIONS[:css_syntax]})",
67
- default: DEFAULT_OPTIONS[:css_syntax])
65
+ def self.markup_syntax(opt)
66
+ opt.bool('-m', '--markup',
67
+ "Markup validation (default: #{DEFAULT_OPTIONS[:markup]})",
68
+ default: DEFAULT_OPTIONS[:markup])
69
+ opt.bool('--css-syntax',
70
+ "Css validation (default: #{DEFAULT_OPTIONS[:css_syntax]})",
71
+ default: DEFAULT_OPTIONS[:css_syntax])
68
72
  end
69
73
 
70
- def self.boolean_options(o)
71
- o.bool('-n', '--not-found',
72
- "Log not found url (default: #{DEFAULT_OPTIONS[:not_found]})",
73
- default: DEFAULT_OPTIONS[:not_found])
74
- o.bool('--color',
75
- "Show colored output (default: #{DEFAULT_OPTIONS[:color]})",
76
- default: DEFAULT_OPTIONS[:color])
74
+ def self.boolean_options(opt)
75
+ opt.bool('-n', '--not-found',
76
+ "Log not found url (default: #{DEFAULT_OPTIONS[:not_found]})",
77
+ default: DEFAULT_OPTIONS[:not_found])
78
+ opt.bool('--color',
79
+ "Show colored output (default: #{DEFAULT_OPTIONS[:color]})",
80
+ default: DEFAULT_OPTIONS[:color])
77
81
  end
78
82
 
79
- def self.verbose_option(o)
80
- o.bool('-v', '--verbose',
81
- "Show validator errors (default: #{DEFAULT_OPTIONS[:verbose]})",
82
- default: DEFAULT_OPTIONS[:verbose])
83
+ def self.verbose_option(opt)
84
+ opt.bool('-v', '--verbose',
85
+ "Show validator errors (default: #{DEFAULT_OPTIONS[:verbose]})",
86
+ default: DEFAULT_OPTIONS[:verbose])
83
87
  end
84
88
 
85
- def self.version_help(o)
86
- o.on('--version', 'Display version.') do
89
+ def self.version_help(opt)
90
+ opt.on('--version', 'Display version.') do
87
91
  puts ValidateWebsite::VERSION
88
92
  exit
89
93
  end
90
- o.on('-h', '--help', 'Display this help message.') do
91
- puts o
94
+ opt.on('-h', '--help', 'Display this help message.') do
95
+ puts opt
92
96
  exit
93
97
  end
94
98
  end
@@ -97,15 +101,15 @@ module ValidateWebsite
97
101
  # @params [ARGV]
98
102
  # @return [Hash]
99
103
  def self.command_line_parse_crawl(_args)
100
- default_args do |o|
101
- o.string('-s', '--site',
102
- "Website to crawl (default: #{DEFAULT_OPTIONS[:site]})",
103
- default: DEFAULT_OPTIONS[:site])
104
- o.string('-u', '--user-agent',
105
- 'Change user agent',
106
- default: DEFAULT_OPTIONS[:user_agent])
107
- o.regexp('-e', '--exclude', 'Url to exclude (ex: "redirect|news")')
108
- o.string('-c', '--cookies', 'Set defaults cookies')
104
+ default_args do |opt|
105
+ opt.string('-s', '--site',
106
+ "Website to crawl (default: #{DEFAULT_OPTIONS[:site]})",
107
+ default: DEFAULT_OPTIONS[:site])
108
+ opt.string('-u', '--user-agent',
109
+ 'Change user agent',
110
+ default: DEFAULT_OPTIONS[:user_agent])
111
+ opt.regexp('-e', '--exclude', 'Url to exclude (ex: "redirect|news")')
112
+ opt.string('-c', '--cookies', 'Set defaults cookies')
109
113
  end
110
114
  end
111
115
 
@@ -113,14 +117,14 @@ module ValidateWebsite
113
117
  # @params [ARGV]
114
118
  # @return [Hash]
115
119
  def self.command_line_parse_static(_args)
116
- default_args do |o|
117
- o.string('-s', '--site',
118
- "Website to crawl (default: #{DEFAULT_OPTIONS[:site]})",
119
- default: DEFAULT_OPTIONS[:site])
120
- o.string('-p', '--pattern',
121
- "Filename pattern (default: #{DEFAULT_OPTIONS[:pattern]})",
122
- default: DEFAULT_OPTIONS[:pattern])
123
- o.regexp('-e', '--exclude', 'Url to exclude (ex: "redirect|news")')
120
+ default_args do |opt|
121
+ opt.string('-s', '--site',
122
+ "Website to crawl (default: #{DEFAULT_OPTIONS[:site]})",
123
+ default: DEFAULT_OPTIONS[:site])
124
+ opt.string('-p', '--pattern',
125
+ "Filename pattern (default: #{DEFAULT_OPTIONS[:pattern]})",
126
+ default: DEFAULT_OPTIONS[:pattern])
127
+ opt.regexp('-e', '--exclude', 'Url to exclude (ex: "redirect|news")')
124
128
  end
125
129
  end
126
130
  end