validate-website 1.9.0 → 1.11.0

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 +39 -0
  3. data/LICENSE +1 -1
  4. data/README.md +27 -26
  5. data/Rakefile +3 -2
  6. data/bin/validate-website +1 -0
  7. data/bin/validate-website-static +1 -0
  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 +15 -6
  11. data/lib/validate_website/crawl.rb +9 -2
  12. data/lib/validate_website/option_parser.rb +4 -0
  13. data/lib/validate_website/runner.rb +3 -1
  14. data/lib/validate_website/static.rb +12 -2
  15. data/lib/validate_website/static_link.rb +5 -3
  16. data/lib/validate_website/utils.rb +3 -0
  17. data/lib/validate_website/validator.rb +23 -26
  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 +3 -1
  23. data/test/crawler_test.rb +35 -16
  24. data/test/data/html5-fail.html +0 -337
  25. data/test/static_test.rb +25 -5
  26. data/test/test_helper.rb +4 -5
  27. data/test/validator_test.rb +25 -23
  28. data/test/webmock_helper.rb +4 -2
  29. metadata +18 -19
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 5cd3346ce5ce02dd898df5bb28912dcf4c0d682278bdc4e6e2e7b05b4bdf8ef8
4
- data.tar.gz: 7e10dd580a2da57dec3f648a57cd633fbbd6251493a064a2b4077b7fd910a9dc
3
+ metadata.gz: f63d4c84f653035be69262c33ccad0025c48013492b653882a803f7d110e717f
4
+ data.tar.gz: fdf8e994af98a8dbff7411dd480b88f759009a70b5b5c1fcde15120b5db1ad02
5
5
  SHA512:
6
- metadata.gz: fa59986d8a2e40840807c6e43c58cc89fdb359e81cef7c3eb8b307bd08aa4b51c8168f26ea72de9783d1963cb0861e910780eb7e7d138f3f409d2505ee29d010
7
- data.tar.gz: 0f73aae18879b13d7bbadc24a97cca5ca7178498eb060930b81c0059605c129cb25b27c6277b1724f7f364a125cccb8fdcc4ef03a69ee86fa588fd1bdf6d6edb
6
+ metadata.gz: 6b0774aaab6ca32e10d43cfc0dd6c57219cc9e3862af5febd892a30884920195512301f702e5af11459a55c8dde4eaa4238a09833b102924a8ca36c9deb8480f
7
+ data.tar.gz: c0cdf68b1486c2d15257d7fb07e8561f52054b5a234e46162a468b1ffdc6bbc26905563150ccab3053e78a15a70c59142a857afa1aaff7563a22279840752332
data/History.md CHANGED
@@ -1,4 +1,43 @@
1
1
 
2
+ 1.11.0 / 2021-01-08
3
+ ===================
4
+
5
+ * Merge pull request #23 from @marocchino / ruby-3-support
6
+ * Use webrick's escape instead of encode_www_form_component
7
+ * Support ruby 3
8
+ * Fix doc for ValidateWebsite::Core initialize
9
+ * Switch to gitlab ci and remove 2.{3,4} support
10
+ * Update rubocop to 0.76.0
11
+
12
+ 1.10.0 / 2020-07-03
13
+ ==================
14
+
15
+ * Fix build for Ruby 2.3 and 2.4
16
+ * Remove rbx-3 from build
17
+ * Remove minitest-focus and fix minitest 6 warnings
18
+ * Fix html5_validator option and change html5_validator_service_url
19
+ * Add Ruby 2.7 to CI and update jruby
20
+ * Update rubocop and fix offences
21
+ * Remove Ruby 2.2 support and update rubocop
22
+
23
+ 1.9.3 / 2019-04-11
24
+ ==================
25
+
26
+ * Update tidy_ffi to 1.0
27
+ * Avoid testing tidy bug with js
28
+
29
+ 1.9.2 / 2019-03-09
30
+ ==================
31
+
32
+ * Load schema when needed instead of boot
33
+
34
+ 1.9.1 / 2019-03-05
35
+ ==================
36
+
37
+ * Improve start message for static validator
38
+ * Update travis config
39
+ * Fix bundler to <2 on travis (dropped support Ruby < 2.3)
40
+
2
41
  1.9.0 / 2018-12-25
3
42
  ==================
4
43
 
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) 2009-2021 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
@@ -10,34 +10,34 @@ Web crawler for checking the validity of your documents
10
10
 
11
11
  ### Debian
12
12
 
13
- ~~~ console
13
+ ```
14
14
  apt install ruby-dev libxslt1-dev libxml2-dev
15
- ~~~
15
+ ```
16
16
 
17
17
  If you want complete local validation look [tidy
18
18
  packages](https://binaries.html-tidy.org/)
19
19
 
20
20
  ### RubyGems
21
21
 
22
- ~~~ console
22
+ ```
23
23
  gem install validate-website
24
- ~~~
24
+ ```
25
25
 
26
26
  ## Synopsis
27
27
 
28
- ~~~ console
28
+ ```
29
29
  validate-website [OPTIONS]
30
30
  validate-website-static [OPTIONS]
31
- ~~~
31
+ ```
32
32
 
33
33
  ## Examples
34
34
 
35
- ~~~ console
35
+ ```
36
36
  validate-website -v -s https://www.ruby-lang.org/
37
37
  validate-website -v -x tidy -s https://www.ruby-lang.org/
38
38
  validate-website -v -x nu -s https://www.ruby-lang.org/
39
39
  validate-website -h
40
- ~~~
40
+ ```
41
41
 
42
42
  ## Description
43
43
 
@@ -59,30 +59,31 @@ Service](https://checker.html5.org/).
59
59
 
60
60
  ## On your application
61
61
 
62
- ~~~ ruby
62
+ ``` ruby
63
63
  require 'validate_website/validator'
64
64
  body = '<!DOCTYPE html><html></html>'
65
65
  v = ValidateWebsite::Validator.new(Nokogiri::HTML(body), body)
66
66
  v.valid? # => false
67
- ~~~
67
+ ```
68
68
 
69
69
  ## Jekyll static site validation
70
70
 
71
71
  You can add this Rake task to validate a
72
72
  [jekyll](https://github.com/jekyll/jekyll) site:
73
73
 
74
- ~~~ ruby
74
+ ``` ruby
75
75
  desc 'validate _site with validate website'
76
76
  task validate: :build do
77
- Dir.chdir('_site') do
78
- sh("validate-website-static --site '<CONFIG_URL>'") do |ok, res|
79
- unless ok
80
- puts "validate error (status = #{res.exitstatus})"
81
- end
77
+ Dir.chdir("_site") do
78
+ system("validate-website-static",
79
+ "--verbose",
80
+ "--exclude", "examples",
81
+ "--site", HTTP_URL)
82
+ exit($?.exitstatus)
82
83
  end
83
84
  end
84
85
  end
85
- ~~~
86
+ ```
86
87
 
87
88
  ## More info
88
89
 
@@ -109,17 +110,17 @@ validation service.
109
110
  You can download [validator](https://github.com/validator/validator) jar and
110
111
  start it with:
111
112
 
112
- ~~~
113
+ ```
113
114
  java -cp PATH_TO/vnu.jar nu.validator.servlet.Main 8888
114
- ~~~
115
+ ```
115
116
 
116
117
  Then you can use validate-website option:
117
118
 
118
- ~~~
119
+ ```
119
120
  --html5-validator-service-url http://localhost:8888/
120
121
  # or
121
122
  export VALIDATOR_NU_URL="http://localhost:8888/"
122
- ~~~
123
+ ```
123
124
 
124
125
  This will prevent you to be blacklisted from validator webservice.
125
126
 
@@ -127,9 +128,9 @@ This will prevent you to be blacklisted from validator webservice.
127
128
 
128
129
  With standard environment:
129
130
 
130
- ~~~ console
131
+ ```
131
132
  bundle exec rake
132
- ~~~
133
+ ```
133
134
 
134
135
  ## Credits
135
136
 
@@ -144,12 +145,12 @@ See [GitHub](https://github.com/spk/validate-website/graphs/contributors).
144
145
 
145
146
  The MIT License
146
147
 
147
- Copyright (c) 2009-2018 Laurent Arnoud <laurent@spkdev.net>
148
+ Copyright (c) 2009-2021 Laurent Arnoud <laurent@spkdev.net>
148
149
 
149
150
  ---
150
- [![Build](https://img.shields.io/travis-ci/spk/validate-website.svg)](https://travis-ci.org/spk/validate-website)
151
+ [![Build](https://img.shields.io/gitlab/pipeline/spkdev/validate-website/master)](https://gitlab.com/spkdev/validate-website/-/commits/master)
152
+ [![Coverage](https://gitlab.com/spkdev/validate-website/badges/master/coverage.svg)](https://gitlab.com/spkdev/validate-website/-/commits/master)
151
153
  [![Version](https://img.shields.io/gem/v/validate-website.svg)](https://rubygems.org/gems/validate-website)
152
154
  [![Documentation](https://img.shields.io/badge/doc-rubydoc-blue.svg)](http://www.rubydoc.info/gems/validate-website)
153
155
  [![License](https://img.shields.io/badge/license-MIT-blue.svg)](http://opensource.org/licenses/MIT "MIT")
154
- [![Coverage Status](https://img.shields.io/coveralls/github/spk/validate-website.svg)](https://coveralls.io/github/spk/validate-website?branch=master)
155
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
@@ -1,9 +1,10 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'rake/testtask'
2
4
  require 'rubocop/rake_task'
3
5
  require 'asciidoctor'
4
6
 
5
- default = %i[test]
6
- default << :rubocop unless RUBY_ENGINE == 'rbx'
7
+ default = %i[test rubocop]
7
8
  task default: default
8
9
 
9
10
  desc 'Update manpage from asciidoc file'
data/bin/validate-website CHANGED
@@ -1,4 +1,5 @@
1
1
  #!/usr/bin/env ruby
2
+ # frozen_string_literal: true
2
3
 
3
4
  require 'validate_website/runner'
4
5
  exit_status = ValidateWebsite::Runner.run_crawl(ARGV)
data/bin/validate-website-static CHANGED
@@ -1,4 +1,5 @@
1
1
  #!/usr/bin/env ruby
2
+ # frozen_string_literal: true
2
3
 
3
4
  require 'validate_website/runner'
4
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'
@@ -26,11 +28,13 @@ 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
32
35
  # new({ site: "https://example.com/" }, :crawl)
33
36
  # @param [Hash] options
37
+ # @param [Symbol] validation_type `crawl` for web or `static` for local
34
38
  # @return [NilClass]
35
39
  def initialize(options, validation_type)
36
40
  @not_founds_count = 0
@@ -39,15 +43,14 @@ module ValidateWebsite
39
43
  @site = @options[:site]
40
44
  @service_url = @options[:html5_validator_service_url]
41
45
  Validator.html5_validator_service_url = @service_url if @service_url
42
- puts color(:note, "validating #{@site}\n", @options[:color])
43
46
  end
44
47
 
45
48
  def errors?
46
- @errors_count > 0
49
+ @errors_count.positive?
47
50
  end
48
51
 
49
52
  def not_founds?
50
- @not_founds_count > 0
53
+ @not_founds_count.positive?
51
54
  end
52
55
 
53
56
  def exit_status
@@ -71,9 +74,14 @@ module ValidateWebsite
71
74
 
72
75
  private
73
76
 
77
+ def start_message(type)
78
+ puts color(:note, "#{START_MESSAGE} #{type}\n", @options[:color])
79
+ end
80
+
74
81
  def check_css_syntax(page)
75
82
  nodes = Crass::Parser.parse_stylesheet(page.body)
76
83
  return unless any_css_errors?(nodes)
84
+
77
85
  handle_validation_error(page.url)
78
86
  end
79
87
 
@@ -107,10 +115,10 @@ module ValidateWebsite
107
115
  # @param [Nokogiri::HTML::Document] original_doc
108
116
  # @param [String] The raw HTTP response body of the page
109
117
  # @param [String] url
110
- # @param [Regexp] Errors to ignore
118
+ # @param [Hash] Validator options
111
119
  #
112
- def validate(doc, body, url, ignore = nil)
113
- validator = Validator.new(doc, body, ignore: ignore)
120
+ def validate(doc, body, url, options)
121
+ validator = Validator.new(doc, body, **options)
114
122
  if validator.valid?
115
123
  print color(:success, '.', options[:color]) # rspec style
116
124
  else
@@ -121,6 +129,7 @@ module ValidateWebsite
121
129
  def handle_html_validation_error(validator, url)
122
130
  handle_validation_error(url)
123
131
  return unless options[:verbose]
132
+
124
133
  puts color(:error, validator.errors.join(', '), options[:color])
125
134
  end
126
135
 
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
@@ -40,9 +43,10 @@ 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
- result << page.to_absolute(URI.parse(URI.encode(u)))
49
+ result << page.to_absolute(URI.parse(WEBrick::HTTPUtils.escape(u)))
46
50
  end
47
51
  end
48
52
 
@@ -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)
data/lib/validate_website/runner.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'validate_website/core'
2
4
 
3
5
  module ValidateWebsite
@@ -5,7 +7,7 @@ module ValidateWebsite
5
7
  class Runner
6
8
  def self.trap_interrupt
7
9
  trap('INT') do
8
- STDERR.puts "\nExiting..."
10
+ warn "\nExiting..."
9
11
  exit!(1)
10
12
  end
11
13
  end
data/lib/validate_website/static.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
 
@@ -5,12 +7,14 @@ module ValidateWebsite
5
7
  # Class for validation Static website
6
8
  class Static < Core
7
9
  CONTENT_TYPES = ['text/html', 'text/xhtml+xml'].freeze
10
+ START_MESSAGE_TYPE = 'files'
8
11
 
9
12
  attr_reader :history_count
10
13
 
11
14
  def initialize(options = {}, validation_type = :static)
12
15
  @history_count = 0
13
16
  super
17
+ start_message("#{START_MESSAGE_TYPE} in #{Dir.pwd} (#{@site} as site)")
14
18
  end
15
19
 
16
20
  # @param [Hash] options
@@ -22,7 +26,8 @@ module ValidateWebsite
22
26
  files = Dir.glob(@options[:pattern])
23
27
  files.each do |file|
24
28
  next unless File.file?(file)
25
- next if @options[:exclude] && @options[:exclude].match(file)
29
+ next if @options[:exclude]&.match(file)
30
+
26
31
  @history_count += 1
27
32
  check_static_file(file)
28
33
  end
@@ -55,7 +60,10 @@ module ValidateWebsite
55
60
 
56
61
  def check_page(file, page)
57
62
  if page.html? && options[:markup]
58
- validate(page.doc, page.body, file, options[:ignore])
63
+ keys = %i[ignore html5_validator]
64
+ # slice does not exists on Ruby <= 2.4
65
+ slice = Hash[[keys, options.values_at(*keys)].transpose]
66
+ validate(page.doc, page.body, file, slice)
59
67
  end
60
68
  check_static_not_found(page.links) if options[:not_found]
61
69
  end
@@ -66,11 +74,13 @@ module ValidateWebsite
66
74
  static_links = links.map { |l| StaticLink.new(l, @site) }
67
75
  static_links.each do |static_link|
68
76
  next unless static_link.check?
77
+
69
78
  unless File.exist?(static_link.file_path)
70
79
  not_found_error(static_link.file_path)
71
80
  next
72
81
  end
73
82
  next unless static_link.css?
83
+
74
84
  check_static_not_found static_link.extract_urls_from_fake_css_response
75
85
  end
76
86
  end
data/lib/validate_website/static_link.rb CHANGED
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'uri'
2
4
  require 'validate_website/utils'
3
5
  require 'validate_website/static'
@@ -6,7 +8,7 @@ require 'spidr'
6
8
  # rubocop:disable Metrics/BlockLength
7
9
  StaticLink = Struct.new(:link, :site) do
8
10
  def link_uri
9
- @link_uri = URI.parse(URI.encode(link))
11
+ @link_uri = URI.parse(WEBrick::HTTPUtils.escape(link))
10
12
  @link_uri = URI.join(site, @link_uri) if @link_uri.host.nil?
11
13
  @link_uri
12
14
  end
@@ -25,9 +27,9 @@ StaticLink = Struct.new(:link, :site) do
25
27
 
26
28
  def body
27
29
  if File.exist?(link)
28
- open(link).read
30
+ File.open(link).read
29
31
  else
30
- open(file_path).read
32
+ File.open(file_path).read
31
33
  end
32
34
  end
33
35