validate-website 0.7.7 → 0.7.9

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 +7 -0
  2. data/lib/validate_website/core.rb +13 -0
  3. data/lib/validate_website/validator.rb +1 -1
  4. data/spec/core_spec.rb +1 -0
  5. data/spec/fakeweb_helper.rb +40 -48
  6. metadata +51 -38
  7. data/README.rdoc +0 -114
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 508617dba80034c3c180a97bb29ae4b6b20cd346
4
+ data.tar.gz: 8427dd8ee3e1e3e3de26a404b77820d6dcf6b27f
5
+ SHA512:
6
+ metadata.gz: f3a236e0035c6b5fa3f6136066a28abfff550c4f621d37253680d678d38ef97deaee125c4a0cf9512b234549717fe8fb7847730c3df2faddaca417faf2c5f57f
7
+ data.tar.gz: 714e6b037aa011031762ced9cdde2083bb18ad39d7cda69883096bd6a016e40876857c32af586e8284187475797d86f783dd1c9150c41e5a984900b957ca4776
data/lib/validate_website/core.rb CHANGED
@@ -22,6 +22,8 @@ module ValidateWebsite
22
22
  EXIT_FAILURE_NOT_FOUND = 65
23
23
  EXIT_FAILURE_MARKUP_NOT_FOUND = 66
24
24
 
25
+ PING_URL = 'http://www.google.com/'
26
+
25
27
  def initialize(options={}, validation_type=:crawl)
26
28
  @markup_error = nil
27
29
  @not_found_error = nil
@@ -50,6 +52,8 @@ module ValidateWebsite
50
52
  opts = @options.merge(opts)
51
53
  puts color(:note, "validating #{@site}", opts[:color]) unless opts[:quiet]
52
54
 
55
+ puts color(:warning, "No internet connection") unless internet_connection?
56
+
53
57
  @anemone = Anemone.crawl(@site, opts) do |anemone|
54
58
  anemone.skip_links_like Regexp.new(opts[:exclude]) if opts[:exclude]
55
59
 
@@ -88,6 +92,15 @@ module ValidateWebsite
88
92
  end
89
93
  end
90
94
 
95
+ def internet_connection?
96
+ begin
97
+ true if open(ValidateWebsite::Core::PING_URL)
98
+ rescue
99
+ false
100
+ end
101
+ end
102
+
103
+
91
104
  def crawl_static(opts={})
92
105
  opts = @options.merge(opts)
93
106
  puts color(:note, "validating #{@site}", opts[:color])
data/lib/validate_website/validator.rb CHANGED
@@ -45,7 +45,7 @@ module ValidateWebsite
45
45
  # TODO: use a local Java, Python parser... write a Ruby HTML5 parser ?
46
46
  require 'net/http'
47
47
  require 'multipart_body'
48
- url = URI.parse('http://validator.nu/')
48
+ url = URI.parse('http://html5.validator.nu/')
49
49
  multipart = MultipartBody.new(:content => document)
50
50
  http = Net::HTTP.new(url.host)
51
51
  headers = {
data/spec/core_spec.rb CHANGED
@@ -5,6 +5,7 @@ describe ValidateWebsite::Core do
5
5
 
6
6
  before do
7
7
  FakeWeb.clean_registry
8
+ FakeWeb.register_uri(:get, ValidateWebsite::Core::PING_URL, :status => [200, "OK"])
8
9
  @validate_website = ValidateWebsite::Core.new(:color => false)
9
10
  end
10
11
 
data/spec/fakeweb_helper.rb CHANGED
@@ -1,62 +1,54 @@
1
1
  # encoding: UTF-8
2
- begin
3
- require 'fakeweb'
4
- rescue LoadError
5
- warn "You need the 'fakeweb' gem installed to test ValidateWebsite"
6
- exit
7
- end
2
+ require 'fakeweb'
8
3
 
9
4
  FakeWeb.allow_net_connect = false
10
5
 
11
6
  class FakePage
12
- attr_accessor :links
13
- attr_accessor :hrefs
14
- attr_accessor :body
15
-
16
- def initialize(name = '', options = {})
17
- @name = name
18
- @links = [options[:links]].flatten if options.has_key?(:links)
19
- @hrefs = [options[:hrefs]].flatten if options.has_key?(:hrefs)
20
- @redirect = options[:redirect] if options.has_key?(:redirect)
21
- @content_type = options[:content_type] || "text/html"
22
- @body = options[:body]
23
-
24
- create_body unless @body
25
- add_to_fakeweb
26
- end
7
+ attr_accessor :links
8
+ attr_accessor :hrefs
9
+ attr_accessor :body
10
+
11
+ def initialize(name = '', options = {})
12
+ @name = name
13
+ @links = [options[:links]].flatten if options.has_key?(:links)
14
+ @hrefs = [options[:hrefs]].flatten if options.has_key?(:hrefs)
15
+ @redirect = options[:redirect] if options.has_key?(:redirect)
16
+ @content_type = options[:content_type] || "text/html"
17
+ @body = options[:body]
18
+
19
+ create_body unless @body
20
+ add_to_fakeweb
21
+ end
27
22
 
28
- def url
29
- SPEC_DOMAIN + @name
30
- end
23
+ def url
24
+ SPEC_DOMAIN + @name
25
+ end
31
26
 
32
- private
27
+ private
33
28
 
34
- def create_body
35
- @body = "<html><body>"
36
- @links.each{|l| @body += "<a href=\"#{SPEC_DOMAIN}#{l}\"></a>"} if @links
37
- @hrefs.each{|h| @body += "<a href=\"#{h}\"></a>"} if @hrefs
38
- @body += "</body></html>"
39
- end
40
-
41
- def add_to_fakeweb
42
- options = {:body => @body, :content_type => @content_type, :status => [200, "OK"]}
29
+ def create_body
30
+ @body = "<html><body>"
31
+ @links.each{|l| @body += "<a href=\"#{SPEC_DOMAIN}#{l}\"></a>"} if @links
32
+ @hrefs.each{|h| @body += "<a href=\"#{h}\"></a>"} if @hrefs
33
+ @body += "</body></html>"
34
+ end
43
35
 
44
- if @redirect
45
- options[:status] = [301, "Permanently Moved"]
36
+ def add_to_fakeweb
37
+ options = {:body => @body, :content_type => @content_type, :status => [200, "OK"]}
46
38
 
47
- # only prepend SPEC_DOMAIN if a relative url (without an http scheme) was specified
48
- redirect_url = (@redirect =~ /http/) ? @redirect : SPEC_DOMAIN + @redirect
49
- options[:location] = redirect_url
39
+ if @redirect
40
+ options[:status] = [301, "Permanently Moved"]
50
41
 
51
- # register the page this one redirects to
52
- FakeWeb.register_uri(:get, redirect_url, {:body => '',
53
- :content_type => @content_type,
54
- :status => [200, "OK"]})
55
- end
42
+ # only prepend SPEC_DOMAIN if a relative url (without an http scheme) was specified
43
+ redirect_url = (@redirect =~ /http/) ? @redirect : SPEC_DOMAIN + @redirect
44
+ options[:location] = redirect_url
56
45
 
57
- FakeWeb.register_uri(:get, SPEC_DOMAIN + @name, options)
46
+ # register the page this one redirects to
47
+ FakeWeb.register_uri(:get, redirect_url, {:body => '',
48
+ :content_type => @content_type,
49
+ :status => [200, "OK"]})
58
50
  end
59
- end
60
51
 
61
- #default root
62
- #ValidateWebSiteTest::FakePage.new
52
+ FakeWeb.register_uri(:get, SPEC_DOMAIN + @name, options)
53
+ end
54
+ end
metadata CHANGED
@@ -1,82 +1,99 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: validate-website
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.7.7
5
- prerelease:
4
+ version: 0.7.9
6
5
  platform: ruby
7
6
  authors:
8
7
  - Laurent Arnoud
9
8
  autorequire:
10
9
  bindir: bin
11
10
  cert_chain: []
12
- date: 2012-07-23 00:00:00.000000000 Z
11
+ date: 2013-03-18 00:00:00.000000000 Z
13
12
  dependencies:
14
13
  - !ruby/object:Gem::Dependency
15
14
  name: anemone
16
- requirement: &27685000 !ruby/object:Gem::Requirement
17
- none: false
15
+ requirement: !ruby/object:Gem::Requirement
18
16
  requirements:
19
- - - ! '>='
17
+ - - '>='
20
18
  - !ruby/object:Gem::Version
21
19
  version: 0.6.1
22
20
  type: :runtime
23
21
  prerelease: false
24
- version_requirements: *27685000
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - '>='
25
+ - !ruby/object:Gem::Version
26
+ version: 0.6.1
25
27
  - !ruby/object:Gem::Dependency
26
28
  name: rainbow
27
- requirement: &27683920 !ruby/object:Gem::Requirement
28
- none: false
29
+ requirement: !ruby/object:Gem::Requirement
29
30
  requirements:
30
- - - ! '>='
31
+ - - '>='
31
32
  - !ruby/object:Gem::Version
32
33
  version: 1.1.1
33
34
  type: :runtime
34
35
  prerelease: false
35
- version_requirements: *27683920
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - '>='
39
+ - !ruby/object:Gem::Version
40
+ version: 1.1.1
36
41
  - !ruby/object:Gem::Dependency
37
42
  name: multipart_body
38
- requirement: &27683420 !ruby/object:Gem::Requirement
39
- none: false
43
+ requirement: !ruby/object:Gem::Requirement
40
44
  requirements:
41
- - - ! '>='
45
+ - - '>='
42
46
  - !ruby/object:Gem::Version
43
47
  version: 0.2.1
44
48
  type: :runtime
45
49
  prerelease: false
46
- version_requirements: *27683420
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - '>='
53
+ - !ruby/object:Gem::Version
54
+ version: 0.2.1
47
55
  - !ruby/object:Gem::Dependency
48
56
  name: rake
49
- requirement: &27682940 !ruby/object:Gem::Requirement
50
- none: false
57
+ requirement: !ruby/object:Gem::Requirement
51
58
  requirements:
52
- - - ! '>='
59
+ - - '>='
53
60
  - !ruby/object:Gem::Version
54
61
  version: 0.8.7
55
62
  type: :development
56
63
  prerelease: false
57
- version_requirements: *27682940
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - '>='
67
+ - !ruby/object:Gem::Version
68
+ version: 0.8.7
58
69
  - !ruby/object:Gem::Dependency
59
70
  name: minitest
60
- requirement: &27682280 !ruby/object:Gem::Requirement
61
- none: false
71
+ requirement: !ruby/object:Gem::Requirement
62
72
  requirements:
63
- - - ! '>='
73
+ - - '>='
64
74
  - !ruby/object:Gem::Version
65
75
  version: 2.1.0
66
76
  type: :development
67
77
  prerelease: false
68
- version_requirements: *27682280
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - '>='
81
+ - !ruby/object:Gem::Version
82
+ version: 2.1.0
69
83
  - !ruby/object:Gem::Dependency
70
84
  name: fakeweb
71
- requirement: &27681620 !ruby/object:Gem::Requirement
72
- none: false
85
+ requirement: !ruby/object:Gem::Requirement
73
86
  requirements:
74
- - - ! '>='
87
+ - - '>='
75
88
  - !ruby/object:Gem::Version
76
89
  version: 1.3.0
77
90
  type: :development
78
91
  prerelease: false
79
- version_requirements: *27681620
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - '>='
95
+ - !ruby/object:Gem::Version
96
+ version: 1.3.0
80
97
  description: validate-website is a web crawler for checking the markup validity with
81
98
  XML Schema / DTD and not found urls.
82
99
  email: laurent@spkdev.net
@@ -86,7 +103,6 @@ executables:
86
103
  extensions: []
87
104
  extra_rdoc_files: []
88
105
  files:
89
- - README.rdoc
90
106
  - Rakefile
91
107
  - LICENSE
92
108
  - lib/validate_website.rb
@@ -199,27 +215,24 @@ files:
199
215
  - data/schemas/xhtml-iframe-1.xsd
200
216
  - data/schemas/xhtml-framework-1.xsd
201
217
  - data/schemas/xhtml-basic10.xsd
202
- - !binary |-
203
- YmluL3ZhbGlkYXRlLXdlYnNpdGU=
204
- - !binary |-
205
- YmluL3ZhbGlkYXRlLXdlYnNpdGUtc3RhdGlj
218
+ - bin/validate-website
219
+ - bin/validate-website-static
206
220
  homepage: http://github.com/spk/validate-website
207
221
  licenses:
208
222
  - MIT
223
+ metadata: {}
209
224
  post_install_message:
210
225
  rdoc_options: []
211
226
  require_paths:
212
227
  - lib
213
228
  required_ruby_version: !ruby/object:Gem::Requirement
214
- none: false
215
229
  requirements:
216
- - - ! '>='
230
+ - - '>='
217
231
  - !ruby/object:Gem::Version
218
232
  version: '0'
219
233
  required_rubygems_version: !ruby/object:Gem::Requirement
220
- none: false
221
234
  requirements:
222
- - - ! '>='
235
+ - - '>='
223
236
  - !ruby/object:Gem::Version
224
237
  version: '0'
225
238
  requirements:
@@ -227,9 +240,9 @@ requirements:
227
240
  - rainbow
228
241
  - multipart_body
229
242
  rubyforge_project:
230
- rubygems_version: 1.8.11
243
+ rubygems_version: 2.0.0
231
244
  signing_key:
232
- specification_version: 3
245
+ specification_version: 4
233
246
  summary: Web crawler for checking the validity of your documents
234
247
  test_files:
235
248
  - spec/validator_spec.rb
data/README.rdoc DELETED
@@ -1,114 +0,0 @@
1
- = validate-website - Web crawler for checking the validity of your documents
2
-
3
- == INSTALLATION
4
-
5
- === Debian
6
-
7
- aptitude install rubygems ruby-dev libxslt-dev libxml2-dev
8
-
9
- === RubyGems
10
-
11
- gem install validate-website
12
-
13
- == SYNOPSIS
14
-
15
- validate-website [OPTIONS]
16
- validate-website-static [OPTIONS]
17
-
18
- == DESCRIPTION
19
-
20
- validate-website is a web crawler for checking the markup validity with XML
21
- Schema / DTD and not found urls (more info doc/validate-website.txt).
22
-
23
- validate-website-static checks the markup validity of your local documents with
24
- XML Schema / DTD (more info doc/validate-website-static.txt).
25
-
26
- HTML5 support with Validator.nu Web Service.
27
-
28
- == VALIDATE WEBSITE OPTIONS
29
-
30
- -s, --site SITE
31
- Website to crawl (Default: http://localhost:3000/)
32
- -u, --user-agent USERAGENT
33
- Change user agent (Default: Anemone/VERSION)
34
- -e, --exclude EXCLUDE
35
- Url to exclude (ex: redirect|news)
36
- -i, --ignore-errors IGNORE
37
- Ignore certain validation errors (ex: autocorrect)
38
- -f, --file FILE
39
- Save not well formed or not found (with -n used) urls
40
- -c, --cookies COOKIES
41
- Set defaults cookies
42
- -m, --[no-]markup-validation
43
- Markup validation (Default: true)
44
- -n, --not-found
45
- Log not found url (Default: false)
46
- --[no-]color
47
- Show colored output (Default: true)
48
- -v, --verbose
49
- Show detail of validator errors (Default: false).
50
- -q, --quiet
51
- Only report errors (Default: false).
52
- -d, --debug
53
- Show anemone log (Default: false)
54
- -h, --help
55
- Show help message and exit.
56
-
57
- == EXIT STATUS
58
- 0::
59
- Markup is valid and no 404 found.
60
- 64::
61
- Not valid markup found.
62
- 65::
63
- There are pages not found.
64
- 66::
65
- There are not valid markup and pages not found.
66
-
67
- == On your application
68
-
69
- require 'validate_website/validator'
70
- body = '<!DOCTYPE html><html></html>'
71
- v = ValidateWebsite::Validator.new(Nokogiri::HTML(body), body)
72
- v.valid? # => false
73
-
74
- == With RSpec
75
-
76
- On spec/spec_helper.rb:
77
-
78
- require 'validate_website/validator'
79
- require 'validate_website/rspec'
80
-
81
- On your spec/controllers:
82
-
83
- it 'should be valid' do
84
- response.body.should be_w3c_valid
85
- end
86
-
87
- == REQUIREMENTS
88
-
89
- See validate-website.gemspec file.
90
-
91
- == CREDITS
92
-
93
- * Thanks tenderlove for Nokogiri, this tool is inspired from markup_validity.
94
- * And Chris Kite for Anemone web-spider framework.
95
-
96
- == MORE INFO
97
-
98
- The HTML5 support is done by using the Validator.nu Web Service, so the content
99
- of your webpage is logged by a tier. It's not the case for other validation
100
- because validate-website use the XML Schema or DTD stored on the data/ directory.
101
-
102
- Please read http://about.validator.nu/#tos for more info on the HTML5
103
- validation service.
104
-
105
- == CONTRIBUTORS
106
-
107
- * François de Metz (francois2metz)
108
- * Bruno Michel (nono)
109
- * Matt Brictson (mbrictson)
110
-
111
- == LICENSE
112
- The MIT License
113
-
114
- Copyright (c) 2009-2012 Laurent Arnoud <laurent@spkdev.net>