validate-website 0.4.0 → 0.4.1
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +1 -1
- data/bin/validate-website +3 -0
- data/lib/validate_website.rb +6 -5
- data/spec/data/html5.html +46 -0
- data/spec/data/xhtml1-strict.html +19 -0
- data/spec/validate_website_spec.rb +53 -0
- data/spec/validator_spec.rb +34 -0
- metadata +8 -5
- data/spec/css_spec.rb +0 -53
data/Rakefile
CHANGED
data/bin/validate-website
CHANGED
|
@@ -13,7 +13,10 @@ options = validate_website.options
|
|
|
13
13
|
exit_code = validate_website.crawl options[:site],
|
|
14
14
|
:markup_validation => options[:markup_validation],
|
|
15
15
|
:user_agent => options[:useragent],
|
|
16
|
+
:exclude => options[:exclude],
|
|
17
|
+
:file => options[:file],
|
|
16
18
|
:authorization => options[:auth],
|
|
19
|
+
:not_found => options[:not_found],
|
|
17
20
|
:cookies => options[:cookies],
|
|
18
21
|
:accept_cookies => options[:accept_cookies],
|
|
19
22
|
:verbose => options[:debug],
|
data/lib/validate_website.rb
CHANGED
|
@@ -12,8 +12,8 @@ class ValidateWebsite
|
|
|
12
12
|
|
|
13
13
|
def initialize(args=[])
|
|
14
14
|
@options = {
|
|
15
|
-
:markup_validation => true,
|
|
16
15
|
:site => 'http://localhost:3000/',
|
|
16
|
+
:markup_validation => true,
|
|
17
17
|
:useragent => Anemone::Core::DEFAULT_OPTS[:user_agent],
|
|
18
18
|
:exclude => nil,
|
|
19
19
|
:file => nil,
|
|
@@ -78,10 +78,6 @@ class ValidateWebsite
|
|
|
78
78
|
return abs if abs && page.in_domain?(abs)
|
|
79
79
|
end
|
|
80
80
|
|
|
81
|
-
def to_file(msg)
|
|
82
|
-
open(options[:file], 'a').write("#{msg}\n") if options[:file]
|
|
83
|
-
end
|
|
84
|
-
|
|
85
81
|
def crawl(site, opts={})
|
|
86
82
|
exit_code = 0
|
|
87
83
|
|
|
@@ -140,4 +136,9 @@ class ValidateWebsite
|
|
|
140
136
|
end
|
|
141
137
|
exit_code
|
|
142
138
|
end
|
|
139
|
+
|
|
140
|
+
private
|
|
141
|
+
def to_file(msg)
|
|
142
|
+
open(options[:file], 'a').write("#{msg}\n") if options[:file]
|
|
143
|
+
end
|
|
143
144
|
end
|
|
@@ -0,0 +1,46 @@
|
|
|
1
|
+
<!DOCTYPE html>
|
|
2
|
+
<html lang="en">
|
|
3
|
+
<head>
|
|
4
|
+
<meta charset="utf-8" />
|
|
5
|
+
<title>title</title>
|
|
6
|
+
<!-- meta -->
|
|
7
|
+
<meta name="description" content="" />
|
|
8
|
+
<meta name="keywords" content="" />
|
|
9
|
+
<meta name="author" content="" />
|
|
10
|
+
</head>
|
|
11
|
+
<body>
|
|
12
|
+
<header>
|
|
13
|
+
<nav>
|
|
14
|
+
<ul>
|
|
15
|
+
<li><a href="/my-url1" title="title">my url</a></li>
|
|
16
|
+
<li><a href="/my-url2" title="title">my url</a></li>
|
|
17
|
+
<li><a href="/my-url3" title="title">my url</a></li>
|
|
18
|
+
</ul>
|
|
19
|
+
</nav>
|
|
20
|
+
</header>
|
|
21
|
+
|
|
22
|
+
<div>
|
|
23
|
+
<article>
|
|
24
|
+
<h1>article title</h1>
|
|
25
|
+
<p>texte de my article</p>
|
|
26
|
+
<section>
|
|
27
|
+
<h2>article subtitle</h2>
|
|
28
|
+
<p>text</p>
|
|
29
|
+
<figure>
|
|
30
|
+
<a href="/my-url4"><img src="image.png" alt="my image"></a>
|
|
31
|
+
</figure>
|
|
32
|
+
</section>
|
|
33
|
+
</article>
|
|
34
|
+
</div>
|
|
35
|
+
|
|
36
|
+
<footer>
|
|
37
|
+
<nav>
|
|
38
|
+
<ul>
|
|
39
|
+
<li><a href="/my-url5" title="title">my url</a></li>
|
|
40
|
+
<li><a href="/my-url6" title="title">my url</a></li>
|
|
41
|
+
<li><a href="/my-url7" title="title">my url</a></li>
|
|
42
|
+
</ul>
|
|
43
|
+
</nav>
|
|
44
|
+
</footer>
|
|
45
|
+
</body>
|
|
46
|
+
</html>
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
<?xml version="1.0" encoding="UTF-8"?>
|
|
2
|
+
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
|
|
3
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
|
4
|
+
<html xmlns="http://www.w3.org/1999/xhtml">
|
|
5
|
+
<head>
|
|
6
|
+
<title>title</title>
|
|
7
|
+
</head>
|
|
8
|
+
<body>
|
|
9
|
+
<h1>Title 1</h1>
|
|
10
|
+
<p>Paragraphe.</p>
|
|
11
|
+
|
|
12
|
+
<h2>Title 2</h2>
|
|
13
|
+
<ul>
|
|
14
|
+
<li><a href="/my-url1" title="title">my url</a></li>
|
|
15
|
+
<li><a href="/my-url2" title="title">my url</a></li>
|
|
16
|
+
<li><a href="/my-url1" title="title">my url</a></li>
|
|
17
|
+
</ul>
|
|
18
|
+
</body>
|
|
19
|
+
</html>
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper'
|
|
2
|
+
|
|
3
|
+
describe ValidateWebsite do
|
|
4
|
+
|
|
5
|
+
before(:each) do
|
|
6
|
+
FakeWeb.clean_registry
|
|
7
|
+
end
|
|
8
|
+
|
|
9
|
+
context('html') do
|
|
10
|
+
it "should extract url" do
|
|
11
|
+
name = 'xhtml1-strict'
|
|
12
|
+
file = File.join('spec', 'data', "#{name}.html")
|
|
13
|
+
page = FakePage.new(name,
|
|
14
|
+
:body => open(file).read,
|
|
15
|
+
:content_type => 'text/html')
|
|
16
|
+
validate_website = ValidateWebsite.new
|
|
17
|
+
validate_website.crawl(page.url)
|
|
18
|
+
validate_website.anemone.should have(3).pages
|
|
19
|
+
end
|
|
20
|
+
end
|
|
21
|
+
|
|
22
|
+
context('css') do
|
|
23
|
+
it "should crawl css and extract url" do
|
|
24
|
+
page = FakePage.new('test.css',
|
|
25
|
+
:body => ".test {background-image: url(pouet);}
|
|
26
|
+
.tests {background-image: url(/image/pouet.png)}
|
|
27
|
+
.tests {background-image: url(/image/pouet_42.png)}
|
|
28
|
+
.tests {background-image: url(/image/pouet)}",
|
|
29
|
+
:content_type => 'text/css')
|
|
30
|
+
validate_website = ValidateWebsite.new
|
|
31
|
+
validate_website.crawl(page.url)
|
|
32
|
+
validate_website.anemone.should have(5).pages
|
|
33
|
+
end
|
|
34
|
+
|
|
35
|
+
it "should extract url with single quote" do
|
|
36
|
+
page = FakePage.new('test.css',
|
|
37
|
+
:body => ".test {background-image: url('pouet');}",
|
|
38
|
+
:content_type => 'text/css')
|
|
39
|
+
validate_website = ValidateWebsite.new
|
|
40
|
+
validate_website.crawl(page.url)
|
|
41
|
+
validate_website.anemone.should have(2).pages
|
|
42
|
+
end
|
|
43
|
+
|
|
44
|
+
it "should extract url with double quote" do
|
|
45
|
+
page = FakePage.new('test.css',
|
|
46
|
+
:body => ".test {background-image: url(\"pouet\");}",
|
|
47
|
+
:content_type => 'text/css')
|
|
48
|
+
validate_website = ValidateWebsite.new
|
|
49
|
+
validate_website.crawl(page.url)
|
|
50
|
+
validate_website.anemone.should have(2).pages
|
|
51
|
+
end
|
|
52
|
+
end
|
|
53
|
+
end
|
|
@@ -0,0 +1,34 @@
|
|
|
1
|
+
require File.dirname(__FILE__) + '/spec_helper'
|
|
2
|
+
|
|
3
|
+
describe Validator do
|
|
4
|
+
before(:each) do
|
|
5
|
+
FakeWeb.clean_registry
|
|
6
|
+
@http = Anemone::HTTP.new
|
|
7
|
+
end
|
|
8
|
+
|
|
9
|
+
it "xhtml1-strict should be valid" do
|
|
10
|
+
name = 'xhtml1-strict'
|
|
11
|
+
dtd_uri = 'http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd'
|
|
12
|
+
file = File.join('spec', 'data', "#{name}.html")
|
|
13
|
+
page = FakePage.new(name,
|
|
14
|
+
:body => open(file).read,
|
|
15
|
+
:content_type => 'text/html')
|
|
16
|
+
@xhtml1_page = @http.fetch_page(page.url)
|
|
17
|
+
validator = Validator.new(@xhtml1_page)
|
|
18
|
+
validator.dtd.system_id.should == dtd_uri
|
|
19
|
+
validator.namespace.should == name
|
|
20
|
+
validator.should be_valid
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
it "html5 should be valid" do
|
|
24
|
+
pending("need to work on html5")
|
|
25
|
+
name = 'html5'
|
|
26
|
+
file = File.join('spec', 'data', "#{name}.html")
|
|
27
|
+
page = FakePage.new(name,
|
|
28
|
+
:body => open(file).read,
|
|
29
|
+
:content_type => 'text/html')
|
|
30
|
+
@html5_page = @http.fetch_page(page.url)
|
|
31
|
+
validator = Validator.new(@html5_page)
|
|
32
|
+
validator.should be_valid
|
|
33
|
+
end
|
|
34
|
+
end
|
metadata
CHANGED
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: validate-website
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
hash:
|
|
4
|
+
hash: 13
|
|
5
5
|
prerelease: false
|
|
6
6
|
segments:
|
|
7
7
|
- 0
|
|
8
8
|
- 4
|
|
9
|
-
-
|
|
10
|
-
version: 0.4.
|
|
9
|
+
- 1
|
|
10
|
+
version: 0.4.1
|
|
11
11
|
platform: ruby
|
|
12
12
|
authors:
|
|
13
13
|
- Laurent Arnoud
|
|
@@ -15,7 +15,7 @@ autorequire:
|
|
|
15
15
|
bindir: bin
|
|
16
16
|
cert_chain: []
|
|
17
17
|
|
|
18
|
-
date: 2010-
|
|
18
|
+
date: 2010-10-24 00:00:00 +02:00
|
|
19
19
|
default_executable:
|
|
20
20
|
dependencies:
|
|
21
21
|
- !ruby/object:Gem::Dependency
|
|
@@ -186,9 +186,12 @@ files:
|
|
|
186
186
|
- lib/xhtml/xhtml-ruby-1.xsd
|
|
187
187
|
- lib/validate_website.rb
|
|
188
188
|
- bin/validate-website
|
|
189
|
+
- spec/validator_spec.rb
|
|
189
190
|
- spec/spec_helper.rb
|
|
190
|
-
- spec/
|
|
191
|
+
- spec/data/html5.html
|
|
192
|
+
- spec/data/xhtml1-strict.html
|
|
191
193
|
- spec/fakeweb_helper.rb
|
|
194
|
+
- spec/validate_website_spec.rb
|
|
192
195
|
has_rdoc: true
|
|
193
196
|
homepage: http://github.com/spk/validate-website
|
|
194
197
|
licenses: []
|
data/spec/css_spec.rb
DELETED
|
@@ -1,53 +0,0 @@
|
|
|
1
|
-
require File.dirname(__FILE__) + '/spec_helper'
|
|
2
|
-
|
|
3
|
-
describe ValidateWebsite do
|
|
4
|
-
|
|
5
|
-
before(:each) do
|
|
6
|
-
FakeWeb.clean_registry
|
|
7
|
-
end
|
|
8
|
-
|
|
9
|
-
it "should crawl css and extract url" do
|
|
10
|
-
pages = []
|
|
11
|
-
pages << FakePage.new('test.css',
|
|
12
|
-
:body => ".test {background-image: url(pouet);}
|
|
13
|
-
.tests {background-image: url(/image/pouet.png)}
|
|
14
|
-
.tests {background-image: url(/image/pouet_42.png)}
|
|
15
|
-
.tests {background-image: url(/image/pouet)}",
|
|
16
|
-
:content_type => 'text/css')
|
|
17
|
-
pages << FakePage.new('pouet',
|
|
18
|
-
:content_type => 'image/png')
|
|
19
|
-
pages << FakePage.new('image/pouet',
|
|
20
|
-
:content_type => 'image/png')
|
|
21
|
-
pages << FakePage.new('image/pouet.png',
|
|
22
|
-
:content_type => 'image/png')
|
|
23
|
-
pages << FakePage.new('image/pouet_42.png',
|
|
24
|
-
:content_type => 'image/png')
|
|
25
|
-
validate_website = ValidateWebsite.new
|
|
26
|
-
validate_website.crawl(pages[0].url)
|
|
27
|
-
validate_website.anemone.should have(5).pages
|
|
28
|
-
end
|
|
29
|
-
|
|
30
|
-
it "should extract url with single quote" do
|
|
31
|
-
pages = []
|
|
32
|
-
pages << FakePage.new('test.css',
|
|
33
|
-
:body => ".test {background-image: url('pouet');}",
|
|
34
|
-
:content_type => 'text/css')
|
|
35
|
-
pages << FakePage.new('pouet',
|
|
36
|
-
:content_type => 'image/png')
|
|
37
|
-
validate_website = ValidateWebsite.new
|
|
38
|
-
validate_website.crawl(pages[0].url)
|
|
39
|
-
validate_website.anemone.should have(2).pages
|
|
40
|
-
end
|
|
41
|
-
|
|
42
|
-
it "should extract url with double quote" do
|
|
43
|
-
pages = []
|
|
44
|
-
pages << FakePage.new('test.css',
|
|
45
|
-
:body => ".test {background-image: url(\"pouet\");}",
|
|
46
|
-
:content_type => 'text/css')
|
|
47
|
-
pages << FakePage.new('pouet',
|
|
48
|
-
:content_type => 'image/png')
|
|
49
|
-
validate_website = ValidateWebsite.new
|
|
50
|
-
validate_website.crawl(pages[0].url)
|
|
51
|
-
validate_website.anemone.should have(2).pages
|
|
52
|
-
end
|
|
53
|
-
end
|