validate-website 1.0.0 → 1.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 278cca47ee331ef1b68e0c64aaca600af25917d6
-  data.tar.gz: cdb2ba927605214d326b080d5dad5afe4a6a4930
+  metadata.gz: 46efde8e3afaf965afb3a61893bbf6070bf3ee78
+  data.tar.gz: ddcf5e37e699eb74ae6fc299bb7366323c34c2bf
 SHA512:
-  metadata.gz: fde7934823f6e0b41d4baa22a784758c756d104ed2a91429585c50291be9b4e3bf9da60f978fe82bdba05e22d01b5157f0bace57a6f5c3398f6492117e941775
-  data.tar.gz: bf687a37f1a933a981a1696e88ef0b00f311c46db635170b2021faf46475bb44c5612715abbedd96a14cb05e159954716d058e056e09db97ec118c221e1953ca
+  metadata.gz: 7e137db2244e39a6f9fd12d36b8ed5c477f59bd22a6edb8f010315fe27c8fe1d60fbdeeb590396b6a25e01993ce69579a8bc8006b06b2b5a4759e739679b3c22
+  data.tar.gz: 75d4c6e34efa984b0bf0b998fc790f89422742ac40d7cf7b7c5a02e744abf66ac0a9eba0f08a99161e30aeaae07276c3f1ca62bb604ee31e6b18424851f0eda9

data/Rakefile

@@ -8,10 +8,10 @@ RDoc::Task.new do |rd|
   rd.rdoc_files.include("README.rdoc", "lib/**/*.rb")
 end
 
-# install asciidoc libxml2-utils xmlto
+# install asciidoc libxml2-utils xmlto docbook-xsl docbook-xml
 desc 'Update manpage from asciidoc file'
 task :manpage do
-  system('find doc/ -type f -exec a2x -f manpage -D man/man1 {} \;')
+  system('find doc/ -type f -exec a2x -d manpage -f manpage -D man/man1 {} \;')
 end
 
 Rake::TestTask.new do |t|

data/lib/validate_website/core.rb

@@ -44,31 +44,7 @@ module ValidateWebsite
       @options.merge!(ignore_links: @options[:exclude]) if @options[:exclude]
       puts color(:warning, "No internet connection") unless internet_connection?
 
-      @host = URI(@site).host
-      @crawler = Spidr.site(@site, @options) do |crawler|
-        crawler.cookies[@host] = default_cookies if @options[:cookies]
-        crawler.every_css_page do |page|
-          extract_urls_from_css(page).each do |u|
-            crawler.enqueue(u)
-          end
-        end
-
-        crawler.every_html_page do |page|
-          extract_imgs_from_page(page).each do |i|
-            crawler.enqueue(i)
-          end
-
-          if @options[:markup] && page.html?
-            validate(page.doc, page.body, page.url, @options[:ignore])
-          end
-        end
-
-        if @options[:not_found]
-          crawler.every_failed_url do |url|
-            not_found_error(url)
-          end
-        end
-      end
+      @crawler = spidr_crawler(@site, @options)
       print_status_line(@crawler.history.size,
                         @crawler.failures.size,
                         @not_founds_count,
@@ -115,9 +91,9 @@ module ValidateWebsite
     end
 
     def default_cookies
-      WEBrick::Cookie.parse(@options[:cookies]).inject({}) do |hash, cookie|
-        hash[cookie.name] = cookie.value
-        hash
+      WEBrick::Cookie.parse(@options[:cookies]).each_with_object({}) do |c, h|
+        h[c.name] = c.value
+        h
       end
     end
 
@@ -231,5 +207,33 @@ module ValidateWebsite
                          "#{not_founds} not founds",
                          "#{errors} errors"].join(', '), @options[:color])
     end
+
+    def spidr_crawler(site, options)
+      @host = URI(site).host
+      Spidr.site(site, options) do |crawler|
+        crawler.cookies[@host] = default_cookies if options[:cookies]
+        crawler.every_css_page do |page|
+          extract_urls_from_css(page).each do |u|
+            crawler.enqueue(u)
+          end
+        end
+
+        crawler.every_html_page do |page|
+          extract_imgs_from_page(page).each do |i|
+            crawler.enqueue(i)
+          end
+
+          if options[:markup] && page.html?
+            validate(page.doc, page.body, page.url, options[:ignore])
+          end
+        end
+
+        if options[:not_found]
+          crawler.every_failed_url do |url|
+            not_found_error(url)
+          end
+        end
+      end
+    end
   end
 end

data/lib/validate_website/validator.rb

@@ -6,7 +6,7 @@ module ValidateWebsite
   # Document validation from DTD or XSD (webservice for html5)
   class Validator
     XHTML_PATH = File.expand_path('../../../data/schemas', __FILE__)
-    HTML5_VALIDATOR_SERVICE = 'http://html5.validator.nu/'
+    HTML5_VALIDATOR_SERVICE = 'http://validator.w3.org/nu/'
 
     attr_reader :original_doc, :body, :dtd, :doc, :namespace, :xsd, :errors
 

data/man/man1/validate-website-static.1

@@ -2,12 +2,12 @@
 .\"     Title: validate-website-static
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
-.\"      Date: 09/26/2014
+.\"      Date: 02/12/2015
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE\-S" "1" "09/26/2014" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE\-S" "1" "02/12/2015" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -59,7 +59,7 @@ Ignore certain validation errors (ex:
 Markup validation (Default: true)
 .RE
 .PP
-\fB\-n\fR, \fB\-\-notfound\fR
+\fB\-n\fR, \fB\-\-not\-found\fR
 .RS 4
 Log files not on filesystem, pwd considered as root \(Fo / \(Fc (Default: false)
 .RE
@@ -106,4 +106,4 @@ Laurent Arnoud <laurent@spkdev\&.net>
 .sp
 The MIT License
 .sp
-Copyright (c) 2009\-2014 Laurent Arnoud <laurent@spkdev\&.net>
+Copyright (c) 2009\-2015 Laurent Arnoud <laurent@spkdev\&.net>

data/man/man1/validate-website.1

@@ -2,12 +2,12 @@
 .\"     Title: validate-website
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: DocBook XSL Stylesheets v1.78.1 <http://docbook.sf.net/>
-.\"      Date: 09/26/2014
+.\"      Date: 02/12/2015
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE" "1" "09/26/2014" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE" "1" "02/12/2015" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -43,6 +43,11 @@ Website to crawl (Default:
 http://localhost:3000/)
 .RE
 .PP
+\fB\-u\fR, \fB\-\-user\-agent\fR \fIUSERAGENT\fR
+.RS 4
+Change user agent (Default: Spidr\&.user_agent)
+.RE
+.PP
 \fB\-e\fR, \fB\-\-exclude\fR \fIEXCLUDE\fR
 .RS 4
 Url to exclude (ex:
@@ -65,7 +70,7 @@ Set defaults cookies
 Markup validation (Default: true)
 .RE
 .PP
-\fB\-n\fR, \fB\-\-notfound\fR
+\fB\-n\fR, \fB\-\-not\-found\fR
 .RS 4
 Log not found url (Default: false)
 .RE
@@ -112,4 +117,4 @@ Laurent Arnoud <laurent@spkdev\&.net>
 .sp
 The MIT License
 .sp
-Copyright (c) 2009\-2014 Laurent Arnoud <laurent@spkdev\&.net>
+Copyright (c) 2009\-2015 Laurent Arnoud <laurent@spkdev\&.net>

data/spec/core_spec.rb

@@ -2,7 +2,6 @@
 require File.expand_path('../spec_helper', __FILE__)
 
 describe ValidateWebsite::Core do
-
   before do
     WebMock.reset!
     stub_request(:get, ValidateWebsite::Core::PING_URL).to_return(status: 200)
@@ -20,8 +19,10 @@ describe ValidateWebsite::Core do
 
   describe 'options' do
     it 'can change user-agent' do
-      ua = 'Linux / Firefox 29: Mozilla/5.0 (X11; Linux x86_64; rv:29.0) Gecko/20100101 Firefox/29.0'
-      v = ValidateWebsite::Core.new({site: SPEC_DOMAIN, user_agent: ua}, :crawl)
+      ua = %{Linux / Firefox 29: Mozilla/5.0 (X11; Linux x86_64; rv:29.0) \
+      Gecko/20100101 Firefox/29.0}
+      v = ValidateWebsite::Core.new({ site: SPEC_DOMAIN, user_agent: ua },
+                                    :crawl)
       v.crawl
       v.crawler.user_agent.must_equal ua
     end
@@ -30,7 +31,8 @@ describe ValidateWebsite::Core do
   describe('cookies') do
     it 'can set cookies' do
       cookies = 'tz=Europe%2FBerlin; guid=ZcpBshbtStgl9VjwTofq'
-      v = ValidateWebsite::Core.new({site: SPEC_DOMAIN, cookies: cookies}, :crawl)
+      v = ValidateWebsite::Core.new({ site: SPEC_DOMAIN, cookies: cookies },
+                                    :crawl)
       v.crawl
       v.crawler.cookies.cookies_for_host(v.host).must_equal v.default_cookies
     end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: validate-website
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.0.1
 platform: ruby
 authors:
 - Laurent Arnoud
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-10-18 00:00:00.000000000 Z
+date: 2015-02-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: spidr