validate-website 0.5.3 → 0.5.7

data/README.rdoc

@@ -29,8 +29,6 @@ found urls.
       Url to exclude (ex: redirect|news)
   -f, --file FILE
       Save not well formed or not found (with -n used) urls
-  -a, --authorization USER,PASS
-      Basic http authentification
   -c, --cookies COOKIES
       Set defaults cookies
   -m, --[no-]markup-validation

data/Rakefile

@@ -7,7 +7,7 @@ require "rspec/core/rake_task" # RSpec 2.0
 # Globals
 
 PKG_NAME = 'validate-website'
-PKG_VERSION = '0.5.3'
+PKG_VERSION = '0.5.7'
 
 PKG_FILES = ['README.rdoc', 'Rakefile', 'LICENSE']
 Find.find('bin/', 'lib/', 'man/', 'spec/') do |f|
@@ -43,15 +43,15 @@ spec = Gem::Specification.new do |s|
   s.summary = 'Web crawler for checking the validity of your documents'
   s.name = PKG_NAME
   s.version = PKG_VERSION
-  s.requirements << 'spk-anemone' << 'rainbow' << 'spk-html5'
-  s.add_dependency('spk-anemone', '>= 0.4.0')
+  s.requirements << 'anemone' << 'rainbow'
+  s.add_dependency('anemone', '>= 0.5.0')
   s.add_dependency('rainbow', '>= 1.1')
-  s.add_dependency('spk-html5', '= 0.10.1')
   s.add_development_dependency('rspec', '>= 2.0.0')
   s.add_development_dependency('fakeweb', '>= 1.3.0')
   s.require_path = 'lib'
   s.bindir = 'bin'
   s.executables << 'validate-website'
+  s.executables << 'validate-website-static'
   s.files = PKG_FILES
   s.description = 'validate-website is a web crawler for checking the markup' +
     'validity and not found urls.'

data/bin/validate-website

@@ -11,19 +11,6 @@ require 'rubygems' if developer_mode
 require 'validate_website'
 
 validate_website = ValidateWebsite.new(ARGV)
-options = validate_website.options
-
-validate_website.crawl options[:site],
-  :markup_validation => options[:markup_validation],
-  :user_agent        => options[:user_agent],
-  :exclude           => options[:exclude],
-  :file              => options[:file],
-  :authorization     => options[:authorization],
-  :not_found         => options[:not_found],
-  :cookies           => options[:cookies],
-  :accept_cookies    => options[:accept_cookies],
-  :verbose           => options[:debug],
-  :validate_verbose  => options[:verbose],
-  :quiet             => options[:quiet]
+validate_website.crawl
 
 exit(validate_website.exit_status)

data/bin/validate-website-static

@@ -0,0 +1,25 @@
+#!/usr/bin/env ruby
+# encoding: utf-8
+
+lib_dir = File.join(File.dirname(__FILE__), '..', 'lib')
+$:.unshift(File.expand_path(lib_dir))
+
+developer_mode = false
+developer_mode = true if __FILE__ == $0
+require 'rubygems' if developer_mode
+
+require 'validate_website'
+
+validate_website = ValidateWebsite.new(ARGV)
+
+files = Dir.glob(File.join("**", "*.html"))
+files.each do |f|
+  next unless File.file?(f)
+
+  body = open(f).read
+  doc = Nokogiri::HTML(body)
+
+  validate_website.validate(doc, body, f)
+end
+
+exit(validate_website.exit_status)

data/lib/validate_website.rb

@@ -2,12 +2,15 @@
 
 require 'optparse'
 require 'open-uri'
+
 require 'validator'
-require 'anemone'
 require 'colorful_messages'
 
+require 'anemone'
+
 class ValidateWebsite
 
+  attr_accessor :site
   attr_reader :options, :anemone
 
   include ColorfulMessages
@@ -17,34 +20,42 @@ class ValidateWebsite
   EXIT_FAILURE_NOT_FOUND = 65
   EXIT_FAILURE_MARKUP_NOT_FOUND = 66
 
-  def initialize(args=[])
+  def initialize(args=[], validation_type = :crawl)
     @markup_error = nil
     @not_found_error = nil
 
-    @options = {
+    @options_crawl = {
       :site              => 'http://localhost:3000/',
       :markup_validation => true,
-      :user_agent        => Anemone::Core::DEFAULT_OPTS[:user_agent],
       :exclude           => nil,
       :file              => nil,
-      :authorization     => nil,
       # log not found url (404 status code)
       :not_found         => false,
+      # internal verbose for ValidateWebsite
+      :validate_verbose  => false,
+      :quiet             => false,
+
+      # Anemone options see anemone/lib/anemone/core.rb
+      :verbose           => false,
+      :user_agent        => Anemone::Core::DEFAULT_OPTS[:user_agent],
       :cookies           => nil,
       :accept_cookies    => true,
-      :verbose           => false,
-      :debug             => false,
-      :quiet             => false,
+      :redirect_limit    => 0,
     }
-    parse(args)
+    send("parse_#{validation_type}_options", args)
 
-    # truncate file
-    if options[:file]
-      open(options[:file], 'w').write('')
+    @file = @options[:file]
+    if @file
+      # truncate file
+      open(@file, 'w').write('')
     end
+
+    @site = @options[:site]
   end
 
-  def parse(args)
+  def parse_crawl_options(args)
+    @options = @options_crawl
+
     opts = OptionParser.new do |o|
       o.set_summary_indent('  ')
       o.banner =    'Usage: validate-website [OPTIONS]'
@@ -66,12 +77,10 @@ class ValidateWebsite
       }
       o.on("-f", "--file 'FILE'", String,
            "Save not well formed or not found urls") { |v| @options[:file] = v }
-      o.on("-a", "--authorization 'USER,PASS'", Array,
-           "Basic http authentification") { |v|
-        @options[:authorization] = v
-      }
+
       o.on("-c", "--cookies 'COOKIES'", String,
            "Set defaults cookies") { |v| @options[:cookies] = v }
+
       o.on("-m", "--[no-]markup-validation",
            "Markup validation (Default: #{@options[:markup_validation]})") { |v|
         @options[:markup_validation] = v
@@ -81,16 +90,16 @@ class ValidateWebsite
         @options[:not_found] = v
       }
       o.on("-v", "--verbose",
-           "Show validator errors (Default: #{@options[:verbose]})") { |v|
-        @options[:verbose] = v
+           "Show validator errors (Default: #{@options[:validate_verbose]})") { |v|
+        @options[:validate_verbose] = v
       }
       o.on("-q", "--quiet",
            "Only report errors (Default: #{@options[:quiet]})") { |v|
         @options[:quiet] = v
       }
       o.on("-d", "--debug",
-           "Show anemone log (Default: #{@options[:debug]})") { |v|
-        @options[:debug] = v
+           "Show anemone log (Default: #{@options[:verbose]})") { |v|
+        @options[:verbose] = v
       }
 
       o.separator ""
@@ -99,12 +108,32 @@ class ValidateWebsite
     opts.parse!(args)
   end
 
-  def crawl(site, opts={})
-    puts note("Validating #{site}") if opts[:validate_verbose]
+  def validate(doc, body, url, opts={})
+    opts = @options.merge(opts)
+    validator = Validator.new(doc, body)
+    msg = " well formed? %s" % validator.valid?
+    if validator.valid?
+      unless opts[:quiet]
+        print info(url)
+        puts success(msg)
+      end
+    else
+      @markup_error = true
+      print info(url)
+      puts error(msg)
+      puts error(validator.errors.join(", ")) if opts[:validate_verbose]
+      to_file(url)
+    end
+  end
 
-    @anemone = Anemone.crawl(site, opts) do |anemone|
+  def crawl(opts={})
+    opts = @options.merge(opts)
+    puts note("Validating #{@site}") if opts[:validate_verbose]
+
+    @anemone = Anemone.crawl(@site, opts) do |anemone|
       anemone.skip_links_like Regexp.new(opts[:exclude]) if opts[:exclude]
 
+      # select the links on each page to follow (iframe, link, css url)
       anemone.focus_crawl { |p|
         links = []
         if p.html?
@@ -134,20 +163,7 @@ class ValidateWebsite
         if opts[:markup_validation]
           # validate html/html+xml
           if page.html? && page.fetched?
-            validator = Validator.new(page)
-            msg = " well formed? %s" % validator.valid?
-            if validator.valid?
-              unless opts[:quiet]
-                print info(url)
-                puts success(msg)
-              end
-            else
-              @markup_error = true
-              print info(url)
-              puts error(msg)
-              puts error(validator.errors.join(", ")) if opts[:validate_verbose]
-              to_file(url)
-            end
+            validate(page.doc, page.body, url, opts)
           end
         end
 
@@ -156,6 +172,9 @@ class ValidateWebsite
           puts error("%s linked in %s but not exist" % [url, page.referer])
           to_file(url)
         end
+
+        # throw away the page (hope this saves memory)
+        page = nil
       }
     end
   end
@@ -174,7 +193,9 @@ class ValidateWebsite
 
   private
   def to_file(msg)
-    open(options[:file], 'a').write("#{msg}\n") if options[:file]
+    if @file && File.exist?(@file)
+      open(@file, 'a').write("#{msg}\n")
+    end
   end
 
   def get_url(page, elem, attrname)

data/lib/validator.rb

@@ -3,19 +3,21 @@
 class Validator
   XHTML_PATH = File.join(File.dirname(__FILE__), '..', 'lib', 'xhtml')
 
-  attr_reader :page, :dtd, :doc, :namespace, :xsd, :errors
+  attr_reader :original_doc, :body, :dtd, :doc, :namespace, :xsd, :errors
 
-  def initialize(page)
-    @page = page
-    @dtd = @page.doc.internal_subset
+  def initialize(original_doc, body)
+    @original_doc = original_doc
+    @body = body
+    @dtd = @original_doc.internal_subset
     init_namespace(@dtd)
     @errors = []
+    @errors << 'Unknown document' if @namespace.nil?
 
-    if @namespace
-      if @dtd_uri && @page.body.match(@dtd_uri.to_s)
-        document = @page.body.sub(@dtd_uri.to_s, @namespace + '.dtd')
+    if @errors.empty?
+      if @dtd_uri && @body.match(@dtd_uri.to_s)
+        document = @body.sub(@dtd_uri.to_s, @namespace + '.dtd')
       else
-        document = @page.body
+        document = @body
       end
       @doc = Dir.chdir(XHTML_PATH) do
         Nokogiri::XML(document) { |cfg|
@@ -40,19 +42,8 @@ class Validator
         end
         @errors = @doc.errors
       end
-    elsif @page.body =~ /^\<!DOCTYPE html\>/i
-      # html5 doctype
-      # http://dev.w3.org/html5/spec/Overview.html#the-doctype
-      require 'html5'
-      require 'html5/filters/validator'
-      html5_parser = HTML5::HTMLParser.new(:tokenizer => HTMLConformanceChecker)
-      html5_parser.parse(@page.body)
-      @errors = html5_parser.errors.collect do |er|
-        "#{er[1]} line #{er[0][0]}"
-      end
-    else
-      @errors << 'Unknown Document'
     end
+
   rescue Nokogiri::XML::SyntaxError => e
     # http://nokogiri.org/tutorials/ensuring_well_formed_markup.html
     @errors << e

data/man/man1/validate-website.1

@@ -2,12 +2,12 @@
 .\"     Title: validate-website
 .\"    Author: [see the "AUTHOR" section]
 .\" Generator: DocBook XSL Stylesheets v1.75.2 <http://docbook.sf.net/>
-.\"      Date: 12/05/2010
+.\"      Date: 12/10/2010
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE" "1" "12/05/2010" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE" "1" "12/10/2010" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -59,11 +59,6 @@ Url to exclude (ex:
 Save not well formed or not found (with \-n used) urls
 .RE
 .PP
-\fB\-a\fR, \fB\-\-authorization\fR \fIUSER,PASS\fR
-.RS 4
-Basic http authentification
-.RE
-.PP
 \fB\-c\fR, \fB\-\-cookies\fR \fICOOKIES\fR
 .RS 4
 Set defaults cookies

data/spec/data/index.cs.html

@@ -0,0 +1,243 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
+<html lang="cs">
+<head>
+  <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-2">
+  <title>Debian -- Univerz�ln� opera�n� syst�m </title>
+  <link rev="made" href="mailto:webmaster@debian.org">
+  <link rel="shortcut icon" href="favicon.ico">
+  <meta name="Keywords" content="debian, GNU, linux, unix, open source, svobodn�, DFSG">
+  <meta name="Description" content="Debian GNU/Linux je svobodn� distribuce opera�n�ho syst�mu GNU/Linux. Je spravov�n a udr�ov�n za pomoci mnoha dobrovoln�k�, kte�� mu v�nuj� sv�j �as a zku�enosti.">
+  <meta name="Generator" content="WML 2.0.11 (19-Aug-2006)">
+  <meta name="Modified" content="2010-12-02 11:26:39">
+<link rel="alternate" type="application/rss+xml"
+ title="Bezpe�nostn� zpr�vy Debianu (pouze nadpisy)" href="security/dsa">
+<link rel="alternate" type="application/rss+xml"
+ title="Bezpe�nostn� zpr�vy Debianu (souhrn)" href="security/dsa-long">
+<link href="./debian.css" rel="stylesheet" type="text/css">
+  <link href="./debian-cs.css" rel="stylesheet" type="text/css" media="all">
+</head>
+<body>
+<div id="header">
+   <div id="upperheader">
+   <div id="logo">
+  <a href="./"><img src="./logos/openlogo-nd-50.png" width="50" height="61" alt=""></a>
+  <a href="./" rel="start"><img src="Pics/debian.png" width="179" height="61" alt="Projekt Debian"></a>
+  </div> <!-- end logo -->
+</div> <!-- end upperheader -->
+<!--UdmComment-->
+<div id="navbar">
+<p class="hidecss"><a href="#inner">P�esko�it Quicknav</a></p>
+<ul>
+   <li><a href="intro/about">O&nbsp;Debianu</a></li>
+   <li><a href="./News/">Novinky</a></li>
+   <li><a href="distrib/">Jak&nbsp;z�skat&nbsp;Debian</a></li>
+   <li><a href="./support">Podpora</a></li>
+   <li><a href="./devel/">V�voj��sk�&nbsp;koutek</a></li>
+   <li><a href="./sitemap">P�ehled str�nek</a></li>
+   <li><a href="http://search.debian.org/">Hledat</a></li>
+</ul>
+</div> <!-- end navbar -->
+</div> <!-- end header -->
+<!--/UdmComment-->
+<div id="outer">
+<div id="inner">
+<div id="leftcol">
+<!--UdmComment-->
+    <ul>
+    <li><a href="intro/about">O&nbsp;Debianu</a>
+      <ul>
+      <li><a href="./social_contract">Spole�ensk�&nbsp;smlouva</a></li>
+      <li><a href="./intro/free">Svobodn�&nbsp;software</a></li>
+      <li><a href="./partners/">Partne�i</a></li>
+      <li><a href="./donations">Dary</a></li>
+      <li><a href="./contact">Napi�te&nbsp;n�m</a></li>
+      </ul>
+    </li>
+    <li><a href="./News/">Novinky</a>
+      <ul>
+      <li><a href="./News/project/">Novinky&nbsp;projektu</a></li>
+      <li><a href="./events/">Ud�losti</a></li>
+      </ul>
+    </li>
+    <li><a href="distrib/">Jak&nbsp;z�skat&nbsp;Debian</a>
+      <ul>
+      <li><a href="CD/vendors/">Prodejci CD</a></li>
+      <li><a href="CD/">Obrazy CD</a></li>
+      <li><a href="distrib/netinst">S��ov� instalace</a></li>
+      <li><a href="distrib/pre-installed">P�edinstalovan�</a></li>
+      </ul>
+    </li>
+    <li><a href="distrib/packages">Debian�&nbsp;bal��ky</a></li>
+    <li><a href="doc/">Dokumentace</a>
+      <ul>
+      <li><a href="./releases/">Informace&nbsp;k&nbsp;verz�m</a></li>
+      <li><a href="./releases/stable/installmanual">Instala�n�&nbsp;p��ru�ka</a></li>
+      <li><a href="doc/books">Knihy&nbsp;o&nbsp;Debianu</a></li>
+      </ul>
+    </li>
+    <li><a href="./support">Podpora</a>
+      <ul>
+      <li><a href="./international/">Debian&nbsp;a&nbsp;jazyky</a></li>
+      <li><a href="./security/">Bezpe�nostn�&nbsp;informace</a></li>
+      <li><a href="Bugs/">Hl�en� chyb</a></li>
+      <li><a href="MailingLists/">Konference</a></li>
+      <li><a href="http://lists.debian.org/">Archivy&nbsp;konferenc�</a></li>
+      <li><a href="./ports/">Porty/architektury</a></li>
+      </ul>
+    </li>
+    <li><a href="misc/">Ostatn�</a></li>
+    <li><a href="./intro/help">Pomozte Debianu</a></li>
+    <li><a href="./devel/">V�voj��sk�&nbsp;koutek</a></li>
+    <li><a href="./sitemap">P�ehled str�nek</a></li>
+    <li><a href="http://search.debian.org/">Hledat</a></li>
+    </ul>
+    <form method="get" action="http://search.debian.org/">
+    <p>
+    <input type="text" name="q" size="12">
+    </p>
+    </form>
+    <p>
+    <a href="./sponsor.html"><img src="sponsor_img.jpg" alt="Nav�tivte sponzora str�nek" width="102" height="60"></a>
+    </p>
+    <p>
+    <a href="http://validator.w3.org/check/referer"><img src="http://www.w3.org/Icons/valid-html401" alt="Valid HTML 4.01!" width="88" height="31"></a>
+    </p>
+    <p>
+    <img src="http://jigsaw.w3.org/css-validator/images/vcss"
+        alt="Valid CSS!" width="88" height="31">
+    </p>
+<!--/UdmComment-->
+</div> <!-- end leftcol -->
+<div id="maincol">
+<a href="./News/2009/20090214"><img src="Pics/lennybanner_indexed.png" alt="Debian 5.0 - univerz�ln� opera�n� syst�m" width="380" height="310" style="margin-right: 10px; float: left;"></a>
+<h2>Co je Debian?</h2>
+<p><a href="http://www.debian.org/">Debian</a>
+je <a href="intro/free">svobodn�</a> opera�n� syst�m (OS) ur�en� k&nbsp;provozu
+na mnoha r�zn�ch typech po��ta��. Opera�n� syst�m se skl�d� ze z�kladn�ho
+programov�ho vybaven� a&nbsp;dal��ch n�stroj�, kter�ch je k&nbsp;provozu
+po��ta�e t�eba. Vlastn�m z�kladem OS je j�dro. Jeliko� Debian pou��v� j�dro
+<a href="http://www.kernel.org/">Linux</a> a&nbsp;v�t�ina z�kladn�ch syst�mov�ch
+program� byla vytvo�ena v&nbsp;r�mci <a href="http://www.gnu.org/">projektu GNU</a>,
+nese syst�m ozna�en� GNU/Linux.</p>
+<p>Debian GNU/Linux je v�ak v�ce ne� jen samotn� opera�n� syst�m. Obsahuje p�es
+25000 <a href="distrib/packages">bal��k�</a>
+s&nbsp;(p�edkompilovan�mi) programy a&nbsp;dokumentac�, p�ipraven�ch
+pro snadnou instalaci.</p>
+<p><a href="intro/about">Podrobnosti...</a></p>
+<hr>
+<h2>Za��n�me</h2>
+<p><a href="releases/stable/">Posledn� stabiln� verze Debianu</a> m� ��slo
+5.0. Tato verze byla naposledy aktualizov�na
+27. listopadu 2010. P�e�t�te si v�ce
+o&nbsp;<a href="releases/">dostupn�ch verz�ch Debianu</a>.</p>
+<p>Chcete-li za��t pou��vat Debian, m��ete jej z�skat na
+<a href="distrib/">distribu�n� str�nce</a> a&nbsp;pot� nainstalovat za pomoci
+<a href="releases/stable/installmanual">instala�n� p��ru�ky</a>.</p>
+<p>Pokud aktualizujete na nejnov�j�� stabiln� verzi z&nbsp;verze p�edchoz�,
+p�e�tete si pros�m nejprve
+<a href="releases/stable/releasenotes">pozn�mky k&nbsp;vyd�n�</a>.</p>
+<p>Pot�ebujete-li pomoc p�i pou��v�n� nebo nastaven� Debianu, pod�vejte se do
+<a href="doc/">dokumentace</a> nebo na str�nky
+s&nbsp;<a href="support">u�ivatelskou podporou</a>.</p>
+<p>Pro u�ivatele z&nbsp;neanglicky mluv�c�ch zem� jsou tu str�nky
+v�nuj�c� se podpo�e <a href="international/">ostatn�ch jazyk�</a>.</p>
+<p>U�ivatel� pracuj�c� s&nbsp;po��ta�i jin�ch hardwarov�ch platforem,
+ne� je Intel x86, najdou informace na str�nk�ch v�nuj�c�ch se
+<a href="ports/">ostatn�m platform�m</a>.</p>
+<hr>
+<h2>Novinky</h2>
+<p><tt>[27.11.2010]</tt> <strong><a href="News/2010/20101127">Updated Debian GNU/Linux: 5.0.7 released</a></strong><br>
+<tt>[16.11.2010]</tt> <strong><a href="News/2010/20101116b">Debian 6.0 <q>Squeeze</q>: Call for Upgrade and Installation tests</a></strong><br>
+<tt>[16.11.2010]</tt> <strong><a href="News/2010/20101116a">Debian Women IRC Training Sessions</a></strong><br>
+<tt>[02.11.2010]</tt> <strong><a href="News/2010/20101102">Mini-DebConf in Ho Chi Minh City, Vietnam during FOSSASIA 2010</a></strong><br>
+<tt>[19.10.2010]</tt> <strong><a href="News/2010/20101019">Debian to officially welcome non-packaging contributors</a></strong><br>
+<tt>[07.10.2010]</tt> <strong><a href="News/2010/20101007">Debian to be at the Society for Neuroscience meeting</a></strong><br>
+</p>
+<p>Star�� zpr�vy naleznete v&nbsp;<a href="./News/">archivu novinek</a>.
+Pokud chcete b�t o&nbsp;novink�ch ze sv�ta Debianu informov�ni elektronickou
+po�tou, p�ihlaste se do konference
+<a href="MailingLists/debian-announce">debian-announce</a>.</p>
+<hr>
+<h2>Bezpe�nostn� zpr�vy</h2>
+<p><tt>[01.12.2010]</tt> <strong><a href="security/2010/dsa-2129">DSA-2129 krb5</a></strong> - checksum verification weakness <br>
+<tt>[01.12.2010]</tt> <strong><a href="security/2010/dsa-2128">DSA-2128 libxml2</a></strong> - invalid memory access <br>
+<tt>[28.11.2010]</tt> <strong><a href="security/2010/dsa-2127">DSA-2127 wireshark</a></strong> - denial of service <br>
+<tt>[26.11.2010]</tt> <strong><a href="security/2010/dsa-2126">DSA-2126 linux-2.6</a></strong> - privilege escalation/denial of service/information leak <br>
+<tt>[22.11.2010]</tt> <strong><a href="security/2010/dsa-2125">DSA-2125 openssl</a></strong> - buffer overflow <br>
+<tt>[01.11.2010]</tt> <strong><a href="security/2010/dsa-2124">DSA-2124 xulrunner</a></strong> - several vulnerabilities <br>
+<tt>[01.11.2010]</tt> <strong><a href="security/2010/dsa-2123">DSA-2123 nss</a></strong> - several vulnerabilities <br>
+<tt>[22.10.2010]</tt> <strong><a href="security/2010/dsa-2122">DSA-2122 glibc</a></strong> - missing input sanitization <br>
+<tt>[19.10.2010]</tt> <strong><a href="security/2010/dsa-2121">DSA-2121 typo3-src</a></strong> - several vulnerabilities <br>
+<tt>[12.10.2010]</tt> <strong><a href="security/2010/dsa-2120">DSA-2120 postgresql-8.3</a></strong> - privilege escalation <br>
+<tt>[12.10.2010]</tt> <strong><a href="security/2010/dsa-2119">DSA-2119 poppler</a></strong> - several vulnerabilities <br>
+</p>
+<p>Star�� bezpe�nostn� zpr�vy se nach�z� na str�nce
+s&nbsp;<a href="./security/">bezpe�nostn�mi informacemi</a>.
+Pokud chcete b�t na potenci�ln� bezpe�nostn� rizika upozor�ov�ni
+elektronickou po�tou co nejd��ve po jejich ohl�en�, p�ihlaste se do
+konference
+<a href="http://lists.debian.org/debian-security-announce/">debian-security-announce</a>.</p>
+</div> <!-- end maincol -->
+<div class="clr"></div>
+</div> <!-- end inner -->
+<div id="footer">
+  <hr class="hidecss">
+  <!--UdmComment-->
+<p>
+Tato str�nka je tak� dostupn� v n�sleduj�c�ch jazyc�ch:
+</p><p class="navpara">
+ <a href="index.ar.html" title="arab�tina" hreflang="ar" lang="ar" rel="alternate">&#1593;&#1585;&#1576;&#1610;&#1577;&nbsp;(Arabiya)</a>
+ <a href="index.bg.html" title="bulhar�tina" hreflang="bg" lang="bg" rel="alternate">&#1041;&#1098;&#1083;&#1075;&#1072;&#1088;&#1089;&#1082;&#1080;&nbsp;(B&#601;lgarski)</a>
+ <a href="index.ca.html" title="katal�n�tina" hreflang="ca" lang="ca" rel="alternate">catal&agrave;</a>
+ <a href="index.da.html" title="d�n�tina" hreflang="da" lang="da" rel="alternate">dansk</a>
+ <a href="index.de.html" title="n�m�ina" hreflang="de" lang="de" rel="alternate">Deutsch</a>
+ <a href="index.el.html" title="�e�tina" hreflang="el" lang="el" rel="alternate">&#917;&#955;&#955;&#951;&#957;&#953;&#954;&#940;&nbsp;(Ellinika)</a>
+ <a href="index.en.html" title="angli�tina" hreflang="en" lang="en" rel="alternate">English</a>
+ <a href="index.es.html" title="�pan�l�tina" hreflang="es" lang="es" rel="alternate">espa&ntilde;ol</a>
+ <a href="index.eo.html" title="esperanto" hreflang="eo" lang="eo" rel="alternate">Esperanto</a>
+ <a href="index.fr.html" title="francouz�tina" hreflang="fr" lang="fr" rel="alternate">fran&ccedil;ais</a>
+ <a href="index.ko.html" title="korej�tina" hreflang="ko" lang="ko" rel="alternate">&#54620;&#44397;&#50612;&nbsp;(Hangul)</a>
+ <a href="index.hy.html" title="arm�n�tina" hreflang="hy" lang="hy" rel="alternate">&#1344;&#1377;&#1397;&#1381;&#1408;&#1381;&#1398;&nbsp;(hayeren)</a>
+ <a href="index.hr.html" title="chorvat�tina" hreflang="hr" lang="hr" rel="alternate">hrvatski</a>
+ <a href="index.id.html" title="indon�tina" hreflang="id" lang="id" rel="alternate">Indonesia</a>
+ <a href="index.it.html" title="ital�tina" hreflang="it" lang="it" rel="alternate">Italiano</a>
+ <a href="index.he.html" title="hebrej�tina" hreflang="he" lang="he" rel="alternate">&#1506;&#1489;&#1512;&#1497;&#1514;&nbsp;(ivrit)</a>
+ <a href="index.lt.html" title="litev�tina" hreflang="lt" lang="lt" rel="alternate">Lietuvi&#371;</a>
+ <a href="index.hu.html" title="ma�ar�tina" hreflang="hu" lang="hu" rel="alternate">magyar</a>
+ <a href="index.nl.html" title="holand�tina" hreflang="nl" lang="nl" rel="alternate">Nederlands</a>
+ <a href="index.ja.html" title="japon�tina" hreflang="ja" lang="ja" rel="alternate">&#26085;&#26412;&#35486;&nbsp;(Nihongo)</a>
+ <a href="index.nb.html" title="nor�tina" hreflang="nb" lang="nb" rel="alternate">norsk&nbsp;(bokm&aring;l)</a>
+ <a href="index.pl.html" title="pol�tina" hreflang="pl" lang="pl" rel="alternate">polski</a>
+ <a href="index.pt.html" title="portugal�tina" hreflang="pt" lang="pt" rel="alternate">Portugu&ecirc;s</a>
+ <a href="index.ro.html" title="rumun�tina" hreflang="ro" lang="ro" rel="alternate">rom&acirc;n&#259;</a>
+ <a href="index.ru.html" title="ru�tina" hreflang="ru" lang="ru" rel="alternate">&#1056;&#1091;&#1089;&#1089;&#1082;&#1080;&#1081;&nbsp;(Russkij)</a>
+ <a href="index.sk.html" title="sloven�tina" hreflang="sk" lang="sk" rel="alternate">slovensky</a>
+ <a href="index.fi.html" title="fin�tina" hreflang="fi" lang="fi" rel="alternate">suomi</a>
+ <a href="index.sv.html" title="�v�d�tina" hreflang="sv" lang="sv" rel="alternate">svenska</a>
+ <a href="index.ta.html" title="tamil�tina" hreflang="ta" lang="ta" rel="alternate">&#2980;&#2990;&#3007;&#2996;&#3021;&nbsp;(Tamil)</a>
+ <a href="index.tr.html" title="ture�tina" hreflang="tr" lang="tr" rel="alternate">T&uuml;rk&ccedil;e</a>
+ <a href="index.uk.html" title="ukrajin�tina" hreflang="uk" lang="uk" rel="alternate">&#1091;&#1082;&#1088;&#1072;&#1111;&#1085;&#1089;&#1100;&#1082;&#1072;&nbsp;(ukrajins'ka)</a>
+ <a href="index.zh-cn.html" title="��n�tina (��na)" hreflang="zh-CN" lang="zh-CN" rel="alternate">&#20013;&#25991;(&#31616;)</a>
+ <a href="index.zh-hk.html" title="��n�tina (Hong Kong)" hreflang="zh-HK" lang="zh-HK" rel="alternate">&#20013;&#25991;(HK)</a>
+ <a href="index.zh-tw.html" title="��n�tina (Tchai-wan)" hreflang="zh-TW" lang="zh-TW" rel="alternate">&#20013;&#25991;(&#32321;)</a>
+</p><p>
+Jak nastavit <a href="./intro/cn">v�choz� jazyk</a>
+</p>
+<!--/UdmComment-->
+<hr>
+<!--UdmComment-->
+<div id="fineprint">
+  <p>Probl�my t�kaj�c� se webov�ch str�nek oznamujte anglicky na e-mail <a href="mailto:debian-www@lists.debian.org">debian-www@lists.debian.org</a>. Dal�� kontakty z�sk�te na str�nce s&nbsp;<a href="./contact">kontakty</a>.</p>
+<p>
+Posledn� zm�na: �t, 2. pro 11:26:39 UTC 2010
+  <br>
+  Copyright &copy; 1997-2010
+ <a href="http://www.spi-inc.org/">SPI</a>; P�e�tete si <a href="./license" rel="copyright">licen�n� podm�nky</a><br>
+  Debian je registrovan� <a href="./trademark">obchodn� zn�mka</a> organizace Software in the Public Interest, Inc.
+</p>
+</div>
+<!--/UdmComment-->
+</div> <!-- end footer -->
+</div> <!-- end outer -->
+</body>
+</html>

data/spec/validate_website_spec.rb

@@ -14,7 +14,8 @@ describe ValidateWebsite do
       page = FakePage.new(name,
                           :body => open(file).read,
                           :content_type => 'text/html')
-      @validate_website.crawl(page.url)
+      @validate_website.site = page.url
+      @validate_website.crawl(:quiet => true)
       @validate_website.anemone.should have(3).pages
     end
   end
@@ -27,7 +28,8 @@ describe ValidateWebsite do
                                     .tests {background-image: url(/image/pouet_42.png)}
                                     .tests {background-image: url(/image/pouet)}",
                           :content_type => 'text/css')
-      @validate_website.crawl(page.url)
+      @validate_website.site = page.url
+      @validate_website.crawl
       @validate_website.anemone.should have(5).pages
     end
 
@@ -35,7 +37,8 @@ describe ValidateWebsite do
       page = FakePage.new('test.css',
                             :body => ".test {background-image: url('pouet');}",
                             :content_type => 'text/css')
-      @validate_website.crawl(page.url)
+      @validate_website.site = page.url
+      @validate_website.crawl
       @validate_website.anemone.should have(2).pages
     end
 
@@ -43,7 +46,8 @@ describe ValidateWebsite do
       page = FakePage.new('test.css',
                           :body => ".test {background-image: url(\"pouet\");}",
                           :content_type => 'text/css')
-      @validate_website.crawl(page.url)
+      @validate_website.site = page.url
+      @validate_website.crawl
       @validate_website.anemone.should have(2).pages
     end
   end

data/spec/validator_spec.rb

@@ -15,7 +15,7 @@ describe Validator do
                             :body => open(file).read,
                             :content_type => 'text/html')
         @xhtml1_page = @http.fetch_page(page.url)
-        validator = Validator.new(@xhtml1_page)
+        validator = Validator.new(@xhtml1_page.doc, @xhtml1_page.body)
         validator.dtd.system_id.should == dtd_uri
         validator.namespace.should == name
         validator.should be_valid
@@ -25,13 +25,14 @@ describe Validator do
     describe('html5') do
       context('when valid') do
         it "html5 should be valid" do
+          pending("need update html5lib")
           name = 'html5'
           file = File.join('spec', 'data', "#{name}.html")
           page = FakePage.new(name,
                               :body => open(file).read,
                               :content_type => 'text/html')
           @html5_page = @http.fetch_page(page.url)
-          validator = Validator.new(@html5_page)
+          validator = Validator.new(@html5_page.doc, @html5_page.body)
           validator.should be_valid
         end
       end
@@ -44,7 +45,7 @@ describe Validator do
                               :body => open(file).read,
                               :content_type => 'text/html')
           @html5_page = @http.fetch_page(page.url)
-          validator = Validator.new(@html5_page)
+          validator = Validator.new(@html5_page.doc, @html5_page.body)
           validator.should be_valid
         end
       end
@@ -58,7 +59,7 @@ describe Validator do
                             :body => open(file).read,
                             :content_type => 'text/html')
         @html4_strict_page = @http.fetch_page(page.url)
-        validator = Validator.new(@html4_strict_page)
+        validator = Validator.new(@html4_strict_page.doc, @html4_strict_page.body)
         validator.should be_valid
       end
     end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: validate-website
 version: !ruby/object:Gem::Version 
-  hash: 13
+  hash: 5
   prerelease: false
   segments: 
   - 0
   - 5
-  - 3
-  version: 0.5.3
+  - 7
+  version: 0.5.7
 platform: ruby
 authors: 
 - Laurent Arnoud
@@ -15,23 +15,23 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-05 00:00:00 +01:00
+date: 2010-12-10 00:00:00 +01:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
-  name: spk-anemone
+  name: anemone
   prerelease: false
   requirement: &id001 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
       - !ruby/object:Gem::Version 
-        hash: 15
+        hash: 11
         segments: 
         - 0
-        - 4
+        - 5
         - 0
-        version: 0.4.0
+        version: 0.5.0
   type: :runtime
   version_requirements: *id001
 - !ruby/object:Gem::Dependency 
@@ -49,26 +49,10 @@ dependencies:
         version: "1.1"
   type: :runtime
   version_requirements: *id002
-- !ruby/object:Gem::Dependency 
-  name: spk-html5
-  prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
-    none: false
-    requirements: 
-    - - "="
-      - !ruby/object:Gem::Version 
-        hash: 53
-        segments: 
-        - 0
-        - 10
-        - 1
-        version: 0.10.1
-  type: :runtime
-  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: rspec
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  requirement: &id003 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -80,11 +64,11 @@ dependencies:
         - 0
         version: 2.0.0
   type: :development
-  version_requirements: *id004
+  version_requirements: *id003
 - !ruby/object:Gem::Dependency 
   name: fakeweb
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  requirement: &id004 !ruby/object:Gem::Requirement 
     none: false
     requirements: 
     - - ">="
@@ -96,11 +80,12 @@ dependencies:
         - 0
         version: 1.3.0
   type: :development
-  version_requirements: *id005
+  version_requirements: *id004
 description: validate-website is a web crawler for checking the markupvalidity and not found urls.
 email: laurent@spkdev.net
 executables: 
 - validate-website
+- validate-website-static
 extensions: []
 
 extra_rdoc_files: []
@@ -109,6 +94,7 @@ files:
 - README.rdoc
 - Rakefile
 - LICENSE
+- bin/validate-website-static
 - bin/validate-website
 - lib/validator.rb
 - lib/colorful_messages.rb
@@ -207,6 +193,7 @@ files:
 - spec/validator_spec.rb
 - spec/spec_helper.rb
 - spec/data/html5-linuxfr.html
+- spec/data/index.cs.html
 - spec/data/html4-strict.html
 - spec/data/html5.html
 - spec/data/xhtml1-strict.html
@@ -240,9 +227,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       - 0
       version: "0"
 requirements: 
-- spk-anemone
+- anemone
 - rainbow
-- spk-html5
 rubyforge_project: 
 rubygems_version: 1.3.7
 signing_key: