validate-website 0.6.0 → 0.6.1

data/README.rdoc

@@ -18,8 +18,10 @@
 == DESCRIPTION
 
 validate-website is a web crawler for checking the markup validity and not
-found urls.
-validate-website-static check the markup validity of your local documents.
+found urls (more info doc/validate-website.txt).
+
+validate-website-static check the markup validity of your local documents
+(more info doc/validate-website-static.txt).
 
 == VALIDATE WEBSITE OPTIONS
 
@@ -66,6 +68,10 @@ validate-website-static check the markup validity of your local documents.
 * Thanks tenderlove for Nokogiri, this tool is inspired from markup_validity.
 * And Chris Kite for Anemone web-spider framework.
 
+== CONTRIBUTORS
+
+* François de Metz (francois2metz)
+
 == LICENSE
 The MIT License
 

data/Rakefile

@@ -7,10 +7,10 @@ require "rspec/core/rake_task" # RSpec 2.0
 # Globals
 
 PKG_NAME = 'validate-website'
-PKG_VERSION = '0.6.0'
+PKG_VERSION = '0.6.1'
 
 PKG_FILES = ['README.rdoc', 'Rakefile', 'LICENSE']
-Find.find('bin/', 'lib/', 'man/', 'spec/', 'share/') do |f|
+Find.find('bin/', 'lib/', 'man/', 'spec/', 'data/') do |f|
   if FileTest.directory?(f) and f =~ /\.svn|\.git/
     Find.prune
   else
@@ -43,6 +43,7 @@ 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.license = 'MIT'
   s.requirements << 'anemone' << 'rainbow'
   s.add_dependency('anemone', '>= 0.5.0')
   s.add_dependency('rainbow', '>= 1.1')
@@ -55,6 +56,7 @@ spec = Gem::Specification.new do |s|
   s.files = PKG_FILES
   s.description = 'validate-website is a web crawler for checking the markup' +
     'validity and not found urls.'
+  s.test_files = Dir.glob('spec/*_spec.rb')
 end
 
 Rake::GemPackageTask.new(spec) do |pkg|
@@ -68,7 +70,8 @@ task :manpage do
 end
 
 # RSpec 2.0
-RSpec::Core::RakeTask.new(:spec) do |spec|
+RSpec::Core::RakeTask.new(:test) do |spec|
   spec.pattern = 'spec/*_spec.rb'
   spec.rspec_opts = ['--backtrace']
 end
+task :spec => :test

data/lib/validate_website/core.rb

@@ -22,7 +22,7 @@ module ValidateWebsite
     EXIT_FAILURE_NOT_FOUND = 65
     EXIT_FAILURE_MARKUP_NOT_FOUND = 66
 
-    def initialize(options={}, validation_type = :crawl)
+    def initialize(options={}, validation_type=:crawl)
       @markup_error = nil
       @not_found_error = nil
 
@@ -108,6 +108,21 @@ module ValidateWebsite
       end
     end
 
+    # check files linked on static document
+    # see lib/validate_website/runner.rb
+    def check_static_not_found(links, opts={})
+      opts = @options.merge(opts)
+      if opts[:not_found]
+        links.each do |l|
+          unless File.exists?(l.path)
+            @not_found_error = true
+            puts error("%s linked but not exist" % l)
+            to_file(l)
+          end
+        end
+      end
+    end
+
     def exit_status
       if @markup_error && @not_found_error
         EXIT_FAILURE_MARKUP_NOT_FOUND

data/lib/validate_website/option_parser.rb

@@ -26,6 +26,9 @@ module ValidateWebsite
       :file              => nil,
       :validate_verbose  => false,
       :quiet             => false,
+      :markup_validation => true,
+      # log not found url (not on filesystem, pwd considered as root « / »)
+      :not_found         => false,
     }
 
     def self.parse(options, type)
@@ -117,6 +120,14 @@ module ValidateWebsite
              "Save not well formed urls") { |v|
           options[:file] = v
         }
+        o.on("-m", "--[no-]markup-validation",
+             "Markup validation (Default: #{@@default_opts[:markup_validation]})") { |v|
+          options[:markup_validation] = v
+        }
+        o.on("-n", "--not-found",
+             "Log files not on filesystem, pwd considered as root « / » (Default: #{@@default_opts[:not_found]})") { |v|
+          options[:not_found] = v
+        }
         o.on("-v", "--verbose",
              "Show validator errors (Default: #{@@default_opts[:validate_verbose]})") { |v|
           options[:validate_verbose] = v

data/lib/validate_website/runner.rb

@@ -19,16 +19,31 @@ module ValidateWebsite
     def self.run_static(args)
       trap_interrupt
       validate_website = ValidateWebsite::Core.new(args, :static)
-
-      files = Dir.glob(validate_website.options[:pattern])
+      opts = validate_website.options
+      links = []
+      files = Dir.glob(opts[:pattern])
       files.each do |f|
         next unless File.file?(f)
 
         body = open(f).read
         doc = Nokogiri::HTML(body)
 
-        validate_website.validate(doc, body, f)
+        if opts[:not_found]
+          doc.search("//a[@href]").each do |a|
+            u = a['href']
+            next if u.nil? || u.empty?
+            next if u.match(/^https?:\/\//)
+            abs = URI(File.join(Dir.getwd, u)) rescue next
+            links << abs if abs.host.nil?
+          end
+          links.uniq!
+        end
+
+        if opts[:markup_validation]
+          validate_website.validate(doc, body, f)
+        end
       end
+      validate_website.check_static_not_found(links)
       validate_website.exit_status
     end
   end

data/lib/validate_website/validator.rb

@@ -2,7 +2,7 @@
 
 module ValidateWebsite
   class Validator
-    XHTML_PATH = File.join(File.dirname(__FILE__), '..', '..', 'share', 'schemas')
+    XHTML_PATH = File.join(File.dirname(__FILE__), '..', '..', 'data', 'schemas')
 
     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 v1.75.2 <http://docbook.sf.net/>
-.\"      Date: 12/24/2010
+.\"      Date: 04/11/2011
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE\-S" "1" "12/24/2010" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE\-S" "1" "04/11/2011" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -47,6 +47,16 @@ Change filenames pattern (Default: **/*\&.html)
 Save not well formed urls
 .RE
 .PP
+\fB\-m\fR, \fB\-\-[no\-]markup\-validation\fR
+.RS 4
+Markup validation (Default: true)
+.RE
+.PP
+\fB\-n\fR, \fB\-\-not\-found\fR
+.RS 4
+Log files not on filesystem, pwd considered as root \(Fo / \(Fc (Default: false)
+.RE
+.PP
 \fB\-v\fR, \fB\-\-verbose\fR
 .RS 4
 Show detail of validator errors (Default: false)\&.
@@ -79,4 +89,4 @@ Laurent Arnoud <laurent@spkdev\&.net>
 .sp
 The MIT License
 .sp
-Copyright (c) 2009\-2010 Laurent Arnoud <laurent@spkdev\&.net>
+Copyright (c) 2009\-2011 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 v1.75.2 <http://docbook.sf.net/>
-.\"      Date: 12/10/2010
+.\"      Date: 04/11/2011
 .\"    Manual: \ \&
 .\"    Source: \ \&
 .\"  Language: English
 .\"
-.TH "VALIDATE\-WEBSITE" "1" "12/10/2010" "\ \&" "\ \&"
+.TH "VALIDATE\-WEBSITE" "1" "04/11/2011" "\ \&" "\ \&"
 .\" -----------------------------------------------------------------
 .\" * Define some portability stuff
 .\" -----------------------------------------------------------------
@@ -121,4 +121,4 @@ Laurent Arnoud <laurent@spkdev\&.net>
 .sp
 The MIT License
 .sp
-Copyright (c) 2009\-2010 Laurent Arnoud <laurent@spkdev\&.net>
+Copyright (c) 2009\-2011 Laurent Arnoud <laurent@spkdev\&.net>

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification 
 name: validate-website
 version: !ruby/object:Gem::Version 
-  hash: 7
-  prerelease: false
+  hash: 5
+  prerelease: 
   segments: 
   - 0
   - 6
-  - 0
-  version: 0.6.0
+  - 1
+  version: 0.6.1
 platform: ruby
 authors: 
 - Laurent Arnoud
@@ -15,7 +15,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-12-26 00:00:00 +01:00
+date: 2011-04-11 00:00:00 +02:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency 
@@ -112,100 +112,100 @@ files:
 - spec/data/html5.html
 - spec/data/xhtml1-strict.html
 - spec/fakeweb_helper.rb
-- share/schemas/xhtml-blkphras-1.xsd
-- share/schemas/xhtml1-transitional.xsd
-- share/schemas/xhtml1-strict.xsd
-- share/schemas/xhtml-blkstruct-1.xsd
-- share/schemas/xhtml11-modules-1.xsd
-- share/schemas/xhtml-blkpres-1.xsd
-- share/schemas/xhtml-basic11.dtd
-- share/schemas/xhtml-inlpres-1.xsd
-- share/schemas/xhtml-inlphras-1.xsd
-- share/schemas/xhtml-misc-1.xsd
-- share/schemas/xhtml-symbol.ent
-- share/schemas/xhtml1-frameset.xsd
-- share/schemas/xhtml-meta-1.xsd
-- share/schemas/xhtml1-frameset.dtd
-- share/schemas/xml-events-copyright-2.xsd
-- share/schemas/xml-handlers-2.xsd
-- share/schemas/xhtml-object-1.xsd
-- share/schemas/xhtml-bdo-1.xsd
-- share/schemas/frameset.dtd
-- share/schemas/xml-events-1.xsd
-- share/schemas/loose.dtd
-- share/schemas/xhtml-basic10-model-1.xsd
-- share/schemas/xhtml-table-1.xsd
-- share/schemas/xhtml2.xsd
-- share/schemas/xhtml-print-model-1.xsd
-- share/schemas/xhtml-rdfa-1.xsd
-- share/schemas/xhtml-basic-form-1.xsd
-- share/schemas/xhtml-inputmode-1.xsd
-- share/schemas/xhtml-ssismap-1.xsd
-- share/schemas/xhtml-basic10-modules-1.xsd
-- share/schemas/xhtml-events-1.xsd
-- share/schemas/xhtml-form-1.xsd
-- share/schemas/xhtml-struct-1.xsd
-- share/schemas/xml-script-1.xsd
-- share/schemas/xhtml-print-modules-1.xsd
-- share/schemas/xhtml-basic10.xsd
-- share/schemas/xframes-1.xsd
-- share/schemas/xhtml-rdfa-1.dtd
-- share/schemas/xhtml-datatypes-1.xsd
-- share/schemas/xhtml-pres-1.xsd
-- share/schemas/xhtml-charent-1.xsd
-- share/schemas/xhtml1-transitional.dtd
-- share/schemas/xhtml-access-1.xsd
-- share/schemas/xhtml-target-1.xsd
-- share/schemas/xhtml-param-1.xsd
-- share/schemas/xhtml-special.ent
-- share/schemas/xhtml-legacy-1.xsd
-- share/schemas/xhtml-frames-1.xsd
-- share/schemas/xhtml11-model-1.xsd
-- share/schemas/xhtml-inlstyle-1.xsd
-- share/schemas/xhtml-text-1.xsd
-- share/schemas/xhtml1-strict.dtd
-- share/schemas/xhtml-list-1.xsd
-- share/schemas/xhtml-framework-1.xsd
-- share/schemas/xml-events-copyright-1.xsd
-- share/schemas/xhtml-print-1.xsd
-- share/schemas/xml-events-2.xsd
-- share/schemas/xhtml-applet-1.xsd
-- share/schemas/xhtml-style-1.xsd
-- share/schemas/xhtml-base-1.xsd
-- share/schemas/xhtml-nameident-1.xsd
-- share/schemas/xhtml-iframe-1.xsd
-- share/schemas/xhtml-inlstruct-1.xsd
-- share/schemas/xhtml-notations-1.xsd
-- share/schemas/xhtml11-module-redefines-1.xsd
-- share/schemas/xhtml-basic11-modules-1.xsd
-- share/schemas/xml-events-attribs-2.xsd
-- share/schemas/xhtml-rdfa-model-1.xsd
-- share/schemas/xhtml-script-1.xsd
-- share/schemas/xhtml-hypertext-1.xsd
-- share/schemas/xhtml-rdfa-modules-1.xsd
-- share/schemas/xhtml-image-1.xsd
-- share/schemas/xml.xsd
-- share/schemas/xhtml-ruby-basic-1.xsd
-- share/schemas/xhtml-basic11.xsd
-- share/schemas/xml-handlers-1.xsd
-- share/schemas/xml-events-attribs-1.xsd
-- share/schemas/xhtml-link-1.xsd
-- share/schemas/xhtml-metaAttributes-1.xsd
-- share/schemas/xhtml-basic-table-1.xsd
-- share/schemas/xhtml-csismap-1.xsd
-- share/schemas/xhtml-basic11-model-1.xsd
-- share/schemas/xhtml-copyright-1.xsd
-- share/schemas/xhtml-basic10-module-redefines-1.xsd
-- share/schemas/strict.dtd
-- share/schemas/xhtml-edit-1.xsd
-- share/schemas/xhtml11.xsd
-- share/schemas/xhtml-lat1.ent
-- share/schemas/xhtml-attribs-1.xsd
-- share/schemas/xhtml-ruby-1.xsd
+- data/schemas/xhtml-blkphras-1.xsd
+- data/schemas/xhtml1-transitional.xsd
+- data/schemas/xhtml1-strict.xsd
+- data/schemas/xhtml-blkstruct-1.xsd
+- data/schemas/xhtml11-modules-1.xsd
+- data/schemas/xhtml-blkpres-1.xsd
+- data/schemas/xhtml-basic11.dtd
+- data/schemas/xhtml-inlpres-1.xsd
+- data/schemas/xhtml-inlphras-1.xsd
+- data/schemas/xhtml-misc-1.xsd
+- data/schemas/xhtml-symbol.ent
+- data/schemas/xhtml1-frameset.xsd
+- data/schemas/xhtml-meta-1.xsd
+- data/schemas/xhtml1-frameset.dtd
+- data/schemas/xml-events-copyright-2.xsd
+- data/schemas/xml-handlers-2.xsd
+- data/schemas/xhtml-object-1.xsd
+- data/schemas/xhtml-bdo-1.xsd
+- data/schemas/frameset.dtd
+- data/schemas/xml-events-1.xsd
+- data/schemas/loose.dtd
+- data/schemas/xhtml-basic10-model-1.xsd
+- data/schemas/xhtml-table-1.xsd
+- data/schemas/xhtml2.xsd
+- data/schemas/xhtml-print-model-1.xsd
+- data/schemas/xhtml-rdfa-1.xsd
+- data/schemas/xhtml-basic-form-1.xsd
+- data/schemas/xhtml-inputmode-1.xsd
+- data/schemas/xhtml-ssismap-1.xsd
+- data/schemas/xhtml-basic10-modules-1.xsd
+- data/schemas/xhtml-events-1.xsd
+- data/schemas/xhtml-form-1.xsd
+- data/schemas/xhtml-struct-1.xsd
+- data/schemas/xml-script-1.xsd
+- data/schemas/xhtml-print-modules-1.xsd
+- data/schemas/xhtml-basic10.xsd
+- data/schemas/xframes-1.xsd
+- data/schemas/xhtml-rdfa-1.dtd
+- data/schemas/xhtml-datatypes-1.xsd
+- data/schemas/xhtml-pres-1.xsd
+- data/schemas/xhtml-charent-1.xsd
+- data/schemas/xhtml1-transitional.dtd
+- data/schemas/xhtml-access-1.xsd
+- data/schemas/xhtml-target-1.xsd
+- data/schemas/xhtml-param-1.xsd
+- data/schemas/xhtml-special.ent
+- data/schemas/xhtml-legacy-1.xsd
+- data/schemas/xhtml-frames-1.xsd
+- data/schemas/xhtml11-model-1.xsd
+- data/schemas/xhtml-inlstyle-1.xsd
+- data/schemas/xhtml-text-1.xsd
+- data/schemas/xhtml1-strict.dtd
+- data/schemas/xhtml-list-1.xsd
+- data/schemas/xhtml-framework-1.xsd
+- data/schemas/xml-events-copyright-1.xsd
+- data/schemas/xhtml-print-1.xsd
+- data/schemas/xml-events-2.xsd
+- data/schemas/xhtml-applet-1.xsd
+- data/schemas/xhtml-style-1.xsd
+- data/schemas/xhtml-base-1.xsd
+- data/schemas/xhtml-nameident-1.xsd
+- data/schemas/xhtml-iframe-1.xsd
+- data/schemas/xhtml-inlstruct-1.xsd
+- data/schemas/xhtml-notations-1.xsd
+- data/schemas/xhtml11-module-redefines-1.xsd
+- data/schemas/xhtml-basic11-modules-1.xsd
+- data/schemas/xml-events-attribs-2.xsd
+- data/schemas/xhtml-rdfa-model-1.xsd
+- data/schemas/xhtml-script-1.xsd
+- data/schemas/xhtml-hypertext-1.xsd
+- data/schemas/xhtml-rdfa-modules-1.xsd
+- data/schemas/xhtml-image-1.xsd
+- data/schemas/xml.xsd
+- data/schemas/xhtml-ruby-basic-1.xsd
+- data/schemas/xhtml-basic11.xsd
+- data/schemas/xml-handlers-1.xsd
+- data/schemas/xml-events-attribs-1.xsd
+- data/schemas/xhtml-link-1.xsd
+- data/schemas/xhtml-metaAttributes-1.xsd
+- data/schemas/xhtml-basic-table-1.xsd
+- data/schemas/xhtml-csismap-1.xsd
+- data/schemas/xhtml-basic11-model-1.xsd
+- data/schemas/xhtml-copyright-1.xsd
+- data/schemas/xhtml-basic10-module-redefines-1.xsd
+- data/schemas/strict.dtd
+- data/schemas/xhtml-edit-1.xsd
+- data/schemas/xhtml11.xsd
+- data/schemas/xhtml-lat1.ent
+- data/schemas/xhtml-attribs-1.xsd
+- data/schemas/xhtml-ruby-1.xsd
 has_rdoc: true
 homepage: http://github.com/spk/validate-website
-licenses: []
-
+licenses: 
+- MIT
 post_install_message: 
 rdoc_options: []
 
@@ -233,9 +233,10 @@ requirements:
 - anemone
 - rainbow
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.6.2
 signing_key: 
 specification_version: 3
 summary: Web crawler for checking the validity of your documents
-test_files: []
-
+test_files: 
+- spec/core_spec.rb
+- spec/validator_spec.rb