feedvalidator 0.1.0

data/CHANGELOG

@@ -0,0 +1,2 @@
+== FeedValidator 0.1.0
+ * Added the basic features to validate feeds, and new assertions to test cases

data/README

@@ -0,0 +1,71 @@
+= FeedValidator
+
+FeedValidator is an interface to the {W3C Feed Validation online service}[http://validator.w3.org/feed/],
+based on its SOAP 1.2 support. 
+
+It helps to find errors in RSS or ATOM feeds.
+
+FeedValidator add a new assertion (<code>assert_valid_feed</code>) which you can use in Rails applications.
+This assertion implements a cache to improve the performance of the tests and to not abuse of the 
+{W3C Feed Validation online service}[http://validator.w3.org/feed/]
+
+
+== Examples
+
+* For use FeedValidator just do this:
+
+    require 'feed_validator'
+
+    v = W3C::FeedValidator.new()
+    v.validate_url('http://www.w3.org/QA/news.rss')
+    puts v.to_s unless v.valid?
+
+* In Rails you can use it in your functional tests, just modify your /test/test_helper.rb adding this line:
+
+    require 'feed_validator/assertions'
+
+  And now you can use in your functional test, in this way:
+
+    def test_bar_valid_feed
+      get :bar
+      assert_valid_feed
+    end
+
+  Or use the class-level method to quickly create validation tests for a bunch of actions at once:
+
+    assert_valid_feed :bar, :foo
+
+
+== Download
+
+The latest version of FeedValidator can be found at
+
+* http://rubyforge.org/frs/?group_id=1533
+
+Documentation can be found at 
+
+* http://feedvalidator.rubyforge.org
+
+
+== Installation
+
+You can install FeedValidator as a gem:
+  gem install feedvalidator
+  
+Or you can install it from the tarball or zip packages on the download page
+and then extract it to your lib directory as you would with any other
+Ruby library.
+
+
+== License
+
+FeedValidator is released under the MIT license.
+
+
+== Support
+
+You can find the Feed Validator RubyForge page at http://rubyforge.org/projects/feedvalidator.
+
+Feel free to submit commits or feature requests.
+
+For other information, feel free to contact mailto:edgar@lacaraoscura.com.

data/install.rb

@@ -0,0 +1,30 @@
+require 'rbconfig'
+require 'find'
+require 'ftools'
+
+include Config
+
+# this was adapted from rdoc's install.rb by ways of Log4r
+
+$sitedir = CONFIG["sitelibdir"]
+unless $sitedir
+  version = CONFIG["MAJOR"] + "." + CONFIG["MINOR"]
+  $libdir = File.join(CONFIG["libdir"], "ruby", version)
+  $sitedir = $:.find {|x| x =~ /site_ruby/ }
+  if !$sitedir
+    $sitedir = File.join($libdir, "site_ruby")
+  elsif $sitedir !~ Regexp.quote(version)
+    $sitedir = File.join($sitedir, version)
+  end
+end
+
+# the acual gruntwork
+Dir.chdir("lib")
+
+Find.find("feed_validator", "feed_validator.rb") { |f|
+  if f[-3..-1] == ".rb"
+    File::install(f, File.join($sitedir, *f.split(/\//)), 0644, true)
+  else
+    File::makedirs(File.join($sitedir, *f.split(/\//)))
+  end
+}

data/lib/feed_validator.rb

@@ -0,0 +1,164 @@
+#--
+# Copyright (c) 2006 Edgar Gonzalez <edgar@lacaraoscura.com>
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+#++
+#
+# Provide an interface to the {W3C Feed Validation online service}[http://validator.w3.org/feed/], 
+# based on its SOAP 1.2 support. 
+#
+require 'net/http'
+require 'cgi'
+require 'rexml/document'
+
+module W3C
+
+  # Implements an interface to the {W3C Feed Validation online service}[http://validator.w3.org/feed/], 
+  # based on its SOAP 1.2 support. 
+  #
+  # It helps to find errors in RSS or Atom feeds.
+  # ---
+  # Please remember that the {W3C Feed Validation service}[http://validator.w3.org/feed/] is a shared resource,
+  # so do not abuse it: you should make your scripts sleep between requests.
+  #
+  class FeedValidator
+    VERSION = "0.1.0"
+
+    # True if the w3c feed validation service not found errors in the feed.
+    #
+    attr_reader :valid
+    
+    # The complete response (as Net::HTTPResponse object) sent it by the w3c feed validation service.
+    #
+    attr_reader :response
+    
+    # Collection of _errors_ founded by the w3c feed validation service.
+    # Every error is a hash containing: <tt>:type</tt>, <tt>:line</tt>, 
+    # <tt>:column</tt>, <tt>:text</tt>, <tt>:element</tt>
+    #
+    attr_reader :errors
+
+    # Collection of _warnings_ founded by the w3c feed validation service.
+    # Every error is a hash containing: <tt>:type</tt>, <tt>:line</tt>, 
+    # <tt>:column</tt>, <tt>:text</tt>, <tt>:element</tt>
+    #
+    attr_reader :warnings
+
+    # Collection of _informations_ founded by the w3c feed validation service.
+    # Every error is a hash containing: <tt>:type</tt>, <tt>:line</tt>, 
+    # <tt>:column</tt>, <tt>:text</tt>, <tt>:element</tt>
+    #
+    attr_reader :informations
+  
+    # Initialize the feed validator object
+    #
+    def initialize
+      clear
+    end
+    
+    # Validate the data provided. 
+    # Returns a true value if the validation succeeded (regardless of whether the feed contains errors).
+    #
+    def validate_data(rawdata)
+      clear
+      params = "rawdata=#{CGI.escape(rawdata)}&manual=1&output=soap12"
+      begin
+        @response = Net::HTTP.start('validator.w3.org',80).post('/feed/check.cgi',params)
+        parse_response(@response.body)
+        return true
+      rescue
+        return false
+      end      
+    end
+
+    # Validate the url provided. 
+    # Returns a true value if the validation succeeded (regardless of whether the feed contains errors).
+    #
+    def validate_url(url)
+      clear
+      params = "url=#{CGI.escape(url)}&output=soap12"
+      begin
+        @response = Net::HTTP.get_response('validator.w3.org',"/feed/check.cgi?#{params}",80)
+        parse_response(@response.body)
+        return true
+      rescue
+        return false
+      end      
+    end
+
+    alias :valid? :valid
+
+    def to_s
+      msg = "Vailidity: #{@valid}\n"
+      msg << "Errors count: #{@errors.size}\n"
+      @errors.each_with_index{ |item, i| msg << "(#{i+1}) type: #{item[:type]} | line: #{item[:line]} | column: #{item[:column]} | text: #{item[:text]},\n"}  
+      msg << "Warnings count: #{@warnings.size}\n"
+      @warnings.each_with_index{ |item, i| msg << "(#{i+1}) type: #{item[:type]} | line: #{item[:line]} | column: #{item[:column]} | text: #{item[:text]},\n"}  
+      msg << "Informations count: #{@informations.size}\n"
+      @informations.each_with_index{ |item, i| msg << "(#{i+1}) type: #{item[:type]} | line: #{item[:line]} | column: #{item[:column]} | text: #{item[:text]},\n"}  
+      msg
+    end
+
+    private
+    
+    def parse_response(response) #nodoc
+      xml = REXML::Document.new(response)
+      @valid = (/true/.match(xml.root.elements["env:Body/m:feedvalidationresponse/m:validity"].get_text.value))? true : false
+      unless @valid
+        xml.elements.each("env:Envelope/env:Body/m:feedvalidationresponse/m:errors/m:errorlist/error") do |error|
+          @errors << {
+            :type => error.elements["type"].get_text.value,
+            :line => error.elements["line"].get_text.value,
+            :column => error.elements["column"].get_text.value,
+            :text => error.elements["text"].get_text.value,
+            :element => error.elements["element"].get_text.value
+            }
+        end
+      end
+      xml.elements.each("env:Envelope/env:Body/m:feedvalidationresponse/m:warnings/m:warninglist/warning") do |warning|
+        @warnings << {
+          :type => warning.elements["type"].get_text.value,
+          :line => warning.elements["line"].get_text.value,
+          :column => warning.elements["column"].get_text.value,
+          :text => warning.elements["text"].get_text.value,
+          :element => warning.elements["element"].get_text.value
+          }
+      end
+      xml.elements.each("env:Envelope/env:Body/m:feedvalidationresponse/m:informations/m:infolist/information") do |info|
+        @informations << {
+          :type => info.elements["type"].get_text.value,
+          :line => info.elements["line"].get_text.value,
+          :column => info.elements["column"].get_text.value,
+          :text => info.elements["text"].get_text.value,
+          :element => info.elements["element"].get_text.value
+          }
+      end
+    end
+
+    def clear #nodoc
+      @response = nil
+      @valid = false
+      @errors = []
+      @warnings = []
+      @informations = []
+    end
+      
+  end
+end

data/lib/feed_validator/assertions.rb

@@ -0,0 +1,91 @@
+#--
+# Copyright (c) 2006 Edgar Gonzalez <edgar@lacaraoscura.com>
+#
+# Permission is hereby granted, free of charge, to any person obtaining
+# a copy of this software and associated documentation files (the
+# "Software"), to deal in the Software without restriction, including
+# without limitation the rights to use, copy, modify, merge, publish,
+# distribute, sublicense, and/or sell copies of the Software, and to
+# permit persons to whom the Software is furnished to do so, subject to
+# the following conditions:
+#
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+# LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+# OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+# WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+#++
+
+require 'feed_validator'
+require 'test/unit'
+require 'tmpdir'
+require 'md5'
+
+module W3C
+  class FeedValidator
+    # Parse a response from the w3c feed validation service.
+    # Used by assert_valid_feed
+    def parse(response)
+      clear
+      if response.respond_to?(:body)
+        parse_response(response.body)
+      else
+        parse_response(response)
+      end      
+    end
+  end
+end
+
+class Test::Unit::TestCase
+
+  # Assert that feed is valid according the {W3C Feed Validation online service}[http://validator.w3.org/feed/].
+  # By default, it validates the contents of @response.body, which is set after calling
+  # one of the get/post/etc helper methods in rails. You can also pass it a string to be validated.
+  # Validation errors, warnings and informations, if any, will be included in the output. The response from the validator
+  # service will be cached in the system temp directory to minimize duplicate calls.
+  #
+  # For example in Rails, if you have a FooController with an action Bar, put this in foo_controller_test.rb:
+  #
+  #   def test_bar_valid_feed
+  #     get :bar
+  #     assert_valid_feed
+  #   end
+  #
+  def assert_valid_feed(fragment=@response.body)
+    v = W3C::FeedValidator.new()
+    filename = File.join Dir::tmpdir, 'feed.' + MD5.md5(fragment).to_s
+    begin
+      response = File.open filename do |f| Marshal.load(f) end
+      v.parse(response)
+  	rescue   
+      unless v.validate_data(fragment)
+        warn("Sorry! could not validate the feed.")
+        return assert(true,'')
+      end
+      File.open filename, 'w+' do |f| Marshal.dump v.response, f end
+  	end
+    assert(v.valid?, v.valid? ? '' : v.to_s)
+  end
+  
+  # Class-level method to quickly create validation tests for a bunch of actions at once in Rails.
+  # For example, if you have a FooController with three actions, just add one line to foo_controller_test.rb:
+  #
+  #   assert_valid_feed :bar, :baz, :qux
+  #
+  def self.assert_valid_feed(*actions)
+    actions.each do |action|
+      class_eval <<-EOF
+        def test_#{action}_valid_feed
+          get :#{action}
+          assert_valid_feed
+        end
+      EOF
+    end
+  end
+  
+end

data/rakefile

@@ -0,0 +1,109 @@
+require 'rubygems'
+require 'rake'
+require 'rake/testtask'
+require 'rake/rdoctask'
+require 'rake/packagetask'
+require 'rake/gempackagetask'
+require 'rake/contrib/rubyforgepublisher'
+
+PKG_NAME      = 'feedvalidator'
+PKG_VERSION   = '0.1.0'
+PKG_FILE_NAME = "#{PKG_NAME}-#{PKG_VERSION}"
+
+RELEASE_NAME  = "REL #{PKG_VERSION}"
+
+RUBY_FORGE_PROJECT = "feedvalidator"
+RUBY_FORGE_USER    = "edgar"
+
+PKG_FILES = FileList[
+    "lib/**/*", "test/**/*", "examples/**/*", "doc/**/*", "[A-Z]*", "install.rb", "rakefile"
+].exclude(/\b.svn\b|~$/)
+
+desc "Default Task"
+task :default => [ :test_all ]
+
+# Run the unit tests
+
+Rake::TestTask.new("test_all") { |t|
+  t.libs << "test"
+  t.pattern = 'test/**/*_test.rb'
+  t.verbose = true
+}
+
+# Generate the RDoc documentation
+
+Rake::RDocTask.new { |rdoc|
+  rdoc.rdoc_dir = 'doc'
+  rdoc.title    = "FeedValidator"
+  rdoc.options << '--line-numbers' << '--inline-source'
+  rdoc.template = "#{ENV['template']}.rb" if ENV['template']
+  rdoc.rdoc_files.include('README', 'CHANGELOG')
+  rdoc.rdoc_files.include('lib/**/*.rb')
+}
+
+# Create compressed packages
+
+dist_dirs = [ "lib", "test" ]
+
+spec = Gem::Specification.new do |s|
+  s.name = PKG_NAME
+  s.version = PKG_VERSION
+  s.summary = "An interface to the W3C Feed Validation online service"
+  s.description = "Implements a simple system for generating UUIDs."
+
+  s.files = [ "rakefile", "install.rb", "README", "CHANGELOG" ]
+  dist_dirs.each do |dir|
+    s.files = s.files + Dir.glob( "#{dir}/**/*" ).delete_if do |item|
+      item.include?( "\.svn" )
+    end
+  end
+  
+  s.require_path = 'lib'
+  s.autorequire = 'feed_validator'
+
+  s.has_rdoc = true
+  s.extra_rdoc_files = %w( README )
+  s.rdoc_options.concat ['--main',  'README']
+  
+  s.author = "Edgar Gonzalez"
+  s.email = "edgar@lacaraoscura.com"
+  s.homepage = "http://feedvalidator.rubyforge.org"
+  s.rubyforge_project = "feedvalidator"
+end
+  
+Rake::GemPackageTask.new(spec) do |p|
+  p.gem_spec = spec
+  p.need_tar = true
+  p.need_zip = true
+end
+
+task :lines do
+  lines, codelines, total_lines, total_codelines = 0, 0, 0, 0
+
+  for file_name in FileList["lib/**/*.rb"]
+    f = File.open(file_name)
+
+    while line = f.gets
+      lines += 1
+      next if line =~ /^\s*$/
+      next if line =~ /^\s*#/
+      codelines += 1
+    end
+    puts "L: #{sprintf("%4d", lines)}, LOC #{sprintf("%4d", codelines)} | #{file_name}"
+    
+    total_lines     += lines
+    total_codelines += codelines
+    
+    lines, codelines = 0, 0
+  end
+
+  puts "Total: Lines #{total_lines}, LOC #{total_codelines}"
+end
+
+
+# Publishing ------------------------------------------------------
+
+desc "Publish the API documentation"
+task :pdoc => [:rdoc] do 
+  Rake::SshDirPublisher.new("edgar@rubyforge.org", "/var/www/gforge-projects/feedvalidator/", "doc").upload
+end