headhunter 0.0.1 → 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 79ba313e9b12c21aa35c4fc74bfe40f86801c9fd
+  data.tar.gz: afc84375e5fb68c8fe8af5d4e5af6f30826c0d51
+SHA512:
+  metadata.gz: d6c891576972b9fba784d4985f874308a639c8f27973b4813c9542eb08eaca6ef8e5a5a68ac7218e9fb72d5760d36da761ecc67bb5a4f8b24322f86a22314ea2
+  data.tar.gz: 1c8dc6fed4c64758bb0dc3b07756fcd19b8b76ceb53a912cf7c64e09e4abe03b88397eaedc0c732e8795d81c93906c935166deb6d9d7b7f048488db0566ef800

data/lib/headhunter.rb

@@ -0,0 +1,55 @@
+require 'headhunter/css_hunter'
+require 'headhunter/css_validator'
+require 'headhunter/html_validator'
+require 'headhunter/rails'
+# require 'rack/utils'
+
+class Headhunter
+  attr_accessor :results
+
+  def initialize(root)
+    @root = root
+
+    precompile_assets!
+
+    @html_validator = HtmlValidator.new
+    @css_validator  = CssValidator.new(stylesheets)
+    @css_hunter     = CssHunter.new(stylesheets)
+
+    @css_validator.process!
+  end
+
+  def process!(url, html)
+    @html_validator.process!(url, html)
+    @css_hunter.process!(url, html)
+  end
+
+  def clean_up!
+    remove_assets!
+  end
+
+  def report
+    @html_validator.prepare_results_html
+
+    @html_validator.report
+    @css_validator.report
+    @css_hunter.report
+  end
+
+  private
+
+  def precompile_assets!
+    # Remove existing assets! This seems to be necessary to make sure that they don't exist twice, see http://stackoverflow.com/questions/20938891
+    system 'rake assets:clobber HEADHUNTER=false &> /dev/null'
+
+    system 'rake assets:precompile HEADHUNTER=false &> /dev/null'
+  end
+
+  def remove_assets!
+    system 'rake assets:clobber HEADHUNTER=false &> /dev/null'
+  end
+
+  def stylesheets
+    Dir.chdir(@root) { Dir.glob('public/assets/*.css') }
+  end
+end

data/lib/headhunter/css_hunter.rb

@@ -0,0 +1,100 @@
+require 'css_parser'
+require 'nokogiri'
+require 'open-uri'
+
+class Headhunter
+  class CssHunter
+    def initialize(stylesheets)
+      @stylesheets      = stylesheets
+      @parsed_rules     = {}
+      @unused_selectors = []
+      @used_selectors   = []
+
+      load_css!
+    end
+
+    def process!(url, html)
+      analyze(html).each do |selector|
+        @unused_selectors.delete(selector)
+      end
+    end
+
+    def report
+      log.puts "Found #{@used_selectors.size + @unused_selectors.size} CSS selectors.".yellow
+      log.puts "#{@used_selectors.size} selectors are in use.".green if @used_selectors.size > 0
+      log.puts "#{@unused_selectors.size} selectors are not in use: #{@unused_selectors.sort.join(', ').red}".red if @unused_selectors.size > 0
+      log.puts
+    end
+
+    private
+
+    def analyze(html)
+      doc = Nokogiri::HTML(html)
+
+      @unused_selectors.collect do |selector, declarations|
+        # We test against the selector stripped of any pseudo classes,
+        # but we report on the selector with its pseudo classes.
+        stripped_selector = strip(selector)
+
+        next if stripped_selector.empty?
+
+        if doc.search(stripped_selector).any?
+          @used_selectors << selector
+          selector
+        end
+      end
+    end
+
+    def load_css!
+      @stylesheets.each do |stylesheet|
+        new_selector_count = add_css!(fetch(stylesheet))
+      end
+    end
+
+    def fetch(path)
+      log.puts(path)
+
+      loc = path
+
+      begin
+        open(loc).read
+      rescue Errno::ENOENT
+        raise FetchError.new("#{loc} was not found")
+      rescue OpenURI::HTTPError => e
+        raise FetchError.new("retrieving #{loc} raised an HTTP error: #{e.message}")
+      end
+    end
+
+    def add_css!(css)
+      parser = CssParser::Parser.new
+      parser.add_block!(css)
+
+      selector_count = 0
+
+      parser.each_selector do |selector, declarations, specificity|
+        next if @unused_selectors.include?(selector)
+        next if selector =~ @ignore_selectors
+        next if has_pseudo_classes(selector) and @unused_selectors.include?(strip(selector))
+
+        @unused_selectors << selector
+        @parsed_rules[selector] = declarations
+
+        selector_count += 1
+      end
+
+      selector_count
+    end
+
+    def has_pseudo_classes(selector)
+      selector =~ /::?[\w\-]+/
+    end
+
+    def strip(selector)
+      selector = selector.gsub(/^@.*/, '') # @-webkit-keyframes ...
+      selector = selector.gsub(/:.*/, '')  # input#x:nth-child(2):not(#z.o[type='file'])
+      selector
+    end
+  end
+
+  class FetchError < StandardError; end
+end

data/lib/headhunter/css_validator.rb

@@ -0,0 +1,131 @@
+require 'net/http'
+require 'rexml/document'
+
+class Headhunter
+  class CssValidator
+    def initialize(stylesheets)
+      @profile = 'css3' # TODO: Option for profile css1 and css21
+      @stylesheets = stylesheets
+      @messages_per_stylesheet = {}
+    end
+
+    def process!
+      @stylesheets.each do |stylesheet|
+        css = fetch(stylesheet)
+        css = ' ' if css.empty? # The validator returns a 500 error if it receives an empty string
+
+        response = get_validation_response({text: css, profile: @profile, vextwarning: 'true'})
+        unless response_indicates_valid?(response)
+          process_errors(stylesheet, css, response)
+        end
+      end
+    end
+
+    def report
+      log.puts "Validated #{@stylesheets.size} stylesheets.".yellow
+      log.puts "#{x_stylesheets_be(@stylesheets.size - @messages_per_stylesheet.size)} valid.".green if @messages_per_stylesheet.size < @stylesheets.size
+      log.puts "#{x_stylesheets_be(@messages_per_stylesheet.size)} invalid.".red if @messages_per_stylesheet.size > 0
+
+      @messages_per_stylesheet.each_pair do |stylesheet, messages|
+        log.puts "  #{extract_filename(stylesheet)}:".red
+
+        messages.each { |message| log.puts "  - #{message}".red }
+      end
+    end
+
+    private
+
+    # Converts a path like public/assets/application-d205d6f344d8623ca0323cb6f6bd7ca1.css to application.css
+    def extract_filename(path)
+      matches = path.match /^public\/assets\/(.*)-([a-z0-9]*)(\.css)/
+      matches[1] + matches[3]
+    end
+
+    def x_stylesheets_be(size)
+      if size <= 1
+        "#{size} stylesheet is"
+      else
+        "#{size} stylesheets are"
+      end
+    end
+
+    def process_errors(file, css, response)
+      @messages_per_stylesheet[file] = []
+
+      REXML::Document.new(response.body).root.each_element('//m:error') do |e|
+        @messages_per_stylesheet[file] << "#{error_line_prefix}: line #{e.elements['m:line'].text}: #{e.elements['m:message'].get_text.value.strip}\n"
+      end
+    end
+
+    def fetch(path) # TODO: Move to Headhunter!
+      log.puts(path)
+
+      loc = path
+
+      begin
+        open(loc).read
+      rescue Errno::ENOENT
+        raise FetchError.new("#{loc} was not found")
+      rescue OpenURI::HTTPError => e
+        raise FetchError.new("retrieving #{loc} raised an HTTP error: #{e.message}")
+      end
+    end
+
+    def get_validation_response(query_params)
+      query_params.merge!({:output => 'soap12'})
+      get_validator_response(query_params)
+    end
+
+    def response_indicates_valid?(response)
+      response['x-w3c-validator-status'] == 'Valid'
+    end
+
+    def get_validator_response(query_params = {})
+      response = call_validator(query_params)
+
+      raise "HTTP error: #{response.code}" unless response.is_a? Net::HTTPSuccess
+      return response
+    end
+
+    def call_validator(query_params)
+      boundary = Digest::MD5.hexdigest(Time.now.to_s)
+      data = encode_multipart_params(boundary, query_params)
+      return http_start(validator_host).post2(validator_path, data, "Content-type" => "multipart/form-data; boundary=#{boundary}" )
+    end
+
+    def encode_multipart_params(boundary, params = {})
+      ret = ''
+      params.each do |k,v|
+        unless v.empty?
+          ret << "\r\n--#{boundary}\r\n"
+          ret << "Content-Disposition: form-data; name=\"#{k.to_s}\"\r\n\r\n"
+          ret << v
+        end
+      end
+      ret << "\r\n--#{boundary}--\r\n"
+      ret
+    end
+
+    def http_start(host)
+      if ENV['http_proxy']
+        uri = URI.parse(ENV['http_proxy'])
+        proxy_user, proxy_pass = uri.userinfo.split(/:/) if uri.userinfo
+        Net::HTTP.start(host, nil, uri.host, uri.port, proxy_user, proxy_pass)
+      else
+        Net::HTTP.start(host)
+      end
+    end
+
+    def validator_host
+      'jigsaw.w3.org'
+    end
+
+    def validator_path
+      '/css-validator/validator'
+    end
+
+    def error_line_prefix
+      'Invalid css'
+    end
+  end
+end

data/lib/headhunter/html_validator.rb

@@ -0,0 +1,58 @@
+require 'html_validation'
+
+class Headhunter
+  class HtmlValidator
+    def initialize
+      @valid_results   = []
+      @invalid_results = []
+    end
+
+    def process!(url, html)
+      html_validation = PageValidations::HTMLValidation.new.validation(html, random_name)
+      (html_validation.valid? ? @valid_results : @invalid_results) << html_validation
+    end
+
+    def prepare_results_html
+      html = File.read File.dirname(File.expand_path(__FILE__)) + '/templates/results.html'
+      html.gsub! '{{VALID_RESULTS}}', prepare_results_for(@valid_results)
+      html.gsub! '{{INVALID_RESULTS}}', prepare_results_for(@invalid_results)
+      File.open('.validation/results.html', 'w') { |file| file.write(html) }
+    end
+
+    def prepare_results_for(results)
+      results.map do |result|
+        exceptions_html = ::Rack::Utils.escape_html(File.read(".validation/#{result.resource}.exceptions.txt"))
+
+        full_result_html = File.read File.dirname(File.expand_path(__FILE__)) + '/templates/result.html'
+        full_result_html.gsub! '{{RESOURCE}}', result.resource
+        full_result_html.gsub! '{{EXCEPTIONS}}', exceptions_html
+        full_result_html.gsub! '{{HTML_CONTEXT}}', 'context'
+        full_result_html.gsub! '{{LINK}}', "#{result.resource}.html.txt"
+
+        full_result_html
+      end.join
+    end
+
+    def report
+      log.puts "Validated #{@valid_results.size + @invalid_results.size} HTML pages.".yellow
+      log.puts "#{x_pages_be(@valid_results.size)} valid.".green if @valid_results.size > 0
+      log.puts "#{x_pages_be(@invalid_results.size)} invalid.".red if @invalid_results.size > 0
+      log.puts 'Open .validation/results.html to view full results.'
+      log.puts
+    end
+
+    private
+
+    def x_pages_be(size)
+      if size <= 1
+        "#{size} page is"
+      else
+        "#{size} pages are"
+      end
+    end
+
+    def random_name
+      (0...8).map { (65 + rand(26)).chr }.join
+    end
+  end
+end

data/lib/headhunter/rack/capturing_middleware.rb

@@ -0,0 +1,28 @@
+class Headhunter
+  module Rack
+    class CapturingMiddleware
+      def initialize(app, headhunter)
+        @app = app
+        @hh  = headhunter
+      end
+
+      def call(env)
+        response = @app.call(env)
+        process(response)
+        response
+      end
+
+      def process(rack_response)
+        status, headers, response = rack_response
+
+        if html = extract_html_from(response)
+          @hh.process!('unknown', html)
+        end
+      end
+
+      def extract_html_from(response)
+        response[0]
+      end
+    end
+  end
+end

data/lib/headhunter/rails.rb

@@ -0,0 +1,21 @@
+require 'headhunter'
+require 'headhunter/rack/capturing_middleware'
+
+if ENV['HEADHUNTER'] == 'true'
+  class Headhunter
+    module Rails
+      class Railtie < ::Rails::Railtie
+        initializer "headhunter.hijack" do |app|
+          head_hunter = Headhunter.new(::Rails.root)
+
+          at_exit do
+            head_hunter.report
+            head_hunter.clean_up!
+          end
+
+          app.middleware.insert(0, Headhunter::Rack::CapturingMiddleware, head_hunter)
+        end
+      end
+    end
+  end
+end

data/lib/headhunter/templates/result.html

@@ -0,0 +1,8 @@
+<tr>
+  <td>{{RESOURCE}}</td>
+  <td>{{EXCEPTIONS}}</td>
+  <td>{{HTML_CONTEXT}}</td>
+  <td>
+    <a href="{{LINK}}">Full source</a>
+  </td>
+</tr>

data/lib/headhunter/templates/results.html

@@ -0,0 +1,39 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <title>Headhunter Results</title>
+  </head>
+  <body>
+    <h1>Headhunter Results</h1>
+
+    <h2>Invalid results</h2>
+    <table>
+      <thead>
+        <tr>
+          <td>Resource</td>
+          <td>Exceptions</td>
+          <td>HTML context</td>
+          <td>Full source</td>
+        </tr>
+      </thead>
+      <tbody>
+        {{INVALID_RESULTS}}
+      </tbody>
+    </table>
+
+    <h2>Valid results</h2>
+    <table>
+      <thead>
+        <tr>
+          <td>Resource</td>
+          <td>Exceptions</td>
+          <td>HTML context</td>
+          <td>Full source</td>
+        </tr>
+      </thead>
+      <tbody>
+        {{VALID_RESULTS}}
+      </tbody>
+    </table>
+  </body>
+</html>

metadata

@@ -1,8 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: headhunter
 version: !ruby/object:Gem::Version
-  version: 0.0.1
-  prerelease: 
+  version: 0.0.2
 platform: ruby
 authors:
 - Joshua Muheim
@@ -14,23 +13,20 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: css_parser
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -38,7 +34,6 @@ dependencies:
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
     - - ~>
       - !ruby/object:Gem::Version
@@ -46,65 +41,126 @@ dependencies:
 - !ruby/object:Gem::Dependency
   name: html_validation
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: colorize
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
-description: 
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: fuubar
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '2.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '2.0'
+description: Headhunter is an HTML and CSS validation tool that injects itself into
+  your Rails feature tests and automagically checks all your generated HTML and CSS
+  for validity. In addition, it also looks out for unused (and therefore superfluous)
+  CSS selectors.
 email: josh@muheimwebdesign.ch
 executables: []
 extensions: []
 extra_rdoc_files: []
-files: []
+files:
+- lib/headhunter/css_hunter.rb
+- lib/headhunter/css_validator.rb
+- lib/headhunter/html_validator.rb
+- lib/headhunter/rack/capturing_middleware.rb
+- lib/headhunter/rails.rb
+- lib/headhunter/templates/result.html
+- lib/headhunter/templates/results.html
+- lib/headhunter.rb
 homepage: http://github.com/jmuheim/headhunter
 licenses:
 - MIT
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.25
+rubygems_version: 2.1.11
 signing_key: 
-specification_version: 3
-summary: An automatic HTML validator hooks into your request/acceptance/feature test
-  suite and validates your HTML after every request
+specification_version: 4
+summary: Zero config HTML & CSS validation tool for Rails apps
 test_files: []