assert_valid_html 0.1.0

data/lib/assert_valid_html/railtie.rb

@@ -0,0 +1,8 @@
+require "assert_valid_html"
+require "assert_valid_html/test"
+require "rails"
+
+module AssertValidHtml
+  class Railtie < Rails::Railtie
+  end
+end

data/lib/assert_valid_html/test.rb

@@ -0,0 +1,10 @@
+class ActionController::TestCase
+  def assert_valid_html
+    return unless @response.headers['Content-Type'].match(/html/)
+
+    validator = AssertValidHtml::Validator.new(@response.body)
+    assert_block(validator.message){ validator.valid? }
+  end
+
+  alias_method :assert_valid_markup, :assert_valid_html
+end

data/lib/assert_valid_html/validator.rb

@@ -0,0 +1,93 @@
+require "open3"
+
+module AssertValidHtml
+  class Validator
+    ValidationError = Struct.new(:message, :line, :context)
+
+    ALLOWED_ATTRIBUTES = %w[
+      media hreflang rel target value charset autofocus placeholder form
+      required disabled autocomplete min max multiple pattern step list
+      novalidate formaction formenctype formmethod formnovalidate formtarget
+      type label contextmenu scoped async manifest sizes reversed sandbox
+      seamless srcdoc contenteditable draggable hidden role data-\\S* aria-\\S*
+      spellcheck
+    ]
+
+    ALLOWED_ELEMENTS = %w[
+      section article aside hgroup header footer nav figure figcaption video
+      audio source embed progress meter time ruby rt rp wbr canvas command
+      details datalist keygen output
+    ]
+
+    IGNORED = [
+      /Warning: trimming empty/,
+      /lacks "summary" attribute/,
+      /<meta> lacks "content" attribute/, # HTML5
+      /proprietary attribute "xmlns:fb"/, # Facebook
+      /<\/?fb:/                           #    //
+    ]
+
+    def self.ignore(regexp)
+      ignored << regexp
+    end
+
+    def self.ignored
+      @ignored ||= IGNORED.dup
+    end
+
+    def self.ignored_regexp
+      Regexp.new((ignored + [
+        %r{proprietary attribute "(?:#{ALLOWED_ATTRIBUTES.join("|")})"},
+        %r{discarding unexpected </?(?:#{ALLOWED_ELEMENTS.join("|")})>}
+      ]).join("|"))
+    end
+
+    def initialize(html)
+      @html  = html
+      @lines = html.split(/\n/)
+    end
+
+    def valid?
+      errors.empty?
+    end
+
+    def errors
+      @errors ||= (
+        ignored = self.class.ignored_regexp
+        tidy(@html).split(/\n/).select {|w| w =~ /Warning/ && w !~ ignored }
+      ).inject([]){ |array, error|
+        line, message = parse_tidy_message(error)
+        array << ValidationError.new(message, line, context(line))
+      }
+    end
+
+    def context(line)
+      top    = [0, line - 6].max
+      bottom = [[@lines.length - 1, 0].max, line + 4].min
+      (top..bottom).to_a.zip(@lines[top..bottom]).map{ |number, text|
+        "%s %3d | %s" % [number + 1 == line ? "*" : " ", number + 1, text]
+      }.join("\n")
+    end
+
+    def message
+      if valid?
+        "HTML is valid"
+      else
+        (["HTML is invalid"] + errors.map{ |e| e.message + "\n" + e.context }).join("\n\n")
+      end
+    end
+
+  private
+    def parse_tidy_message(error)
+      m = error.match(/^line (\d+) column (\d+) - (.*)/)
+      return m[1].to_i, "#{m[3]} at line #{m[1]} column #{m[2]}"
+    end
+
+    def tidy(html)
+      stdin, stdout, stderr = Open3.popen3("tidy -q -e -utf8")
+      stdin << html
+      stdin.close
+      stderr.read
+    end
+  end
+end

data/lib/assert_valid_html/version.rb

@@ -0,0 +1,9 @@
+module AssertValidHtml
+  module VERSION #:nodoc:
+    MAJOR = 0
+    MINOR = 1
+    TINY  = 0
+
+    STRING = [MAJOR, MINOR, TINY].join('.')
+  end
+end

data/lib/assert_valid_html.rb

@@ -0,0 +1,2 @@
+require 'assert_valid_html/railtie' if defined?(Rails)
+require "assert_valid_html/validator"

metadata

@@ -0,0 +1,71 @@
+--- !ruby/object:Gem::Specification 
+name: assert_valid_html
+version: !ruby/object:Gem::Version 
+  hash: 27
+  prerelease: false
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
+platform: ruby
+authors: 
+- Paul Battley
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2010-11-17 00:00:00 +00:00
+default_executable: 
+dependencies: []
+
+description: 
+email: pbattley@gmail.com
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/assert_valid_html.rb
+- lib/assert_valid_html/validator.rb
+- lib/assert_valid_html/test.rb
+- lib/assert_valid_html/version.rb
+- lib/assert_valid_html/railtie.rb
+has_rdoc: true
+homepage: 
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Check HTML validity without using an external web service
+test_files: []
+