html-proofer 3.12.1 → 3.15.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 04d2b18950f5d8c6b2bcfadb24dec58d50d7c2fd8997977506a79a22d24aeeef
-  data.tar.gz: f33be2af98f5a199b563eb78aef31518c94b304c1fd120985dc3ee2febee233f
+  metadata.gz: 722b9c6547474c7a4654e46a3c7af273eaa8a77b7538592ab0df4b42dd787ea2
+  data.tar.gz: 240979d4d2d62dbdd76ab14d868c8c0ecf420e10c93ae1cdc5c8182106fef698
 SHA512:
-  metadata.gz: 1e9fd7e64a8c76c74351128fd63a25c1c56ce11351fc8cd4ce0e91ee793586ab71609ae247d3fa66615b089546887a330cb2eeec9550888ebbf9f8abb59b628d
-  data.tar.gz: bed4a30375077f6bfd35900f75976e9f960deb316421e113b65b33ad7d61f9084be427f5241c3700aa1d8fbd717d4104389855db71a43f60f846af58c3a6694b
+  metadata.gz: 483c149a8b502277cb3d5d02f3aa4e009c27b1ef1a0c9f775b27410515a6654a013f434d018933c8991227d3826648902f0831613efddf3523e031a49dd586f8
+  data.tar.gz: 823bc37d94226a5dfed9d0db49ae6b8803ff74a719e8d3332b08d934bdaaa2c83374b41b5591fd6a714b6f8bca41a65bc6fa0ea099f6eadb5b17176ed5f61c56

data/bin/htmlproofer

@@ -20,13 +20,13 @@ Mercenary.program(:htmlproofer) do |p|
   p.option 'as_links', '--as-links', 'Assumes that `PATH` is a comma-separated array of links to check.'
   p.option 'alt_ignore', '--alt-ignore image1,[image2,...]', Array, 'A comma-separated list of Strings or RegExps containing `img`s whose missing `alt` tags are safe to ignore'
   p.option 'assume_extension', '--assume-extension', 'Automatically add extension (e.g. `.html`) to file paths, to allow extensionless URLs (as supported by Jekyll 3 and GitHub Pages) (default: `false`).'
-  p.option 'checks_to_ignore', '--checks-to-ignore check1,[check2,...]', Array, ' An array of Strings indicating which checks you\'d like to not perform.'
+  p.option 'checks_to_ignore', '--checks-to-ignore check1,[check2,...]', Array, 'A comma-separated list of Strings indicating which checks you do not want to run (default: `[]`)'
   p.option 'check_external_hash', '--check-external-hash', 'Checks whether external hashes exist (even if the webpage exists). This slows the checker down (default: `false`).'
   p.option 'check_favicon', '--check-favicon', 'Enables the favicon checker (default: `false`).'
-  p.option 'check_html', '--check-html', 'Enables HTML validation errors from Nokogiri (default: `false`).'
+  p.option 'check_html', '--check-html', 'Enables HTML validation errors from Nokogumbo (default: `false`).'
   p.option 'check_img_http', '--check-img-http', 'Fails an image if it\'s marked as `http` (default: `false`).'
   p.option 'check_opengraph', '--check-opengraph', 'Enables the Open Graph checker (default: `false`).'
-  p.option 'check_sri', '--check-sri', 'Check that `<link>` and `<script>` external resources do use SRI (default: `false`).'
+  p.option 'check_sri', '--check-sri', 'Check that `<link>` and `<script>` external resources use SRI (default: `false`).'
   p.option 'directory_index_file', '--directory-index-file <filename>', String, 'Sets the file to look for when a link refers to a directory. (default: `index.html`)'
   p.option 'disable_external', '--disable-external', 'If `true`, does not run the external link checker, which can take a lot of time (default: `false`)'
   p.option 'empty_alt_ignore', '--empty-alt-ignore', 'If `true`, ignores images with empty alt tags'
@@ -37,9 +37,10 @@ Mercenary.program(:htmlproofer) do |p|
   p.option 'file_ignore', '--file-ignore file1,[file2,...]', Array, 'A comma-separated list of Strings or RegExps containing file paths that are safe to ignore'
   p.option 'http_status_ignore', '--http-status-ignore 123,[xxx, ...]', Array, 'A comma-separated list of numbers representing status codes to ignore.'
   p.option 'internal_domains', '--internal-domains domain1,[domain2,...]', Array, 'A comma-separated list of Strings containing domains that will be treated as internal urls.'
-  p.option 'report_invalid_tags', '--report-invalid-tags', 'Ignore `check_html` errors associated with unknown markup (default: `false`)'
-  p.option 'report_missing_names', '--report-missing-names', 'Ignore `check_html` errors associated with missing entities (default: `false`)'
-  p.option 'report_script_embeds', '--report-script-embeds', 'Ignore `check_html` errors associated with `script`s (default: `false`)'
+  p.option 'report_invalid_tags', '--report-invalid-tags', 'When `check_html` is enabled, HTML markup that is unknown to Nokogumbo are reported as errors (default: `false`)'
+  p.option 'report_missing_names', '--report-missing-names', 'When `check_html` is enabled, HTML markup that are missing entity names are reported as errors (default: `false`)'
+  p.option 'report_script_embeds', '--report-script-embeds', 'When `check_html` is enabled, `script` tags containing markup are reported as errors (default: `false`)'
+  p.option 'report_missing_doctype', '--report-missing-doctype', 'When `check_html` is enabled, HTML markup with missing or out-of-order `DOCTYPE` are reported as errors (default: `false`)'
   p.option 'log_level', '--log-level <level>', String, 'Sets the logging level, as determined by Yell. One of `:debug`, `:info`, `:warn`, `:error`, or `:fatal`. (default: `:info`)'
   p.option 'only_4xx', '--only-4xx', 'Only reports errors for links that fall within the 4xx status code range'
   p.option 'storage_dir', '--storage-dir PATH', String, 'Directory where to store the cache log (default: "tmp/.htmlproofer")'
@@ -47,6 +48,7 @@ Mercenary.program(:htmlproofer) do |p|
   p.option 'typhoeus_config', '--typhoeus-config CONFIG', String, 'JSON-formatted string of Typhoeus config. Will override the html-proofer defaults.'
   p.option 'url_ignore', '--url-ignore link1,[link2,...]', Array, 'A comma-separated list of Strings or RegExps containing URLs that are safe to ignore. It affects all HTML attributes. Note that non-HTTP(S) URIs are always ignored'
   p.option 'url_swap', '--url-swap re:string,[re:string,...]', Array, 'A comma-separated list containing key-value pairs of `RegExp => String`. It transforms URLs that match `RegExp` into `String` via `gsub`. The escape sequences `\\:` should be used to produce literal `:`s.'
+  p.option 'root_dir', '--root-folder PATH', String, 'The absolute path to the directory serving your html-files. Used when running html-proofer on a file, rather than a directory.'
 
   p.action do |args, opts|
     args = ['.'] if args.empty?
@@ -56,9 +58,7 @@ Mercenary.program(:htmlproofer) do |p|
 
     # prepare everything to go to proofer
     p.options.reject { |o| opts[o.config_key].nil? }.each do |option|
-      if opts[option.config_key].is_a?(Array)
-        opts[option.config_key] = opts[option.config_key].map { |i| HTMLProofer::Configuration.to_regex?(i) }
-      end
+      opts[option.config_key] = opts[option.config_key].map { |i| HTMLProofer::Configuration.to_regex?(i) } if opts[option.config_key].is_a?(Array)
       options[option.config_key.to_sym] = opts[option.config_key]
     end
 
@@ -81,10 +81,9 @@ Mercenary.program(:htmlproofer) do |p|
     options[:validation][:report_script_embeds] = opts['report_script_embeds'] unless opts['report_script_embeds'].nil?
     options[:validation][:report_missing_names] = opts['report_missing_names'] unless opts['report_missing_names'].nil?
     options[:validation][:report_invalid_tags] = opts['report_invalid_tags'] unless opts['report_invalid_tags'].nil?
+    options[:validation][:report_missing_doctype] = opts['report_missing_doctype'] unless opts['report_missing_doctype'].nil?
 
-    unless opts['typhoeus_config'].nil?
-      options[:typhoeus] = HTMLProofer::Configuration.parse_json_option('typhoeus_config', opts['typhoeus_config'])
-    end
+    options[:typhoeus] = HTMLProofer::Configuration.parse_json_option('typhoeus_config', opts['typhoeus_config']) unless opts['typhoeus_config'].nil?
 
     unless opts['timeframe'].nil?
       options[:cache] ||= {}

data/lib/html-proofer.rb

@@ -17,38 +17,38 @@ require 'fileutils'
 begin
   require 'awesome_print'
   require 'pry-byebug'
-rescue LoadError; end
+rescue LoadError; end # rubocop:disable Lint/SuppressedException
 module HTMLProofer
-  def check_file(file, options = {})
+  def self.check_file(file, options = {})
     raise ArgumentError unless file.is_a?(String)
     raise ArgumentError, "#{file} does not exist" unless File.exist?(file)
+
     options[:type] = :file
     HTMLProofer::Runner.new(file, options)
   end
-  module_function :check_file
 
-  def check_directory(directory, options = {})
+  def self.check_directory(directory, options = {})
     raise ArgumentError unless directory.is_a?(String)
     raise ArgumentError, "#{directory} does not exist" unless Dir.exist?(directory)
+
     options[:type] = :directory
     HTMLProofer::Runner.new([directory], options)
   end
-  module_function :check_directory
 
-  def check_directories(directories, options = {})
+  def self.check_directories(directories, options = {})
     raise ArgumentError unless directories.is_a?(Array)
+
     options[:type] = :directory
     directories.each do |directory|
       raise ArgumentError, "#{directory} does not exist" unless Dir.exist?(directory)
     end
     HTMLProofer::Runner.new(directories, options)
   end
-  module_function :check_directories
 
-  def check_links(links, options = {})
+  def self.check_links(links, options = {})
     raise ArgumentError unless links.is_a?(Array)
+
     options[:type] = :links
     HTMLProofer::Runner.new(links, options)
   end
-  module_function :check_links
 end

data/lib/html-proofer/cache.rb

@@ -9,7 +9,7 @@ module HTMLProofer
     include HTMLProofer::Utils
 
     DEFAULT_STORAGE_DIR = File.join('tmp', '.htmlproofer')
-    DEFAULT_CACHE_FILE_NAME = 'cache.log'.freeze
+    DEFAULT_CACHE_FILE_NAME = 'cache.log'
 
     attr_reader :exists, :cache_log, :storage_dir, :cache_file
 
@@ -120,9 +120,8 @@ module HTMLProofer
       @cache_log.each_pair do |url, cache|
         if within_timeframe?(cache['time'])
           next if cache['message'].empty? # these were successes to skip
-          urls_to_check[url] = cache['filenames'] # these are failures to retry
         else
-          urls_to_check[url] = cache['filenames'] # pass or fail, recheck expired links
+          urls_to_check[url] = cache['filenames'] # recheck expired links
         end
       end
       urls_to_check
@@ -142,23 +141,16 @@ module HTMLProofer
     end
 
     def setup_cache!(options)
-      @storage_dir = if options[:storage_dir]
-                       options[:storage_dir]
-                     else
-                       DEFAULT_STORAGE_DIR
-                     end
+      @storage_dir = options[:storage_dir] || DEFAULT_STORAGE_DIR
 
       FileUtils.mkdir_p(storage_dir) unless Dir.exist?(storage_dir)
 
-      cache_file_name = if options[:cache_file]
-                          options[:cache_file]
-                        else
-                          DEFAULT_CACHE_FILE_NAME
-                        end
+      cache_file_name = options[:cache_file] || DEFAULT_CACHE_FILE_NAME
 
       @cache_file = File.join(storage_dir, cache_file_name)
 
       return unless File.exist?(cache_file)
+
       contents = File.read(cache_file)
       @cache_log = contents.empty? ? {} : JSON.parse(contents)
     end
@@ -174,7 +166,7 @@ module HTMLProofer
       when :days
         @cache_datetime - measurement
       when :hours
-        @cache_datetime - Rational(measurement/24.0)
+        @cache_datetime - Rational(measurement / 24.0)
       end.to_time
     end
   end

data/lib/html-proofer/check.rb

@@ -29,6 +29,7 @@ module HTMLProofer
 
     def add_to_external_urls(url)
       return if @external_urls[url]
+
       add_path_for_url(url)
     end
 
@@ -45,6 +46,7 @@ module HTMLProofer
 
       ObjectSpace.each_object(Class) do |c|
         next unless c.superclass == self
+
         classes << c
       end
 

data/lib/html-proofer/check/favicon.rb

@@ -6,22 +6,24 @@ class FaviconCheck < ::HTMLProofer::Check
     @html.xpath('//link[not(ancestor::pre or ancestor::code)]').each do |node|
       favicon = create_element(node)
       next if favicon.ignore?
+
       found = true if favicon.rel.split(' ').last.eql? 'icon'
       break if found
     end
 
     return if found
 
-    return if is_immediate_redirect?
+    return if immediate_redirect?
 
     add_issue('no favicon specified')
   end
 
   private
 
-  def is_immediate_redirect?
-    # allow any instant-redirect meta tag
-    @html.xpath("//meta[@http-equiv='refresh']").attribute('content').value.start_with? '0;' rescue false
+  # allow any instant-redirect meta tag
+  def immediate_redirect?
+    @html.xpath("//meta[@http-equiv='refresh']").attribute('content').value.start_with? '0;'
+  rescue StandardError
+    false
   end
-
 end

data/lib/html-proofer/check/html.rb

@@ -1,28 +1,31 @@
 # frozen_string_literal: true
 
 class HtmlCheck < ::HTMLProofer::Check
-  SCRIPT_EMBEDS_MSG = /Element script embeds close tag/
-  INVALID_TAG_MSG = /Tag ([\w\-:]+) invalid/
-  INVALID_PREFIX = /Namespace prefix/
-  PARSE_ENTITY_REF = /htmlParseEntityRef: no name/
+  # tags embedded in scripts are used in templating languages: http://git.io/vOovv
+  SCRIPT_EMBEDS_MSG = /Element script embeds close tag/.freeze
+  INVALID_TAG_MSG = /Tag ([\w\-:]+) invalid/.freeze
+  INVALID_PREFIX = /Namespace prefix/.freeze
+  PARSE_ENTITY_REF = /htmlParseEntityRef: no name/.freeze
+  DOCTYPE_MSG = /The doctype must be the first token in the document/.freeze
 
   def run
     @html.errors.each do |error|
-      message = error.message
-      line    = error.line
-
-      if message =~ INVALID_TAG_MSG || message =~ INVALID_PREFIX
-        next unless options[:validation][:report_invalid_tags]
-      end
-
-      if message =~ PARSE_ENTITY_REF
-        next unless options[:validation][:report_missing_names]
-      end
-
-      # tags embedded in scripts are used in templating languages: http://git.io/vOovv
-      next if !options[:validation][:report_script_embeds] && message =~ SCRIPT_EMBEDS_MSG
+      add_issue(error.message, line: error.line) if report?(error.message)
+    end
+  end
 
-      add_issue(message, line: line)
+  def report?(message)
+    case message
+    when SCRIPT_EMBEDS_MSG
+      options[:validation][:report_script_embeds]
+    when INVALID_TAG_MSG, INVALID_PREFIX
+      options[:validation][:report_invalid_tags]
+    when PARSE_ENTITY_REF
+      options[:validation][:report_missing_names]
+    when DOCTYPE_MSG
+      options[:validation][:report_missing_doctype]
+    else
+      true
     end
   end
 end

data/lib/html-proofer/check/images.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 class ImageCheck < ::HTMLProofer::Check
-  SCREEN_SHOT_REGEX = /Screen(?: |%20)Shot(?: |%20)\d+-\d+-\d+(?: |%20)at(?: |%20)\d+.\d+.\d+/
+  SCREEN_SHOT_REGEX = /Screen(?: |%20)Shot(?: |%20)\d+-\d+-\d+(?: |%20)at(?: |%20)\d+.\d+.\d+/.freeze
 
   def empty_alt_tag?
     @img.alt.nil? || @img.alt.strip.empty?
@@ -38,13 +38,9 @@ class ImageCheck < ::HTMLProofer::Check
         add_issue("internal image #{@img.url} does not exist", line: line, content: content)
       end
 
-      if empty_alt_tag? && !@img.ignore_empty_alt? && !@img.ignore_alt?
-        add_issue("image #{@img.url} does not have an alt attribute", line: line, content: content)
-      end
+      add_issue("image #{@img.url} does not have an alt attribute", line: line, content: content) if empty_alt_tag? && !@img.ignore_empty_alt? && !@img.ignore_alt?
 
-      if @img.check_img_http? && @img.scheme == 'http'
-        add_issue("image #{@img.url} uses the http scheme", line: line, content: content)
-      end
+      add_issue("image #{@img.url} uses the http scheme", line: line, content: content) if @img.check_img_http? && @img.scheme == 'http'
     end
 
     external_urls

data/lib/html-proofer/check/links.rb

@@ -34,7 +34,8 @@ class LinkCheck < ::HTMLProofer::Check
       if missing_href?
         next if @link.allow_missing_href?
         # HTML5 allows dropping the href: http://git.io/vBX0z
-        next if @html.internal_subset.name == 'html' && @html.internal_subset.external_id.nil?
+        next if @html.internal_subset.nil? || (@html.internal_subset.name == 'html' && @html.internal_subset.external_id.nil?)
+
         add_issue('anchor has no href attribute', line: line, content: content)
         next
       end
@@ -47,9 +48,10 @@ class LinkCheck < ::HTMLProofer::Check
         # we need to skip these for now; although the domain main be valid,
         # curl/Typheous inaccurately return 404s for some links. cc https://git.io/vyCFx
         next if @link.respond_to?(:rel) && @link.rel == 'dns-prefetch'
+
         add_to_external_urls(@link.href)
         next
-      elsif !@link.internal? && !@link.exists?
+      elsif @link.internal? && !@link.exists?
         add_issue("internally linking to #{@link.href}, which does not exist", line: line, content: content)
       end
 
@@ -74,6 +76,7 @@ class LinkCheck < ::HTMLProofer::Check
       handle_tel(link, line, content)
     when 'http'
       return unless @options[:enforce_https]
+
       add_issue("#{link.href} is not an HTTPS link", line: line, content: content)
     end
   end
@@ -103,9 +106,7 @@ class LinkCheck < ::HTMLProofer::Check
       add_issue("trying to find hash of #{link.href}, but #{link.absolute_path} does not exist", line: line, content: content)
     else
       target_html = create_nokogiri link.absolute_path
-      unless hash_check target_html, link.hash
-        add_issue("linking to #{link.href}, but #{link.hash} does not exist", line: line, content: content)
-      end
+      add_issue("linking to #{link.href}, but #{link.hash} does not exist", line: line, content: content) unless hash_check target_html, link.hash
     end
   end
 
@@ -129,10 +130,13 @@ class LinkCheck < ::HTMLProofer::Check
     html.xpath(*xpaths)
   end
 
-  IGNORABE_REL = %(canonical alternate next prev previous icon manifest apple-touch-icon)
+  # Whitelist for affected elements from Subresource Integrity specification
+  # https://w3c.github.io/webappsec-subresource-integrity/#link-element-for-stylesheets
+  SRI_REL_TYPES = %(stylesheet)
 
   def check_sri(line, content)
-    return if IGNORABE_REL.include?(@link.rel)
+    return unless SRI_REL_TYPES.include?(@link.rel)
+
     if !defined?(@link.integrity) && !defined?(@link.crossorigin)
       add_issue("SRI and CORS not provided in: #{@link.src}", line: line, content: content)
     elsif !defined?(@link.integrity)

data/lib/html-proofer/check/opengraph.rb

@@ -1,4 +1,3 @@
-# encoding: utf-8
 # frozen_string_literal: true
 
 class OpenGraphElement < ::HTMLProofer::Element

data/lib/html-proofer/configuration.rb

@@ -51,7 +51,8 @@ module HTMLProofer
     VALIDATION_DEFAULTS = {
       report_script_embeds: false,
       report_missing_names: false,
-      report_invalid_tags: false
+      report_invalid_tags: false,
+      report_missing_doctype: false
     }.freeze
 
     CACHE_DEFAULTS = {}.freeze
@@ -65,19 +66,19 @@ module HTMLProofer
     end
 
     def self.parse_json_option(option_name, config)
-      raise ArgumentError.new('Must provide an option name in string format.') unless option_name.is_a?(String)
-      raise ArgumentError.new('Must provide an option name in string format.') unless !option_name.strip.empty?
+      raise ArgumentError, 'Must provide an option name in string format.' unless option_name.is_a?(String)
+      raise ArgumentError, 'Must provide an option name in string format.' if option_name.strip.empty?
 
       return {} if config.nil?
 
-      raise ArgumentError.new('Must provide a JSON configuration in string format.') unless config.is_a?(String)
+      raise ArgumentError, 'Must provide a JSON configuration in string format.' unless config.is_a?(String)
 
       return {} if config.strip.empty?
 
       begin
         JSON.parse(config)
-      rescue
-        raise ArgumentError.new("Option '" + option_name + "' did not contain valid JSON.")
+      rescue StandardError
+        raise ArgumentError, "Option '" + option_name + "' did not contain valid JSON."
       end
     end
   end

data/lib/html-proofer/element.rb

@@ -18,7 +18,7 @@ module HTMLProofer
         instance_variable_set("@#{name}", value.value)
       end
 
-      @aria_hidden = (defined?(@aria_hidden) && @aria_hidden == 'true') ? true : false
+      @aria_hidden = defined?(@aria_hidden) && @aria_hidden == 'true' ? true : false
 
       @data_proofer_ignore = defined?(@data_proofer_ignore)
 
@@ -56,9 +56,11 @@ module HTMLProofer
 
     def url
       return @url if defined?(@url)
+
       @url = (@src || @srcset || @href || '').delete("\u200b").strip
       @url = Addressable::URI.join(base.attr('href') || '', url).to_s if base
       return @url if @check.options[:url_swap].empty?
+
       @url = swap(@url, @check.options[:url_swap])
     end
 
@@ -77,11 +79,11 @@ module HTMLProofer
     end
 
     def hash
-      parts.fragment unless parts.nil?
+      parts&.fragment
     end
 
     def scheme
-      parts.scheme unless parts.nil?
+      parts&.scheme
     end
 
     # path is to an external server
@@ -137,9 +139,22 @@ module HTMLProofer
       !internal?
     end
 
-    # path is an anchor or a query
     def internal?
-      hash_link || param_link || slash_link
+      relative_link? || internal_absolute_link?
+    end
+
+    def internal_absolute_link?
+      url.start_with?('/')
+    end
+
+    def relative_link?
+      return false if remote?
+
+      hash_link || param_link || url.start_with?('.') || url =~ /^\S/
+    end
+
+    def link_points_to_same_page?
+      hash_link || param_link
     end
 
     def hash_link
@@ -150,21 +165,20 @@ module HTMLProofer
       url.start_with?('?')
     end
 
-    def slash_link
-      url.start_with?('|')
-    end
-
     def file_path
-      return if path.nil?
+      return if path.nil? || path.empty?
 
       path_dot_ext = ''
 
-      if @check.options[:assume_extension]
-        path_dot_ext = path + @check.options[:extension]
-      end
+      path_dot_ext = path + @check.options[:extension] if @check.options[:assume_extension]
 
       if path =~ %r{^/} # path relative to root
-        base = File.directory?(@check.src) ? @check.src : File.dirname(@check.src)
+        if File.directory?(@check.src)
+          base = @check.src
+        else
+          root_dir = @check.options[:root_dir]
+          base = root_dir || File.dirname(@check.src)
+        end
       elsif File.exist?(File.expand_path(path, @check.src)) || File.exist?(File.expand_path(path_dot_ext, @check.src)) # relative links, path is a file
         base = File.dirname @check.path
       elsif File.exist?(File.join(File.dirname(@check.path), path)) || File.exist?(File.join(File.dirname(@check.path), path_dot_ext)) # relative links in nested dir, path is a file
@@ -174,7 +188,6 @@ module HTMLProofer
       end
 
       file = File.join base, path
-
       if @check.options[:assume_extension] && File.file?("#{file}#{@check.options[:extension]}")
         file = "#{file}#{@check.options[:extension]}"
       elsif File.directory?(file) && !unslashed_directory?(file) # implicit index support
@@ -187,6 +200,7 @@ module HTMLProofer
     # checks if a file exists relative to the current pwd
     def exists?
       return @checked_paths[absolute_path] if @checked_paths.key? absolute_path
+
       @checked_paths[absolute_path] = File.exist? absolute_path
     end
 
@@ -220,12 +234,14 @@ module HTMLProofer
     end
 
     def html
-      # If link is on the same page, then URL is on the current page so can use the same HTML as for current page
-      if (hash_link || param_link) && internal?
+      # If link is on the same page, then URL is on the current page. use the same HTML as for current page
+      if link_points_to_same_page?
         @html
-      elsif slash_link && internal?
+      elsif internal?
         # link on another page, e.g. /about#Team - need to get HTML from the other page
         create_nokogiri(absolute_path)
+      else
+        raise NotImplementedError, 'HTMLProofer should not have gotten here. Please report this as a bug.'
       end
     end
   end

data/lib/html-proofer/issue.rb

@@ -56,9 +56,7 @@ module HTMLProofer
           @logger.log :error, "  *  #{issue}"
         else
           msg = "  *  #{issue.send(second_report)}#{issue.line}"
-          if !issue.content.nil? && !issue.content.empty?
-            msg = "#{msg}\n     #{issue.content}"
-          end
+          msg = "#{msg}\n     #{issue.content}" if !issue.content.nil? && !issue.content.empty?
           @logger.log(:error, msg)
         end
       end

data/lib/html-proofer/middleware.rb

@@ -2,6 +2,7 @@
 
 module HTMLProofer
   class Middleware
+    include HTMLProofer::Utils
 
     class InvalidHtmlError < StandardError
       def initialize(failures)
@@ -9,18 +10,18 @@ module HTMLProofer
       end
 
       def message
-          "HTML Validation errors (skip by adding `?proofer-ignore` to URL): \n#{@failures.join("\n")}"
+        "HTML Validation errors (skip by adding `?proofer-ignore` to URL): \n#{@failures.join("\n")}"
       end
     end
 
     def self.options
       @options ||= {
-        type:                :file,
-        allow_missing_href:  true, # Permitted in html5
-        allow_hash_href:     true,
+        type: :file,
+        allow_missing_href: true, # Permitted in html5
+        allow_hash_href: true,
         check_external_hash: true,
-        check_html:          true,
-        url_ignore:          [/.*/], # Don't try to check local files exist
+        check_html: true,
+        url_ignore: [/.*/] # Don't try to check local files exist
       }
     end
 
@@ -46,20 +47,21 @@ module HTMLProofer
       '<BR',
       '<P',
       '<!--'
-    ]
+    ].freeze
 
     def call(env)
       result = @app.call(env)
       return result if env['REQUEST_METHOD'] != 'GET'
       return result if env['QUERY_STRING'] =~ /proofer-ignore/
       return result if result.first != 200
+
       body = []
       result.last.each { |e| body << e }
 
       body = body.join('')
       begin
         html = body.lstrip
-      rescue
+      rescue StandardError
         return result # Invalid encoding; it's not gonna be html.
       end
       if HTML_SIGNATURE.any? { |sig| html.upcase.start_with? sig }
@@ -67,12 +69,10 @@ module HTMLProofer
           'response',
           Middleware.options
         ).check_parsed(
-          Nokogiri::HTML(Utils.clean_content(html)), 'response'
+          Nokogiri::HTML5(html, max_errors: -1), 'response'
         )
 
-        if parsed[:failures].length > 0
-          raise InvalidHtmlError.new(parsed[:failures])
-        end
+        raise InvalidHtmlError, parsed[:failures] unless parsed[:failures].empty?
       end
       result
     end

data/lib/html-proofer/runner.rb

@@ -4,7 +4,7 @@ module HTMLProofer
   class Runner
     include HTMLProofer::Utils
 
-    attr_reader :options, :external_urls
+    attr_reader :options, :external_urls, :failures
 
     def initialize(src, opts = {})
       @src = src
@@ -103,9 +103,7 @@ module HTMLProofer
           check = Object.const_get(klass).new(src, path, html, @options)
           check.run
           external_urls = check.external_urls
-          if @options[:url_swap]
-            external_urls = Hash[check.external_urls.map { |url, file| [swap(url, @options[:url_swap]), file] }]
-          end
+          external_urls = Hash[check.external_urls.map { |url, file| [swap(url, @options[:url_swap]), file] }] if @options[:url_swap]
           result[:external_urls].merge!(external_urls)
           result[:failures].concat(check.issues)
         end
@@ -148,6 +146,7 @@ module HTMLProofer
 
     def checks
       return @checks if defined?(@checks) && !@checks.nil?
+
       @checks = HTMLProofer::Check.subchecks.map(&:name)
       @checks.delete('FaviconCheck') unless @options[:check_favicon]
       @checks.delete('HtmlCheck') unless @options[:check_html]
@@ -159,6 +158,7 @@ module HTMLProofer
     def failed_tests
       result = []
       return result if @failures.empty?
+
       @failures.each { |f| result << f.to_s }
       result
     end

data/lib/html-proofer/url_validator.rb

@@ -36,6 +36,7 @@ module HTMLProofer
 
     def remove_query_values
       return nil if @external_urls.nil?
+
       paths_with_queries = {}
       iterable_external_urls = @external_urls.dup
       @external_urls.each_key do |url|
@@ -46,6 +47,7 @@ module HTMLProofer
                 nil
               end
         next if uri.nil? || uri.query.nil?
+
         iterable_external_urls.delete(url) unless new_url_query_values?(uri, paths_with_queries)
       end
       iterable_external_urls
@@ -108,9 +110,9 @@ module HTMLProofer
       external_urls.each_pair do |url, filenames|
         url = begin
                  clean_url(url)
-               rescue URI::Error, Addressable::URI::InvalidURIError
-                 add_external_issue(filenames, "#{url} is an invalid URL")
-                 next
+              rescue URI::Error, Addressable::URI::InvalidURIError
+                add_external_issue(filenames, "#{url} is an invalid URL")
+                next
                end
 
         method = if hash?(url) && @options[:check_external_hash]
@@ -144,22 +146,20 @@ module HTMLProofer
       href = response.request.base_url.to_s
       method = response.request.options[:method]
       response_code = response.code
-      response.body.gsub!("\x00", '')
+      response.body.delete!("\x00")
 
-      if filenames.nil?
-        debug_msg = "Received a #{response_code} for #{href}"
-      else
-        debug_msg = "Received a #{response_code} for #{href}  in #{filenames.join(' ')}"
-      end
+      debug_msg = if filenames.nil?
+                    "Received a #{response_code} for #{href}"
+                  else
+                    "Received a #{response_code} for #{href}  in #{filenames.join(' ')}"
+                  end
 
       @logger.log :debug, debug_msg
 
       return if @options[:http_status_ignore].include?(response_code)
 
       if response_code.between?(200, 299)
-        unless check_hash_in_2xx_response(href, effective_url, response, filenames)
-          @cache.add(href, filenames, response_code)
-        end
+        @cache.add(href, filenames, response_code) unless check_hash_in_2xx_response(href, effective_url, response, filenames)
       elsif response.timed_out?
         handle_timeout(href, filenames, response_code)
       elsif response_code.zero?
@@ -168,6 +168,7 @@ module HTMLProofer
         queue_request(:get, href, filenames)
       else
         return if @options[:only_4xx] && !response_code.between?(400, 499)
+
         # Received a non-successful http response.
         msg = "External link #{href} failed: #{response_code} #{response.return_message}"
         add_external_issue(filenames, msg, response_code)
@@ -191,9 +192,7 @@ module HTMLProofer
         xpath << [%(//*[@name="user-content-#{hash}"]|//*[@id="user-content-#{hash}"])]
         # when linking to a file on GitHub, like #L12-L34, only the first "L" portion
         # will be identified as a linkable portion
-        if hash =~ /\A(L\d)+/
-          xpath << [%(//td[@id="#{Regexp.last_match[1]}"])]
-        end
+        xpath << [%(//td[@id="#{Regexp.last_match[1]}"])] if hash =~ /\A(L\d)+/
       end
 
       return unless body_doc.xpath(xpath.join('|')).empty?
@@ -208,6 +207,7 @@ module HTMLProofer
       msg = "External link #{href} failed: got a time out (response code #{response_code})"
       @cache.add(href, filenames, 0, msg)
       return if @options[:only_4xx]
+
       add_external_issue(filenames, msg, response_code)
     end
 
@@ -218,6 +218,7 @@ module HTMLProofer
              Either way, the return message (if any) from the server is: #{return_message}"
       @cache.add(href, filenames, 0, msg)
       return if @options[:only_4xx]
+
       add_external_issue(filenames, msg, response_code)
     end
 

data/lib/html-proofer/utils.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require 'nokogiri'
+require 'nokogumbo'
 
 module HTMLProofer
   module Utils
@@ -15,9 +15,8 @@ module HTMLProofer
                   path
                 end
 
-      Nokogiri::HTML(clean_content(content))
+      Nokogiri::HTML5(content)
     end
-    module_function :create_nokogiri
 
     def swap(href, replacement)
       replacement.each do |link, replace|
@@ -25,16 +24,5 @@ module HTMLProofer
       end
       href
     end
-    module_function :swap
-
-    # address a problem with Nokogiri's parsing URL entities
-    # problem from http://git.io/vBYU1
-    # solution from http://git.io/vBYUi
-    def clean_content(string)
-      string.gsub(%r{(?:https?:)?//([^>]+)}i) do |url|
-        url.gsub(/&(?!amp;)/, '&')
-      end
-    end
-    module_function :clean_content
   end
 end

data/lib/html-proofer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HTMLProofer
-  VERSION = '3.12.1'.freeze
+  VERSION = '3.15.0'
 end

metadata

@@ -1,59 +1,59 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 3.12.1
+  version: 3.15.0
 platform: ruby
 authors:
 - Garen Torikian
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-09-07 00:00:00.000000000 Z
+date: 2019-12-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: mercenary
+  name: addressable
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '2.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.3'
+        version: '2.3'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: mercenary
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '0.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '0.3'
 - !ruby/object:Gem::Dependency
-  name: rainbow
+  name: nokogumbo
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.0'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
-  name: typhoeus
+  name: parallel
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
@@ -67,21 +67,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
-  name: yell
+  name: rainbow
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '3.0'
 - !ruby/object:Gem::Dependency
-  name: parallel
+  name: typhoeus
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
@@ -95,21 +95,21 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '1.3'
 - !ruby/object:Gem::Dependency
-  name: addressable
+  name: yell
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.3'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.3'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
-  name: redcarpet
+  name: awesome_print
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -123,7 +123,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rubocop
+  name: codecov
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -137,7 +137,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rubocop-standard
+  name: pry-byebug
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -151,7 +151,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: rubocop-performance
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -165,7 +165,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: codecov
+  name: redcarpet
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -193,7 +193,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '3.1'
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: rubocop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -207,7 +207,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: pry-byebug
+  name: rubocop-performance
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -221,7 +221,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: awesome_print
+  name: rubocop-standard
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -235,33 +235,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
-  name: vcr
+  name: timecop
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.9'
+        version: '0.8'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.9'
+        version: '0.8'
 - !ruby/object:Gem::Dependency
-  name: timecop
+  name: vcr
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '2.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.8'
+        version: '2.9'
 description: Test your rendered HTML files to make sure they're accurate.
 email:
 - gjtorikian@gmail.com