html-proofer 3.14.1 → 3.15.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e652993805b4e62434a27fd09f20936c71d1abfa2588e1ea991ed00d5174cfa4
-  data.tar.gz: 1e4feee6f61dbadd8ed0d91e25950c0f643e3f29ee1cf881fa9bde6f37854901
+  metadata.gz: 722b9c6547474c7a4654e46a3c7af273eaa8a77b7538592ab0df4b42dd787ea2
+  data.tar.gz: 240979d4d2d62dbdd76ab14d868c8c0ecf420e10c93ae1cdc5c8182106fef698
 SHA512:
-  metadata.gz: a6955c42ec89662b66b83422555e0d43c837f2d11f9e67bf85f587b2301d7c24f6f0275e16b31c904ee9da2999dde8583994d532f5be7a2b2f838dda2dab6e1b
-  data.tar.gz: d261d16b8fcd86ceeac73eac6594b3c30a589015b5400ad785e879ce8b77ad7793fd85609063b6b57ffb08333ac07e1982a1b7cae449ab3e7cc5e0f1c36d6e5d
+  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")'
@@ -80,6 +81,7 @@ 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?
 
     options[:typhoeus] = HTMLProofer::Configuration.parse_json_option('typhoeus_config', opts['typhoeus_config']) unless opts['typhoeus_config'].nil?
 

data/lib/html-proofer.rb

@@ -17,7 +17,7 @@ require 'fileutils'
 begin
   require 'awesome_print'
   require 'pry-byebug'
-rescue LoadError; end # rubocop:disable Lint/HandleExceptions
+rescue LoadError; end # rubocop:disable Lint/SuppressedException
 module HTMLProofer
   def self.check_file(file, options = {})
     raise ArgumentError unless file.is_a?(String)

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

@@ -1,28 +1,31 @@
 # frozen_string_literal: true
 
 class HtmlCheck < ::HTMLProofer::Check
+  # 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/links.rb

@@ -34,7 +34,7 @@ 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

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

data/lib/html-proofer/middleware.rb

@@ -69,7 +69,7 @@ module HTMLProofer
           'response',
           Middleware.options
         ).check_parsed(
-          Nokogiri::HTML(clean_content(html)), 'response'
+          Nokogiri::HTML5(html, max_errors: -1), 'response'
         )
 
         raise InvalidHtmlError, parsed[:failures] unless parsed[:failures].empty?

data/lib/html-proofer/url_validator.rb

@@ -146,7 +146,7 @@ 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")
 
       debug_msg = if filenames.nil?
                     "Received a #{response_code} for #{href}"

data/lib/html-proofer/utils.rb

@@ -1,6 +1,6 @@
 # frozen_string_literal: true
 
-require 'nokogiri'
+require 'nokogumbo'
 
 module HTMLProofer
   module Utils
@@ -15,7 +15,7 @@ module HTMLProofer
                   path
                 end
 
-      Nokogiri::HTML(clean_content(content))
+      Nokogiri::HTML5(content)
     end
 
     def swap(href, replacement)
@@ -24,14 +24,5 @@ module HTMLProofer
       end
       href
     end
-
-    # 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
   end
 end

data/lib/html-proofer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HTMLProofer
-  VERSION = '3.14.1'
+  VERSION = '3.15.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 3.14.1
+  version: 3.15.0
 platform: ruby
 authors:
 - Garen Torikian
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-11-17 00:00:00.000000000 Z
+date: 2019-12-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -39,19 +39,19 @@ dependencies:
       - !ruby/object:Gem::Version
         version: '0.3'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: nokogumbo
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.10'
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: parallel
   requirement: !ruby/object:Gem::Requirement