html-proofer 3.4.0 → 3.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: dbcb9a266ebfc0ded83c471ce4c39b316707cdc8
-  data.tar.gz: 95eaa7fb30840606d11dc234eb9b6e5917971100
+  metadata.gz: c8e32513d55bbc3b6fe0b8b238199fa0270c13a4
+  data.tar.gz: 6b1f6264dae93f15f2e09e4542e2f7b5d6ffff3c
 SHA512:
-  metadata.gz: 91e54490b69b026d0e2ddefbdc6a89858c6943b3193a2f80b389835f45d10708f5b9abb919c3eece6a6827b0630afc67f2d1d49b0c60c5a669fcdf6ecfdac444
-  data.tar.gz: a97d14e881323aa66e7a7c31bd1db5f007890d3715ba0950a9bf51f44117f076e982cc7c85a0b1e9433f5c4dfd5d5ecb12212b5d92108d4c21c7e4e3bbdc885e
+  metadata.gz: b9f3c3a6028eb2eae4b3fb0f999702c80c06b3a89a6a715ee7f1d5b09d12b50ca47bd739c8696d1b6ff531f647afa3b85d1ee29c04fb0c81fa5e60896787661f
+  data.tar.gz: b5eaa5f478efd12a53161a91218da9661a979dfe91cd1ba2873b365ec94ec0c9b2f9d8202befacb062c92da6820cd83a914e54fa9c83046a12648ba11b862337

data/bin/htmlproofer

@@ -23,6 +23,7 @@ Mercenary.program(:htmlproofer) do |p|
   p.option 'check_html', '--check-html', 'Enables HTML validation errors from Nokogiri (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 'directory_index_file', '--directory-index-file', 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'

data/lib/html-proofer.rb

@@ -14,6 +14,7 @@ require 'fileutils'
 
 begin
   require 'awesome_print'
+  require 'pry'
 rescue LoadError; end
 
 module HTMLProofer

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

@@ -38,8 +38,11 @@ class LinkCheck < ::HTMLProofer::Check
 
       # intentionally here because we still want valid? & missing_href? to execute
       next if @link.non_http_remote?
-      # does the file even exist?
+
       if !@link.internal? && @link.remote?
+        # 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.try(:rel) == 'dns-prefetch'
         add_to_external_urls(@link.href)
         next
       elsif !@link.internal? && !@link.exists?

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

@@ -22,8 +22,19 @@ class ScriptCheck < ::HTMLProofer::Check
       elsif !@script.exists?
         add_issue("internal script #{@script.src} does not exist", line: line, content: content)
       end
+      check_sri(line, content) if @script.check_sri?
     end
 
     external_urls
   end
+
+  def check_sri(line, content)
+    if !defined? @script.integrity and !defined? @script.crossorigin
+      add_issue("SRI and CORS not provided in: #{@script.src}", line: line, content: content)
+    elsif !defined? @script.integrity
+      add_issue("Integrity is missing in: #{@script.src}", line: line, content: content)
+    elsif !defined? @script.crossorigin
+      add_issue("CORS not provided for external resource in: #{@script.src}", line: line, content: content)
+    end
+  end
 end

data/lib/html-proofer/configuration.rb

@@ -12,6 +12,7 @@ module HTMLProofer
       :check_img_http => false,
       :check_opengraph => false,
       :checks_to_ignore => [],
+      :check_sri => false,
       :directory_index_file => 'index.html',
       :disable_external => false,
       :empty_alt_ignore => false,

data/lib/html-proofer/element.rb

@@ -26,6 +26,10 @@ module HTMLProofer
 
       @html = check.html
 
+      parent_attributes = obj.ancestors.map { |a| a.try(:attributes) }
+      parent_attributes.pop # remove document at the end
+      @parent_ignorable = parent_attributes.any? { |a| !a["data-proofer-ignore"].nil? }
+
       # fix up missing protocols
       @href.insert 0, 'http:' if @href =~ %r{^//}
       @src.insert 0, 'http:' if @src =~ %r{^//}
@@ -75,6 +79,7 @@ module HTMLProofer
 
     def ignore?
       return true if @data_proofer_ignore
+      return true if @parent_ignorable
 
       return true if url =~ /^javascript:/
 
@@ -103,6 +108,10 @@ module HTMLProofer
       @check.options[:check_img_http]
     end
 
+    def check_sri?
+      @check.options[:check_sri]
+    end
+
     # path is external to the file
     def external?
       !internal?

data/lib/html-proofer/url_validator.rb

@@ -121,7 +121,13 @@ module HTMLProofer
     end
 
     def clean_url(href)
-      Addressable::URI.parse(href).normalize
+      # catch any obvious issues, like strings in port numbers
+      parsed = Addressable::URI.parse(href)
+      if href !~ %r{^([!#$&-;=?-\[\]_a-z~]|%[0-9a-fA-F]{2})+$}
+        parsed.normalize
+      else
+        href
+      end
     end
 
     def queue_request(method, href, filenames)
@@ -149,14 +155,14 @@ module HTMLProofer
         end
       elsif response.timed_out?
         handle_timeout(href, filenames, response_code)
-      elsif response_code == 0
+      elsif response_code.zero?
         handle_failure(effective_url, filenames, response_code, response.return_message)
       elsif method == :head
         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}"
+        msg = "External link #{href.chomp('/')} failed: #{response_code} #{response.return_message}"
         add_external_issue(filenames, msg, response_code)
         @cache.add(href, filenames, response_code, msg)
       end
@@ -179,21 +185,21 @@ module HTMLProofer
 
       return unless body_doc.xpath(xpath).empty?
 
-      msg = "External link #{href} failed: #{effective_url} exists, but the hash '#{hash}' does not"
+      msg = "External link #{href.chomp('/')} failed: #{effective_url} exists, but the hash '#{hash}' does not"
       add_external_issue(filenames, msg, response.code)
       @cache.add(href, filenames, response.code, msg)
       true
     end
 
     def handle_timeout(href, filenames, response_code)
-      msg = "External link #{href} failed: got a time out (response code #{response_code})"
+      msg = "External link #{href.chomp('/')} 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
 
     def handle_failure(href, filenames, response_code, return_message)
-      msg = "External link #{href} failed: response code #{response_code} means something's wrong.
+      msg = "External link #{href.chomp('/')} failed: response code #{response_code} means something's wrong.
              It's possible libcurl couldn't connect to the server or perhaps the request timed out.
              Sometimes, making too many requests at once also breaks things.
              Either way, the return message (if any) from the server is: #{return_message}"

data/lib/html-proofer/version.rb

@@ -1,3 +1,3 @@
 module HTMLProofer
-  VERSION = '3.4.0'.freeze
+  VERSION = '3.5.0'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 3.4.0
+  version: 3.5.0
 platform: ruby
 authors:
 - Garen Torikian
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-12-16 00:00:00.000000000 Z
+date: 2017-03-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mercenary
@@ -170,6 +170,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.0
 - !ruby/object:Gem::Dependency
   name: awesome_print
   requirement: !ruby/object:Gem::Requirement