html-proofer 3.0.0 → 3.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1ce6c96e75683a8da4de60754d83aef138221d02
-  data.tar.gz: b341f1ee5b7237e58cba8e775dfaa152eaeeb0a5
+  metadata.gz: 2d69ea6f2eb74095372c3f46f5b0b40beb25d4c2
+  data.tar.gz: b788331194e898263a88a47f41c60f77a4f3051a
 SHA512:
-  metadata.gz: 000ff0816076d1e8b738526f380e88309fdc04d93fa203a43d62960696064062b7942647a5f79be0f8e7239ca69e67f08f669866352cabf67152a6f95beb643b
-  data.tar.gz: 1863ee52843f2d5071170aaed79ce2ae9f6902ffb1a99d93021b746eb9d3d792d460d4caff2f703907291915b0bc8861af8967cd4f5a394e0a6604aa23e0dec0
+  metadata.gz: a98a1fd90173d4481caae3c2fa7b702e1d5ab04cd262f4c555d250b7ce4518e29bcb0f3cfba7cd33d88526389bd05f3665b3ebb6ca0a46404057fa01f7663c62
+  data.tar.gz: 603de7c0256dde6120f0cce01e4803768c09468c620a04d81d6b053bd3d66e72573bc8fbe33efa9597a090fcd3c9f8744826021829e1619fc35fdc584c8c7513

data/bin/htmlproofer

@@ -18,9 +18,10 @@ Mercenary.program(:htmlproofer) do |p|
   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 'check_external_hash', '--check-external-hash', 'Checks whether external hashes exist (even if the website exists). This slows the checker down (default: `false`).'
+  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_img_http', '--check-img-http', 'Fails an image if it\'s marked as `http` (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'
@@ -31,12 +32,14 @@ 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 '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 'log_level', '--log-level <level>', String, 'Sets the logging level, as determined by Yell'
   p.option 'only_4xx', '--only-4xx', 'Only reports errors for links that fall within the 4xx status code range'
   p.option 'timeframe', '--timeframe <time>', String, 'A string representing the caching timeframe.'
   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`.'
+  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 'internal_domains', '--internal-domains domain1,[domain2,...]', Array, 'A comma-separated list of Strings containing domains that will be treated as internal urls.'
 
   p.action do |args, opts|
     args = ['.'] if args.empty?
@@ -46,7 +49,7 @@ Mercenary.program(:htmlproofer) do |p|
 
     # prepare everything to go to proofer
     p.options.select { |o| !opts[o.config_key].nil? }.each do |option|
-      if option.return_type.to_s == 'Array' # TODO: is_a? doesn't work here?
+      if opts[option.config_key].is_a?(Array)
         opts[option.config_key] = opts[option.config_key].map { |i| HTMLProofer::Configuration.to_regex?(i) }
       end
       options[option.config_key.to_sym] = opts[option.config_key]
@@ -56,8 +59,11 @@ Mercenary.program(:htmlproofer) do |p|
     unless opts['url_swap'].nil?
       options[:url_swap] = {}
       opts['url_swap'].each do |s|
-        pair = s.split(':', 2)
-        options[:url_swap][Regexp.new(pair[0])] = pair[1]
+        splt = s.split(/(?<!\\):/,2)
+
+        re = splt[0].gsub(/\\:/, ':')
+        string = splt[1].gsub(/\\:/, ':')
+        options[:url_swap][Regexp.new(re)] = string
       end
     end
 
@@ -67,11 +73,14 @@ Mercenary.program(:htmlproofer) do |p|
     # FIXME: this is gross
     options[:validation] = {}
     options[:validation][:report_script_embeds] = opts['report_script_embeds']
+    options[:validation][:report_missing_names] = opts['report_missing_names']
     options[:validation][:report_invalid_tags] = opts['report_invalid_tags']
 
     options[:cache] = {}
     options[:cache][:timeframe] = opts['timeframe'] unless opts['timeframe'].nil?
 
+    options[:http_status_ignore] = Array(options[:http_status_ignore]).map(&:to_i)
+
     paths = path.split(',')
     if opts['as_links']
       links = path.delete(' ').split(',')

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

@@ -2,6 +2,7 @@ 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/
 
   def run
     @html.errors.each do |error|
@@ -12,6 +13,10 @@ class HtmlCheck < ::HTMLProofer::Check
         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
 

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

@@ -37,9 +37,13 @@ class ImageCheck < ::HTMLProofer::Check
         end
       end
 
-      if @img.alt.nil? || (empty_alt_tag? && !@img.ignore_empty_alt?)
+      if !@img.ignore_alt? && (@img.alt.nil? || (empty_alt_tag? && !@img.ignore_empty_alt?))
         add_issue("image #{@img.url} does not have an alt attribute", line: line)
       end
+
+      if @img.check_img_http? && @img.scheme == 'http'
+        add_issue("image #{@img.url} uses the http scheme", line: line)
+      end
     end
 
     external_urls

data/lib/html-proofer/configuration.rb

@@ -9,6 +9,7 @@ module HTMLProofer
       :check_external_hash => false,
       :check_favicon => false,
       :check_html => false,
+      :check_img_http => false,
       :checks_to_ignore => [],
       :directory_index_file => 'index.html',
       :disable_external => false,
@@ -19,10 +20,11 @@ module HTMLProofer
       :external_only => false,
       :file_ignore => [],
       :http_status_ignore => [],
+      :internal_domains => [],
       :log_level => :info,
       :only_4xx => false,
       :url_ignore => [],
-      :url_swap => []
+      :url_swap => {}
     }
 
     TYPHOEUS_DEFAULTS = {
@@ -40,6 +42,7 @@ module HTMLProofer
 
     VALIDATION_DEFAULTS = {
       :report_script_embeds => false,
+      :report_missing_names => false,
       :report_invalid_tags => false
     }
 

data/lib/html-proofer/element.rb

@@ -6,10 +6,10 @@ module HTMLProofer
   class Element
     include HTMLProofer::Utils
 
-    attr_reader :id, :name, :alt, :href, :link, :src, :line
+    attr_reader :id, :name, :alt, :href, :link, :src, :line, :data_proofer_ignore
 
     def initialize(obj, check)
-      # Contruct readable ivars for every element
+      # Construct readable ivars for every element
       obj.attributes.each_pair do |attribute, value|
         name = "#{attribute.tr('-:.', '_')}".to_sym
         (class << self; self; end).send(:attr_reader, name)
@@ -25,10 +25,11 @@ module HTMLProofer
       # fix up missing protocols
       @href.insert 0, 'http:' if @href =~ %r{^//}
       @src.insert 0, 'http:' if @src =~ %r{^//}
+      @srcset.insert 0, 'http:' if @srcset =~ %r{^//}
     end
 
     def url
-      url = @src || @srcset || @href || ''
+      url = (@src || @srcset || @href || '').gsub("\u200b", '')
       return url if @check.options[:url_swap].empty?
       swap(url, @check.options[:url_swap])
     end
@@ -39,7 +40,7 @@ module HTMLProofer
 
     def parts
       @parts ||= Addressable::URI.parse url
-    rescue URI::Error, Addressable::URI::InvalidURIError
+    rescue URI::Error, Addressable::URI::InvalidURIError => e
       @parts = nil
     end
 
@@ -76,9 +77,9 @@ module HTMLProofer
 
       # ignore user defined URLs
       return true if ignores_pattern_check(@check.options[:url_ignore])
+    end
 
-      # ignore user defined alts
-      return false unless 'ImageCheck' == @type
+    def ignore_alt?
       return true if ignores_pattern_check(@check.options[:alt_ignore])
     end
 
@@ -90,6 +91,10 @@ module HTMLProofer
       @check.options[:allow_hash_href]
     end
 
+    def check_img_http?
+      @check.options[:check_img_http]
+    end
+
     # path is external to the file
     def external?
       !internal?

data/lib/html-proofer/runner.rb

@@ -23,6 +23,15 @@ module HTMLProofer
         FileUtils.mkdir_p(STORAGE_DIR)
       end
 
+      # Add swap patterns for internal domains
+      unless @options[:internal_domains].empty?
+        @options[:internal_domains].each do |dom|
+          @options[:url_swap][Regexp.new("^http://#{dom}")] = ''
+          @options[:url_swap][Regexp.new("^https://#{dom}")] = ''
+          @options[:url_swap][Regexp.new("^//#{dom}")] = ''
+        end
+      end
+
       @failures = []
     end
 
@@ -96,7 +105,11 @@ module HTMLProofer
           @logger.log :debug, "Checking #{klass.to_s.downcase} on #{path} ..."
           check = Object.const_get(klass).new(src, path, html, @options)
           check.run
-          result[:external_urls].merge!(check.external_urls)
+          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
+          result[:external_urls].merge!(external_urls)
           result[:failures].concat(check.issues)
         end
       end

data/lib/html-proofer/url_validator.rb

@@ -150,7 +150,7 @@ module HTMLProofer
       elsif response.timed_out?
         handle_timeout(href, filenames, response_code)
       elsif response_code == 0
-        handle_failure(href, filenames, response_code)
+        handle_failure(href, filenames, response_code, response.return_message)
       elsif method == :head
         queue_request(:get, href, filenames)
       else
@@ -192,8 +192,11 @@ module HTMLProofer
       add_external_issue(filenames, msg, response_code)
     end
 
-    def handle_failure(href, filenames, response_code)
-      msg = "External link #{href} failed: response code #{response_code} means something's wrong"
+    def handle_failure(href, filenames, response_code, return_message)
+      msg = "External link #{href} 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}"
       @cache.add(href, filenames, 0, msg)
       return if @options[:only_4xx]
       add_external_issue(filenames, msg, response_code)

data/lib/html-proofer/version.rb

@@ -1,3 +1,3 @@
 module HTMLProofer
-  VERSION = '3.0.0'
+  VERSION = '3.1.0'.freeze
 end

data/lib/html-proofer.rb

@@ -1,10 +1,11 @@
 def require_all(path)
-  glob = File.join(File.dirname(__FILE__), path, '*.rb')
-  Dir[glob].each do |f|
+  dir = File.join(File.dirname(__FILE__), path)
+  Dir[File.join(dir, '*.rb')].each do |f|
     require f
   end
 end
 
+require_relative 'html-proofer/utils'
 require_all 'html-proofer'
 require_all 'html-proofer/check'
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 3.0.0
+  version: 3.1.0
 platform: ruby
 authors:
 - Garen Torikian
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-03-05 00:00:00.000000000 Z
+date: 2016-09-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mercenary
@@ -112,16 +112,22 @@ dependencies:
   name: activesupport
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '6.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
         version: '4.2'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '6.0'
 - !ruby/object:Gem::Dependency
   name: redcarpet
   requirement: !ruby/object:Gem::Requirement