html-proofer 3.18.6 → 3.19.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e2d6deb85601ff3f5e5df02999f1b55f29231e5658f1d4fa9986c002b3cc0263
-  data.tar.gz: e20a007144a866b41b97eb36a964ca1372d693ade77acc69a9c9e706b353c8ef
+  metadata.gz: d06dbda8bf9baad3be96b5565fcb86de0892d4241c6b7ede08c3c2d7203f6752
+  data.tar.gz: da895d696b7b9d1f3ca9c2e504e0c375ce9942f53dd5c2174f80570d32e3ad5b
 SHA512:
-  metadata.gz: c51154450eb20c04c0b7038effb12ab8d258457ea5560421b5a2a0739342504afebb8fd092fe4378838a076636ff2665eb691f513b8b34b49af2e89ffba988c2
-  data.tar.gz: fcb7bf492588fabc991caf1f779fca14a7b553d3ce00dbf55ba24aebf3c39f7613af6a408d94c3a3faaeb21dceb8265ece91ca9bf4320aee7d4f3dca133ba4de
+  metadata.gz: 693f677cb91b9b0e79135ef27ed2771d34d7e5fee5bd368b20b5791a4e25a468ba769d299c2cd1417eccd989d9ac1290cfaf9dfd90b9534fa0af0440382e4e0f
+  data.tar.gz: c6c33f309e3f8b00dc1721653f2e2099c647c9bd8d3b4ecaab4ec7b97161925911d1e6e3c8cabb30b9b9eb2274fed7238ed338da7d85d25b7c6981d537f6435d

data/bin/htmlproofer

@@ -48,6 +48,7 @@ Mercenary.program(:htmlproofer) do |p|
   p.option 'storage_dir', '--storage-dir PATH', String, 'Directory where to store the cache log (default: "tmp/.htmlproofer")'
   p.option 'timeframe', '--timeframe <time>', String, 'A string representing the caching timeframe.'
   p.option 'typhoeus_config', '--typhoeus-config CONFIG', String, 'JSON-formatted string of Typhoeus config. Will override the html-proofer defaults.'
+  p.option 'hydra_config', '--hydra-config CONFIG', String, 'JSON-formatted string of Hydra 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-dir PATH', String, 'The absolute path to the directory serving your html-files.'
@@ -87,7 +88,8 @@ Mercenary.program(:htmlproofer) do |p|
     options[:validation][:report_eof_tags] = opts['report_eof_tags'] unless opts['report_eof_tags'].nil?
     options[:validation][:report_mismatched_tags] = opts['report_mismatched_tags'] unless opts['report_mismatched_tags'].nil?
 
-    options[:typhoeus] = HTMLProofer::Configuration.parse_json_option('typhoeus_config', opts['typhoeus_config']) unless opts['typhoeus_config'].nil?
+    options[:typhoeus] = HTMLProofer::Configuration.parse_json_option('typhoeus_config', opts['typhoeus_config'], symbolize_names: false) unless opts['typhoeus_config'].nil?
+    options[:hydra] = HTMLProofer::Configuration.parse_json_option('hydra_config', opts['hydra_config']) unless opts['hydra_config'].nil?
 
     unless opts['timeframe'].nil?
       options[:cache] ||= {}

data/lib/html-proofer/cache.rb

@@ -3,6 +3,7 @@
 require_relative 'utils'
 require 'date'
 require 'json'
+require 'uri'
 
 module HTMLProofer
   class Cache
@@ -11,6 +12,8 @@ module HTMLProofer
     DEFAULT_STORAGE_DIR = File.join('tmp', '.htmlproofer')
     DEFAULT_CACHE_FILE_NAME = 'cache.log'
 
+    URI_REGEXP = URI::DEFAULT_PARSER.make_regexp
+
     attr_reader :exists, :cache_log, :storage_dir, :cache_file
 
     def initialize(logger, options)
@@ -30,6 +33,8 @@ module HTMLProofer
     end
 
     def within_timeframe?(time)
+      return false if time.nil?
+
       (@parsed_timeframe..@cache_time).cover?(Time.parse(time))
     end
 
@@ -71,10 +76,14 @@ module HTMLProofer
       @cache_log[clean_url(url)] = data
     end
 
-    def detect_url_changes(found)
-      existing_urls = @cache_log.keys.map { |url| clean_url(url) }
+    def detect_url_changes(found, type)
       found_urls = found.keys.map { |url| clean_url(url) }
 
+      # if there were no urls, bail
+      return {} if found_urls.empty?
+
+      existing_urls = @cache_log.keys.map { |url| clean_url(url) }
+
       # prepare to add new URLs detected
       additions = found.reject do |url, _|
         url = clean_url(url)
@@ -91,19 +100,20 @@ module HTMLProofer
       @logger.log :info, "Adding #{new_link_text} to the cache..."
 
       # remove from cache URLs that no longer exist
-      del = 0
+      deletions = 0
       @cache_log.delete_if do |url, _|
         url = clean_url(url)
+
         if found_urls.include?(url)
           false
-        else
+        elsif url_matches_type?(url, type)
           @logger.log :debug, "Removing #{url} from cache check"
-          del += 1
+          deletions += 1
           true
         end
       end
 
-      del_link_text = pluralize(del, 'link', 'links')
+      del_link_text = pluralize(deletions, 'link', 'links')
       @logger.log :info, "Removing #{del_link_text} from the cache..."
 
       additions
@@ -113,21 +123,22 @@ module HTMLProofer
     # caches need access to this file. Write a proper versioned
     # schema in the future
     def write
-      file = {}
-      file = JSON.parse(File.read(cache_file)) if File.exist?(cache_file)
-      File.write(cache_file, file.merge(@cache_log).to_json)
+      File.write(cache_file, @cache_log.to_json)
     end
 
     def load?
       @load.nil?
     end
 
-    def retrieve_urls(urls)
-      urls_to_check = detect_url_changes(urls)
+    def retrieve_urls(urls, type)
+      urls_to_check = detect_url_changes(urls, type)
+
       @cache_log.each_pair do |url, cache|
         next if within_timeframe?(cache['time']) && cache['message'].empty? # these were successes to skip
 
-        urls_to_check[url] = cache['filenames'] # recheck expired links
+        if url_matches_type?(url, type)
+          urls_to_check[url] = cache['filenames'] # recheck expired links
+        end
       end
       urls_to_check
     end
@@ -154,9 +165,9 @@ module HTMLProofer
 
       @cache_file = File.join(storage_dir, cache_file_name)
 
-      return unless File.exist?(cache_file)
+      return unless File.exist?(@cache_file)
 
-      contents = File.read(cache_file)
+      contents = File.read(@cache_file)
       @cache_log = contents.empty? ? {} : JSON.parse(contents)
     end
 
@@ -174,5 +185,10 @@ module HTMLProofer
         @cache_datetime - Rational(measurement / 24.0)
       end.to_time
     end
+
+    def url_matches_type?(url, type)
+      return true if type == :internal && url !~ URI_REGEXP
+      return true if type == :external && url =~ URI_REGEXP
+    end
   end
 end

data/lib/html-proofer/configuration.rb

@@ -67,7 +67,7 @@ module HTMLProofer
       end
     end
 
-    def self.parse_json_option(option_name, config)
+    def self.parse_json_option(option_name, config, symbolize_names: true)
       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?
 
@@ -78,7 +78,7 @@ module HTMLProofer
       return {} if config.strip.empty?
 
       begin
-        JSON.parse(config)
+        JSON.parse(config, { symbolize_names: symbolize_names })
       rescue StandardError
         raise ArgumentError, "Option '#{option_name} did not contain valid JSON."
       end

data/lib/html-proofer/runner.rb

@@ -125,7 +125,7 @@ module HTMLProofer
           end
 
           external_urls = check.external_urls
-          external_urls = check.external_urls.map { |url, file| [swap(url, @options[:url_swap]), file] }.to_h if @options[:url_swap]
+          external_urls = check.external_urls.transform_keys { |url| swap(url, @options[:url_swap]) } if @options[:url_swap]
           result[:external_urls].merge!(external_urls)
           result[:failures].concat(check.issues)
         end
@@ -238,7 +238,7 @@ module HTMLProofer
     end
 
     def load_internal_cache
-      urls_to_check = @cache.retrieve_urls(@internal_urls)
+      urls_to_check = @cache.retrieve_urls(@internal_urls, :internal)
       cache_text = pluralize(urls_to_check.count, 'internal link', 'internal links')
       @logger.log :info, "Found #{cache_text} in the cache..."
 

data/lib/html-proofer/url_validator.rb

@@ -26,7 +26,7 @@ module HTMLProofer
       @external_urls = remove_query_values
 
       if @cache.use_cache?
-        urls_to_check = @cache.retrieve_urls(@external_urls)
+        urls_to_check = @cache.retrieve_urls(@external_urls, :external)
         external_link_checker(urls_to_check)
         @cache.write
       else

data/lib/html-proofer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module HTMLProofer
-  VERSION = '3.18.6'
+  VERSION = '3.19.2'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 3.18.6
+  version: 3.19.2
 platform: ruby
 authors:
 - Garen Torikian
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2021-02-21 00:00:00.000000000 Z
+date: 2021-06-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -287,7 +287,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.4.10
+      version: 2.6.0
   - - "<"
     - !ruby/object:Gem::Version
       version: '4.0'