html-proofer 1.0.0 → 1.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0e7b88c5fd839aa05b97b85399326a9db187a340
-  data.tar.gz: e0a0c34a2602aca002797185b7ee488b1a94314d
+  metadata.gz: e6fdca322142a45bad728b408d6e00e155fe01ce
+  data.tar.gz: 288123bd8384f03768178f352a90729e85101b89
 SHA512:
-  metadata.gz: 904bc7984ee9ddba79e06833a9e235e26c5d388c7581493f79f210053248d4d7916dfe849c8eac7e5fc75815f5be2dbf9d88b3f043eb1181e95f11241cae698b
-  data.tar.gz: 509fe2ee57606ea93e1c175bafc8bf8ff39891a93c0bfa8c7ea3242f731f184e4a884bb1deea9d2433074f3b816d25542873deed24e7df4a3f421e64d2f106ba
+  metadata.gz: 997be4ed93329ceb98a5fd2aa6caf7b1e664d78fc9c65057c4c76e766ada8851f4c4edb1756a80c5f54313f97048ce867bf5337d1266b62a3831d514ede33856
+  data.tar.gz: 88defb2fc1bda8ffa7a15f8fda61efcdb943074513eb73738613b556c84c75b33f4d35fa8debbd79d8fb0b33fbbe1c7a858dca396770cf4c97ef63b0655c0ee5

data/README.md

@@ -121,8 +121,9 @@ The `HTML::Proofer` constructor takes an optional hash of additional options:
 | Option | Description | Default |
 | :----- | :---------- | :------ |
 | `disable_external` | If `true`, does not run the external link checker, which can take a lot of time. | `false` |
-| `ext` | The extension of your HTML files including the dot. | `.html` |
+| `ext` | The extension of your HTML files including the dot. | `.html`
 | `favicon` | Enables the favicon checker. | `false` |
+| `as_link_array` | Assumes that you've passed in just an array of links to check. | `false` |
 | `href_ignore` | An array of Strings or RegExps containing `href`s that are safe to ignore. Certain URIs, like `mailto` and `tel`, are always ignored. | `[]` |
 | `alt_ignore` | An array of Strings or RegExps containing `img`s whose missing `alt` tags are safe to ignore. | `[]` |
 | `href_swap` | A hash containing key-value pairs of `RegExp => String`. It transforms links that match `RegExp` into `String` via `gsub`. | `{}` |
@@ -134,11 +135,11 @@ You can also pass in any of Typhoeus' options for the external link check. For e
 HTML::Proofer.new("out/", {:ext => ".htm", :verbose = > true, :ssl_verifyhost => 2 })
 ```
 
-This sets `HTML::Proofer`'s' extensions to use _.htm_, and gives Typhoeus a configurtion for it to be verbose, and use specific SSL settings. Check [the Typhoeus documentation](https://github.com/typhoeus/typhoeus#other-curl-options) for more information on what options it can receive.
+This sets `HTML::Proofer`'s extensions to use _.htm_, and gives Typhoeus a configuration for it to be verbose, and use specific SSL settings. Check [the Typhoeus documentation](https://github.com/typhoeus/typhoeus#other-curl-options) for more information on what options it can receive.
 
 ## Ignoring content
 
-Add the `data-proofer-ignore` attribute to any `<a>` or `<img>` tag to ignore it from the checks.
+Add the `data-proofer-ignore` attribute to any tag to ignore it from the checks.
 
 ## Custom tests
 

data/bin/htmlproof

@@ -16,6 +16,7 @@ Mercenary.program(:htmlproof) do |p|
 
   p.option 'ext', '--ext EXT', 'The extension of your HTML files (default: `.html`)'
   p.option 'favicon', '--favicon', 'Enables the favicon checker (default: `false`).'
+  p.option 'as-links', '--as-links', 'Assumes that `PATH` is an array of links to check.'
   p.option 'swap', '--swap regex:string,[regex:string,...]', Array, 'Array containing key-value pairs of `RegExp:String`. It transforms links that match `RegExp` into `String`'
   p.option 'href_ignore', '--href_ignore link1,[link2,...]', Array, 'Array of Strings containing `href`s that are safe to ignore. Certain URIs, like `mailto` and `tel`, are always ignored.'
   p.option 'alt_ignore', '--alt_ignore image1,[image2,...]', Array, 'Array of Strings containing `img`s whose missing `alt` tags are safe to ignore'
@@ -35,12 +36,15 @@ Mercenary.program(:htmlproof) do |p|
         options[:href_swap][%r{#{pair[0]}}] = pair[1]
       end
     end
-    options[:href_ignore] = opts["ignore"] unless opts["href_ignore"].nil?
-    options[:alt_ignore] = opts["ignore"] unless opts["alt_ignore"].nil?
+    options[:as_link_array] = opts["as-links"] unless opts["as-links"].nil?
+    options[:href_ignore] = opts["href_ignore"] unless opts["href_ignore"].nil?
+    options[:alt_ignore] = opts["alt_ignore"] unless opts["alt_ignore"].nil?
     options[:disable_external] = opts["disable_external"] unless opts["disable_external"].nil?
     options[:favicon] = opts["favicon"] unless opts["favicon"].nil?
     options[:verbose] = opts["verbose"] unless opts["verbose"].nil?
 
+    path = path.delete(' ').split(",") if options[:as_link_array]
+
     HTML::Proofer.new(path, options).run
   end
 end

data/html-proofer.gemspec

@@ -3,7 +3,7 @@ $:.push File.expand_path("../lib", __FILE__)
 
 Gem::Specification.new do |gem|
   gem.name          = "html-proofer"
-  gem.version       = "1.0.0"
+  gem.version       = "1.1.0"
   gem.authors       = ["Garen Torikian"]
   gem.email         = ["gjtorikian@gmail.com"]
   gem.description   = %q{Test your rendered HTML files to make sure they're accurate.}

data/lib/html/proofer.rb

@@ -11,7 +11,7 @@ module HTML
     attr_accessor :failed_tests
 
     def initialize(src, opts={})
-      @srcDir = src
+      @src = src
 
       @proofer_opts = {
         :ext => ".html",
@@ -20,7 +20,8 @@ module HTML
         :href_ignore => [],
         :alt_ignore => [],
         :disable_external => false,
-        :verbose => false
+        :verbose => false,
+        :as_link_array => false
       }
       @options = @proofer_opts.merge({:followlocation => true}).merge(opts)
 
@@ -33,52 +34,33 @@ module HTML
     end
 
     def run
-      total_files = 0
-      external_urls = {}
-
-      logger.info "Running #{get_checks} checks on #{@srcDir} on *#{@options[:ext]}... \n\n".white
-
-      files.each do |path|
-        total_files += 1
-        html = HTML::Proofer.create_nokogiri(path)
-
-        get_checks.each do |klass|
-          logger.debug "Checking #{klass.to_s.downcase} on #{path} ...".blue
-          check = klass.new(@srcDir, path, html, @options)
-          check.run
-          external_urls.merge!(check.external_urls)
-          @failed_tests.concat(check.issues) if check.issues.length > 0
+      unless @options[:as_link_array]
+        total_files = 0
+        external_urls = {}
+
+        logger.info "Running #{get_checks} checks on #{@src} on *#{@options[:ext]}... \n\n".white
+
+        files.each do |path|
+          total_files += 1
+          html = HTML::Proofer.create_nokogiri(path)
+
+          get_checks.each do |klass|
+            logger.debug "Checking #{klass.to_s.downcase} on #{path} ...".blue
+            check = klass.new(@src, path, html, @options)
+            check.run
+            external_urls.merge!(check.external_urls)
+            @failed_tests.concat(check.issues) if check.issues.length > 0
+          end
         end
-      end
-
-      # the hypothesis is that Proofer runs way faster if we pull out
-      # all the external URLs and run the checks at the end. Otherwise, we're halting
-      # the consuming process for every file. In addition, sorting the list lets
-      # libcurl keep connections to hosts alive. Finally, we'll make a HEAD request,
-      # rather than GETing all the contents
-      external_urls = Hash[external_urls.sort]
 
-      unless @options[:disable_external]
-        logger.info "Checking #{external_urls.length} external links...".yellow
+        external_link_checker(external_urls) unless @options[:disable_external]
 
-        # Typhoeus won't let you pass any non-Typhoeus option
-        @proofer_opts.each_key do |opt|
-          @options.delete opt
-        end
-
-        Ethon.logger = logger # log from Typhoeus/Ethon
-
-        external_urls.each_pair do |href, filenames|
-          request = Typhoeus::Request.new(href, @options.merge({:method => :head}))
-          request.on_complete { |response| response_handler(response, filenames) }
-          hydra.queue request
-        end
-        logger.debug "Running requests for all #{hydra.queued_requests.size} external URLs...".yellow
-        hydra.run
+        logger.info "Ran on #{total_files} files!\n\n".green
+      else
+        external_urls = Hash[*@src.map{ |s| [s, nil] }.flatten]
+        external_link_checker(external_urls) unless @options[:disable_external]
       end
 
-      logger.info "Ran on #{total_files} files!\n\n".green
-
       if @failed_tests.empty?
         logger.info "HTML-Proofer finished successfully.".green
       else
@@ -90,17 +72,47 @@ module HTML
       end
     end
 
+    # the hypothesis is that Proofer runs way faster if we pull out
+    # all the external URLs and run the checks at the end. Otherwise, we're halting
+    # the consuming process for every file. In addition, sorting the list lets
+    # libcurl keep connections to hosts alive. Finally, we'll make a HEAD request,
+    # rather than GETing all the contents
+    def external_link_checker(external_urls)
+      external_urls = Hash[external_urls.sort]
+
+      logger.info "Checking #{external_urls.length} external links...".yellow
+
+      # Typhoeus won't let you pass any non-Typhoeus option
+      @proofer_opts.each_key do |opt|
+        @options.delete opt
+      end
+
+      Ethon.logger = logger # log from Typhoeus/Ethon
+
+      external_urls.each_pair do |href, filenames|
+        request = Typhoeus::Request.new(href, @options.merge({:method => :head}))
+        request.on_complete { |response| response_handler(response, filenames) }
+        hydra.queue request
+      end
+      logger.debug "Running requests for all #{hydra.queued_requests.size} external URLs...".yellow
+      hydra.run
+    end
+
     def response_handler(response, filenames)
       href = response.options[:effective_url]
       method = response.request.options[:method]
       response_code = response.code
 
-      logger.debug "Received a #{response_code} for #{href} in #{filenames.join(' ')}"
+      debug_msg = "Received a #{response_code} for #{href}"
+      debug_msg << " in #{filenames.join(' ')}" unless filenames.nil?
+      logger.debug debug_msg
 
       if response_code.between?(200, 299)
         # continue with no op
       elsif response.timed_out?
-         @failed_tests << "#{filenames.join(' ').blue}: External link #{href} failed: got a time out"
+        failed_test_msg = "External link #{href} failed: got a time out"
+        failed_test_msg.insert(0, "#{filenames.join(' ').blue}: ") unless filenames.nil?
+        @failed_tests << failed_test_msg
       elsif (response_code == 405 || response_code == 420 || response_code == 503) && method == :head
         # 420s usually come from rate limiting; let's ignore the query and try just the path with a GET
         uri = URI(href)
@@ -113,7 +125,9 @@ module HTML
         response_handler(next_response, filenames)
       else
         # Received a non-successful http response.
-        @failed_tests << "#{filenames.join(' ').blue}: External link #{href} failed: #{response_code} #{response.return_message}"
+        failed_test_msg = "External link #{href} failed: #{response_code} #{response.return_message}"
+        failed_test_msg.insert(0, "#{filenames.join(' ').blue}: ") unless filenames.nil?
+        @failed_tests << failed_test_msg
       end
     end
 
@@ -122,10 +136,10 @@ module HTML
     end
 
     def files
-      if File.directory? @srcDir
-        Dir.glob("#{@srcDir}/**/*#{@options[:ext]}")
+      if File.directory? @src
+        Dir.glob("#{@src}/**/*#{@options[:ext]}")
       else
-        File.extname(@srcDir) == @options[:ext] ? [@srcDir] : []
+        File.extname(@src) == @options[:ext] ? [@src] : []
       end
     end
 

data/spec/html/proofer/links_spec.rb

@@ -165,4 +165,10 @@ describe "Links test" do
     output = capture_stderr { HTML::Proofer.new(internal, options).run }
     output.should match /without trailing slash/
   end
+
+  it "works for array of links" do
+    options = { :as_link_array => true}
+    output = capture_stderr { HTML::Proofer.new(["www.github.com", "foofoofoo.biz"], options).run }
+    output.should match /foofoo.biz\/? failed: 0 Couldn't resolve host name/
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html-proofer
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.1.0
 platform: ruby
 authors:
 - Garen Torikian
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-07-20 00:00:00.000000000 Z
+date: 2014-07-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mercenary