html-proofer 2.3.0 → 2.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5e5d2a78c7071f5534b4fb0d22c34337d9b92a6c
-  data.tar.gz: 4e89db1b52488116724d07608297d3abfb6581bb
+  metadata.gz: 199072065aae813f6812515b7738fe44e7061b5c
+  data.tar.gz: bdcb52a9e1ded0ceb863e19969fa1b27dfc583ab
 SHA512:
-  metadata.gz: 84e99216d622692010d127c80f4cf4a128b5391535169418a9715d99f1d0ccdfcbe3edf976ee769ce2d5021b1989c6e232d00de72ae8574f82eb29b925a0e269
-  data.tar.gz: 57e675836bb4a138dcfd84a0751772bbd99d05d3605dc8c1f922197683fe92a65563f0618393720a5ed3f44101025977f94f2dbf7cba96161def098148ad98ce
+  metadata.gz: 8f4e700f69c02bdca9bf0e351fcd768b59b6a27f972a0e8687db668c9e9de24babb4daf75129fd178116e58d2f0eb44c4b808ccc7c584ad4c7626c288eeabd1b
+  data.tar.gz: 980595b0f55a55aaeaf4d1a6338c1ddd968bc12ec54fb89fb00f95a34f8812e7d869c351852c5f06ffe52a2bb0df115c07bfb79a72d38d43b76d9d2feec91951

data/README.md

@@ -140,6 +140,8 @@ The `HTML::Proofer` constructor takes an optional hash of additional options:
 | `alt_ignore` | An array of Strings or RegExps containing `img`s whose missing `alt` tags are safe to ignore. | `[]` |
 | `empty_alt_ignore` | If `true`, ignores images with empty alt tags. | `false` |
 | `check_external_hash` | Checks whether external hashes exist (even if the website exists). This slows the checker down. | `false` |
+| `check_favicon` | Enables the favicon checker. | `false` |
+| `check_html` | Enables HTML validation errors from Nokogiri | `false` |
 |`checks_to_ignore`| An array of Strings indicating which checks you'd like to not perform. | `[]`
 | `directory_index_file` | Sets the file to look for when a link refers to a directory. | `index.html` |
 | `disable_external` | If `true`, does not run the external link checker, which can take a lot of time. | `false` |
@@ -148,10 +150,9 @@ The `HTML::Proofer` constructor takes an optional hash of additional options:
 | `file_ignore` | An array of Strings or RegExps containing file paths that are safe to ignore. | `[]` |
 | `href_ignore` | An array of Strings or RegExps containing `href`s that are safe to ignore. Note that non-HTTP(S) URIs are always ignored. | `[]` |
 | `href_swap` | A hash containing key-value pairs of `RegExp => String`. It transforms links that match `RegExp` into `String` via `gsub`. | `{}` |
+| `ignore_script_embeds` | When `check_html` is enabled, `script` tags containing markup [are reported as errors](http://git.io/vOovv). Enabling this option ignores those errors. | `false`
 | `only_4xx` | Only reports errors for links that fall within the 4xx status code range. | `false` |
 | `url_ignore` | An array 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. | `[]` |
-| `check_favicon` | Enables the favicon checker. | `false` |
-| `check_html` | Enables HTML validation errors from Nokogiri | `false` |
 | `verbose` | If `true`, outputs extra information as the checking happens. Useful for debugging. | `false` |
 
 ### Configuring Typhoeus and Hydra

data/bin/htmlproof

@@ -27,6 +27,8 @@ Mercenary.program(:htmlproof) do |p|
   p.option 'empty_alt_ignore', '--empty-alt-ignore', 'Ignores images with empty alt tags.'
   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_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 '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', 'Disables the external link checker (default: `false`)'
   p.option 'error_sort', '--error-sort SORT', 'Defines the sort order for error output. Can be `path`, `desc`, or `status` (default: `path`).'
@@ -34,9 +36,9 @@ Mercenary.program(:htmlproof) do |p|
   p.option 'file_ignore', '--file-ignore file1,[file2,...]', Array, 'Comma-separated list of Strings or RegExps containing file paths that are safe to ignore'
   p.option 'href_ignore', '--href-ignore link1,[link2,...]', Array, 'Comma-separated list of Strings or RegExps containing `href`s that are safe to ignore.'
   p.option 'href_swap', '--href-swap re:string,[re:string,...]', Array, 'Comma-separated list of key-value pairs of `RegExp:String`. Transforms links matching `RegExp` into `String`'
+  p.option 'ignore_script_errors', '--ignore-script-errors', 'Ignore `check_html` errors associated with `script`s (default: `false`)'
   p.option 'only_4xx', '--only-4xx', 'Only reports errors for links that fall within the 4x status code range.'
-  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 'url_ignore', '--url-ignore link1,[link2,...]', Array, 'Comma-separated list of Strings or RegExps containing URLs that are safe to ignore.'
   p.option 'verbose', '--verbose', 'Enables more verbose logging.'
 
   p.action do |args, opts|

data/html-proofer.gemspec

@@ -28,4 +28,5 @@ Gem::Specification.new do |gem|
   gem.add_development_dependency 'rspec', '~> 3.1'
   gem.add_development_dependency 'rake'
   gem.add_development_dependency 'awesome_print'
+  gem.add_development_dependency 'vcr', '~> 2.9'
 end

data/lib/html/proofer.rb

@@ -21,7 +21,7 @@ module HTML
   class Proofer
     include Utils
 
-    attr_reader :options, :typhoeus_opts, :hydra_opts, :parallel_opts
+    attr_reader :options, :typhoeus_opts, :hydra_opts, :parallel_opts, :validation_opts
 
     TYPHOEUS_DEFAULTS = {
       :followlocation => true,
@@ -62,6 +62,9 @@ module HTML
       @parallel_opts = opts[:parallel] || {}
       opts.delete(:parallel)
 
+      @validation_opts = opts[:validation] || {}
+      opts.delete(:validation)
+
       @options = @proofer_opts.merge(opts)
 
       @failed_tests = []
@@ -124,7 +127,7 @@ module HTML
 
         checks.each do |klass|
           logger.log :debug, :yellow, "Checking #{klass.to_s.downcase} on #{path} ..."
-          check = Object.const_get(klass).new(@src, path, html, @options, @typhoeus_opts, @hydra_opts, @parallel_opts)
+          check = Object.const_get(klass).new(@src, path, html, @options, @typhoeus_opts, @hydra_opts, @parallel_opts, @validation_opts)
           check.run
           result[:external_urls].merge!(check.external_urls)
           result[:failed_tests].concat(check.issues) if check.issues.length > 0

data/lib/html/proofer/check_runner.rb

@@ -6,9 +6,9 @@ module HTML
     class CheckRunner
 
       attr_reader :issues, :src, :path, :options, :typhoeus_opts, :hydra_opts, :parallel_opts, \
-                  :external_urls, :href_ignores, :url_ignores, :alt_ignores, :empty_alt_ignore
+                  :validation_opts, :external_urls, :href_ignores, :url_ignores, :alt_ignores, :empty_alt_ignore
 
-      def initialize(src, path, html, options, typhoeus_opts, hydra_opts, parallel_opts)
+      def initialize(src, path, html, options, typhoeus_opts, hydra_opts, parallel_opts, validation_opts)
         @src    = src
         @path   = path
         @html   = remove_ignored(html)
@@ -16,6 +16,7 @@ module HTML
         @typhoeus_opts = typhoeus_opts
         @hydra_opts = hydra_opts
         @parallel_opts = parallel_opts
+        @validation_opts = validation_opts
         @issues = []
         @href_ignores = @options[:href_ignore]
         @url_ignores = @options[:url_ignore]

data/lib/html/proofer/checks/html.rb

@@ -1,7 +1,6 @@
 # encoding: utf-8
 
 class HtmlCheck < ::HTML::Proofer::CheckRunner
-
   # new html5 tags (source: http://www.w3schools.com/html/html5_new_elements.asp)
   # and svg child tags (source: https://developer.mozilla.org/en-US/docs/Web/SVG/Element)
   HTML5_TAGS = %w(article aside bdi details dialog figcaption
@@ -30,11 +29,16 @@ class HtmlCheck < ::HTML::Proofer::CheckRunner
 
   def run
     @html.errors.each do |e|
+      message = e.message
+      line    = e.line
       # Nokogiri (or rather libxml2 underhood) only recognizes html4 tags,
       # so we need to skip errors caused by the new tags in html5
-      next if HTML5_TAGS.include? e.to_s[/Tag ([\w-]+) invalid/o, 1]
+      next if HTML5_TAGS.include? message[/Tag ([\w-]+) invalid/o, 1]
+
+      # tags embedded in scripts are used in templating languages: http://git.io/vOovv
+      next if @validation_opts[:ignore_script_embeds] && message =~ /Element script embeds close tag/
 
-      add_issue(e.to_s)
+      add_issue(message, line)
     end
   end
 end

data/lib/html/proofer/version.rb

@@ -1,6 +1,6 @@
 module HTML
   class Proofer
-    VERSION = '2.3.0'
+    VERSION = '2.4.0'
   end
 end
 

data/spec/html/proofer/fixtures/html/ignore_script_embeds.html

@@ -0,0 +1,3 @@
+<script type="text/html" id="navbar-logged-in">
+    <li><a href="https://www.github.com/features">Home</a></li>
+</script>

data/spec/html/proofer/fixtures/links/linkWithRedirect.html

@@ -7,6 +7,8 @@
 	<p>Blah blah blah. <a href="https://help.github.com/changing-author-info/">This is another redirect.</a>. </p>
 
   <p>Blah blah blah. <a href="http://timclem.wordpress.com/2012/03/01/mind-the-end-of-your-line/">This is a third redirect.</a>. </p>
+
+	<p> <a href="https://github.com/github/repository-sync">and a fourth!</a> </p>
 </body>
 
 </html>

data/spec/html/proofer/fixtures/vcr_cassettes/images/existingImageExternal_html.yml

@@ -0,0 +1,62 @@
+---
+http_interactions:
+- request:
+    method: head
+    uri: http://upload.wikimedia.org/wikipedia/en/thumb/2/22/Heckert_GNU_white.svg/256px-Heckert_GNU_white.svg.png
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Server:
+      - nginx/1.9.2
+      Date:
+      - Mon, 06 Jul 2015 05:07:46 GMT
+      Content-Type:
+      - image/png
+      Content-Length:
+      - '27063'
+      Connection:
+      - keep-alive
+      X-Object-Meta-Sha1base36:
+      - mm95ioarmv2n0yvfyg4czr9qxzhf44v
+      Last-Modified:
+      - Fri, 18 Oct 2013 02:15:06 GMT
+      Etag:
+      - b02df8baa52837645bd58a219be4d9dc
+      X-Timestamp:
+      - '1382062505.22715'
+      X-Trans-Id:
+      - txe81e86cdeba44675ac9e2-00559a0458
+      X-Varnish:
+      - 2210500677 2206883823, 3151289350 3151285732
+      Via:
+      - 1.1 varnish, 1.1 varnish
+      Accept-Ranges:
+      - bytes
+      Age:
+      - '2250'
+      X-Cache:
+      - cp1061 hit (7), cp1072 frontend hit (1)
+      Strict-Transport-Security:
+      - max-age=31536000
+      Access-Control-Allow-Origin:
+      - "*"
+      Access-Control-Expose-Headers:
+      - Age, Date, Content-Length, Content-Range, X-Content-Duration, X-Cache, X-Varnish
+      Timing-Allow-Origin:
+      - "*"
+    body:
+      encoding: UTF-8
+      string: ''
+    http_version: '1.1'
+    adapter_metadata:
+      effective_url: https://upload.wikimedia.org/wikipedia/en/thumb/2/22/Heckert_GNU_white.svg/256px-Heckert_GNU_white.svg.png
+  recorded_at: Mon, 06 Jul 2015 05:07:46 GMT
+recorded_with: VCR 2.9.3

data/spec/html/proofer/fixtures/vcr_cassettes/images/ignoreAltButNotLink_html_alt_ignore_/_/_.yml

@@ -0,0 +1,45 @@
+---
+http_interactions:
+- request:
+    method: head
+    uri: http://www.kakakakakaakkakakakakakakaakakak.biz.foo.net/
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 0
+      message: 
+    headers: {}
+    body:
+      encoding: UTF-8
+      string: ''
+    http_version: 
+    adapter_metadata:
+      effective_url: http://www.kakakakakaakkakakakakakakaakakak.biz.foo.net/
+  recorded_at: Mon, 06 Jul 2015 05:07:39 GMT
+- request:
+    method: get
+    uri: http://www.kakakakakaakkakakakakakakaakakak.biz.foo.net/
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 0
+      message: 
+    headers: {}
+    body:
+      encoding: UTF-8
+      string: ''
+    http_version: 
+    adapter_metadata:
+      effective_url: http://www.kakakakakaakkakakakakakakaakakak.biz.foo.net/
+  recorded_at: Mon, 06 Jul 2015 05:07:39 GMT
+recorded_with: VCR 2.9.3

data/spec/html/proofer/fixtures/vcr_cassettes/images/image_missing_protocol_invalid_html.yml

@@ -0,0 +1,117 @@
+---
+http_interactions:
+- request:
+    method: head
+    uri: http://upload.wikimedia.org/wikipedia/en/thumb/fooooof.png
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 404
+      message: Not Found
+    headers:
+      Server:
+      - nginx/1.9.2
+      Date:
+      - Mon, 06 Jul 2015 05:07:40 GMT
+      Content-Type:
+      - text/html; charset=UTF-8
+      Content-Length:
+      - '225'
+      Connection:
+      - keep-alive
+      X-Trans-Id:
+      - tx98122b2ce400416787ffa-00559a0d1c
+      X-Varnish:
+      - 1571621725, 2249256766
+      Via:
+      - 1.1 varnish, 1.1 varnish
+      Accept-Ranges:
+      - bytes
+      Age:
+      - '0'
+      X-Cache:
+      - cp1099 miss (0), cp1063 frontend miss (0)
+      Strict-Transport-Security:
+      - max-age=31536000
+      Access-Control-Allow-Origin:
+      - "*"
+      Access-Control-Expose-Headers:
+      - Age, Date, Content-Length, Content-Range, X-Content-Duration, X-Cache, X-Varnish
+      Timing-Allow-Origin:
+      - "*"
+    body:
+      encoding: UTF-8
+      string: ''
+    http_version: '1.1'
+    adapter_metadata:
+      effective_url: https://upload.wikimedia.org/wikipedia/en/thumb/fooooof.png
+  recorded_at: Mon, 06 Jul 2015 05:07:41 GMT
+- request:
+    method: get
+    uri: http://upload.wikimedia.org/wikipedia/en/thumb/fooooof.png
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 404
+      message: Not Found
+    headers:
+      Server:
+      - nginx/1.9.2
+      Date:
+      - Mon, 06 Jul 2015 05:07:41 GMT
+      Content-Type:
+      - text/html; charset=UTF-8
+      Content-Length:
+      - '225'
+      Connection:
+      - keep-alive
+      X-Trans-Id:
+      - tx98122b2ce400416787ffa-00559a0d1c
+      X-Varnish:
+      - 1571621725, 2249257000 2249256766
+      Via:
+      - 1.1 varnish, 1.1 varnish
+      Accept-Ranges:
+      - bytes
+      Age:
+      - '0'
+      X-Cache:
+      - cp1099 miss (0), cp1063 frontend hit (1)
+      Strict-Transport-Security:
+      - max-age=31536000
+      Access-Control-Allow-Origin:
+      - "*"
+      Access-Control-Expose-Headers:
+      - Age, Date, Content-Length, Content-Range, X-Content-Duration, X-Cache, X-Varnish
+      Timing-Allow-Origin:
+      - "*"
+    body:
+      encoding: UTF-8
+      string: |-
+        <html>
+         <head>
+          <title>404 Not Found</title>
+         </head>
+         <body>
+          <h1>404 Not Found</h1>
+          The resource could not be found.<br /><br />
+        Regexp failed to match URI: &quot;/wikipedia/en/thumb/fooooof.png&quot;
+
+
+         </body>
+        </html>
+    http_version: '1.1'
+    adapter_metadata:
+      effective_url: https://upload.wikimedia.org/wikipedia/en/thumb/fooooof.png
+  recorded_at: Mon, 06 Jul 2015 05:07:41 GMT
+recorded_with: VCR 2.9.3

data/spec/html/proofer/fixtures/vcr_cassettes/images/image_missing_protocol_valid_html.yml

@@ -0,0 +1,62 @@
+---
+http_interactions:
+- request:
+    method: head
+    uri: http://upload.wikimedia.org/wikipedia/en/thumb/2/22/Heckert_GNU_white.svg/256px-Heckert_GNU_white.svg.png
+    body:
+      encoding: US-ASCII
+      string: ''
+    headers:
+      User-Agent:
+      - Mozilla/5.0 (compatible; HTML Proofer/2.3.0; +https://github.com/gjtorikian/html-proofer)
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Server:
+      - nginx/1.9.2
+      Date:
+      - Mon, 06 Jul 2015 05:07:45 GMT
+      Content-Type:
+      - image/png
+      Content-Length:
+      - '27063'
+      Connection:
+      - keep-alive
+      X-Object-Meta-Sha1base36:
+      - mm95ioarmv2n0yvfyg4czr9qxzhf44v
+      Last-Modified:
+      - Fri, 18 Oct 2013 02:15:06 GMT
+      Etag:
+      - b02df8baa52837645bd58a219be4d9dc
+      X-Timestamp:
+      - '1382062505.22715'
+      X-Trans-Id:
+      - txe81e86cdeba44675ac9e2-00559a0458
+      X-Varnish:
+      - 2210500677 2206883823, 3151285732
+      Via:
+      - 1.1 varnish, 1.1 varnish
+      Accept-Ranges:
+      - bytes
+      Age:
+      - '2249'
+      X-Cache:
+      - cp1061 hit (7), cp1072 frontend miss (0)
+      Strict-Transport-Security:
+      - max-age=31536000
+      Access-Control-Allow-Origin:
+      - "*"
+      Access-Control-Expose-Headers:
+      - Age, Date, Content-Length, Content-Range, X-Content-Duration, X-Cache, X-Varnish
+      Timing-Allow-Origin:
+      - "*"
+    body:
+      encoding: UTF-8
+      string: ''
+    http_version: '1.1'
+    adapter_metadata:
+      effective_url: https://upload.wikimedia.org/wikipedia/en/thumb/2/22/Heckert_GNU_white.svg/256px-Heckert_GNU_white.svg.png
+  recorded_at: Mon, 06 Jul 2015 05:07:45 GMT
+recorded_with: VCR 2.9.3