percy-capybara 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cd953a74c101d2d27b26683822c2710457019e42
-  data.tar.gz: 286f6ddbfec8d9af9555400274044b81025851c4
+  metadata.gz: 1b9ab13cdb41b837b527594bbe81b6558b62fc5e
+  data.tar.gz: 8a1cb46009774c52c868d8b14ef404b4d3d913a9
 SHA512:
-  metadata.gz: 9fed3dbe1df1868b5227ebc453326f0488fd9d70d0b9bc96cdb236b23cc3f676d3d15f7c2fe4630210c5b632c681f1a5c3ba3a0f3dbe1dbf74b092f63a74ffa7
-  data.tar.gz: 5f160fc9dea15be3ceabf208876130324641c6285c9a3febcf8cf3f847f873598b8c0dbb3f4698185cebff3e5a9bb282821fb61a5904772b484cdca911342eb1
+  metadata.gz: 054078223dae7d409556cae8f308763e3552c5491e29e443a2411f928a23a5272e182e02c9c72b488eedf8f2b593b0830a2580ce7271ef15c4179a42a3f2a078
+  data.tar.gz: 8145c3640a24875a8c10907194a9839da7c3958f97700d6ab338d20aadb65c9e571a04905b583715da78555b072b0f07e7c39c6b73301c7273c28fc3359c49a9

data/lib/percy/capybara/client/snapshots.rb

@@ -7,6 +7,40 @@ module Percy
   module Capybara
     class Client
       module Snapshots
+        # Modified version of Diego Perini's URL regex. https://gist.github.com/dperini/729294
+        URL_REGEX = Regexp.new(
+          # protocol identifier
+          "(?:(?:https?:)?//)" +
+          "(?:" +
+            # IP address exclusion
+            # private & local networks
+            "(?!(?:10|127)(?:\\.\\d{1,3}){3})" +
+            "(?!(?:169\\.254|192\\.168)(?:\\.\\d{1,3}){2})" +
+            "(?!172\\.(?:1[6-9]|2\\d|3[0-1])(?:\\.\\d{1,3}){2})" +
+            # IP address dotted notation octets
+            # excludes loopback network 0.0.0.0
+            # excludes reserved space >= 224.0.0.0
+            # excludes network & broacast addresses
+            # (first & last IP address of each class)
+            "(?:[1-9]\\d?|1\\d\\d|2[01]\\d|22[0-3])" +
+            "(?:\\.(?:1?\\d{1,2}|2[0-4]\\d|25[0-5])){2}" +
+            "(?:\\.(?:[1-9]\\d?|1\\d\\d|2[0-4]\\d|25[0-4]))" +
+          "|" +
+            # host name
+            "(?:(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)" +
+            # domain name
+            "(?:\\.(?:[a-z\\u00a1-\\uffff0-9]-*)*[a-z\\u00a1-\\uffff0-9]+)*" +
+            # TLD identifier
+            "(?:\\.(?:[a-z\\u00a1-\\uffff]{2,}))" +
+          ")" +
+          # port number
+          "(?::\\d{2,5})?" +
+          # resource path
+          "(?:/[^\\s\"']*)?"
+        )
+        PATH_REGEX = /\/[^\\s\"']*/
+        DATA_URL_REGEX = /\Adata:/
+
         # Takes a snapshot of the given page HTML and its assets.
         #
         # @param [Capybara::Session] page The Capybara page to snapshot.
@@ -100,12 +134,13 @@ module Percy
           JS
           resource_urls = _evaluate_script(page, script)
 
-          resource_urls.each do |resource_url|
-            response = _fetch_resource_url(resource_url)
+          resource_urls.each do |url|
+            next if !_is_valid_url?(url)
+            response = _fetch_resource_url(url)
             next if !response
             sha = Digest::SHA256.hexdigest(response.body)
             resources << Percy::Client::Resource.new(
-              resource_url, mimetype: 'text/css', content: response.body)
+              url, mimetype: 'text/css', content: response.body)
           end
           resources
         end
@@ -127,10 +162,8 @@ module Percy
               srcs << temp_url.split(' ').first
             end
 
-            srcs.each do |src|
-              # Skip data URIs.
-              next if src.match(/\Adata:/)
-              image_urls << src
+            srcs.each do |url|
+              image_urls << url
             end
           end
 
@@ -162,13 +195,18 @@ module Percy
             temp_urls = raw_image_url.scan(/url\(["']?(.*?)["']?\)/)
             # background-image can accept multiple url()s, so temp_urls is an array of URLs.
             temp_urls.each do |temp_url|
-              # Skip data URIs.
-              next if temp_url[0].match(/\Adata:/)
-              image_urls << temp_url[0]
+              url = temp_url[0]
+              image_urls << url
             end
           end
 
           image_urls.each do |image_url|
+            next if !_is_valid_url?(image_url)
+
+            # If url references are blank, browsers will often fill them with the current page's
+            # URL, which makes no sense and will never be renderable. Strip these.
+            next if image_url == page.current_url
+
             # Make the resource URL absolute to the current page. If it is already absolute, this
             # will have no effect.
             resource_url = URI.join(page.current_url, image_url).to_s
@@ -189,6 +227,12 @@ module Percy
         end
         private :_get_image_resources
 
+        # @private
+        def _is_valid_url?(url)
+          # It is a URL or a path, but not a data URI.
+          (URL_REGEX.match(url) || PATH_REGEX.match(url)) && !DATA_URL_REGEX.match(url)
+        end
+
         # @private
         def _fetch_resource_url(url)
           response = Percy::Capybara::HttpFetcher.fetch(url)

data/lib/percy/capybara/version.rb

@@ -1,5 +1,5 @@
 module Percy
   module Capybara
-    VERSION = '0.2.4'
+    VERSION = '0.2.5'
   end
 end

data/percy-capybara.gemspec

@@ -18,7 +18,7 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
   spec.require_paths = ['lib']
 
-  spec.add_dependency 'percy-client', '>= 0.2.7'
+  spec.add_dependency 'percy-client', '>= 0.2.11'
 
   spec.add_development_dependency 'bundler', '~> 1.7'
   spec.add_development_dependency 'rake', '~> 10.0'

data/spec/lib/percy/capybara/client/testdata/test-images.html

@@ -36,6 +36,12 @@
   <h2>img srcset</h2>
   <img width="200" src="/images/srcset-base.png" srcset="/images/srcset-first.png 200w, /images/srcset-second.png 400w">
 
+  <h2>blank image src (not included)</h2>
+  <img src=""></div>
+
+  <h2>empty background-image url (uses current page url, should not be included)</h2>
+  <div style="background: url() 200px 200px no-repeat"></div>
+
   <h2>Duplicates of some of the above images, to verify they are not duplicated in resources:</h2>
   <img src="images/img-relative.png">
   <img src="/images/img-relative-to-root.png">

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: percy-capybara
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Perceptual Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-07-24 00:00:00.000000000 Z
+date: 2015-07-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: percy-client
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
+        version: 0.2.11
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.2.7
+        version: 0.2.11
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -204,7 +204,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Percy::Capybara