govspeak 5.3.0 → 5.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 117026a2b98a5909e89263c2d9f05091b492e8b2
-  data.tar.gz: b6f5a662a795899e4beb399d87ade54181f40e81
+  metadata.gz: 40e1c3a28d1f53eab54a104139116e0405c4450a
+  data.tar.gz: 89520dfd370e31fd803fa8d127fb546ab35521e3
 SHA512:
-  metadata.gz: da21f89b2844d3174d1820ecd0aa991ea6a2aac40a58a5967549cdc128f71a46bfd3776e7667f7a28f0add49173c0c2ad0f50f8c7dfb4a9292f87ea2b7698c20
-  data.tar.gz: ae41a3cdb7664e6694f23c96d9f67f24304b813371eea173523627dd695f7e44ce78b00602791c0b8baf106b9e999336da6efe39c23a7334fc5875ed25a112f4
+  metadata.gz: 0afe56bcf4cd1160adb293500706b3ee3d2198b53792d18b7e8ad263ba7b81c3a770bfd63bd25e41b7ea9063d9243e31679e2fafa0b70e9a06e74f46eeb740f9
+  data.tar.gz: ff7509b60e910c01f83a8fbb7a0326b008898903186167609221c9f38fa805624f214139cea19afd2feb8181043aaf11faf455db51f5ca975078d7946c8b4bea

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 5.4.0
+* Add an optional `website_root` argument to `Govspeak::Document#extracted_links` in order to get all links as fully qualified URLs [#122](https://github.com/alphagov/govspeak/pull/122)
+
 ## 5.3.0
 * Add a link extraction class for finding links in documents [#120](https://github.com/alphagov/govspeak/pull/120)
 

data/lib/govspeak.rb

@@ -95,8 +95,8 @@ module Govspeak
       Govspeak::StructuredHeaderExtractor.new(self).call
     end
 
-    def extracted_links
-      Govspeak::LinkExtractor.new(self).call
+    def extracted_links(website_root: nil)
+      Govspeak::LinkExtractor.new(self, website_root: website_root).call
     end
 
     def preprocess(source)

data/lib/govspeak/link_extractor.rb

@@ -1,7 +1,8 @@
 module Govspeak
   class LinkExtractor
-    def initialize(document)
+    def initialize(document, website_root: nil)
       @document = document
+      @website_root = website_root
     end
 
     def call
@@ -10,8 +11,16 @@ module Govspeak
 
   private
 
+    attr_reader :document, :website_root
+
     def extract_links
-      document_anchors.map { |link| link['href'] }
+      document_anchors.map do |link|
+        if website_root && link['href'].start_with?('/')
+          "#{website_root}#{link['href']}"
+        else
+          link['href']
+        end
+      end
     end
 
     def document_anchors
@@ -22,7 +31,7 @@ module Govspeak
       doc = Nokogiri::HTML::Document.new
       doc.encoding = "UTF-8"
 
-      doc.fragment(@document.to_html)
+      doc.fragment(document.to_html)
     end
   end
 end

data/lib/govspeak/version.rb

@@ -1,3 +1,3 @@
 module Govspeak
-  VERSION = "5.3.0".freeze
+  VERSION = "5.4.0".freeze
 end

data/test/govspeak_link_extractor_test.rb

@@ -12,6 +12,8 @@ class GovspeakLinkExtractorTest < Minitest::Test
 [not_a_link](#somepage)
 
 [mailto:](mailto:someone@www.example.com)
+
+[absolute_path](/cais-trwydded-yrru-dros-dro)
     }
   end
 
@@ -24,7 +26,7 @@ class GovspeakLinkExtractorTest < Minitest::Test
   end
 
   test "Links are extracted from the body" do
-    expected_links = ["http://www.example.com", "http://www.gov.com"]
+    expected_links = %w{http://www.example.com http://www.gov.com /cais-trwydded-yrru-dros-dro}
     assert_equal expected_links, links
   end
 
@@ -39,4 +41,9 @@ class GovspeakLinkExtractorTest < Minitest::Test
   test "Links are not extracted if they begin with mailto:" do
     refute_includes ["mailto:someone@www.example.com"], links
   end
+
+  test "Absolute links are transformed to a url when website_root passed in" do
+    urls = doc.extracted_links(website_root: "http://www.example.com")
+    assert urls.include?("http://www.example.com/cais-trwydded-yrru-dros-dro")
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: govspeak
 version: !ruby/object:Gem::Version
-  version: 5.3.0
+  version: 5.4.0
 platform: ruby
 authors:
 - GOV.UK Dev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-01-04 00:00:00.000000000 Z
+date: 2018-01-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: kramdown
@@ -320,19 +320,19 @@ signing_key:
 specification_version: 4
 summary: Markup language for single domain
 test_files:
-- test/govspeak_attachments_test.rb
-- test/govspeak_attachments_inline_test.rb
-- test/govspeak_link_test.rb
 - test/govspeak_link_extractor_test.rb
+- test/govspeak_structured_headers_test.rb
+- test/govspeak_button_test.rb
+- test/with_deep_merge_test.rb
+- test/blockquote_extra_quote_remover_test.rb
+- test/govspeak_test_helper.rb
+- test/govspeak_link_test.rb
 - test/govspeak_contacts_test.rb
 - test/test_helper.rb
+- test/html_validator_test.rb
+- test/html_sanitizer_test.rb
+- test/govspeak_attachments_inline_test.rb
 - test/govspeak_test.rb
+- test/govspeak_attachments_test.rb
 - test/govspeak_attachments_image_test.rb
-- test/with_deep_merge_test.rb
-- test/html_validator_test.rb
-- test/govspeak_structured_headers_test.rb
-- test/blockquote_extra_quote_remover_test.rb
 - test/presenters/h_card_presenter_test.rb
-- test/govspeak_button_test.rb
-- test/govspeak_test_helper.rb
-- test/html_sanitizer_test.rb