micromicro 0.1.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ae75d6afb6f7d98bc3a2fc12333ccbd31824e1cecd8336057e551fe6b392a643
-  data.tar.gz: 877da43669217907635d71015ec574ebc656e8755c8f6267229cebde36f281b0
+  metadata.gz: 6c5c3cb23e1c8338fef3d7cca36c47e4dcc834f3819525c01bd7ce6dab314971
+  data.tar.gz: 27794eaac80a6701c7910f4e31200a4bc999d0b8082b3ca1d2dd5a87a0bdaa82
 SHA512:
-  metadata.gz: a4b5a68c2d343fe0935d2103016aacf0b94d7a7c391d3ea360160a25fcb01bc16b7c70ae715e12b17142cedb928bea782b8057db5002df3e9ece2a99fdf1558c
-  data.tar.gz: 16a62f01b013d56547cebcac3001ecf59b77b3c14653f473a833d66589c6be31b5c53c2e6c547e0ce5c65f3dafb18feeb94be30ae0f57c65a96def024d6afccb
+  metadata.gz: d59f245021fb8bec36e1e319cffce3c3a6168ea763952efc8759bda7cb7a7bf13420632cdcfd2b988d72524a348f5a1238ff206cfd3aa75bfb5a57621f4f3b8c
+  data.tar.gz: 9355a25a3b65fe72828abf95d4dcec2829e46772904487b030a906cd95708f4bc946570f507bae326df2a3e8066e3de1c332799977cf8db749269e095bba413b

data/.simplecov

@@ -2,9 +2,11 @@ require 'simplecov-console'
 
 formatters = [SimpleCov::Formatter::HTMLFormatter]
 
+# rubocop:disable Style/IfUnlessModifier
 if RSpec.configuration.files_to_run.length > 1
   formatters << SimpleCov::Formatter::Console
 end
+# rubocop:enable Style/IfUnlessModifier
 
 SimpleCov.start do
   formatter SimpleCov::Formatter::MultiFormatter.new(formatters)

data/CHANGELOG.md

@@ -1,5 +1,15 @@
 # Changelog
 
+## 1.0.0 / 2020-11-08
+
+- Add `MicroMicro::Item#plain_text_properties` and `MicroMicro::Item#url_properties` methods (351e1f1)
+- Add `MicroMicro::Collections::RelationshipsCollection#rels` and `MicroMicro::Collections::RelationshipsCollection#urls` methods(c0e5665)
+- Add `MicroMicro::Collections::PropertiesCollection#names` and `MicroMicro::Collections::PropertiesCollection#values` methods (65486bc)
+- Add `MicroMicro::Collections::ItemsCollection#types` method (6b53a81)
+- Update absolutely dependency (4e67bb2)
+- Add `Collectible` concern and refactor using Composite design pattern (82503b8)
+- Update absolutely dependency (4578fb4)
+
 ## 0.1.0 / 2020-05-06
 
 - Initial release!

data/Gemfile

@@ -6,9 +6,9 @@ gemspec
 gem 'pry-byebug', '~> 3.9'
 gem 'rake', '~> 13.0'
 gem 'reek', '~> 6.0'
-gem 'rspec', '~> 3.9'
-gem 'rubocop', '~> 0.82.0'
-gem 'rubocop-performance', '~> 1.5'
-gem 'rubocop-rspec', '~> 1.38'
-gem 'simplecov', '~> 0.18.5'
+gem 'rspec', '~> 3.10'
+gem 'rubocop', '~> 1.2'
+gem 'rubocop-performance', '~> 1.8'
+gem 'rubocop-rspec', '~> 2.0'
+gem 'simplecov', '~> 0.19.1'
 gem 'simplecov-console', '~> 0.7.2'

data/README.md

@@ -53,7 +53,7 @@ An example using a simple `String` of HTML as input:
 require 'micromicro'
 
 doc = MicroMicro.parse('<div class="h-card">Jason Garber</div>', 'https://sixtwothree.org')
-#=> #<MicroMicro::Document items: #<MicroMicro::Collections::ItemsCollection count: 1, members: [#<MicroMicro::Item types: ["h-card"], properties: 1, children: 0>]>, relations: #<MicroMicro::Collections::RelationsCollection count: 0, members: []>>
+#=> #<MicroMicro::Document items: #<MicroMicro::Collections::ItemsCollection count: 1, members: [#<MicroMicro::Item types: ["h-card"], properties: 1, children: 0>]>, relationships: #<MicroMicro::Collections::RelationshipsCollection count: 0, members: []>>
 
 doc.to_h
 #=> { :items => [{ :type => ["h-card"], :properties => { :name => ["Jason Garber"] } }], :rels => {}, :"rel-urls" => {} }
@@ -71,7 +71,7 @@ url = "https://tantek.com"
 rsp = Net::HTTP.get(URI.parse(url))
 
 doc = MicroMicro.parse(rsp, url)
-#=> #<MicroMicro::Document items: #<MicroMicro::Collections::ItemsCollection count: 1, members: […]>, relations: #<MicroMicro::Collections::RelationsCollection count: 31, members: […]>>
+#=> #<MicroMicro::Document items: #<MicroMicro::Collections::ItemsCollection count: 1, members: […]>, relationships: #<MicroMicro::Collections::RelationshipsCollection count: 31, members: […]>>
 
 doc.to_h
 #=> { :items => [{ :type => ["h-card"], :properties => {…}, :children => […]}], :rels => {…}, :'rel-urls' => {…} }
@@ -81,30 +81,65 @@ doc.to_h
 
 Building on the example above, a MicroMicro-parsed document is navigable and manipulable using a familiar `Enumerable`-esque interface.
 
+#### Items
+
 ```ruby
 doc.items.first
 #=> #<MicroMicro::Item types: ["h-card"], properties: 42, children: 6>
 
+# 🆕 in v1.0.0
+doc.items.types
+#=> ["h-card"]
+
+doc.items.first.children
+#=> #<MicroMicro::Collections::ItemsCollection count: 6, members: […]>
+```
+
+#### Properties
+
+```ruby
 doc.items.first.properties
 #=> #<MicroMicro::Collections::PropertiesCollection count: 42, members: […]>
 
+# 🆕 in v1.0.0
+doc.items.first.plain_text_properties
+#=> #<MicroMicro::Collections::PropertiesCollection count: 34, members: […]>
+
+# 🆕 in v1.0.0
+doc.items.first.url_properties
+#=> #<MicroMicro::Collections::PropertiesCollection count: 11, members: […]>
+
+# 🆕 in v1.0.0
+doc.items.first.properties.names
+#=> ["category", "name", "note", "org", "photo", "pronoun", "pronouns", "role", "uid", "url"]
+
+# 🆕 in v1.0.0
+doc.items.first.properties.values
+#=> [{:value=>"https://tantek.com/photo.jpg", :alt=>""}, "https://tantek.com/", "Tantek Çelik", "Inventor, writer, teacher, runner, coder, more.", "Inventor", "writer", "teacher", "runner", "coder", …]
+
 doc.items.first.properties[7]
 #=> #<MicroMicro::Property name: "category", prefix: "p", value: "teacher">
 
 doc.items.first.properties.take(5).map { |property| [property.name, property.value] }
 #=> [["photo", { :value => "https://tantek.com/photo.jpg", :alt => "" }], ["url", "https://tantek.com/"], ["uid", "https://tantek.com/"], ["name", "Tantek Çelik"], ["role", "Inventor, writer, teacher, runner, coder, more."]]
+```
 
-doc.items.first.children
-#=> #<MicroMicro::Collections::ItemsCollection count: 6, members: […]>
+#### Relationships
 
-doc.relations.first
-#=> #<MicroMicro::Relation href: "https://tantek.com/", rels: ["canonical"]>
+```ruby
+doc.relationships.first
+#=> #<MicroMicro::Relationship href: "https://tantek.com/", rels: ["canonical"]>
 
-doc.relations.map(&:rels).flatten.uniq.sort
+# 🆕 in v1.0.0
+doc.relationships.rels
 #=> ["alternate", "apple-touch-icon-precomposed", "author", "authorization_endpoint", "bookmark", "canonical", "hub", "icon", "me", "microsub", …]
 
-doc.relations.find { |relation| relation.rels.include?('webmention') }
-# => #<MicroMicro::Relation href: "https://webmention.io/tantek.com/webmention", rels: ["webmention"]>
+# 🆕 in v1.0.0
+doc.relationships.urls
+#=> ["http://dribbble.com/tantek/", "http://last.fm/user/tantekc", "https://aperture.p3k.io/microsub/277", "https://en.wikipedia.org/wiki/User:Tantek", "https://github.com/tantek", "https://indieauth.com/auth", "https://indieauth.com/openid", "https://micro.blog/t", "https://pubsubhubbub.superfeedr.com/", "https://tantek.com/", …]
+
+doc.relationships.find { |relationship| relationship.rels.include?('webmention') }
+# => #<MicroMicro::Relationship href: "https://webmention.io/tantek.com/webmention", rels: ["webmention"]>
 ```
 
 ## Contributing

data/lib/micro_micro/collectible.rb

@@ -0,0 +1,13 @@
+module MicroMicro
+  module Collectible
+    attr_accessor :collection
+
+    def next_all
+      collection.split(self).last
+    end
+
+    def prev_all
+      collection.split(self).first
+    end
+  end
+end

data/lib/micro_micro/collections/base_collection.rb

@@ -1,15 +1,15 @@
 module MicroMicro
   module Collections
     class BaseCollection
+      extend Forwardable
+
       include Enumerable
 
-      delegate :[], :each, :last, :length, :split, to: :members
+      def_delegators :members, :[], :each, :last, :length, :split
 
-      # @param members [Array<MicroMicro::Item, MicroMicro::Property, MicroMicro::Relation>]
+      # @param members [Array<MicroMicro::Item, MicroMicro::Property, MicroMicro::Relationship>]
       def initialize(members = [])
-        @members = members
-
-        decorate_members if respond_to?(:decorate_members, true)
+        members.each { |member| push(member) }
       end
 
       # @return [String]
@@ -17,21 +17,20 @@ module MicroMicro
         format(%(#<#{self.class.name}:%#0x count: #{count}, members: #{members.inspect}>), object_id)
       end
 
-      # @param member [MicroMicro::Item, MicroMicro::Property, MicroMicro::Relation]
-      # @return [self]
+      # @param member [MicroMicro::Item, MicroMicro::Property, MicroMicro::Relationship]
       def push(member)
-        members.push(member)
+        members << member
 
-        decorate_members if respond_to?(:decorate_members, true)
-
-        self
+        member.collection = self
       end
 
       alias << push
 
       private
 
-      attr_reader :members
+      def members
+        @members ||= []
+      end
     end
   end
 end

data/lib/micro_micro/collections/items_collection.rb

@@ -5,6 +5,11 @@ module MicroMicro
       def to_a
         map(&:to_h)
       end
+
+      # @return [Array<String>]
+      def types
+        @types ||= map(&:types).flatten.uniq.sort
+      end
     end
   end
 end

data/lib/micro_micro/collections/properties_collection.rb

@@ -1,17 +1,19 @@
 module MicroMicro
   module Collections
     class PropertiesCollection < BaseCollection
+      # @return [Array<String>]
+      def names
+        @names ||= map(&:name).uniq.sort
+      end
+
       # @return [Hash{Symbol => Array<String, Hash>}]
       def to_h
-        group_by(&:name).symbolize_keys.deep_transform_values do |property|
-          property.item_node? ? property.value.to_h : property.value
-        end
+        group_by(&:name).symbolize_keys.deep_transform_values(&:value)
       end
 
-      private
-
-      def decorate_members
-        each { |member| member.collection = self }
+      # @return [Array<String, Hash>]
+      def values
+        @values ||= map(&:value).uniq
       end
     end
   end

data/lib/micro_micro/collections/{relations_collection.rb → relationships_collection.rb}

@@ -1,23 +1,32 @@
 module MicroMicro
   module Collections
-    class RelationsCollection < BaseCollection
-      # @see microformats2 Parsing Specification section 1.4
+    class RelationshipsCollection < BaseCollection
       # @see http://microformats.org/wiki/microformats2-parsing#parse_a_hyperlink_element_for_rel_microformats
       #
-      # @return [Hash{Symbole => Hash{Symbol => Array, String}}]
+      # @return [Hash{Symbol => Hash{Symbol => Array, String}}]
       def group_by_url
-        group_by(&:href).symbolize_keys.transform_values { |relations| relations.first.to_h.slice!(:href) }
+        group_by(&:href).symbolize_keys.transform_values { |relationships| relationships.first.to_h.slice!(:href) }
       end
 
-      # @see microformats2 Parsing Specification section 1.4
       # @see http://microformats.org/wiki/microformats2-parsing#parse_a_hyperlink_element_for_rel_microformats
       #
       # @return [Hash{Symbol => Array<String>}]
       def group_by_rel
+        # flat_map { |member| member.rels.map { |rel| [rel, member.href] } }.group_by(&:shift).symbolize_keys.transform_values(&:flatten).transform_values(&:uniq)
         each_with_object(Hash.new { |hash, key| hash[key] = [] }) do |member, hash|
           member.rels.each { |rel| hash[rel] << member.href }
         end.symbolize_keys.transform_values(&:uniq)
       end
+
+      # @return [Array<String>]
+      def rels
+        @rels ||= map(&:rels).flatten.uniq.sort
+      end
+
+      # @return [Array<String>]
+      def urls
+        @urls ||= map(&:href).uniq.sort
+      end
     end
   end
 end

data/lib/micro_micro/document.rb

@@ -1,57 +1,117 @@
 module MicroMicro
   class Document
-    # @param markup [String] the HTML to parse
-    # @param base_url [String] the URL associated with the provided markup
+    # A map of HTML `srcset` attributes and their associated element names
+    #
+    # @see https://html.spec.whatwg.org/#srcset-attributes
+    # @see https://html.spec.whatwg.org/#attributes-3
+    HTML_IMAGE_CANDIDATE_STRINGS_ATTRIBUTES_MAP = {
+      'imagesrcset' => %w[link],
+      'srcset'      => %w[img source]
+    }.freeze
+
+    # A map of HTML URL attributes and their associated element names
+    #
+    # @see https://html.spec.whatwg.org/#attributes-3
+    HTML_URL_ATTRIBUTES_MAP = {
+      'action'     => %w[form],
+      'cite'       => %w[blockquote del ins q],
+      'data'       => %w[object],
+      'formaction' => %w[button input],
+      'href'       => %w[a area base link],
+      'manifest'   => %w[html],
+      'ping'       => %w[a area],
+      'poster'     => %w[video],
+      'src'        => %w[audio embed iframe img input script source track video]
+    }.freeze
+
+    # Parse a string of HTML for microformats2-encoded data.
+    #
+    #   MicroMicro::Document.new('<a href="/" class="h-card" rel="me">Jason Garber</a>', 'https://sixtwothree.org')
+    #
+    # Or, pull the source HTML of a page on the Web:
+    #
+    #   url = 'https://tantek.com'
+    #   markup = Net::HTTP.get(URI.parse(url))
+    #
+    #   doc = MicroMicro::Document.new(markup, url)
+    #
+    # @param markup [String] The HTML to parse for microformats2-encoded data.
+    # @param base_url [String] The URL associated with markup. Used for relative URL resolution.
     def initialize(markup, base_url)
       @markup = markup
       @base_url = base_url
+
+      resolve_relative_urls
     end
 
     # @return [String]
     def inspect
-      format(%(#<#{self.class.name}:%#0x items: #{items.inspect}, relations: #{relations.inspect}>), object_id)
+      format(%(#<#{self.class.name}:%#0x items: #{items.inspect}, relationships: #{relationships.inspect}>), object_id)
     end
 
+    # A collection of items parsed from the provided markup.
+    #
     # @return [MicroMicro::Collections::ItemsCollection]
     def items
       @items ||= Collections::ItemsCollection.new(Item.items_from(document))
     end
 
-    # @return [MicroMicro::Collections::RelationsCollection]
-    def relations
-      @relations ||= Collections::RelationsCollection.new(Relation.relations_from(document))
+    # A collection of relationships parsed from the provided markup.
+    #
+    # @return [MicroMicro::Collections::RelationshipsCollection]
+    def relationships
+      @relationships ||= Collections::RelationshipsCollection.new(Relationship.relationships_from(document))
     end
 
-    # @see microformats2 Parsing Specification section 1.1
+    # Return the parsed document as a Hash.
+    #
     # @see http://microformats.org/wiki/microformats2-parsing#parse_a_document_for_microformats
     #
-    # @return [Hash]
+    # @return [Hash{Symbol => Array, Hash}]
     def to_h
       {
         items: items.to_a,
-        rels: relations.group_by_rel,
-        'rel-urls': relations.group_by_url
+        rels: relationships.group_by_rel,
+        'rel-urls': relationships.group_by_url
       }
     end
 
+    # Ignore this node?
+    #
     # @param node [Nokogiri::XML::Element]
     # @return [Boolean]
     def self.ignore_node?(node)
       ignored_node_names.include?(node.name)
     end
 
+    # A list of HTML element names the parser should ignore.
+    #
     # @return [Array<String>]
     def self.ignored_node_names
       %w[script style template]
     end
 
+    # @see http://microformats.org/wiki/microformats2-parsing#parse_an_element_for_properties
+    # @see http://microformats.org/wiki/microformats2-parsing#parsing_for_implied_properties
+    #
+    # @param context [Nokogiri::HTML::Document, Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
+    # @yield [context]
+    # @return [String]
+    def self.text_content_from(context)
+      context.css(*ignored_node_names).unlink
+
+      yield(context) if block_given?
+
+      context.text.strip
+    end
+
     private
 
     attr_reader :base_url, :markup
 
     # @return [Nokogiri::XML::Element, nil]
     def base_element
-      @base_element ||= Nokogiri::HTML(markup).at_css('base[href]')
+      @base_element ||= Nokogiri::HTML(markup).at('//base[@href]')
     end
 
     # @return [Nokogiri::HTML::Document]
@@ -59,12 +119,32 @@ module MicroMicro
       @document ||= Nokogiri::HTML(markup, resolved_base_url)
     end
 
+    def resolve_relative_urls
+      HTML_URL_ATTRIBUTES_MAP.each do |attribute, names|
+        document.xpath(*names.map { |name| "//#{name}[@#{attribute}]" }).each do |node|
+          node[attribute] = Absolutely.to_abs(base: resolved_base_url, relative: node[attribute].strip)
+        end
+      end
+
+      HTML_IMAGE_CANDIDATE_STRINGS_ATTRIBUTES_MAP.each do |attribute, names|
+        document.xpath(*names.map { |name| "//#{name}[@#{attribute}]" }).each do |node|
+          candidates = node[attribute].split(',').map(&:strip).map { |candidate| candidate.match(/^(?<url>.+?)(?<descriptor>\s+.+)?$/) }
+
+          node[attribute] = candidates.map { |candidate| "#{Absolutely.to_abs(base: resolved_base_url, relative: candidate[:url])}#{candidate[:descriptor]}" }.join(', ')
+        end
+      end
+
+      self
+    end
+
     # @return [String]
     def resolved_base_url
       @resolved_base_url ||= begin
-        return base_url unless base_element
-
-        Absolutely.to_abs(base: base_url, relative: base_element['href'])
+        if base_element
+          Absolutely.to_abs(base: base_url, relative: base_element['href'].strip)
+        else
+          base_url
+        end
       end
     end
   end