micromicro 1.1.0 → 3.0.0

data/lib/micro_micro/property.rb

@@ -1,5 +1,9 @@
+# frozen_string_literal: true
+
 module MicroMicro
   class Property
+    include Collectible
+
     PROPERTY_PARSERS_MAP = {
       'dt' => Parsers::DateTimePropertyParser,
       'e'  => Parsers::EmbeddedMarkupPropertyParser,
@@ -7,97 +11,163 @@ module MicroMicro
       'u'  => Parsers::UrlPropertyParser
     }.freeze
 
-    include Collectible
+    private_constant :PROPERTY_PARSERS_MAP
+
+    class PropertyNodeSearch
+      attr_reader :node_set
+
+      def initialize(document)
+        @node_set = Nokogiri::XML::NodeSet.new(document, [])
+      end
+
+      def search(context)
+        context.each { |node| search(node) } if context.is_a?(Nokogiri::XML::NodeSet)
+
+        if context.is_a?(Nokogiri::XML::Element) && !Helpers.ignore_node?(context)
+          node_set << context if Helpers.property_node?(context)
 
-    attr_reader :name, :node, :prefix
+          search(context.element_children) unless Helpers.item_node?(context)
+        end
+
+        node_set
+      end
+    end
+
+    private_constant :PropertyNodeSearch
+
+    # This {MicroMicro::Property}'s +name+ value.
+    #
+    # @return [String]
+    attr_reader :name
+
+    # This {MicroMicro::Property}'s node.
+    #
+    # @return [Nokogiri::XML::Element]
+    attr_reader :node
 
+    # This {MicroMicro::Property}'s +prefix+ value.
+    #
+    # @return [String] One of +dt+, +e+, +p+, or +u+.
+    attr_reader :prefix
+
+    # Extract {MicroMicro::Property}s from a context.
+    #
+    # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
+    # @return [Array<MicroMicro::Property>]
+    def self.from_context(context)
+      PropertyNodeSearch
+        .new(context.document)
+        .search(context)
+        .flat_map do |node|
+          Helpers.property_class_names_from(node).map { |token| new(node, token) }
+        end
+    end
+
+    # Parse a node for property data.
+    #
     # @param node [Nokogiri::XML::Element]
-    # @param name [String]
-    # @param prefix [String<dt, e, p, u>]
-    def initialize(node, name:, prefix:)
+    # @param token [String] A hyphen-separated token representing a microformats2
+    #   property value (e.g. +p-name+, +u-url+).
+    def initialize(node, token)
       @node = node
-      @name = name
-      @prefix = prefix
+      @prefix, @name = token.split(/-/, 2)
     end
 
+    # Is this {MicroMicro::Property} a datetime property?
+    #
+    # @return [Boolean]
+    def date_time_property?
+      prefix == 'dt'
+    end
+
+    # Is this {MicroMicro::Property} an embedded markup property?
+    #
+    # @return [Boolean]
+    def embedded_markup_property?
+      prefix == 'e'
+    end
+
+    # Always return +false+ when asked if this {MicroMicro::Property} is an
+    # implied property.
+    #
+    # @see MicroMicro::ImpliedProperty#implied?
+    #
     # @return [Boolean]
     def implied?
       false
     end
 
     # @return [String]
+    #
+    # :nocov:
     def inspect
-      format(%(#<#{self.class.name}:%#0x name: #{name.inspect}, prefix: #{prefix.inspect}, value: #{value.inspect}>), object_id)
+      "#<#{self.class}:#{format('%#0x', object_id)} " \
+        "name: #{name.inspect}, " \
+        "prefix: #{prefix.inspect}, " \
+        "value: #{value.inspect}>"
     end
+    # :nocov:
 
+    # Parse this {MicroMicro::Property}'s node as a {MicroMicro::Item}, if
+    # applicable.
+    #
     # @return [MicroMicro::Item, nil]
     def item
       @item ||= Item.new(node) if item_node?
     end
 
+    # Should this {MicroMicro::Property}'s node be parsed as a
+    # {MicroMicro::Item}?
+    #
+    # @see MicroMicro::Helpers.item_node?
+    #
     # @return [Boolean]
     def item_node?
-      @item_node ||= Item.item_node?(node)
+      @item_node ||= Helpers.item_node?(node)
     end
 
-    # @return [String, Hash]
-    def value
-      @value ||= begin
-        return parser.value unless item_node?
-
-        hash = item.to_h
-
-        return hash.merge(parser.value) if prefix == 'e'
-
-        p_property = item.properties.find { |property| property.name == 'name' } if prefix == 'p'
-        u_property = item.properties.find { |property| property.name == 'url' } if prefix == 'u'
-
-        hash.merge(value: (p_property || u_property || parser).value)
-      end
+    # Is this {MicroMicro::Property} a plain text property?
+    #
+    # @return [Boolean]
+    def plain_text_property?
+      prefix == 'p'
     end
 
+    # Is this {MicroMicro::Property} a url property?
+    #
     # @return [Boolean]
-    def value?
-      value.present?
+    def url_property?
+      prefix == 'u'
     end
 
-    # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
-    # @param node_set [Nokogiri::XML::NodeSet]
-    # @return [Nokogiri::XML::NodeSet]
-    def self.nodes_from(context, node_set = Nokogiri::XML::NodeSet.new(context.document, []))
-      context.each { |node| nodes_from(node, node_set) } if context.is_a?(Nokogiri::XML::NodeSet)
+    # Return this {MicroMicro::Property}'s parsed value.
+    #
+    # @return [String, Hash]
+    #
+    # rubocop:disable Metrics
+    def value
+      @value ||=
+        if item_node?
+          hash = item.to_h
 
-      if context.is_a?(Nokogiri::XML::Element) && !Document.ignore_node?(context)
-        node_set << context if property_node?(context)
+          return hash.merge(parser.value) if embedded_markup_property?
 
-        nodes_from(context.element_children, node_set) unless Item.item_node?(context)
-      end
+          p_property = item.properties.find { |property| property.name == 'name' } if plain_text_property?
+          u_property = item.properties.find { |property| property.name == 'url' } if url_property?
 
-      node_set
-    end
-
-    # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
-    # @return [Array<MicroMicro::Property>]
-    def self.properties_from(context)
-      nodes_from(context).map do |node|
-        types_from(node).map { |prefix, name| new(node, name: name, prefix: prefix) }
-      end.flatten
+          hash.merge(value: (p_property || u_property || parser).value)
+        else
+          parser.value
+        end
     end
+    # rubocop:enable Metrics
 
-    # @param node [Nokogiri::XML::Element]
-    # @return [Boolean]
-    def self.property_node?(node)
-      types_from(node).any?
-    end
-
-    # @param node [Nokogiri::XML::Element]
-    # @return [Array<Array(String, String)>]
+    # Returns +true+ if this {MicroMicro::Property}'s +value+ is anything other
+    # than blank or +nil+.
     #
-    # @example
-    #   node = Nokogiri::HTML('<a href="https://sixtwothree.org" class="p-name u-url">Jason Garber</a>').at_css('a')
-    #   MicroMicro::Property.types_from(node) #=> [['p', 'name'], ['u', 'url']]
-    def self.types_from(node)
-      node.classes.select { |token| token.match?(/^(?:dt|e|p|u)(?:-[0-9a-z]+)?(?:-[a-z]+)+$/) }.map { |token| token.split(/-/, 2) }.uniq
+    # @return [Boolean]
+    def value?
+      value.present?
     end
 
     private

data/lib/micro_micro/relationship.rb

@@ -1,32 +1,60 @@
+# frozen_string_literal: true
+
 module MicroMicro
   class Relationship
     include Collectible
 
+    # Extract {MicroMicro::Relationship}s from a context.
+    #
+    # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
+    # @return [Array<MicroMicro::Relationship>]
+    def self.from_context(context)
+      context.css('[href][rel]:not([rel=""])')
+             .reject { |node| Helpers.ignore_nodes?(node.ancestors) }
+             .map { |node| new(node) }
+    end
+
+    # Parse a node for relationship data.
+    #
     # @param node [Nokogiri::XML::Element]
+    # @return [MicroMicro::Relationship]
     def initialize(node)
       @node = node
     end
 
+    # The value of the node's +href+ attribute.
+    #
     # @return [String]
     def href
       @href ||= node['href']
     end
 
+    # The value of the node's +hreflang+ attribute, if present.
+    #
     # @return [String, nil]
     def hreflang
       @hreflang ||= node['hreflang']&.strip
     end
 
     # @return [String]
+    #
+    # :nocov:
     def inspect
-      format(%(#<#{self.class.name}:%#0x href: #{href.inspect}, rels: #{rels.inspect}>), object_id)
+      "#<#{self.class}:#{format('%#0x', object_id)} " \
+        "href: #{href.inspect}, " \
+        "rels: #{rels.inspect}>"
     end
+    # :nocov:
 
+    # The value of the node's +media+ attribute, if present.
+    #
     # @return [String, nil]
     def media
       @media ||= node['media']&.strip
     end
 
+    # Return the parsed {MicroMicro::Relationship} as a Hash.
+    #
     # @return [Hash{Symbol => String}]
     def to_h
       {
@@ -40,40 +68,37 @@ module MicroMicro
       }.select { |_, value| value.present? }
     end
 
+    # An Array of unique values from node's +rel+ attribute.
+    #
     # @return [Array<String>]
     def rels
       @rels ||= node['rel'].split.uniq.sort
     end
 
+    # The node's text content.
+    #
     # @return [String]
     def text
       @text ||= node.text
     end
 
+    # The value of the node's +title+ attribute, if present.
+    #
     # @return [String, nil]
     def title
       @title ||= node['title']&.strip
     end
 
+    # The value of the node's +type+ attribute, if present.
+    #
     # @return [String, nil]
     def type
       @type ||= node['type']&.strip
     end
 
-    # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
-    # @return [Nokogiri::XML::NodeSet]
-    def self.nodes_from(context)
-      context.css('[href][rel]:not([rel=""])').reject { |node| (node.ancestors.map(&:name) & Document.ignored_node_names).any? }
-    end
-
-    # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
-    # @return [Array<MicroMicro::Relationship>]
-    def self.relationships_from(context)
-      nodes_from(context).map { |node| new(node) }
-    end
-
     private
 
+    # @return [Nokogiri::XML::Element]
     attr_reader :node
   end
 end

data/lib/micro_micro/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module MicroMicro
-  VERSION = '1.1.0'.freeze
+  VERSION = '3.0.0'
 end

data/lib/micromicro.rb

@@ -1,48 +1,54 @@
+# frozen_string_literal: true
+
 require 'forwardable'
 
-require 'addressable/uri'
 require 'active_support/core_ext/array/grouping'
 require 'active_support/core_ext/hash/deep_transform_values'
 require 'active_support/core_ext/hash/keys'
 require 'active_support/core_ext/hash/slice'
 require 'active_support/core_ext/object/blank'
 require 'nokogiri'
+require 'nokogiri/html-ext'
+
+require_relative 'micro_micro/version'
+require_relative 'micro_micro/collectible'
+require_relative 'micro_micro/helpers'
 
-require 'micro_micro/version'
-require 'micro_micro/collectible'
+require_relative 'micro_micro/parsers/date_time_parser'
+require_relative 'micro_micro/parsers/value_class_pattern_parser'
 
-require 'micro_micro/parsers/date_time_parser'
-require 'micro_micro/parsers/value_class_pattern_parser'
+require_relative 'micro_micro/parsers/base_property_parser'
+require_relative 'micro_micro/parsers/date_time_property_parser'
+require_relative 'micro_micro/parsers/embedded_markup_property_parser'
+require_relative 'micro_micro/parsers/plain_text_property_parser'
+require_relative 'micro_micro/parsers/url_property_parser'
 
-require 'micro_micro/parsers/base_property_parser'
-require 'micro_micro/parsers/date_time_property_parser'
-require 'micro_micro/parsers/embedded_markup_property_parser'
-require 'micro_micro/parsers/implied_name_property_parser'
-require 'micro_micro/parsers/implied_photo_property_parser'
-require 'micro_micro/parsers/implied_url_property_parser'
-require 'micro_micro/parsers/plain_text_property_parser'
-require 'micro_micro/parsers/url_property_parser'
+require_relative 'micro_micro/parsers/base_implied_property_parser'
+require_relative 'micro_micro/parsers/implied_name_property_parser'
+require_relative 'micro_micro/parsers/implied_photo_property_parser'
+require_relative 'micro_micro/parsers/implied_url_property_parser'
 
-require 'micro_micro/document'
-require 'micro_micro/item'
-require 'micro_micro/property'
-require 'micro_micro/implied_property'
-require 'micro_micro/relationship'
+require_relative 'micro_micro/document'
+require_relative 'micro_micro/item'
+require_relative 'micro_micro/property'
+require_relative 'micro_micro/implied_property'
+require_relative 'micro_micro/relationship'
 
-require 'micro_micro/collections/base_collection'
-require 'micro_micro/collections/items_collection'
-require 'micro_micro/collections/properties_collection'
-require 'micro_micro/collections/relationships_collection'
+require_relative 'micro_micro/collections/base_collection'
+require_relative 'micro_micro/collections/items_collection'
+require_relative 'micro_micro/collections/properties_collection'
+require_relative 'micro_micro/collections/relationships_collection'
 
 module MicroMicro
   # Parse a string of HTML for microformats2-encoded data.
-  # Convenience method for MicroMicro::Document.new.
   #
+  # Convenience method for {MicroMicro::Document#initialize}.
+  #
+  # @example
   #   MicroMicro.parse('<a href="/" class="h-card" rel="me">Jason Garber</a>', 'https://sixtwothree.org')
   #
-  # @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.
-  # @return [MicroMicro::Document]
+  # @param (see MicroMicro::Document#initialize)
+  # @return (see MicroMicro::Document#initialize)
   def self.parse(markup, base_url)
     Document.new(markup, base_url)
   end

data/micromicro.gemspec

@@ -1,7 +1,9 @@
+# frozen_string_literal: true
+
 require_relative 'lib/micro_micro/version'
 
 Gem::Specification.new do |spec|
-  spec.required_ruby_version = Gem::Requirement.new('>= 2.5', '< 4')
+  spec.required_ruby_version = '>= 2.7', '< 4'
 
   spec.name          = 'micromicro'
   spec.version       = MicroMicro::VERSION
@@ -19,10 +21,13 @@ Gem::Specification.new do |spec|
 
   spec.require_paths = ['lib']
 
-  spec.metadata['bug_tracker_uri'] = "#{spec.homepage}/issues"
-  spec.metadata['changelog_uri']   = "#{spec.homepage}/blob/v#{spec.version}/CHANGELOG.md"
+  spec.metadata = {
+    'bug_tracker_uri'       => "#{spec.homepage}/issues",
+    'changelog_uri'         => "#{spec.homepage}/blob/v#{spec.version}/CHANGELOG.md",
+    'rubygems_mfa_required' => 'true'
+  }
 
-  spec.add_runtime_dependency 'addressable', '~> 2.7'
-  spec.add_runtime_dependency 'activesupport', '~> 6.1'
-  spec.add_runtime_dependency 'nokogiri', '~> 1.11'
+  spec.add_runtime_dependency 'activesupport', '~> 7.0'
+  spec.add_runtime_dependency 'nokogiri', '>= 1.13'
+  spec.add_runtime_dependency 'nokogiri-html-ext', '~> 0.2.2'
 end

metadata

@@ -1,57 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: micromicro
 version: !ruby/object:Gem::Version
-  version: 1.1.0
+  version: 3.0.0
 platform: ruby
 authors:
 - Jason Garber
-autorequire:
+autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-06-11 00:00:00.000000000 Z
+date: 2022-08-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: addressable
+  name: activesupport
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '7.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.7'
+        version: '7.0'
 - !ruby/object:Gem::Dependency
-  name: activesupport
+  name: nokogiri
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '6.1'
+        version: '1.13'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '6.1'
+        version: '1.13'
 - !ruby/object:Gem::Dependency
-  name: nokogiri
+  name: nokogiri-html-ext
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: 0.2.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.11'
+        version: 0.2.2
 description: Extract microformats2-encoded data from HTML documents.
 email:
 - jason@sixtwothree.org
@@ -69,8 +69,10 @@ files:
 - lib/micro_micro/collections/properties_collection.rb
 - lib/micro_micro/collections/relationships_collection.rb
 - lib/micro_micro/document.rb
+- lib/micro_micro/helpers.rb
 - lib/micro_micro/implied_property.rb
 - lib/micro_micro/item.rb
+- lib/micro_micro/parsers/base_implied_property_parser.rb
 - lib/micro_micro/parsers/base_property_parser.rb
 - lib/micro_micro/parsers/date_time_parser.rb
 - lib/micro_micro/parsers/date_time_property_parser.rb
@@ -91,8 +93,9 @@ licenses:
 - MIT
 metadata:
   bug_tracker_uri: https://github.com/jgarber623/micromicro/issues
-  changelog_uri: https://github.com/jgarber623/micromicro/blob/v1.1.0/CHANGELOG.md
-post_install_message:
+  changelog_uri: https://github.com/jgarber623/micromicro/blob/v3.0.0/CHANGELOG.md
+  rubygems_mfa_required: 'true'
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -100,7 +103,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.5'
+      version: '2.7'
   - - "<"
     - !ruby/object:Gem::Version
       version: '4'
@@ -110,8 +113,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.16
-signing_key:
+rubygems_version: 3.3.16
+signing_key: 
 specification_version: 4
 summary: Extract microformats2-encoded data from HTML documents.
 test_files: []