micromicro 1.1.0 → 2.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (30) hide show
  1. checksums.yaml +4 -4
  2. data/CHANGELOG.md +22 -1
  3. data/CONTRIBUTING.md +3 -3
  4. data/README.md +9 -9
  5. data/lib/micro_micro/collectible.rb +2 -0
  6. data/lib/micro_micro/collections/base_collection.rb +7 -1
  7. data/lib/micro_micro/collections/items_collection.rb +3 -1
  8. data/lib/micro_micro/collections/properties_collection.rb +12 -0
  9. data/lib/micro_micro/collections/relationships_collection.rb +10 -9
  10. data/lib/micro_micro/document.rb +10 -98
  11. data/lib/micro_micro/helpers.rb +82 -0
  12. data/lib/micro_micro/implied_property.rb +2 -0
  13. data/lib/micro_micro/item.rb +53 -60
  14. data/lib/micro_micro/parsers/base_implied_property_parser.rb +29 -0
  15. data/lib/micro_micro/parsers/base_property_parser.rb +4 -12
  16. data/lib/micro_micro/parsers/date_time_parser.rb +60 -25
  17. data/lib/micro_micro/parsers/date_time_property_parser.rb +7 -6
  18. data/lib/micro_micro/parsers/embedded_markup_property_parser.rb +3 -2
  19. data/lib/micro_micro/parsers/implied_name_property_parser.rb +14 -16
  20. data/lib/micro_micro/parsers/implied_photo_property_parser.rb +19 -43
  21. data/lib/micro_micro/parsers/implied_url_property_parser.rb +11 -30
  22. data/lib/micro_micro/parsers/plain_text_property_parser.rb +3 -1
  23. data/lib/micro_micro/parsers/url_property_parser.rb +20 -12
  24. data/lib/micro_micro/parsers/value_class_pattern_parser.rb +27 -42
  25. data/lib/micro_micro/property.rb +68 -56
  26. data/lib/micro_micro/relationship.rb +15 -13
  27. data/lib/micro_micro/version.rb +3 -1
  28. data/lib/micromicro.rb +31 -26
  29. data/micromicro.gemspec +11 -6
  30. metadata +22 -19
@@ -1,5 +1,9 @@
1
+ # frozen_string_literal: true
2
+
1
3
  module MicroMicro
2
4
  class Property
5
+ include Collectible
6
+
3
7
  PROPERTY_PARSERS_MAP = {
4
8
  'dt' => Parsers::DateTimePropertyParser,
5
9
  'e' => Parsers::EmbeddedMarkupPropertyParser,
@@ -7,17 +11,46 @@ module MicroMicro
7
11
  'u' => Parsers::UrlPropertyParser
8
12
  }.freeze
9
13
 
10
- include Collectible
11
-
12
14
  attr_reader :name, :node, :prefix
13
15
 
16
+ # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
17
+ # @return [Array<MicroMicro::Property>]
18
+ def self.from_context(context)
19
+ node_set_from(context).flat_map do |node|
20
+ Helpers.property_class_names_from(node).map { |token| new(node, token) }
21
+ end
22
+ end
23
+
24
+ # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
25
+ # @param node_set [Nokogiri::XML::NodeSet]
26
+ # @return [Nokogiri::XML::NodeSet]
27
+ def self.node_set_from(context, node_set = Nokogiri::XML::NodeSet.new(context.document, []))
28
+ context.each { |node| node_set_from(node, node_set) } if context.is_a?(Nokogiri::XML::NodeSet)
29
+
30
+ if context.is_a?(Nokogiri::XML::Element) && !Helpers.ignore_node?(context)
31
+ node_set << context if Helpers.property_node?(context)
32
+
33
+ node_set_from(context.element_children, node_set) unless Helpers.item_node?(context)
34
+ end
35
+
36
+ node_set
37
+ end
38
+
14
39
  # @param node [Nokogiri::XML::Element]
15
- # @param name [String]
16
- # @param prefix [String<dt, e, p, u>]
17
- def initialize(node, name:, prefix:)
40
+ # @param token [String]
41
+ def initialize(node, token)
18
42
  @node = node
19
- @name = name
20
- @prefix = prefix
43
+ @prefix, @name = token.split(/-/, 2)
44
+ end
45
+
46
+ # @return [Boolean]
47
+ def date_time_property?
48
+ prefix == 'dt'
49
+ end
50
+
51
+ # @return [Boolean]
52
+ def embedded_markup_property?
53
+ prefix == 'e'
21
54
  end
22
55
 
23
56
  # @return [Boolean]
@@ -25,10 +58,15 @@ module MicroMicro
25
58
  false
26
59
  end
27
60
 
61
+ # :nocov:
28
62
  # @return [String]
29
63
  def inspect
30
- format(%(#<#{self.class.name}:%#0x name: #{name.inspect}, prefix: #{prefix.inspect}, value: #{value.inspect}>), object_id)
64
+ "#<#{self.class}:#{format('%#0x', object_id)} " \
65
+ "name: #{name.inspect}, " \
66
+ "prefix: #{prefix.inspect}, " \
67
+ "value: #{value.inspect}>"
31
68
  end
69
+ # :nocov:
32
70
 
33
71
  # @return [MicroMicro::Item, nil]
34
72
  def item
@@ -37,67 +75,41 @@ module MicroMicro
37
75
 
38
76
  # @return [Boolean]
39
77
  def item_node?
40
- @item_node ||= Item.item_node?(node)
78
+ @item_node ||= Helpers.item_node?(node)
41
79
  end
42
80
 
43
- # @return [String, Hash]
44
- def value
45
- @value ||= begin
46
- return parser.value unless item_node?
47
-
48
- hash = item.to_h
49
-
50
- return hash.merge(parser.value) if prefix == 'e'
51
-
52
- p_property = item.properties.find { |property| property.name == 'name' } if prefix == 'p'
53
- u_property = item.properties.find { |property| property.name == 'url' } if prefix == 'u'
54
-
55
- hash.merge(value: (p_property || u_property || parser).value)
56
- end
81
+ # @return [Boolean]
82
+ def plain_text_property?
83
+ prefix == 'p'
57
84
  end
58
85
 
59
86
  # @return [Boolean]
60
- def value?
61
- value.present?
87
+ def url_property?
88
+ prefix == 'u'
62
89
  end
63
90
 
64
- # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
65
- # @param node_set [Nokogiri::XML::NodeSet]
66
- # @return [Nokogiri::XML::NodeSet]
67
- def self.nodes_from(context, node_set = Nokogiri::XML::NodeSet.new(context.document, []))
68
- context.each { |node| nodes_from(node, node_set) } if context.is_a?(Nokogiri::XML::NodeSet)
69
-
70
- if context.is_a?(Nokogiri::XML::Element) && !Document.ignore_node?(context)
71
- node_set << context if property_node?(context)
91
+ # @return [String, Hash]
92
+ # rubocop:disable Metrics
93
+ def value
94
+ @value ||=
95
+ if item_node?
96
+ hash = item.to_h
72
97
 
73
- nodes_from(context.element_children, node_set) unless Item.item_node?(context)
74
- end
98
+ return hash.merge(parser.value) if embedded_markup_property?
75
99
 
76
- node_set
77
- end
100
+ p_property = item.properties.find { |property| property.name == 'name' } if plain_text_property?
101
+ u_property = item.properties.find { |property| property.name == 'url' } if url_property?
78
102
 
79
- # @param context [Nokogiri::XML::NodeSet, Nokogiri::XML::Element]
80
- # @return [Array<MicroMicro::Property>]
81
- def self.properties_from(context)
82
- nodes_from(context).map do |node|
83
- types_from(node).map { |prefix, name| new(node, name: name, prefix: prefix) }
84
- end.flatten
103
+ hash.merge(value: (p_property || u_property || parser).value)
104
+ else
105
+ parser.value
106
+ end
85
107
  end
108
+ # rubocop:enable Metrics
86
109
 
87
- # @param node [Nokogiri::XML::Element]
88
110
  # @return [Boolean]
89
- def self.property_node?(node)
90
- types_from(node).any?
91
- end
92
-
93
- # @param node [Nokogiri::XML::Element]
94
- # @return [Array<Array(String, String)>]
95
- #
96
- # @example
97
- # node = Nokogiri::HTML('<a href="https://sixtwothree.org" class="p-name u-url">Jason Garber</a>').at_css('a')
98
- # MicroMicro::Property.types_from(node) #=> [['p', 'name'], ['u', 'url']]
99
- def self.types_from(node)
100
- node.classes.select { |token| token.match?(/^(?:dt|e|p|u)(?:-[0-9a-z]+)?(?:-[a-z]+)+$/) }.map { |token| token.split(/-/, 2) }.uniq
111
+ def value?
112
+ value.present?
101
113
  end
102
114
 
103
115
  private
@@ -1,7 +1,17 @@
1
+ # frozen_string_literal: true
2
+
1
3
  module MicroMicro
2
4
  class Relationship
3
5
  include Collectible
4
6
 
7
+ # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
8
+ # @return [Array<MicroMicro::Relationship>]
9
+ def self.relationships_from(context)
10
+ context.css('[href][rel]:not([rel=""])')
11
+ .reject { |node| Helpers.ignore_nodes?(node.ancestors) }
12
+ .map { |node| new(node) }
13
+ end
14
+
5
15
  # @param node [Nokogiri::XML::Element]
6
16
  def initialize(node)
7
17
  @node = node
@@ -17,10 +27,14 @@ module MicroMicro
17
27
  @hreflang ||= node['hreflang']&.strip
18
28
  end
19
29
 
30
+ # :nocov:
20
31
  # @return [String]
21
32
  def inspect
22
- format(%(#<#{self.class.name}:%#0x href: #{href.inspect}, rels: #{rels.inspect}>), object_id)
33
+ "#<#{self.class}:#{format('%#0x', object_id)} " \
34
+ "href: #{href.inspect}, " \
35
+ "rels: #{rels.inspect}>"
23
36
  end
37
+ # :nocov:
24
38
 
25
39
  # @return [String, nil]
26
40
  def media
@@ -60,18 +74,6 @@ module MicroMicro
60
74
  @type ||= node['type']&.strip
61
75
  end
62
76
 
63
- # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
64
- # @return [Nokogiri::XML::NodeSet]
65
- def self.nodes_from(context)
66
- context.css('[href][rel]:not([rel=""])').reject { |node| (node.ancestors.map(&:name) & Document.ignored_node_names).any? }
67
- end
68
-
69
- # @param context [Nokogiri::HTML::Document, Nokogiri::XML::Element]
70
- # @return [Array<MicroMicro::Relationship>]
71
- def self.relationships_from(context)
72
- nodes_from(context).map { |node| new(node) }
73
- end
74
-
75
77
  private
76
78
 
77
79
  attr_reader :node
@@ -1,3 +1,5 @@
1
+ # frozen_string_literal: true
2
+
1
3
  module MicroMicro
2
- VERSION = '1.1.0'.freeze
4
+ VERSION = '2.0.0'
3
5
  end
data/lib/micromicro.rb CHANGED
@@ -1,38 +1,43 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require 'forwardable'
2
4
 
3
- require 'addressable/uri'
4
5
  require 'active_support/core_ext/array/grouping'
5
6
  require 'active_support/core_ext/hash/deep_transform_values'
6
7
  require 'active_support/core_ext/hash/keys'
7
8
  require 'active_support/core_ext/hash/slice'
8
9
  require 'active_support/core_ext/object/blank'
9
10
  require 'nokogiri'
11
+ require 'nokogiri/html-ext'
12
+
13
+ require_relative 'micro_micro/version'
14
+ require_relative 'micro_micro/collectible'
15
+ require_relative 'micro_micro/helpers'
16
+
17
+ require_relative 'micro_micro/parsers/date_time_parser'
18
+ require_relative 'micro_micro/parsers/value_class_pattern_parser'
19
+
20
+ require_relative 'micro_micro/parsers/base_property_parser'
21
+ require_relative 'micro_micro/parsers/date_time_property_parser'
22
+ require_relative 'micro_micro/parsers/embedded_markup_property_parser'
23
+ require_relative 'micro_micro/parsers/plain_text_property_parser'
24
+ require_relative 'micro_micro/parsers/url_property_parser'
25
+
26
+ require_relative 'micro_micro/parsers/base_implied_property_parser'
27
+ require_relative 'micro_micro/parsers/implied_name_property_parser'
28
+ require_relative 'micro_micro/parsers/implied_photo_property_parser'
29
+ require_relative 'micro_micro/parsers/implied_url_property_parser'
30
+
31
+ require_relative 'micro_micro/document'
32
+ require_relative 'micro_micro/item'
33
+ require_relative 'micro_micro/property'
34
+ require_relative 'micro_micro/implied_property'
35
+ require_relative 'micro_micro/relationship'
10
36
 
11
- require 'micro_micro/version'
12
- require 'micro_micro/collectible'
13
-
14
- require 'micro_micro/parsers/date_time_parser'
15
- require 'micro_micro/parsers/value_class_pattern_parser'
16
-
17
- require 'micro_micro/parsers/base_property_parser'
18
- require 'micro_micro/parsers/date_time_property_parser'
19
- require 'micro_micro/parsers/embedded_markup_property_parser'
20
- require 'micro_micro/parsers/implied_name_property_parser'
21
- require 'micro_micro/parsers/implied_photo_property_parser'
22
- require 'micro_micro/parsers/implied_url_property_parser'
23
- require 'micro_micro/parsers/plain_text_property_parser'
24
- require 'micro_micro/parsers/url_property_parser'
25
-
26
- require 'micro_micro/document'
27
- require 'micro_micro/item'
28
- require 'micro_micro/property'
29
- require 'micro_micro/implied_property'
30
- require 'micro_micro/relationship'
31
-
32
- require 'micro_micro/collections/base_collection'
33
- require 'micro_micro/collections/items_collection'
34
- require 'micro_micro/collections/properties_collection'
35
- require 'micro_micro/collections/relationships_collection'
37
+ require_relative 'micro_micro/collections/base_collection'
38
+ require_relative 'micro_micro/collections/items_collection'
39
+ require_relative 'micro_micro/collections/properties_collection'
40
+ require_relative 'micro_micro/collections/relationships_collection'
36
41
 
37
42
  module MicroMicro
38
43
  # Parse a string of HTML for microformats2-encoded data.
data/micromicro.gemspec CHANGED
@@ -1,7 +1,9 @@
1
+ # frozen_string_literal: true
2
+
1
3
  require_relative 'lib/micro_micro/version'
2
4
 
3
5
  Gem::Specification.new do |spec|
4
- spec.required_ruby_version = Gem::Requirement.new('>= 2.5', '< 4')
6
+ spec.required_ruby_version = '>= 2.7', '< 4'
5
7
 
6
8
  spec.name = 'micromicro'
7
9
  spec.version = MicroMicro::VERSION
@@ -19,10 +21,13 @@ Gem::Specification.new do |spec|
19
21
 
20
22
  spec.require_paths = ['lib']
21
23
 
22
- spec.metadata['bug_tracker_uri'] = "#{spec.homepage}/issues"
23
- spec.metadata['changelog_uri'] = "#{spec.homepage}/blob/v#{spec.version}/CHANGELOG.md"
24
+ spec.metadata = {
25
+ 'bug_tracker_uri' => "#{spec.homepage}/issues",
26
+ 'changelog_uri' => "#{spec.homepage}/blob/v#{spec.version}/CHANGELOG.md",
27
+ 'rubygems_mfa_required' => 'true'
28
+ }
24
29
 
25
- spec.add_runtime_dependency 'addressable', '~> 2.7'
26
- spec.add_runtime_dependency 'activesupport', '~> 6.1'
27
- spec.add_runtime_dependency 'nokogiri', '~> 1.11'
30
+ spec.add_runtime_dependency 'activesupport', '~> 7.0'
31
+ spec.add_runtime_dependency 'nokogiri', '>= 1.13'
32
+ spec.add_runtime_dependency 'nokogiri-html-ext', '~> 0.2.0'
28
33
  end
metadata CHANGED
@@ -1,57 +1,57 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: micromicro
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.1.0
4
+ version: 2.0.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Jason Garber
8
- autorequire:
8
+ autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2021-06-11 00:00:00.000000000 Z
11
+ date: 2022-08-12 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
- name: addressable
14
+ name: activesupport
15
15
  requirement: !ruby/object:Gem::Requirement
16
16
  requirements:
17
17
  - - "~>"
18
18
  - !ruby/object:Gem::Version
19
- version: '2.7'
19
+ version: '7.0'
20
20
  type: :runtime
21
21
  prerelease: false
22
22
  version_requirements: !ruby/object:Gem::Requirement
23
23
  requirements:
24
24
  - - "~>"
25
25
  - !ruby/object:Gem::Version
26
- version: '2.7'
26
+ version: '7.0'
27
27
  - !ruby/object:Gem::Dependency
28
- name: activesupport
28
+ name: nokogiri
29
29
  requirement: !ruby/object:Gem::Requirement
30
30
  requirements:
31
- - - "~>"
31
+ - - ">="
32
32
  - !ruby/object:Gem::Version
33
- version: '6.1'
33
+ version: '1.13'
34
34
  type: :runtime
35
35
  prerelease: false
36
36
  version_requirements: !ruby/object:Gem::Requirement
37
37
  requirements:
38
- - - "~>"
38
+ - - ">="
39
39
  - !ruby/object:Gem::Version
40
- version: '6.1'
40
+ version: '1.13'
41
41
  - !ruby/object:Gem::Dependency
42
- name: nokogiri
42
+ name: nokogiri-html-ext
43
43
  requirement: !ruby/object:Gem::Requirement
44
44
  requirements:
45
45
  - - "~>"
46
46
  - !ruby/object:Gem::Version
47
- version: '1.11'
47
+ version: 0.2.0
48
48
  type: :runtime
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
52
  - - "~>"
53
53
  - !ruby/object:Gem::Version
54
- version: '1.11'
54
+ version: 0.2.0
55
55
  description: Extract microformats2-encoded data from HTML documents.
56
56
  email:
57
57
  - jason@sixtwothree.org
@@ -69,8 +69,10 @@ files:
69
69
  - lib/micro_micro/collections/properties_collection.rb
70
70
  - lib/micro_micro/collections/relationships_collection.rb
71
71
  - lib/micro_micro/document.rb
72
+ - lib/micro_micro/helpers.rb
72
73
  - lib/micro_micro/implied_property.rb
73
74
  - lib/micro_micro/item.rb
75
+ - lib/micro_micro/parsers/base_implied_property_parser.rb
74
76
  - lib/micro_micro/parsers/base_property_parser.rb
75
77
  - lib/micro_micro/parsers/date_time_parser.rb
76
78
  - lib/micro_micro/parsers/date_time_property_parser.rb
@@ -91,8 +93,9 @@ licenses:
91
93
  - MIT
92
94
  metadata:
93
95
  bug_tracker_uri: https://github.com/jgarber623/micromicro/issues
94
- changelog_uri: https://github.com/jgarber623/micromicro/blob/v1.1.0/CHANGELOG.md
95
- post_install_message:
96
+ changelog_uri: https://github.com/jgarber623/micromicro/blob/v2.0.0/CHANGELOG.md
97
+ rubygems_mfa_required: 'true'
98
+ post_install_message:
96
99
  rdoc_options: []
97
100
  require_paths:
98
101
  - lib
@@ -100,7 +103,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
100
103
  requirements:
101
104
  - - ">="
102
105
  - !ruby/object:Gem::Version
103
- version: '2.5'
106
+ version: '2.7'
104
107
  - - "<"
105
108
  - !ruby/object:Gem::Version
106
109
  version: '4'
@@ -110,8 +113,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
110
113
  - !ruby/object:Gem::Version
111
114
  version: '0'
112
115
  requirements: []
113
- rubygems_version: 3.2.16
114
- signing_key:
116
+ rubygems_version: 3.3.16
117
+ signing_key:
115
118
  specification_version: 4
116
119
  summary: Extract microformats2-encoded data from HTML documents.
117
120
  test_files: []