Module: Html2rss::AutoSource::Scraper::Schema::CategoryExtractor

Defined in:
lib/html2rss/auto_source/scraper/schema/category_extractor.rb

Overview

Extracts categories from Schema.org structured data.

Class Method Summary collapse

Class Method Details

.call(schema_object) ⇒ Array<String>

Extracts categories from a schema object.

Parameters:

  • schema_object (Hash) —

    The schema object

Returns:

  • (Array<String>) —

    Array of category strings



15
16
17
18
19
20
21
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 15

def self.call(schema_object)
  # Build union of all category sources
  field_categories = extract_field_categories(schema_object)
  about_categories = extract_about_categories(schema_object)

  (field_categories | about_categories).to_a
end

.extract_about_array(about) ⇒ Set<String>

Extracts categories from an about array.

Parameters:

  • about (Array) —

    The about array

Returns:

  • (Set<String>) —

    Set of category strings



78
79
80
81
82
83
84
85
86
87
88
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 78

def self.extract_about_array(about)
  Set.new.tap do |categories|
    about.each do |item|
      if item.is_a?(Hash) && item[:name]
        categories.add(item[:name].to_s)
      elsif item.is_a?(String)
        categories.add(item)
      end
    end
  end
end

.extract_about_categories(schema_object) ⇒ Set<String>

Extracts categories from the about field.

Parameters:

  • schema_object (Hash) —

    The schema object

Returns:

  • (Set<String>) —

    Set of category strings



41
42
43
44
45
46
47
48
49
50
51
52
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 41

def self.extract_about_categories(schema_object)
  about = schema_object[:about]
  return Set.new unless about

  if about.is_a?(Array)
    extract_about_array(about)
  elsif about.is_a?(String)
    extract_string_categories(about)
  else
    Set.new
  end
end

.extract_field_categories(schema_object) ⇒ Set<String>

Extracts categories from keywords, categories, and tags fields.

Parameters:

  • schema_object (Hash) —

    The schema object

Returns:

  • (Set<String>) —

    Set of category strings



28
29
30
31
32
33
34
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 28

def self.extract_field_categories(schema_object)
  Set.new.tap do |categories|
    %w[keywords categories tags].each do |field|
      categories.merge(extract_field_value(schema_object, field))
    end
  end
end

.extract_field_value(schema_object, field) ⇒ Set<String>

Extracts categories from a single field value.

Parameters:

  • schema_object (Hash) —

    The schema object

  • field (String) —

    The field name

Returns:

  • (Set<String>) —

    Set of category strings



60
61
62
63
64
65
66
67
68
69
70
71
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 60

def self.extract_field_value(schema_object, field)
  value = schema_object[field.to_sym]
  return Set.new unless value

  if value.is_a?(Array)
    Set.new(value.map(&:to_s).reject(&:empty?))
  elsif value.is_a?(String)
    extract_string_categories(value)
  else
    Set.new
  end
end

.extract_string_categories(string) ⇒ Set<String>

Extracts categories from a string by splitting on separators.

Parameters:

  • string (String) —

    source string that may contain category delimiters

Returns:

  • (Set<String>) —

    Set of category strings



95
96
97
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 95

def self.extract_string_categories(string)
  Set.new(string.split(/[,;|]/).map(&:strip).reject(&:empty?))
end