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
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 15

def self.call(schema_object)
  Set.new.tap do |categories|
    extract_field_categories!(categories, schema_object)
    extract_about_categories!(categories, schema_object)
  end.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



103
104
105
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 103

def self.extract_about_array(about)
  Set.new.tap { |categories| extract_about_array!(categories, about) }
end

.extract_about_array!(categories, about) ⇒ void

This method returns an undefined value.

Extracts categories from an about array.

Parameters:

  • categories (Set<String>) —

    Accumulator set

  • about (Array) —

    The about array



113
114
115
116
117
118
119
120
121
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 113

def self.extract_about_array!(categories, about)
  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

.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



48
49
50
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 48

def self.extract_about_categories(schema_object)
  Set.new.tap { |categories| extract_about_categories!(categories, schema_object) }
end

.extract_about_categories!(categories, schema_object) ⇒ void

This method returns an undefined value.

Extracts categories from the about field.

Parameters:

  • categories (Set<String>) —

    Accumulator set

  • schema_object (Hash) —

    The schema object



58
59
60
61
62
63
64
65
66
67
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 58

def self.extract_about_categories!(categories, schema_object)
  about = schema_object[:about]
  return unless about

  if about.is_a?(Array)
    extract_about_array!(categories, about)
  elsif about.is_a?(String)
    extract_string_categories!(categories, about)
  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



27
28
29
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 27

def self.extract_field_categories(schema_object)
  Set.new.tap { |categories| extract_field_categories!(categories, schema_object) }
end

.extract_field_categories!(categories, schema_object) ⇒ void

This method returns an undefined value.

Extracts categories from keywords, categories, and tags fields.

Parameters:

  • categories (Set<String>) —

    Accumulator set

  • schema_object (Hash) —

    The schema object



37
38
39
40
41
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 37

def self.extract_field_categories!(categories, schema_object)
  %i[keywords categories tags].each do |field|
    extract_field_value!(categories, schema_object[field])
  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



75
76
77
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 75

def self.extract_field_value(schema_object, field)
  Set.new.tap { |categories| extract_field_value!(categories, schema_object[field.to_sym]) }
end

.extract_field_value!(categories, value) ⇒ void

This method returns an undefined value.

Extracts categories from a single field value.

Parameters:

  • categories (Set<String>) —

    Accumulator set

  • value (Object) —

    The field value



85
86
87
88
89
90
91
92
93
94
95
96
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 85

def self.extract_field_value!(categories, value)
  return unless value

  if value.is_a?(Array)
    value.each do |item|
      s = item.to_s
      categories.add(s) unless s.empty?
    end
  elsif value.is_a?(String)
    extract_string_categories!(categories, value)
  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



128
129
130
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 128

def self.extract_string_categories(string)
  Set.new.tap { |categories| extract_string_categories!(categories, string) }
end

.extract_string_categories!(categories, string) ⇒ void

This method returns an undefined value.

Extracts categories from a string by splitting on separators.

Parameters:

  • categories (Set<String>) —

    Accumulator set

  • string (String) —

    source string that may contain category delimiters



138
139
140
141
142
143
 
# File 'lib/html2rss/auto_source/scraper/schema/category_extractor.rb', line 138

def self.extract_string_categories!(categories, string)
  string.split(/[,;|]/).each do |part|
    s = part.strip
    categories.add(s) unless s.empty?
  end
end