class AlgoliaHTMLExtractor

def extract
  heading_selector = 'h1,h2,h3,h4,h5,h6'
  # We select all nodes that match either the headings or the elements to
  # extract. This will allow us to loop over it in order it appears in the DOM
  all_selector = "#{heading_selector},#{@options[:css_selector]}"
  items = []
  current_hierarchy = {
    lvl0: nil,
    lvl1: nil,
    lvl2: nil,
    lvl3: nil,
    lvl4: nil,
    lvl5: nil
  }
  current_position = 0 # Position of the DOM node in the tree
  current_lvl = nil # Current closest hierarchy level
  current_anchor = nil # Current closest anchor
  @dom.css(all_selector).each do |node|
    # If it's a heading, we update our current hierarchy
    if node.matches?(heading_selector)
      # Which level heading is it?
      current_lvl = extract_tag_name(node).gsub(/^h/, '').to_i - 1
      # Update this level, and set all the following ones to nil
      current_hierarchy["lvl#{current_lvl}".to_sym] = extract_text(node)
      (current_lvl + 1..6).each do |lvl|
        current_hierarchy["lvl#{lvl}".to_sym] = nil
      end
      # Update the anchor, if the new heading has one
      new_anchor = extract_anchor(node)
      current_anchor = new_anchor if new_anchor
    end
    # Stop if node is not to be extracted
    next unless node.matches?(@options[:css_selector])
    # Stop if node is empty
    text = extract_text(node)
    next if text.empty?
    item = {
      html: extract_html(node),
      text: text,
      tag_name: extract_tag_name(node),
      hierarchy: current_hierarchy.clone,
      anchor: current_anchor,
      node: node,
      weight: {
        position: current_position,
        heading: heading_weight(current_lvl)
      }
    }
    item[:uuid] = uuid(item)
    items << item
    current_position += 1
  end
  items
end