bidirectional_links_generator.rb

# frozen_string_literal: true
class BidirectionalLinksGenerator < Jekyll::Generator
  def generate(site)
    graph_nodes = []
    graph_edges = []

    all_notes = site.collections['notes'].docs
    all_pages = site.collections['pages'].docs

    all_docs = all_notes + all_pages

    link_extension = !!site.config["use_html_extension"] ? '.html' : ''

    all_docs.each do |current_note|

      # Convert all Wiki/Roam-style double-bracket link syntax to plain HTML
      # anchor tag elements (<a>) with "internal-link" CSS class
      all_docs.each do |note_potentially_linked_to|
        title_from_filename = File.basename(
          note_potentially_linked_to.basename,
          File.extname(note_potentially_linked_to.basename)
        ).gsub('_', ' ').capitalize

        external_href = note_potentially_linked_to.data["source"]

        new_href = external_href ||= "#{note_potentially_linked_to.url}#{link_extension}"
        anchor_tag = "<a class='internal-link' href='#{new_href}'>\\1</a>"

        # Replace double-bracketed links with label using note title
        # [[A note about cats|this is a link to the note about cats]]
        current_note.content = current_note.content.gsub(
          /\[\[#{title_from_filename}\|(.+?)(?=\])\]\](?!.*?[\r\n]+[`{3,}|~{3,}])/i,
          anchor_tag
        )

        # Replace double-bracketed links with label using note filename
        # [[cats|this is a link to the note about cats]]
        current_note.content = current_note.content.gsub(
          /\[\[#{note_potentially_linked_to.data['title']}\|(.+?)(?=\])\]\](?!.*?[\r\n]+[`{3,}|~{3,}])/i,
          anchor_tag
        )

        # Replace double-bracketed links using note title
        # [[a note about cats]]
        current_note.content = current_note.content.gsub(
          /\[\[(#{note_potentially_linked_to.data['title']})\]\](?!.*?[\r\n]+[`{3,}|~{3,}])/i,
          anchor_tag
        )

        # Replace double-bracketed links using note filename
        # [[cats]]
        current_note.content = current_note.content.gsub(
          /\[\[(#{title_from_filename})\]\](?!.*?[\r\n]+[`{3,}|~{3,}])/i,
          anchor_tag
        )

      end

      # At this point, all remaining double-bracket-wrapped words are
      # pointing to non-existing pages, so let's turn them into disabled
      # links by greying them out and changing the cursor
      # Still need to find a way to exclude from codeblocks with ```
      current_note.content = current_note.content.gsub(
        /\[\[(.+?)\|(.+?)\]\]/,
        <<~HTML.chomp    # replace with this HTML (\\1 is what was inside the brackets)
          <span title='There is no note that matches this link.' class='invalid-link'>\\1</span>
        HTML
      )
      # current_note.content = current_note.content.gsub(
      #   /
      #   (?:^\[{2}.|\s{1}\[{2}) # Starting with [[ on newline or preceded by space
      #   ([^\]]+) # Capture entire filename
      #   \]{2} # Make sure it ends in ]]
      #   (?!.*?[\r\n]+[`{3,}|~{3,}]) # Exclude codeblocks
      #   /x, # match on the remaining double-bracket links
      #   <<~HTML.chomp    # replace with this HTML (\\1 is what was inside the brackets)
      #     <span title='There is no note that matches this link.' class='invalid-link'>
      #       \\1
      #     </span>
      #   HTML
      # )
    end

    # Identify note backlinks and add them to each note
    all_notes.each do |current_note|
      # Nodes: Jekyll
      notes_linking_to_current_note = all_notes.filter do |e|
        e.content.include?(current_note.url) and !e.data['source']
      end

      # Nodes: Graph
      graph_nodes << {
        id: note_id_from_note(current_note),
        path: "#{current_note.url}#{link_extension}",
        label: current_note.data['title'],
      } unless current_note.path.include?('_notes/index.html')

      # Edges: Jekyll
      current_note.data['backlinks'] = notes_linking_to_current_note

      # Edges: Graph
      notes_linking_to_current_note.each do |n|
        graph_edges << {
          source: note_id_from_note(n),
          target: note_id_from_note(current_note),
        }
      end
    end

    File.write('_includes/notes_graph.json', JSON.dump({
      edges: graph_edges,
      nodes: graph_nodes,
    }))
  end

  def note_id_from_note(note)
    note.data['title']
      .dup
      .gsub(/\W+/, ' ')
      .delete(' ')
      .to_i(36)
      .to_s
  end
end