In a directory of Zettel notes, find all those without incoming links

find_zettel_orphans.rb

#!/usr/bin/env ruby
require 'set'

# Change the path here:
ARCHIVE = '~/Archive/'

EXTENSIONS = %w{.md .txt .markdown .mdown .text}

#################################################################

def zettel_id(filename)
  filename[/^[0-9][0-9_\-]+[0-9]/]
end

class Zettel
  @@all = {}
  attr_accessor :file, :id, :outbound, :inbound

  def initialize(file, id)
    @file = file
    @id = id
    @outbound = []
    @inbound = Set.new
  end
    
  def add_outbound_by_id(*ids)
    other_zettel = ids.select { |id| id != @id }
      .map { |id| Zettel::by_id(id) }
      .reject(&:nil?)

    # Link from this Zettel to other
    self.outbound.push(other_zettel)

    # Link other back to this Zettel
    other_zettel.each do |outbound_zettel|
      outbound_zettel.inbound.add(self)
    end    
  end
  
  def is_orphan?
    @inbound.size === 0
  end
  
  def self.by_id(id)
    @@all[id]
  end
  
  def self.all
    @@all.values
  end
  
  def self.each
    @@all.each_value do |zettel|
      yield zettel
    end
  end
  
  def self.add(file)
    return unless id = zettel_id(file)
    @@all[id] = Zettel.new(file, id)
  end
end

INPUT_DIR = File.expand_path(ARCHIVE)
Dir.entries(INPUT_DIR)
  .select { |path| EXTENSIONS.include?(File.extname(path)) }
  .each { |file| Zettel.add(file) }

puts "Analyzing #{Zettel.all.count} Zettel IDs ..."

Zettel.each do |zettel|
  content = File.read(File.join(INPUT_DIR, zettel.file))
  zettel.add_outbound_by_id(*content.scan(/[0-9][0-9_\-]+[0-9]/))
end

orphans = Zettel.all.select(&:is_orphan?)

score = (1 - orphans.count.to_f / Zettel.all.count.to_f).round(2)

puts orphans.map { |o| o.file }
puts "----------------------"
puts orphans.count.to_s + " of #{Zettel.all.count} notes are orphans (score: #{score})"

2020-04-28: Updated revision with unique-Zettel-lookup adapted from @msteen's fork: https://gist.github.com/msteen/a7362b703997a1417c297980390721b1