Clean up the bloated Backblaze bzfileids.dat

purge_bzfileids.rb

#!/usr/bin/env ruby
# Place in `/Library/Backblaze.bzpkg/bzdata/bzbackup`, and run with:
#
# ```
# ruby purge_bzfileids.rb
# ```
# 
# It will process `bzfileids.dat` placing any file that exists in
# `bzfileids.dat-found` and any missing file in `bzfileids.dat-missing`. You can
# then back up your original file and replace it with `bzfileids.dat-found`.
#
# My original file was almost 1.4GB. It had grown so large that the backup would
# cause all my fans spin and it never seemed to complete. Backblaze support
# suggested I delete my entire backup with them and start over. After running
# this script, my new `bzfileids.dat` file is 301MB. Still huge, but about 1/5th
# the size. The backup seemed to go much more smoothly.

missing = File.open('./bzfileids.dat-missing', 'a+b')
found = File.open('./bzfileids.dat-found', 'a+b')

File.open('./bzfileids.dat').each_with_index do |line, index|
  split = line.match(/^([a-z0-9_-]+)\s+(.+)$/)
  if split
    path = split[2]

    if File.exist?(path)
      found.puts line
    else
      missing.puts line
    end
  else
    puts "#{index} Invalid line found: #{line}"
  end
end

missing.close
found.close