Find old binary blobs in Git repository. Usage example `ruby find-old-binaries.rb master 0.5 true`

find-old-binaries.rb

#!/usr/bin/env ruby -w
head, treshold, only_orphans = ARGV
only_orphans ||= false
head ||= 'HEAD'
Megabyte = 1000 ** 2
treshold = (treshold || 0.1).to_f * Megabyte

# Usage:
# ruby find-old-binaries.rb <branch> <size limit in MB> <show only orphans?>
#
# If <show only orphans?> the script will output only binary blobs that
# ARE NOT INTO THE CURRENT CHECKED OUT BRANCH.
#
# Useful to know the binary blobs that can be removed from the Git history
# to reduce repository size (if you do not care about history)

big_files = {}

IO.popen("git rev-list #{head}", 'r') do |rev_list|
  rev_list.each_line do |commit|
    commit.chomp!
    for object in `git ls-tree -zrl #{commit}`.split("\0")
      bits, type, sha, size, path = object.split(/\s+/, 5)
      size = size.to_i
      big_files[sha] = [path, size, commit] if size >= treshold
    end
  end
end

big_files.each do |sha, (path, size, commit)|
  where = `git show -s #{commit} --format='%h: %cr'`.chomp
  orphan = false
  if not File.exist?(path) 
      orphan = true
  end
  if only_orphans
    if orphan
        puts "%4.1fM\t%s\t(%s)" % [size.to_f / Megabyte, path, where]
    end
  else
    puts "%4.1fM\t%s\t(%s) %s" % [size.to_f / Megabyte, path, where, orphan]
  end
end