Find and delete big files from git history

gitclean

#!/usr/bin/env ruby
def usage
  puts """
    gitclean - List and remove big files from git history

    Usage:   gitclean list [<rev> <threshold>]
             gitclean del <file>
    Example: gitclean list master 10
             gitclean del that-huge-logfile.log
  """
  exit
end

command = ARGV.shift
['list', 'del'].include? command or usage

if command == 'del'
  file = ARGV.shift
  file.to_s.empty? and usage
  exec "git filter-branch -f --index-filter 'git rm -r --cached --ignore-unmatch #{file}' HEAD"
  exit
end

if command == 'list'
  head, treshold = ARGV
  head ||= 'HEAD'
  Megabyte = 1000 ** 2
  treshold = (treshold || 0.1).to_f * Megabyte

  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
    puts "%4.1fM\t%s\t(%s)" % [size.to_f / Megabyte, path, where]
  end

  exit
end