Find big files in git history that don't exist in head. Usage: `ruby find-big-files-not-in-head.rb [size in MB] [rev]`

find-big-files-not-in-head.rb

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

big_files = {}
commit_number = 0
commits_count = 0

IO.popen("git rev-list #{head}", 'r') do |rev_list|
  commits_count = rev_list.each_line.count
  puts "%s commits" % [commits_count]
end

IO.popen("git rev-list #{head}", 'r') do |rev_list|
  rev_list.each_line do |commit|
    commit_number += 1
    if commit_number >= 1000 then
      break
    end
    commit.chomp!
    puts "commit %6d / %d %s" % [commit_number, commits_count, commit]
    for object in `git ls-tree -zrl #{commit}`.split("\0")
      bits, type, sha, size, path = object.split(/\s+/, 5)
      size = size.to_i
      if size > treshold then
        if big_files.has_key? sha and big_files[sha][0] != path then
          warn "Another path for #{sha} is #{path}"
        else
          big_files[sha] = [path, size, commit]
        end
      end
    end
  end
end

big_files.each do |sha, (path, size, commit)|
  # where = `git show -s #{commit} --format='%h: %cr'`.chomp
  # fatal: ambiguous argument '%cr'': unknown revision or path not in the working tree.
  where = `git show -s #{commit} --format=oneline`.chomp
  puts "%4.1fM\t%s\t%s" % [size.to_f / Megabyte, path, where]
end