#!/usr/bin/env ruby

# Calculates sizes of repository at different commits in git
#
# 20060819 Initial release
# 20060820 Pass arguments to git-rev-list
#
# (c)2006 R. Nijlunsing <git@tux.tmfweb.nl>
# License: LGPLv2

require 'set'
require 'enumerator'

if ARGV.empty?
  puts "Calculates sizes of repository at different commits"
  puts
  puts "Usage: #{$0} <arguments for git-rev-list>"
  puts "Example: #{$0} HEAD"
  exit 1
end

class Sizes
  attr_reader :trees, :blobs, :bytes
  def initialize(trees, blobs, bytes); @trees = trees; @blobs = blobs; @bytes = bytes; end
  def add(o); @trees += o.trees; @blobs += o.blobs; @bytes += o.bytes; end
end

def tree_size(tree)
  return $sha2size[tree] if $sha2size.include?(tree)
  size = Sizes.new(1, 0, 0)
  blobs = []			# Blobs with unknown sizes
  File.popen("git cat-file -p #{tree}", "r") { |io|
    while line = io.gets
      line =~ %r{^[0-9]{6} ([a-z]+) ([0-9a-f]+)}
      type, sha1 = $1, $2
      if $sha2size.include?(sha1)
        size.add($sha2size[sha1])
      elsif type == "tree"
	size.add(tree_size(sha1))
      elsif type == "blob"
	blobs << sha1
      else
        raise type
      end
    end
  }
  if blobs.size > 0
    # Do all _blobs_ at once. For this to help, git-cat-file should accept
    # more than one filename a time.
    blobs.each_slice(1) { |blobs_slice|
      File.popen("git cat-file -s #{blobs_slice.join(' ')}", "r") { |io|
        blobs_slice.each { |blob|
          blob_size = $sha2size[blob] = Sizes.new(0, 1, io.gets.to_i)
	  size.add(blob_size)
        }
      }
    }
  end
  $sha2size[tree] = size
end

$sha2size = {}			# SHA1 -> Sizes

File.popen("git rev-list #{ARGV.join(' ')}", "r") do |cio|
  while commit = cio.gets
    tree = nil			# Root tree of this commit
    commit = commit.chomp
    File.popen("git cat-file -p #{commit}", "r") do |io|
      while (line = io.gets) && !tree
        tree = $1 if line =~ %r{^tree ([a-f0-9]+)}
      end
    end
    if tree
      sizes = tree_size(tree)
      puts "#{commit} #{sizes.trees} #{sizes.blobs} #{sizes.bytes}"
    end
  end
end