Created
October 8, 2014 14:19
-
-
Save StevenWolfe/78c201ba29e865bbaec4 to your computer and use it in GitHub Desktop.
Ruby script used to identify large files in a git repository, even if they aren't in HEAD. Taken from: http://stackoverflow.com/a/7945209/60724
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env ruby -w | |
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 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment