much better script for finding large files in git repos

git-large-files

@@ -1,23 +1,33 @@
-#!/usr/bin/env ruby -w
-head, treshold = ARGV
-head ||= 'HEAD'
-Megabyte = 1000 ** 2
-treshold = (treshold || 0.1).to_f * Megabyte
+#!/bin/bash
+#set -x 
 
-big_files = {}
+# Shows you the largest objects in your repo's pack file.
+# Written for osx.
+#
+# @see http://stubbisms.wordpress.com/2009/07/10/git-script-to-show-largest-pack-objects-and-trim-your-waist-line/
+# @author Antony Stubbs
 
-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
+# set the internal field spereator to line break, so that we can iterate easily over the verify-pack output
+IFS=$'\n';
 
-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
+# list all objects including their size, sort by size, take top 10
+objects=`git verify-pack -v .git/objects/pack/pack-*.idx | grep -v chain | sort -k3nr | head -n 40`
+
+echo "All sizes are in kB. The pack column is the size of the object, compressed, inside the pack file."
+
+output="size,pack,SHA,location"
+for y in $objects
+do
+	# extract the size in bytes
+	size=$((`echo $y | cut -f 5 -d ' '`/1024))
+	# extract the compressed size in bytes
+	compressedSize=$((`echo $y | cut -f 6 -d ' '`/1024))
+	# extract the SHA
+	sha=`echo $y | cut -f 1 -d ' '`
+	# find the objects location in the repository tree
+	other=`git rev-list --all --objects | grep $sha`
+	#lineBreak=`echo -e "\n"`
+	output="${output}\n${size},${compressedSize},${other}"
+done
+
+echo -e $output | column -t -s ', '