git-discover-large-blobs

#!/usr/bin/env bash
#set -x

# Shows you the largest objects in your repo's pack file.
#
# @see http://stubbisms.wordpress.com/2009/07/10/git-script-to-show-largest-pack-objects-and-trim-your-waist-line/
# @author Antony Stubbs
# ChangeLog
#
#       Originally by Antony Stubbs http://stubbisms.wordpress.com/2009/07/10/git-script-to-show-largest-pack-objects-and-trim-your-waist-line/
#
#       <javabrett>
#       - Make command work when in the non-root directory of a repo, or from the top-level of a bare repo
#


# set the internal field separator to line break, so that we can iterate easily over the verify-pack output
IFS=$'\n';

# find top-level dir of a non-bare repo
_GIT_DIR=$(git rev-parse --show-toplevel) || exit 1

if [ -n "${_GIT_DIR}" ] && [ -d "${_GIT_DIR}"/.git/objects/pack ]; then
	PACK_DIR=${_GIT_DIR}/.git/objects/pack
elif [ -d ./objects/pack ]; then
	# bare repo
	PACK_DIR=./objects/pack
else
	echo "Cannot locate pack directory"
	exit 1
fi

# list all objects including their size, sort by size, take top 10
objects=$(git verify-pack -v "${PACK_DIR}"/pack-*.idx | grep -v chain | sort -k3nr | head)

echo "All sizes are in kB's. 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 ', '