Retrieve and return the n largest files in a git repository

git-big-files

#!/bin/sh

# Retrieve and return the n largest files in a git repository
# Note: adapted from http://stubbisms.wordpress.com/2009/07/10/git-script-to-show-largest-pack-objects-and-trim-your-waist-line/

# Usage

function usage()
{
    echo "Usage: `basename $0` [-n count]"
}

# Check that we are in the root of a git repository

if [ ! -d .git ]; then
    echo "Error: `basename $0` must be called from the root of a git repository"

    usage

    exit 1
fi

# Retrieve the arguments, if any

count=10

while [ "$1" != "" ]; do
    case $1 in
        -n )
            shift

            if [ $# -eq 0 ]; then
                usage

                exit 1
            fi

            count=$1

            ;;
        -h )
            usage

            exit

            ;;
        * )
            usage

            exit 1
    esac

    shift
done

# Set the internal field spereator to line break, so that we can iterate easily
# over the verify-pack output

IFS=$'\n';

# Retrieve the n largest files

objects=`git verify-pack -v .git/objects/pack/pack-*.idx | grep -v chain | sort -k3nr | head -n $count`

# List the n largest files, including their size, pack, SHA and location

output="Size (KB)|Pack (KB)|SHA|Location"

for object in $objects
do
	# Extract the size in KBs

	size=$((`echo $object | cut -f 5 -d ' '`/1024))

	# Extract the compressed size in KBs

	pack=$((`echo $object | cut -f 6 -d ' '`/1024))

	# Extract the SHA

	sha=`echo $object | cut -f 1 -d ' '`

	# Find the object location in the git repository tree

	location=`git rev-list --all --objects | grep $sha | cut -d " " -f 2`

	# lineBreak=`echo -e "\n"`

	output="${output}\n${size}|${pack}|${sha}|${location}"
done

echo $output | column -t -s '|'