Show largest file in git repo

git-large-files.sh

#!/bin/bash
#set -x 
 
# Shows you the largest objects in your repo's pack file.
# Written for osx.
#
# @see https://stubbisms.wordpress.com/2009/07/10/git-script-to-show-largest-pack-objects-and-trim-your-waist-line/
# @author Antony Stubbs
 
LANG=C
export LANG

# Default to 10 files
NBFILES=10

# Minimal size
MINSIZE=1000

pack_path=objects/pack
# if we are in a working directory
[ -d .git ] && pack_path=.git/$pack_path

# check argument
[ $# -ge 1 ] && NBFILES=$1

# set the internal field spereator to line break, so that we can iterate easily over the verify-pack output
IFS=$'\n';
 
# list all objects including their size, sort by size, take top 10
objects=`git verify-pack -v $pack_path/pack-*.idx | awk '/ blob / && $3 >= '$MINSIZE' {print}' | sort -nr -k 3,3 | head -n $NBFILES`
 
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 ', '