gitsplit-findbigfiles.sh

#!/bin/bash
#set -x 

# 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

# Modified by Luka Kladaric <[email protected]>
# - cache the rev-list instead of pulling it up for each file
# - cache the top objects list, an expensive operation
# - no "drop cache" command, delete *.cache manually

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

GET_FILES=${1:-100} # default: 100 files
TOP_OBJECTS_CACHE="top_objects.cache"
REV_LIST_CACHE="rev_list.cache"

# cache a list of all objects including their size, sort by size
if [ ! -f $TOP_OBJECTS_CACHE ]
then
    git verify-pack -v .git/objects/pack/pack-*.idx | grep -v chain | sort -k3nr > $TOP_OBJECTS_CACHE
    rm $REV_LIST_CACHE
fi

# cache a list of all 
if [ ! -f $REV_LIST_CACHE ]
then
    git rev-list --all --objects > $REV_LIST_CACHE
fi

objects=`head -n $GET_FILES $TOP_OBJECTS_CACHE`

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=`grep $sha $REV_LIST_CACHE`
    output="${output}\n${size},${compressedSize},${other}"
done

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