Find closest commit in a repo to a working dir without history

find_closest_sha1.py

#!/usr/bin/env python
import subprocess
import shlex
import sys
import os
import posixpath
import operator

# original by unutbu: http://stackoverflow.com/a/7779979
# revised by Miha Lunar

print sys.argv[1]
gitdir,workdir=map(os.path.abspath,sys.argv[1:3])
print gitdir, workdir
os.chdir(gitdir)
proc=subprocess.Popen(shlex.split('git rev-list --all'),stdout=subprocess.PIPE)
shas,err=proc.communicate()
shas=shas.split()
head=shas[0]

data={}
for sha1 in shas:
    subprocess.Popen(shlex.split('git checkout {s}'.format(s=sha1))).wait()
    diffcmd = 'diff "{g}" "{w}"'.format(g=gitdir,w=workdir)
    print diffcmd
    proc=subprocess.Popen(shlex.split(diffcmd),
                          stdout=subprocess.PIPE)
    out,err=proc.communicate()
    distance=len(out)
    data[sha1]=distance
    
    answer=min(data.items(),key=operator.itemgetter(1))[0]
    print('{current}   closest: {closest}'.format(current=sha1, closest=answer))

subprocess.Popen(shlex.split('git checkout {h}'.format(h=head))).wait()