Python Script to Identify Git Commits with Files Over a Specific Size

git-big.py

#!/usr/bin/env python

'''
Modified version from:
    http://stackoverflow.com/questions/298314/find-files-in-git-repo-over-x-megabytes-that-dont-exist-in-head

Examples:

    # Commits bigger than 1MB
    python git-big.py 1048576

    # Output visible on console and logged to file
    python git-big.py 1048576 | tee ~/big-commits.log
'''

import os, sys

def getOutput(cmd):
    return os.popen(cmd).read()

def convert_bytes(bytes):
    bytes = float(bytes)
    if bytes >= 1099511627776:
        terabytes = bytes / 1099511627776
        size = '%.2fT' % terabytes
    elif bytes >= 1073741824:
        gigabytes = bytes / 1073741824
        size = '%.2fG' % gigabytes
    elif bytes >= 1048576:
        megabytes = bytes / 1048576
        size = '%.2fM' % megabytes
    elif bytes >= 1024:
        kilobytes = bytes / 1024
        size = '%.2fK' % kilobytes
    else:
        size = '%.2fb' % bytes
    return size

if (len(sys.argv) <> 2):
    print "usage: %s size (bytes)" % sys.argv[0]
else:
    maxSize = int(sys.argv[1])
    revisions = getOutput("git rev-list HEAD").split()
    total = 0
    paths = set()
    unbuffered = os.fdopen(sys.stdout.fileno(), 'w', 0)
    separator = ('-' * 50) + "\n"

    unbuffered.write('\nCommits larger than %s:\n' % convert_bytes(maxSize))
    unbuffered.write(separator)
    unbuffered.write("      Size  Commit  Path\n")
    unbuffered.write(separator)
    for revision in revisions:
        files = getOutput("git ls-tree -zrl %s" % revision).split('\0')
        for file in files:
            if file == "":
                continue
            splitdata = file.split();
            commit = splitdata[2];
            size = int(splitdata[3])
            path = splitdata[4]
            if (size > maxSize) and path not in paths:
                total = total + size
                paths.add(path)
                unbuffered.write("%10s %s %s\n" % (convert_bytes(size), commit[0:7], path))

    # Show the total
    unbuffered.write(separator)
    unbuffered.write('%10s\n' % convert_bytes(total))