Just a quick little function to extract the current git revision hash from a filename. This is useful for data-versioning, say, when running a development version of a feature extractor on a fixed sample.

git versioning

import os
import git

def get_git_revision(filename, default='unversioned'):
    '''Walk up a path name until we find a git dir, then grab its current revision.
    
    If the file is not under any git repository, returns ''.
    '''
    
    old_filename = None
    filename = os.path.realpath(filename)

    while filename != old_filename:
        try:
            g = git.Git(filename)
            rev = g.log(['-n 1', '--format=%H'])
            return rev
        except:
            old_filename = filename
            filename = os.path.dirname(filename)
            
    return default