authorship.py

authorship_py2.py

#!/usr/bin/env python
import os
import re
from collections import defaultdict
import subprocess

author_line_count = defaultdict(lambda: 0)

email_re = re.compile(r'<.*?>')

devnull = open(os.devnull, 'w')

def git_blame(path):
    process = subprocess.Popen(['git', 'blame', '-e', path], stdout=subprocess.PIPE, stderr=devnull)
    out, err = process.communicate()
    return out.splitlines()


for root, dirs, files in os.walk(".", topdown=False):
    for name in files:
        ext = os.path.splitext(name)[1]
        if ext in ['.py', '.h', '.cpp', '.c', '.ino']:
            for row in git_blame(os.path.join(root, name)):
                m = email_re.search(row)
                if m:
                    email = m.group(0)
                    author_line_count[email] += 1


for key, value in sorted(author_line_count.iteritems(), key=lambda (k,v): (-v,k)):
    print "%s: %s" % (key, value)

git log --pretty=%H

... gives list of all commit on current branch since inital commit. Could be used to determine authorship throughout repository history.