Show number of changed lines per author in git

Question

i want to see the number of removed/added line, grouped by author for a given branch in git history. there is git shortlog -s which shows me the number of commi

Answer 1

On my repos I've gotten a lot of trash output from the one-liners floating around, so here is a Python script to do it right:

import subprocess
import collections
import sys


def get_lines_from_call(command):
    return subprocess.check_output(command).splitlines()

def get_files(paths=()):
    command = ['git', 'ls-files']
    command.extend(paths)
    return get_lines_from_call(command)

def get_blame(path):
    return get_lines_from_call(['git', 'blame', path])


def extract_name(line):
    """
    Extract the author from a line of a standard git blame
    """
    return line.split('(', 1)[1].split(')', 1)[0].rsplit(None, 4)[0]


def get_file_authors(path):
    return [extract_name(line) for line in get_blame(path)]


def blame_stats(paths=()):
    counter = collections.Counter()
    for filename in get_files(paths):
        counter.update(get_file_authors(filename))
    return counter


def main():
    counter = blame_stats(sys.argv[1:])
    max_width = len(str(counter.most_common(1)[0][1]))
    for name, count in reversed(counter.most_common()):
        print('%s %s' % (str(count).rjust(max_width), name))

if __name__ == '__main__':
    main()

Note that the arguments to the script will be passed to git ls-files, so if you only want to show Python files: blame_stats.py '**/*.py'

If you only want to show files in one subdirectory:blame_stats.py some_dir

And so on.