Last active
September 4, 2023 07:46
-
-
Save alesker/66a72bb0cd2d7d7739a878568478aa75 to your computer and use it in GitHub Desktop.
Python (Python 3) script to count contributions based on git-blame
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
import subprocess | |
import re | |
import operator | |
import sys | |
import os.path | |
path = '.' | |
if (len(sys.argv) > 1): | |
path = sys.argv[1] | |
extensions_filter = "" | |
if (len(sys.argv) > 2): | |
extensions = sys.argv[2].split(',') | |
extensions_filter = '|'.join(map(lambda ext: '\.' + ext + '$', extensions)) | |
excluded_paths = "" | |
if (len(sys.argv) > 3): | |
excluded_paths = sys.argv[3] | |
exclusions_filter = "" | |
if (len(sys.argv) > 3): | |
excluded_paths = sys.argv[3].split(',') | |
exclusions_filter = "".join(map(lambda path: ' -e ' + path, excluded_paths)) | |
print("Path: " + path) | |
git_ls_cmd = 'git ls-tree -r --name-only HEAD ' + path + ' | egrep "' + extensions_filter + '"' | |
if (len(exclusions_filter) > 0): | |
git_ls_cmd += ' | egrep -v ' + exclusions_filter + '' | |
filelist = subprocess.getoutput(git_ls_cmd).split('\n'); | |
name_dict = { } | |
for filename in filelist: | |
if filename == '' or not os.path.isfile(filename): | |
break | |
blamelist = subprocess.getoutput("git blame -w -C -C '" + filename + "'").split('\n') # add -C -C for copypaste detection | |
for line in blamelist: | |
components = re.findall("(\^?[0-9A-Fa-f]{7,8}).+\((.*) +(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2} (\+|-)\d{4}) +[0-9]+\) (.*)", line)[0] | |
if not re.match("^[ \t]*$", components[3]): | |
#print components[1] | |
name = components[1].strip() | |
if name in name_dict: | |
name_dict[name] = name_dict[name] + 1 | |
else: | |
name_dict[name] = 1 | |
sum_lines = 0 | |
for name, count in name_dict.items(): | |
sum_lines += count | |
sorted_name_tuple = sorted(name_dict.items(), key=operator.itemgetter(1), reverse=True) | |
for name_tuple in sorted_name_tuple: | |
print('{0:>25}: {1:5} {2:6.2%}'.format(name_tuple[0], name_tuple[1], name_tuple[1] / float(sum_lines))) | |
print('\n{0:>25}: {1:5}'.format("Total lines", sum_lines)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment