Last active
January 5, 2020 04:08
-
-
Save alldne/2a95a4839a7c5a3c6112414f40469081 to your computer and use it in GitHub Desktop.
parse-git-log-numstat.py
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 python3 | |
| import sys | |
| import os | |
| import fileinput | |
| from collections import Counter | |
| def main(): | |
| n = None | |
| if len(sys.argv) > 1: | |
| n = int(sys.argv[1]) | |
| parse_stdin_and_show_most_common(n) | |
| def parse_stdin_and_show_most_common(n): | |
| chars = { digit for digit in map(str, range(0, 11)) } | |
| # For binary files, outputs two - instead of saying 0 0. (git log --help) | |
| chars.add("-") | |
| def contains_path(line): | |
| return line[0] in chars | |
| def extract_filename(fullpath): | |
| fullpath = fullpath.split("\t")[2] | |
| return os.path.basename(fullpath.strip()) | |
| lines = (line for line in sys.stdin) | |
| paths = filter(contains_path, lines) | |
| filenames = map(extract_filename, paths) | |
| counter = Counter(filenames) | |
| print_result(counter, n) | |
| def print_result(counter, n): | |
| for filename, count in counter.most_common(n): | |
| print(f"{count}\t{filename}") | |
| if __name__ == "__main__": | |
| main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment