ディレクトリツリーに存在する拡張子を集計するスクリプト

extstats.py

#!/usr/bin/env python3

import sys
import os
from pathlib import Path
from collections import Counter

def eprint(*args, **kwargs):
    print(*args, file=sys.stderr, **kwargs)

def main():
    try:
        if len(sys.argv) == 1:
            path = Path(".")
        elif len(sys.argv) == 2:
            path = Path(sys.argv[1])
        else:
            eprint("Usage: ./extstats.py [DIR]")
            return 1
        try:
            path = path.resolve(strict=True)
            if not path.is_dir():
                raise RuntimeError()
        except Exception:
            eprint("No such directory")
            return 1
        files = (p for p in path.rglob("*", case_sensitive=False) if p.is_file())
        exts = (f.suffix.lower() for f in files)
        counts = Counter(exts)
        for ext, count in sorted(counts.items(), key=lambda t: t[1], reverse=True):
            try:
                print(f"{ext}\t{count}", flush=True)
            except BrokenPipeError:
                devnull = os.open(os.devnull, os.O_WRONLY)
                os.dup2(devnull, sys.stdout.fileno())
                return 128 + 13
    except KeyboardInterrupt:
        return 128 + 2
    return 0

if __name__ == "__main__":
    sys.exit(main())