Sort input lines by extension

sort-by-ext

#!/usr/bin/env python3

# Copyright (C) 2023  Andre Kugland
# This script is released under the MIT License.

"""
sort-by-ext: Sort input lines by extension.

Usage: sort-by-ext [-0]

This script is a command-line utility that reads lines of text from standard
input, sorts them by file extension, and writes the sorted lines to standard
output.

Options:
    -0, --null  use the null character as separator instead of newline

The purpose of this script is to reorder the files in the creation of a tar
archive, so that a better compression ratio can be achieved.

Example:
    find . -type f -print0 | sort-by-ext -0 | tar --null -czf archive.tgz -T -
"""

if __name__ != "__main__":
    raise Exception("This script is not meant to be imported.")

import sys
from os.path import basename, splitext
import argparse


def make_sort_key(line: bytes) -> bytes:
    """Return a key that can be used to sort the given line."""
    base = basename(line)
    ext = splitext(base)[1]
    return ext + b"/" + base + b"/" + line


parser = argparse.ArgumentParser(add_help=False)
parser.add_argument("-0", "--null", action="store_true")
parser.add_argument("-h", "--help", action="store_true")
args = parser.parse_args()
if args.help:
    print(__doc__.strip())
    exit(0)
separator = b"\0" if args.null else b"\n"
# Make sure stdin and stdout are opened in binary mode
with (
    open(sys.stdin.fileno(), "rb", closefd=False) as stdin,
    open(sys.stdout.fileno(), "wb", closefd=False) as stdout,
):
    lines = stdin.read().split(separator)
    if lines[-1] == b"":  # Remove trailing empty line if present
        lines.pop()
    lines.sort(key=make_sort_key)
    for line in lines:
        stdout.write(line + separator)