translit_filenames.py

#!/usr/bin/env python
import argparse
import pathlib
import re
import sys
from collections import defaultdict
from functools import partial

print_err = partial(print, file=sys.stderr)

TRANS_TABLE = defaultdict(
    str,
    {
        "а": "a",
        "б": "b",
        "в": "v",
        "г": "g",
        "д": "d",
        "е": "e",
        "ё": "yo",
        "ж": "zh",
        "з": "z",
        "и": "i",
        "й": "y",
        "к": "k",
        "л": "l",
        "м": "m",
        "н": "n",
        "о": "o",
        "п": "p",
        "р": "r",
        "с": "s",
        "т": "t",
        "у": "u",
        "ф": "f",
        "х": "h",
        "ц": "ts",
        "ч": "ch",
        "ш": "sh",
        "щ": "shch",
        "ъ": "",
        "ы": "y",
        "ь": "",
        "э": "e",
        "ю": "yu",
        "я": "ya",
        "А": "A",
        "Б": "B",
        "В": "V",
        "Г": "G",
        "Д": "D",
        "Е": "E",
        "Ё": "Yo",
        "Ж": "Zh",
        "З": "Z",
        "И": "I",
        "Й": "Y",
        "К": "K",
        "Л": "L",
        "М": "M",
        "Н": "N",
        "О": "O",
        "П": "P",
        "Р": "R",
        "С": "S",
        "Т": "T",
        "У": "U",
        "Ф": "F",
        "Х": "H",
        "Ц": "Ts",
        "Ч": "Ch",
        "Ш": "Sh",
        "Щ": "Shch",
        "Ъ": "",
        "Ы": "Y",
        "Ь": "",
        "Э": "E",
        "Ю": "Yu",
        "Я": "Ya",
    },
)


def translit(text):
    return "".join(TRANS_TABLE.get(char, char) for char in text)


def translit_filenames(directory_path: pathlib.Path, to_lower: bool = False) -> None:
    for item in sorted(directory_path.rglob("*"), reverse=True):
        if item.name.startswith("."):
            continue

        new_name = translit(item.name)
        new_name = re.sub(r"\s+", "-", new_name).strip("-")
        if to_lower:
            new_name = new_name.lower()

        if item.name != new_name:
            new_path = item.parent / new_name
            if new_path.exists() and new_path != item:
                continue

            print_err(f"{item} -> {new_path}")
            item.rename(new_path)


if __name__ == "__main__":
    parser = argparse.ArgumentParser(
        description="Renames files and directories recursively using transliteration."
    )

    parser.add_argument(
        "directory", type=pathlib.Path, help="Path to the directory to process."
    )

    parser.add_argument(
        "-lc",
        "--lower-case",
        "--lower",
        help="To lower case",
        action=argparse.BooleanOptionalAction,
        default=False,
    )
    args = parser.parse_args()

    if args.directory.is_dir():
        translit_filenames(args.directory, args.lower_case)