Extract numeric chunks from a string

number_chunks_extractor.py

#!/usr/bin/env python3
import re
import unicodedata
from typing import List

# Constants
KANJI_DIGITS = '〇零一壱二弐三参四五伍六七八九'
ARABIC_DIGITS = '001122334556789'
KANJI_TO_ARABIC_MAPPING = str.maketrans(KANJI_DIGITS, ARABIC_DIGITS)
UNICODE_NORMALIZATION_FORM = 'NFKC'


def kanji_to_arabic(input_string: str) -> str:
    """
    Converts Kanji numerals in the input string to Arabic numerals.
    Args:
        input_string (str): The string containing Kanji numerals.
    Returns:
        str: The string with Kanji numerals converted to Arabic numerals.
    """
    return input_string.translate(KANJI_TO_ARABIC_MAPPING)


def extract_number_chunks(input_string: str) -> List[str]:
    """
    Extracts numeric chunks from a string after normalizing it.
    Args:
        input_string (str): The input string.
    Returns:
        List[str]: A list of extracted numbers as strings.
    """
    normalized_string = unicodedata.normalize(UNICODE_NORMALIZATION_FORM, input_string)
    return re.findall(r'\d+', normalized_string)


def main(input_string: str):
    return extract_number_chunks(kanji_to_arabic(input_string))


if __name__ == '__main__':
    test_string = '001-1223鶴の壱五四八番_455/67::89'
    expected_result = ['001', '1223', '1548', '455', '67', '89']
    print("Test String:", test_string)
    print("Expected result:", expected_result)
    result = main(test_string)
    assert result == expected_result, "Assertion failed!"
    print("Assertion passed!")  # Optional: Feedback that assertion was successful