parser.py

from typing import Dict
from pprint import pprint


def parse_dataset(filename: str) -> Dict[str, str]:
    data = {}
    with open(filename) as f:
        for line in f:
            line = line.rstrip()
            if line.startswith(">"):
                label = line[1:]
                data[label] = ""
            else:
                print(line)
                data[label] += line
    return data


if __name__ == "__main__":
    data = parse_dataset(input("path to dataset\n> "))
    pprint(data)

vowels.py

VOWELS = {'a', 'e', 'i', 'o', 'u'}


def is_vowel(c: str) -> bool:
    return c in VOWELS


def longest_sub_vowel_str(s: str) -> str:
    idx = 0
    possible_longest = curr_longest = ""
    while idx < len(s):
        if is_vowel(s[idx]):
            possible_longest = ""
            while is_vowel(s[idx]) and idx < len(s):
                possible_longest += s[idx]
                idx += 1
        if len(possible_longest) > len(curr_longest):
            curr_longest = possible_longest
        idx += 1
    return curr_longest