todset.py

def todset(text: str):
    lines = [x.rstrip("\n").lower().split("→") for x in text.split("\n")]
    lines = [(x[0].replace("\\n", "\n"), x[1].replace("\\n", "\n")) for x in lines]

    responses = []
    for i in lines:
        if i[1] not in responses:
            responses.append(i[1])

    dset = {}
    for sample in tqdm(lines):
        dset[sample[0]] = responses.index(sample[1])

    return (responses, dset)