from backend.app.text_preprocess import preprocess_korean, split_sentences


def test_preprocess_numbers():
    out = preprocess_korean("예산은 1,250,000원입니다.")
    assert "원" in out
    assert "1,250,000" not in out


def test_split_sentences():
    chunks = split_sentences("첫 문장입니다. 두 번째 문장입니다.", max_chars=50)
    assert len(chunks) >= 1
    assert all(len(c) <= 50 for c in chunks)