import pytest

from app.normalize.text import normalize, normalize_person, slugify, strip_accents


@pytest.mark.parametrize(
    ("raw", "expected"),
    [
        ("Café Noir", "cafe noir"),
        ("naïve", "naive"),
        ("Łódź", "lodz"),
    ],
)
def test_strip_accents_and_lower(raw: str, expected: str) -> None:
    assert normalize(raw) == expected


def test_normalize_drops_leading_articles() -> None:
    assert normalize("The Big Lebowski") == "big lebowski"
    assert normalize("A Quick One") == "quick one"
    assert normalize("An Honest Take") == "honest take"


def test_normalize_collapses_whitespace_and_punct() -> None:
    assert normalize("Hello,   world!!!") == "hello world"
    assert normalize("foo--bar__baz") == "foo bar baz"


def test_normalize_handles_none_and_empty() -> None:
    assert normalize(None) == ""
    assert normalize("") == ""
    assert normalize("   ") == ""


def test_normalize_person_keeps_initials() -> None:
    # „Mia M." → „mia m" (kropka usunięta jako interpunkcja)
    assert normalize_person("Mia M.") == "mia m"
    assert normalize_person("Mia Malkova") == "mia malkova"


def test_slugify_is_url_safe() -> None:
    assert slugify("Brazzers Network") == "brazzers-network"
    assert slugify("Mia Malkova") == "mia-malkova"
    assert slugify("") == ""


def test_strip_accents_idempotent() -> None:
    once = strip_accents("naïve")
    twice = strip_accents(once)
    assert once == twice == "naive"