from news.util import canonical_url, content_hash, stable_id


def test_canonical_url_strips_tracking_and_www():
    a = canonical_url("https://www.bbc.co.uk/news/world-123?utm_source=rss&utm_medium=feed")
    b = canonical_url("https://bbc.co.uk/news/world-123/")
    assert a == b == "https://bbc.co.uk/news/world-123"


def test_canonical_url_keeps_meaningful_query():
    url = canonical_url("https://news.ycombinator.com/item?id=4242&utm_campaign=x")
    assert url == "https://news.ycombinator.com/item?id=4242"


def test_canonical_url_drops_fragment():
    assert canonical_url("https://x.com/a#section") == "https://x.com/a"


def test_stable_id_is_deterministic_and_distinct():
    assert stable_id("source", "u") == stable_id("source", "u")
    assert stable_id("source", "u") != stable_id("source", "v")


def test_content_hash_matches_only_identical_text():
    assert content_hash("a b") == content_hash("a b")
    assert content_hash("a b") != content_hash("a  b")