siftlode/backend/tests/test_feed_views.py

"""Feed search + watch-state views (E2 S3), DB-lane.

Regression nets for two query rewrites that must stay behaviour-equivalent:
- PERF-12: the search channel-name branch moved from an ORed `unaccent(channels.title) ILIKE` (which
  defeated the search_vector GIN) to a pre-resolved `channel_id IN (...)`. A search must STILL return
  both videos whose text matches AND videos whose CHANNEL name matches.
- PERF-16: the watched/hidden/in_progress views moved from an outer join + `coalesce(state.status,'new')`
  to an inner join on video_states + the raw column. Each view must return exactly the same set.
"""
from datetime import datetime, timezone

import pytest

from app.models import Channel, ChannelTag, Subscription, Tag, Video, VideoState


def _dt(day: int) -> datetime:
    return datetime(2024, 1, day, tzinfo=timezone.utc)


def _video(vid: str, ch: str, title: str) -> Video:
    return Video(
        id=vid, channel_id=ch, published_at=_dt(1), title=title,
        is_short=False, live_status="none", via_search=False, via_explore=False,
    )


def _feed_ids(client, query: str) -> set[str]:
    resp = client.get(f"/api/feed?{query}&limit=50")
    assert resp.status_code == 200, resp.text
    return {it["id"] for it in resp.json()["items"]}


def test_search_matches_both_video_text_and_channel_name(db, as_user, make_user):
    # Two subscribed channels: one whose NAME matches the query (its video's text does not), and one
    # whose video TEXT matches (its name does not). The pre-resolved channel_id branch must still OR in
    # the name match, so both videos come back — and an unrelated video on a matching-name-less channel
    # stays out.
    user = make_user(email="search@example.com")
    db.add_all([
        Channel(id="UCkube", title="Kubernetes Weekly", subscriber_count=10),
        Channel(id="UCother", title="Some Other Channel", subscriber_count=10),
    ])
    db.add_all([
        Subscription(user_id=user.id, channel_id="UCkube", priority=0, hidden=False),
        Subscription(user_id=user.id, channel_id="UCother", priority=0, hidden=False),
    ])
    db.add_all([
        _video("vidChan", "UCkube", "Totally unrelated content"),   # channel NAME matches
        _video("vidText", "UCother", "kubernetes deep dive"),        # video TEXT matches
        _video("vidNone", "UCother", "cooking pasta at home"),       # neither matches
    ])
    db.commit()

    ids = _feed_ids(as_user(user), "q=kubernetes&show=all")
    assert ids == {"vidChan", "vidText"}


def test_watch_state_views_return_the_right_sets(db, as_user, make_user):
    user = make_user(email="views@example.com")
    db.add(Channel(id="UCv", title="Channel V", subscriber_count=10))
    db.add(Subscription(user_id=user.id, channel_id="UCv", priority=0, hidden=False))
    db.add_all([
        _video("vWatch", "UCv", "watched one"),
        _video("vHide", "UCv", "hidden one"),
        _video("vProg", "UCv", "in progress one"),
        _video("vNew", "UCv", "brand new one"),
    ])
    db.flush()
    db.add_all([
        VideoState(user_id=user.id, video_id="vWatch", status="watched"),
        VideoState(user_id=user.id, video_id="vHide", status="hidden"),
        # in progress = a stored resume position while still "new" (not watched/hidden)
        VideoState(user_id=user.id, video_id="vProg", status="new", position_seconds=30),
        # vNew has NO state row -> "new"/unwatched
    ])
    db.commit()

    client = as_user(user)
    assert _feed_ids(client, "show=watched") == {"vWatch"}
    assert _feed_ids(client, "show=hidden") == {"vHide"}
    assert _feed_ids(client, "show=in_progress") == {"vProg"}
    # unwatched excludes watched + hidden, keeps new AND in-progress
    assert _feed_ids(client, "show=unwatched") == {"vProg", "vNew"}
    # "all" shows everything except hidden
    assert _feed_ids(client, "show=all") == {"vWatch", "vProg", "vNew"}


def _seed_tagged(db, make_user):
    """A user subscribed to 4 channels with a spread of language/topic/other tags and differing video
    counts, so the count sum and the per-category facet drill-down are all non-trivial."""
    user = make_user(email="summary@example.com")
    tags = {
        "L1": Tag(user_id=None, name="Hungarian", category="language"),
        "L2": Tag(user_id=None, name="English", category="language"),
        "T1": Tag(user_id=None, name="Tech", category="topic"),
        "T2": Tag(user_id=None, name="Gaming", category="topic"),
        "O1": Tag(user_id=None, name="Favourite", category="other"),
        "O2": Tag(user_id=None, name="Docs", category="other"),
        # A USER-owned tag (+ a user-owned ChannelTag link below) so the visibility branch
        # `ChannelTag.user_id == user.id` is exercised, not only the system `user_id IS NULL` one.
        "U1": Tag(user_id=user.id, name="MyPin", category="other"),
    }
    db.add_all(tags.values())
    chans = {c: Channel(id=c, title=c, subscriber_count=10) for c in ("chA", "chB", "chC", "chD")}
    db.add_all(chans.values())
    db.flush()
    # channel -> (system) tag keys. chA carries two languages (L1+L2); chC two "other" tags (O1+O2)
    # AND chA carries O1 too — so the per-category any/all match narrows NON-TRIVIALLY (AND != OR) for
    # language and other, not only topic: e.g. other {O1,O2} → OR {chA,chC} vs AND {chC}; language
    # {L1,L2} → OR {chA,chB,chC} vs AND {chA}. (chA/chB share topic tags T1/T2 for the topic case.)
    links = {
        "chA": ["L1", "L2", "T1", "O1"],
        "chB": ["L1", "T2"],
        "chC": ["L2", "T1", "O1", "O2"],
        "chD": [],
    }
    for cid, tkeys in links.items():
        db.add(Subscription(user_id=user.id, channel_id=cid, priority=0, hidden=False))
        for tk in tkeys:
            db.add(ChannelTag(channel_id=cid, tag_id=tags[tk].id, user_id=None))
    # The user's own private link (visible only to them): chB carries U1 for this user.
    db.add(ChannelTag(channel_id="chB", tag_id=tags["U1"].id, user_id=user.id))
    # differing video counts per channel (chA:3, chB:2, chC:1, chD:2)
    counts = {"chA": 3, "chB": 2, "chC": 1, "chD": 2}
    for cid, n in counts.items():
        db.add_all([_video(f"{cid}v{i}", cid, f"{cid} clip {i}") for i in range(n)])
    db.commit()
    return user, {k: v.id for k, v in tags.items()}


# Query-param combos (as a template with {L1}/{T1}/… placeholders) that stress every facet path:
# no tags, single-category, cross-category, disjunctive + conjunctive topic modes, and a search filter.
_SUMMARY_CASES = [
    "show=all",
    "show=all&tags={L1}",
    "show=all&tags={T1}",
    "show=all&tags={L1}&tags={T1}",
    "show=all&tags={T1}&tags={T2}&tag_mode_topic=or",
    "show=all&tags={T1}&tags={T2}&tag_mode_topic=and",
    # Per-category any/all is NOT topic-only — language and other must drill down identically too.
    "show=all&tags={L1}&tags={L2}&tag_mode_language=or",
    "show=all&tags={L1}&tags={L2}&tag_mode_language=and",
    "show=all&tags={O1}&tags={O2}&tag_mode_other=and",
    "show=all&tags={U1}",  # user-owned tag (visibility == user.id branch)
    "show=all&tags={U1}&tags={L1}",  # user tag AND a system tag, cross-category
    "show=all&q=clip",
    "show=unwatched",
]


@pytest.mark.parametrize("case", _SUMMARY_CASES)
def test_feed_summary_matches_count_plus_facets(db, as_user, make_user, case):
    # /feed/summary must return byte-identical numbers to the old /feed/count + /facets it replaces,
    # across the full matrix of tag filters — it reimplements the tag drill-down in Python, so this is
    # the equivalence net.
    user, tag_ids = _seed_tagged(db, make_user)
    client = as_user(user)
    qs = case.format(**tag_ids)

    summary = client.get(f"/api/feed/summary?{qs}")
    count = client.get(f"/api/feed/count?{qs}")
    facets = client.get(f"/api/facets?{qs}")
    assert summary.status_code == count.status_code == facets.status_code == 200

    assert summary.json()["count"] == count.json()["count"], qs
    assert summary.json()["facets"] == facets.json()["counts"], qs