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 import feedquery

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}. (For topic, chA and chB each carry a DIFFERENT topic tag
    # — T1 vs T2 — so topic {T1,T2} → OR {chA,chB,chC} vs AND {} empty.)
    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
    # "No tag" filter (item B): channels with no USER tag. It stays applied in the base pass, so the
    # facet/count lockstep must still hold with it on (alone, and combined with a positive tag filter).
    "show=all&untagged=true",
    "show=all&untagged=true&tags={L1}",
    "show=all&q=clip",
    "show=unwatched",
    # A deleted tag's id (a saved view or the feed state still holds it) matches nothing.
    "show=all&tags=987654",
    "show=all&tags={L1}&tags=987654",
]


def test_a_deleted_tags_id_filters_to_nothing_not_to_everything(db, as_user, make_user):
    """A saved view or the feed's filter state keeps a tag id after the tag is deleted. The feed used
    to drop an unknown id, so that view silently showed the WHOLE feed under its old name (E32 S2).
    A filter on a tag that no longer exists matches nothing; the chip says the tag is gone."""
    user, tag_ids = _seed_tagged(db, make_user)
    client = as_user(user)
    everything = client.get("/api/feed/count?show=all")
    assert everything.status_code == 200
    assert everything.json()["count"] == 8
    for qs in ("show=all&tags=987654", f"show=all&tags={tag_ids['L1']}&tags=987654"):
        r = client.get(f"/api/feed/count?{qs}")
        assert r.status_code == 200
        assert r.json()["count"] == 0, qs
        r = client.get(f"/api/feed?{qs}")
        assert r.status_code == 200
        assert r.json()["items"] == [], qs


def test_another_users_private_tag_answers_like_one_that_does_not_exist(db, as_user, make_user):
    """The category split resolved any tag id, so a foreign PRIVATE tag landed in its real category
    and the summary's facets differed from a non-existent id's: an oracle for which foreign ids exist
    (E32 review). Both must now read as "missing"."""
    user, tag_ids = _seed_tagged(db, make_user)
    stranger = make_user(email="stranger@example.com")
    private = Tag(user_id=stranger.id, name="Secret", category="language")
    db.add(private)
    db.commit()
    assert feedquery.tags_by_category(db, user, [tag_ids["L1"], private.id]) == {
        "language": [tag_ids["L1"]],
        feedquery.MISSING_TAG_CATEGORY: [private.id],
    }
    client = as_user(user)
    foreign = client.get(f"/api/feed/summary?show=all&tags={tag_ids['T1']}&tags={private.id}")
    absent = client.get(f"/api/feed/summary?show=all&tags={tag_ids['T1']}&tags=987654")
    assert foreign.status_code == absent.status_code == 200
    assert foreign.json() == absent.json()


def test_untagged_filter_keeps_only_channels_the_user_has_not_tagged(db, as_user, make_user):
    """The "No tag" filter (item B): `untagged=true` keeps only channels with NO tag the USER personally
    attached (no user-owned ChannelTag). System/auto tags (user_id NULL) don't count, and another user's
    tag on the same channel doesn't either."""
    user = make_user(email="untagged@example.com")
    other = make_user(email="someone-else@example.com")
    mine = Tag(user_id=user.id, name="Fav", category="other")
    sys_topic = Tag(user_id=None, name="Tech", category="topic")
    theirs = Tag(user_id=other.id, name="TheirTag", category="other")
    db.add_all([mine, sys_topic, theirs])
    chans = {c: Channel(id=c, title=c, subscriber_count=10) for c in ("chMine", "chSys", "chNone")}
    db.add_all(chans.values())
    db.flush()
    # chMine: the user's own tag → tagged. chSys: only a system tag + another user's tag → still
    # "untagged" for THIS user. chNone: nothing at all → untagged.
    db.add(ChannelTag(channel_id="chMine", tag_id=mine.id, user_id=user.id, source="user"))
    db.add(ChannelTag(channel_id="chSys", tag_id=sys_topic.id, user_id=None, source="auto"))
    db.add(ChannelTag(channel_id="chSys", tag_id=theirs.id, user_id=other.id, source="user"))
    for cid in chans:
        db.add(Subscription(user_id=user.id, channel_id=cid, priority=0, hidden=False))
        db.add(_video(f"{cid}v", cid, f"{cid} clip"))
    db.commit()
    client = as_user(user)

    # Off: every subscribed channel shows.
    assert _feed_ids(client, "show=all") == {"chMinev", "chSysv", "chNonev"}
    # On: only channels the user has NOT personally tagged (a system tag / another user's tag don't count).
    assert _feed_ids(client, "show=all&untagged=true") == {"chSysv", "chNonev"}


def test_feed_years_counts_ignore_the_date_narrowing_but_honour_other_filters(
    db, as_user, make_user
):
    """The year facet (item 8 / E8·S2): `/api/feed/years` returns a per-year video count, newest first,
    with the publish-date narrowing DROPPED (so switching years stays a drill-down) but every other
    filter still applied (here: a channel pick)."""
    user = make_user(email="years@example.com")
    chans = {c: Channel(id=c, title=c, subscriber_count=10) for c in ("chX", "chY")}
    db.add_all(chans.values())
    db.flush()
    # chX: 2 videos in 2024, 1 in 2022; chY: 1 in 2023 (should drop once we scope to chX).
    spread = {
        "chX": [(2024, 1), (2024, 2), (2022, 5)],
        "chY": [(2023, 3)],
    }
    for cid, dates in spread.items():
        db.add(Subscription(user_id=user.id, channel_id=cid, priority=0, hidden=False))
        for i, (yr, day) in enumerate(dates):
            db.add(
                Video(
                    id=f"{cid}v{i}",
                    channel_id=cid,
                    published_at=datetime(yr, 1, day, tzinfo=timezone.utc),
                    title=f"{cid} clip {i}",
                    is_short=False,
                    live_status="none",
                    via_search=False,
                    via_explore=False,
                )
            )
    db.commit()
    client = as_user(user)

    # All channels: every year present, counted, newest first.
    resp = client.get("/api/feed/years?show=all")
    assert resp.status_code == 200, resp.text
    assert resp.json()["years"] == [
        {"year": 2024, "count": 2},
        {"year": 2023, "count": 1},
        {"year": 2022, "count": 1},
    ]

    # A channel filter narrows the year list; a date narrowing is ignored (the point of the facet — so
    # a selected year never zeroes out the others). Scoping to chX drops 2023, keeps 2024 (×2) + 2022.
    resp = client.get("/api/feed/years?show=all&channel_ids=chX&published_after=2024-01-01")
    assert resp.status_code == 200, resp.text
    assert resp.json()["years"] == [
        {"year": 2024, "count": 2},
        {"year": 2022, "count": 1},
    ]


def test_feed_years_buckets_by_utc_year_under_a_non_utc_session(db, make_user):
    """feed_years must bucket by UTC year to stay in lockstep with the year filter's UTC-pinned
    published_after/before bounds. published_at is timestamptz; a bare extract('year', …) would use the
    DB session timezone, so a video just before midnight UTC on New Year's Eve would bucket into the
    wrong (local) year on a non-UTC session and disagree with the feed the year chip drills into. Called
    directly on this session (the HTTP client uses a separate connection SET TIME ZONE wouldn't reach)."""
    from sqlalchemy import text

    from app.feedquery import feed_years

    user = make_user(email="tz-years@example.com")
    db.add(Channel(id="chTZ", title="chTZ", subscriber_count=1))
    db.add(Subscription(user_id=user.id, channel_id="chTZ", priority=0, hidden=False))
    # 2023-12-31 23:30 UTC — a positive-offset session tz local-shifts this into 2024.
    db.add(
        Video(
            id="tzv0",
            channel_id="chTZ",
            published_at=datetime(2023, 12, 31, 23, 30, tzinfo=timezone.utc),
            title="NYE clip",
            is_short=False,
            live_status="none",
            via_search=False,
            via_explore=False,
        )
    )
    db.commit()

    params: dict = {
        "tags": [],
        "tag_modes": {"language": "or", "topic": "or", "other": "or"},
        "untagged": False,
        "channel_ids": [],
        "q": None,
        "min_duration": None,
        "max_duration": None,
        "max_age_days": None,
        "published_after": None,
        "published_before": None,
        "show_normal": True,
        "include_shorts": False,
        "include_live": False,
        "show": "all",
        "scope": "my",
        "library_source": "organic",
    }
    db.execute(
        text("SET TIME ZONE 'Asia/Tokyo'")
    )  # +9: pushes the video's local wall-clock into 2024
    try:
        years = feed_years(db, user, **params)
    finally:
        db.execute(text("SET TIME ZONE 'UTC'"))  # SET (not SET LOCAL) survives rollback — reset it
    # UTC bucketing keeps the boundary video in 2023; a bare session-tz extract would report 2024.
    assert years == [{"year": 2023, "count": 1}]


@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