myYouTube/tests/test_sync.py

from datetime import datetime, timezone

from app.config import settings
from app.models.channel import Channel
from app.models.video import Video
from app.services import sync


def _fake_credentials():
    return object()


def test_sync_subscriptions_idempotent_and_unsubscribes(monkeypatch, db_session):
    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: _fake_credentials())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_subscriptions",
        lambda creds: [
            {
                "youtube_channel_id": "chanA",
                "youtube_subscription_id": "subA",
                "title": "Channel A",
                "description": "d",
                "thumbnail_url": "t",
            },
            {
                "youtube_channel_id": "chanB",
                "youtube_subscription_id": "subB",
                "title": "Channel B",
                "description": "d",
                "thumbnail_url": "t",
            },
        ],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_uploads_playlists",
        lambda creds, ids: {cid: {"uploads_playlist_id": f"UU{cid}", "subscriber_count": 12345} for cid in ids},
    )

    result = sync.sync_subscriptions(db_session)

    assert result["status"] == "completed"
    assert result["channels_added"] == 2
    assert result["channels_unsubscribed"] == 0

    channels = db_session.query(Channel).order_by(Channel.youtube_channel_id).all()
    assert [c.youtube_channel_id for c in channels] == ["chanA", "chanB"]
    assert all(c.subscribed for c in channels)
    assert channels[0].uploads_playlist_id == "UUchanA"
    assert channels[0].subscriber_count == 12345

    # Second sync: chanA disappears from subscriptions, chanC appears.
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_subscriptions",
        lambda creds: [
            {
                "youtube_channel_id": "chanB",
                "youtube_subscription_id": "subB",
                "title": "Channel B",
                "description": "d",
                "thumbnail_url": "t",
            },
            {
                "youtube_channel_id": "chanC",
                "youtube_subscription_id": "subC",
                "title": "Channel C",
                "description": "d",
                "thumbnail_url": "t",
            },
        ],
    )

    result2 = sync.sync_subscriptions(db_session)

    assert result2["channels_added"] == 1
    assert result2["channels_updated"] == 1
    assert result2["channels_unsubscribed"] == 1

    channels = {c.youtube_channel_id: c for c in db_session.query(Channel).all()}
    assert len(channels) == 3
    assert channels["chanA"].subscribed is False
    assert channels["chanB"].subscribed is True
    assert channels["chanC"].subscribed is True


def test_sync_subscriptions_skips_none_subscriber_count(monkeypatch, db_session):
    channel = Channel(
        youtube_channel_id="chanA",
        youtube_subscription_id="subA",
        title="Channel A",
        subscribed=True,
        subscriber_count=12345,
    )
    db_session.add(channel)
    db_session.commit()

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: _fake_credentials())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_subscriptions",
        lambda creds: [
            {
                "youtube_channel_id": "chanA",
                "youtube_subscription_id": "subA",
                "title": "Channel A",
                "description": "d",
                "thumbnail_url": "t",
            },
        ],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_uploads_playlists",
        lambda creds, ids: {cid: {"uploads_playlist_id": f"UU{cid}", "subscriber_count": None} for cid in ids},
    )

    result = sync.sync_subscriptions(db_session)

    assert result["status"] == "completed"
    db_session.refresh(channel)
    assert channel.uploads_playlist_id == "UUchanA"
    # None in the API response must not overwrite the previously stored count.
    assert channel.subscriber_count == 12345


def test_sync_in_progress_raises(monkeypatch, db_session):
    sync._subscriptions_lock.acquire()
    try:
        try:
            sync.sync_subscriptions(db_session)
            assert False, "expected SyncInProgress"
        except sync.SyncInProgress:
            pass
    finally:
        sync._subscriptions_lock.release()


def _seed_channel(db_session, youtube_channel_id="chanA", uploads_playlist_id="UUchanA"):
    channel = Channel(
        youtube_channel_id=youtube_channel_id,
        title="Channel",
        subscribed=True,
        uploads_playlist_id=uploads_playlist_id,
    )
    db_session.add(channel)
    db_session.commit()
    db_session.refresh(channel)
    return channel


def test_sync_videos_adds_new_videos(monkeypatch, db_session):
    channel = _seed_channel(db_session)

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: object())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_playlist_video_ids_incremental",
        lambda creds, playlist_id, known_ids, max_results, stop_threshold: ["vid1"],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: [
            {
                "youtube_video_id": "vid1",
                "youtube_channel_id": channel.youtube_channel_id,
                "title": "Video One",
                "description": "d",
                "thumbnail_url": "t",
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": "PT5M",
            }
        ],
    )

    result = sync.sync_videos(db_session)

    assert result["status"] == "completed"
    assert result["videos_added"] == 1
    assert result["channels_checked"] == 1

    video = db_session.query(Video).filter_by(youtube_video_id="vid1").one()
    assert video.title == "Video One"
    assert video.duration_seconds == 300
    assert video.youtube_url == "https://www.youtube.com/watch?v=vid1"


def test_sync_videos_second_run_is_idempotent_and_fetches_no_details(monkeypatch, db_session):
    channel = _seed_channel(db_session)

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: object())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_playlist_video_ids_incremental",
        lambda creds, playlist_id, known_ids, max_results, stop_threshold: ["vid1"],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: [
            {
                "youtube_video_id": "vid1",
                "youtube_channel_id": channel.youtube_channel_id,
                "title": "Video One",
                "description": "d",
                "thumbnail_url": "t",
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": "PT5M",
            }
        ],
    )

    first = sync.sync_videos(db_session)
    assert first["videos_added"] == 1

    # Second run: vid1 is now known, so the incremental fetch reports nothing
    # new and no details are requested at all (existing videos are not
    # metadata-refreshed by design).
    details_calls = []
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_playlist_video_ids_incremental",
        lambda creds, playlist_id, known_ids, max_results, stop_threshold: [],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: details_calls.append(list(ids)) or [],
    )

    second = sync.sync_videos(db_session)

    assert second["videos_added"] == 0
    assert second["videos_updated"] == 0
    assert details_calls == [[]]
    assert db_session.query(Video).count() == 1


def test_sync_videos_passes_known_ids_and_backfill_settings(monkeypatch, db_session):
    channel = _seed_channel(db_session)
    db_session.add_all(
        [
            Video(
                youtube_video_id="known1",
                channel_id=channel.id,
                title="Known 1",
                published_at=datetime(2026, 9, 1, tzinfo=timezone.utc),
                youtube_url="https://www.youtube.com/watch?v=known1",
            ),
            Video(
                youtube_video_id="known2",
                channel_id=channel.id,
                title="Known 2",
                published_at=datetime(2026, 9, 1, tzinfo=timezone.utc),
                youtube_url="https://www.youtube.com/watch?v=known2",
            ),
        ]
    )
    db_session.commit()

    captured = {}

    def fake_incremental(creds, playlist_id, known_ids, max_results, stop_threshold):
        captured.update(known_ids=known_ids, max_results=max_results, stop_threshold=stop_threshold)
        return ["vid1"]

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: object())
    monkeypatch.setattr(sync.youtube_client, "fetch_playlist_video_ids_incremental", fake_incremental)
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: [
            {
                "youtube_video_id": "vid1",
                "youtube_channel_id": channel.youtube_channel_id,
                "title": "Video One",
                "description": "d",
                "thumbnail_url": "t",
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": "PT5M",
            }
        ],
    )

    result = sync.sync_videos(db_session)

    assert result["videos_added"] == 1
    assert captured["known_ids"] == {"known1", "known2"}
    assert captured["max_results"] == settings.videos_backfill_cap
    assert captured["stop_threshold"] == settings.videos_known_stop_threshold


def test_sync_videos_backfill_cap_ingests_all_candidates(monkeypatch, db_session):
    channel = _seed_channel(db_session)
    cap = settings.videos_backfill_cap
    new_ids = [f"vid{i}" for i in range(cap)]

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: object())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_playlist_video_ids_incremental",
        lambda creds, playlist_id, known_ids, max_results, stop_threshold: new_ids,
    )
    details_calls = []
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: details_calls.append(list(ids))
        or [
            {
                "youtube_video_id": vid,
                "youtube_channel_id": channel.youtube_channel_id,
                "title": f"Title {vid}",
                "description": "d",
                "thumbnail_url": "t",
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": None,
            }
            for vid in ids
        ],
    )

    result = sync.sync_videos(db_session)

    assert result["videos_added"] == cap
    assert result["videos_updated"] == 0
    assert set(details_calls[0]) == set(new_ids)
    assert db_session.query(Video).count() == cap


def test_sync_videos_skips_unknown_channel(monkeypatch, db_session):
    _seed_channel(db_session, "chanA")

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: object())
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_playlist_video_ids_incremental",
        lambda creds, playlist_id, known_ids, max_results, stop_threshold: [],
    )
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: [
            {
                "youtube_video_id": "vidX",
                "youtube_channel_id": "unknown-channel",
                "title": "Orphan",
                "description": "",
                "thumbnail_url": None,
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": None,
            }
        ],
    )

    result = sync.sync_videos(db_session)

    assert result["videos_skipped"] == 1
    assert db_session.query(Video).count() == 0


class _FakeResponse:
    def __init__(self, payload, status_code=200):
        self.status_code = status_code
        self._payload = payload
        self.text = str(payload)

    def json(self):
        return self._payload


class _FakeCredentials:
    token = "fake-token"


class _FakeClient:
    """Serves canned playlistItems pages through the real incremental fetcher."""

    def __init__(self, pages):
        self._pages = list(pages)
        self.requests = []

    def __enter__(self):
        return self

    def __exit__(self, *args):
        return False

    def get(self, url, params=None, headers=None):
        self.requests.append({"url": url, "params": params})
        return self._pages.pop(0)


def _page(items, next_token=None):
    return _FakeResponse(
        {
            "items": [{"contentDetails": {"videoId": vid}} for vid in items],
            **({"nextPageToken": next_token} if next_token else {}),
        }
    )


def test_sync_videos_stops_pagination_on_known_run(monkeypatch, db_session):
    """A channel with many known videos in a row after the new ones: the
    incremental fetch must stop paginating once the known-run threshold is hit
    and only the new ids must get details."""
    channel = _seed_channel(db_session)
    known = [f"known{i}" for i in range(60)]
    db_session.add_all(
        [
            Video(
                youtube_video_id=vid,
                channel_id=channel.id,
                title=f"Known {vid}",
                published_at=datetime(2026, 9, 1, tzinfo=timezone.utc),
                youtube_url=f"https://www.youtube.com/watch?v={vid}",
            )
            for vid in known
        ]
    )
    db_session.commit()

    # Page 1: two new videos then 48 known; page 2 continues with known ids,
    # so the run crosses 50 on the second page and pagination must stop there
    # (a third page exists and must never be requested).
    client = _FakeClient(
        [
            _page(["new1", "new2", *known[:48]], next_token="page2"),
            _page(known[48:58], next_token="page3"),
            _page(["never-seen"]),
        ]
    )
    details_calls = []

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: _FakeCredentials())
    monkeypatch.setattr(sync.youtube_client.httpx, "Client", lambda timeout: client)
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: details_calls.append(list(ids))
        or [
            {
                "youtube_video_id": vid,
                "youtube_channel_id": channel.youtube_channel_id,
                "title": f"Title {vid}",
                "description": "",
                "thumbnail_url": None,
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": None,
            }
            for vid in ids
        ],
    )

    result = sync.sync_videos(db_session)

    assert result["videos_added"] == 2
    assert len(client.requests) == 2  # stopped on page 2, page 3 never fetched
    assert set(details_calls[0]) == {"new1", "new2"}
    assert db_session.query(Video).count() == 62


def test_sync_videos_stops_at_backfill_cap(monkeypatch, db_session):
    """More new videos than the cap: pagination stops once the cap is reached
    and details are fetched for exactly the capped candidates."""
    channel = _seed_channel(db_session)
    cap = settings.videos_backfill_cap
    pages = [_page([f"vid{page * 50 + i}" for i in range(50)], next_token=f"p{page + 2}") for page in range(6)]
    client = _FakeClient(pages)
    details_calls = []

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: _FakeCredentials())
    monkeypatch.setattr(sync.youtube_client.httpx, "Client", lambda timeout: client)
    monkeypatch.setattr(
        sync.youtube_client,
        "fetch_videos_details",
        lambda creds, ids: details_calls.append(list(ids))
        or [
            {
                "youtube_video_id": vid,
                "youtube_channel_id": channel.youtube_channel_id,
                "title": f"Title {vid}",
                "description": "",
                "thumbnail_url": None,
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": None,
            }
            for vid in ids
        ],
    )

    result = sync.sync_videos(db_session)

    assert len(client.requests) == 4  # 4 pages x 50 = cap reached
    assert result["videos_added"] == cap
    assert len(details_calls[0]) == cap
    assert db_session.query(Video).count() == cap


def test_sync_videos_cap_is_hard_history_depth_limit(monkeypatch, db_session):
    """videos_backfill_cap is an intentional history-depth limit, not a
    per-sync batch: a 250-video channel ingests only the newest 200 videos
    ever; a later sync without new videos stops after one page of known ids
    and adds nothing; a new video on top of the playlist is picked up while
    the beyond-the-cap history never surfaces."""
    channel = _seed_channel(db_session)
    cap = settings.videos_backfill_cap

    def _details(creds, ids):
        return [
            {
                "youtube_video_id": vid,
                "youtube_channel_id": channel.youtube_channel_id,
                "title": f"Title {vid}",
                "description": "",
                "thumbnail_url": None,
                "published_at": "2026-09-10T12:00:00Z",
                "duration_iso8601": None,
            }
            for vid in ids
        ]

    monkeypatch.setattr(sync.google_oauth, "get_credentials", lambda db: _FakeCredentials())
    monkeypatch.setattr(sync.youtube_client, "fetch_videos_details", _details)

    # Uploads playlist, newest first: vid249 .. vid0.
    playlist = [f"vid{i}" for i in range(249, -1, -1)]

    def _run(ids):
        client = _FakeClient(
            [_page(ids[i : i + 50], next_token=f"page{i // 50}") for i in range(0, len(ids), 50)]
        )
        monkeypatch.setattr(sync.youtube_client.httpx, "Client", lambda timeout: client)
        return sync.sync_videos(db_session), client

    # First sync: 250 videos, only the newest 200 fit under the cap.
    result1, client1 = _run(playlist)
    assert result1["videos_added"] == cap
    assert db_session.query(Video).count() == cap
    assert len(client1.requests) == 4  # 4 pages x 50 = cap, older pages untouched
    synced = {v.youtube_video_id for v in db_session.query(Video).all()}
    assert synced == {f"vid{i}" for i in range(50, 250)}
    assert "vid49" not in synced  # older than the cap: never backfilled by design

    # Second sync, nothing new: one page of 50 known ids in a row stops it.
    result2, client2 = _run(playlist)
    assert result2["videos_added"] == 0
    assert len(client2.requests) == 1
    assert db_session.query(Video).count() == cap

    # Third sync, one new video on top: only that one is added, the
    # beyond-the-cap history still does not surface.
    result3, client3 = _run(["vid250", *playlist])
    assert result3["videos_added"] == 1
    assert len(client3.requests) == 2  # page 2 needed to confirm 50 known in a row
    synced_after = {v.youtube_video_id for v in db_session.query(Video).all()}
    assert synced_after == {f"vid{i}" for i in range(50, 251)}
    assert "vid49" not in synced_after


def test_is_videos_sync_running_reflects_lock():
    sync._videos_lock.acquire()
    try:
        assert sync.is_videos_sync_running() is True
    finally:
        sync._videos_lock.release()
    assert sync.is_videos_sync_running() is False