FabledCurator/tests/test_source_service.py

import pytest
from sqlalchemy import select

from backend.app.models import Artist, Source
from backend.app.services.source_service import (
    KNOWN_PLATFORMS,
    ArtistNotFoundError,
    DuplicateSourceError,
    EmptyUrlError,
    InvalidConfigError,
    SourceService,
    UnknownPlatformError,
)

pytestmark = pytest.mark.integration


async def _artist(db, name="Alice"):
    a = Artist(name=name, slug=name.lower())
    db.add(a)
    await db.flush()
    return a


@pytest.mark.asyncio
async def test_known_platforms_is_gs_six(db):
    assert KNOWN_PLATFORMS == frozenset({
        "patreon", "subscribestar", "hentaifoundry",
        "discord", "pixiv", "deviantart",
    })
    assert "fanbox" not in KNOWN_PLATFORMS


@pytest.mark.asyncio
async def test_create_flips_is_subscription_on_first_source(db):
    artist = await _artist(db)
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
    )
    assert rec.id is not None
    is_sub = (await db.execute(
        select(Artist.is_subscription).where(Artist.id == artist.id)
    )).scalar_one()
    assert is_sub is True


@pytest.mark.asyncio
async def test_delete_last_source_flips_is_subscription_off(db):
    artist = await _artist(db)
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
    )
    await svc.delete(rec.id)
    is_sub = (await db.execute(
        select(Artist.is_subscription).where(Artist.id == artist.id)
    )).scalar_one()
    assert is_sub is False


@pytest.mark.asyncio
async def test_create_rejects_unknown_platform(db):
    artist = await _artist(db)
    svc = SourceService(db)
    with pytest.raises(UnknownPlatformError):
        await svc.create(
            artist_id=artist.id, platform="myspace", url="https://m/x",
        )


@pytest.mark.asyncio
async def test_create_rejects_non_dict_config(db):
    artist = await _artist(db)
    svc = SourceService(db)
    with pytest.raises(InvalidConfigError):
        await svc.create(
            artist_id=artist.id, platform="patreon",
            url="https://patreon.com/alice", config_overrides=[1, 2, 3],
        )


@pytest.mark.asyncio
async def test_create_rejects_empty_url(db):
    artist = await _artist(db)
    svc = SourceService(db)
    with pytest.raises(EmptyUrlError):
        await svc.create(artist_id=artist.id, platform="patreon", url="   ")


@pytest.mark.asyncio
async def test_create_rejects_unknown_artist(db):
    svc = SourceService(db)
    with pytest.raises(ArtistNotFoundError):
        await svc.create(artist_id=99999, platform="patreon", url="https://x/y")


@pytest.mark.asyncio
async def test_create_duplicate_raises_with_existing_id(db):
    artist = await _artist(db)
    svc = SourceService(db)
    first = await svc.create(
        artist_id=artist.id, platform="patreon", url="https://patreon.com/alice",
    )
    with pytest.raises(DuplicateSourceError) as exc:
        await svc.create(
            artist_id=artist.id, platform="patreon",
            url="https://patreon.com/alice",
        )
    assert exc.value.existing_id == first.id


@pytest.mark.asyncio
async def test_list_filters_by_artist(db):
    a = await _artist(db, "Alice")
    b = await _artist(db, "Bob")
    svc = SourceService(db)
    await svc.create(artist_id=a.id, platform="patreon", url="https://patreon.com/a")
    await svc.create(artist_id=b.id, platform="patreon", url="https://patreon.com/b")
    only_a = await svc.list(artist_id=a.id)
    assert [s.artist_id for s in only_a] == [a.id]
    all_rows = await svc.list()
    assert len(all_rows) == 2


@pytest.mark.asyncio
async def test_update_changes_fields(db):
    artist = await _artist(db)
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon", url="https://patreon.com/a",
    )
    updated = await svc.update(rec.id, enabled=False, config_overrides={"videos": False})
    assert updated.enabled is False
    assert updated.config_overrides == {"videos": False}


@pytest.mark.asyncio
async def test_list_hides_sidecar_synthetic_anchors(db):
    """Filesystem-import synthetic Sources (url='sidecar:<platform>:<slug>',
    enabled=False — historical pre-alembic-0030 artifact) used to leak into the
    Subscriptions UI as phantom subscriptions because list() didn't filter
    them. They aren't pollable feeds; hide by default."""
    artist = await _artist(db, "Alice")
    real = Source(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice", enabled=True, config_overrides={},
    )
    synthetic = Source(
        artist_id=artist.id, platform="patreon",
        url="sidecar:patreon:alice", enabled=False, config_overrides={},
    )
    db.add_all([real, synthetic])
    await db.commit()

    svc = SourceService(db)
    visible = await svc.list()
    visible_urls = {s.url for s in visible}
    assert "https://patreon.com/alice" in visible_urls
    assert "sidecar:patreon:alice" not in visible_urls

    # Same filter applies to the artist-scoped list path (the artist detail
    # page hits /api/sources?artist_id=N).
    artist_scoped = await svc.list(artist_id=artist.id)
    assert {s.url for s in artist_scoped} == {"https://patreon.com/alice"}

    # include_synthetic=True opts back in for admin tooling.
    everything = await svc.list(include_synthetic=True)
    assert {s.url for s in everything} >= {
        "https://patreon.com/alice", "sidecar:patreon:alice",
    }


# --- Plan #544: backfill counter -------------------------------------------


@pytest.mark.asyncio
async def test_start_backfill_arms_run_until_done(db):
    """start_backfill sets state=running + the chunk cap and clears any prior
    cursor/chunk state, returning the updated record for the API to echo."""
    from backend.app.services.source_service import BACKFILL_MAX_CHUNKS

    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice",
    )
    # Simulate a prior, finished walk leaving stale checkpoint state.
    await db.execute(
        Source.__table__.update().where(Source.id == rec.id).values(
            config_overrides={"_backfill_state": "complete", "_backfill_cursor": "old",
                              "_backfill_chunks": 7},
        )
    )
    await db.commit()

    updated = await svc.start_backfill(rec.id)
    assert updated.backfill_state == "running"
    assert updated.backfill_chunks == 0
    assert updated.backfill_runs_remaining == BACKFILL_MAX_CHUNKS

    co = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert co.get("_backfill_state") == "running"
    assert "_backfill_cursor" not in co


@pytest.mark.asyncio
async def test_stop_backfill_returns_to_idle(db):
    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice",
    )
    await svc.start_backfill(rec.id)
    updated = await svc.stop_backfill(rec.id)
    assert updated.backfill_state is None
    assert updated.backfill_runs_remaining == 0
    co = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert "_backfill_state" not in (co or {})


@pytest.mark.asyncio
async def test_start_recovery_arms_bypass_flag(db):
    """Plan #697: start_recovery arms the backfill state machine PLUS the
    _backfill_bypass_seen flag (recovery), surfaced on the record so the UI badge
    can label it 'Recovering'. Clears any prior checkpoint state."""
    from backend.app.services.source_service import BACKFILL_MAX_CHUNKS

    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice",
    )
    # Simulate a prior walk's posts counter — start must clear it (plan #704).
    await db.execute(
        Source.__table__.update().where(Source.id == rec.id).values(
            config_overrides={"_backfill_posts": 42},
        )
    )
    await db.commit()

    updated = await svc.start_recovery(rec.id)
    assert updated.backfill_state == "running"
    assert updated.backfill_bypass_seen is True
    assert updated.backfill_posts == 0  # cleared for a fresh walk
    assert updated.backfill_runs_remaining == BACKFILL_MAX_CHUNKS

    co = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert co.get("_backfill_bypass_seen") is True
    assert "_backfill_posts" not in co

    # Stop clears the bypass flag too (shared lifecycle).
    stopped = await svc.stop_backfill(rec.id)
    assert stopped.backfill_bypass_seen is False
    co2 = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert "_backfill_bypass_seen" not in (co2 or {})


@pytest.mark.asyncio
async def test_start_recapture_arms_recapture_flag(db):
    """#830: start_recapture arms the backfill state machine PLUS the
    _backfill_recapture flag, surfaced on the record so the badge can label it
    'Recapturing'. Mutually exclusive with recovery (clears bypass_seen); stop
    clears it."""
    from backend.app.services.source_service import BACKFILL_MAX_CHUNKS

    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice",
    )
    # Pre-arm recovery, then recapture must clear bypass_seen (mutual exclusion).
    await svc.start_recovery(rec.id)

    updated = await svc.start_recapture(rec.id)
    assert updated.backfill_state == "running"
    assert updated.backfill_recapture is True
    assert updated.backfill_bypass_seen is False
    assert updated.backfill_runs_remaining == BACKFILL_MAX_CHUNKS

    co = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert co.get("_backfill_recapture") is True
    assert "_backfill_bypass_seen" not in co

    # to_dict carries the new field for the API/UI.
    assert updated.to_dict()["backfill_recapture"] is True

    # Stop clears the recapture flag too.
    stopped = await svc.stop_backfill(rec.id)
    assert stopped.backfill_recapture is False
    co2 = (await db.execute(
        select(Source.config_overrides).where(Source.id == rec.id)
    )).scalar_one()
    assert "_backfill_recapture" not in (co2 or {})


@pytest.mark.asyncio
async def test_start_backfill_raises_when_source_missing(db):
    svc = SourceService(db)
    with pytest.raises(LookupError):
        await svc.start_backfill(99999)


@pytest.mark.asyncio
async def test_new_enabled_source_starts_in_backfill_mode(db):
    """Plan #693: freshly added enabled sources have no archive yet, so they
    arm run-until-done backfill — state 'running' — to walk the full history
    on the first ticks instead of blowing the wall-clock cap in tick mode."""
    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice-new",
    )
    assert rec.backfill_state == "running"


@pytest.mark.asyncio
async def test_new_disabled_source_skips_backfill(db):
    """Disabled sources (incl. sidecar synthetics that arrive disabled) are
    never polled, so don't burn a backfill budget on them."""
    artist = await _artist(db, "Alice")
    svc = SourceService(db)
    rec = await svc.create(
        artist_id=artist.id, platform="patreon",
        url="https://patreon.com/alice-disabled",
        enabled=False,
    )
    assert rec.backfill_runs_remaining == 0