FabledCurator/tests/test_artist_membership_suggestions.py

"""Milestone 388 E4: proposing that a creator and a membership are the same.

E4's own first instruction was to verify before building, and the verification
said the association ALREADY works — `Source.artist_id` is a plain FK, the API
takes an `artist_id`, the add-source dialog attaches to an existing artist, and
`reassign` moves a source with post/image re-attribution. So these test the
SUGGESTION, which is what was actually missing.

The failure to avoid is a wrong link. Accepting adds a SOURCE rather than
merging artists precisely because the first is trivially undone and the second
silently mixes two creators' work — so most of what follows pins refusals, and
the weights are asserted structurally so they survive a refactor of the scorer.
"""
from datetime import UTC, datetime

import pytest
from sqlalchemy import select

from backend.app.models import (
    Artist,
    ArtistMembershipSuggestion,
    PlatformMembership,
    Post,
    Source,
)
from backend.app.services.artist_membership_service import (
    DEFAULT_THRESHOLD,
    WEIGHTS,
    ArtistMembershipService,
    declared_signal,
    name_signal,
    weighted_score,
)
from tests.roster_builders import membership as _membership

pytestmark = pytest.mark.integration


# --- the structural guard --------------------------------------------------


def test_the_weights_encode_the_judgement_rather_than_a_code_path():
    """Three claims, asserted against WEIGHTS directly so they survive any
    refactor of the scorer. Do NOT fix a failure here by moving the numbers —
    the arithmetic IS the decision.

      * an EXACT name match alone proposes (same slug is strong evidence, and
        demanding corroboration would propose almost nothing);
      * a CONTAINMENT name match alone does not ("art" sits inside "artgirl");
      * the declaration ALONE never proposes, because a creator may link
        another creator's Patreon and a link is not a claim of identity.
    """
    assert sum(WEIGHTS.values()) == pytest.approx(1.0)
    assert weighted_score({"name": 1.0}) >= DEFAULT_THRESHOLD
    assert weighted_score({"name": 0.6}) < DEFAULT_THRESHOLD
    assert weighted_score({"declared": 1.0}) < DEFAULT_THRESHOLD
    assert weighted_score({"name": 0.6, "declared": 1.0}) >= DEFAULT_THRESHOLD


# --- the signals -----------------------------------------------------------


def _m(**kw):
    kw.setdefault("platform", "patreon")
    kw.setdefault("external_campaign_id", "1")
    return PlatformMembership(**kw)


def test_name_matches_on_either_the_display_name_or_the_vanity():
    """Creators routinely differ between the two, and either may be what the
    operator typed when they created the artist."""
    m = _m(display_name="Team Melon Collie",
           details={"campaign": {"vanity": "MelonCollieStudios"}})
    assert name_signal(m, Artist(name="Team Melon Collie", slug="x")) == 1.0
    assert name_signal(m, Artist(name="meloncolliestudios", slug="x")) == 1.0


def test_a_containment_match_is_a_hint_not_a_match():
    m = _m(display_name="Maewix Studios", details={})
    got = name_signal(m, Artist(name="Maewix", slug="x"))
    assert 0 < got < 1.0


def test_a_short_slug_does_not_match_by_containment():
    """A 3-character slug is inside a great many longer ones — containment
    there is a coincidence generator, not a signal."""
    m = _m(display_name="Artgirl Studios", details={})
    assert name_signal(m, Artist(name="art", slug="art")) == 0.0


def test_unrelated_names_do_not_match():
    m = _m(display_name="Maewix", details={})
    assert name_signal(m, Artist(name="Floppystack", slug="x")) == 0.0


def test_the_declaration_reads_through_an_anchor_href():
    """These links live in an `href`, and html_to_plain discards attributes —
    the trap that already caught E5's invite detection."""
    body = '<p>Support me: <a href="https://www.patreon.com/maewix">here</a></p>'
    assert declared_signal(body, "maewix") == 1.0


def test_the_declaration_is_specific_to_THIS_membership():
    """A creator linking SOMEONE ELSE's Patreon must not link the two."""
    body = '<a href="https://www.patreon.com/someoneelse">a friend</a>'
    assert declared_signal(body, "maewix") == 0.0


def test_the_declaration_tolerates_the_c_and_cw_url_variants():
    """Patreon serves /c/<vanity> and /cw/<vanity> per campaign (#3886)."""
    assert declared_signal("see https://www.patreon.com/c/maewix", "maewix") == 1.0
    assert declared_signal("see https://www.patreon.com/cw/maewix", "maewix") == 1.0


# --- end to end ------------------------------------------------------------


async def _artist_with_discord(db, name, slug):
    a = Artist(name=name, slug=slug)
    db.add(a)
    await db.flush()
    db.add(Source(
        artist_id=a.id, platform="discord",
        url=f"https://discord.com/channels/1/{slug}", enabled=True,
    ))
    await db.flush()
    return a


@pytest.mark.asyncio
async def test_a_matching_name_proposes_the_link(db):
    artist = await _artist_with_discord(db, "Maewix", "maewix")
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    made = await ArtistMembershipService(db).match_membership(m.id)
    await db.commit()
    assert made == 1

    s = (await db.execute(select(ArtistMembershipSuggestion))).scalar_one()
    assert s.artist_id == artist.id
    assert s.status == "pending", "nothing is linked without the operator"


@pytest.mark.asyncio
async def test_an_artist_already_on_that_platform_is_never_proposed(db):
    """The link exists; a suggestion would be noise."""
    artist = await _artist_with_discord(db, "Maewix", "maewix")
    db.add(Source(
        artist_id=artist.id, platform="patreon",
        url="https://www.patreon.com/maewix", enabled=True,
    ))
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    assert await ArtistMembershipService(db).match_membership(m.id) == 0


@pytest.mark.asyncio
async def test_a_membership_already_tracked_elsewhere_is_never_proposed(db):
    """C4's shared identity join, used here as the NEGATIVE check.

    A membership FC already has a source for is tracked — even when that source
    sits under a DIFFERENT artist — and proposing it to this one would be the
    wrong link this service exists to avoid. `_candidate_artists` cannot see
    this on its own: it only knows whether the artist in front of it has a
    source on the platform, not whether someone else already does.
    """
    await _artist_with_discord(db, "Maewix", "maewix")
    other = Artist(name="Someone Else", slug="someoneelse")
    db.add(other)
    await db.flush()
    db.add(Source(
        artist_id=other.id, platform="patreon",
        url="https://www.patreon.com/maewix", enabled=True,
    ))
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    assert await ArtistMembershipService(db).match_membership(m.id) == 0


@pytest.mark.asyncio
async def test_an_artist_with_no_sources_at_all_is_never_proposed(db):
    """Not a creator FC follows through another channel, which is the whole
    case this step is about."""
    a = Artist(name="Maewix", slug="maewix")
    db.add(a)
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    assert await ArtistMembershipService(db).match_membership(m.id) == 0


@pytest.mark.asyncio
async def test_a_weak_name_needs_the_declaration(db):
    artist = await _artist_with_discord(db, "Maewix", "maewix")
    # BOTH identity fields must be weak, or the test contradicts itself: the
    # first draft left the default vanity exactly matching the artist slug, so
    # the name signal was legitimately 1.0 and the code was right to propose.
    # CI caught it — a test bug, not a code bug.
    m = await _membership(
        db, display_name="Maewix Studios Official",
        details={"campaign": {"vanity": "maewixstudios"}},
        url="https://www.patreon.com/maewixstudios",
    )
    await db.commit()
    assert await ArtistMembershipService(db).match_membership(m.id) == 0

    db.add(Post(
        artist_id=artist.id, source_id=None, external_post_id="p1",
        description='<a href="https://www.patreon.com/maewixstudios">mine</a>',
        post_date=datetime.now(UTC),
    ))
    await db.commit()
    assert await ArtistMembershipService(db).match_membership(m.id) == 1


@pytest.mark.asyncio
async def test_accepting_adds_a_source_and_never_merges_artists(db):
    """THE safety property. Adding a source is trivially undone; a wrong merge
    mixes two creators' work with nothing left to separate them by."""
    artist = await _artist_with_discord(db, "Maewix", "maewix")
    m = await _membership(db, display_name="Maewix")
    await db.commit()
    artists_before = len((await db.execute(select(Artist))).scalars().all())

    svc = ArtistMembershipService(db)
    await svc.match_membership(m.id)
    await db.commit()
    s = (await db.execute(select(ArtistMembershipSuggestion))).scalar_one()

    result = await svc.accept(s.id)
    await db.commit()
    assert result["status"] == "linked"

    sources = (await db.execute(
        select(Source).where(Source.artist_id == artist.id)
    )).scalars().all()
    assert {x.platform for x in sources} == {"discord", "patreon"}
    assert len((await db.execute(select(Artist))).scalars().all()) == artists_before, (
        "no artist may be created or destroyed by accepting"
    )


@pytest.mark.asyncio
async def test_accepting_twice_does_not_add_a_second_source(db):
    """A source appearing between the proposal and the click is the operator
    having done it by hand — not an error."""
    artist = await _artist_with_discord(db, "Maewix", "maewix")
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    svc = ArtistMembershipService(db)
    await svc.match_membership(m.id)
    await db.commit()
    s = (await db.execute(select(ArtistMembershipSuggestion))).scalar_one()

    await svc.accept(s.id)
    await db.commit()
    second = await svc.accept(s.id)
    await db.commit()
    assert "already_linked" in second

    sources = (await db.execute(
        select(Source).where(
            Source.artist_id == artist.id, Source.platform == "patreon",
        )
    )).scalars().all()
    assert len(sources) == 1


@pytest.mark.asyncio
async def test_a_dismissed_pair_is_never_proposed_again(db):
    await _artist_with_discord(db, "Maewix", "maewix")
    m = await _membership(db, display_name="Maewix")
    await db.commit()

    svc = ArtistMembershipService(db)
    assert await svc.match_membership(m.id) == 1
    await db.commit()
    s = (await db.execute(select(ArtistMembershipSuggestion))).scalar_one()
    await svc.dismiss(s.id)
    await db.commit()

    assert await svc.match_membership(m.id) == 0
    await db.commit()
    rows = (await db.execute(select(ArtistMembershipSuggestion))).scalars().all()
    assert len(rows) == 1 and rows[0].status == "dismissed"


@pytest.mark.asyncio
async def test_the_vanity_falls_back_to_the_url_when_details_lack_it(db):
    """C1 modelled the roster before any platform was characterised, so the
    vanity lives in `details` rather than a column — and must still be findable
    for a row written before that field was understood."""
    m = await _membership(
        db, display_name="Something Else", details={},
        url="https://www.patreon.com/maewix",
    )
    assert m.vanity_or_none() == "maewix"