FabledCurator/tests/test_gated_reason.py

"""Milestone 387 C5: why the posts are invisible, in the roster's own words.

A3 gave a tier-gated source a count — "47 posts you can't see". The roster can
turn that into a reason, and the whole risk of this step is that a reason is a
much stronger claim than a count. So most of what follows pins refusals:

* an unrecognised status says NOTHING rather than guessing lapsed;
* a campaign absent from the roster says nothing, because absence is not
  evidence (the same discipline as `test_post_is_gated_only_on_explicit_false`);
* a stale roster degrades to the bare count rather than asserting last week's
  reason as today's;
* a current FREE follower is not told they used to be a patron.

And the one that matters most: no fetch path can read the roster at all. That
is asserted structurally, not by inspection — the roster explains a skip that
already happened, and must never be able to cause one.
"""
from __future__ import annotations

import ast
from datetime import timedelta
from pathlib import Path

import pytest

from backend.app.models import Artist, Source
from backend.app.services.download_result import ErrorType
from backend.app.services.membership_roster import (
    GATED_FREE,
    GATED_LAPSED,
    GATED_TIER,
    ROSTER_STALE_AFTER,
    gated_reason,
    gated_reasons_for_sources,
)
from tests.roster_builders import membership as _membership
from tests.roster_builders import synced as _synced

# --- the pure mapping: status word -> the words we are entitled to say -------
#
# No database, so these run in the unit lane. `gated_reason` is where the claim
# is actually decided; everything below it is plumbing.


def test_a_former_patron_is_told_the_membership_ended():
    assert gated_reason("patreon", "former_patron") == GATED_LAPSED


def test_an_active_patron_is_told_the_tier_does_not_reach_these_posts():
    assert gated_reason("patreon", "active_patron") == GATED_TIER


def test_a_current_free_follower_is_not_told_they_used_to_be_a_patron():
    """`free` and `lapsed` are different states and must not share a sentence.

    Both make `has_paid_access` False, which is why the reason is derived from
    the status axis first rather than from that boolean: "you're not a patron
    any more" is a false statement about someone who never was one.
    """
    assert gated_reason("patreon", "active_patron", is_free_member=True) == GATED_FREE
    assert gated_reason("patreon", "former_patron", is_free_member=True) == GATED_LAPSED


@pytest.mark.parametrize("status", [None, "declined_patron", "", "wat"])
def test_an_unrecognised_status_says_nothing(status):
    """Unknown is not lapsed.

    `declined_patron` is in here on purpose: it is the plausible-looking word
    the C0 capture proved is NOT in the `patron_status` vocabulary. If someone
    adds it to MEMBERSHIP_STATUS on the strength of the request filter, this
    test is where that shows up.
    """
    assert gated_reason("patreon", status) is None


def test_a_platform_that_has_never_been_characterised_says_nothing():
    """An uncharacterised platform inherits silence, not a Patreon guess.

    This named SubscribeStar until D1 characterised it (note #3989). Left as it
    was, it would have kept passing only because `active_patron` is not a
    SubscribeStar word, testing nothing its name claims.
    """
    assert gated_reason("hentaifoundry", "active_patron") is None


def test_subscribestar_explains_the_gate_in_its_own_words():
    """SubscribeStar's status is which table the creator sits in, and those
    identifiers reach the same three reasons as Patreon's words."""
    assert gated_reason("subscribestar", "active_subscriptions") == GATED_TIER
    assert gated_reason("subscribestar", "cancelled_subscriptions") == GATED_LAPSED
    # Patreon's vocabulary does not leak across platforms.
    assert gated_reason("subscribestar", "former_patron") is None


# --- the join, against the database ----------------------------------------


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


async def _gated_source(db, artist, *, url="https://www.patreon.com/maewix",
                        platform="patreon", overrides=None):
    s = Source(
        artist_id=artist.id, platform=platform, url=url, enabled=True,
        error_type=ErrorType.TIER_LIMITED, config_overrides=overrides,
    )
    db.add(s)
    await db.flush()
    return s


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_matched_active_membership_explains_the_gate(db):
    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db)
    await _synced(db)

    assert await gated_reasons_for_sources(db, [source]) == {source.id: GATED_TIER}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_lapsed_membership_explains_the_gate(db):
    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db, status="former_patron")
    await _synced(db)

    assert await gated_reasons_for_sources(db, [source]) == {source.id: GATED_LAPSED}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_campaign_absent_from_the_roster_adds_no_words(db):
    """The third case in the step: absence is not evidence.

    The sweep succeeded an hour ago and this creator is simply not in it. That
    could mean the subscription lapsed — or that the sweep's pagination is
    incomplete, or that the creator renamed. The count stands alone.
    """
    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db, campaign="somebody-else",
                      url="https://www.patreon.com/someoneelse",
                      details={"campaign": {"vanity": "someoneelse"}})
    await _synced(db)

    assert await gated_reasons_for_sources(db, [source]) == {}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_stale_roster_degrades_to_the_bare_count(db):
    """Same data as the passing case, one stale sync state.

    A reason is a claim about NOW. Last week's roster cannot make it.
    """
    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db, status="former_patron")
    await _synced(db, ago=ROSTER_STALE_AFTER + timedelta(hours=1))

    assert await gated_reasons_for_sources(db, [source]) == {}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_never_synced_platform_degrades_to_the_bare_count(db):
    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db, status="former_patron")
    # No MembershipSync row at all.

    assert await gated_reasons_for_sources(db, [source]) == {}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_one_platforms_fresh_sweep_does_not_vouch_for_anothers(db):
    """Freshness is per platform, so a working Patreon sweep cannot lend its
    credibility to a SubscribeStar roster that has never run (D1's future)."""
    artist = await _artist(db)
    patreon = await _gated_source(db, artist)
    other = await _gated_source(
        db, artist, platform="subscribestar",
        url="https://subscribestar.adult/maewix",
    )
    await _membership(db, status="former_patron")
    # SubscribeStar's REAL word, so that the freshness gate is the only thing
    # excluding this membership. With a Patreon word (as this test first had),
    # the vocabulary excluded it and removing the gate would have left it green.
    await _membership(db, platform="subscribestar", campaign="s1",
                      status="cancelled_subscriptions",
                      url="https://subscribestar.adult/maewix",
                      details={"campaign": {"vanity": "maewix"}})
    await _synced(db)  # patreon only

    reasons = await gated_reasons_for_sources(db, [patreon, other])
    assert reasons == {patreon.id: GATED_LAPSED}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_the_cached_campaign_id_wins_over_a_stale_url(db):
    """Inherited from `match_kind` via the shared join — asserted here so C5
    keeps identity in step with C4 rather than quietly growing its own."""
    artist = await _artist(db)
    source = await _gated_source(
        db, artist, url="https://www.patreon.com/old-handle",
        overrides={"patreon_campaign_id": "c1"},
    )
    await _membership(db, campaign="c1", url="https://www.patreon.com/new-handle",
                      details={"campaign": {"vanity": "new-handle"}},
                      status="former_patron")
    await _synced(db)

    assert await gated_reasons_for_sources(db, [source]) == {source.id: GATED_LAPSED}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_no_sources_asks_the_database_nothing(db):
    assert await gated_reasons_for_sources(db, []) == {}


@pytest.mark.integration
@pytest.mark.asyncio
async def test_the_source_list_carries_the_reason_to_the_ui(db):
    """End to end through `SourceService.list`, because the field being on the
    record is not the same as the field reaching the payload."""
    from backend.app.services.source_service import SourceService

    artist = await _artist(db)
    source = await _gated_source(db, artist)
    await _membership(db, status="former_patron")
    await _synced(db)
    await db.commit()

    records = await SourceService(db).list()
    row = next(r.to_dict() for r in records if r.id == source.id)
    assert row["gated_reason"] == GATED_LAPSED


@pytest.mark.integration
@pytest.mark.asyncio
async def test_a_source_that_is_not_gated_gets_no_reason(db):
    """The roster annotates a gated state; it never puts one on a healthy row.

    A source walking fine whose creator the operator stopped paying for has
    nothing to explain — and saying "you're not a patron any more" beside a
    healthy row would be the roster asserting inaccessibility on its own.
    """
    from backend.app.services.source_service import SourceService

    artist = await _artist(db)
    source = Source(
        artist_id=artist.id, platform="patreon", enabled=True,
        url="https://www.patreon.com/maewix", error_type=None,
    )
    db.add(source)
    await db.flush()
    await _membership(db, status="former_patron")
    await _synced(db)
    await db.commit()

    records = await SourceService(db).list()
    row = next(r.to_dict() for r in records if r.id == source.id)
    assert row["gated_reason"] is None
    assert row["tier_gated_count"] is None


# --- the line that must not be crossed --------------------------------------

_APP = Path(__file__).resolve().parents[1] / "backend" / "app"

# The modules that FETCH: the walk, the downloaders, the per-platform clients
# and ingesters. Named as ROOTS of an import walk rather than as the place the
# assertion looks — the check follows their transitive first-party imports, so
# it still holds when the logic inside them moves (rule #167).
_FETCH_ROOTS = [
    "services/download_service.py",
    "services/ingest_core.py",
    "services/native_ingest_common.py",
    "services/gallery_dl.py",
    "services/refetch_service.py",
]

# Reading ANY of these is reading the roster.
_ROSTER_MODULES = {"services.membership_roster", "services.membership_reconcile"}


def _first_party_imports(path: Path) -> set[str]:
    """Every `backend.app.*` module this file imports, as a dotted path
    relative to `backend/app` — absolute and relative forms both."""
    tree = ast.parse(path.read_text())
    # The dotted parts of the package CONTAINING this module. `parts[:-1]` is
    # right for both forms without a special case: `services/foo.py` drops
    # `foo` to leave `services`, and `api/__init__.py` drops `__init__` to
    # leave `api` — which is exactly what `from .` means inside each.
    pkg = path.relative_to(_APP).with_suffix("").parts[:-1]
    out: set[str] = set()
    for node in ast.walk(tree):
        if isinstance(node, ast.ImportFrom):
            if node.level:
                # `from ..models import X` -> walk up from the containing
                # package. Clamped at 0: a level that climbs past `backend.app`
                # leaves this tree, and an unclamped negative index would wrap
                # and silently resolve to the wrong module.
                up = max(len(pkg) - (node.level - 1), 0)
                mod = list(pkg[:up]) + (node.module.split(".") if node.module else [])
            elif node.module and node.module.startswith("backend.app."):
                mod = node.module[len("backend.app."):].split(".")
            else:
                continue
            if not mod:
                # `from . import x` in a module sitting directly under
                # `backend/app` (celery_app.py does this): the package is the
                # app root, so the alias alone is the module's dotted name.
                for alias in node.names:
                    out.add(alias.name)
                continue
            out.add(".".join(mod))
            # `from .membership_roster import x` and
            # `from . import membership_roster` must both resolve to the module.
            for alias in node.names:
                out.add(".".join([*mod, alias.name]))
        elif isinstance(node, ast.Import):
            for alias in node.names:
                if alias.name.startswith("backend.app."):
                    out.add(alias.name[len("backend.app."):])
    return out


def _reachable_from(roots: list[str]) -> set[str]:
    seen: set[str] = set()
    queue = [r[:-3].replace("/", ".") for r in roots]
    while queue:
        mod = queue.pop()
        if mod in seen:
            continue
        seen.add(mod)
        parts = [p for p in mod.split(".") if p]
        if not parts:
            continue
        for candidate in (_APP.joinpath(*parts) / "__init__.py",
                          _APP.joinpath(*parts).with_suffix(".py")):
            if candidate.is_file():
                queue.extend(_first_party_imports(candidate) - seen)
                break
    return seen


def test_the_fetch_roots_all_exist():
    """Falsifiability guard for the guard below.

    A reachability check passes trivially if its roots resolve to nothing, so a
    renamed module would silently turn the real assertion into a no-op that
    still reads as coverage.
    """
    missing = [r for r in _FETCH_ROOTS if not (_APP / r).is_file()]
    assert not missing, f"fetch roots moved or were renamed: {missing}"


# The falsifiability controls. FC runs no local verification (rule #85), so a
# guard cannot be falsified by hand before it is committed — it has to carry its
# own proof that it is capable of failing, and re-prove it on every run. These
# two assert the walker finds roster imports that ARE there, one direct and one
# through a hop, so the real assertion below can never pass merely because the
# walk resolved nothing.


def test_the_walk_sees_a_direct_roster_import():
    """`source_service` legitimately reads the roster — it is what annotates the
    Subscriptions rows. If this stops holding the walker has gone blind, not the
    dependency gone away."""
    assert "services.membership_roster" in _reachable_from(["services/source_service.py"])


def test_the_walk_follows_more_than_one_hop():
    """api/sources.py -> services/source_service.py -> services/membership_roster.py.

    A one-hop walker would pass the guard below on a fetch path that reaches the
    roster through any intermediate module, which is the likeliest way this ever
    actually regresses.
    """
    reachable = _reachable_from(["api/sources.py"])
    assert "services.source_service" in reachable
    assert "services.membership_roster" in reachable


def test_no_fetch_path_can_read_the_roster():
    """The roster explains a skip. It must never be able to cause one.

    Entitled-tier data says which tiers the account holds, not which posts
    those tiers unlock — `current_user_can_view` is the only per-post truth. A
    fetch path that could consult the roster could decide not to fetch
    something the operator is paying for, silently, and that is the worst
    failure available in this milestone.

    Import reachability rather than a call-site scan: a module that cannot
    reach the roster cannot consult it, and unlike a grep for a function name
    this keeps holding when the functions are renamed.
    """
    reachable = _reachable_from(_FETCH_ROOTS)
    assert not (reachable & _ROSTER_MODULES), (
        "a fetch path can now reach the membership roster: "
        f"{sorted(reachable & _ROSTER_MODULES)}. The roster may annotate a "
        "gated state, never produce one — see membership_roster.gated_reason."
    )