"""The learned membership roster: what the account actually subscribes to.

Milestone 387, phase C. Sibling of `service_roster` (milestone 365) and built
on the same insight — an absence is only observable against a record of
presence. There, a stopped worker; here, a subscription that lapsed.

## Nothing calls this yet

`touch_membership` is written before its caller because the caller (the sweep,
C3) needs a client seam (C2) that needs Patreon's real response characterised
from a captured sample (C0), and that capture needs the operator's browser
session. The write side does not depend on any of it: an upsert keyed on
(platform, external_campaign_id) is the same regardless of what the payload
turns out to look like, and `details` carries whatever C0 finds.

## Why the whitelist lives here and not in the column

`platform_membership.status` is an unconstrained String holding the PLATFORM's
own word — `active_patron`, not some normalised FC value. The mapping from
those words to FC's meaning is a read-site concern and belongs in code that can
be corrected without a migration, because the vocabulary comes from whatever
each platform says and will be discovered per platform rather than designed up
front. `MEMBERSHIP_STATUS` below is a place for that knowledge to accumulate as
platforms are characterised; it is deliberately empty of guesses today.
"""

from __future__ import annotations

import logging

from collections.abc import Awaitable, Callable
from datetime import UTC, datetime, timedelta

from sqlalchemy import func, select
from sqlalchemy.dialects.postgresql import insert as pg_insert
from sqlalchemy.ext.asyncio import AsyncSession

from ..models import MembershipSync, PlatformMembership

log = logging.getLogger(__name__)

# Platform word -> whether the account currently has paid access.
#
# Every entry here must come from a CHARACTERISED response, never from API docs
# or a plausible guess — project rule 130, and inventing a status before seeing
# it in a real payload is exactly the failure it names.
#
# patreon: from a live capture of the operator's own session, 2026-09-10
# (Scribe note #3886). Only two values were OBSERVED in `patron_status` and
# only those two are here.
#
# `declined_patron` is deliberately ABSENT even though it looks obviously
# right. It appears in the request's `filter[membership_type]`, and the capture
# proved that filter is NOT the same vocabulary as the attribute — a row
# selected by the filter as `free_member` came back with
# `patron_status: former_patron`, a word the filter does not contain. Reading
# the filter as an enum is the specific mistake the capture caught; adding
# `declined_patron` on the strength of it would be repeating that mistake one
# step later.
#
# Unknown words are NOT an error: an unrecognised status means the roster
# records evidence it cannot yet interpret, which is a better state than
# dropping the row or asserting a meaning for it.
MEMBERSHIP_STATUS: dict[str, dict[str, bool]] = {
    "patreon": {
        "active_patron": True,
        "former_patron": False,
    },
}


def has_paid_access(
    platform: str, status: str | None, *, is_free_member: bool = False,
) -> bool | None:
    """Does this membership mean the account currently PAYS for access?

    Returns None for a status this code has not been taught, which callers must
    treat as "unknown" rather than as False. The difference matters: False says
    the operator has lost access, and asserting that from an unrecognised word
    would tell them to cancel a source they are still paying for.

    `is_free_member` is a second axis, not a status, and that is Patreon's
    design rather than ours: the capture shows a free follow expressed as a
    boolean alongside `patron_status`, so a "current" membership can still be
    one nobody is paying for. Taking status alone would report a free follower
    as a paying patron, and C4 would then never offer to clean it up.

    (Honest limit: the capture contains no ACTIVE free member, so it cannot
    demonstrate the two axes coming apart. The separation is what the payload's
    shape says; the sample only shows it is possible, not that it happens.)
    """
    if status is None:
        return None
    known = MEMBERSHIP_STATUS.get(platform, {}).get(status)
    if known is None:
        return None
    if not known:
        return False
    return not is_free_member


async def touch_membership(
    session: AsyncSession,
    *,
    platform: str,
    external_campaign_id: str,
    display_name: str | None = None,
    url: str | None = None,
    status: str | None = None,
    tier_names: list | None = None,
    amount_cents: int | None = None,
    currency: str | None = None,
    details: dict | None = None,
) -> None:
    """Record that this membership was observed just now.

    Upsert rather than read-modify-write, for the same reason as
    `service_roster.touch_service`: a sweep may overlap its own previous run,
    and the last writer is simply the most recent sighting.

    `first_seen_at` is deliberately NOT in the update set. It is the one field
    that answers "has this ever been true", which is what makes a membership's
    later DISAPPEARANCE readable as a lapse rather than indistinguishable from
    a creator FC never knew about. Every other column is last-writer-wins,
    including status — a membership that goes from active to former must move.
    """
    stmt = pg_insert(PlatformMembership).values(
        platform=platform,
        external_campaign_id=external_campaign_id,
        display_name=display_name,
        url=url,
        status=status,
        tier_names=tier_names,
        amount_cents=amount_cents,
        currency=currency,
        details=details or {},
    )
    stmt = stmt.on_conflict_do_update(
        constraint="uq_platform_membership_platform_campaign",
        set_={
            "display_name": stmt.excluded.display_name,
            "url": stmt.excluded.url,
            "status": stmt.excluded.status,
            "tier_names": stmt.excluded.tier_names,
            "amount_cents": stmt.excluded.amount_cents,
            "currency": stmt.excluded.currency,
            "details": stmt.excluded.details,
            "last_seen_at": func.now(),
        },
    )
    await session.execute(stmt)


# ---------------------------------------------------------------------------
# The sweep, and the state that makes its failures readable (#387 C3)
# ---------------------------------------------------------------------------
#
# How long a successful sync stays trustworthy. Beyond this the roster is
# STALE, and C4 must refuse to draw conclusions from it — "you are tracking 12
# sources you no longer subscribe to", computed from a roster that stopped
# syncing a week ago, is an invitation to cancel things the operator is still
# paying for.
#
# Generous relative to the daily cadence: a few missed runs are a blip, not a
# reason to stop trusting a roster that changes on a billing cycle.
ROSTER_STALE_AFTER = timedelta(days=3)


async def get_sync_state(session: AsyncSession, platform: str) -> MembershipSync | None:
    return (await session.execute(
        select(MembershipSync).where(MembershipSync.platform == platform)
    )).scalar_one_or_none()


def roster_is_fresh(state: MembershipSync | None, *, now: datetime | None = None) -> bool:
    """May a caller draw CONCLUSIONS from this roster?

    False for never-synced and for stale, and those are deliberately the same
    answer here even though the UI must tell them apart: both mean the roster
    is not evidence. The asymmetry that matters is that `False` never means
    "you subscribe to nothing" — it means "we do not know", and a caller that
    cannot represent "we do not know" must not be asking this question.
    """
    if state is None or state.last_success_at is None:
        return False
    now = now or datetime.now(UTC)
    return (now - state.last_success_at) <= ROSTER_STALE_AFTER


async def _record_sync(session: AsyncSession, platform: str, **values) -> None:
    stmt = pg_insert(MembershipSync).values(platform=platform, **values)
    await session.execute(stmt.on_conflict_do_update(
        constraint="uq_membership_sync_platform",
        set_={**values, "updated_at": func.now()},
    ))


async def sync_platform(
    session: AsyncSession,
    *,
    platform: str,
    fetch: Callable[[], Awaitable[list]],
    now: datetime | None = None,
) -> dict:
    """Walk one platform's roster and record what happened.

    `fetch` is injected rather than built here so the error-to-state mapping —
    the part with the consequences — is testable without a credential, and so
    this service needs to know nothing about how any particular client is
    constructed.

    THE FETCH COMPLETES BEFORE ANYTHING IS WRITTEN. That ordering is the whole
    safety property: a walk that dies half way through pagination writes
    nothing, so a failure can never leave a roster that is partly this week's
    and partly last week's. (`touch_membership` never deletes, so a failure
    cannot empty the roster either — but "intact" should mean intact, not
    merely non-empty.)

    Returns a summary dict; never raises for a platform failure, because one
    platform failing must not abort the others.
    """
    now = now or datetime.now(UTC)
    await _record_sync(session, platform, last_attempt_at=now)
    await session.commit()

    try:
        memberships = await fetch()
    except Exception as exc:  # noqa: BLE001 - deliberately broad, see below
        # Broad on purpose: a sweep is a background job, and ANY escape here
        # kills the run for every other platform too. The exception's class
        # name is recorded so the distinction the client drew (auth vs drift
        # vs transport) survives into the UI, which is where it is actionable.
        #
        # EXCEPT the worker asking us to stop. Celery raises its soft time
        # limit as an ordinary Exception subclass, so a broad catch swallows
        # the shutdown request and lets the sweep run on into the HARD limit,
        # where it is SIGKILLed mid-transaction. A sweep that cannot be stopped
        # is worse than one that fails. (KeyboardInterrupt and SystemExit are
        # BaseException and pass through this clause already.)
        from celery.exceptions import SoftTimeLimitExceeded

        if isinstance(exc, SoftTimeLimitExceeded):
            raise
        await session.rollback()
        await _record_sync(
            session, platform,
            last_error_type=type(exc).__name__,
            last_error_message=str(exc)[:2000],
        )
        await session.commit()
        log.warning("membership sync failed for %s: %s", platform, exc)
        return {"platform": platform, "ok": False, "error": type(exc).__name__}

    for m in memberships:
        await touch_membership(
            session,
            platform=platform,
            external_campaign_id=m.campaign_id,
            display_name=m.display_name,
            url=m.url,
            status=m.status,
            tier_names=m.tier_names or None,
            amount_cents=m.amount_cents,
            currency=m.currency,
            details={**(m.details or {}), "is_free_member": m.is_free_member},
        )
    await _record_sync(
        session, platform,
        last_success_at=now,
        last_count=len(memberships),
        # Cleared on success — a stale error beside a fresh success would read
        # as "still broken" forever.
        last_error_type=None,
        last_error_message=None,
    )
    await session.commit()
    log.info("membership sync ok for %s: %d membership(s)", platform, len(memberships))
    return {"platform": platform, "ok": True, "count": len(memberships)}