webmail-client/plugins/webmail_plugin_antispam/webmail_plugin_antispam/policy.py

"""Settings and allow/deny rules — the policy half of classification (SPEC §C.3).

Kept apart from the hook so the decision logic is testable without a database or
an engine: :func:`decide` is a pure function of (rules, score, thresholds).
"""

from __future__ import annotations

import uuid
from dataclasses import dataclass
from typing import Any

from sqlalchemy import text

from app.plugins.sdk import sdk

_SDK = sdk("antispam")

# §C.3 defaults, used when a user has never opened the settings page.
DEFAULTS = {
    "enabled_accounts": [],  # empty = every account
    "move_threshold": 12.0,
    "banner_threshold": 6.0,
    "network_checks": False,
    "learn_from_provider_junk": True,
}


@dataclass(frozen=True)
class Settings:
    enabled_accounts: list[str]
    move_threshold: float
    banner_threshold: float
    network_checks: bool
    learn_from_provider_junk: bool

    def covers(self, account_id: str) -> bool:
        """Empty list means every account — the common case stays cheap."""
        return not self.enabled_accounts or account_id in self.enabled_accounts


async def load_settings(user_id: uuid.UUID) -> Settings:
    async with _SDK.session(user_id) as s:
        row = (
            await s.execute(
                text(
                    "SELECT enabled_accounts, move_threshold, banner_threshold, "
                    "network_checks, learn_from_provider_junk "
                    "FROM plg_antispam_settings WHERE user_id = :u"
                ),
                {"u": str(user_id)},
            )
        ).first()
    if row is None:
        d: Any = DEFAULTS
        return Settings(
            enabled_accounts=[],
            move_threshold=d["move_threshold"],
            banner_threshold=d["banner_threshold"],
            network_checks=d["network_checks"],
            learn_from_provider_junk=d["learn_from_provider_junk"],
        )
    return Settings(
        enabled_accounts=[str(a) for a in (row[0] or [])],
        move_threshold=float(row[1]),
        banner_threshold=float(row[2]),
        network_checks=bool(row[3]),
        learn_from_provider_junk=bool(row[4]),
    )


async def load_rules(user_id: uuid.UUID) -> dict[str, set[str]]:
    """``{"allow": {...}, "deny": {...}}`` of lower-cased patterns."""
    async with _SDK.session(user_id) as s:
        rows = (
            await s.execute(
                text("SELECT kind, pattern FROM plg_antispam_rules WHERE user_id = :u"),
                {"u": str(user_id)},
            )
        ).all()
    out: dict[str, set[str]] = {"allow": set(), "deny": set()}
    for kind, pattern in rows:
        if kind in out:
            out[kind].add(str(pattern).strip().lower())
    return out


async def sender_in_contacts(user_id: uuid.UUID, email: str) -> bool:
    """Is this sender in the user's address book?

    Someone you have deliberately saved is not someone whose mail should vanish
    into Junk — so a contact caps the verdict at a banner (see :func:`decide`).

    Reads the contacts plugin's table directly. Cross-plugin, and deliberately
    forgiving: if that plugin is not installed the table does not exist, which is
    not an error here, just "no contacts to check". The addresses are stored as
    the user typed them, so both sides are lower-cased rather than relying on the
    jsonb containment index.
    """
    addr = (email or "").strip().lower()
    if not addr:
        return False
    try:
        async with _SDK.session(user_id) as s:
            row = (
                await s.execute(
                    text(
                        "SELECT 1 FROM plg_contacts_contacts "
                        "WHERE user_id = :u AND ("
                        "  lower(default_email) = :e "
                        "  OR EXISTS (SELECT 1 FROM jsonb_array_elements(emails) AS x "
                        "             WHERE lower(x->>'value') = :e)) "
                        "LIMIT 1"
                    ),
                    {"u": str(user_id), "e": addr},
                )
            ).first()
        return row is not None
    except Exception:  # noqa: BLE001 - contacts plugin absent, or its schema moved
        return False


def matches(patterns: set[str], email: str) -> bool:
    """A pattern is either a whole address or ``@domain`` for everyone there."""
    addr = (email or "").strip().lower()
    if not addr:
        return False
    if addr in patterns:
        return True
    _, _, domain = addr.partition("@")
    return bool(domain) and f"@{domain}" in patterns


def decide(
    *,
    sender: str,
    rules: dict[str, set[str]],
    score: float | None,
    settings: Settings,
    contact: bool = False,
) -> str:
    """The §C.4 decision, in order. Returns the verdict action.

    Deny beats allow beats engine: an explicit user rule is a statement about a
    sender that no score should override. ``score is None`` means the engine
    could not be reached — fail open, deliver as ``none``.

    ``contact`` (the sender is in the user's address book) caps the outcome at a
    banner: their mail is never moved to Junk. Not silenced entirely, because the
    way this goes wrong in practice is a contact's account being compromised and
    spamming its own address book — the user still deserves the warning. An
    explicit deny rule still wins: that is the user overruling us on purpose.
    """
    if matches(rules["deny"], sender):
        return "deny_listed"
    if matches(rules["allow"], sender):
        return "allow_listed"
    if score is None:
        return "none"
    if score >= settings.move_threshold:
        return "banner" if contact else "moved"
    if score >= settings.banner_threshold:
        return "banner"
    return "none"