infrasynth-backend-kit/infrasynth/files/scanner.py
jcv-dev 551b42eab5 feat: production-hardening pass across the kit
Close the gaps between the documented contract (API-STANDARD, TENANCY,
ENTITLEMENTS) and the implementation, and remove committed build artifacts.

Security:
- verify + process inbound webhooks (HMAC/handler verify, size limit,
  timestamp tolerance, idempotency via InboundEvent.external_id)
- real 2FA login flow (pre-auth challenge; tokens only after verify/recovery)
- wire HybridPermission into security/audit views; add API-key rotate and
  users/<id>/permissions|roles endpoints
- tenant-scoped throttling on by default; webhook replay protection
- verify MercadoPago webhook signatures
- login brute-force guard, configurable password policy, real ALTCHA PoW

Correctness:
- apply verified billing webhooks idempotently (subscription/entitlement/
  invoice/PaymentTransaction); scheduled payment lifecycle jobs
- capture audit update diffs automatically; add audit retention purge
- working notification retries, per-channel rate limits, log retention
- pluggable virus scanner, upload-size limit, pipeline toggle
- feature rollout %/environment targeting; settings-driven registrations
- workflow guards (instance cap, route depth, self-assignment, clone on re-entry)
- wire every previously-dead INFRASYNTH_* setting; drop truly dead ones

Delivery:
- README + CHANGELOG; CI format check + coverage gate
- keep test media out of the tree; untrack .coverage, __pycache__,
  egg-info, docs/ and invoice artifacts
2026-09-24 10:41:21 -05:00

83 lines
2.9 KiB
Python

"""Pluggable virus scanning for uploaded files.
Configured via ``INFRASYNTH_FILES``:
* ``VIRUS_SCANNER``: ``"noop"`` (default) or ``"clamav"``.
* ``CLAMAV_SOCKET``: ``clamd`` socket path or ``host:port`` (when ``clamav``).
* ``REQUIRE_VIRUS_SCAN``: when ``True``, a ``noop`` scanner is rejected at call
time so a production deployment cannot silently skip scanning.
A custom scanner is any object with ``scan(data: bytes) -> ScanResult``; set
``VIRUS_SCANNER`` to its dotted path and it is imported on demand.
"""
from __future__ import annotations
import io
from dataclasses import dataclass
from typing import Protocol, runtime_checkable
from django.core.exceptions import ImproperlyConfigured
from infrasynth.shared.settings_utils import get_setting
__all__ = ["ScanResult", "VirusScanner", "NoOpScanner", "ClamAVScanner", "get_scanner"]
@dataclass(frozen=True)
class ScanResult:
clean: bool
threat: str = ""
scanner: str = ""
@runtime_checkable
class VirusScanner(Protocol):
def scan(self, data: bytes) -> ScanResult: ...
class NoOpScanner:
"""Pass-through scanner. Explicit, logged, and refused when required."""
name = "noop"
def scan(self, data: bytes) -> ScanResult:
if get_setting("INFRASYNTH_FILES", "REQUIRE_VIRUS_SCAN", False):
raise ImproperlyConfigured("REQUIRE_VIRUS_SCAN is enabled but no virus scanner is configured.")
return ScanResult(clean=True, scanner=self.name)
class ClamAVScanner:
"""ClamAV scanner over a Unix socket or a TCP endpoint (needs ``clamd``)."""
name = "clamav"
def __init__(self, socket: str | None = None):
try:
import clamd # type: ignore[import-not-found]
except ImportError as exc: # pragma: no cover - optional dependency
raise ImproperlyConfigured("VIRUS_SCANNER='clamav' requires the 'clamd' package to be installed.") from exc
socket = socket or get_setting("INFRASYNTH_FILES", "CLAMAV_SOCKET", "/var/run/clamav/clamd.ctl")
if ":" in socket and not socket.startswith("/"):
host, port = socket.rsplit(":", 1)
self._client = clamd.ClamdNetworkSocket(host=host, port=int(port))
else:
self._client = clamd.ClamdUnixSocket(path=socket)
def scan(self, data: bytes) -> ScanResult:
result = self._client.instream(io.BytesIO(data))
status, signature = result.get("stream", ("ERROR", "unknown"))
if status == "OK":
return ScanResult(clean=True, scanner=self.name)
return ScanResult(clean=False, threat=signature or "unknown threat", scanner=self.name)
def get_scanner() -> VirusScanner:
configured = get_setting("INFRASYNTH_FILES", "VIRUS_SCANNER", "noop")
if configured in ("noop", None):
return NoOpScanner()
if configured == "clamav":
return ClamAVScanner()
from django.utils.module_loading import import_string
return import_string(configured)()