Files
DECNET/decnet/web/ingester.py
anti 035499f255 feat: add component-aware RFC 5424 application logging system
- Modify Rfc5424Formatter to read decnet_component from LogRecord
  and use it as RFC 5424 APP-NAME field (falls back to 'decnet')
- Add get_logger(component) factory in decnet/logging/__init__.py
  with _ComponentFilter that injects decnet_component on each record
- Wire all five layers to their component tag:
    cli -> 'cli', engine -> 'engine', api -> 'api' (api.py, ingester,
    routers), mutator -> 'mutator', collector -> 'collector'
- Add structured INFO/DEBUG/WARNING/ERROR log calls throughout each
  layer per the defined vocabulary; DEBUG calls are suppressed unless
  DECNET_DEVELOPER=true
- Add tests/test_logging.py covering factory, filter, formatter
  component-awareness, fallback behaviour, and level gating
2026-04-13 07:39:01 -04:00

101 lines
3.5 KiB
Python

import asyncio
import os
import json
from typing import Any
from pathlib import Path
from decnet.logging import get_logger
from decnet.web.db.repository import BaseRepository
logger = get_logger("api")
async def log_ingestion_worker(repo: BaseRepository) -> None:
"""
Background task that tails the DECNET_INGEST_LOG_FILE.json and
inserts structured JSON logs into the SQLite repository.
"""
_base_log_file: str | None = os.environ.get("DECNET_INGEST_LOG_FILE")
if not _base_log_file:
logger.warning("DECNET_INGEST_LOG_FILE not set. Log ingestion disabled.")
return
_json_log_path: Path = Path(_base_log_file).with_suffix(".json")
_position: int = 0
logger.info("ingest worker started path=%s", _json_log_path)
while True:
try:
if not _json_log_path.exists():
await asyncio.sleep(2)
continue
_stat: os.stat_result = _json_log_path.stat()
if _stat.st_size < _position:
# File rotated or truncated
_position = 0
if _stat.st_size == _position:
# No new data
await asyncio.sleep(1)
continue
with open(_json_log_path, "r", encoding="utf-8", errors="replace") as _f:
_f.seek(_position)
while True:
_line: str = _f.readline()
if not _line:
break # EOF reached
if not _line.endswith('\n'):
# Partial line read, don't process yet, don't advance position
break
try:
_log_data: dict[str, Any] = json.loads(_line.strip())
logger.debug("ingest: record decky=%s event_type=%s", _log_data.get("decky"), _log_data.get("event_type"))
await repo.add_log(_log_data)
await _extract_bounty(repo, _log_data)
except json.JSONDecodeError:
logger.error("ingest: failed to decode JSON log line: %s", _line.strip())
continue
# Update position after successful line read
_position = _f.tell()
except Exception as _e:
_err_str = str(_e).lower()
if "no such table" in _err_str or "no active connection" in _err_str or "connection closed" in _err_str:
logger.error("ingest: post-shutdown or fatal DB error: %s", _e)
break # Exit worker — DB is gone or uninitialized
logger.error("ingest: error in worker: %s", _e)
await asyncio.sleep(5)
await asyncio.sleep(1)
async def _extract_bounty(repo: BaseRepository, log_data: dict[str, Any]) -> None:
"""Detect and extract valuable artifacts (bounties) from log entries."""
_fields = log_data.get("fields")
if not isinstance(_fields, dict):
return
# 1. Credentials (User/Pass)
_user = _fields.get("username")
_pass = _fields.get("password")
if _user and _pass:
await repo.add_bounty({
"decky": log_data.get("decky"),
"service": log_data.get("service"),
"attacker_ip": log_data.get("attacker_ip"),
"bounty_type": "credential",
"payload": {
"username": _user,
"password": _pass
}
})
# 2. Add more extractors here later (e.g. file hashes, crypto keys)