f4aa7caaa9
Brings up the documented target architecture as a docker-compose stack — a modular monolith with the Ghidra step split into its own async worker. - worker/: RQ queue (lazy redis import) + run_acquisition task (Job status queued→started→finished/failed, drives ams.acquire with sink=db) - Job model + JobOut schema; Snapshot.data is JSONB on Postgres - POST/GET /jobs: stream an upload to a shared volume, enqueue, poll status - docker/api.Dockerfile (slim) + docker/worker.Dockerfile (JDK21 + Ghidra fetched at build, overridable via GHIDRA_URL) + docker-compose.yml - ghidra.py: AMS_GHIDRA_SCRIPTS override for in-container script path - pyproject: [worker] extra (rq/redis/psycopg), python-multipart in [api] - tests: 4 new (task success/failure + endpoint enqueue/503) -> 22/22 Verified: API image builds, container serves /health + /ui + /jobs; compose config validates. Worker image (downloads ~1 GB Ghidra) not built here. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
56 lines
1.8 KiB
Python
56 lines
1.8 KiB
Python
"""The RQ task body. Runs inside the Ghidra-equipped worker container.
|
|
|
|
It re-points SQLAlchemy at the shared DATABASE_URL (the worker is a separate process
|
|
from the API), drives the acquisition pipeline, and walks the Job row through its
|
|
status transitions so the API/UI can poll progress."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import traceback
|
|
|
|
from ..acquire import acquire
|
|
from ..api.db import configure, get_session, init_db
|
|
from ..api.models import Job
|
|
|
|
|
|
def _set(job_id: int, **fields):
|
|
"""Patch a Job row in its own short-lived session (worker may run far from the API)."""
|
|
db = get_session()
|
|
try:
|
|
job = db.get(Job, job_id)
|
|
if job is None:
|
|
return None
|
|
for k, v in fields.items():
|
|
setattr(job, k, v)
|
|
db.commit()
|
|
return job
|
|
finally:
|
|
db.close()
|
|
|
|
|
|
def run_acquisition(
|
|
job_id: int,
|
|
source_path: str,
|
|
game_name: str | None = None,
|
|
database_url: str | None = None,
|
|
) -> dict:
|
|
"""Acquire `source_path` into the catalog, updating Job #`job_id` as it goes.
|
|
|
|
Returns a small result dict (also stored by RQ). Errors are recorded on the Job row
|
|
and re-raised so RQ marks the job failed."""
|
|
configure(database_url)
|
|
init_db()
|
|
|
|
_set(job_id, status="started", error=None)
|
|
try:
|
|
result = acquire(source_path, game_name, sink="db")
|
|
except Exception as exc: # record then re-raise so RQ sees the failure too
|
|
_set(job_id, status="failed", error="{0}: {1}".format(type(exc).__name__, exc))
|
|
traceback.print_exc()
|
|
raise
|
|
|
|
_set(job_id, status="finished", snapshot_id=result.imported_id,
|
|
dll_name=os.path.basename(result.dll), error=None)
|
|
return {"snapshot_id": result.imported_id, "engine": result.engine, "dll": result.dll}
|