feat: add product archive retention cleanup

This commit is contained in:
2026-09-12 13:55:31 +08:00
parent 87a3d44359
commit da5c2b4503
5 changed files with 595 additions and 24 deletions
+99 -13
View File
@@ -12,6 +12,7 @@ import threading
import time
import uuid
import zipfile
from contextlib import asynccontextmanager
from datetime import datetime, timezone
from pathlib import Path
from typing import Optional
@@ -23,6 +24,7 @@ from PIL import Image, ImageDraw, ImageFont
from core import config as wc_config
from core.fonts import get_cached_font
from .cleanup_service import CleanupReport, CleanupService
from .job_manager import JobManager
from .line_spacing import analyze_svg_line_spacing_file
from .log_config import get_logger
@@ -67,7 +69,7 @@ FONTS_DIR = PROJECT_ROOT / "service_fonts"
DESIGN_TEMPLATES_DIR = PROJECT_ROOT / "service_design_templates"
METADATA_DIR = PROJECT_ROOT / "service_metadata"
ORDERS_DIR = PROJECT_ROOT / "service_orders"
PRODUCT_ARCHIVES_DIR = PROJECT_ROOT / "service_product_archives"
PRODUCT_ARCHIVES_DIR = PROJECT_ROOT / "service_products"
ASSETS_DIR.mkdir(parents=True, exist_ok=True)
PROJECTS_DIR.mkdir(parents=True, exist_ok=True)
FONTS_DIR.mkdir(parents=True, exist_ok=True)
@@ -81,8 +83,19 @@ manager = JobManager(metadata_store)
storage = Storage(WORKSPACE_DIR)
runner = JobRunner(PROJECT_ROOT, manager)
product_archive_store = ProductArchiveStore(PRODUCT_ARCHIVES_DIR / "metadata")
cleanup_service = CleanupService(storage, metadata_store, product_archive_store)
app = FastAPI(title="WordCloud Test Service", version="0.1.0")
@asynccontextmanager
async def _app_lifespan(_app: FastAPI):
_start_cleanup_scheduler()
try:
yield
finally:
_stop_cleanup_scheduler()
app = FastAPI(title="WordCloud Test Service", version="0.1.0", lifespan=_app_lifespan)
app.add_middleware(
CORSMiddleware,
@@ -162,26 +175,27 @@ def health() -> dict:
@app.get("/api/maintenance/storage-summary")
def storage_summary() -> dict:
referenced_jobs: set[str] = set()
asset_referenced_jobs: set[str] = set()
for d in _list_dirs(ASSETS_DIR):
meta = _read_asset_meta(d)
job_id = meta.get("job_id") or ""
if job_id:
referenced_jobs.add(job_id)
stale = storage.stale_job_dirs(
referenced_job_ids=referenced_jobs,
exclude_job_ids=metadata_store.job_ids(),
max_age_days=0,
)
asset_referenced_jobs.add(job_id)
report = cleanup_service.preview(datetime.now(timezone.utc))
archive_protected_jobs = cleanup_service.archive_protected_job_ids()
return {
"job_dir_count": len(storage.list_job_ids()),
"referenced_job_ids": len(referenced_jobs),
"stale_job_count": len(stale),
"reclaimable_bytes": sum(item["size_bytes"] for item in stale),
"referenced_job_ids": len(asset_referenced_jobs),
"asset_referenced_job_ids": sorted(asset_referenced_jobs),
"archive_protected_job_ids": sorted(archive_protected_jobs),
"archive_protected_job_count": len(archive_protected_jobs),
"temporary_job_ids": [item.job_id for item in report.temporary_jobs],
"stale_job_count": len(report.temporary_jobs),
"reclaimable_bytes": report.reclaimable_bytes,
"metadata_db_bytes": metadata_store.summarize()["db_size_bytes"],
"jobs_in_db": metadata_store.summarize()["jobs"],
"events_in_db": metadata_store.summarize()["events"],
"dry_run_only": True,
"dry_run_only": not _cleanup_apply_enabled(),
}
@@ -1023,6 +1037,78 @@ def _require_orders_auth(request: Request) -> None:
raise HTTPException(status_code=403, detail="需要登录") # noqa: S105
def _cleanup_apply_enabled() -> bool:
return os.environ.get("CLEANUP_APPLY_ENABLED", "false").strip().lower() == "true"
def _run_scheduled_cleanup_once(now: datetime | None = None) -> CleanupReport:
run_at = now or datetime.now(timezone.utc)
apply_enabled = _cleanup_apply_enabled()
report = cleanup_service.apply(run_at) if apply_enabled else cleanup_service.preview(run_at)
log.info(
"cleanup cycle apply=%s temporary_jobs=%d pending_products=%d reclaimable_bytes=%d "
"reminder_job_ids=%s deleted_job_ids=%s deleted_product_ids=%s",
apply_enabled,
len(report.temporary_jobs),
len(report.pending_products),
report.reclaimable_bytes,
report.reminder_job_ids,
report.deleted_job_ids,
report.deleted_product_ids,
)
return report
_cleanup_scheduler_stop = threading.Event()
_cleanup_scheduler_thread: threading.Thread | None = None
def _cleanup_scheduler_loop() -> None:
while not _cleanup_scheduler_stop.wait(24 * 60 * 60):
try:
_run_scheduled_cleanup_once()
except Exception:
log.exception("scheduled cleanup cycle failed")
def _start_cleanup_scheduler() -> None:
global _cleanup_scheduler_thread
_run_scheduled_cleanup_once()
if _cleanup_scheduler_thread is not None and _cleanup_scheduler_thread.is_alive():
return
_cleanup_scheduler_stop.clear()
_cleanup_scheduler_thread = threading.Thread(
target=_cleanup_scheduler_loop,
name="retention-cleanup",
daemon=True,
)
_cleanup_scheduler_thread.start()
def _stop_cleanup_scheduler() -> None:
global _cleanup_scheduler_thread
_cleanup_scheduler_stop.set()
if _cleanup_scheduler_thread is not None:
_cleanup_scheduler_thread.join(timeout=1)
_cleanup_scheduler_thread = None
@app.get("/api/maintenance/cleanup-candidates", response_model=CleanupReport)
def cleanup_candidates(request: Request) -> CleanupReport:
_require_orders_auth(request)
return cleanup_service.preview(datetime.now(timezone.utc))
@app.post("/api/maintenance/cleanup-run", response_model=CleanupReport)
def cleanup_run(request: Request, payload: dict) -> CleanupReport:
_require_orders_auth(request)
if payload.get("confirm") is not True:
raise HTTPException(status_code=400, detail="confirm must be true")
if not _cleanup_apply_enabled():
raise HTTPException(status_code=409, detail="cleanup apply is disabled")
return cleanup_service.apply(datetime.now(timezone.utc))
@app.post("/api/login")
async def login(request: Request) -> dict:
try: