Files
FabledCurator/backend/app/services/migrators/verify.py
T

81 lines
2.9 KiB
Python

"""Post-migration verification: row counts + sha256 sampling."""
from __future__ import annotations
import hashlib
from pathlib import Path
from sqlalchemy import func, select
from sqlalchemy.ext.asyncio import AsyncSession
from ...models import Artist, Credential, ImageRecord, Source, Tag
async def verify_async(db: AsyncSession, *, expected: dict | None = None) -> dict:
"""Return per-check status dicts. `expected` is optional row-count
assertions; checks default to status='ok' when no expected provided."""
expected = expected or {}
results: dict[str, dict] = {}
checks = {
"artist_subscriptions": (
select(func.count(Artist.id)).where(Artist.is_subscription.is_(True))
),
"source_count": select(func.count(Source.id)),
"credential_count": select(func.count(Credential.id)),
"tag_count": select(func.count(Tag.id)),
"image_record_imported_or_downloaded": (
select(func.count(ImageRecord.id))
.where(ImageRecord.origin.in_(["imported_filesystem", "downloaded"]))
),
}
for name, stmt in checks.items():
actual = (await db.execute(stmt)).scalar_one()
exp = expected.get(name)
status = "ok" if exp is None or exp == actual else "mismatch"
results[name] = {"status": status, "actual": int(actual), "expected": exp}
return results
async def verify_sha256_sample(
db: AsyncSession, *, sample_size: int = 20,
) -> dict:
"""Sample N image_records; verify file exists + sha256 matches."""
rows = (await db.execute(
select(ImageRecord.id, ImageRecord.path, ImageRecord.sha256)
.order_by(func.random()).limit(sample_size)
)).all()
matched = 0
mismatched = 0
missing = 0
samples: list[dict] = []
for img_id, path, expected_sha in rows:
p = Path(path)
# Sync stdlib filesystem ops are intentional: this verify pass runs
# inside a Celery task under asyncio.run; no other awaitables compete
# for the loop. Same pattern as download_service.py.
if not p.exists(): # noqa: ASYNC240
missing += 1
samples.append({"id": img_id, "path": path, "result": "missing"})
continue
h = hashlib.sha256()
with p.open("rb") as f: # noqa: ASYNC230
for chunk in iter(lambda: f.read(65536), b""):
h.update(chunk)
if h.hexdigest() == expected_sha:
matched += 1
samples.append({"id": img_id, "result": "ok"})
else:
mismatched += 1
samples.append({
"id": img_id, "path": path, "result": "mismatch",
"expected_sha": expected_sha, "actual_sha": h.hexdigest(),
})
return {
"sample_size": len(rows),
"matched": matched,
"mismatched": mismatched,
"missing": missing,
"samples": samples,
}