Files
goods/ingestion/opengoods/jobs/seed_off.py
T
novaalphastrikeomegaz663 044c870df7
CI / Go (api) (pull_request) Failing after 22s
CI / Python (ingestion) (pull_request) Successful in 14s
CI / Migrations (postgres) (pull_request) Failing after 18s
feat(ingestion): harden OFF ingestion for bulk seeding
- Add retry/backoff (429 + 5xx, Retry-After aware) to the OFF adapter so
  transient API errors no longer abort a run.
- Clamp bounded text fields (serving_size, net_content_unit,
  country_of_origin) to their column widths in transform; long OFF values
  previously raised StringDataRightTruncation and rolled back the batch.
- Load each record inside a savepoint (load_record_safe) so one malformed
  source record is skipped instead of aborting the whole import; jobs now
  report an errored count.
- Tests for retry behaviour, serving_size clamping, and per-record isolation.

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-06-20 06:55:56 +00:00

69 lines
2.3 KiB
Python

"""Seed the database with Open Food Facts data.
Usage:
# from a list of barcodes via the OFF API
python -m opengoods.jobs.seed_off --barcodes 3017624010701 5449000000996
# from a downloaded OFF JSONL dump (optionally .gz), limited to N records
python -m opengoods.jobs.seed_off --dump products.jsonl.gz --limit 1000
The OFF read API is rate-limited client-side; for large imports use a dump.
"""
from __future__ import annotations
import argparse
import sys
from collections.abc import Iterator
import psycopg
from opengoods.adapters.openfoodfacts import OpenFoodFactsAdapter, read_dump
from opengoods.etl.load import default_dsn, ensure_source, load_record_safe
from opengoods.etl.transform import transform
def _raw_records(args: argparse.Namespace) -> Iterator[dict]:
if args.dump:
records = read_dump(args.dump)
else:
adapter = OpenFoodFactsAdapter(min_interval=args.min_interval)
records = adapter.fetch(args.barcodes)
for i, rec in enumerate(records):
if args.limit and i >= args.limit:
break
yield rec
def run(args: argparse.Namespace) -> int:
loaded = skipped = errored = 0
with psycopg.connect(args.dsn, autocommit=False) as conn:
source_id = ensure_source(conn)
for raw in _raw_records(args):
rec = transform(raw)
if rec is None:
skipped += 1
continue
if load_record_safe(conn, rec, source_id, raw):
loaded += 1
else:
errored += 1
conn.commit()
print(f"loaded={loaded} skipped={skipped} errored={errored}")
return 0
def main(argv: list[str] | None = None) -> int:
parser = argparse.ArgumentParser(description="Seed OpenGoods from Open Food Facts")
src = parser.add_mutually_exclusive_group(required=True)
src.add_argument("--barcodes", nargs="+", help="barcodes to fetch via the OFF API")
src.add_argument("--dump", help="path to an OFF JSONL dump (.jsonl or .jsonl.gz)")
parser.add_argument("--limit", type=int, default=0, help="max records to load (0 = all)")
parser.add_argument("--min-interval", type=float, default=4.0, help="API throttle seconds")
parser.add_argument("--dsn", default=default_dsn(), help="PostgreSQL DSN")
return run(parser.parse_args(argv))
if __name__ == "__main__":
sys.exit(main())