Files
wiggleverse-ecomm/backend/app/domains/products/imagefetch.py
T
ben.stull c929282e07
ci / check (push) Has been cancelled
ci / check (pull_request) Has been cancelled
fix(products): bomb-safe image processing + per-image error isolation; honest claim/resumability docs (SLICE-7 review)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-12 00:58:10 -07:00

147 lines
6.2 KiB
Python

"""The post-commit image-fetch phase (SD-0002 §6.5.4, §6.9).
In-process, bounded-concurrency, resumable. For a run's pending images: fetch
each URL behind an SSRF guard with INV-18 bounds, run platform/images, store
renditions via the objectstore, and move the image pending -> fetched |
rejected_* | failed. Per-image idempotent (claim guard), so the phase can die
and resume. Lives in the domains layer (imports repo + platform); main.py
schedules it post-confirm and runs recovery at startup.
"""
from __future__ import annotations
import ipaddress
import socket
import time
from concurrent.futures import ThreadPoolExecutor
from urllib.parse import urlsplit
import httpx
from app.platform import images as images_mod
from app.platform import telemetry
from . import repo
MAX_FETCH_BYTES = 20 * 1024 * 1024 # INV-18
FETCH_TIMEOUT_S = 30 # INV-18
FETCH_CONCURRENCY = 4 # §6.6
_CONTENT_PREFIX = "image/"
class FetchBlocked(Exception):
"""SSRF guard or bounds refusal — maps to image status 'failed' with reason."""
def _guard_host(url: str, allow_private: bool) -> None:
parts = urlsplit(url)
if parts.scheme not in {"http", "https"}:
raise FetchBlocked(f"unsupported scheme: {parts.scheme!r}")
host = parts.hostname
if not host:
raise FetchBlocked("no host")
if allow_private:
return
try:
infos = socket.getaddrinfo(host, parts.port or (443 if parts.scheme == "https" else 80))
except socket.gaierror as exc:
raise FetchBlocked(f"dns failure: {exc}") from exc
for info in infos:
ip = ipaddress.ip_address(info[4][0])
if (ip.is_private or ip.is_loopback or ip.is_link_local
or ip.is_reserved or ip.is_multicast or ip.is_unspecified):
raise FetchBlocked(f"non-public address: {ip}")
def fetch_bytes(url: str, allow_private: bool) -> tuple[bytes, str]:
"""SSRF-guarded, bounded GET. Returns (bytes, content_type). Raises FetchBlocked."""
_guard_host(url, allow_private)
with httpx.Client(follow_redirects=False, timeout=FETCH_TIMEOUT_S) as client:
with client.stream("GET", url) as resp:
if resp.status_code != 200:
raise FetchBlocked(f"http {resp.status_code}")
ctype = resp.headers.get("content-type", "").split(";")[0].strip().lower()
if not ctype.startswith(_CONTENT_PREFIX):
raise FetchBlocked(f"not an image content-type: {ctype!r}")
chunks: list[bytes] = []
total = 0
for chunk in resp.iter_bytes():
total += len(chunk)
if total > MAX_FETCH_BYTES:
raise FetchBlocked("oversize")
chunks.append(chunk)
return b"".join(chunks), ctype
def _key(storefront_id: int, image_id: int, name: str) -> str:
return f"storefronts/{storefront_id}/product-images/{image_id}/{name}"
def _process_one(pool, store, image: dict, allow_private: bool) -> None:
with pool.connection() as conn:
claimed = repo.claim_image_for_fetch(conn, image["id"])
conn.commit()
if not claimed:
return
image_id, sf = image["id"], image["storefront_id"]
try:
data, ctype = fetch_bytes(image["source_url"], allow_private)
except (FetchBlocked, httpx.HTTPError) as exc:
with pool.connection() as conn:
repo.mark_image_failed(conn, image_id, str(exc)[:200]); conn.commit()
return
try:
result = images_mod.process(data)
if isinstance(result, images_mod.Rejected):
reason = ("below the resolution bar" if result.reason == "rejected_low_res"
else "not a supported image")
with pool.connection() as conn:
repo.mark_image_rejected(conn, image_id, result.reason, reason); conn.commit()
return
keys = {"original": _key(sf, image_id, "original"),
"thumb": _key(sf, image_id, "thumb.webp"),
"card": _key(sf, image_id, "card.webp"),
"detail": _key(sf, image_id, "detail.webp")}
store.put(keys["original"], data, ctype)
store.put(keys["thumb"], result.renditions["thumb"], "image/webp")
store.put(keys["card"], result.renditions["card"], "image/webp")
store.put(keys["detail"], result.renditions["detail"], "image/webp")
with pool.connection() as conn:
repo.mark_image_fetched(conn, image_id, keys); conn.commit()
except Exception as exc: # noqa: BLE001 — one bad image must never wedge the run (review fix)
with pool.connection() as conn:
repo.mark_image_failed(conn, image_id, f"processing error: {type(exc).__name__}")
conn.commit()
def run_image_phase(pool, store, run_id: int, allow_private: bool) -> None:
"""Fetch all pending images of one run, then move the run to a terminal status."""
started = time.monotonic()
with pool.connection() as conn:
pending = repo.pending_images_for_run(conn, run_id)
if pending:
with ThreadPoolExecutor(max_workers=FETCH_CONCURRENCY) as pool_x:
list(pool_x.map(lambda img: _process_one(pool, store, img, allow_private), pending))
with pool.connection() as conn:
counts = repo.run_image_counts(conn, run_id)
status = ("complete_with_problems"
if counts["rejected"] + counts["failed"] > 0 else "complete")
repo.set_run_status(conn, run_id, status)
conn.commit()
telemetry.emit("image_phase_completed", run_id=run_id, fetched=counts["fetched"],
rejected=counts["rejected"], failed=counts["failed"],
duration_ms=int((time.monotonic() - started) * 1000))
def recover_incomplete_runs(pool, store, allow_private: bool) -> list[int]:
"""Startup scan (§6.9): resume any run stuck in fetching_images. Returns the ids."""
with pool.connection() as conn:
runs = repo.incomplete_runs(conn)
resumed: list[int] = []
for run in runs:
with pool.connection() as conn:
pending = len(repo.pending_images_for_run(conn, run["id"]))
telemetry.emit("image_phase_recovered", run_id=run["id"], pending_resumed=pending)
run_image_phase(pool, store, run["id"], allow_private)
resumed.append(run["id"])
return resumed