fix(importer): catch PIL OSError during transparency + phash blocks, skip as invalid_image instead of letting Celery autoretry loop forever

Operator hit a corrupt JPEG in the IR set 2026-05-25: PIL.verify() only
validates header structure but doesn't catch truncated/broken pixel
data. The error surfaces later in _transparency_pct (via getchannel
'A' -> load) or compute_phash (load) — both blow up with OSError
'broken data stream when reading image file'. Celery's autoretry_for
then bounces the same file forever instead of marking it skipped.

Wrap both PIL.load-triggering call sites with try/except OSError ->
ImportResult(status=skipped, skip_reason=invalid_image).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-25 02:34:36 -04:00
parent 52445eb501
commit 68cffce322
2 changed files with 77 additions and 3 deletions
+22 -3
View File
@@ -280,7 +280,18 @@ class Importer:
)
if self.settings.skip_transparent and has_alpha:
pct = self._transparency_pct(source)
try:
pct = self._transparency_pct(source)
except OSError as exc:
# PIL.verify() at line 263 only validates header structure;
# truncated/corrupt pixel data only surfaces when load()
# actually decodes (here via getchannel('A')). Convert to
# invalid_image skip so the Celery autoretry loop doesn't
# bounce the same broken file forever.
return ImportResult(
status="skipped", skip_reason=SkipReason.invalid_image,
error=f"PIL load failed during transparency check: {exc}",
)
if pct >= self.settings.transparency_threshold:
return ImportResult(
status="skipped", skip_reason=SkipReason.too_transparent,
@@ -302,8 +313,16 @@ class Importer:
# Perceptual near-dup (images only; videos keep phash NULL).
phash = None
if not is_video(source):
with Image.open(source) as im:
phash = compute_phash(im)
try:
with Image.open(source) as im:
phash = compute_phash(im)
except OSError as exc:
# Same rationale as the transparency-check guard above:
# broken-pixel-data files pass verify() but blow up here.
return ImportResult(
status="skipped", skip_reason=SkipReason.invalid_image,
error=f"PIL load failed during phash compute: {exc}",
)
if phash is not None:
cand_rows = self.session.execute(
select(