From 220803c4d0a8c6eab065ff970b453790b35fc60a Mon Sep 17 00:00:00 2001 From: Victor Kuznetsov Date: Mon, 13 Jul 2026 11:54:33 +0300 Subject: [PATCH] fix(metadata): remove_ai_metadata is fail-safe on a truncated/corrupt image PIL raises OSError decoding a truncated file, which crashed remove_ai_metadata (the PNG/WebP PIL re-save path) -- a direct library caller like a web worker 500s on a partial upload. ~0.2% of the real upload corpus is truncated. The strip now probes decodability first and, on failure, copies the input through unchanged and returns rather than raising (we cannot strip what we cannot parse), mirroring strip_c2pa_boxes' fail-safe. identify already handled these. The CLI `metadata --remove` on an unreadable file therefore now exits 0 with the input passed through, not a clean error (exit 1) -- `visible`, which must decode to remove a mark, still exits 1. Test updated to the per-command contract. Co-Authored-By: Claude Opus 4.8 --- CLAUDE.md | 2 +- src/remove_ai_watermarks/metadata.py | 17 +++++++++++++++++ tests/test_cli.py | 21 ++++++++++++++------- tests/test_metadata.py | 21 +++++++++++++++++++++ 4 files changed, 53 insertions(+), 8 deletions(-) diff --git a/CLAUDE.md b/CLAUDE.md index 8e64f20..0e374fd 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -54,7 +54,7 @@ Compact map. The full per-module detail (design decisions, tuned thresholds, cal - `noai/c2pa.py` — C2PA reading. `extract_c2pa_info(path)` uses the official **c2pa-python `Reader`** first (core dep, any container; `read_manifest_store_json` returns the WHOLE store JSON — active + ingredient manifests — so an AI marker on a parent manifest is seen), and falls back to the hand-rolled caBX/CBOR parser (`has_c2pa_metadata` / `extract_c2pa_chunk` / `_extract_c2pa_info_png`) for synthetic/partial blobs the validator rejects or a broken/absent wheel. The registry scan (issuer / source-type / SynthID / soft-binding) is shared by both paths via `_populate_registry_fields`, so the return-dict shape is identical. Do not reimplement chunk parsing; chunk reads are clamped to the remaining file size by design. `extract_c2pa_chunk`/`inject_c2pa_chunk` stay PNG-only (raw caBX bytes, test/extractor use). - `noai/constants.py` — the single `C2PA_AI_VENDORS` registry (+ `C2PA_SOFT_BINDINGS`) from which `C2PA_ISSUERS` / `SYNTHID_C2PA_ISSUERS` / `C2PA_IDENTITY_AI_ORGS` / `identify._ISSUER_PLATFORM` are all derived. Add a new vendor as one registry entry; never edit the derived dicts and never add inline. A vendor's `asserts_ai=True` flag means its mere presence asserts AI generation even without a `trainedAlgorithmicMedia` digital-source-type (a pure-generator brand with a distinctive issuer/generator string, e.g. **Dreamina** — ByteDance's international Jimeng brand, signed as "Bytedance Pte. Ltd." with a "Dreamina/x.y" claim generator and no source-type); NEVER set it for common-word issuers (Adobe/Google/OpenAI/Microsoft) that appear incidentally in unrelated bytes — those stay source-type-gated in `identify._attribute_platform`. -- `metadata.py` — `scan_head(path)` is the shared (memoized) input for every C2PA/AIGC/IPTC byte scan; use it instead of `open().read(1MB)` for any new marker scan. Also home to `synthid_source`, `xai_signature`, `iptc_ai_system`, `aigc_label`, `huggingface_job`, `samsung_genai`, and `remove_ai_metadata` (fail-safe `strip_c2pa_boxes`). **`remove_ai_metadata` is the SINGLE metadata stripper** (the legacy PIL-re-encoding `noai/cleaner` was deleted; the diffusion core and the public `noai.remove_ai_metadata` re-export now point here). It strips **losslessly** per container: ISOBMFF (HEIC/AVIF/MP4) blanks tokens / strips boxes in place; **JPEG uses `_strip_jpeg_metadata_lossless`** — a marker-segment walk that drops the AI-bearing APP segments (C2PA APP11; XMP APP1 carrying C2PA, a China-AIGC token, OR an IPTC `digitalSourceType` / 2025.1 AI-disclosure marker; IPTC-IIM APP13) and scrubs AI EXIF tags via piexif, copying the entropy-coded scan verbatim so **the pixels are bit-identical** (no DCT re-encode). **Detection<->removal parity across every marker placement is load-bearing** — anything a scanner flags, the strip must reach, or a re-served file still reads as AI: (a) the APP1-XMP branch of `_jpeg_app_carries_ai` checks the IPTC marker sets too, not only C2PA/AIGC (the Instagram/MidJourney/Meta "Made with AI" `digitalSourceType` lives in XMP, not the APP13 IIM record); (b) a bare `AIGC{...}` / `{"AIGC":{...}}` block in a NON-standard APP segment (near JFIF on some China gens) is dropped via `_is_aigc_exif_value`, not only the APP11/APP1/APP13 cases; (c) the China TC260 `{"AIGC":{...}}` block in EXIF `UserComment`/`ImageDescription` is scrubbed by `_scrub_ai_exif` (Doubao producer + Tencent service-provider schemas); (d) the Samsung Galaxy AI `PhotoEditor_Re_Edit_Data` trailer past the JPEG EOI is truncated by `_strip_samsung_trailer` (and `samsung_genai` reads the file tail so a multi-MB photo's trailer past the 512 KB quick-scan window is still DETECTED). Pixels stay bit-identical throughout, so a `--strip-metadata` on a q100 removal output does NOT crush it back to q75; PNG/WebP re-saves are pixel-lossless (WebP written at cv2 lossless mode, quality 101 — quality 1-100 is lossy). Regression: `tests/test_metadata.py::TestHasAiMetadata::{test_jpeg_metadata_strip_is_pixel_lossless, test_jpeg_strip_removes_iptc_marker_in_xmp}`, `TestSamsungGenai::{test_remove_strips_post_eoi_trailer, test_detects_trailer_past_scan_window}`, the AIGC-EXIF/bare-APP removal tests, and `tests/test_noai.py::TestISOBMFF::{test_blank_aigc_block_in_exif, test_blank_xai_signature_pair_in_exif}`. `exif_generator` matches a VALUE against `AI_GENERATOR_TOKENS` across EXIF `Software`/`Make`/`Artist`/`ImageDescription`, XMP `CreatorTool`, AND PNG `tEXt` chunks (`Software`/`Source`/`Title`/`Description` — NovelAI stamps there, not EXIF). **Detection and removal must stay in parity:** a generator that stamps an AI-shaped VALUE under a non-AI KEY (NovelAI's `Title`/`Source`) is dropped on removal by `_is_ai_value` (value-token match, mirrors `exif_generator`), NOT by `_is_ai_key` alone — else the cleaned file still reads as that generator. Add a new no-C2PA generator = one `AI_GENERATOR_TOKENS` entry (use a distinctive token, e.g. `reve.com` not bare `reve`); detection and removal then both follow. Regression: `tests/test_metadata.py::TestExifGenerator::{test_novelai_png_text_chunk_detected,test_novelai_removal_parity}`. +- `metadata.py` — `scan_head(path)` is the shared (memoized) input for every C2PA/AIGC/IPTC byte scan; use it instead of `open().read(1MB)` for any new marker scan. Also home to `synthid_source`, `xai_signature`, `iptc_ai_system`, `aigc_label`, `huggingface_job`, `samsung_genai`, and `remove_ai_metadata` (fail-safe `strip_c2pa_boxes`). **`remove_ai_metadata` is the SINGLE metadata stripper** (the legacy PIL-re-encoding `noai/cleaner` was deleted; the diffusion core and the public `noai.remove_ai_metadata` re-export now point here). It strips **losslessly** per container: ISOBMFF (HEIC/AVIF/MP4) blanks tokens / strips boxes in place; **JPEG uses `_strip_jpeg_metadata_lossless`** — a marker-segment walk that drops the AI-bearing APP segments (C2PA APP11; XMP APP1 carrying C2PA, a China-AIGC token, OR an IPTC `digitalSourceType` / 2025.1 AI-disclosure marker; IPTC-IIM APP13) and scrubs AI EXIF tags via piexif, copying the entropy-coded scan verbatim so **the pixels are bit-identical** (no DCT re-encode). **Detection<->removal parity across every marker placement is load-bearing** — anything a scanner flags, the strip must reach, or a re-served file still reads as AI: (a) the APP1-XMP branch of `_jpeg_app_carries_ai` checks the IPTC marker sets too, not only C2PA/AIGC (the Instagram/MidJourney/Meta "Made with AI" `digitalSourceType` lives in XMP, not the APP13 IIM record); (b) a bare `AIGC{...}` / `{"AIGC":{...}}` block in a NON-standard APP segment (near JFIF on some China gens) is dropped via `_is_aigc_exif_value`, not only the APP11/APP1/APP13 cases; (c) the China TC260 `{"AIGC":{...}}` block in EXIF `UserComment`/`ImageDescription` is scrubbed by `_scrub_ai_exif` (Doubao producer + Tencent service-provider schemas); (d) the Samsung Galaxy AI `PhotoEditor_Re_Edit_Data` trailer past the JPEG EOI is truncated by `_strip_samsung_trailer` (and `samsung_genai` reads the file tail so a multi-MB photo's trailer past the 512 KB quick-scan window is still DETECTED). Pixels stay bit-identical throughout, so a `--strip-metadata` on a q100 removal output does NOT crush it back to q75; PNG/WebP re-saves are pixel-lossless (WebP written at cv2 lossless mode, quality 101 — quality 1-100 is lossy). **`remove_ai_metadata` is fail-safe on an undecodable image:** a truncated/corrupt file (PIL raises `OSError` decoding it; ~0.2% of real uploads) is copied through UNCHANGED rather than crashing a direct library caller (a web worker would 500 on a partial upload), mirroring `strip_c2pa_boxes` — we cannot strip what we cannot parse, but we never raise. Regression: `tests/test_metadata.py::TestHasAiMetadata::test_remove_ai_metadata_failsafe_on_truncated_png`. Regression: `tests/test_metadata.py::TestHasAiMetadata::{test_jpeg_metadata_strip_is_pixel_lossless, test_jpeg_strip_removes_iptc_marker_in_xmp}`, `TestSamsungGenai::{test_remove_strips_post_eoi_trailer, test_detects_trailer_past_scan_window}`, the AIGC-EXIF/bare-APP removal tests, and `tests/test_noai.py::TestISOBMFF::{test_blank_aigc_block_in_exif, test_blank_xai_signature_pair_in_exif}`. `exif_generator` matches a VALUE against `AI_GENERATOR_TOKENS` across EXIF `Software`/`Make`/`Artist`/`ImageDescription`, XMP `CreatorTool`, AND PNG `tEXt` chunks (`Software`/`Source`/`Title`/`Description` — NovelAI stamps there, not EXIF). **Detection and removal must stay in parity:** a generator that stamps an AI-shaped VALUE under a non-AI KEY (NovelAI's `Title`/`Source`) is dropped on removal by `_is_ai_value` (value-token match, mirrors `exif_generator`), NOT by `_is_ai_key` alone — else the cleaned file still reads as that generator. Add a new no-C2PA generator = one `AI_GENERATOR_TOKENS` entry (use a distinctive token, e.g. `reve.com` not bare `reve`); detection and removal then both follow. Regression: `tests/test_metadata.py::TestExifGenerator::{test_novelai_png_text_chunk_detected,test_novelai_removal_parity}`. - `identify.py` — aggregates every locally-readable signal into one `ProvenanceReport`; `is_ai_generated` is True or None, never asserted False. `ProvenanceReport.ai_source_kind` exposes the C2PA digital-source-type split — `"generated"` (trainedAlgorithmicMedia, fully AI) vs `"enhanced"` (compositeWithTrainedAlgorithmicMedia, a real photo with an AI-composited region), else None — so a caller branches full-frame scrub vs region-targeted clean (see `noai/tiling.feather_region_composite` + `WatermarkRemover.remove_watermark(region=...)`). The sparkle provenance threshold is the SHARED `watermark_registry.GEMINI_SPARKLE_TRUST_CONF` (imported, not a private copy) so the provenance "is there a sparkle" verdict and the removal "take the sparkle" decision can never drift. `import identify` is deliberately light (lazy `noai/__init__`, fits a 512 MB host) — keep heavy imports out (the `watermark_registry` constant import stays light: engines are lazy there). Add capture-camera tokens to `_DEVICE_C2PA_PLATFORM` only when verified against a real C2PA file; editing-app/AI-device signer tokens go to `_SIGNER_C2PA_PLATFORM`; generator/issuer platforms to `C2PA_AI_VENDORS` in `constants.py`. The IPTC `digitalSourceType` **`algorithmicMedia`** (bare) is PROCEDURAL (an algorithm not trained on sampled data), NOT AI/ML generation, so it is deliberately absent from `IPTC_AI_MARKERS` — flagging it made `identify` assert AI + `has_invisible_target` True, scrubbing clean procedural content (it is a distinct token from `trainedAlgorithmicMedia`, so real "Made with AI" labels are unaffected; regression `test_metadata.py::...test_bare_algorithmic_media_not_flagged_ai`). Integrity-clash detection is high-precision by design (only hard generator stamps feed it, source-grouped independence). `_vendor_of` normalizes ByteDance/Canva/ElevenLabs/Black Forest Labs (as well as OpenAI/Google/... ) so their C2PA claims participate in the clash check; the generic **China TC260 AIGC label names no specific vendor**, so when a TC260-applying vendor (ByteDance, `_TC260_VENDORS`) is co-attributed the label is attributed to it (a legit Doubao image carrying its own TC260 label must NOT clash), while a NON-TC260 vendor next to a TC260 label still clashes as a laundering tell. Corpus-validated: adding the vendors introduced 0 new clashes on 5000 carriers. - `watermark_registry.py` — the single catalog of known visible watermarks (gemini / doubao / jimeng / samsung / jimeng_pill). **Removal is LOCALIZE -> FILL for every mark:** each mark is localized to a binary full-frame footprint mask (a `Localization`), then ONE shared, swappable fill inpaints that mask via `fill(image, mask, backend=...)` (delegates to `region_eraser.erase`). Reverse-alpha (the old `original = (wm - a*logo)/(1-a)` inversion of a captured alpha map + thin residual inpaint) is GONE for ALL marks; why it was dropped is recorded in `docs/module-internals.md`. Backends: `cv2` (classical inpaint, no deps, the floor), `migan` (MI-GAN ONNX, light, the memory-tight pick where LaMa will not fit), `lama` (big-LaMa ONNX, best quality, heavier, auto-preferred when a learned backend is available); `auto` = LaMa > MI-GAN > cv2, best available. The captured alpha maps (`scripts/visible_alpha_solve.py`) are still used to DETECT the marks and to shape the mask, but NOT for pixel recovery. **`--mark auto` removes EVERY detected mark in one pass** via `remove_auto_marks(image, *, sensitivity="auto", provenance=frozenset(), backend="auto")` (marks coexist -- a Jimeng-basic image has the top-left pill AND the bottom-right wordmark; a single-strongest pick would leave one). **Three orthogonal axes:** `backend` (the fill), `sensitivity` (how hard to trust a borderline mark: `auto`/`strict`/`assume_ai`, see the `Sensitivity` literal), and `provenance` (vendor keys metadata confirms -- the evidence that drives `auto`). **Perception / decision / action are separated:** `_build_candidates(image)` runs every detector at BOTH trust levels (strict + relaxed) and packages raw verdicts + features into `Candidate`s (no policy); the pure arbiter `decide(candidates, Context(sensitivity, provenance)) -> [Decision]` makes every keep/drop call (per-mark `resolve_relax` + the pill gate) with no image/IO, so it is unit-testable in isolation; then each winner is localized -> filled. Do NOT put policy back into the engines (the one exception, the Gemini FP gate, stays in `gemini_engine` because `identify` shares that confidence). `detect_marks(..., provenance=frozenset())` stays strict (identify verdict, precision over recall); `KnownMark.remove/detect/localize(..., provenance: bool)` take the already-resolved boolean. **How auto/assume decide (this is metadata-INDEPENDENT for recall):** the visual detectors are pixel-based and need no metadata; the recall gain comes from RELAXING the false-positive gate, not from metadata. `strict` never relaxes (clean images untouched); `auto` relaxes a mark only on same-product evidence -- metadata provenance for that vendor OR a confidently detected sibling mark of the SAME product (`_PRODUCT_OF`; Doubao and Jimeng are both bottom-right ByteDance but distinct products, so they do NOT cross-relax); `assume_ai` relaxes every mark (the caller asserts AI -- a metadata-stripped screenshot uploaded to a remover). Corpus finding: Gemini sparkle removal on Google-C2PA images is ~46% under `strict`/metadata-free `auto` and ~92% under `assume_ai` (recovering marks the vendor moved or re-rendered); the library CANNOT infer AI from a stripped image, so only the caller's `assume_ai` reaches the high recall there. A wrong relaxation just fills a small corner near-losslessly (the localize -> fill benign failure mode), which is what makes `assume_ai` acceptable. Metadata provenance mapping (feeds `auto`, read by `cli._visible_provenance`): Google/Gemini C2PA issuer -> gemini; China-AIGC (TC260) label -> doubao/jimeng; `samsung_genai` -> samsung. **The `jimeng_pill` is CAPTURE-LESS** (`pill_engine.py`): the top-left "AI生成" label has no captured alpha map, so it is detect-by-synthetic-silhouette; its footprint is a fixed top-left geometry box. Its weak edge-NCC detector (~7% raw false-fire) is gated in `remove_auto_marks` via **`_keep_pill`** (32k real-upload corpus validation 2026-07): the pill never rides on a **Doubao** detection, and has confirmation arms because metadata/intent confirms the platform, not pill presence. **(1) Bottom-right "★ 即梦AI" wordmark fired** — ~94% precise and survives **metadata-STRIPPED uploads** (screenshots / re-saves, ~61% of pills carry a detectable wordmark): remove **unrestricted**. **(2) TC260 metadata confirms Jimeng** (`"jimeng" in provenance`, no wordmark) **OR the caller asserts AI** (`sensitivity == "assume_ai"`) — the metadata-only arm is only ~27% precise and its false fires are **textured ceilings/walls that the fill visibly SMEARS**, so remove **only when the top-left footprint is flat enough for an invisible fill** (`pill_engine.footprint_is_flat`, median-Sobel texture ≤ `_FLAT_TEXTURE_MAX`) — the flatness guard holds even under `assume_ai`. This keeps real flat-scene pills (incl. metadata-only ones the wordmark misses) plus harmless flat false fires, and leaves the damaging textured false fires untouched. Do NOT drop the wordmark arm or loosen the flatness guard. `cli._write_bgr_with_alpha` must NOT zero alpha in the watermark bbox (issue #30 white-box regression). **The localizer is cheap CPU (cv2/numpy), so a memory-tight caller runs it anywhere; the heavy MI-GAN/LaMa fill is opt-in and chosen by the caller** (a small worker can use cv2; a GPU/model worker can use MI-GAN/LaMa). Adding a new mark needs only a DETECTION silhouette (removal is template-free — the glyph-blob bbox is filled, no capture involved). Produce that silhouette SYNTHETICALLY: font-render the mark's glyphs (the pill's `scripts/render_pill_silhouette.py` is the pattern; commit the rendered PNG under `assets/`) and calibrate the NCC threshold on real positives. The old solid/gray/white app-capture workflow (`scripts/visible_alpha_solve.py`) is RETIRED with reverse-alpha — existing marks still carry their captured silhouettes, but a NEW mark does NOT require captures. (The 2026-06-22 "synthetic reconstruction below the quality bar" objection was about reverse-alpha PIXEL recovery, which is gone; it does not apply to a synthetic detection silhouette.) Data-safety still binds the committed asset: the silhouette must be font-rendered synthetic, never derived from user uploads — seeing a real sample to learn the glyphs / font / position / locale is fine, but the committed template stays synthetic. So nothing is parked for lack of a capture: Meta AI and more Samsung locales just need the glyphs + font + locale + calibration positives; any Grok visible mark additionally needs confirming it even HAS one (its known signal is EXIF-only `xai_signature`). - `gemini_engine.py` — visible Gemini-sparkle detector + localizer (cv2/numpy, no GPU): top-K size-weighted fusion candidate selection (`_SELECT_TOPK`), corner-promote, false-positive gate (the provenance prior relaxes the gate + lowers the trust threshold when a Google/Gemini C2PA issuer confirms the vendor). **White-core rescue:** the FP gate demotes a low-gradient match (soft edges), but a real FAINT sparkle also has soft edges -- so the gate keeps a low-grad match that is a strong (conf ≥ `_SPARKLE_KEEP_CONF` 0.52), bright (margin), near-WHITE-core sparkle (`_core_saturation` ≤ `_SPARKLE_WHITE_SAT` 0.20): a real sparkle core is white, a clean bright corner that shape-matches (sky/sun) is colored. This recovers ~14/20 metadata-stripped faint sparkles under the DEFAULT strict/auto (no flag, no metadata) at ~1.25% clean false-fire (baseline 0.55%); the ~0.51-scoring bright-bg FPs stay demoted (below 0.52). A learned classifier on the SAME features was measured WORSE than the tuned gate (2026-07 tier-1: MLP 86.7% recall vs 90.8% at equal FP), so the heuristic stays; a patch-CNN with richer features is the only lever left (roadmapped P2, low expected value -- the wall is fundamental). Detection scores the top-K size-weighted matches by full fusion (spatial+gradient+variance) and keeps the highest — NOT the raw-NCC argmax, which re-admits the tiny-patch FPs the size weight suppresses (the osachub 2026-06-12 sub-0.85 corner-sparkle regression; see `docs/module-internals.md`). Keep the 0.85 corner-promote NCC gate; a margin/chroma-gated lower promote was measured and REJECTED 2026-06-11 (~33% FP on non-Google content). Removal is localize -> fill: `footprint_mask` returns the sparkle footprint (the captured alpha thresholded LOW so the faint halo is included, then dilated by a sparkle-relative margin), and the shared `watermark_registry.fill` inpaints it. The captured alpha maps are used only to detect and to shape the mask, not for pixel recovery. `detect_sparkle_confidence` reuses a process-wide `_shared_engine()` singleton (lru_cache) — the engine holds only constant assets (captures, alpha maps, a precomputed 16..118 template ladder) and takes the image as an arg, so do NOT reconstruct `GeminiEngine()` per call: that reloaded assets + recomputed alpha maps + rebuilt the template cache on every one of ~34k `identify` calls (−24% on the sparkle path once made a singleton, output byte-identical). `detect_watermark`/`footprint_mask` guard `image.size == 0` before `to_bgr`, and return an empty (detected=False) result when no template scale fits (short side < 16 px), rather than dereferencing an empty candidate list. diff --git a/src/remove_ai_watermarks/metadata.py b/src/remove_ai_watermarks/metadata.py index 3a547e2..de27e35 100644 --- a/src/remove_ai_watermarks/metadata.py +++ b/src/remove_ai_watermarks/metadata.py @@ -1120,6 +1120,23 @@ def remove_ai_metadata( ): return output_path + # Fail-safe for a truncated / corrupt image: PIL raises OSError when it decodes a + # partial file (`img.copy()` / `img.save()` below), which would crash a direct + # library caller (a web worker 500s on a partial upload). Probe decodability first; + # if it fails, copy the input through unchanged and return -- we cannot strip what we + # cannot parse, but we never raise (mirrors strip_c2pa_boxes' fail-safe). + try: + with Image.open(source_path) as _probe: + _probe.load() + except Exception: + logger.warning("Could not decode %s to strip metadata (truncated/corrupt); copied through", source_path) + if output_path != source_path: + import shutil + + output_path.parent.mkdir(parents=True, exist_ok=True) + shutil.copyfile(source_path, output_path) + return output_path + # Read image and filter metadata with Image.open(source_path) as img: img = img.copy() diff --git a/tests/test_cli.py b/tests/test_cli.py index 2cd012b..6cd630c 100644 --- a/tests/test_cli.py +++ b/tests/test_cli.py @@ -949,14 +949,21 @@ def test_visible_backend_runtime_error_exits_cleanly(runner, tmp_path, monkeypat ) @pytest.mark.parametrize("cmd", [["metadata", "--remove"], ["visible", "--backend", "cv2"]]) def test_unreadable_input_exits_cleanly(runner, tmp_path, name, content, cmd): - """Regression: a corrupt / empty / non-image file (real prod uploads include - truncated files) must produce a clean 'Error: cannot read/process' + exit 1, NOT a - raw PIL.UnidentifiedImageError / OSError / ValueError traceback. Found by the runtime - mode fuzz across metadata --remove and visible.""" + """Regression: a corrupt / empty / non-image file (real prod uploads include ~0.2% + truncated files) must NEVER leak a raw PIL/OSError/ValueError traceback. `metadata + --remove` is fail-safe -- an undecodable file is copied through unchanged (exit 0), + a strip that cannot parse the file is a no-op, not a crash; `visible` must decode to + remove a mark, so it is a clean error (exit 1). Found by the runtime mode fuzz.""" bad = tmp_path / name bad.write_bytes(content) out = tmp_path / "out.png" result = runner.invoke(main, [cmd[0], str(bad), "-o", str(out), *cmd[1:]]) - assert result.exit_code == 1, result.output - assert isinstance(result.exception, SystemExit), f"leaked a raw traceback: {result.exception!r}" - assert "Error" in result.output + assert result.exception is None or isinstance(result.exception, SystemExit), ( + f"leaked a raw traceback: {result.exception!r}" + ) + if cmd[0] == "metadata": + assert result.exit_code == 0, result.output # fail-safe copy-through + assert out.read_bytes() == content # input passed through unchanged + else: + assert result.exit_code == 1, result.output # cannot remove a mark from unreadable input + assert "Error" in result.output diff --git a/tests/test_metadata.py b/tests/test_metadata.py index 6d97919..6725006 100644 --- a/tests/test_metadata.py +++ b/tests/test_metadata.py @@ -226,6 +226,27 @@ class TestHasAiMetadata: assert np.array_equal(before, after), "pixels changed: the DCT scan was re-encoded" assert not has_ai_metadata(out), "IPTC AI marker in XMP survived the strip" + def test_remove_ai_metadata_failsafe_on_truncated_png(self, tmp_path: Path): + """Regression: a truncated / corrupt image must NOT crash remove_ai_metadata (a + direct library caller like a web worker would 500 on a partial upload). PIL raises + OSError decoding a truncated PNG; the strip must fail SAFE -- copy the input through + unchanged and return, mirroring strip_c2pa_boxes. Real prod corpus: ~0.2% of + uploads are truncated.""" + import cv2 + import numpy as np + + from remove_ai_watermarks.metadata import remove_ai_metadata + + real = tmp_path / "real.png" + cv2.imwrite(str(real), np.random.default_rng(0).integers(0, 256, (128, 128, 3), dtype=np.uint8)) + truncated = tmp_path / "truncated.png" + truncated.write_bytes(real.read_bytes()[: real.stat().st_size // 2]) # chop the IDAT stream + out = tmp_path / "out.png" + # Must not raise; output is the input copied through (undecodable -> nothing to strip). + result = remove_ai_metadata(truncated, out) + assert result == out + assert out.read_bytes() == truncated.read_bytes() + class TestC2paMarkerIn: """The C2PA presence check requires a JUMBF wrapper or the C2PA uuid box, so