Files
remove-ai-watermarks/tests/test_region_eraser.py
T
Victor Kuznetsov 5d0e6c3a65 fix: harden metadata parsers and engines; sync docs (full-repo review)
Apply fixes from a full-repo review (code, tests, docs).

Security / correctness:
- Clamp attacker-controlled PNG/caBX chunk lengths to the remaining file
  size in metadata.py and noai/c2pa.py (a malformed length no longer drives
  a multi-GB read); skipped chunks seek instead of read.
- noai/isobmff.strip_c2pa_boxes is now fail-safe on a malformed box: return
  the original bytes with a warning instead of silently truncating the tail,
  so metadata --remove can no longer emit a corrupt file.
- doubao_engine._fixed_alpha_map clamps the glyph box to the image (no crash
  on degenerate width-vs-height).
- watermark_remover._run_region_hires gates the phaseCorrelate offset on
  response and magnitude (a spurious shift no longer garbles text) and drops
  the generator after a CPU fallback (no MPS/CPU device mismatch).

Robustness:
- gemini_engine, doubao_engine, region_eraser normalize grayscale and RGBA
  inputs to BGR at the engine entry points.
- image_io.imwrite returns False on an unwritable path (matches cv2).
- invisible_engine guards a None imread result before use.
- trustmark_detector._decoder uses a double-checked threading lock.
- ctrlregen.tiling.tile_positions raises on overlap >= tile.
- humanizer chromatic shift no longer wraps opposite-edge pixels.
- identify OpenAI caveat keyed on the normalized vendor, not a substring.
- Remove the dead "visible --detect-threshold" CLI option.
- publish.yml verifies the release tag matches the package version.

Docs:
- README strength 0.05 to 0.10; .env.example HF_TOKEN marked optional;
  doubao_capture README updated to reverse-alpha-only; CLAUDE.md synced with
  the new behaviors and the batch command.

Tests: new test_security_clamp.py for the read clamp and isobmff fail-safe;
erase CLI coverage; integrity-clash rule 2 end-to-end; multi-tag EXIF
survival and cross-format strip guards; channel/size, tiling, humanizer, and
imwrite regressions. Full suite 493 passed, 2 skipped; ruff and pyright src/
clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-05-30 18:00:39 -07:00

93 lines
3.5 KiB
Python

"""Tests for the universal region eraser."""
from __future__ import annotations
import numpy as np
import pytest
from remove_ai_watermarks.region_eraser import boxes_to_mask, erase, lama_available
class TestBoxesToMask:
def test_mask_set_inside_box(self):
mask = boxes_to_mask((100, 100), [(10, 20, 30, 40)], dilate=0)
assert mask[25, 15] == 255 # inside
assert mask[0, 0] == 0 # outside
assert mask.shape == (100, 100)
def test_multiple_boxes(self):
mask = boxes_to_mask((100, 100), [(0, 0, 10, 10), (90, 90, 10, 10)], dilate=0)
assert mask[5, 5] == 255
assert mask[95, 95] == 255
assert mask[50, 50] == 0
def test_dilate_grows_mask(self):
m0 = boxes_to_mask((100, 100), [(40, 40, 10, 10)], dilate=0)
m5 = boxes_to_mask((100, 100), [(40, 40, 10, 10)], dilate=5)
assert m5.sum() > m0.sum()
def test_box_clipped_to_bounds(self):
# box partly outside the image must not raise and stays in-bounds
mask = boxes_to_mask((50, 50), [(40, 40, 100, 100)], dilate=0)
assert mask[45, 45] == 255
class TestEraseCv2:
def _image_with_logo(self) -> tuple[np.ndarray, tuple[int, int, int, int]]:
img = np.full((200, 200, 3), 120, np.uint8) # flat gray background
box = (140, 160, 50, 30)
x, y, w, h = box
img[y : y + h, x : x + w] = (255, 255, 255) # bright "logo"
return img, box
def test_erase_changes_region(self):
img, box = self._image_with_logo()
out = erase(img, boxes=[box], backend="cv2")
x, y, w, h = box
# on a flat background the logo region should be repainted near gray
region = out[y : y + h, x : x + w]
assert abs(float(region.mean()) - 120) < 20
assert not np.array_equal(out, img)
def test_pixels_outside_box_untouched(self):
img, box = self._image_with_logo()
out = erase(img, boxes=[box], backend="cv2", dilate=0)
# a far corner must be identical
assert np.array_equal(img[:50, :50], out[:50, :50])
def test_no_boxes_returns_copy(self):
img = np.full((100, 100, 3), 50, np.uint8)
out = erase(img, boxes=[], backend="cv2")
assert np.array_equal(img, out)
def test_empty_mask_returns_copy(self):
img = np.full((100, 100, 3), 50, np.uint8)
out = erase(img, mask=np.zeros((100, 100), np.uint8), backend="cv2")
assert np.array_equal(img, out)
class TestNonBgrInputs:
"""cv2.inpaint rejects 4-channel BGRA and 2D-only entry points must work."""
def test_grayscale_2d_does_not_raise(self):
gray = np.full((100, 100), 120, np.uint8)
out = erase(gray, boxes=[(40, 40, 20, 20)], backend="cv2")
assert out.shape == gray.shape
def test_bgra_preserves_alpha_and_does_not_raise(self):
bgra = np.full((100, 100, 4), 120, np.uint8)
bgra[..., 3] = 200 # opaque-ish alpha plane
out = erase(bgra, boxes=[(40, 40, 20, 20)], backend="cv2", dilate=0)
assert out.shape == bgra.shape
# alpha plane is carried through unchanged
assert np.array_equal(out[..., 3], bgra[..., 3])
class TestLamaBackend:
def test_lama_raises_when_unavailable(self):
img = np.full((100, 100, 3), 50, np.uint8)
if lama_available():
pytest.skip("onnxruntime installed; cannot test the unavailable path")
with pytest.raises(RuntimeError, match="onnxruntime"):
erase(img, boxes=[(10, 10, 20, 20)], backend="lama")