Fix stupid Python runtimeerror

Fixes issue [Bug]: Optimized pdf not rendering with Quartz / Core Graphics #1536

docs/release_notes.md

@@ -25,6 +25,11 @@ about a forthcoming release that has not been tagged yet. A release is only
 official when it's tagged and posted to PyPI.
 :::
 
+## v16.10.3
+
+- Blocked optimization of images with pre-blended soft masks. {issue}`1536`
+- Fixed warning from hypothesis on running tests.
+
 ## v16.10.2
 
 - Blacklist pikepdf 9.8.0 due to an incompatible change.

pyproject.toml

@@ -16,8 +16,8 @@ dependencies = [
   "img2pdf>=0.5",
   "packaging>=20",
   "pdfminer.six>=20220319",
-  "pi-heif",                   # Heif image format - maintainers: if this is removed, it will NOT break
-  "pikepdf>=8.10.1, != 9.8.0",
+  "pi-heif",                 # Heif image format - maintainers: if this is removed, it will NOT break
+  "pikepdf>=8.10.1,!=9.8.0",
   "Pillow>=10.0.1",
   "pluggy>=1",
   "rich>=13",
@@ -102,7 +102,6 @@ exclude_lines = [
 
 [tool.pytest.ini_options]
 minversion = "6.0"
-norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
 testpaths = ["tests"]
 addopts = "-n auto"
 markers = ["slow"]

src/ocrmypdf/__main__.py

@@ -78,6 +78,7 @@ def run(args=None):
 
 if __name__ == '__main__':
     multiprocessing.freeze_support()
-    if os.name == 'posix':
-        multiprocessing.set_start_method('forkserver')
+    if sys.platform not in ('win32', 'darwin'):
+        with suppress(RuntimeError):
+            multiprocessing.set_start_method('forkserver')
     sys.exit(run())

src/ocrmypdf/optimize.py

@@ -126,6 +126,13 @@ def extract_image_filter(
     if Name.Decode in image:
         log.debug(f"xref {xref}: skipping image with Decode table")
         return None  # Don't mess with custom Decode tables
+    if image.get(Name.SMask, Dictionary()).get(Name.Matte, None) is not None:
+        # https://github.com/ocrmypdf/OCRmyPDF/issues/1536
+        # Do not attempt to optimize images that have a SMask with a Matte.
+        # That means alpha channel pre-blending is used, and we're not prepared
+        # to deal with the complexities of that.
+        log.debug(f"xref {xref}: skipping image whose SMask has Matte")
+        return None
 
     return pim, filtdp
 

tests/test_optimize.py

@@ -6,7 +6,7 @@ from __future__ import annotations
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
 import img2pdf
 import pikepdf
@@ -220,7 +220,7 @@ def test_find_formx(resources):
 
 
 def test_extract_image_filter_with_pdf_image():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 200
     image.Width = 10
@@ -235,20 +235,20 @@ def test_extract_image_filter_with_pdf_image():
 
 
 def test_extract_image_filter_with_non_image():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Form
     assert extract_image_filter(image, None) is None
 
 
 def test_extract_image_filter_with_small_stream_size():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 50
     assert extract_image_filter(image, None) is None
 
 
 def test_extract_image_filter_with_small_dimensions():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 200
     image.Width = 5
@@ -257,7 +257,7 @@ def test_extract_image_filter_with_small_dimensions():
 
 
 def test_extract_image_filter_with_multiple_compression_filters():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 200
     image.Width = 10
@@ -268,7 +268,7 @@ def test_extract_image_filter_with_multiple_compression_filters():
 
 
 def test_extract_image_filter_with_wide_gamut_image():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 200
     image.Width = 10
@@ -296,7 +296,7 @@ def test_extract_image_filter_with_jpeg2000_image():
 
 
 def test_extract_image_filter_with_ccitt_group_3_image():
-    image = MagicMock()
+    image = Dictionary()
     image.Subtype = Name.Image
     image.Length = 200
     image.Width = 10
@@ -309,7 +309,7 @@ def test_extract_image_filter_with_ccitt_group_3_image():
 
 # Triggers pikepdf bug
 # def test_extract_image_filter_with_decode_table():
-#     image = MagicMock()
+#     image = Dictionary()
 #     image.Subtype = Name.Image
 #     image.Length = 200
 #     image.Width = 10
@@ -319,3 +319,26 @@ def test_extract_image_filter_with_ccitt_group_3_image():
 #     image.ColorSpace = Name.DeviceGray
 #     image.Decode = [42, 0]
 #     assert extract_image_filter(image, None) is None
+
+
+def test_extract_image_filter_with_rgb_smask_matte():
+    image = Dictionary()
+    image.Subtype = Name.Image
+    image.Length = 200
+    image.Width = 10
+    image.Height = 10
+    image.Filter = Name.FlateDecode
+    image.BitsPerComponent = 8
+    image.ColorSpace = Name.DeviceRGB
+    image.SMask = Dictionary(
+        Type=Name.Image,
+        Subtype=Name.Image,
+        Length=200,
+        Width=10,
+        Height=10,
+        Filter=Name.FlateDecode,
+        BitsPerComponent=8,
+        ColorSpace=Name.DeviceGray,
+        Matte=Array([1, 2, 3]),
+    )
+    assert extract_image_filter(image, None) is None