v11.7.3 release notes

docs/release_notes.rst

@@ -12,6 +12,13 @@ may be unreliable. Use the API to depend on precise behavior.
 The public API may be useful in scripts that launch OCRmyPDF processes or that
 wish to use some of its features for working with PDFs.
 
+v11.7.3
+=======
+
+-  Exclude CCITT Group 3 images from being optimized. Some libraries
+   OCRmyPDF uses do not seem to handle this obscure compression format properly.
+   You may get errors or possible corrupted output images without this fix.
+
 v11.7.2
 =======
 

src/ocrmypdf/optimize.py

@@ -95,6 +95,10 @@ def extract_image_filter(
         log.debug(f"Skipping JPEG2000 iamge, xref {xref}")
         return None  # Don't do JPEG2000
 
+    if filtdp[0] == Name.CCITTFaxDecode and filtdp[1].get('/K', 0) >= 0:
+        log.debug(f"Skipping CCITT Group 3 image, xref {xref}")
+        return None  # pikepdf doesn't support Group 3 yet
+
     if Name.Decode in image:
         log.debug(f"Skipping image with Decode table, xref {xref}")
         return None  # Don't mess with custom Decode tables

tests/test_optimize.py

@@ -185,3 +185,16 @@ def test_optimize_off(resources, outpdf):
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
+
+
+def test_group3(resources, outdir):
+    with pikepdf.open(resources / 'ccitt.pdf') as pdf:
+        im = pdf.pages[0].Resources.XObject['/Im1']
+        assert (
+            opt.extract_image_filter(pdf, outdir, im, im.objgen[0]) is not None
+        ), "Group 4 should be allowed"
+
+        im.DecodeParms['/K'] = 0
+        assert (
+            opt.extract_image_filter(pdf, outdir, im, im.objgen[0]) is None
+        ), "Group 3 should be disallowed"