v11.7.3 release notes

See https://github.com/python-pillow/Pillow/blob/master/CHANGES.rst

docs/release_notes.rst

@@ -12,6 +12,21 @@ 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
+=======
+
+-  Updated pinned versions in main.txt, primarily to upgrade Pillow to 8.1.2, due
+   to recently disclosed security vulnerabilities in that software.
+-  The ``--sidecar`` parameter now causes an exception if set to the same file as
+   the input or output PDF.
+
 v11.7.1
 =======
 

requirements/main.txt

@@ -1,12 +1,12 @@
 # requirements.txt can be used to replicate the developer's build environment
 # setup.py lists a separate set of requirements that are looser to simplify
 # installation
-cffi == 1.14.3
+cffi == 1.14.5
-coloredlogs == 14.0  # technically optional
+coloredlogs == 15.0  # technically optional
 img2pdf == 0.4.0
 pdfminer.six == 20201018
-pikepdf == 2.0.0
+pikepdf == 2.9.0
 pluggy == 0.13.1
-Pillow == 8.0.1
+Pillow == 8.1.2
-reportlab == 3.5.55
+reportlab == 3.5.65
-tqdm == 4.51.0
+tqdm == 4.59.0

requirements/test.txt

@@ -1,7 +1,7 @@
-pytest >= 5.0.0
+pytest >= 6.0.0
 pytest-helpers-namespace >= 2019.1.8
-pytest-xdist >= 1.31.0
+pytest-xdist >= 2.2.0
-pytest-cov >= 2.10.0
+pytest-cov >= 2.11.1
 python-xmp-toolkit == 2.0.1  # requires apt-get install libexempi3
                      # or brew install exempi
 #PyMuPDF == 1.13.4    # optional

requirements/watcher.txt

@@ -1 +1 @@
-watchdog == 0.10.2
+watchdog == 1.0.2

src/ocrmypdf/_validation.py

@@ -112,6 +112,10 @@ def check_options_sidecar(options):
                 "--sidecar filename must be specified when output file is stdout."
             )
         options.sidecar = options.output_file + '.txt'
+    if options.sidecar == options.input_file or options.sidecar == options.output_file:
+        raise BadArgsError(
+            "--sidecar file must be different from the input and output files"
+        )
 
 
 def check_options_preprocessing(options):

src/ocrmypdf/cli.py

@@ -167,7 +167,8 @@ Online documentation is located at:
         metavar='FILE',
         help="Generate sidecar text files that contain the same text recognized "
         "by Tesseract. This may be useful for building a OCR text database. "
-        "If FILE is omitted, the sidecar file be named {output_file}.txt "
+        "If FILE is omitted, the sidecar file be named {output_file}.txt; the next "
+        "argument must NOT be the name of the input PDF. "
         "If FILE is set to '-', the sidecar is written to stdout (a "
         "convenient way to preview OCR quality). The output file and sidecar "
         "may not both use stdout at the same time.",

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"

tests/test_validation.py

@@ -18,6 +18,8 @@ from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import BadArgsError, MissingDependencyError
 from ocrmypdf.pdfinfo import PdfInfo
 
+run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api
+
 
 def make_opts_pm(input_file='a.pdf', output_file='b.pdf', language='eng', **kwargs):
     if language is not None:
@@ -270,3 +272,9 @@ def test_two_languages():
             *make_opts_pm(language='fakelang1+fakelang2'), {'fakelang1', 'fakelang2'}
         )
         mock.assert_called()
+
+
+def test_sidecar_equals_output(resources, no_outpdf):
+    op = no_outpdf
+    with pytest.raises(BadArgsError, match=r'--sidecar'):
+        run_ocrmypdf_api(resources / 'trivial.pdf', op, '--sidecar', op)