v14.4.0 docs and release notes

Instead present error message in exception.

.docker/Dockerfile

@@ -17,16 +17,32 @@ FROM base as builder
 
 # Note we need leptonica here to build jbig2
 RUN apt-get update && apt-get install -y --no-install-recommends \
+  build-essential autoconf automake libtool \
+  libleptonica-dev \
+  zlib1g-dev \
   python3-dev \
   python3-distutils \
+  libffi-dev \
   ca-certificates \
   curl \
   git \
   libcairo2-dev \
   pkg-config
 
-# Get the latest pip
+# Get the latest pip (Ubuntu version doesn't support manylinux2010)
-RUN curl https://bootstrap.pypa.io/get-pip.py | python3
+RUN \
+  curl https://bootstrap.pypa.io/get-pip.py | python3
+
+# Compile and install jbig2
+# Needs libleptonica-dev, zlib1g-dev
+RUN \
+  mkdir jbig2 \
+  && curl -L https://github.com/agl/jbig2enc/archive/ea6a40a.tar.gz | \
+  tar xz -C jbig2 --strip-components=1 \
+  && cd jbig2 \
+  && ./autogen.sh && ./configure && make && make install \
+  && cd .. \
+  && rm -rf jbig2
 
 COPY . /app
 
@@ -40,13 +56,11 @@ FROM base
 RUN apt-get update && apt-get install -y --no-install-recommends \
   software-properties-common gpg-agent
 RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel
-RUN add-apt-repository -y ppa:alex-p/jbig2enc
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
   fonts-droid-fallback \
   jbig2dec \
-  jbig2 \
   img2pdf \
   libsm6 libxext6 libxrender-dev \
   pngquant \

.github/workflows/build.yml

@@ -255,6 +255,32 @@ jobs:
           password: ${{ secrets.TOKEN_PYPI }}
           # repository_url: https://test.pypi.org/legacy/
 
+  create_release:
+    name: Create GitHub release
+    needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]
+    runs-on: ubuntu-latest
+    if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
+    permissions:
+      # Required to create a release
+      contents: write
+    steps:
+      - uses: actions/download-artifact@v3
+        with:
+          name: artifact
+          path: dist
+
+      - name: Create Release
+        id: create-release
+        uses: shogo82148/actions-create-release@v1
+
+      - name: Upload Assets
+        uses: shogo82148/actions-upload-release-asset@v1
+        with:
+          upload_url: ${{ steps.create-release.outputs.upload_url }}
+          asset_path: |
+            ./dist/*.whl
+            ./dist/*.tar.gz
+
   docker:
     name: Build Docker images
     needs: [wheel_sdist_linux, test_linux, test_macos, test_windows]

docs/cookbook.rst

@@ -372,3 +372,17 @@ Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
 
     Image processing and PDF/A conversion can also introduce lossy transformations
     to your PDF images, even when ``--optimize 1`` is in use.
+
+
+Digitally signed PDFs
+=====================
+
+OCRmyPDF cannot preserve digital signatures in PDFs and also add to OCR to them.
+By default, it will refuse to modify a signed PDF regardless of other settings. You can
+override this behavior with ``--invalidate-digital-signatures``; as the name suggests,
+any digital signatures will be invalidated.
+
+OCRmyPDF cannot open documents that are encrypted with a digital certificate.
+
+Versions of OCRmyPDF prior to 14.4.0 would invalidate existing digital signatures
+without warning.

docs/jbig2.rst

@@ -24,14 +24,6 @@ On macOS, Homebrew packages jbig2enc and OCRmyPDF includes it by
 default. The Docker image for OCRmyPDF also builds its own JBIG2 encoder
 from source.
 
-On Ubuntu, you can install the JBIG2 encoder using the following PPA:
-
-.. code-block:: bash
-
-   sudo add-apt-repository ppa:alex-p/jbig2enc
-   sudo apt update
-   sudo apt install jbig2enc
-
 For all other Linux, you must build a JBIG2 encoder from source:
 
 .. code-block:: bash

docs/release_notes.rst

@@ -28,6 +28,19 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v14.4.0
+=======
+
+-  Digitally signed PDFs are now detected. If the PDF is signed, OCRmyPDF will
+   refuse to modify it. Previously, only encrypted PDFs were detected, not
+   those that were signed but not encrypted. :issue:`1040`
+-  In addition, `--invalidate-digital-signatures` can be used to override the
+   above behavior and modify the PDF anyway. :issue:`1040`
+-  tqdm progress bars replaced with "rich" progress bars. The rich library is
+   a new dependency. Certain APIs that used tqdm are now deprecated and will
+   be removed in the next major release.
+-  Improved integration with GitHub Releases. Thanks to @stumpylog.
+
 v14.3.0
 =======
 

misc/completion/ocrmypdf.bash

@@ -31,6 +31,7 @@ __ocrmypdf_arguments()
 --force-ocr              (OCR documents that already have printable text)
 --skip-text              (skip OCR on any pages that already contain text)
 --redo-ocr               (redo OCR on any pages that seem to have OCR already)
+--invalidate-digital-signatures (remove digital signatures from PDF)
 --skip-big               (skip OCR on pages larger than this many MPixels)
 --optimize               (select optimization level)
 --jpeg-quality           (JPEG quality [0..100])

misc/completion/ocrmypdf.fish

@@ -16,6 +16,7 @@ complete -c ocrmypdf -l remove-vectors -d "don't send vector objects to OCR"
 complete -c ocrmypdf -s f -l force-ocr -d "OCR documents that already have printable text"
 complete -c ocrmypdf -s s -l skip-ocr -d "skip OCR on pages that text, otherwise try OCR"
 complete -c ocrmypdf -l redo-ocr -d "redo OCR on any pages that seem to have OCR already"
+complete -c ocrmypdf -l invalidate-digital-signatures -d "invalidate digital signatures and allow OCR to proceed"
 
 complete -c ocrmypdf -s k -l keep-temporary-files -d "keep temporary files (debug)"
 

pyproject.toml

@@ -17,7 +17,6 @@ license = {text = "MPL-2.0"}
 requires-python = ">=3.8"
 dependencies = [
   "Pillow>=8.2.0",
-  "coloredlogs>=14.0",
   "deprecation>=2.1.0",
   "img2pdf>=0.3.0", # pure Python
   "packaging>=20",
@@ -25,6 +24,7 @@ dependencies = [
   "pikepdf>=5.0.1",
   "pluggy>=0.13.0",
   "reportlab>=3.5.66",
+  "rich>=13",
   "tqdm>=4",
   "importlib-resources>=5;python_version<'3.9'",  # until Python 3.9
   "typing-extensions>=4;python_version<'3.10'",

src/ocrmypdf/_logging.py

@@ -8,6 +8,17 @@ from __future__ import annotations
 import logging
 from contextlib import suppress
 
+from rich.console import Console
+from rich.logging import RichHandler
+from rich.progress import (
+    BarColumn,
+    MofNCompleteColumn,
+    Progress,
+    TaskProgressColumn,
+    TextColumn,
+    TimeRemainingColumn,
+)
+from rich.table import Column
 from tqdm import tqdm
 
 
@@ -41,3 +52,59 @@ class TqdmConsole:
     def flush(self):
         with suppress(AttributeError):
             self.file.flush()
+
+
+class RichLoggingHandler(RichHandler):
+    def __init__(self, console: Console, **kwargs):
+        super().__init__(
+            console=console, show_level=False, show_time=False, markup=True, **kwargs
+        )
+
+
+class RichTqdmProgressAdapter:
+    """Adapt tqdm API to rich progress bar."""
+
+    def __init__(
+        self,
+        *,
+        console: Console,
+        desc: str,
+        total: float | None = None,
+        unit: str | None = None,
+        unit_scale: float | None = 1.0,
+        disable: bool = False,
+        **kwargs,
+    ):
+        self.progress = Progress(
+            TextColumn(
+                "[progress.description]{task.description}",
+                table_column=Column(min_width=20),
+            ),
+            BarColumn(),
+            TaskProgressColumn(),
+            MofNCompleteColumn(),
+            TimeRemainingColumn(),
+            console=console,
+            auto_refresh=True,
+            redirect_stderr=True,
+            redirect_stdout=False,
+            disable=disable,
+            **kwargs,
+        )
+        self.unit_scale = unit_scale
+        self.progress_bar = self.progress.add_task(
+            desc, total=total * self.unit_scale, unit=unit
+        )
+
+    def __enter__(self):
+        self.progress.start()
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self.progress.refresh()
+        self.progress.stop()
+        return False
+
+    def update(self, value=None):
+        advance = self.unit_scale if value is None else value
+        self.progress.update(self.progress_bar, advance=advance)

src/ocrmypdf/_pipeline.py

@@ -27,6 +27,7 @@ from ocrmypdf._jobcontext import PageContext, PdfContext
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (
+    DigitalSignatureError,
     DpiError,
     EncryptedPdfError,
     InputFileError,
@@ -80,34 +81,32 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             if im.info['dpi'] <= (96, 96) and not options.image_dpi:
                 log.info("Image size: (%d, %d)", *im.size)
                 log.info("Image resolution: (%d, %d)", *im.info['dpi'])
-                log.error(
+                raise DpiError(
                     "Input file is an image, but the resolution (DPI) is "
                     "not credible.  Estimate the resolution at which the "
                     "image was scanned and specify it using --image-dpi."
                 )
-                raise DpiError()
         elif not options.image_dpi:
             log.info("Image size: (%d, %d)", *im.size)
-            log.error(
+            raise DpiError(
                 "Input file is an image, but has no resolution (DPI) "
                 "in its metadata.  Estimate the resolution at which "
                 "image was scanned and specify it using --image-dpi."
             )
-            raise DpiError()
 
         if im.mode in ('RGBA', 'LA'):
-            log.error(
+            raise UnsupportedImageFormatError(
                 "The input image has an alpha channel. Remove the alpha "
                 "channel first."
             )
-            raise UnsupportedImageFormatError()
 
         if 'iccprofile' not in im.info:
             if im.mode == 'RGB':
                 log.info("Input image has no ICC profile, assuming sRGB")
             elif im.mode == 'CMYK':
-                log.error("Input CMYK image has no ICC profile, not usable")
+                raise UnsupportedImageFormatError(
-                raise UnsupportedImageFormatError()
+                    "Input CMYK image has no ICC profile, not usable"
+                )
 
     try:
         log.info("Image seems valid. Try converting to PDF...")
@@ -125,7 +124,6 @@ def triage_image_file(input_file: Path, output_file: Path, options) -> None:
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
-        log.error(e)
         raise UnsupportedImageFormatError() from e
 
 
@@ -195,18 +193,21 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
     options = context.options
 
     if pdfinfo.needs_rendering:
-        log.error(
+        raise InputFileError(
             "This PDF contains dynamic XFA forms created by Adobe LiveCycle "
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
-        raise InputFileError()
+    if pdfinfo.has_signature:
+        if options.invalidate_digital_signatures:
+            log.warning("All digital signatures will be invalidated")
+        else:
+            raise DigitalSignatureError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
-            log.error(
+            raise InputFileError(
                 "This PDF has a user fillable form. --redo-ocr is not "
                 "currently possible on such files."
             )
-            raise InputFileError()
         else:
             log.warning(
                 "This PDF has a fillable form. "
@@ -853,7 +854,9 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
     with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
         docinfo = get_docinfo(original, context)
         with pdf.open_metadata() as meta_pdf:
-            meta_pdf.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+            meta_pdf.load_from_docinfo(
+                docinfo, delete_missing=False, raise_failure=False
+            )
             # If xmp:CreateDate is missing, set it to the modify date to
             # ensure consistency with Ghostscript.
             if 'xmp:CreateDate' not in meta_pdf:

src/ocrmypdf/api.py

@@ -15,9 +15,6 @@ from pathlib import Path
 from typing import AnyStr, BinaryIO, Iterable, Union
 from warnings import warn
 
-import coloredlogs
-from humanfriendly.terminal import enable_ansi_support
-
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
@@ -112,14 +109,7 @@ def configure_logging(
     else:
         fmt = '%(pageno)s%(message)s'
 
-    use_colors = progress_bar_friendly
     formatter = None
-    if use_colors:
-        use_colors = enable_ansi_support()
-        if use_colors:
-            use_colors = coloredlogs.terminal_supports_colors()
-        if use_colors:
-            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
 
     if not formatter:
         formatter = logging.Formatter(fmt=fmt)

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -16,10 +16,10 @@ from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_compl
 from contextlib import suppress
 from typing import Callable, Iterable, Type, Union
 
-from tqdm import tqdm
+from rich.console import Console as RichConsole
 
 from ocrmypdf import Executor, hookimpl
-from ocrmypdf._logging import TqdmConsole
+from ocrmypdf._logging import RichLoggingHandler, RichTqdmProgressAdapter
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
@@ -168,13 +168,20 @@ def get_executor(progressbar_class):
     return StandardExecutor(pbar_class=progressbar_class)
 
 
+RICH_CONSOLE = RichConsole(stderr=True)
+
+
 @hookimpl
 def get_progressbar_class():
     """Return the default progress bar class."""
-    return tqdm
+
+    def partial_RichTqdmProgressAdapter(*args, **kwargs):
+        return RichTqdmProgressAdapter(*args, **kwargs, console=RICH_CONSOLE)
+
+    return partial_RichTqdmProgressAdapter
 
 
 @hookimpl
 def get_logging_console():
     """Return the default logging console handler."""
-    return logging.StreamHandler(stream=TqdmConsole(sys.stderr))
+    return RichLoggingHandler(console=RICH_CONSOLE)

src/ocrmypdf/cli.py

@@ -359,6 +359,13 @@ Online documentation is located at:
         help="Skip OCR on pages larger than the specified amount of megapixels, "
         "but include skipped pages in final output",
     )
+    ocrsettings.add_argument(
+        '--invalidate-digital-signatures',
+        action='store_true',
+        help="Normally, OCRmyPDF will refuse to OCR a PDF that has a digital "
+        "signature. This option allows OCR to proceed, but the digital signature "
+        "will be invalidated.",
+    )
 
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"

src/ocrmypdf/exceptions.py

@@ -108,6 +108,18 @@ class EncryptedPdfError(ExitCodeException):
     )
 
 
+class DigitalSignatureError(ExitCodeException):
+    """PDF has a digital signature."""
+
+    exit_code = ExitCode.input_file
+    message = dedent(
+        """\
+        Input PDF has a digital signature. OCR would alter the document,
+        invalidating the signature.
+        """
+    )
+
+
 class TesseractConfigError(ExitCodeException):
     """Tesseract config can't be parsed."""
 

src/ocrmypdf/extra_plugins/semfree.py

@@ -12,7 +12,7 @@ worker communicates only with the main process.
 
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
-It is less efficient than the standard implementation, so not th edefault.
+It is less efficient than the standard implementation, so not the default.
 """
 
 from __future__ import annotations

src/ocrmypdf/pdfinfo/info.py

@@ -21,7 +21,9 @@ from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence,
 from warnings import warn
 
 from pikepdf import (
+    Name,
     Object,
+    Page,
     Pdf,
     PdfImage,
     PdfInlineImage,
@@ -491,15 +493,15 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     since the object does not know its own name.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
+    resources = container[Name.Resources]
-    if '/XObject' not in resources:
+    if Name.XObject not in resources:
         return
-    for key, candidate in resources['/XObject'].items():
+    for key, candidate in resources[Name.XObject].items():
-        if candidate is None or '/Subtype' not in candidate:
+        if candidate is None or Name.Subtype not in candidate:
             continue
-        if candidate['/Subtype'] == '/Image':
+        if candidate[Name.Subtype] == Name.Image:
             pdfimage = candidate
             yield (pdfimage, key)
 
@@ -535,15 +537,15 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     The container may be a page, or a parent Form XObject.
 
     """
-    if '/Resources' not in container:
+    if Name.Resources not in container:
         return
-    resources = container['/Resources']
+    resources = container[Name.Resources]
-    if '/XObject' not in resources:
+    if Name.XObject not in resources:
         return
-    xobjs = resources['/XObject'].as_dict()
+    xobjs = resources[Name.XObject].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate is None or candidate['/Subtype'] != '/Form':
+        if candidate is None or candidate[Name.Subtype] != Name.Form:
             continue
 
         form_xobject = candidate
@@ -581,16 +583,19 @@ def _process_content_streams(
     downsampling.
 
     """
-    if container.get('/Type') == '/Page' and '/Contents' in container:
+    if container.get(Name.Type) == Name.Page and Name.Contents in container:
         initial_shorthand = shorthand or UNIT_SQUARE
-    elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
+    elif (
+        container.get(Name.Type) == Name.XObject
+        and container[Name.Subtype] == Name.Form
+    ):
         # Set the CTM to the state it was when the "Do" operator was
         # encountered that is drawing this instance of the Form XObject
         ctm = PdfMatrix(shorthand) if shorthand else PdfMatrix.identity()
 
         # A Form XObject may provide its own matrix to map form space into
         # user space. Get this if one exists
-        form_shorthand = container.get('/Matrix', PdfMatrix.identity())
+        form_shorthand = container.get(Name.Matrix, PdfMatrix.identity())
         form_matrix = PdfMatrix(form_shorthand)
 
         # Concatenate form matrix with CTM to ensure CTM is correct for
@@ -771,7 +776,7 @@ class PageInfo:
         check_pages: Container[int],
         detailed_analysis: bool,
     ):
-        page = pdf.pages[pageno]
+        page: Page = pdf.pages[pageno]
         mediabox = [Decimal(d) for d in page.MediaBox.as_list()]
         width_pt = mediabox[2] - mediabox[0]
         height_pt = mediabox[3] - mediabox[1]
@@ -779,7 +784,7 @@ class PageInfo:
         check_this_page = pageno in check_pages
 
         if check_this_page and detailed_analysis:
-            pscript5_mode = str(pdf.docinfo.get('/Creator')).startswith('PScript5')
+            pscript5_mode = str(pdf.docinfo.get(Name.Creator)).startswith('PScript5')
             miner = get_page_analysis(infile, pageno, pscript5_mode)
             self._textboxes = list(simplify_textboxes(miner, get_text_boxes))
             bboxes = (box.bbox for box in self._textboxes)
@@ -789,17 +794,13 @@ class PageInfo:
             self._textboxes = []
             self._has_text = None  # i.e. "no information"
 
-        userunit = page.get('/UserUnit', Decimal(1.0))
+        userunit = page.get(Name.UserUnit, Decimal(1.0))
         if not isinstance(userunit, Decimal):
             userunit = Decimal(userunit)
         self._userunit = userunit
         self._width_inches = width_pt * userunit / Decimal(72.0)
         self._height_inches = height_pt * userunit / Decimal(72.0)
-
+        self._rotate = int(getattr(page.obj, 'Rotate', 0))
-        try:
-            self._rotate = int(page['/Rotate'])
-        except KeyError:
-            self._rotate = 0
 
         userunit_shorthand = (userunit, 0, 0, userunit, 0, 0)
 
@@ -953,6 +954,10 @@ DEFAULT_EXECUTOR = SerialExecutor()
 class PdfInfo:
     """Get summary information about a PDF."""
 
+    _has_acroform: bool = False
+    _has_signature: bool = False
+    _needs_rendering: bool = False
+
     def __init__(
         self,
         infile,
@@ -980,13 +985,13 @@ class PdfInfo:
                 check_pages=check_pages,
                 detailed_analysis=detailed_analysis,
             )
-            self._needs_rendering = pdf.Root.get('/NeedsRendering', False)
+            self._needs_rendering = pdf.Root.get(Name.NeedsRendering, False)
-            self._has_acroform = False
+            if Name.AcroForm in pdf.Root:
-            if '/AcroForm' in pdf.Root:
+                if len(pdf.Root.AcroForm.get(Name.Fields, [])) > 0:
-                if len(pdf.Root.AcroForm.get('/Fields', [])) > 0:
                     self._has_acroform = True
-                elif '/XFA' in pdf.Root.AcroForm:
+                elif Name.XFA in pdf.Root.AcroForm:
                     self._has_acroform = True
+                self._has_signature = bool(pdf.Root.AcroForm.get(Name.SigFlags, 0) & 1)
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
@@ -1006,9 +1011,14 @@ class PdfInfo:
 
     @property
     def has_acroform(self) -> bool:
-        """Return True if any page has an AcroForm."""
+        """Return True if the document catalog has an AcroForm."""
         return self._has_acroform
 
+    @property
+    def has_signature(self) -> bool:
+        """Return True if the document annotations has a digital signature."""
+        return self._has_signature
+
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""

tests/test_acroform.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 
 import logging
 
+import pikepdf
 import pytest
 
 import ocrmypdf
@@ -19,10 +20,11 @@ def acroform(resources):
     return resources / 'acroform.pdf'
 
 
-def test_acroform_and_redo(acroform, caplog, no_outpdf):
+def test_acroform_and_redo(acroform, no_outpdf):
-    with pytest.raises(ocrmypdf.exceptions.InputFileError):
+    with pytest.raises(
+        ocrmypdf.exceptions.InputFileError, match='--redo-ocr is not currently possible'
+    ):
         check_ocrmypdf(acroform, no_outpdf, '--redo-ocr')
-    assert '--redo-ocr is not currently possible' in caplog.text
 
 
 def test_acroform_message(acroform, caplog, outpdf):
@@ -30,3 +32,23 @@ def test_acroform_message(acroform, caplog, outpdf):
     check_ocrmypdf(acroform, outpdf, '--plugin', 'tests/plugins/tesseract_noop.py')
     assert 'fillable form' in caplog.text
     assert '--force-ocr' in caplog.text
+
+
+@pytest.fixture
+def digitally_signed(acroform, outdir):
+    out = outdir / 'acroform_signed.pdf'
+    with pikepdf.open(acroform) as pdf:
+        pdf.Root.AcroForm.SigFlags = 3
+        pdf.save(out)
+    yield out
+
+
+def test_digital_signature(digitally_signed, no_outpdf):
+    with pytest.raises(ocrmypdf.exceptions.DigitalSignatureError):
+        check_ocrmypdf(digitally_signed, no_outpdf)
+
+
+def test_digital_signature_invalidate(digitally_signed, no_outpdf):
+    check_ocrmypdf(
+        digitally_signed, no_outpdf, '--force-ocr', '--invalidate-digital-signatures'
+    )