v13.4.5 release notes

Needing to update this every time has become more inconvenient than dealing
with the occasional breakage in a new release.

.docker/Dockerfile

@@ -1,7 +1,7 @@
 # OCRmyPDF
 #
 
-FROM ubuntu:21.04 as base
+FROM ubuntu:22.04 as base
 
 ENV LANG=C.UTF-8
 ENV TZ=UTC

.github/ISSUE_TEMPLATE/2-problem-with-a-specific-input-file.md

@@ -22,7 +22,7 @@ Run with verbosity or higher `-v1` to see more detailed logging. This informatio
 **Example file**
 If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
 
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
 
 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 

.github/ISSUE_TEMPLATE/3-feature_request.md

@@ -19,7 +19,7 @@ A clear and concise description of any alternative solutions or features you've
 **Example file**
 If your issue concerns how OCRmyPDF processes certain files, and please provide an example file that helps illustrate how OCRmyPDF's output could be improve.
 
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/jbarlow83/OCRmyPDF/wiki) for OCRmyPDF's author only.
+Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/ocrmypdf/OCRmyPDF/wiki) for OCRmyPDF's author only.
 
 Links to files hosted elsewhere are perfectly acceptable. You could also look in ``tests/resources`` and see if any of those files reproduce your issue.
 

.github/workflows/build.yml

@@ -21,17 +21,19 @@ jobs:
       matrix:
         include:
           - os: ubuntu-18.04
-            python: 3.7
+            python: "3.7"
           - os: ubuntu-20.04
-            python: 3.8
+            python: "3.8"
           - os: ubuntu-20.04
-            python: 3.9
+            python: "3.9"
+          - os: ubuntu-20.04
+            python: "3.10"
           - os: ubuntu-latest
-            python: 3.9
+            python: "3.9"
           - os: ubuntu-latest
             python: "pypy-3.7"
           - os: ubuntu-latest
-            python: 3.9
+            python: "3.9"
             tesseract5: true
 
     env:
@@ -120,7 +122,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.9"]
+        python: ["3.9", "3.10"]
 
     env:
       OS: ${{ matrix.os }}
@@ -175,7 +177,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9"]
+        python: ["3.9", "3.10"]
 
     env:
       OS: ${{ matrix.os }}

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.1.0
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
@@ -8,26 +8,26 @@ repos:
       - id: check-yaml
       - id: debug-statements
   - repo: https://github.com/pycqa/isort
-    rev: 5.9.3
+    rev: 5.10.1
     hooks:
       - id: isort
         args: ["--profile", "black"]
   - repo: https://github.com/psf/black
-    rev: 21.9b0
+    rev: 22.3.0
     hooks:
       - id: black
         language_version: python
   - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.19.0
+    rev: v1.20.1
     hooks:
       - id: setup-cfg-fmt
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.29.0
+    rev: v2.31.1
     hooks:
       - id: pyupgrade
         args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.910-1
+    rev: v0.942
     hooks:
       - id: mypy
         additional_dependencies:

README.md

@@ -1,9 +1,7 @@
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
-[![Build Status](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+[![Build Status](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
 
-[azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-[travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
@@ -106,7 +104,7 @@ ocrmypdf --help
 
 Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/en/latest/index.html).
 
-Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
+Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
 ## Requirements
 

debian/copyright

@@ -1,7 +1,7 @@
 Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
 Upstream-Name: OCRmyPDF
 Upstream-Contact: James R. Barlow <barlow.jim@gmail.com>
-Source: https://github.com/jbarlow83/OCRmyPDF
+Source: https://github.com/ocrmypdf/OCRmyPDF
 
 Files: *
 Copyright:

docs/advanced.rst

@@ -67,11 +67,11 @@ without modifying the PDF. This is to ensure that PDFs that were
 previously OCRed or were "born digital" rather than scanned are not
 processed.
 
-If ``--skip-text`` is issued, then no OCR will be performed on pages
-that already have text. The page will be copied to the output. This may
-be useful for documents that contain both "born digital" and scanned
-content, or to use OCRmyPDF to normalize and convert to PDF/A regardless
-of their contents.
+If ``--skip-text`` is issued, then no image processing or OCR will be
+performed on pages that already have text. The page will be copied to
+the output. This may be useful for documents that contain both "born
+digital" and scanned content, or to use OCRmyPDF to normalize and
+convert to PDF/A regardless of their contents.
 
 If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
 Text is categorized as either visible or invisible. Invisible text (OCR)

docs/api.rst

@@ -68,6 +68,14 @@ OCRmyPDF, use processes.
     not take at least one of these steps, process semantics will prevent
     OCRmyPDF from working correctly.
 
+.. warning::
+
+    On macOS with Python 3.7, you must call
+    :func:`multiprocessing.set_start_method("spawn")`. Without this, multiprocessing
+    will be unstable. From the command line, OCRmyPDF does this automatically,
+    but as an API user you must do this. See Python bpo-33725 for details.
+    Python 3.8+ also resolve this automatically.
+
 Logging
 -------
 

docs/conf.py

@@ -42,7 +42,7 @@ extensions = [
 # Extension settings
 intersphinx_mapping = {'https://docs.python.org/': None}
 napoleon_use_rtype = False
-issues_github_path = "jbarlow83/OCRmyPDF"
+issues_github_path = "ocrmypdf/OCRmyPDF"
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']

docs/cookbook.rst

@@ -243,10 +243,11 @@ You can also optimize all images without performing any OCR:
 
     ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
 
-Perform OCR only certain pages
-------------------------------
+Process only certain pages
+--------------------------
 
-You can ask OCRmyPDF to only apply OCR to certain pages.
+You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
+and OCR to certain pages.
 
 .. code-block:: bash
 
@@ -260,10 +261,10 @@ overlap pages. OCRmyPDF does not currently account for document page numbers,
 such as an introduction section of a book that uses Roman numerals. It simply
 counts the number of virtual pieces of paper since the start.
 
-Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages in
-the file and convert it to PDF/A, unless you disable those options. In this
-example, we want to OCR only the title and otherwise change the PDF as little
-as possible:
+Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
+in the file and convert it to PDF/A, unless you disable those options. Both of these
+steps are "whole file" operations. In this example, we want to OCR only the title
+and otherwise change the PDF as little as possible:
 
 .. code-block:: bash
 

docs/docker.rst

@@ -59,7 +59,7 @@ Using the Docker image on the command line
 ==========================================
 
 **Unlike typical Docker containers**, in this section the OCRmyPDF Docker
-container is emphemeral – it runs for one OCR job and terminates, just like a
+container is ephemeral – it runs for one OCR job and terminates, just like a
 command line program. We are using Docker to deliver an application (as opposed
 to the more conventional case, where a Docker container runs as a server).
 

docs/installation.rst

@@ -375,7 +375,7 @@ languages you can optionally install them all:
 .. note::
 
    Users who previously installed OCRmyPDF from the private tap should
-   switch to the mainline version (``brew untap jbarlow83/ocrmypdf``)
+   switch to the mainline version (``brew untap ocrmypdf/OCRmyPDF``)
    and install from there.
 
 Manual installation on macOS
@@ -696,7 +696,7 @@ environment:
 
 .. code-block:: bash
 
-    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip3 install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 Or, to install in `development
 mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
@@ -704,14 +704,14 @@ allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
 
-    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip3 install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 You may find it easiest to install in a virtual environment, rather than
 system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
@@ -738,7 +738,7 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF

docs/jbig2.rst

@@ -32,6 +32,9 @@ For all other Linux, you must build a JBIG2 encoder from source:
 
 .. _jbig2-lossy:
 
+Dependencies include libtoolize and libleptonica, which on Ubuntu systems 
+are packaged as libtool and libleptonica-dev.
+
 Lossy mode JBIG2
 ================
 

docs/languages.rst

@@ -54,6 +54,33 @@ to what languages it should search for. Multiple languages can be
 requested using either ``-l eng+fra`` (English and French) or
 ``-l eng -l fra``.
 
+Gentoo users
+============
+
+On Gentoo the package ``app-text/tessdata_fast``, which ``app-text/tesseract`` depends on, handles Tesseract languages.
+It accepts USE flags to select what languages should be installed, these can be set in ``/etc/portage/package.use``.
+Alternatively one can globally set the `L10N use extension <https://wiki.gentoo.org/wiki/Localization/Guide#L10N>`__ in ``/etc/portage/make.conf``.
+This enables these languages for all packages (e.g. including aspell).
+
+.. code-block:: bash
+
+   # Display a list of all Tesseract language packs
+   equery uses app-text/tessdata_fast
+   
+   # Add English and German language support for Tesseract only
+   echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
+   
+   # Add global English and German language support (the `l10n_` from equery has to be omited)
+   echo L10N="de en" >> /etc/portage/make.conf
+   
+   # update system to reflect changed USE flags
+   emerge --update --deep --newuse @world
+
+You can then pass the ``-l LANG`` argument to OCRmyPDF to give a hint as
+to what languages it should search for. Multiple languages can be
+requested using either ``-l eng+fra`` (English and French) or
+``-l eng -l fra``.
+
 macOS users
 ===========
 

docs/maintainers.rst

@@ -2,7 +2,7 @@
 Maintainer notes
 ================
 
-This is for those who package OCRmyPDF for downstream use.  (Thank you 
+This is for those who package OCRmyPDF for downstream use.  (Thank you
 for your hard work.)
 
 Known ports/packagers
@@ -25,7 +25,7 @@ Non-Python dependencies
 
 Note that we have non-Python dependencies. In particular, OCRmyPDF requires
 Ghostscript and Tesseract OCR to be installed and needs to be able to locate their
-binaries on the system PATH. On Windows, OCRmyPDF will also check the registry 
+binaries on the system PATH. On Windows, OCRmyPDF will also check the registry
 for their locations.
 
 Tesseract OCR relies on SIMD for performance and only has proper support for this
@@ -38,13 +38,13 @@ OCRmyPDF uses setuptools-scm for versioning, which derives the version from
 Git as a single source of truth. This may be unsuitable for some distributions, e.g.
 to indicate that your distribution modifies OCRmyPDF in some way.
 
-You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if 
+You can patch the ``__version__`` variable in ``src/ocrmypdf/_version.py`` if
 necessary.
 
 OCRmyPDF uses setuptools-scm-git-archive to ensure that tarballs downloaded from
 GitHub contain version information. Unfortunately, these tarballs are not always
-deterministic. See this 
-`issue <https://github.com/jbarlow83/OCRmyPDF/issues/841#issuecomment-936562696>`_.
+deterministic. See this
+`issue <https://github.com/ocrmypdf/OCRmyPDF/issues/841#issuecomment-936562696>`_.
 
 jbig2enc
 --------

docs/plugins.rst

@@ -152,6 +152,16 @@ hooks. As such, you cannot "chain" a series of plugin filters together in this
 way. Instead, a single hook implementation should be responsible for any such
 chaining operations.
 
+Examples
+========
+
+* OCRmyPDF's test suite contains several plugins that are used to simulate certain
+  test conditions.
+* `ocrmypdf-papermerge <https://github.com/papermerge/OCRmyPDF_papermerge>`_ is
+  a production plugin that integrates OCRmyPDF and the Papermerge document
+  management system.
+
+
 Custom command line arguments
 -----------------------------
 

docs/release_notes.rst

@@ -12,11 +12,96 @@ 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.
 
-.. note::
+The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
+referred to in these notes may exist the main branch but have not been
+tagged yet.
 
-   Python 3.6 reaches end of life on December 23, 2021. We have already ended support
-   for Python 3.6 but might release fixes for critical issues if necessary before that
-   date.
+.. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
+
+v13.4.5
+=======
+
+-  Remove upper bound on pdfminer.six version.
+-  Documentation.
+
+v13.4.4
+=======
+
+-  Updated pdfminer.six version.
+-  Docker image changed to Ubuntu 22.04 now that it is released and provides the
+   dependencies we need. This seems more consistent than our recent change to
+   Debian.
+
+v13.4.3
+=======
+
+-  Fix error on pytest.skip() with older versions of pytest.
+-  Documentation updates.
+
+v13.4.2
+=======
+
+-  Worked around a
+   `major regression in Ghostscript 9.56.0 <https://bugs.ghostscript.com/show_bug.cgi?id=705187>`__
+   where **all OCR text is stripped out of the PDF**. It simply removes all text,
+   even generated by software other than OCRmyPDF. Fortunately, we can ask
+   Ghostscript 9.56.0 to use its old behavior that worked correctly for our purposes.
+   Users must avoid the combination (Ghostscript 9.56.0, ocrmypdf <13.4.2) since
+   older versions of OCRmyPDF have no way of detecting that this particular
+   version of Ghostscript removes all OCR text.
+-  Marked pdfminer 20220319 as supported.
+-  Fixed some deprecation warnings from recent versions of Pillow and pytest.
+-  Test suite now covers Python 3.10 (Python 3.10 worked fine before, but was not
+   being tested).
+-  Docker image now uses debian:bookworm-slim as the base image to fix the Docker
+   image build.
+
+v13.4.1
+=======
+
+-  Temporarily make threads rather than processes the default executor worker, due
+   to a persistent deadlock issue when processes are used. Add a new command line
+   argument ``--no-use-threads`` to disable this.
+
+v13.4.0
+=======
+
+-  Fixed test failures when using pikepdf 5.0.0.
+-  Various improvements to the optimizer. In particular, we now recognize PDF images
+   that are encoded with both deflate (PNG) and DCT (JPEG), and also produce PDF
+   with images compressed with deflate and DCT, since this often yields file size
+   improvements compared to plain DCT.
+
+v13.3.0
+=======
+
+-  Made a harmless but "scary" exception after failing to optimize an image less scary.
+-  Added a warning if a page image is too large for unpaper to clean. The image is
+   passed through without cleaning. This is due to a hard-coded limitation in a
+   C library used by unpaper so it cannot be rectified easily.
+-  We now use better default settings when calling img2pdf.
+-  We no longer try to optimize images that we failed to save in certain situations.
+-  We now account for some differences in text output from Tesseract 5 compared to
+   Tesseract 4.
+-  Better handling of Ghostscript producing empty images when attempting to rasterize
+   page images.
+
+v13.2.0
+=======
+
+-  Removed all runtime uses of distutils since it is deprecated in standard library. We
+   previous used ``distutils.version`` to examine version numbers of dependencies
+   at run time, and now use ``packaging.version`` for this. This is a new
+   dependency.
+-  Fixed an error message advising the user that Ghostscript was not installed being
+   suppressed when this condition actually happens.
+-  Fixed an issue with incorrect page number and totals being displayed in the progress
+   bar. This was purely a display/presentation issue. :issue:`876`.
+
+v13.1.1
+=======
+
+-  Fixed issue with attempting to deskew a blank page on Tesseract 5. :issue:`868`.
 
 v13.1.0
 =======
@@ -48,7 +133,7 @@ v13.0.0
    Tesseract 5.x has implemented improvements to thresholding, so this feature will be
    redundant anyway.
 -  ``--deskew`` was previous calculated by a Leptonica algorithm. We now use a feature
-   of Tesseract to term the appropriate the angle to deskew a page. The deskew angle
+   of Tesseract to find the appropriate the angle to deskew a page. The deskew angle
    according to Tesseract may differ from Leptonica's algorithm. At least in theory,
    Tesseract's deskew angle is informed by a more complex analysis than Leptonica,
    so this should improve results in general. We also use Pillow to perform the

misc/webservice.py

@@ -59,7 +59,7 @@ def do_ocrmypdf(file):
         return Response("--sidecar not supported", 501, mimetype='text/plain')
 
     ocrmypdf_args = ["ocrmypdf", *cmd_args, up_file, down_file]
-    proc = run(ocrmypdf_args, stdout=PIPE, stderr=PIPE, encoding="utf-8")
+    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8")
     if proc.returncode != 0:
         stderr = proc.stderr
         return Response(stderr, 400, mimetype='text/plain')

setup.cfg

@@ -3,7 +3,7 @@ name = ocrmypdf
 description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
 long_description = file: README.md
 long_description_content_type = text/markdown
-url = https://github.com/jbarlow83/OCRmyPDF
+url = https://github.com/ocrmypdf/OCRmyPDF
 author = James R. Barlow
 author_email = james@purplerock.ca
 license = MPL-2.0
@@ -39,8 +39,8 @@ keywords =
     scanning
 project_urls =
     Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/jbarlow83/ocrmypdf
-    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
+    Source = https://github.com/ocrmypdf/OCRmyPDF
+    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
 
 [options]
 packages = find:
@@ -48,8 +48,9 @@ install_requires =
     Pillow>=8.2.0
     coloredlogs>=14.0  # strictly optional
     img2pdf>=0.3.0,<0.5  # pure Python
-    pdfminer.six!=20200720,>=20191110,<=20211012
-    pikepdf>=4.0.0
+    packaging>=20
+    pdfminer.six!=20200720,>=20191110
+    pikepdf!=5.0.0,>=4.0.0
     pluggy>=0.13.0,<2
     reportlab>=3.5.66
     tqdm>=4

src/ocrmypdf/_exec/ghostscript.py

@@ -18,12 +18,19 @@ from shutil import which
 from subprocess import PIPE, CalledProcessError
 from typing import Optional
 
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
+
 log = logging.getLogger(__name__)
 
 missing_gs_error = """
@@ -71,7 +78,8 @@ def jpeg_passthrough_available() -> bool:
 
 
 def _gs_error_reported(stream) -> bool:
-    return True if re.search(r'error', stream, flags=re.IGNORECASE) else False
+    match = re.search(r'error', stream, flags=re.IGNORECASE)
+    return bool(match)
 
 
 def rasterize_pdf(
@@ -124,20 +132,27 @@ def rasterize_pdf(
         if _gs_error_reported(stderr):
             log.error(stderr)
 
-    with Image.open(BytesIO(p.stdout)) as im:
-        if rotation is not None:
-            log.debug("Rotating output by %i", rotation)
-            # rotation is a clockwise angle and Image.ROTATE_* is
-            # counterclockwise so this cancels out the rotation
-            if rotation == 90:
-                im = im.transpose(Image.ROTATE_90)
-            elif rotation == 180:
-                im = im.transpose(Image.ROTATE_180)
-            elif rotation == 270:
-                im = im.transpose(Image.ROTATE_270)
-            if rotation % 180 == 90:
-                page_dpi = page_dpi.flip_axis()
-        im.save(fspath(output_file), dpi=page_dpi)
+    try:
+        with Image.open(BytesIO(p.stdout)) as im:
+            if rotation is not None:
+                log.debug("Rotating output by %i", rotation)
+                # rotation is a clockwise angle and Image.ROTATE_* is
+                # counterclockwise so this cancels out the rotation
+                if rotation == 90:
+                    im = im.transpose(Transpose.ROTATE_90)
+                elif rotation == 180:
+                    im = im.transpose(Transpose.ROTATE_180)
+                elif rotation == 270:
+                    im = im.transpose(Transpose.ROTATE_270)
+                if rotation % 180 == 90:
+                    page_dpi = page_dpi.flip_axis()
+            im.save(fspath(output_file), dpi=page_dpi)
+    except UnidentifiedImageError:
+        log.error(
+            f"Ghostscript (using {raster_device} at {raster_dpi} dpi) produced "
+            "an invalid page image file."
+        )
+        raise
 
 
 class GhostscriptFollower:
@@ -161,8 +176,7 @@ class GhostscriptFollower:
                 )
                 return
         else:
-            m = self.re_page.match(line.strip())
-            if m:
+            if self.re_page.match(line.strip()):
                 self.progressbar.update()
 
 
@@ -203,14 +217,18 @@ def generate_pdfa(
     # Older versions of Ghostscript expect a leading slash in
     # sColorConversionStrategy, newer ones should not have it. See Ghostscript
     # git commit fe1c025d.
-    strategy = ('/' + strategy) if version() < '9.19' else strategy
+    gs_version = version()
+    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
 
-    if version() == '9.23':
+    if gs_version == '9.23':
         # 9.23: added JPEG passthrough as a new feature, but with a bug that
         # incorrectly formats some images. Fixed as of 9.24. So we disable this
         # feature for 9.23.
         # https://bugs.ghostscript.com/show_bug.cgi?id=699216
         compression_args.append('-dPassThroughJPEGImages=false')
+    elif gs_version == '9.56.0':
+        # 9.56.0 breaks our OCR...?
+        compression_args.append('-dNEWPDF=false')
 
     # nb no need to specify ProcessColorModel when ColorConversionStrategy
     # is set; see:

src/ocrmypdf/_exec/tesseract.py

@@ -9,13 +9,13 @@
 
 import logging
 import re
-from distutils.version import StrictVersion
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
 from typing import Dict, Iterator, List, Optional
 
+from packaging.version import Version
 from PIL import Image
 
 from ocrmypdf.exceptions import (
@@ -60,25 +60,54 @@ class TesseractLoggerAdapter(logging.LoggerAdapter):
         return '[tesseract] %s' % (msg), kwargs
 
 
-class TesseractVersion(StrictVersion):
-
-    version_re = re.compile(
-        r'''
-        ^(\d+) \. (\d+) (\. (\d+))?  # groups: 1/major, 2/minor, 3/[skip], 4/patch
-        [-]?  # optional hyphen separator
-        (?: ((?:alpha|beta|rc|dev)\d*)? [.\-\ ]? (\d+)? )?  # 5/prerelease, 6/prerelease_num
-        (?:(?:-\d+)?-g[0-9a-f]+)?  # untagged git version
-        $
-        ''',
-        re.VERBOSE | re.ASCII,
+TESSERACT_VERSION_PATTERN = r"""
+    v?
+    (?:
+        (?:(?P<epoch>[0-9]+)!)?                           # epoch
+        (?P<release>[0-9]+(?:\.[0-9]+)*)                  # release segment
+        (?P<pre>                                          # pre-release
+            [-_\.]?
+            (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
+            [-_\.]?
+            (?P<pre_n>[0-9]+)?
+        )?
+        (?P<post>                                         # post release
+            (?:-(?P<post_n1>[0-9]+))
+            |
+            (?:
+                [-_\.]?
+                (?P<post_l>post|rev|r)
+                [-_\.]?
+                (?P<post_n2>[0-9]+)?
+            )
+        )?
+        (?P<dev>                                          # dev release
+            [-_\.]?
+            (?P<dev_l>dev)
+            [-_\.]?
+            (?P<dev_n>[0-9]+)?
+        )?
+        (?P<date>
+            [-_\.]
+            (?:20[0-9][0-9] [0-1][0-9] [0-3][0-9])       # yyyy mm dd
+        )?
+        (?P<gitcount>
+            [-_\.]?
+            [0-9]+
+        )?
+        (?P<gitcommit>
+            [-_\.]?
+            g[0-9a-f]{2,10}
+        )?
     )
+    (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))?       # local version
+"""
 
-    def parse(self, vstring):
-        try:
-            super().parse(vstring)
-        except TypeError as e:
-            if 'int() argument must be a string' in str(e):
-                super().parse(vstring + '-0')
+
+class TesseractVersion(Version):
+    _regex = re.compile(
+        r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
+    )
 
 
 def version() -> str:
@@ -200,7 +229,9 @@ def get_deskew(
     except CalledProcessError as e:
         tesseract_log_output(e.stdout)
         tesseract_log_output(e.stderr)
-        if b'Empty page!!' in e.output:  # Not enough info for a skew angle
+        if b'Empty page!!' in e.output or (
+            e.output == b'' and e.returncode == 1
+        ):  # Not enough info for a skew angle - Tess 4 and 5 return different errors
             return 0.0
 
         raise SubprocessOutputError() from e
@@ -313,7 +344,7 @@ def generate_hocr(
         _generate_null_hocr(output_hocr, output_text, input_file)
     except CalledProcessError as e:
         tesseract_log_output(e.output)
-        if b'Image too large' in e.output:
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
             _generate_null_hocr(output_hocr, output_text, input_file)
             return
 
@@ -385,7 +416,7 @@ def generate_pdf(
         use_skip_page(output_pdf, output_text)
     except CalledProcessError as e:
         tesseract_log_output(e.output)
-        if b'Image too large' in e.output:
+        if b'Image too large' in e.output or b'Empty page!!' in e.output:
             use_skip_page(output_pdf, output_text)
             return
         raise SubprocessOutputError() from e

src/ocrmypdf/_exec/unpaper.py

@@ -13,69 +13,94 @@
 import logging
 import os
 import shlex
+from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
 from tempfile import TemporaryDirectory
-from typing import List, Optional, Tuple, Union
+from typing import Iterator, List, Optional, Tuple, Union
 
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
-from ocrmypdf.subprocess import get_version
-from ocrmypdf.subprocess import run as external_run
+from ocrmypdf.subprocess import get_version, run
+
+UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
 DecFloat = Union[Decimal, float]
 
 log = logging.getLogger(__name__)
 
 
+class UnpaperImageTooLargeError(Exception):
+    def __init__(
+        self,
+        w,
+        h,
+        message="Image with size {}x{} is too large for cleaning with 'unpaper'.",
+    ):
+        self.w = w
+        self.h = h
+        self.message = message.format(w, h)
+        super().__init__(self.message)
+
+
 def version() -> str:
     return get_version('unpaper')
 
 
-def _setup_unpaper_io(tmpdir: Path, input_file: Path) -> Tuple[Path, Path]:
+def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
     SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
-    with Image.open(input_file) as im:
-        im_modified = False
-        if im.mode not in SUFFIXES:
-            log.info("Converting image to other colorspace")
-            try:
-                if im.mode == 'P' and len(im.getcolors()) == 2:
-                    im = im.convert(mode='1')
-                else:
-                    im = im.convert(mode='RGB')
-            except OSError as e:
-                raise MissingDependencyError(
-                    "Could not convert image with type " + im.mode
-                ) from e
-            else:
-                im_modified = True
+    im_modified = False
+
+    if im.mode not in SUFFIXES:
+        log.info("Converting image to other colorspace")
         try:
-            suffix = SUFFIXES[im.mode]
-        except KeyError:
+            if im.mode == 'P' and len(im.getcolors()) == 2:
+                im = im.convert(mode='1')
+            else:
+                im = im.convert(mode='RGB')
+        except OSError as e:
             raise MissingDependencyError(
-                "Failed to convert image to a supported format."
-            ) from None
-
-        if im_modified or input_file.suffix != '.pnm':
-            input_pnm = tmpdir / 'input.pnm'
-            im.save(input_pnm, format='PPM')
+                "Could not convert image with type " + im.mode
+            ) from e
         else:
-            # No changes, PNG input, just use the file we already have
-            input_pnm = input_file
-        output_pnm = tmpdir / f'output{suffix}'
-    return input_pnm, output_pnm
+            im_modified = True
+    try:
+        suffix = SUFFIXES[im.mode]
+    except KeyError:
+        raise MissingDependencyError(
+            "Failed to convert image to a supported format."
+        ) from None
+    return im, im_modified, suffix
 
 
-def run(
+@contextmanager
+def _setup_unpaper_io(input_file: Path) -> Iterator[Tuple[Path, Path, Path]]:
+    with Image.open(input_file) as im:
+        if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
+            raise UnpaperImageTooLargeError(w=im.width, h=im.height)
+        im, im_modified, suffix = _convert_image(im)
+
+        with TemporaryDirectory() as tmpdir:
+            tmppath = Path(tmpdir)
+            if im_modified or input_file.suffix != '.pnm':
+                input_pnm = tmppath / 'input.pnm'
+                im.save(input_pnm, format='PPM')
+            else:
+                # No changes, PNG input, just use the file we already have
+                input_pnm = input_file
+
+            output_pnm = tmppath / f'output{suffix}'
+            yield input_pnm, output_pnm, tmppath
+
+
+def run_unpaper(
     input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
-    with TemporaryDirectory() as tmpdir:
-        input_pnm, output_pnm = _setup_unpaper_io(Path(tmpdir), input_file)
-
+    with _setup_unpaper_io(input_file) as (input_pnm, output_pnm, tmpdir):
         # To prevent any shenanigans from accepting arbitrary parameters in
         # --unpaper-args, we:
         # 1) run with cwd set to a tmpdir with only unpaper's files
@@ -84,7 +109,7 @@ def run(
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
         args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
-        external_run(
+        run(
             args_unpaper,
             close_fds=True,
             check=True,
@@ -117,7 +142,7 @@ def clean(
     *,
     dpi: DecFloat,
     unpaper_args: Optional[List[str]] = None,
-):
+) -> Path:
     default_args = [
         '--layout',
         'none',
@@ -131,4 +156,9 @@ def clean(
     ]
     if not unpaper_args:
         unpaper_args = default_args
-    run(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+    try:
+        run_unpaper(input_file, output_file, dpi=dpi, mode_args=unpaper_args)
+        return output_file
+    except UnpaperImageTooLargeError as e:
+        log.warning(str(e))
+        return input_file

src/ocrmypdf/_pipeline.py

@@ -32,12 +32,19 @@ from ocrmypdf.exceptions import (
     PriorOcrFoundError,
     UnsupportedImageFormatError,
 )
-from ocrmypdf.helpers import Resolution, safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.optimize import optimize
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    BICUBIC = Image.Resampling.BICUBIC  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    BICUBIC = Image.BICUBIC  # type: ignore
+
 log = logging.getLogger(__name__)
 
 VECTOR_PAGE_DPI = 400
@@ -98,8 +105,8 @@ def triage_image_file(input_file, output_file, options):
             img2pdf.convert(
                 os.fspath(input_file),
                 layout_fun=layout_fun,
-                with_pdfrw=False,
                 outputstream=outf,
+                **IMG2PDF_KWARGS,
             )
         log.info("Successfully converted to PDF, processing...")
     except img2pdf.ImageOpenError as e:
@@ -484,7 +491,9 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
         # According to Pillow docs, .rotate() will automatically use Image.NEAREST
         # resampling if image is mode '1' or 'P'
         deskewed = im.rotate(
-            deskew_angle_degrees, resample=Image.BICUBIC, fillcolor='white'
+            deskew_angle_degrees,
+            resample=BICUBIC,
+            fillcolor=ImageColor.getcolor('white', mode=im.mode),
         )
         deskewed.save(output_file, dpi=dpi)
 
@@ -494,13 +503,12 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
 def preprocess_clean(input_file: Path, page_context: PageContext):
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
-    unpaper.clean(
+    return unpaper.clean(
         input_file,
         output_file,
         dpi=dpi.x,
         unpaper_args=page_context.options.unpaper_args,
     )
-    return output_file
 
 
 def create_ocr_image(image: Path, page_context: PageContext):
@@ -613,7 +621,7 @@ def create_pdf_page_from_image(
 
         layout_fun = img2pdf.get_layout_fun(pagesize)
         img2pdf.convert(
-            imfile, with_pdfrw=False, layout_fun=layout_fun, outputstream=pdf
+            imfile, layout_fun=layout_fun, outputstream=pdf, **IMG2PDF_KWARGS
         )
         log.debug('convert done')
 

src/ocrmypdf/_validation.py

@@ -41,7 +41,7 @@ log = logging.getLogger(__name__)
 
 
 def check_platform():
-    if os.name == 'nt' and sys.maxsize <= 2 ** 32:  # pragma: no cover
+    if os.name == 'nt' and sys.maxsize <= 2**32:  # pragma: no cover
         # 32-bit interpreter on Windows
         log.error(
             "You are running OCRmyPDF in a 32-bit (x86) Python interpreter."

src/ocrmypdf/api.py

@@ -295,7 +295,7 @@ def ocr(  # pylint: disable=unused-argument
             text already, and settings did not tell us to proceed.
         ocrmypdf.InputFileError: Any other problem with the input file.
         ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
-        ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
+        ocrmypdf.EncryptedPdfError: If the input PDF is encrypted (password protected).
             OCRmyPDF does not remove passwords.
         ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
             valid.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -134,7 +134,6 @@ class StandardExecutor(Executor):
                 for future in as_completed(futures):
                     result = future.result()
                     task_finished(result, pbar)
-                    pbar.update()
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
                 executor.shutdown(wait=False, cancel_futures=True)

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -18,13 +18,13 @@ log = logging.getLogger(__name__)
 
 @hookimpl
 def check_options(options):
-    gs_version = ghostscript.version()
     check_external_program(
         program='gs',
         package='ghostscript',
-        version_checker=gs_version,
+        version_checker=ghostscript.version,
         need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
     )
+    gs_version = ghostscript.version()
     if gs_version in ('9.24', '9.51'):
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "

src/ocrmypdf/cli.py

@@ -142,7 +142,7 @@ Online documentation is located at:
         'output_file',
         metavar="output_pdf",
         help="Output searchable PDF file (or '-' to write to standard output). "
-        "Existing files will be ovewritten. If same as input file, the "
+        "Existing files will be overwritten. If same as input file, the "
         "input file will be updated only if processing is successful.",
     )
     parser.add_argument(
@@ -228,7 +228,13 @@ Online documentation is located at:
         help=argparse.SUPPRESS,
     )
     jobcontrol.add_argument(
-        '--use-threads', action='store_true', help=argparse.SUPPRESS
+        '--use-threads', action='store_true', default=True, help=argparse.SUPPRESS
+    )
+    jobcontrol.add_argument(
+        '--no-use-threads',
+        action='store_false',
+        dest='use_threads',
+        help=argparse.SUPPRESS,
     )
 
     metadata = parser.add_argument_group(

src/ocrmypdf/helpers.py

@@ -19,10 +19,21 @@ from math import isclose, isfinite
 from pathlib import Path
 from typing import Any, Sequence
 
+import img2pdf
 import pikepdf
+from packaging.version import Version
 
 log = logging.getLogger(__name__)
 
+if Version(img2pdf.__version__) < Version('0.4.0'):
+    IMG2PDF_KWARGS = dict(without_pdfw=True)
+elif Version(img2pdf.__version__) < Version('0.4.3'):
+    IMG2PDF_KWARGS = dict(engine=img2pdf.Engine.pikepdf)
+else:
+    IMG2PDF_KWARGS = dict(
+        engine=img2pdf.Engine.pikepdf, rotation=img2pdf.Rotation.ifvalid
+    )
+
 
 class Resolution(namedtuple('Resolution', ('x', 'y'))):
     """The number of pixels per inch in each 2D direction.
@@ -209,11 +220,19 @@ def check_pdf(input_file: Path) -> bool:
     else:
         with pdf:
             messages = pdf.check()
+            success = True
             for msg in messages:
                 if 'error' in msg.lower():
                     log.error(msg)
+                    success = False
+                elif (
+                    "/DecodeParms: operation for dictionary attempted on object "
+                    "of type null" in msg
+                ):
+                    pass  # Ignore/spurious warning
                 else:
                     log.warning(msg)
+                    success = False
 
             sio = StringIO()
             linearize_msgs = ''
@@ -228,7 +247,7 @@ def check_pdf(input_file: Path) -> bool:
                 if linearize_msgs:
                     log.warning(linearize_msgs)
 
-            if not messages and not linearize_msgs:
+            if success and not linearize_msgs:
                 return True
             return False
 

src/ocrmypdf/optimize.py

@@ -8,6 +8,7 @@
 import logging
 import sys
 import tempfile
+import threading
 from collections import defaultdict
 from os import fspath
 from pathlib import Path
@@ -23,6 +24,7 @@ from typing import (
     Sequence,
     Tuple,
 )
+from zlib import compress
 
 import img2pdf
 from pikepdf import (
@@ -31,6 +33,7 @@ from pikepdf import (
     Object,
     ObjectStreamMode,
     Pdf,
+    PdfError,
     PdfImage,
     Stream,
     UnsupportedImageTypeError,
@@ -41,7 +44,7 @@ from ocrmypdf._concurrent import Executor, SerialExecutor
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf.exceptions import OutputFileAccessError
-from ocrmypdf.helpers import safe_symlink
+from ocrmypdf.helpers import IMG2PDF_KWARGS, safe_symlink
 
 log = logging.getLogger(__name__)
 
@@ -78,33 +81,49 @@ def extract_image_filter(
     if image.Subtype != Name.Image:
         return None
     if image.Length < 100:
-        log.debug(f"Skipping small image, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with small stream size")
         return None
     if image.Width < 8 or image.Height < 8:  # Issue 732
-        log.debug(f"Skipping oddly sized image, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with unusually small dimensions")
         return None
 
     pim = PdfImage(image)
 
     if len(pim.filter_decodeparms) > 1:
-        log.debug(f"Skipping multiply filtered image, xref {xref}")
-        return None
-    filtdp = pim.filter_decodeparms[0]
+        first_filtdp = pim.filter_decodeparms[0]
+        second_filtdp = pim.filter_decodeparms[1]
+        if (
+            len(pim.filter_decodeparms) == 2
+            and first_filtdp[0] == Name.FlateDecode
+            and first_filtdp[1].get(Name.Predictor, 1) == 1
+            and second_filtdp[0] == Name.DCTDecode
+            and not second_filtdp[1]
+        ):
+            log.debug(
+                f"xref {xref}: found image compressed as /FlateDecode /DCTDecode, "
+                "marked for JPEG optimization"
+            )
+            filtdp = pim.filter_decodeparms[1]
+        else:
+            log.debug(f"xref {xref}: skipping image with multiple compression filters")
+            return None
+    else:
+        filtdp = pim.filter_decodeparms[0]
 
     if pim.bits_per_component > 8:
-        log.debug(f"Skipping wide gamut image, xref {xref}")
+        log.debug(f"xref {xref}: skipping wide gamut image")
         return None  # Don't mess with wide gamut images
 
     if filtdp[0] == Name.JPXDecode:
-        log.debug(f"Skipping JPEG2000 image, xref {xref}")
+        log.debug(f"xref {xref}: skipping JPEG2000 image")
         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}")
+        log.debug(f"xref {xref}: skipping CCITT Group 3 image")
         return None  # pikepdf doesn't support Group 3 yet
 
     if Name.Decode in image:
-        log.debug(f"Skipping image with Decode table, xref {xref}")
+        log.debug(f"xref {xref}: skipping image with Decode table")
         return None  # Don't mess with custom Decode tables
 
     return pim, filtdp
@@ -172,14 +191,6 @@ def extract_image_generic(
         # jpeg_quality_estimate = 117.0 * (bytes_per_pixel ** 0.213)
         # if jpeg_quality_estimate < 65:
         #     return None
-
-        # We could get the ICC profile here, but there's no need to look at it
-        # for quality transcoding
-        # if icc:
-        #     stream = BytesIO(raw_jpeg.read_raw_bytes())
-        #     iccbytes = icc.read_bytes()
-        #     with Image.open(stream) as im:
-        #         im.save(jpg_name(root, xref), icc_profile=iccbytes)
         try:
             imgname = root / f'{xref:08d}'
             with imgname.open('wb') as f:
@@ -200,7 +211,11 @@ def extract_image_generic(
     elif not pim.indexed and pim.colorspace in pim.SIMPLE_COLORSPACES:
         # An optimization opportunity here, not currently taken, is directly
         # generating a PNG from compressed data
-        pim.as_pil_image().save(png_name(root, xref))
+        try:
+            pim.as_pil_image().save(png_name(root, xref))
+        except NotImplementedError:
+            log.warning("PDF contains an atypical image that cannot be optimized.")
+            return None
         return XrefExt(xref, '.png')
     elif (
         not pim.indexed
@@ -255,9 +270,9 @@ def extract_images(
                 # Ignore soft masks
                 smask_xref = Xref(image.SMask.objgen[0])
                 exclude_xrefs.add(smask_xref)
-                log.debug(f"Skipping image {smask_xref} because it is an SMask")
+                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
             include_xrefs.add(xref)
-            log.debug(f"Treating {xref} as an optimization candidate")
+            log.debug(f"xref {xref}: treating as an optimization candidate")
             if xref not in pageno_for_xref:
                 pageno_for_xref[xref] = pageno
 
@@ -269,7 +284,9 @@ def extract_images(
                 pike=pike, root=root, image=image, xref=xref, options=options
             )
         except Exception:  # pylint: disable=broad-except
-            log.exception(f"While extracting image xref {xref}, an error occurred")
+            log.exception(
+                f"xref {xref}: While extracting this image, an error occurred"
+            )
             errors += 1
         else:
             if result:
@@ -290,7 +307,7 @@ def extract_images_generic(
             pngs.append(xref_ext.xref)
         elif xref_ext.ext == '.jpg':
             jpegs.append(xref_ext.xref)
-    log.debug("Optimizable images: JPEGs: %s PNGs: %s", len(jpegs), len(pngs))
+    log.debug(f"Optimizable images: JPEGs: {len(jpegs)} PNGs: {len(pngs)}")
     return jpegs, pngs
 
 
@@ -302,7 +319,7 @@ def extract_images_jbig2(pike: Pdf, root: Path, options) -> Dict[int, List[XrefE
         group = pageno // options.jbig2_page_group_size
         jbig2_groups[group].append(xref_ext)
 
-    log.debug("Optimizable images: JBIG2 groups: %s", (len(jbig2_groups),))
+    log.debug(f"Optimizable images: JBIG2 groups: {len(jbig2_groups)}")
     return jbig2_groups
 
 
@@ -401,15 +418,11 @@ def convert_to_jbig2(
 def _optimize_jpeg(args: Tuple[Xref, Path, Path, int]) -> Tuple[Xref, Optional[Path]]:
     xref, in_jpg, opt_jpg, jpeg_quality = args
 
-    # This may produce a debug warning from PIL
-    # DEBUG:PIL.Image:Error closing: 'NoneType' object has no attribute
-    # 'close'.  Seems to be mostly harmless
-    # https://github.com/python-pillow/Pillow/issues/1144
     with Image.open(in_jpg) as im:
         im.save(opt_jpg, optimize=True, quality=jpeg_quality)
 
     if opt_jpg.stat().st_size > in_jpg.stat().st_size:
-        log.debug("xref %s, jpeg, made larger - skip", xref)
+        log.debug(f"xref {xref}, jpeg, made larger - skip")
         opt_jpg.unlink()
         return xref, None
     return xref, opt_jpg
@@ -436,7 +449,7 @@ def transcode_jpegs(
         use_threads=True,  # Processes are significantly slower at this task
         max_workers=options.jobs,
         tqdm_kwargs=dict(
-            desc="JPEGs",
+            desc="Recompressing JPEGs",
             total=len(jpegs),
             unit='image',
             disable=not options.progress_bar,
@@ -447,10 +460,77 @@ def transcode_jpegs(
     )
 
 
+def _find_deflatable_jpeg(
+    *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
+) -> Optional[XrefExt]:
+    result = extract_image_filter(pike, root, image, xref)
+    if result is None:
+        return None
+    pim, filtdp = result
+
+    if filtdp[0] == Name.DCTDecode and not filtdp[1] and options.optimize >= 1:
+        return XrefExt(xref, '.memory')
+
+    return None
+
+
+def _deflate_jpeg(args: Tuple[Pdf, threading.Lock, Xref, int]) -> Tuple[Xref, bytes]:
+    pike, lock, xref, complevel = args
+    with lock:
+        xobj = pike.get_object(xref, 0)
+        try:
+            data = xobj.read_raw_bytes()
+        except PdfError:
+            return xref, b''
+    compdata = compress(data, complevel)
+    if len(compdata) >= len(data):
+        return xref, b''
+    return xref, compdata
+
+
+def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
+    jpegs = []
+    for _pageno, xref_ext in extract_images(pike, root, options, _find_deflatable_jpeg):
+        xref = xref_ext.xref
+        log.debug(f'xref {xref}: marking this JPEG as deflatable')
+        jpegs.append(xref)
+
+    complevel = 9 if options.optimize == 3 else 6
+
+    # Our calls to xobj.write() in finish() need coordination
+    lock = threading.Lock()
+
+    def deflate_args() -> Iterator:
+        for xref in jpegs:
+            yield pike, lock, xref, complevel
+
+    def finish(result, pbar):
+        xref, compdata = result
+        if len(compdata) > 0:
+            with lock:
+                xobj = pike.get_object(xref, 0)
+                xobj.write(compdata, filter=[Name.FlateDecode, Name.DCTDecode])
+        pbar.update()
+
+    executor(
+        use_threads=True,  # We're sharing the pdf directly, must use threads
+        max_workers=options.jobs,
+        tqdm_kwargs=dict(
+            desc="Deflating JPEGs",
+            total=len(jpegs),
+            unit='image',
+            disable=not options.progress_bar,
+        ),
+        task=_deflate_jpeg,
+        task_arguments=deflate_args(),
+        task_finished=finish,
+    )
+
+
 def _transcode_png(pike: Pdf, filename: Path, xref: Xref) -> bool:
     output = filename.with_suffix('.png.pdf')
     with output.open('wb') as f:
-        img2pdf.convert(fspath(filename), outputstream=f)
+        img2pdf.convert(fspath(filename), outputstream=f, **IMG2PDF_KWARGS)
 
     with Pdf.open(output) as pdf_image:
         foreign_image = next(iter(pdf_image.pages[0].images.values()))
@@ -560,6 +640,7 @@ def optimize(
 
         jpegs, pngs = extract_images_generic(pike, root, options)
         transcode_jpegs(pike, jpegs, root, options, executor)
+        deflate_jpegs(pike, root, options, executor)
         # if options.optimize >= 2:
         # Try pngifying the jpegs
         #    transcode_pngs(pike, jpegs, jpg_name, root, options)

src/ocrmypdf/pdfinfo/info.py

@@ -25,6 +25,7 @@ from typing import (
     Mapping,
     NamedTuple,
     Optional,
+    Sequence,
     Tuple,
     Union,
 )
@@ -646,8 +647,8 @@ def _pdf_pageinfo_concurrent(
     max_workers,
     check_pages,
     detailed_analysis=False,
-):
-    pages = [None] * len(pdf.pages)
+) -> Sequence[Optional['PageInfo']]:
+    pages: Sequence[Optional['PageInfo']] = [None] * len(pdf.pages)
 
     def update_pageinfo(result, pbar):
         page = result
@@ -918,17 +919,17 @@ class PdfInfo:
                     self._has_acroform = True
 
     @property
-    def pages(self):
+    def pages(self) -> Sequence[Optional[PageInfo]]:
         return self._pages
 
     @property
     def min_version(self) -> str:
         # The minimum PDF is the maximum version that any particular page needs
-        return max(page.min_version for page in self.pages)
+        return max(page.min_version for page in self.pages if page)
 
     @property
     def has_userunit(self) -> bool:
-        return any(page.userunit != 1.0 for page in self.pages)
+        return any(page.userunit != 1.0 for page in self.pages if page)
 
     @property
     def has_acroform(self) -> bool:

src/ocrmypdf/pluginspec.py

@@ -132,6 +132,7 @@ def get_progressbar_class():
     Here is how OCRmyPDF will use the progress bar:
 
     Example:
+
         pbar_class = pm.hook.get_progressbar_class()
         with pbar_class(**tqdm_kwargs) as pbar:
             ...
@@ -235,9 +236,9 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
     ``image_filename``. The hook may overwrite ``image_filename`` with a new file.
 
     The output image should preserve the same physical unit dimensions, that is
-    (width * dpi_x, height * dpi_y). That is, if the image is resized, the DPI
+    ``(width * dpi_x, height * dpi_y)``. That is, if the image is resized, the DPI
     must be adjusted by the reciprocal. If this is not preserved, the PDF page
-    will be resized and the OCR layer misaligned. OCRmyPDF does not nothing
+    will be resized and the OCR layer misaligned. OCRmyPDF does nothing
     to enforce these constraints; it is up to the plugin to do sensible things.
 
     OCRmyPDF will create the PDF page based on the image format used (unless the
@@ -399,8 +400,7 @@ def get_ocr_engine() -> OcrEngine:
     """Returns an OcrEngine to use for processing this file.
 
     The OcrEngine may be instantiated multiple times, by both the main process
-    and child process. As such, it must be obtain store any state in ``options``
-    or some common location.
+    and child process.
 
     Note:
         This is a :ref:`firstresult hook<firstresult>`.

src/ocrmypdf/subprocess/__init__.py

@@ -13,12 +13,13 @@ import re
 import sys
 from collections.abc import Mapping
 from contextlib import suppress
-from distutils.version import LooseVersion, Version
 from functools import lru_cache
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
 from typing import Callable, Optional, Type, Union
 
+from packaging.version import Version
+
 from ocrmypdf.exceptions import MissingDependencyError
 
 # pylint: disable=logging-format-interpolation
@@ -266,11 +267,11 @@ def check_external_program(
     *,
     program: str,
     package: str,
-    version_checker: Union[str, Callable],
+    version_checker: Callable,
     need_version: str,
     required_for: Optional[str] = None,
     recommended=False,
-    version_parser: Type[Version] = LooseVersion,
+    version_parser: Type[Version] = Version,
 ):
     """Check for required version of external program and raise exception if not.
 
@@ -291,7 +292,7 @@ def check_external_program(
     try:
         if callable(version_checker):
             found_version = version_checker()
-        else:
+        else:  # deprecated
             found_version = version_checker
     except (CalledProcessError, FileNotFoundError, MissingDependencyError):
         _error_missing_program(program, package, required_for, recommended)

src/ocrmypdf/subprocess/_windows.py

@@ -4,11 +4,13 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+# type: ignore
+# Non-Windows mypy now breaks when trying to typecheck winreg
+
 import logging
 import os
 import shutil
 import sys
-from distutils.version import LooseVersion
 from itertools import chain
 from pathlib import Path
 from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
@@ -18,11 +20,23 @@ try:
 except ModuleNotFoundError as e:
     raise ModuleNotFoundError("This module is for Windows only") from e
 
+
 log = logging.getLogger(__name__)
 
 T = TypeVar('T')
 
 
+def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
+    """Compare Ghostscript version numbers."""
+    try:
+        release = [int(elem) for elem in s.split('.', maxsplit=3)]
+        while len(release) < 3:
+            release.append(0)
+        return (release[0], release[1], release[2])
+    except ValueError:
+        return (0, 0, 0)
+
+
 def registry_enum(
     key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
 ) -> Iterator[T]:
@@ -51,7 +65,9 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Artifex\GPL Ghostscript"
         ) as k:
-            latest_gs = max(registry_subkeys(k), key=LooseVersion, default='0')
+            latest_gs = max(
+                registry_subkeys(k), key=ghostscript_version_key, default=(0, 0, 0)
+            )
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
         ) as k:

tests/cache/manifest.jsonl

@@ -80,3 +80,5 @@
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}

tests/conftest.py

@@ -134,8 +134,7 @@ def run_ocrmypdf(
 
     p = run(
         p_args,
-        stdout=PIPE,
-        stderr=PIPE,
+        capture_output=True,
         text=text,
         check=False,
     )

tests/plugins/tesseract_cache.py

@@ -50,6 +50,7 @@ import logging
 import platform
 import re
 import shutil
+import threading
 from functools import partial
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError, CompletedProcess
@@ -176,26 +177,40 @@ def cached_run(options, run_args, **run_kwargs):
 
 
 class CacheOcrEngine(TesseractOcrEngine):
+    # Concurrent threads (with --use-threads) might try to use different parts
+    # of the OcrEngine, so we need a lock to protect the state of patched
+    # module whenever it's patched. Should refactor ocrmypdf._exec.tesseract so that
+    # it does not to be patched at all for testing.
+    lock = threading.Lock()
+
     @staticmethod
     def get_orientation(input_file, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             return TesseractOcrEngine.get_orientation(input_file, options)
 
     @staticmethod
     def get_deskew(input_file, options) -> float:
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             return TesseractOcrEngine.get_deskew(input_file, options)
 
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/test_completion.py

@@ -24,8 +24,7 @@ def test_fish():
             ['fish', '-n', 'misc/completion/ocrmypdf.fish'],
             check=True,
             encoding='utf-8',
-            stdout=PIPE,
-            stderr=PIPE,
+            capture_output=True,
         )
         assert proc.stderr == '', proc.stderr
     except FileNotFoundError:
@@ -41,8 +40,7 @@ def test_bash():
             ['bash', '-n', 'misc/completion/ocrmypdf.bash'],
             check=True,
             encoding='utf-8',
-            stdout=PIPE,
-            stderr=PIPE,
+            capture_output=True,
         )
         assert proc.stderr == '', proc.stderr
     except FileNotFoundError:

tests/test_concurrency.py

@@ -13,6 +13,7 @@ from ocrmypdf import ExitCode
 from .conftest import run_ocrmypdf_api
 
 
+@pytest.mark.skipif(True, reason="--use-threads is currently default")
 @pytest.mark.skipif(os.name == 'nt', reason="Windows doesn't have SIGKILL")
 def test_simulate_oom_killer(resources, no_outpdf):
     exitcode = run_ocrmypdf_api(

tests/test_ghostscript.py

@@ -6,11 +6,13 @@
 
 
 import logging
+import subprocess
 from decimal import Decimal
+from unittest.mock import patch
 
 import pikepdf
 import pytest
-from PIL import Image
+from PIL import Image, UnidentifiedImageError
 
 from ocrmypdf._exec.ghostscript import rasterize_pdf
 from ocrmypdf.exceptions import ExitCode
@@ -124,3 +126,20 @@ def test_ghostscript_feature_elision(resources, outpdf):
         '--plugin',
         'tests/plugins/gs_feature_elision.py',
     )
+
+
+def test_rasterize_pdf_errors(resources, no_outpdf, caplog):
+    with patch('ocrmypdf._exec.ghostscript.run') as mock:
+        # ghostscript can produce
+        mock.return_value = subprocess.CompletedProcess(
+            ['fakegs'], returncode=0, stdout=b'', stderr=b'error this is an error'
+        )
+        with pytest.raises(UnidentifiedImageError):
+            rasterize_pdf(
+                resources / 'francais.pdf',
+                no_outpdf,
+                raster_device='pngmono',
+                raster_dpi=Resolution(100, 100),
+            )
+        assert "this is an error" in caplog.text
+        assert "invalid page image file" in caplog.text

tests/test_main.py

@@ -630,8 +630,7 @@ def test_compression_preserved(ocrmypdf_exec, resources, image, outpdf):
         ]
         p = run(
             p_args,
-            stdout=PIPE,
-            stderr=PIPE,
+            capture_output=True,
             stdin=input_stream,
             text=True,
             check=False,
@@ -691,8 +690,7 @@ def test_compression_changed(ocrmypdf_exec, resources, image, compression, outpd
         ]
         p = run(
             p_args,
-            stdout=PIPE,
-            stderr=PIPE,
+            capture_output=True,
             stdin=input_stream,
             text=True,
             check=False,

tests/test_optimize.py

@@ -17,7 +17,7 @@ from PIL import Image, ImageDraw
 from ocrmypdf import optimize as opt
 from ocrmypdf._exec import jbig2enc, pngquant
 from ocrmypdf._exec.ghostscript import rasterize_pdf
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 
 from .conftest import check_ocrmypdf
 
@@ -81,7 +81,7 @@ def test_jbig2_lossy(lossy, resources, outpdf):
         '--image-dpi',
         '200',
         '--optimize',
-        3,
+        '3',
         '--jpg-quality',
         '50',
         '--png-quality',
@@ -139,8 +139,8 @@ def test_multiple_pngs(resources, outdir):
         img2pdf.convert(
             fspath(resources / 'baiona_colormapped.png'),
             fspath(resources / 'baiona_gray.png'),
-            with_pdfrw=False,
             outputstream=inpdf,
+            **IMG2PDF_KWARGS,
         )
 
     def mockquant(input_file, output_file, *_args):

tests/test_pdfinfo.py

@@ -17,7 +17,7 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
 from ocrmypdf.exceptions import InputFileError
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 from ocrmypdf.pdfinfo.layout import PDFPage
 
@@ -67,9 +67,9 @@ def test_single_page_image(eight_by_eight, outpdf):
         img2pdf.convert(
             bio,
             producer="img2pdf",
-            with_pdfrw=False,
             layout_fun=layout_fun,
             outputstream=f,
+            **IMG2PDF_KWARGS,
         )
     info = pdfinfo.PdfInfo(outpdf)
 
@@ -173,17 +173,15 @@ def test_stack_abuse():
     p = pikepdf.Pdf.new()
 
     stream = pikepdf.Stream(p, b'q ' * 35)
-    with pytest.warns(None) as record:
+    with pytest.warns(UserWarning, match="overflowed"):
         pdfinfo.info._interpret_contents(stream)
-    assert 'overflowed' in str(record[0].message)
 
     stream = pikepdf.Stream(p, b'q Q Q Q Q')
-    with pytest.warns(None) as record:
+    with pytest.warns(UserWarning, match="underflowed") as record:
         pdfinfo.info._interpret_contents(stream)
-    assert 'underflowed' in str(record[0].message)
 
     stream = pikepdf.Stream(p, b'q ' * 135)
-    with pytest.warns(None):
+    with pytest.warns(UserWarning):
         with pytest.raises(RuntimeError):
             pdfinfo.info._interpret_contents(stream)
 

tests/test_preprocessing.py

@@ -40,6 +40,11 @@ def test_deskew(resources, outdir):
     assert -0.5 < skew_angle < 0.5, "Deskewing failed"
 
 
+def test_deskew_blank_page(resources, outpdf):
+    # Tesseract doesn't like blank pages - make sure we can get through
+    check_ocrmypdf(resources / 'blank.pdf', outpdf, '--deskew')
+
+
 @pytest.mark.xfail(reason="remove background disabled")
 def test_remove_background(resources, outdir):
     # Ensure the input image does not contain pure white/black

tests/test_rotation.py

@@ -18,13 +18,19 @@ from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf._exec import ghostscript
 from ocrmypdf._plugin_manager import get_plugin_manager
-from ocrmypdf.helpers import Resolution
+from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution
 from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf
 
 # pylintx: disable=unused-variable
 
+# Remove this workaround when we require Pillow >= 10
+try:
+    Transpose = Image.Transpose  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Transpose = Image  # type: ignore
 
 RENDERERS = ['hocr', 'sandwich']
 
@@ -222,7 +228,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
         with Image.open(fspath(resources / 'typewriter.png')) as im:
             if image_angle != 0:
                 ccw_angle = -image_angle % 360
-                im = im.transpose(getattr(Image, f'ROTATE_{ccw_angle}'))
+                im = im.transpose(getattr(Transpose, f'ROTATE_{ccw_angle}'))
             im.save(memimg, format='PNG')
         memimg.seek(0)
         mempdf = BytesIO()
@@ -230,6 +236,7 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
             memimg.read(),
             layout_fun=img2pdf.get_fixed_dpi_layout_fun((200, 200)),
             outputstream=mempdf,
+            **IMG2PDF_KWARGS,
         )
         mempdf.seek(0)
         pike = pikepdf.open(mempdf)

tests/test_stdio.py

@@ -30,12 +30,12 @@ def test_stdin(ocrmypdf_exec, resources, outpdf):
             '--plugin',
             'tests/plugins/tesseract_noop.py',
         ]
-        run(p_args, stdout=PIPE, stderr=PIPE, stdin=input_stream, check=True)
+        run(p_args, capture_output=True, stdin=input_stream, check=True)
 
 
 def test_stdout(ocrmypdf_exec, resources, outpdf):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(msg="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     input_file = str(resources / 'francais.pdf')
     output_file = str(outpdf)
@@ -72,7 +72,7 @@ def test_bad_locale(monkeypatch):
 )
 def test_dev_null(resources):
     if 'COV_CORE_DATAFILE' in os.environ:
-        pytest.skip(msg="Coverage uses stdout")
+        pytest.skip("Coverage uses stdout")
 
     p = run_ocrmypdf(
         resources / 'trivial.pdf',

tests/test_unpaper.py

@@ -5,19 +5,24 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+import logging
 from os import fspath
 from unittest.mock import patch
 
 import pytest
+from PIL import Image
 
+from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 
-from .conftest import check_ocrmypdf, have_unpaper, run_ocrmypdf
+from .conftest import check_ocrmypdf, have_unpaper, ocrmypdf_exec, run_ocrmypdf
 
 # pylint: disable=redefined-outer-name
 
+needs_unpaper = pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+
 
 def test_no_unpaper(resources, no_outpdf):
     input_ = fspath(resources / "c02-22.pdf")
@@ -45,7 +50,7 @@ def test_old_unpaper(resources, no_outpdf):
         mock.assert_called()
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_clean(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -56,7 +61,7 @@ def test_clean(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_valid(resources, outpdf):
     check_ocrmypdf(
         resources / "skew.pdf",
@@ -69,7 +74,7 @@ def test_unpaper_args_valid(resources, outpdf):
     )
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid_filename(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -84,7 +89,7 @@ def test_unpaper_args_invalid_filename(resources, outpdf):
     assert p.returncode == ExitCode.bad_args
 
 
-@pytest.mark.skipif(not have_unpaper(), reason="requires unpaper")
+@needs_unpaper
 def test_unpaper_args_invalid(resources, outpdf):
     p = run_ocrmypdf(
         resources / "skew.pdf",
@@ -98,3 +103,16 @@ def test_unpaper_args_invalid(resources, outpdf):
     # Can't tell difference between unpaper choking on bad arguments or some
     # other unpaper failure
     assert p.returncode == ExitCode.child_process_error
+
+
+@needs_unpaper
+def test_unpaper_image_too_big(resources, outdir, caplog):
+    with patch('ocrmypdf._exec.unpaper.UNPAPER_IMAGE_PIXEL_LIMIT', 42):
+        infile = resources / 'crom.png'
+        unpaper.clean(infile, outdir / 'out.png', dpi=300) == infile
+
+        assert any(
+            'too large for cleaning' in rec.message
+            for rec in caplog.get_records('call')
+            if rec.levelno == logging.WARNING
+        )