Docker arm64 needs to build pycairo; add its dependencies

All supported Ghostscript versions have proper UserUnit support.

.docker/Dockerfile

@@ -1,5 +1,5 @@
-# OCRmyPDF
-#
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 
 FROM ubuntu:22.04 as base
 
@@ -25,7 +25,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   libffi-dev \
   ca-certificates \
   curl \
-  git
+  git \
+  libcairo2-dev \
+  pkg-config
 
 # Get the latest pip (Ubuntu version doesn't support manylinux2010)
 RUN \
@@ -50,8 +52,14 @@ RUN pip3 install --no-cache-dir .[test,webservice,watcher]
 
 FROM base
 
+# For Tesseract 5
+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 apt-get update && apt-get install -y --no-install-recommends \
   ghostscript \
+  jbig2dec \
   img2pdf \
   libsm6 libxext6 libxrender-dev \
   pngquant \
@@ -74,7 +82,7 @@ COPY --from=builder /app/misc/webservice.py /app/
 COPY --from=builder /app/misc/watcher.py /app/
 
 # Copy minimal project files to get the test suite.
-COPY --from=builder /app/setup.cfg /app/setup.py /app/README.md /app/
+COPY --from=builder /app/pyproject.toml /app/README.md /app/
 COPY --from=builder /app/tests /app/tests
 
 ENTRYPOINT ["/usr/local/bin/ocrmypdf"]

.dockerignore

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # dotfiles
 .*
 !.coveragerc

.gitattributes

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # Always use Unix convention for new lines
 * text eol=lf
 

.github/FUNDING.yml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # These are supported funding model platforms
 
 github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]

.github/ISSUE_TEMPLATE/feature_request.md

@@ -17,11 +17,7 @@ A clear and concise description of what you want to happen.
 A clear and concise description of any alternative solutions or features you've considered. Please include the versions of OCRmyPDF and other supporting programs (Tesseract OCR, Ghostscript) - maybe an alternative already exists in a newer version.
 
 **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/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.
+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. You could also look in ``tests/resources`` and see if any of those files demonstrates your issue.
 
 **Additional context**
 Add any other context or screenshots about the feature request here.

.github/ISSUE_TEMPLATE/general-issues.md

@@ -1,7 +1,7 @@
 ---
 name: General issues
 about: Installation, packages, dependencies, "nothing works", test suite failures...
-title: ''
+title: "[BUG]"
 labels: ''
 assignees: ''
 
@@ -23,6 +23,7 @@ If applicable, add screenshots to help explain your problem.
  - OS:
  - Python version:
  - OCRmyPDF version:
+ - Platform: x64 or ARM
 
 **Installation**
 How did you install OCRmyPDF? Did you install it from your operating system's

.github/ISSUE_TEMPLATE/problem-with-specific-file.md

@@ -1,7 +1,7 @@
 ---
-name: Problem with a specific input file
+name: Problem with specific file
 about: Something went wrong while trying to OCR a specific file
-title: ''
+title: "[BUG]"
 labels: ''
 assignees: ''
 

.github/dependabot.yml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # To get started with Dependabot version updates, you'll need to specify which
 # package ecosystems to update and where the package manifests are located.
 # Please see the documentation for all configuration options:

.github/workflows/build.yml

@@ -1,3 +1,5 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 name: Test and deploy
 
 on:
@@ -20,8 +22,6 @@ jobs:
     strategy:
       matrix:
         include:
-          - os: ubuntu-18.04
-            python: "3.7"
           - os: ubuntu-20.04
             python: "3.8"
           - os: ubuntu-20.04
@@ -31,7 +31,13 @@ jobs:
           - os: ubuntu-latest
             python: "3.9"
           - os: ubuntu-latest
-            python: "pypy-3.8"
+            python: "3.10"
+          - os: ubuntu-latest
+            python: "3.11"
+          # - os: ubuntu-latest
+          #   python: "pypy3.8"
+          #- os: ubuntu-latest
+          #  python: "pypy3.9"
           - os: ubuntu-latest
             python: "3.9"
             tesseract5: true
@@ -73,12 +79,6 @@ jobs:
             unpaper \
             zlib1g
 
-      - name: Install Ubuntu 18.04 packages
-        if: matrix.os == 'ubuntu-18.04'
-        run: |
-          sudo apt-get install -y --no-install-recommends \
-            libexempi3
-
       - name: Install Ubuntu 20.04 packages
         if: matrix.os == 'ubuntu-20.04' || matrix.os == 'ubuntu-latest'
         run: |
@@ -96,7 +96,7 @@ jobs:
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -122,7 +122,7 @@ jobs:
     strategy:
       matrix:
         os: [macos-latest]
-        python: ["3.9", "3.10"]
+        python: ["3.10", "3.11"]
 
     env:
       OS: ${{ matrix.os }}
@@ -133,12 +133,8 @@ jobs:
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v4
-        name: Install Python
-        with:
-          python-version: ${{ matrix.python }}
-
       - name: Install Homebrew deps
+        continue-on-error: true
         run: |
           brew update
           brew install \
@@ -149,10 +145,15 @@ jobs:
             pngquant \
             tesseract
 
+      - uses: actions/setup-python@v4
+        name: Install Python
+        with:
+          python-version: ${{ matrix.python }}
+
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Report versions
         run: |
@@ -177,7 +178,7 @@ jobs:
     strategy:
       matrix:
         os: [windows-latest]
-        python: ["3.9", "3.10"]
+        python: ["3.10", "3.11"]
 
     env:
       OS: ${{ matrix.os }}
@@ -201,7 +202,7 @@ jobs:
       - name: Install Python packages
         run: |
           python -m pip install --upgrade pip wheel
-          python -m pip install .[test]
+          python -m pip install --prefer-binary .[test]
 
       - name: Test
         run: |
@@ -228,9 +229,8 @@ jobs:
 
       - name: Make wheels and sdist
         run: |
-          python -m pip install --upgrade pip wheel
-          python setup.py sdist
-          python setup.py bdist_wheel
+          python -m pip install --upgrade pip wheel build
+          python -m build --sdist --wheel
 
       - uses: actions/upload-artifact@v3
         with:

.gitignore

@@ -1,14 +1,15 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: CC-BY-SA-4.0
+
 # dotfiles
-.*
-!.coveragerc
-!.dockerignore
-!.git_archival.txt
-!.gitattributes
-!.gitignore
-!.pre-commit-config.yaml
-!.readthedocs.yaml
-!.github/
-!.docker/
+.coverage
+.venv*/
+.tox/
+.vscode/
+.hypothesis/
+.ipynb_checkpoints/
+.mypy_cache/
+.pytest_cache/
 
 # Dev scratch
 *.ipynb
@@ -42,4 +43,3 @@ docs/_build/
 docs/_static/
 docs/_templates/
 docs/Makefile
-ocrmypdf/lib/_*.py

.pre-commit-config.yaml

@@ -1,33 +1,28 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
       - id: check-toml
       - id: check-yaml
       - id: debug-statements
-  - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: "v0.0.261"
     hooks:
-      - id: isort
-        args: ["--profile", "black", "-a", "from __future__ import annotations"]
+      - id: ruff
+        files: "src/.*\\.pyi?$"
+        args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black
-    rev: 22.6.0
+    rev: 23.3.0
     hooks:
       - id: black
         language_version: python
-  - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.20.2
-    hooks:
-      - id: setup-cfg-fmt
-  - repo: https://github.com/asottile/pyupgrade
-    rev: v2.37.2
-    hooks:
-      - id: pyupgrade
-        args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    rev: v1.2.0
     hooks:
       - id: mypy
         additional_dependencies:

.readthedocs.yaml

@@ -1,3 +1,6 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
 # Read the Docs configuration file
 # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
 
@@ -14,7 +17,7 @@ formats:
 
 # Optionally set the version of Python and requirements required to build your docs
 python:
-  version: "3.7"
+  version: "3.8"
   install:
     - method: pip
       path: .

.reuse/dep5

@@ -0,0 +1,132 @@
+Format: https://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Upstream-Name: OCRmyPDF
+Upstream-Contact: James R. Barlow <james@purplerock.ca>
+Source: https://github.com/ocrmypdf/OCRmyPDF
+
+
+Files:
+ .git_archival.txt
+ docs/images/logo-social.png
+ docs/images/logo-square-256.svg
+ docs/images/logo-square.png
+ docs/images/logo-square.svg
+ docs/images/logo.svg
+ setup.cfg
+Copyright: (C) 2022 James R. Barlow
+License: MPL-2.0
+
+Files:
+ .github/ISSUE_TEMPLATE/*.md
+ docs/images/macos-workflow.png
+Copyright: (C) 2022 James R. Barlow
+License: CC-BY-SA-4.0
+
+Files:
+ tests/resources/acroform.pdf
+ tests/resources/aspect.pdf
+ tests/resources/blank.pdf
+ tests/resources/cmyk.pdf
+ tests/resources/crom.png
+ tests/resources/enormous.pdf
+ tests/resources/formxobject.pdf
+ tests/resources/francais.pdf
+ tests/resources/hugemono.pdf
+ tests/resources/invalid.pdf
+ tests/resources/kcs.pdf
+ tests/resources/livecycle.pdf
+ tests/resources/missing_docinfo.pdf
+ tests/resources/negzero.pdf
+ tests/resources/no_contents.pdf
+ tests/resources/toc.pdf
+ tests/resources/trivial.pdf
+ tests/resources/truetype_font_nomapping.pdf
+ tests/resources/type3_font_nomapping.pdf
+Copyright: (C) 2022 James R. Barlow
+License: CC-BY-SA-4.0
+
+Files:
+ tests/resources/graph.pdf
+ tests/resources/graph_ocred.pdf
+Copyright: (C) 2012 SmokeyJoe
+License: GFDL-1.2-or-later or CC-BY-SA-3.0
+
+Files: tests/resources/c02-22.pdf
+ tests/resources/congress.jpg
+ tests/resources/multipage.pdf
+Copyright: Public domain
+License: public-domain
+ Copyright on these files has expired.
+
+Files: docs/images/bitmap_vs_svg.svg
+Copyright: (C) 2006 Yug
+License: CC-BY-SA-2.5
+
+Files: tests/cache/*
+Copyright: (C) 2022 James R. Barlow
+License: CC-BY-SA-4.0
+
+Files: tests/resources/linn.png
+ tests/resources/linn.pdf
+ tests/resources/linn.txt
+ tests/resources/ccitt.pdf
+ tests/resources/cardinal.pdf
+ tests/resources/jbig2.pdf
+ tests/resources/skew.pdf
+ tests/resources/rotated_skew.pdf
+ tests/resources/poster.pdf
+Copyright: (C) 1985 Forat Electronics
+License: GFDL-1.2-or-later or CC-BY-SA-3.0
+
+Files: tests/resources/lichtenstein.pdf
+Copyright: (C) 2001 Andreas Tille
+ (C) 2007 Alessio Damato
+License: GFDL-1.2-or-later or CC-BY-SA-3.0
+
+Files: tests/resources/masks.pdf
+Copyright: held by the contributors to the German Wikipedia article "Linux"
+ see: https://de.wikipedia.org/w/index.php?title=Linux&action=history
+ (masks.pdf generated from Wikipedia article as of 2016-08-24)
+License: CC-BY-SA-3.0
+
+Files: tests/resources/epson.pdf
+Copyright: held by the contributors to the Wikipedia article "Optical character recognition"
+ see: https://en.wikipedia.org/w/index.php?title=Optical_character_recognition&action=history
+ (epson.pdf generated from Wikipedia article as of 2016-09-14)
+License: CC-BY-SA-3.0
+
+Files: tests/resources/typewriter.png tests/resources/2400dpi.pdf
+Copyright: (C) 2005 Ellywa
+License: GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0
+Comment:
+ Obtained from: https://commons.wikimedia.org/wiki/File:Triumph.typewriter_text_Linzensoep.gif
+
+Files: tests/resources/overlay.pdf
+Copyright: (C) 2017 Max Anderson
+License: MIT
+
+Files:
+ tests/resources/baiona*.png
+ tests/resources/baiona*.jpg
+ tests/resources/link.pdf
+ tests/resources/palette.pdf
+Copyright: (C) 2014 Euskaldunaa
+License: CC-BY-SA-4.0
+
+Files: tests/resources/vector.pdf
+Copyright: (C) 2018 Catscratch
+License: MIT
+
+Files: src/ocrmypdf/data/sRGB.icc
+Copyright:  Kai-Uwe Behrmann <www.behrmann.name>
+            Marti Maria <www.littlecms.com>
+            Photogamut <www.photogamut.org>
+            Graeme Gill <www.argyllcms.com>
+            ColorSolutions <www.basICColor.com>
+License: Zlib
+
+Files: tests/resources/3small.pdf
+Copyright: (C) 2014 Euskaldunaa
+ (C) 2017 James R. Barlow
+ (C) 2005 Ellywa
+License: CC-BY-SA-4.0 and (GFDL-1.2-or-later or CC-BY-SA-1.0 or CC-BY-SA-2.0 or CC-BY-SA-2.5 or CC-BY-SA-3.0)
+Comment: concatenation of baiona_gray.png, crom.png and typewriter.png/2400dpi.pdf

README.md

@@ -1,3 +1,7 @@
+<!-- SPDX-FileCopyrightText: 2014 Julien Pfefferkorn -->
+<!-- SPDX-FileCopyrightText: 2015 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
 [![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]
@@ -66,7 +70,7 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | macOS (Homebrew)              | ``brew install ocrmypdf``     |
 | macOS (nix)                   | ``nix-env -i  ocrmypdf``      |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
-| FreeBSD                       | ``pkg install py37-ocrmypdf`` |
+| FreeBSD                       | ``pkg install py-ocrmypdf``   |
 | Conda                         | ``conda install ocrmypdf``    |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |
 
@@ -92,10 +96,7 @@ brew install tesseract-lang
 
 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.
 
-OCRmyPDF supports Tesseract 4.0 and the beta versions of Tesseract 5.0. It will
-automatically use whichever version it finds first on the `PATH` environment
-variable. On Windows, if `PATH` does not provide a Tesseract binary, we use
-the highest version number that is installed according to the Windows Registry.
+OCRmyPDF supports Tesseract 4.1.1+. It will automatically use whichever version it finds first on the `PATH` environment variable. On Windows, if `PATH` does not provide a Tesseract binary, we use the highest version number that is installed according to the Windows Registry.
 
 ## Documentation and support
 
@@ -111,7 +112,7 @@ Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF
 
 ## Requirements
 
-In addition to the required Python version (3.7+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
+In addition to the required Python version (3.8+), OCRmyPDF requires external program installations of Ghostscript and Tesseract OCR. OCRmyPDF is pure Python, and runs on pretty much everything: Linux, macOS, Windows and FreeBSD.
 
 ## Press & Media
 
@@ -122,6 +123,7 @@ In addition to the required Python version (3.7+), OCRmyPDF requires external pr
 - [heise Durchsuchbare PDF-Dokumente mit OCRmyPDF erstellen](https://www.heise.de/ratgeber/Durchsuchbare-PDF-Dokumente-mit-OCRmyPDF-erstellen-4607592.html)
 - [Excellent Utilities: OCRmyPDF](https://www.linuxlinks.com/excellent-utilities-ocrmypdf-add-ocr-text-layer-scanned-pdfs/)
 - [LinuxUser Texterkennung mit OCRmyPDF und Scanbd automatisieren](https://www.linux-community.de/ausgaben/linuxuser/2021/06/texterkennung-mit-ocrmypdf-und-scanbd-automatisieren/)
+- [Y Combinator discussion](https://news.ycombinator.com/item?id=32028752)
 
 ## Business enquiries
 

docs/advanced.rst

@@ -160,7 +160,7 @@ Changing tesseract configuration variables
 ------------------------------------------
 
 You can override tesseract's default `control
-parameters <https://github.com/tesseract-ocr/tesseract/wiki/ControlParams>`__
+parameters <https://tesseract-ocr.github.io/tessdoc/tess3/ControlParams.html>`__
 with a configuration file.
 
 As an example, this configuration will disable Tesseract's dictionary

docs/api.rst

@@ -72,14 +72,6 @@ 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/batch.rst

@@ -21,8 +21,8 @@ processors. To maximize parallelism without overloading your system with
 processes, consider using ``parallel -j 2`` to limit parallel to running
 two jobs at once.
 
-This command will run all ocrmypdf all files named ``*.pdf`` in the
-current directory and write them to the previous created ``output/``
+This command will run ``ocrmypdf`` on all files named ``*.pdf`` in the
+current directory and write them to the previously created ``output/``
 folder. It will not search subdirectories.
 
 The ``--tag`` argument tells parallel to print the filename as a prefix
@@ -133,7 +133,7 @@ Users may need to customize the script to meet their requirements.
     "OCR_OUTPUT_DIRECTORY", "Set output directory (should not be under input)"
     "OCR_ARCHIVE_DIRECTORY", "Set archive directory for processed originals (should not be under input, requires ``OCR_ON_SUCCESS_ARCHIVE`` to be set)"
     "OCR_ON_SUCCESS_DELETE", "This will delete the input file if the exit code is 0 (OK)"
-    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed orignal file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
+    "OCR_ON_SUCCESS_ARCHIVE", "This will move the processed original file to ``OCR_ARCHIVE_DIRECTORY`` if the exit code is 0 (OK). Note that ``OCR_ON_SUCCESS_DELETE`` takes precedence over this option, i.e. if both options are set, the input file will be deleted."
     "OCR_OUTPUT_DIRECTORY_YEAR_MONTH", "This will place files in the output in ``{output}/{year}/{month}/{filename}``"
     "OCR_DESKEW", "Apply deskew to crooked input PDFs"
     "OCR_JSON_SETTINGS", "A JSON string specifying any other arguments for ``ocrmypdf.ocr``, e.g. ``'OCR_JSON_SETTINGS={""rotate_pages"": true}'``."

docs/conf.py

@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: CC-BY-SA-4.0
 
+# ruff: noqa: E402
+
 # ocrmypdf documentation build configuration file, created by
 # sphinx-quickstart on Sun Sep  4 14:29:43 2016.
 #
@@ -22,8 +24,6 @@
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
 
-"""isort:skip_file"""
-
 # -- General configuration ------------------------------------------------
 
 # If your documentation needs a minimal Sphinx version, state it here.
@@ -76,6 +76,7 @@ author = 'James R. Barlow'
 # The short X.Y version.
 
 import os
+from importlib.metadata import version as package_version
 
 on_rtd = os.environ.get('READTHEDOCS') == 'True'
 
@@ -96,10 +97,6 @@ if on_rtd:
     ]
     sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 
-try:
-    from importlib_metadata import version as package_version
-except ModuleNotFoundError:
-    from importlib.metadata import version as package_version
 
 # The full version, including alpha/beta/rc tags.
 release = package_version('ocrmypdf')

docs/cookbook.rst

@@ -283,7 +283,7 @@ argument. (Normally, OCRmyPDF will exit with an error if asked to modify
 a file with OCR.)
 
 This may be helpful for users who want to take advantage of accuracy
-improvements in Tesseract 4.0 for files they previously OCRed with an
+improvements in Tesseract for files they previously OCRed with an
 earlier version of Tesseract and OCRmyPDF.
 
 .. code-block:: bash
@@ -360,7 +360,7 @@ The types of optimization available may expand over time. By default,
 OCRmyPDF compresses data streams inside PDFs, and will change
 inefficient compression modes to more modern versions. A program like
 ``qpdf`` can be used to change encodings, e.g. to inspect the internals
-fo a PDF.
+for a PDF.
 
 .. code-block:: bash
 

docs/installation.rst

@@ -21,7 +21,7 @@ These platforms have one-liner installs:
 +-------------------------------+-----------------------------------------+
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
 +-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``                |
+| Fedora                        | ``dnf install ocrmypdf tesseract-osd``  |
 +-------------------------------+-----------------------------------------+
 | macOS                         | ``brew install ocrmypdf``               |
 +-------------------------------+-----------------------------------------+
@@ -44,7 +44,7 @@ install, or install a more recent version than your platform provides, read on.
 Installing on Linux
 ===================
 
-Debian and Ubuntu 18.04 or newer
+Debian and Ubuntu 20.04 or newer
 --------------------------------
 
 .. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
@@ -56,9 +56,6 @@ Debian and Ubuntu 18.04 or newer
 .. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
     :alt: Debian unstable
 
-.. |ubu-1804| image:: https://repology.org/badge/version-for-repo/ubuntu_18_04/ocrmypdf.svg
-    :alt: Ubuntu 18.04 LTS
-
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
@@ -72,7 +69,7 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2204|              |
+| |ubu-2004| |ubu-2204|                         |
 +-----------------------------------------------+
 
 Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
@@ -80,7 +77,7 @@ of Windows Subsystem for Linux, may simply
 
 .. code-block:: bash
 
-    apt-get install ocrmypdf
+    apt install ocrmypdf
 
 As indicated in the table above, Debian and Ubuntu releases may lag
 behind the latest version. If the version available for your platform is
@@ -124,7 +121,7 @@ Users of Fedora 29 or later may simply
 
 .. code-block:: bash
 
-    dnf install ocrmypdf
+    dnf install ocrmypdf tesseract-osd
 
 For full details on version availability, check the `Fedora Package
 Tracker <https://apps.fedoraproject.org/packages/ocrmypdf>`__.
@@ -198,46 +195,6 @@ To install for the current user only:
 
 To add JBIG2 encoding, see :ref:`jbig2`.
 
-Ubuntu 18.04 LTS
-----------------
-
-Ubuntu 18.04 includes ocrmypdf 6.1.2 - you can install that with ``apt``, but
-it is quite old now. To install a more recent version, uninstall the old version
-of ocrmypdf, and install the following dependencies:
-
-.. code-block:: bash
-
-    sudo apt-get -y remove ocrmypdf
-    sudo apt-get -y update
-    sudo apt-get -y install \
-        ghostscript \
-        icc-profiles-free \
-        libxml2 \
-        pngquant \
-        python3-distutils \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract-ocr \
-        zlib1g \
-        unpaper
-
-We will need a newer version of ``pip`` then was available for Ubuntu 18.04:
-
-.. code-block:: bash
-
-    wget https://bootstrap.pypa.io/get-pip.py && python3 get-pip.py
-
-Then install the most recent ocrmypdf for the local user and set the
-user's ``PATH`` to check for the user's Python packages.
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    python3 -m pip install --user ocrmypdf
-
-To add JBIG2 encoding, see :ref:`jbig2`.
-
 Arch Linux (AUR)
 ----------------
 
@@ -336,7 +293,7 @@ Homebrew
 
 .. image:: https://img.shields.io/homebrew/v/ocrmypdf.svg
     :alt: homebrew
-    :target: http://brewformulas.org/Ocrmypdf
+    :target: https://formulae.brew.sh/formula/ocrmypdf
 
 OCRmyPDF is now a standard `Homebrew <https://brew.sh>`__ formula. To
 install on macOS:
@@ -417,9 +374,9 @@ Native Windows
 
 You must install the following for Windows:
 
-* Python 3.7 (64-bit) or later
-* Tesseract 4.0 or later
-* Ghostscript 9.50 or later
+* Python 3.8 (64-bit) or later
+* Tesseract 4.1.1 (64-bit) or later
+* Ghostscript 9.50 (64-bit) or later
 
 Using the `Chocolatey <https://chocolatey.org/>`_ package manager, install the
 following when running in an Administrator command prompt:
@@ -438,10 +395,8 @@ Administrator.):
 
 * ``pip install ocrmypdf``
 
-Chocolatey automatically selects appropriate versions of these applications. If you
-are installing them manually, please install 64-bit versions of all applications for
-64-bit Windows, or 32-bit versions of all applications for 32-bit Windows. Mixing
-the "bitness" of these programs will lead to errors.
+Chocolatey automatically selects appropriate versions of these applications. Please make sure
+you are installing the 64-bit versions.
 
 OCRmyPDF will check the Windows Registry and standard locations in your Program Files
 for third party software it needs (specifically, Tesseract and Ghostscript). To
@@ -456,6 +411,10 @@ to change the PATH.
     Please download Python from Python.org or Chocolatey instead, and do not use the
     Microsoft Store version.
 
+.. warning::
+
+    32-bit Windows might work, but is not supported.
+
 Windows Subsystem for Linux
 ---------------------------
 
@@ -481,7 +440,7 @@ Cygwin64
 
 First install the the following prerequisite Cygwin packages using ``setup-x86_64.exe``::
 
-    python37 (or later)
+    python38 (or later)
     python3?-devel
     python3?-pip
     python3?-lxml
@@ -571,7 +530,7 @@ programs being installed.
     ``apt install python3-pip python3-venv``, create a virtual environment,
     and install OCRmyPDF in that environment.
 
-    `See here for more inforation on Debian-Python issues
+    `See here for more information on Debian-Python issues
     <https://gist.github.com/tiran/2dec9e03c6f901814f6d1e8dad09528e>`__.
 
 For best results, first install `your platform's
@@ -616,9 +575,9 @@ manager. ``pip`` cannot provide them.
 
 The following versions are required:
 
--  Python 3.7 or newer
--  Ghostscript 9.23 or newer
--  Tesseract 4.0.0 or newer
+-  Python 3.8 or newer
+-  Ghostscript 9.50 or newer
+-  Tesseract 4.1.1 or newer
 -  jbig2enc 0.29 or newer
 -  pngquant 2.5 or newer
 -  unpaper 6.1
@@ -649,7 +608,7 @@ unfortunately, the ``pip install`` command cannot satisfy all of them.
 Installing HEAD revision from sources
 =====================================
 
-If you have ``git`` and Python 3.7 or newer installed, you can install
+If you have ``git`` and Python 3.8 or newer installed, you can install
 from source. When the ``pip`` installer runs, it will alert you if
 dependencies are missing.
 
@@ -679,7 +638,7 @@ system-wide:
 .. code-block:: bash
 
     git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv
+    python3 -m venv venv
     source venv/bin/activate
     cd OCRmyPDF
     pip install .

docs/introduction.rst

@@ -85,7 +85,7 @@ OCRmyPDF analyzes each page of a PDF to determine the colorspace and
 resolution (DPI) needed to capture all of the information on that page
 without losing content. It uses
 `Ghostscript <http://ghostscript.com/>`__ to rasterize the page, and
-then performs on OCR the rasterized image to create an OCR "layer".
+then performs OCR on the rasterized image to create an OCR "layer".
 The layer is then grafted back onto the original PDF.
 
 While one can use a program like Ghostscript or ImageMagick to get an
@@ -190,11 +190,10 @@ Ghostscript also imposes some limitations:
    behavior can be suppressed by setting ``--pdfa-image-compression`` to
    ``jpeg`` or ``lossless`` to set all images to one type or the other.
    Ghostscript has no option to maintain the input image's format.
-   (Ghostscript 9.25+ can copy JPEG images without transcoding them;
-   earlier versions will transcode.)
+   (Modern Ghostscript can copy JPEG images without transcoding them.)
 -  Ghostscript's PDF/A conversion removes any XMP metadata that is not
    one of the standard XMP metadata namespaces for PDFs. In particular,
-   PRISM Metdata is removed.
+   PRISM Metadata is removed.
 -  Ghostscript's PDF/A conversion seems to remove or deactivate
    hyperlinks and other active content.
 

docs/jbig2.rst

@@ -37,7 +37,8 @@ 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.
+are packaged as libtool and libleptonica-dev. On Fedora (35) they are packaged
+as libtool and leptonica-devel.
 
 Lossy mode JBIG2
 ================

docs/languages.rst

@@ -74,7 +74,7 @@ This enables these languages for all packages (e.g. including aspell).
    # 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)
+   # Add global English and German language support (the `l10n_` from equery has to be omitted)
    echo L10N="de en" >> /etc/portage/make.conf
    
    # update system to reflect changed USE flags

docs/plugins.rst

@@ -76,20 +76,16 @@ Setuptools plugins
 You can also create a plugin that OCRmyPDF will always automatically load if both are
 installed in the same virtual environment, using a setuptools entrypoint.
 
-Your package's ``setup.py`` would need to contain the following, for a plugin
+Your package's ``pyproject.toml`` would need to contain the following, for a plugin
 named ``ocrmypdf-exampleplugin``:
 
-.. code-block:: python
+.. code-block:: toml
 
-    # sample ./setup.py file
-    from setuptools import setup
+    [project]
+    name = "ocrmypdf-exampleplugin"
 
-    setup(
-        name="ocrmypdf-exampleplugin",
-        packages=["exampleplugin"],
-        # the following makes a plugin available to pytest
-        entry_points={"ocrmypdf": ["exampleplugin = exampleplugin.pluginmodule"]},
-    )
+    [project.entry-points."ocrmypdf"]
+    exampleplugin = "exampleplugin.pluginmodule"
 
 .. code-block:: ini
 

docs/release_notes.rst

@@ -28,6 +28,72 @@ tagged yet.
 
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v14.2.0
+=======
+
+-  Added `--tesseract-downsample-above` to downsample larger images even when
+   they do not exceed Tesseract's internal limits. This can be used to speed
+   up OCR, possibly sacrificing accuracy.
+-  Fixed resampling AttributeError on older Pillow. :issue:`1096`
+-  Removed an error about using Ghostscript on PDFs with that have the /UserUnit
+   feature in use. Previously, Ghostscript would fail to process these PDFs,
+   but in all supported versions it is now supported, so the error is no longer
+   needed.
+-  Improved documentation around installing other language packs for Tesseract.
+
+v14.1.0
+=======
+
+-  Added ``--tesseract-non-ocr-timeout``. This allows using Tesseract's deskew
+   and other non-OCR features while disabling OCR using ``--tesseract-timeout 0``.
+-  Added ``--tesseract-downsample-large-images``. This downsamples larges images
+   that exceed the maximum image size Tesseract can handle. Large images may still
+   take a long time to process, but this allows them to be processed if that
+   is desired.
+-  Fixed :issue:`1082`, an issue with snap packaged building.
+-  Change linter to ruff, fix lint errors, update documentation.
+
+v14.0.4
+=======
+
+-  Fixed :issue:`1066, 1075`, an exception when processing certain malformed PDFs.
+
+v14.0.3
+=======
+
+-  Fixed :issue:`1068`, avoid deleting /dev/null when running as root.
+-  Other documentation fixes.
+
+v14.0.2
+=======
+
+-  Fixed :issue:`1052`, an exception on attempting to process certain nonconforming PDFs.
+-  Explicitly documented that Windows 32-bit is no longer supported.
+-  Fixed source installation instructions.
+-  Other documentation fixes.
+
+v14.0.1
+=======
+
+-  Fixed some version checks done with smart version comparison.
+-  Added missing jbig2dec to Docker image.
+
+v14.0.0
+=======
+
+-  Dropped support for Python 3.7.
+-  Dropped support generally speaking, all dependencies older than what Ubuntu 20.04
+   provides.
+-  Ghostscript 9.50 or newer is now required. Shims to support old versions were
+   removed.
+-  Tesseract 4.1.1 or newer is now required. Shims to support old versions were
+   removed.
+-  Docker image now uses Tesseract 5.
+-  Dropped setup.cfg configuration for pyproject.toml.
+-  Removed deprecation exception PdfMergeFailedError.
+-  A few more public domain test files were removed or replaced. We are aiming for
+   100% compliance with SPDX and generally towards simplifying copyright.
+
 v13.7.0
 =======
 
@@ -681,7 +747,7 @@ v10.3.2
 v10.3.1
 =======
 
--  Fixed a number of test suite failures with pdfminer.six older than veresion 20200402.
+-  Fixed a number of test suite failures with pdfminer.six older than version 20200402.
 -  Enabled support for pdfminer.six 20200720.
 
 v10.3.0

misc/batch.py

@@ -2,11 +2,18 @@
 # SPDX-FileCopyrightText: 2016 findingorder <https://github.com/findingorder>
 # SPDX-License-Identifier: MIT
 
+"""Example of using ocrmypdf as a library in a script.
+
+This script will recursively search a directory for PDF files and run OCR on
+them. It will log the results. It runs OCR on every file, even if it already
+has text. OCRmyPDF will detect files that already have text.
+
+You should edit this script to meet your needs.
+"""
+
 from __future__ import annotations
 
-# This script must be edited to meet your needs.
 import logging
-import os
 import sys
 from pathlib import Path
 

misc/docker-compose.example.yml

@@ -1,3 +1,5 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
 ---
 version: "3.3"
 services:

misc/example_plugin.py

@@ -1,8 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R Barlow: https://github.com/jbarlow83
 # SPDX-License-Identifier: MIT
 
-"""
-An example of an OCRmyPDF plugin.
+"""An example of an OCRmyPDF plugin.
 
 This plugin adds two new command line arguments
     --grayscale-ocr: converts the image to grayscale before performing OCR on it

misc/synology.py

@@ -2,6 +2,8 @@
 # SPDX-FileCopyrightText: 2017 Enantiomerie
 # SPDX-License-Identifier: MIT
 
+"""Example OCRmyPDF for Synology NAS."""
+
 from __future__ import annotations
 
 # This script must be edited to meet your needs.
@@ -25,10 +27,7 @@ logging.basicConfig(
     filemode='w',
 )
 
-if len(sys.argv) > 1:
-    start_dir = sys.argv[1]
-else:
-    start_dir = '.'
+start_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
 
 for dir_name, _subdirs, file_list in os.walk(start_dir):
     logging.info(dir_name)

misc/watcher.py

@@ -3,6 +3,8 @@
 # SPDX-FileCopyrightText: 2020 James R Barlow <https://github.com/jbarlow83>
 # SPDX-License-Identifier: MIT
 
+"""Watch a directory for new PDFs and OCR them."""
+
 from __future__ import annotations
 
 import json
@@ -38,6 +40,7 @@ DESKEW = getenv_bool('OCR_DESKEW')
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
 USE_POLLING = getenv_bool('OCR_USE_POLLING')
+RETRIES_LOADING_FILE = int(os.getenv('OCR_RETRIES_LOADING_FILE', '5'))
 LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO')
 PATTERNS = ['*.pdf', '*.PDF']
 
@@ -64,7 +67,7 @@ def wait_for_file_ready(file_path):
     # watchdog event before the file is actually fully on disk, causing
     # pikepdf to fail.
 
-    retries = 5
+    retries = RETRIES_LOADING_FILE
     while retries:
         try:
             pdf = pikepdf.open(file_path)
@@ -103,6 +106,8 @@ def execute_ocrmypdf(file_path):
         elif ON_SUCCESS_ARCHIVE:
             log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
             shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
+        else:
+            log.info('OCR is done')
     else:
         log.info('OCR is done')
 
@@ -140,6 +145,7 @@ def main():
         f"DESKEW: {DESKEW}\n"
         f"ARGS: {OCR_JSON_SETTINGS}\n"
         f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"
+        f"RETRIES_LOADING_FILE: {RETRIES_LOADING_FILE}\n"
         f"USE_POLLING: {USE_POLLING}\n"
         f"LOGLEVEL: {LOGLEVEL}"
     )

misc/webservice.py

@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: 2019 James R. Barlow
 # SPDX-License-Identifier: AGPL-3.0-or-later
 
-"""This is a simple web service/HTTP wrapper for OCRmyPDF
+"""This is a simple web service/HTTP wrapper for OCRmyPDF.
 
 This may be more convenient than the command line tool for some Docker users.
 Note that OCRmyPDF uses Ghostscript, which is licensed under AGPLv3+. While
@@ -15,7 +15,7 @@ from __future__ import annotations
 
 import os
 import shlex
-from subprocess import PIPE, run
+from subprocess import run
 from tempfile import TemporaryDirectory
 
 from flask import Flask, Response, request, send_from_directory
@@ -48,7 +48,7 @@ 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, capture_output=True, encoding="utf-8")
+    proc = run(ocrmypdf_args, capture_output=True, encoding="utf-8", check=False)
     if proc.returncode != 0:
         stderr = proc.stderr
         return Response(stderr, 400, mimetype='text/plain')

pyproject.toml

@@ -1,16 +1,103 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
 [build-system]
 requires = [
-  "setuptools >= 52",
+  "setuptools >= 61",
   "setuptools_scm[toml] >= 7.0.5",
   "wheel"
 ]
 build-backend = "setuptools.build_meta"
 
+[project]
+name = "ocrmypdf"
+dynamic = ["version"]
+description = "OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched"
+readme = "README.md"
+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",
+  "pdfminer.six>=20201018",
+  "pikepdf>=5.0.1",
+  "pluggy>=0.13.0",
+  "reportlab>=3.5.66",
+  "tqdm>=4",
+  "importlib-resources>=5;python_version<'3.9'",  # until Python 3.9
+  "typing-extensions>=4;python_version<'3.10'",
+]
+authors = [{name = "James R. Barlow", email="james@purplerock.ca"}]
+classifiers = [
+  "Development Status :: 5 - Production/Stable",
+  "Environment :: Console",
+  "Intended Audience :: End Users/Desktop",
+  "Intended Audience :: Science/Research",
+  "Intended Audience :: System Administrators",
+  "License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)",
+  "Operating System :: MacOS :: MacOS X",
+  "Operating System :: Microsoft :: Windows :: Windows 10",
+  "Operating System :: POSIX",
+  "Operating System :: POSIX :: BSD",
+  "Operating System :: POSIX :: Linux",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.8",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Topic :: Scientific/Engineering :: Image Recognition",
+  "Topic :: Text Processing :: Indexing",
+  "Topic :: Text Processing :: Linguistic",
+]
+keywords = [
+  "PDF",
+  "OCR",
+  "optical character recognition",
+  "PDF/A",
+  "scanning",
+]
+
+[project.urls]
+Documentation = "https://ocrmypdf.readthedocs.io/"
+Source = "https://github.com/ocrmypdf/OCRmyPDF"
+Tracker = "https://github.com/ocrmypdf/OCRmyPDF/issues"
+
+[project.optional-dependencies]
+docs = ["sphinx", "sphinx-issues", "sphinx-rtd-theme"]
+extended_test = ["PyMuPDF==1.19.1"]
+test = [
+  "coverage[toml]>=5",
+  "hypothesis>=6.0.0",
+  "pytest>=6.0.0",
+  "pytest-cov>=2.11.1",
+  "pytest-xdist>=2.2.0",
+  "python-xmp-toolkit==2.0.1",  # also requires apt-get install libexempi3
+  "types-Pillow",
+  "types-humanfriendly",
+]
+watcher = ["watchdog>=1.0.2"]
+webservice = ["Flask>=1"]
+
+[project.scripts]
+ocrmypdf = "ocrmypdf.__main__:run"
+
+[tool.setuptools.package-data]
+ocrmypdf = ["data/sRGB.icc", "py.typed"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = false
+
 [tool.setuptools_scm]
 
+[tool.distutils.bdist_wheel]
+python-tag = "py38"
+
 [tool.black]
 line-length = 88
-target-version = ["py37", "py38"]
+target-version = ["py38", "py39", "py310", "py311"]
 skip-string-normalization = true
 include = '\.pyi?$'
 exclude = '''
@@ -94,12 +181,30 @@ module = [
   'pdfminer.*',
   'reportlab.*',
   'fitz',
-  'libxmp.utils',
-  'importlib_metadata'
+  'libxmp.utils'
 ]
 ignore_missing_imports = true
 
-[tool.pylint.basic]
-good-names = ["i", "j", "k", "ex", "Run", "_", "e", "p", "im", "w", "h", "m", "x", "y", "a", "b", "fp", "n", "f", "s", "v", "q", "dx", "dy"]
-logging-format-style = "old"
-disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "logging-fstring-interpolation", "missing-function-docstring", "too-few-public-methods"]
+[tool.ruff]
+select = [
+  "D", # pydocstyle
+  "E", # pycodestyle
+  "W", # pycodestyle
+  "F", # pyflakes
+  "I001", # isort
+  "UP", # pyupgrade
+]
+target-version = "py38"
+
+[tool.ruff.isort]
+known-first-party = ["ocrmypdf"]
+required-imports = ["from __future__ import annotations"]
+
+[tool.ruff.pydocstyle]
+convention = "google"
+
+[tool.ruff.per-file-ignores]
+"docs/conf.py" = ["D100", "D101", "D105"]
+"tests/*.py" = ["D100", "D101", "D102", "D103", "D105"]
+"misc/*.py" = ["D103", "D101", "D102"]
+"src/ocrmypdf/builtin_plugins/*.py" = ["D103", "D102", "D105"]

setup.cfg

@@ -1,116 +0,0 @@
-[metadata]
-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/ocrmypdf/OCRmyPDF
-author = James R. Barlow
-author_email = james@purplerock.ca
-license = MPL-2.0
-license_file = LICENSE
-license_files =
-    LICENSE
-classifiers =
-    Development Status :: 5 - Production/Stable
-    Environment :: Console
-    Intended Audience :: End Users/Desktop
-    Intended Audience :: Science/Research
-    Intended Audience :: System Administrators
-    License :: OSI Approved :: Mozilla Public License 2.0 (MPL 2.0)
-    Operating System :: MacOS :: MacOS X
-    Operating System :: Microsoft :: Windows :: Windows 10
-    Operating System :: POSIX
-    Operating System :: POSIX :: BSD
-    Operating System :: POSIX :: Linux
-    Programming Language :: Python :: 3
-    Programming Language :: Python :: 3 :: Only
-    Programming Language :: Python :: 3.7
-    Programming Language :: Python :: 3.8
-    Programming Language :: Python :: 3.9
-    Programming Language :: Python :: 3.10
-    Topic :: Scientific/Engineering :: Image Recognition
-    Topic :: Text Processing :: Indexing
-    Topic :: Text Processing :: Linguistic
-keywords =
-    PDF
-    OCR
-    optical character recognition
-    PDF/A
-    scanning
-project_urls =
-    Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/ocrmypdf/OCRmyPDF
-    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
-
-[options]
-packages = find:
-install_requires =
-    Pillow>=8.2.0
-    coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0  # pure Python
-    packaging>=20
-    pdfminer.six!=20200720,>=20191110
-    pikepdf!=5.0.0,>=4.0.0
-    pluggy>=0.13.0
-    reportlab>=3.5.66
-    tqdm>=4
-    importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
-    importlib-resources>=5;python_version<'3.9'  # until Python 3.9
-    typing-extensions>=4;python_version<'3.10'
-python_requires = >=3.7
-include_package_data = True
-package_dir =
-    =src
-platforms = any
-setup_requires =
-    setuptools-scm
-    setuptools-scm-git-archive
-zip_safe = False
-
-[options.packages.find]
-where = src
-
-[options.entry_points]
-console_scripts =
-    ocrmypdf = ocrmypdf.__main__:run
-
-[options.extras_require]
-docs =
-    sphinx
-    sphinx-issues
-    sphinx-rtd-theme
-extended_test =
-    PyMuPDF==1.19.1
-test =
-    coverage[toml]>=5
-    pytest>=6.0.0
-    pytest-cov>=2.11.1
-    pytest-xdist>=2.2.0
-    python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
-    types-Pillow
-    types-humanfriendly
-watcher =
-    watchdog>=1.0.2
-webservice =
-    Flask>=1
-
-[options.package_data]
-ocrmypdf =
-    data/sRGB.icc
-    py.typed
-
-[bdist_wheel]
-python-tag = py37
-
-[aliases]
-test = pytest
-
-[check-manifest]
-ignore =
-    .github
-
-[flake8]
-ignore = D203,F401,W503,E501,E203,F841
-exclude = .git,__pycache__,docs/conf.py,build,dist,.venv,.venvpp,.eggs,tmp,src/ocrmypdf/lib/
-max-complexity = 10
-max-line-length = 100

setup.py

@@ -1,10 +0,0 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
-# SPDX-License-Identifier: MPL-2.0
-
-"""setup.py to support older setuptools and pip."""
-
-from __future__ import annotations
-
-from setuptools import setup
-
-setup()

snapcraft.yaml

@@ -1,3 +1,8 @@
+# SPDX-FileCopyrightText: 2022 Alexander Langanke
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2023 林博仁(Buo-ren, Lin) <Buo.Ren.Lin@gmail.com>
+# SPDX-License-Identifier: MPL-2.0
+
 name: ocrmypdf
 title: OCRmyPDF
 base: core20
@@ -41,9 +46,19 @@ parts:
     stage-packages:
       - lib32stdc++6
 
+  jbig2enc:
+    plugin: autotools
+    source: https://github.com/agl/jbig2enc.git
+    source-tag: '0.29'
+    build-packages:
+      - libleptonica-dev
+
   ocrmypdf:
     plugin: python
-    source: https://github.com/ocrmypdf/OCRmyPDF.git
+    source: .
+
+    build-packages:
+      - python3-pip
 
     stage-packages:
       - ghostscript
@@ -66,7 +81,14 @@ parts:
       - setuptools
       - tqdm
       - pipe
+      - wheel
 
     override-build: |
+      pip3 install --user dephell[full]
+      $HOME/.local/bin/dephell deps convert \
+          --from-path pyproject.toml \
+          --from-format pyproject \
+          --to-path setup.py \
+          --to-format setuppy
       snapcraftctl build
       ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/RELEASE.md

@@ -1,3 +1,6 @@
+<!-- SPDX-FileCopyrightText: 2022 James R. Barlow -->
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
 # Release checklist
 
 ## Patch release
@@ -14,11 +17,11 @@
 
 - Check README.md
 
-- Check setup.py
+- Check pyproject.toml
 
     - Are classifiers up to date?
     - Is `python_requires` correct?
-    - Python 3.6 is EOL on December 2021-12. Could drop support then.
+    - Is it to drop support for older Pythons?
     - Can we tighten any `install_requires` dependencies?
 
 - Search for old version shims we can remove

src/ocrmypdf/__init__.py

@@ -21,7 +21,6 @@ from ocrmypdf.exceptions import (
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
-    PdfMergeFailedError,
     PriorOcrFoundError,
     SubprocessOutputError,
     TesseractConfigError,
@@ -30,3 +29,33 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.pluginspec import OcrEngine, OrientationConfidence
 
 hookimpl = _HookimplMarker('ocrmypdf')
+
+__all__ = [
+    '__version__',
+    'BadArgsError',
+    'configure_logging',
+    'DpiError',
+    'EncryptedPdfError',
+    'Executor',
+    'ExitCode',
+    'ExitCodeException',
+    'helpers',
+    'hocrtransform',
+    'hookimpl',
+    'InputFileError',
+    'MissingDependencyError',
+    'ocr',
+    'OcrEngine',
+    'OrientationConfidence',
+    'OutputFileAccessError',
+    'PageContext',
+    'pdfa',
+    'PdfContext',
+    'pdfinfo',
+    'PriorOcrFoundError',
+    'PROGRAM_NAME',
+    'SubprocessOutputError',
+    'TesseractConfigError',
+    'UnsupportedImageFormatError',
+    'Verbosity',
+]

src/ocrmypdf/__main__.py

@@ -11,7 +11,6 @@ import os
 import signal
 import sys
 from contextlib import suppress
-from multiprocessing import set_start_method
 
 from ocrmypdf import __version__
 from ocrmypdf._plugin_manager import get_parser_options_plugins
@@ -29,10 +28,16 @@ log = logging.getLogger('ocrmypdf')
 
 
 def sigbus(*args):
+    """Handle SIGBUS signals.
+
+    pikepdf, depending on configuration, may use mmap so SIGBUS is a
+    possibility.
+    """
     raise InputFileError("Lost access to the input file")
 
 
 def run(args=None):
+    """Run the ocrmypdf command line interface."""
     _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
     with suppress(AttributeError, PermissionError):
@@ -71,6 +76,4 @@ def run(args=None):
 
 
 if __name__ == '__main__':
-    if sys.platform == 'darwin' and sys.version_info < (3, 8):
-        set_start_method('spawn')  # see python bpo-33725
     sys.exit(run())

src/ocrmypdf/_concurrent.py

@@ -51,8 +51,7 @@ class Executor(ABC):
         task_arguments: Iterable | None = None,
         task_finished: Callable | None = None,
     ) -> None:
-        """
-        Set up parallel execution and progress reporting.
+        """Set up parallel execution and progress reporting.
 
         Args:
             use_threads: If ``False``, the workload is the sort that will benefit from
@@ -60,7 +59,7 @@ class Executor(ABC):
                 heavily, and parallelizing it with threads is not expected to be
                 performant).
             max_workers: The maximum number of workers that should be run.
-            tdqm_kwargs: Arguments to set up the progress bar.
+            tqdm_kwargs: Arguments to set up the progress bar.
             worker_initializer: Called when a worker is initialized, in the worker's
                 execution context. If the child workers are processes, it must be
                 possible to marshall/pickle the worker initializer.
@@ -73,7 +72,6 @@ class Executor(ABC):
                 task. This runs in the parent's context, but the parameters must be
                 marshallable to the worker.
         """
-
         if not task_arguments:
             return  # Nothing to do!
         if not worker_initializer:

src/ocrmypdf/_exec/__init__.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Manage third party executables"""
+"""Manage third party executables."""
 
 from __future__ import annotations

src/ocrmypdf/_exec/ghostscript.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to Ghostscript executable"""
+"""Interface to Ghostscript executable."""
 
 from __future__ import annotations
 
@@ -14,6 +14,7 @@ from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError
 
+from packaging.version import Version
 from PIL import Image, UnidentifiedImageError
 
 from ocrmypdf.exceptions import SubprocessOutputError
@@ -47,21 +48,6 @@ def version():
     return get_version(GS)
 
 
-def jpeg_passthrough_available() -> bool:
-    """Returns True if the installed version of Ghostscript supports JPEG passthru
-
-    Prior to 9.23, Ghostscript decoded and re-encoded JPEGs internally. In 9.23
-    it gained the ability to keep JPEGs unmodified. However, the 9.23
-    implementation was buggy and would deletes the last two bytes of images in
-    some cases, as reported here.
-    https://bugs.ghostscript.com/show_bug.cgi?id=699216
-
-    The issue was fixed for 9.24, hence that is the first version we consider
-    the feature available. (Ghostscript 9.24 has its own problems is blacklisted.)
-    """
-    return version() >= '9.24'
-
-
 def _gs_error_reported(stream) -> bool:
     match = re.search(r'error', stream, flags=re.IGNORECASE)
     return bool(match)
@@ -201,20 +187,10 @@ def generate_pdfa(
         ]
 
     strategy = 'LeaveColorUnchanged'
-    # Older versions of Ghostscript expect a leading slash in
-    # sColorConversionStrategy, newer ones should not have it. See Ghostscript
-    # git commit fe1c025d.
-    gs_version = version()
-    strategy = ('/' + strategy) if gs_version < '9.19' else strategy
-
-    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...?
+    gs_version = Version(version())
+    if gs_version == Version('9.56.0'):
+        # 9.56.0 breaks our OCR, should be fixed in 9.56.1
+        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
         compression_args.append('-dNEWPDF=false')
 
     # nb no need to specify ProcessColorModel when ColorConversionStrategy

src/ocrmypdf/_exec/jbig2enc.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to jbig2 executable"""
+"""Interface to jbig2 executable."""
 
 from __future__ import annotations
 

src/ocrmypdf/_exec/pngquant.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to pngquant executable"""
+"""Interface to pngquant executable."""
 
 from __future__ import annotations
 

src/ocrmypdf/_exec/tesseract.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Interface to Tesseract executable"""
+"""Interface to Tesseract executable."""
 
 from __future__ import annotations
 
@@ -33,11 +33,13 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
  <head>
   <title></title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
+  <meta name='ocr-capabilities'
+    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word ocrp_wconf'/>
 </head>
 <body>
-  <div class='ocr_page' id='page_1' title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
+  <div class='ocr_page' id='page_1'
+    title='image "_blank.png"; bbox 0 0 {0} {1}; ppageno 0'>
   </div>
  </body>
 </html>
@@ -52,7 +54,7 @@ TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
-    "Prepend [tesseract] to messages emitted from tesseract"
+    """Prepend [tesseract] to messages emitted from tesseract."""
 
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
@@ -104,7 +106,8 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
-    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
+    """Modify standard packaging.Version regex to support Tesseract idiosyncrasies."""
+
     _regex = re.compile(
         r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
     )
@@ -114,15 +117,6 @@ def version() -> str:
     return get_version('tesseract', regex=r'tesseract\s(.+)')
 
 
-def has_user_words() -> bool:
-    """Does Tesseract have --user-words capability?
-
-    Not available in 4.0, but available in 4.1. Also available in 3.x, but
-    we no longer support 3.x.
-    """
-    return version() >= '4.1'
-
-
 def has_thresholding() -> bool:
     """Does Tesseract have -c thresholding method capability?"""
     return version() >= '5.0'
@@ -244,7 +238,7 @@ def get_deskew(
 
 def tesseract_log_output(stream: bytes) -> None:
     tlog = TesseractLoggerAdapter(
-        log, extra=log.extra if hasattr(log, 'extra') else None
+        log, extra=log.extra if hasattr(log, 'extra') else None  # type: ignore
     )
 
     if not stream:
@@ -289,8 +283,10 @@ def page_timedout(timeout: float) -> None:
 
 
 def _generate_null_hocr(output_hocr: Path, output_text: Path, image: Path) -> None:
-    """Produce a .hocr file that reports no text detected on a page that is
-    the same size as the input image."""
+    """Produce a .hocr file that reports no text detected.
+
+    Ensures page is the same size as the input image.
+    """
     with Image.open(image) as im:
         w, h = im.size
 

src/ocrmypdf/_exec/unpaper.py

@@ -1,11 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-from __future__ import annotations
+"""Interface to unpaper executable."""
 
-# unpaper documentation:
-# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-"""Interface to unpaper executable"""
+from __future__ import annotations
 
 import logging
 import os
@@ -22,6 +20,10 @@ from PIL import Image
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
+# unpaper documentation:
+# https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
+
+
 if sys.version_info >= (3, 10):
     from tempfile import TemporaryDirectory
 else:

src/ocrmypdf/_graft.py

@@ -37,7 +37,6 @@ def _update_resources(*, obj, font, font_key, procset):
 
     obj can be a page or Form XObject.
     """
-
     resources = _ensure_dictionary(obj, Name.Resources)
     fonts = _ensure_dictionary(resources, Name.Font)
     if font_key is not None and font_key not in fonts:
@@ -131,7 +130,8 @@ class OcrGrafter:
         text_misaligned = (text_rotation - content_rotation) % 360
         log.debug(
             f"Text rotation: (text, autorotate, content) -> text misalignment = "
-            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> {text_misaligned}"
+            f"({text_rotation}, {autorotate_correction}, {content_rotation}) -> "
+            f"{text_misaligned}"
         )
 
         if textpdf and self.font:
@@ -166,7 +166,6 @@ class OcrGrafter:
         the font to page 1 even if page 1 doesn't use it, so we have a way to get it
         back.
         """
-
         page0 = self.pdf_base.pages[0]
         _update_resources(
             obj=page0, font=self.font, font_key=self.font_key, procset=self.procset
@@ -199,8 +198,7 @@ class OcrGrafter:
         return self.output_file
 
     def _find_font(self, text):
-        """Copy a font from the filename text into pdf_base"""
-
+        """Copy a font from the filename text into pdf_base."""
         font, font_key = None, None
         possible_font_names = ('/f-0-0', '/F1')
         try:
@@ -233,8 +231,7 @@ class OcrGrafter:
         text_rotation: int,
         strip_old_text: bool,
     ):
-        """Insert the text layer from text page 0 on to pdf_base at page_num"""
-
+        """Insert the text layer from text page 0 on to pdf_base at page_num."""
         # pylint: disable=invalid-name
 
         log.debug("Grafting")

src/ocrmypdf/_jobcontext.py

@@ -59,7 +59,7 @@ class PdfContext:
 class PageContext:
     """Holds our context for a page.
 
-    Must be pickable, so stores only intrinsic/simple data elements or those
+    Must be pickle-able, so stores only intrinsic/simple data elements or those
     capable of their serializing themselves via ``__getstate__``.
     """
 

src/ocrmypdf/_logging.py

@@ -24,7 +24,7 @@ class PageNumberFilter(logging.Filter):
 
 
 class TqdmConsole:
-    """Wrapper to log messages in a way that is compatible with tqdm progress bar
+    """Wrapper to log messages in a way that is compatible with tqdm progress bar.
 
     This routes log messages through tqdm so that it can print them above the
     progress bar, and then refresh the progress bar, rather than overwriting

src/ocrmypdf/_pipeline.py

@@ -1,4 +1,5 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2018-2022 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
 # SPDX-License-Identifier: MPL-2.0
 
 """OCRmyPDF page processing pipeline functions."""
@@ -13,7 +14,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Iterable
+from typing import Any, BinaryIO, Iterable, Sequence, cast
 
 import img2pdf
 import pikepdf
@@ -35,7 +36,7 @@ from ocrmypdf.exceptions import (
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
 from ocrmypdf.pdfa import generate_pdfa_ps
-from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
+from ocrmypdf.pdfinfo import Colorspace, Encoding, PageInfo, PdfInfo
 
 # Remove this workaround when we require Pillow >= 10
 try:
@@ -49,7 +50,7 @@ log = logging.getLogger(__name__)
 VECTOR_PAGE_DPI = 400
 
 
-def triage_image_file(input_file, output_file, options):
+def triage_image_file(input_file: Path, output_file: Path, options) -> None:
     log.info("Input file is not a PDF, checking if it is an image...")
     try:
         im = Image.open(input_file)
@@ -113,23 +114,24 @@ def triage_image_file(input_file, output_file, options):
         raise UnsupportedImageFormatError() from e
 
 
-def _pdf_guess_version(input_file, search_window=1024):
+def _pdf_guess_version(input_file: Path, search_window=1024) -> str:
     """Try to find version signature at start of file.
 
     Not robust enough to deal with appended files.
 
     Returns empty string if not found, indicating file is probably not PDF.
     """
-
     with open(input_file, 'rb') as f:
         signature = f.read(search_window)
     m = re.search(br'%PDF-(\d\.\d)', signature)
     if m:
-        return m.group(1)
+        return m.group(1).decode('ascii')
     return ''
 
 
-def triage(original_filename, input_file, output_file, options):
+def triage(
+    original_filename: str, input_file: Path, output_file: Path, options
+) -> Path:
     try:
         if _pdf_guess_version(input_file):
             if options.image_dpi:
@@ -153,9 +155,9 @@ def get_pdfinfo(
     input_file,
     *,
     executor: Executor,
-    detailed_analysis=False,
-    progbar=False,
-    max_workers=None,
+    detailed_analysis: bool = False,
+    progbar: bool = False,
+    max_workers: int | None = None,
     check_pages=None,
 ) -> PdfInfo:
     try:
@@ -173,7 +175,7 @@ def get_pdfinfo(
         raise InputFileError() from e
 
 
-def validate_pdfinfo_options(context: PdfContext):
+def validate_pdfinfo_options(context: PdfContext) -> None:
     pdfinfo = context.pdfinfo
     options = context.options
 
@@ -183,15 +185,6 @@ def validate_pdfinfo_options(context: PdfContext):
             "Designer and can only be read by Adobe Acrobat or Adobe Reader."
         )
         raise InputFileError()
-    if pdfinfo.has_userunit and options.output_type.startswith('pdfa'):
-        log.error(
-            "This input file uses a PDF feature that is not supported "
-            "by Ghostscript, so you cannot use --output-type=pdfa for this "
-            "file. (Specifically, it uses the PDF-1.6 /UserUnit feature to "
-            "support very large or small page sizes, and Ghostscript cannot "
-            "output these files.)  Use --output-type=pdf instead."
-        )
-        raise InputFileError()
     if pdfinfo.has_acroform:
         if options.redo_ocr:
             log.error(
@@ -214,12 +207,12 @@ def validate_pdfinfo_options(context: PdfContext):
     context.plugin_manager.hook.validate(pdfinfo=pdfinfo, options=options)
 
 
-def _vector_page_dpi(pageinfo):
-    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0.0
+def _vector_page_dpi(pageinfo: PageInfo) -> int:
+    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0
 
 
-def get_page_dpi(pageinfo, options):
-    "Get the DPI when nonsquare DPI is tolerable"
+def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:
+    """Get the DPI when nonsquare DPI is tolerable."""
     xres = max(
         pageinfo.dpi.x or VECTOR_PAGE_DPI,
         options.oversample or 0.0,
@@ -233,8 +226,8 @@ def get_page_dpi(pageinfo, options):
     return Resolution(float(xres), float(yres))
 
 
-def get_page_square_dpi(pageinfo, options) -> Resolution:
-    "Get the DPI when we require xres == yres, scaled to physical units"
+def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
+    """Get the DPI when we require xres == yres, scaled to physical units."""
     xres = pageinfo.dpi.x or 0.0
     yres = pageinfo.dpi.y or 0.0
     userunit = float(pageinfo.userunit) or 1.0
@@ -249,8 +242,8 @@ def get_page_square_dpi(pageinfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def get_canvas_square_dpi(pageinfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript units"""
+def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
+    """Get the DPI when we require xres == yres, in Postscript units."""
     units = float(
         max(
             (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
@@ -262,7 +255,7 @@ def get_canvas_square_dpi(pageinfo, options) -> Resolution:
     return Resolution(units, units)
 
 
-def is_ocr_required(page_context: PageContext):
+def is_ocr_required(page_context: PageContext) -> bool:
     pageinfo = page_context.pageinfo
     options = page_context.options
 
@@ -312,8 +305,8 @@ def is_ocr_required(page_context: PageContext):
             log.warning(
                 "page has no images - "
                 "all vector content will be "
-                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and likely "
-                "increasing file size. Use --oversample to adjust the "
+                f"rasterized at {VECTOR_PAGE_DPI} DPI, losing some resolution and "
+                "likely increasing file size. Use --oversample to adjust the "
                 "DPI."
             )
         else:
@@ -337,7 +330,7 @@ def is_ocr_required(page_context: PageContext):
     return ocr_required
 
 
-def rasterize_preview(input_file: Path, page_context: PageContext):
+def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
     output_file = page_context.get_path('rasterize_preview.jpg')
     canvas_dpi = get_canvas_square_dpi(page_context.pageinfo, page_context.options)
     page_dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
@@ -354,10 +347,8 @@ def rasterize_preview(input_file: Path, page_context: PageContext):
     return output_file
 
 
-def describe_rotation(page_context: PageContext, orient_conf, correction: int):
-    """
-    Describe the page rotation we are going to perform.
-    """
+def describe_rotation(page_context: PageContext, orient_conf, correction: int) -> str:
+    """Describe the page rotation we are going to perform."""
     direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
     turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}
 
@@ -383,7 +374,7 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int):
     return f"{facing}, confidence {orient_conf.confidence:.2f} - {action}"
 
 
-def get_orientation_correction(preview: Path, page_context: PageContext):
+def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
     """Work out orientation correct for each page.
 
     We ask Ghostscript to draw a preview page, which will rasterize with the
@@ -398,7 +389,6 @@ def get_orientation_correction(preview: Path, page_context: PageContext):
     which points it (hopefully) upright. _graft.py takes care of the orienting
     the image and text layers.
     """
-
     orient_conf = page_context.plugin_manager.hook.get_ocr_engine().get_orientation(
         preview, page_context.options
     )
@@ -469,18 +459,17 @@ def rasterize(
     return output_file
 
 
-def preprocess_remove_background(input_file: Path, page_context: PageContext):
+def preprocess_remove_background(input_file: Path, page_context: PageContext) -> Path:
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
         raise NotImplementedError("--remove-background is temporarily not implemented")
         # output_file = page_context.get_path('pp_rm_bg.png')
         # leptonica.remove_background(input_file, output_file)
         # return output_file
-    else:
-        log.info("background removal skipped on mono page")
-        return input_file
+    log.info("background removal skipped on mono page")
+    return input_file
 
 
-def preprocess_deskew(input_file: Path, page_context: PageContext):
+def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
     output_file = page_context.get_path('pp_deskew.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
 
@@ -500,7 +489,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
     return output_file
 
 
-def preprocess_clean(input_file: Path, page_context: PageContext):
+def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:
     output_file = page_context.get_path('pp_clean.png')
     dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)
     return unpaper.clean(
@@ -511,11 +500,12 @@ def preprocess_clean(input_file: Path, page_context: PageContext):
     )
 
 
-def create_ocr_image(image: Path, page_context: PageContext):
-    """Create the image we send for OCR. May not be the same as the display
-    image depending on preprocessing. This image will never be shown to the
-    user."""
+def create_ocr_image(image: Path, page_context: PageContext) -> Path:
+    """Create the image we send for OCR.
 
+    Might not be the same as the display image depending on preprocessing.
+    This image will never be shown to the user.
+    """
     output_file = page_context.get_path('ocr.png')
     options = page_context.options
     with Image.open(image) as im:
@@ -559,7 +549,7 @@ def create_ocr_image(image: Path, page_context: PageContext):
     return output_file
 
 
-def ocr_engine_hocr(input_file: Path, page_context: PageContext):
+def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path, Path]:
     hocr_out = page_context.get_path('ocr_hocr.hocr')
     hocr_text_out = page_context.get_path('ocr_hocr.txt')
     options = page_context.options
@@ -574,9 +564,11 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext):
     return (hocr_out, hocr_text_out)
 
 
-def should_visible_page_image_use_jpg(pageinfo):
+def should_visible_page_image_use_jpg(pageinfo: PageInfo) -> bool:
     # If all images were JPEGs originally, produce a JPEG as output
-    return pageinfo.images and all(im.enc == Encoding.jpeg for im in pageinfo.images)
+    return bool(pageinfo.images) and all(
+        im.enc == Encoding.jpeg for im in pageinfo.images
+    )
 
 
 def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
@@ -599,8 +591,8 @@ def create_visible_page_jpg(image: Path, page_context: PageContext) -> Path:
 
 
 def create_pdf_page_from_image(
-    image: Path, page_context: PageContext, orientation_correction
-):
+    image: Path, page_context: PageContext, orientation_correction: int
+) -> Path:
     # We rasterize a square DPI version of each page because most image
     # processing tools don't support rectangular DPI. Use the square DPI as it
     # accurately describes the image. It would be possible to resample the image
@@ -628,11 +620,10 @@ def create_pdf_page_from_image(
     output_file = page_context.plugin_manager.hook.filter_pdf_page(
         page=page_context, image_filename=image, output_pdf=output_file
     )
-
     return output_file
 
 
-def render_hocr_page(hocr: Path, page_context: PageContext):
+def render_hocr_page(hocr: Path, page_context: PageContext) -> Path:
     options = page_context.options
     output_file = page_context.get_path('ocr_hocr.pdf')
     dpi = get_page_square_dpi(page_context.pageinfo, options)
@@ -649,7 +640,9 @@ def render_hocr_page(hocr: Path, page_context: PageContext):
     return output_file
 
 
-def ocr_engine_textonly_pdf(input_image: Path, page_context: PageContext):
+def ocr_engine_textonly_pdf(
+    input_image: Path, page_context: PageContext
+) -> tuple[Path, Path]:
     output_pdf = page_context.get_path('ocr_tess.pdf')
     output_text = page_context.get_path('ocr_tess.txt')
     options = page_context.options
@@ -695,13 +688,13 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
     return pdfmark
 
 
-def generate_postscript_stub(context: PdfContext):
+def generate_postscript_stub(context: PdfContext) -> Path:
     output_file = context.get_path('pdfa.ps')
     generate_pdfa_ps(output_file)
     return output_file
 
 
-def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
+def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -> Path:
     options = context.options
     input_pdfinfo = context.pdfinfo
     fix_docinfo_file = context.get_path('fix_docinfo.pdf')
@@ -748,14 +741,14 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext):
     return output_file
 
 
-def should_linearize(working_file: Path, context: PdfContext):
+def should_linearize(working_file: Path, context: PdfContext) -> bool:
     filesize = os.stat(working_file).st_size
     if filesize > (context.options.fast_web_view * 1_000_000):
         return True
     return False
 
 
-def get_pdf_save_settings(output_type: str):
+def get_pdf_save_settings(output_type: str) -> dict[str, Any]:
     if output_type == 'pdfa-1':
         # Trigger recompression to ensure object streams are removed, because
         # Acrobat complains about them in PDF/A-1b validation.
@@ -773,7 +766,7 @@ def get_pdf_save_settings(output_type: str):
         )
 
 
-def metadata_fixup(working_file: Path, context: PdfContext):
+def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
     output_file = context.get_path('metafix.pdf')
     options = context.options
 
@@ -829,7 +822,9 @@ def metadata_fixup(working_file: Path, context: PdfContext):
     return output_file
 
 
-def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
+def optimize_pdf(
+    input_file: Path, context: PdfContext, executor: Executor
+) -> tuple[Path, Sequence[str]]:
     output_file = context.get_path('optimize.pdf')
     output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
         input_pdf=input_file,
@@ -865,7 +860,7 @@ def enumerate_compress_ranges(iterable):
         yield (skipped_from, index), None
 
 
-def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext):
+def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Path:
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
         for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
@@ -890,15 +885,17 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext):
     return output_file
 
 
-def copy_final(input_file, output_file, _context: PdfContext):
+def copy_final(
+    input_file: Path, output_file: str | Path | BinaryIO, _context: PdfContext
+) -> None:
     log.debug('%s -> %s', input_file, output_file)
-    with open(input_file, 'rb') as input_stream:
+    with input_file.open('rb') as input_stream:
         if output_file == '-':
-            copyfileobj(input_stream, sys.stdout.buffer)
+            copyfileobj(input_stream, sys.stdout.buffer)  # type: ignore[misc]
             sys.stdout.flush()
         elif hasattr(output_file, 'writable'):
-            output_stream = output_file
-            copyfileobj(input_stream, output_stream)
+            output_stream = cast(BinaryIO, output_file)
+            copyfileobj(input_stream, output_stream)  # type: ignore[misc]
             with suppress(AttributeError):
                 output_stream.flush()
         else:

src/ocrmypdf/_sync.py

@@ -1,4 +1,5 @@
-# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-FileCopyrightText: 2019-2022 James R. Barlow
+# SPDX-FileCopyrightText: 2019 Martin Wind
 # SPDX-License-Identifier: MPL-2.0
 
 """Implements the concurrent and page synchronous parts of the pipeline."""
@@ -206,7 +207,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
         filtered_image = page_context.plugin_manager.hook.filter_page_image(
             page=page_context, image_filename=visible_image_out
         )
-        if filtered_image:
+        if filtered_image is not None:  # None if no hook is present
             visible_image_out = filtered_image
         pdf_page_from_image_out = create_pdf_page_from_image(
             visible_image_out, page_context, orientation_correction
@@ -250,8 +251,7 @@ def worker_init(max_pixels: int) -> None:
 
 
 def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
-    """Execute the pipeline concurrently"""
-
+    """Execute the pipeline concurrently."""
     # Run exec_page_sync on every page context
     options = context.options
     max_workers = min(len(context.pdfinfo), options.jobs)
@@ -315,8 +315,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
 def configure_debug_logging(
     log_filename: Path, prefix: str = ''
 ) -> logging.FileHandler:
-    """
-    Create a debug log file at a specified location.
+    """Create a debug log file at a specified location.
 
     Arguments:
         log_filename: Where to the put the log file.
@@ -419,13 +418,13 @@ def run_pipeline(
                 options, start_input_file, options.output_file, optimize_messages
             )
 
-    except (KeyboardInterrupt if not api else NeverRaise):
+    except KeyboardInterrupt if not api else NeverRaise:
         if options.verbose >= 1:
             log.exception("KeyboardInterrupt")
         else:
             log.error("KeyboardInterrupt")
         return ExitCode.ctrl_c
-    except (ExitCodeException if not api else NeverRaise) as e:
+    except ExitCodeException if not api else NeverRaise as e:
         e = cast(ExitCodeException, e)
         if options.verbose >= 1:
             log.exception("ExitCodeException")
@@ -434,7 +433,7 @@ def run_pipeline(
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise):
+    except PIL.Image.DecompressionBombError if not api else NeverRaise:
         log.exception(
             "A decompression bomb error was encountered while executing the "
             "pipeline. Use the argument --max-image-mpixels to raise the maximum "
@@ -452,7 +451,7 @@ def run_pipeline(
             "argument."
         )
         return ExitCode.child_process_error
-    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
+    except Exception if not api else NeverRaise:  # pylint: disable=broad-except
         log.exception("An exception occurred while executing the pipeline")
         return ExitCode.other_error
     finally:

src/ocrmypdf/_validation.py

@@ -61,12 +61,20 @@ def check_options_languages(options: Namespace, ocr_engine_languages: set[str])
         return
     missing_languages = options.languages - ocr_engine_languages
     if missing_languages:
+        lang_text = '\n'.join(lang for lang in missing_languages)
         msg = (
             "OCR engine does not have language data for the following "
             "requested languages: \n"
+            f"{lang_text}\n"
+            "Please install the appropriate language data for your OCR engine.\n"
+            "\n"
+            "See the online documentation for instructions:\n"
+            "    https://ocrmypdf.readthedocs.io/en/latest/languages.html\n"
+            "\n"
+            "Note: most languages are identified by a 3-digit ISO 639-2 Code.\n"
+            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'."
+            "\n"
         )
-        msg += '\n'.join(lang for lang in missing_languages)
-        msg += '\nNote: most languages are identified by a 3-digit ISO 639-2 Code'
         raise MissingDependencyError(msg)
 
 
@@ -109,12 +117,10 @@ def check_options_output(options: Namespace) -> None:
 def check_options_sidecar(options: Namespace) -> None:
     if options.sidecar == '\0':
         if options.output_file == '-':
-            raise BadArgsError(
-                "--sidecar filename must be specified when output file is stdout."
-            )
+            raise BadArgsError("--sidecar filename needed when output file is stdout.")
         elif options.output_file == os.devnull:
             raise BadArgsError(
-                "--sidecar filename must be specified when output file is /dev/null or NUL."
+                "--sidecar filename needed when output file is /dev/null or NUL."
             )
         options.sidecar = options.output_file + '.txt'
     if options.sidecar == options.input_file or options.sidecar == options.output_file:
@@ -134,7 +140,7 @@ def check_options_preprocessing(options: Namespace) -> None:
             package='unpaper',
             version_checker=unpaper.version,
             need_version='6.1',
-            required_for=['--clean, --clean-final'],
+            required_for="--clean, --clean-final",  # Problem arguments
         )
         try:
             if options.unpaper_args:
@@ -221,7 +227,7 @@ def check_options_metadata(options: Namespace) -> None:
 def check_options_pillow(options: Namespace) -> None:
     PIL.Image.MAX_IMAGE_PIXELS = int(options.max_image_mpixels * 1_000_000)
     if PIL.Image.MAX_IMAGE_PIXELS == 0:
-        PIL.Image.MAX_IMAGE_PIXELS = None
+        PIL.Image.MAX_IMAGE_PIXELS = None  # type: ignore
 
 
 def _check_plugin_invariant_options(options: Namespace) -> None:
@@ -276,7 +282,8 @@ def create_input_file(options: Namespace, work_folder: Path) -> tuple[Path, str]
                     "permissions correctly.\n"
                     "You may find it easier to use stdin/stdout:"
                     "\n"
-                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
+                    "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf"
+                    "\n"
                 )
             raise InputFileError(msg) from e
 
@@ -333,7 +340,7 @@ def report_output_file_size(
     for arg in image_preproc:
         if getattr(options, arg, False):
             reasons.append(
-                f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
+                f"--{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
     reasons.extend(optimize_messages)

src/ocrmypdf/_version.py

@@ -8,10 +8,7 @@ OCRmyPDF uses setuptools_scm to derive version from git tags.
 
 from __future__ import annotations
 
-try:
-    from importlib.metadata import version as _package_version
-except ImportError:
-    from importlib_metadata import version as _package_version  # type: ignore
+from importlib.metadata import version as _package_version
 
 PROGRAM_NAME = 'ocrmypdf'
 

src/ocrmypdf/api.py

@@ -15,6 +15,9 @@ 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
@@ -22,15 +25,6 @@ from ocrmypdf._validation import check_options
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-try:
-    import coloredlogs
-except ModuleNotFoundError:
-    coloredlogs = None  # pylint: disable=invalid-name
-
-if coloredlogs:
-    from humanfriendly.terminal import enable_ansi_support
-
-
 StrPath = Union[Path, AnyStr]
 PathOrIO = Union[BinaryIO, StrPath]
 
@@ -92,7 +86,6 @@ def configure_logging(
     Returns:
         The toplevel logger for ocrmypdf (or the root logger, if we are managing it).
     """
-
     prefix = '' if manage_root_logger else 'ocrmypdf'
 
     log = logging.getLogger(prefix)
@@ -121,7 +114,7 @@ def configure_logging(
 
     use_colors = progress_bar_friendly
     formatter = None
-    if coloredlogs and use_colors:
+    if use_colors:
         use_colors = enable_ansi_support()
         if use_colors:
             use_colors = coloredlogs.terminal_supports_colors()
@@ -149,6 +142,7 @@ def configure_logging(
 def create_options(
     *, input_file: PathOrIO, output_file: PathOrIO, parser: ArgumentParser, **kwargs
 ):
+    """Construct an options object from the input/output files and keyword arguments."""
     cmdline = []
     deferred = []
 
@@ -209,59 +203,72 @@ def create_options(
     return options
 
 
-def ocr(  # pylint: disable=unused-argument
+def ocr(  # noqa: ruff: disable=D417
     input_file: PathOrIO,
     output_file: PathOrIO,
     *,
-    language: Iterable[str] = None,
-    image_dpi: int = None,
-    output_type=None,
+    language: Iterable[str] | None = None,
+    image_dpi: int | None = None,
+    output_type: str | None = None,
     sidecar: StrPath | None = None,
-    jobs: int = None,
-    use_threads: bool = None,
-    title: str = None,
-    author: str = None,
-    subject: str = None,
-    keywords: str = None,
-    rotate_pages: bool = None,
-    remove_background: bool = None,
-    deskew: bool = None,
-    clean: bool = None,
-    clean_final: bool = None,
-    unpaper_args: str = None,
-    oversample: int = None,
-    remove_vectors: bool = None,
-    force_ocr: bool = None,
-    skip_text: bool = None,
-    redo_ocr: bool = None,
-    skip_big: float = None,
-    optimize: int = None,
-    jpg_quality: int = None,
-    png_quality: int = None,
-    jbig2_lossy: bool = None,
-    jbig2_page_group_size: int = None,
-    pages: str = None,
-    max_image_mpixels: float = None,
-    tesseract_config: Iterable[str] = None,
-    tesseract_pagesegmode: int = None,
-    tesseract_oem: int = None,
-    tesseract_thresholding: int = None,
-    pdf_renderer=None,
-    tesseract_timeout: float = None,
-    rotate_pages_threshold: float = None,
-    pdfa_image_compression=None,
-    user_words: os.PathLike = None,
-    user_patterns: os.PathLike = None,
-    fast_web_view: float = None,
-    plugins: Iterable[StrPath] = None,
+    jobs: int | None = None,
+    use_threads: bool | None = None,
+    title: str | None = None,
+    author: str | None = None,
+    subject: str | None = None,
+    keywords: str | None = None,
+    rotate_pages: bool | None = None,
+    remove_background: bool | None = None,
+    deskew: bool | None = None,
+    clean: bool | None = None,
+    clean_final: bool | None = None,
+    unpaper_args: str | None = None,
+    oversample: int | None = None,
+    remove_vectors: bool | None = None,
+    force_ocr: bool | None = None,
+    skip_text: bool | None = None,
+    redo_ocr: bool | None = None,
+    skip_big: float | None = None,
+    optimize: int | None = None,
+    jpg_quality: int | None = None,
+    png_quality: int | None = None,
+    jbig2_lossy: bool | None = None,
+    jbig2_page_group_size: int | None = None,
+    pages: str | None = None,
+    max_image_mpixels: float | None = None,
+    tesseract_config: Iterable[str] | None = None,
+    tesseract_pagesegmode: int | None = None,
+    tesseract_oem: int | None = None,
+    tesseract_thresholding: int | None = None,
+    pdf_renderer: str | None = None,
+    tesseract_timeout: float | None = None,
+    tesseract_non_ocr_timeout: float | None = None,
+    rotate_pages_threshold: float | None = None,
+    pdfa_image_compression: str | None = None,
+    user_words: os.PathLike | None = None,
+    user_patterns: os.PathLike | None = None,
+    fast_web_view: float | None = None,
+    plugins: Iterable[StrPath] | None = None,
     plugin_manager=None,
-    keep_temporary_files: bool = None,
-    progress_bar: bool = None,
+    keep_temporary_files: bool | None = None,
+    progress_bar: bool | None = None,
     **kwargs,
 ):
     """Run OCRmyPDF on one PDF or image.
 
     For most arguments, see documentation for the equivalent command line parameter.
+
+    This API takes a threading lock, because OCRmyPDF uses global state in particular
+    for the plugin system. The jobs parameter will be used to create a pool of
+    worker threads or processes at different times, subject to change. A Python
+    process can only run one OCRmyPDF task at a time.
+
+    To run parallelize instances OCRmyPDF, use separate Python processes to scale
+    horizontally. Generally speaking you should set jobs=sqrt(cpu_count) and run
+    sqrt(cpu_count) processes as a starting point. If you have files with a high page
+    count, run fewer processes and more jobs per process. If you have a lot of short
+    files, run more processes and fewer jobs per process.
+
     A few specific arguments are discussed here:
 
     Args:
@@ -283,9 +290,8 @@ def ocr(  # pylint: disable=unused-argument
             When a stream is used as output, whether via a writable object or
             ``"-"``, some final validation steps are not performed (we do not read
             back the stream after it is written).
+
     Raises:
-        ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
-            with the OCR layer.
         ocrmypdf.MissingDependencyError: If a required dependency program is missing or
             was not found on PATH.
         ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that

src/ocrmypdf/builtin_plugins/__init__.py

@@ -1,8 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-from __future__ import annotations
+"""Plugins in this package are automatically loaded by ocrmypdf."""
 
-# This file exists only mark builtin_plugins as a package.
-# The plugin manager will not load it, so anything defined here may not be
-# processed as a module.
+from __future__ import annotations

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -1,9 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-from __future__ import annotations
-
 """OCRmyPDF's multiprocessing/multithreading abstraction layer."""
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import multiprocessing
@@ -30,7 +30,7 @@ WorkerInit = Callable[[Queue, UserInit, int], None]
 
 
 def log_listener(q: Queue):
-    """Listen to the worker processes and forward the messages to logging
+    """Listen to the worker processes and forward the messages to logging.
 
     For simplicity this is a thread rather than a process. Only one process
     should actually write to sys.stderr or whatever we're using, so if this is
@@ -39,7 +39,6 @@ def log_listener(q: Queue):
     See:
     https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
-
     while True:
         try:
             record = q.get()
@@ -55,12 +54,12 @@ def log_listener(q: Queue):
 
 
 def process_sigbus(*args):
+    """Handle SIGBUS signal at the worker level."""
     raise InputFileError("A worker process lost access to an input file")
 
 
 def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
-    """Initialize a process pool worker"""
-
+    """Initialize a process pool worker."""
     # Ignore SIGINT (our parent process will kill us gracefully)
     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
@@ -82,6 +81,7 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    """Begin a thread pool worker."""
     del q  # unused but required argument
     del loglevel  # unused but required argument
     # As a thread, block SIGBUS so the main thread deals with it...
@@ -164,14 +164,17 @@ class StandardExecutor(Executor):
 
 @hookimpl
 def get_executor(progressbar_class):
+    """Return the default executor."""
     return StandardExecutor(pbar_class=progressbar_class)
 
 
 @hookimpl
 def get_progressbar_class():
+    """Return the default progress bar class."""
     return tqdm
 
 
 @hookimpl
 def get_logging_console():
+    """Return the default logging console handler."""
     return logging.StreamHandler(stream=TqdmConsole(sys.stderr))

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -8,7 +8,6 @@ import logging
 
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
-from ocrmypdf._validation import HOCR_OK_LANGS
 from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.subprocess import check_external_program
 
@@ -17,41 +16,24 @@ log = logging.getLogger(__name__)
 
 @hookimpl
 def check_options(options):
+    """Check that the options are valid for this plugin."""
     check_external_program(
         program='gs',
         package='ghostscript',
         version_checker=ghostscript.version,
-        need_version='9.15',  # limited by Travis CI / Ubuntu 14.04 backports
+        need_version='9.50',  # Ubuntu 20.04's version
     )
     gs_version = ghostscript.version()
-    if gs_version in ('9.24', '9.51'):
+    if gs_version in ('9.51',):
         raise MissingDependencyError(
             f"Ghostscript {gs_version} contains serious regressions and is not "
             "supported. Please upgrade to a newer version, or downgrade to the "
             "previous version."
         )
 
-    # We have these constraints to check for.
-    # 1. Ghostscript < 9.20 mangles multibyte Unicode
-    # 2. hocr doesn't work on non-Latin languages (so don't select it)
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
-    if gs_version < '9.20' and options.output_type != 'pdf' and not is_latin:
-        # https://bugs.ghostscript.com/show_bug.cgi?id=696874
-        # Ghostscript < 9.20 fails to encode multibyte characters properly
-        log.warning(
-            f"The installed version of Ghostscript ({gs_version}) does not work "
-            "correctly with the OCR languages you specified. Use --output-type pdf or "
-            "upgrade to Ghostscript 9.20 or later to avoid this issue."
-        )
-
     if options.output_type == 'pdfa':
         options.output_type = 'pdfa-2'
 
-    if options.output_type == 'pdfa-3' and ghostscript.version() < '9.19':
-        raise MissingDependencyError(
-            "--output-type pdfa-3 requires Ghostscript 9.19 or later"
-        )
-
 
 @hookimpl
 def rasterize_pdf_page(
@@ -64,6 +46,7 @@ def rasterize_pdf_page(
     rotation,
     filter_vector,
 ):
+    """Rasterize a single page of a PDF file using Ghostscript."""
     ghostscript.rasterize_pdf(
         input_file,
         output_file,
@@ -87,6 +70,7 @@ def generate_pdfa(
     pdfa_part,
     progressbar_class,
 ):
+    """Generate a PDF/A from the list of PDF pages and PDF/A metadata."""
     ghostscript.generate_pdfa(
         pdf_pages=[*pdf_pages, pdfmark],
         output_file=output_file,

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -8,10 +8,14 @@ from __future__ import annotations
 import logging
 import os
 
+from PIL import Image
+
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
+from ocrmypdf._jobcontext import PageContext
 from ocrmypdf.cli import numeric, str_to_int
 from ocrmypdf.helpers import clamp
+from ocrmypdf.imageops import calculate_downsample, downsample_image
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program
 
@@ -43,7 +47,7 @@ def add_options(parser):
         metavar='MODE',
         choices=range(0, 4),
         help=(
-            "Set Tesseract 4.0+ OCR engine mode: "
+            "Set Tesseract 4+ OCR engine mode: "
             "0 - original Tesseract only; "
             "1 - neural nets LSTM only; "
             "2 - Tesseract + LSTM; "
@@ -58,7 +62,7 @@ def add_options(parser):
         metavar='METHOD',
         help=(
             "Set Tesseract 5.0+ input image thresholding mode. This may improve OCR "
-            "results on low quality images or those that contain high constrast color. "
+            "results on low quality images or those that contain high contrast color. "
             "legacy-otsu is the Tesseract default; adaptive-otsu is an improved Otsu "
             "algorithm with improved sort for background color changes; sauvola is "
             "based on local standard deviation."
@@ -69,8 +73,48 @@ def add_options(parser):
         default=180.0,
         type=numeric(float, 0),
         metavar='SECONDS',
-        help='Give up on OCR after the timeout, but copy the preprocessed page '
-        'into the final output',
+        help=(
+            "Give up on OCR after the timeout, but copy the preprocessed page "
+            "into the final output."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-non-ocr-timeout',
+        default=180.0,
+        type=numeric(float, 0),
+        metavar='SECONDS',
+        help=(
+            "Give up on non-OCR operations such as deskewing and orientation "
+            "after timeout. This is a separate timeout from --tesseract-timeout "
+            "because these operations are not as expensive as OCR."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-large-images',
+        action='store_true',
+        help=(
+            "Downsample large images before OCR. Tesseract has an upper limit on the "
+            "size images it will support. If this argument is given, OCRmyPDF will "
+            "downsample large images to fit Tesseract. This may reduce OCR quality, "
+            "on large images the most desirable text is usually larger. If this "
+            "parameter is not supplied, Tesseract will error out and produce no OCR "
+            "on the page in question. This argument should be used with a high value "
+            "of --tesseract-timeout to ensure Tesseract has enough to time."
+        ),
+    )
+    tess.add_argument(
+        '--tesseract-downsample-above',
+        action='store',
+        type=numeric(int, 100, 32767),
+        default=32767,
+        help=(
+            "Downsample images larger than this size pixel size in either dimension "
+            "before OCR. --tesseract-downsample-large-images downsamples only when "
+            "an image exceeds Tesseract's internal limits. This argument causes "
+            "downsampling to occur when an image exceeds the given size. This may "
+            "reduce OCR quality, but on large images the most desirable text is "
+            "usually larger."
+        ),
     )
     tess.add_argument(
         '--user-words',
@@ -93,7 +137,7 @@ def check_options(options):
         program='tesseract',
         package={'linux': 'tesseract-ocr'},
         version_checker=tesseract.version,
-        need_version='4.0.0-beta.1',  # using backport for Travis CI
+        need_version='4.1.1',  # Ubuntu 20.04 version
         version_parser=tesseract.TesseractVersion,
     )
 
@@ -101,11 +145,6 @@ def check_options(options):
     if options.pdf_renderer == 'auto':
         options.pdf_renderer = 'sandwich'
 
-    if not tesseract.has_user_words() and (options.user_words or options.user_patterns):
-        log.warning(
-            "Tesseract 4.0 (which you have installed) ignores --user-words and "
-            "--user-patterns, so these arguments have no effect."
-        )
     if not tesseract.has_thresholding() and options.tesseract_thresholding != 0:
         log.warning(
             "The installed version of Tesseract does not support changes to its "
@@ -137,6 +176,25 @@ def validate(pdfinfo, options):
     log.debug("Using Tesseract OpenMP thread limit %d", tess_threads)
 
 
+@hookimpl
+def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
+    """Filter the image before OCR.
+
+    Tesseract cannot handle images with more than 32767 pixels in either axis,
+    or more than 2**31 bytes. This function resizes the image to fit within
+    those limits.
+    """
+    threshold = min(page.options.tesseract_downsample_above, 32767)
+
+    options = page.options
+    if options.tesseract_downsample_large_images:
+        size = calculate_downsample(
+            image, max_size=(threshold, threshold), max_bytes=(2**31) - 1
+        )
+        image = downsample_image(image, size)
+    return image
+
+
 class TesseractOcrEngine(OcrEngine):
     """Implements OCR with Tesseract."""
 
@@ -161,7 +219,7 @@ class TesseractOcrEngine(OcrEngine):
         return tesseract.get_orientation(
             input_file,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod
@@ -170,7 +228,7 @@ class TesseractOcrEngine(OcrEngine):
             input_file,
             languages=options.languages,
             engine_mode=options.tesseract_oem,
-            timeout=options.tesseract_timeout,
+            timeout=options.tesseract_non_ocr_timeout,
         )
 
     @staticmethod

src/ocrmypdf/cli.py

@@ -15,7 +15,7 @@ T = TypeVar('T', int, float)
 
 
 def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    """Validator for numeric params"""
+    """Validator for numeric params."""
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
 
@@ -46,7 +46,7 @@ def str_to_int(mapping: Mapping[str, int]):
 
 
 class ArgumentParser(argparse.ArgumentParser):
-    """Override parser's default behavior of calling sys.exit()
+    """Override parser's default behavior of calling sys.exit().
 
     https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
 
@@ -57,13 +57,21 @@ class ArgumentParser(argparse.ArgumentParser):
     """
 
     def __init__(self, *args, **kwargs):
+        """Initialize the parser."""
         super().__init__(*args, **kwargs)
         self._api_mode = False
 
     def enable_api_mode(self):
+        """Enable API mode.
+
+        When set, the parser will not call sys.exit() on error. OCRmyPDF was originally
+        a command line program, but now it has an API. The API works by synthesizing
+        command line arguments.
+        """
         self._api_mode = True
 
     def error(self, message):
+        """Override the default argparse error behavior."""
         if not self._api_mode:
             super().error(message)
             return
@@ -74,11 +82,13 @@ class LanguageSetAction(argparse.Action):
     """Manages a list of languages."""
 
     def __init__(self, option_strings, dest, default=None, **kwargs):
+        """Initialize the action."""
         if default is None:
             default = set()
         super().__init__(option_strings, dest, default=default, **kwargs)
 
     def __call__(self, parser, namespace, values, option_string=None):
+        """Add a language to the set."""
         dest = getattr(namespace, self.dest)
         if '+' in values:
             dest.update(lang for lang in values.split('+'))
@@ -87,6 +97,7 @@ class LanguageSetAction(argparse.Action):
 
 
 def get_parser():
+    """Get the main CLI parser."""
     parser = ArgumentParser(
         prog=_PROGRAM_NAME,
         allow_abbrev=True,

src/ocrmypdf/exceptions.py

@@ -35,6 +35,7 @@ class ExitCodeException(Exception):
     message = ""
 
     def __str__(self):
+        """Return a string representation of the exception."""
         super_msg = super().__str__()  # Don't do str(super())
         if self.message:
             return self.message.format(super_msg)
@@ -47,26 +48,6 @@ class BadArgsError(ExitCodeException):
     exit_code = ExitCode.bad_args
 
 
-class PdfMergeFailedError(ExitCodeException):  # deprecated
-    """An intermediate PDF can't be merged.
-
-    No longer in use.
-    """
-
-    exit_code = ExitCode.input_file
-    message = dedent(
-        '''\
-        Failed to merge PDF image layer with OCR layer
-
-        Usually this happens because the input PDF file is malformed and
-        ocrmypdf cannot correct the problem on its own.
-
-        Try using
-            ocrmypdf --pdf-renderer sandwich  [..other args..]
-        '''
-    )
-
-
 class MissingDependencyError(ExitCodeException):
     """A third-party dependency is missing."""
 
@@ -114,7 +95,7 @@ class EncryptedPdfError(ExitCodeException):
 
     exit_code = ExitCode.encrypted_pdf
     message = dedent(
-        '''\
+        """\
         Input PDF is encrypted. The encryption must be removed to
         perform OCR.
 
@@ -123,7 +104,7 @@ class EncryptedPdfError(ExitCodeException):
 
         You can remove the encryption using
             qpdf --decrypt [--password=[password]] infilename
-        '''
+        """
     )
 
 

src/ocrmypdf/extra_plugins/__init__.py

@@ -1,3 +1,9 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 #
 # SPDX-License-Identifier: MPL-2.0
+
+"""Extra plugins. These are not automatically inserted when ocrmypdf is run.
+
+You can use these plugins by specifying them on the command line, e.g.:
+ocrmypdf --plugin ocrmypdf.extra_plugins.semfree ...
+"""

src/ocrmypdf/extra_plugins/semfree.py

@@ -54,6 +54,7 @@ def split_every(n: int, iterable: Iterable) -> Iterator:
 
 
 def process_sigbus(*args):
+    """Handle SIGBUS signal at the worker level."""
     raise InputFileError("A worker process lost access to an input file")
 
 
@@ -61,20 +62,21 @@ class ConnectionLogHandler(logging.handlers.QueueHandler):
     """Handler used by child processes to forward log messages to parent."""
 
     def __init__(self, conn: Connection) -> None:
+        """Initialize the handler."""
         # sets the parent's queue to None - parent only touches queue
         # in enqueue() which we override
         super().__init__(None)  # type: ignore
         self.conn = conn
 
     def enqueue(self, record):
+        """Enqueue a log message."""
         self.conn.send(('log', record))
 
 
 def process_loop(
     conn: Connection, user_init: Callable[[], None], loglevel, task, task_args
 ):
-    """Initialize a process pool worker"""
-
+    """Initialize a process pool worker."""
     # Install SIGBUS handler (so our parent process can abort somewhat gracefully)
     with suppress(AttributeError):  # Windows and Cygwin do not have SIGBUS
         # Windows and Cygwin do not have pthread_sigmask or SIGBUS
@@ -166,8 +168,7 @@ class LambdaExecutor(Executor):
                         continue
 
                     if msg_type == MessageType.result:
-                        if task_finished:
-                            task_finished(msg, pbar)
+                        task_finished(msg, pbar)
                     elif msg_type == 'log':
                         record = msg
                         logger = logging.getLogger(record.name)
@@ -185,14 +186,20 @@ class LambdaExecutor(Executor):
 
 @hookimpl
 def get_executor(progressbar_class):
+    """Return a LambdaExecutor instance."""
     return LambdaExecutor(pbar_class=progressbar_class)
 
 
 @hookimpl
 def get_logging_console():
+    """Return a logging.StreamHandler instance."""
     return logging.StreamHandler()
 
 
 @hookimpl
 def get_progressbar_class():
+    """Return a NullProgressBar instance.
+
+    This executor cannot use a progress bar.
+    """
     return NullProgressBar

src/ocrmypdf/helpers.py

@@ -10,14 +10,12 @@ import multiprocessing
 import os
 import shutil
 import warnings
-from collections import namedtuple
 from collections.abc import Iterable
 from contextlib import suppress
-from functools import wraps
 from io import StringIO
 from math import isclose, isfinite
 from pathlib import Path
-from typing import Any, Sequence
+from typing import Any, Generic, Sequence, SupportsFloat, SupportsRound, TypeVar
 
 import img2pdf
 import pikepdf
@@ -35,23 +33,36 @@ else:
     )
 
 
-class Resolution(namedtuple('Resolution', ('x', 'y'))):
+T = TypeVar('T', bound=SupportsRound[Any])
+
+
+class Resolution(Generic[T]):
     """The number of pixels per inch in each 2D direction.
 
     Resolution objects are considered "equal" for == purposes if they are
     equal to a reasonable tolerance.
     """
 
-    __slots__ = ()
+    x: T
+    y: T
+
+    __slots__ = ('x', 'y')
+
+    def __init__(self, x: T, y: T):
+        """Construct a Resolution object."""
+        self.x = x
+        self.y = y
 
     # rel_tol after converting from dpi to pixels per meter and saving
     # as integer with rounding, as many file formats
     CONVERSION_ERROR = 0.002
 
-    def round(self, ndigits: int):
+    def round(self, ndigits: int) -> Resolution:
+        """Round to ndigits after the decimal point."""
         return Resolution(round(self.x, ndigits), round(self.y, ndigits))
 
-    def to_int(self):
+    def to_int(self) -> Resolution[int]:
+        """Round to nearest integer."""
         return Resolution(int(round(self.x)), int(round(self.y)))
 
     @classmethod
@@ -60,13 +71,20 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
 
     @property
     def is_square(self) -> bool:
+        """True if the resolution is square (x == y)."""
         return self._isclose(self.x, self.y)
 
     @property
     def is_finite(self) -> bool:
-        return isfinite(self.x) and isfinite(self.y)
+        """True if both x and y are finite numbers."""
+        if isinstance(self.x, SupportsFloat) and isinstance(self.y, SupportsFloat):
+            return isfinite(self.x) and isfinite(self.y)
+        return True
 
-    def take_max(self, vals, yvals=None):
+    def take_max(
+        self, vals: Iterable[Any], yvals: Iterable[Any] | None = None
+    ) -> Resolution:
+        """Return a new Resolution object with the maximum resolution of inputs."""
         if yvals is not None:
             return Resolution(max(self.x, *vals), max(self.y, *yvals))
         max_x, max_y = self.x, self.y
@@ -75,16 +93,24 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
             max_y = max(y, max_y)
         return Resolution(max_x, max_y)
 
-    def flip_axis(self):
+    def flip_axis(self) -> Resolution[T]:
+        """Return a new Resolution object with x and y swapped."""
         return Resolution(self.y, self.x)
 
+    def __getitem__(self, idx: int | slice) -> T:
+        """Support [0] and [1] indexing."""
+        return (self.x, self.y)[idx]
+
     def __str__(self):
+        """Return a string representation of the resolution."""
         return f"{self.x:f}x{self.y:f}"
 
     def __repr__(self):  # pragma: no cover
+        """Return a repr() of the resolution."""
         return f"Resolution({self.x}x{self.y} dpi)"
 
     def __eq__(self, other):
+        """Return True if the resolution is equal to another resolution."""
         if isinstance(other, tuple) and len(other) == 2:
             other = Resolution(*other)
         if not isinstance(other, Resolution):
@@ -93,7 +119,7 @@ class Resolution(namedtuple('Resolution', ('x', 'y'))):
 
 
 class NeverRaise(Exception):
-    """An exception that is never raised"""
+    """An exception that is never raised."""
 
 
 def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
@@ -138,6 +164,10 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
 
 
 def samefile(file1: os.PathLike, file2: os.PathLike):
+    """Return True if two files are the same file.
+
+    Attempts to account for different relative paths to the same file.
+    """
     if os.name == 'nt':
         return file1 == file2
     else:
@@ -155,7 +185,7 @@ def monotonic(seq: Sequence) -> bool:
 
 
 def page_number(input_file: os.PathLike) -> int:
-    """Get one-based page number implied by filename (000002.pdf -> 2)"""
+    """Get one-based page number implied by filename (000002.pdf -> 2)."""
     return int(os.path.basename(os.fspath(input_file))[0:6])
 
 
@@ -184,7 +214,7 @@ def is_file_writable(test_file: os.PathLike) -> bool:
             p = p.resolve(strict=False)
 
         # p.is_file() throws an exception in some cases
-        if p.exists() and p.is_file():
+        if p.exists() and (p.is_file() or p.samefile(os.devnull)):
             return os.access(
                 os.fspath(p),
                 os.W_OK,
@@ -258,13 +288,20 @@ def clamp(n, smallest, largest):  # mypy doesn't understand types for this
 
 
 def remove_all_log_handlers(logger):
-    "Remove all log handlers, usually used in a child process."
+    """Remove all log handlers, usually used in a child process.
+
+    The child process inherits the log handlers from the parent process when
+    a fork occurs. Typically we want to remove all log handlers in the child
+    process so that the child process can set up a single queue handler to
+    forward log messages to the parent process.
+    """
     for handler in logger.handlers[:]:
         logger.removeHandler(handler)
         handler.close()  # To ensure handlers with opened resources are released
 
 
 def pikepdf_enable_mmap():
+    """Enable pikepdf mmap."""
     # try:
     #     if pikepdf._qpdf.set_access_default_mmap(True):
     #         log.debug("pikepdf mmap enabled")
@@ -275,20 +312,3 @@ def pikepdf_enable_mmap():
     # Fix is not in pybind11 2.6.0
     # log.debug("pikepdf mmap disabled")
     return
-
-
-def deprecated(func):
-    """Warn that function is deprecated."""
-
-    @wraps(func)
-    def new_func(*args, **kwargs):
-        warnings.simplefilter('always', DeprecationWarning)  # turn off filter
-        warnings.warn(
-            f"Call to deprecated function {func.__name__}.",
-            category=DeprecationWarning,
-            stacklevel=2,
-        )
-        warnings.simplefilter('default', DeprecationWarning)  # reset filter
-        return func(*args, **kwargs)
-
-    return new_func

src/ocrmypdf/hocrtransform.py

@@ -14,10 +14,11 @@ import re
 import warnings
 from math import atan, cos, sin
 from pathlib import Path
-from typing import Any, NamedTuple, Optional, Tuple, Union
+from typing import Any, NamedTuple
 from xml.etree import ElementTree
 
 with warnings.catch_warnings():
+    # reportlab uses deprecated load_module
     warnings.filterwarnings(
         'ignore', category=DeprecationWarning, message=r".*load_module.*"
     )
@@ -98,11 +99,10 @@ class HocrTransformError(Exception):
 
 
 class HocrTransform:
+    """A class for converting documents from the hOCR format.
 
-    """
-    A class for converting documents from the hOCR format.
     For details of the hOCR format, see:
-    http://kba.cloud/hocr-spec/
+    http://kba.cloud/hocr-spec/.
     """
 
     box_pattern = re.compile(r'bbox((\s+\d+){4})')
@@ -118,6 +118,7 @@ class HocrTransform:
     )
 
     def __init__(self, *, hocr_filename: str | Path, dpi: float):
+        """Initialize the HocrTransform object."""
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
 
@@ -142,9 +143,7 @@ class HocrTransform:
             raise HocrTransformError("hocr file is missing page dimensions")
 
     def __str__(self):  # pragma: no cover
-        """
-        Return the textual content of the HTML body
-        """
+        """Return the textual content of the HTML body."""
         if self.hocr is None:
             return ''
         body = self.hocr.find(self._child_xpath('body'))
@@ -154,9 +153,7 @@ class HocrTransform:
             return ''
 
     def _get_element_text(self, element: Element):
-        """
-        Return the textual content of the element and its children
-        """
+        """Return the textual content of the element and its children."""
         text = ''
         if element.text is not None:
             text += element.text
@@ -168,10 +165,7 @@ class HocrTransform:
 
     @classmethod
     def element_coordinates(cls, element: Element) -> Rect:
-        """
-        Returns a tuple containing the coordinates of the bounding box around
-        an element
-        """
+        """Get coordinates of the bounding box around an element."""
         out = Rect._make(0 for _ in range(4))
         if 'title' in element.attrib:
             matches = cls.box_pattern.search(element.attrib['title'])
@@ -182,9 +176,7 @@ class HocrTransform:
 
     @classmethod
     def baseline(cls, element: Element) -> tuple[float, float]:
-        """
-        Returns a tuple containing the baseline slope and intercept.
-        """
+        """Get baseline's slope and intercept."""
         if 'title' in element.attrib:
             matches = cls.baseline_pattern.search(element.attrib['title'])
             if matches:
@@ -192,9 +184,7 @@ class HocrTransform:
         return (0.0, 0.0)
 
     def pt_from_pixel(self, pxl) -> Rect:
-        """
-        Returns the quantity in PDF units (pt) given quantity in pixels
-        """
+        """Returns the quantity in PDF units (pt) given quantity in pixels."""
         return Rect._make((c / self.dpi * inch) for c in pxl)
 
     def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
@@ -205,21 +195,9 @@ class HocrTransform:
 
     @classmethod
     def replace_unsupported_chars(cls, s: str) -> str:
-        """
-        Given an input string, returns the corresponding string that:
-        * is available in the Helvetica facetype
-        * does not contain any ligature (to allow easy search in the PDF file)
-        """
+        """Replaces characters with those available in the Helvetica typeface."""
         return s.translate(cls.ligatures)
 
-    def topdown_position(self, element):
-        pxl_line_coords = self.element_coordinates(element)
-        line_box = self.pt_from_pixel(pxl_line_coords)
-        # Coordinates here are still in the hocr coordinate system, so 0 on the y axis
-        # is the top of the page and increasing values of y will move towards the
-        # bottom of the page.
-        return line_box.y2
-
     def to_pdf(
         self,
         *,
@@ -230,8 +208,8 @@ class HocrTransform:
         invisible_text: bool = False,
         interword_spaces: bool = False,
     ) -> None:
-        """
-        Creates a PDF file with an image superimposed on top of the text.
+        """Creates a PDF file with an image superimposed on top of the text.
+
         Text is positioned according to the bounding box of the lines in
         the hOCR file.
         The image need not be identical to the image used to create the hOCR
@@ -322,6 +300,7 @@ class HocrTransform:
 
     @classmethod
     def polyval(cls, poly, x):  # pragma: no cover
+        """Calculate the value of a polynomial at a point."""
         return x * poly[0] + poly[1]
 
     def _do_line(

src/ocrmypdf/imageops.py

@@ -0,0 +1,172 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+"""OCR-related image manipulation."""
+
+from __future__ import annotations
+
+import logging
+from functools import singledispatch
+from math import floor, sqrt
+from typing import Optional, Tuple
+
+from PIL import Image
+
+# Remove this workaround when we require Pillow >= 9.1.0
+try:
+    Resampling = Image.Resampling  # type: ignore
+except AttributeError:
+    # Pillow 9 shim
+    Resampling = Image  # type: ignore
+
+
+# While from __future__ import annotations, we use singledispatch here, which
+# does not support annotations. Disable check about using old-style typing
+# until Python 3.10, OR when drop singledispatch in ocrmypdf 15.
+# ruff: noqa: UP006
+# ruff: noqa: UP007
+
+
+log = logging.getLogger(__name__)
+
+
+def bytes_per_pixel(mode: str) -> int:
+    """Return the number of padded bytes per pixel for a given PIL image mode.
+
+    In RGB mode we assume 4 bytes per pixel, which is the case for most
+    consumers.
+    """
+    if mode in ('1', 'L', 'P'):
+        return 1
+    if mode in ('LA', 'PA', 'La') or mode.startswith('I;16'):
+        return 2
+    return 4
+
+
+@singledispatch
+def calculate_downsample(
+    image_size: Tuple[int, int],
+    bytes_per_pixel: int,
+    *,
+    max_size: Optional[Tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> Tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image_size: Dimensions of image.
+        bytes_per_pixel: Number of bytes per pixel.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    size = image_size
+
+    if max_size is not None:
+        overage = max_size[0] / size[0], max_size[1] / size[1]
+        size_factor = min(overage)
+        if size_factor < 1.0:
+            log.debug("Resizing image to fit image dimensions limit")
+            size = floor(size[0] * size_factor), floor(size[1] * size_factor)
+            if size[0] == 0:
+                size = 1, min(size[1], max_size[1])
+            elif size[1] == 0:
+                size = min(size[0], max_size[0]), 1
+
+    if max_pixels is not None:
+        if size[0] * size[1] > max_pixels:
+            log.debug("Resizing image to fit image pixel limit")
+            pixels_factor = sqrt(max_pixels / (size[0] * size[1]))
+            size = floor(size[0] * pixels_factor), floor(size[1] * pixels_factor)
+
+    if max_bytes is not None:
+        bpp = bytes_per_pixel
+        # stride = bytes per line
+        stride = size[0] * bpp
+        height = size[1]
+        if stride * height > max_bytes:
+            log.debug("Resizing image to fit image byte size limit")
+            bytes_factor = sqrt(max_bytes / (stride * height))
+            scaled_stride = floor(stride * bytes_factor)
+            scaled_height = floor(height * bytes_factor)
+            if scaled_stride == 0:
+                scaled_stride = bpp
+                scaled_height = min(max_bytes // bpp, scaled_height)
+            if scaled_height == 0:
+                scaled_height = 1
+                scaled_stride = min(max_bytes // scaled_height, scaled_stride)
+            size = floor(scaled_stride / bpp), scaled_height
+
+    return size
+
+
+@calculate_downsample.register
+def _(
+    image: Image.Image,
+    arg: None = None,
+    *,
+    max_size: Optional[Tuple[int, int]] = None,
+    max_pixels: Optional[int] = None,
+    max_bytes: Optional[int] = None,
+) -> Tuple[int, int]:
+    """Calculate image size required to downsample an image to fit limits.
+
+    If no limit is exceeded, the input image's size is returned.
+
+    Args:
+        image: The image to downsample.
+        max_size: The maximum width and height of the image.
+        max_pixels: The maximum number of pixels in the image. Some image consumers
+            limit the total number of pixels as some value other than width*height.
+        max_bytes: The maximum number of bytes in the image. RGB is counted as 4
+            bytes; all other modes are counted as 1 byte.
+    """
+    return calculate_downsample(
+        image.size,
+        bytes_per_pixel(image.mode),
+        max_size=max_size,
+        max_pixels=max_pixels,
+        max_bytes=max_bytes,
+    )
+
+
+def downsample_image(
+    image: Image.Image,
+    new_size: tuple[int, int],
+    *,
+    resample_mode: Image.Resampling = Resampling.BICUBIC,
+    reducing_gap: int = 3,
+) -> Image.Image:
+    """Downsample an image to fit within the given limits.
+
+    The DPI is adjusted to match the new size, which is how we can ensure the
+    OCR is positioned correctly.
+
+    Args:
+        image: The image to downsample
+        new_size: The new size of the image.
+        resample_mode: The resampling mode to use when downsampling.
+        reducing_gap: The reducing gap to use when downsampling (for larger
+            reductions).
+    """
+    if new_size == image.size:
+        return image
+
+    original_size = image.size
+    original_dpi = image.info['dpi']
+    image = image.resize(
+        new_size,
+        resample=resample_mode,
+        reducing_gap=reducing_gap,
+    )
+    image.info['dpi'] = (
+        round(original_dpi[0] * new_size[0] / original_size[0]),
+        round(original_dpi[1] * new_size[1] / original_size[1]),
+    )
+    log.debug(f"Rescaled image to {image.size} pixels and {image.info['dpi']} dpi")
+    return image

src/ocrmypdf/optimize.py

@@ -53,20 +53,24 @@ class XrefExt(NamedTuple):
 
 
 def img_name(root: Path, xref: Xref, ext: str) -> Path:
+    """Return the name of an image file for a given xref and extension."""
     return root / f'{xref:08d}{ext}'
 
 
 def png_name(root: Path, xref: Xref) -> Path:
+    """Return the name of a PNG file for a given xref."""
     return img_name(root, xref, '.png')
 
 
 def jpg_name(root: Path, xref: Xref) -> Path:
+    """Return the name of a JPEG file for a given xref."""
     return img_name(root, xref, '.jpg')
 
 
 def extract_image_filter(
     pike: Pdf, root: Path, image: Stream, xref: Xref
 ) -> tuple[PdfImage, tuple[Name, Object]] | None:
+    """Determine if an image is extractable."""
     del pike  # unused args
     del root
 
@@ -124,6 +128,7 @@ def extract_image_filter(
 def extract_image_jbig2(
     *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
+    """Extract an image, saving it as a JBIG2 file."""
     del options  # unused arg
 
     result = extract_image_filter(pike, root, image, xref)
@@ -165,6 +170,7 @@ def extract_image_jbig2(
 def extract_image_generic(
     *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
 ) -> XrefExt | None:
+    """Generic image extraction."""
     result = extract_image_filter(pike, root, image, xref)
     if result is None:
         return None
@@ -230,7 +236,7 @@ def extract_images(
     options,
     extract_fn: Callable[..., XrefExt | None],
 ) -> Iterator[tuple[int, XrefExt]]:
-    """Extract image using extract_fn
+    """Extract image using extract_fn.
 
     Enumerate images on each page, lookup their xref/ID number in the PDF.
     Exclude images that are soft masks (i.e. alpha transparency related).
@@ -244,7 +250,6 @@ def extract_images(
     it does a tuple should be returned: (xref, ext) where .ext is the file
     extension. extract_fn must also extract the file it finds interesting.
     """
-
     include_xrefs: MutableSet[Xref] = set()
     exclude_xrefs: MutableSet[Xref] = set()
     pageno_for_xref = {}
@@ -289,8 +294,7 @@ def extract_images(
 def extract_images_generic(
     pike: Pdf, root: Path, options
 ) -> tuple[list[Xref], list[Xref]]:
-    """Extract any >=2bpp image we think we can improve"""
-
+    """Extract any >=2bpp image we think we can improve."""
     jpegs = []
     pngs = []
     for _, xref_ext in extract_images(pike, root, options, extract_image_generic):
@@ -304,8 +308,7 @@ def extract_images_generic(
 
 
 def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefExt]]:
-    """Extract any bitonal image that we think we can improve as JBIG2"""
-
+    """Extract any bitonal image that we think we can improve as JBIG2."""
     jbig2_groups = defaultdict(list)
     for pageno, xref_ext in extract_images(pike, root, options, extract_image_jbig2):
         group = pageno // options.jbig2_page_group_size
@@ -318,7 +321,7 @@ def extract_images_jbig2(pike: Pdf, root: Path, options) -> dict[int, list[XrefE
 def _produce_jbig2_images(
     jbig2_groups: dict[int, list[XrefExt]], root: Path, options, executor: Executor
 ) -> None:
-    """Produce JBIG2 images from their groups"""
+    """Produce JBIG2 images from their groups."""
 
     def jbig2_group_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
@@ -423,6 +426,8 @@ def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | Non
 def transcode_jpegs(
     pike: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
 ) -> None:
+    """Optimize JPEGs according to optimization settings."""
+
     def jpeg_args() -> Iterator[tuple[Xref, Path, Path, int]]:
         for xref in jpegs:
             in_jpg = jpg_name(root, xref)
@@ -481,6 +486,12 @@ def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, by
 
 
 def deflate_jpegs(pike: Pdf, root: Path, options, executor: Executor) -> None:
+    """Apply FlateDecode to JPEGs.
+
+    This is a lossless compression method that is supported by all PDF viewers,
+    and generally results in a smaller file size compared to straight DCTDecode
+    images.
+    """
     jpegs = []
     for _pageno, xref_ext in extract_images(pike, root, options, _find_deflatable_jpeg):
         xref = xref_ext.xref
@@ -568,6 +579,7 @@ def transcode_pngs(
     options,
     executor,
 ) -> None:
+    """Apply lossy transcoding to PNGs."""
     modified: MutableSet[Xref] = set()
     if options.optimize >= 2:
         png_quality = (
@@ -614,6 +626,7 @@ def optimize(
     save_settings,
     executor: Executor = DEFAULT_EXECUTOR,
 ) -> Path:
+    """Optimize images in a PDF file."""
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
@@ -670,11 +683,12 @@ def optimize(
 
 
 def main(infile, outfile, level, jobs=1):
+    """Entry point for direct optimization of a file."""
     from shutil import copy  # pylint: disable=import-outside-toplevel
     from tempfile import TemporaryDirectory  # pylint: disable=import-outside-toplevel
 
     class OptimizeOptions:
-        """Emulate ocrmypdf's options"""
+        """Emulate ocrmypdf's options."""
 
         def __init__(
             self, input_file, jobs, optimize_, jpeg_quality, png_quality, jb2lossy

src/ocrmypdf/pdfa.py

@@ -1,9 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""
-Utilities for PDF/A production and confirmation with Ghostspcript.
-"""
+"""Utilities for PDF/A production and confirmation with Ghostspcript."""
 
 from __future__ import annotations
 
@@ -25,8 +23,8 @@ def _postscript_objdef(
     alias: str,
     dictionary: dict[str, str],
     *,
-    stream_name: str = None,
-    stream_data: bytes = None,
+    stream_name: str | None = None,
+    stream_data: bytes | None = None,
 ) -> Iterator[str]:
     assert (stream_name is None) == (stream_data is None)
 
@@ -75,7 +73,7 @@ def _make_postscript(icc_name: str, icc_data: bytes, colors: int) -> Iterator[st
 
 
 def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
-    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion
+    """Create a Postscript PDFMARK file for Ghostscript PDF/A conversion.
 
     pdfmark is an extension to the Postscript language that describes some PDF
     features like bookmarks and annotations. It was originally specified Adobe
@@ -84,7 +82,7 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
     Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript
     to create a PDF/A, we need to create a pdfmark file with the necessary metadata.
 
-    This function takes care of the many version-specific bugs and pecularities in
+    This function takes care of the many version-specific bugs and peculiarities in
     Ghostscript's handling of pdfmark.
 
     The only information we put in specifies that we want the file to be a
@@ -118,7 +116,6 @@ def file_claims_pdfa(filename: Path):
     This only checks if the XMP metadata contains a PDF/A marker. It does not
     do full PDF/A validation.
     """
-
     with pikepdf.open(filename) as pdf:
         pdfmeta = pdf.open_metadata()
         if not pdfmeta.pdfa_status:

src/ocrmypdf/pdfinfo/__init__.py

@@ -6,4 +6,6 @@
 
 from __future__ import annotations
 
-from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo
+from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PageInfo, PdfInfo
+
+__all__ = ["Colorspace", "Encoding", "PageInfo", "PdfInfo"]

src/ocrmypdf/pdfinfo/info.py

@@ -17,16 +17,7 @@ from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
-from typing import (
-    Container,
-    Iterable,
-    Iterator,
-    Mapping,
-    NamedTuple,
-    Optional,
-    Sequence,
-    Tuple,
-)
+from typing import Container, Iterable, Iterator, Mapping, NamedTuple, Sequence, Tuple
 from warnings import warn
 
 from pikepdf import (
@@ -173,7 +164,7 @@ class TextMarker:
 
 
 def _normalize_stack(graphobjs):
-    """Convert runs of qQ's in the stack into single graphobjs"""
+    """Convert runs of qQ's in the stack into single graphobjs."""
     for operands, operator in graphobjs:
         operator = str(operator)
         if re.match(r'Q*q+$', operator):  # Zero or more Q, one or more q
@@ -209,7 +200,6 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
     undefined in the spec, but we just pretend nothing happened and leave the
     CTM unchanged.
     """
-
     stack = []
     ctm = PdfMatrix(initial_shorthand)
     xobject_settings: list[XobjectSettings] = []
@@ -316,7 +306,6 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
     /MediaBox.
 
     """
-
     a, b, c, d, _, _ = ctm_shorthand  # pylint: disable=invalid-name
 
     # Calculate the width and height of the image in PDF units
@@ -333,7 +322,12 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
 
 
 class ImageInfo:
-    """Information about an image found in a PDF."""
+    """Information about an image found in a PDF.
+
+    This gathers information from pikepdf and pdfminer.six, and is pickle-able
+    so that it can be passed to a worker process, unlike objects from those
+    libraries.
+    """
 
     DPI_PREC = Decimal('1.000')
 
@@ -348,6 +342,7 @@ class ImageInfo:
         inline: PdfInlineImage | None = None,
         shorthand=None,
     ):
+        """Initialize an ImageInfo."""
         self._name = str(name)
         self._shorthand = shorthand
 
@@ -414,45 +409,62 @@ class ImageInfo:
 
     @property
     def name(self):
+        """Name of the image as it appears in the PDF."""
         return self._name
 
     @property
     def type_(self):
+        """Type of image, either 'image' or 'stencil'."""
         return self._type
 
     @property
     def width(self):
+        """Width of the image in pixels."""
         return self._width
 
     @property
     def height(self):
+        """Height of the image in pixels."""
         return self._height
 
     @property
     def bpc(self):
+        """Bits per component."""
         return self._bpc
 
     @property
     def color(self):
+        """Colorspace of the image."""
         return self._color if self._color is not None else '?'
 
     @property
     def comp(self):
+        """Number of components/channels in the image."""
         return self._comp if self._comp is not None else '?'
 
     @property
     def enc(self):
+        """Encoding of the image."""
         return self._enc if self._enc is not None else 'image'
 
     @property
-    def renderable(self):
+    def renderable(self) -> bool:
+        """Whether the image is renderable.
+
+        Some PDFs in the wild have invalid images that are not renderable.
+        """
         return self.dpi.is_finite and self.width >= 0 and self.height >= 0
 
     @property
     def dpi(self):
+        """Dots per inch of the image.
+
+        Calculated based on where and how the image is drawn in the PDF.
+        """
         return _get_dpi(self._shorthand, (self._width, self._height))
 
     def __repr__(self):
+        """Return a string representation of the image."""
         return (
             f"<ImageInfo '{self.name}' {self.type_} {self.width}x{self.height} "
             f"{self.color} {self.comp} {self.bpc} {self.enc} {self.dpi}>"
@@ -460,8 +472,7 @@ class ImageInfo:
 
 
 def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
-    "Find inline images in the contentstream"
-
+    """Find inline images in the contentstream."""
     for n, inline in enumerate(contentsinfo.inline_images):
         yield ImageInfo(
             name=f'inline-{n:02d}', shorthand=inline.shorthand, inline=inline.iimage
@@ -469,7 +480,7 @@ def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
 
 
 def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
-    """Search for all XObject-based images in the container
+    """Search for all XObject-based images in the container.
 
     Usually the container is a page, but it could also be a Form XObject
     that contains images. Filter out the Form XObjects which are dealt with
@@ -480,33 +491,29 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     since the object does not know its own name.
 
     """
-
     if '/Resources' not in container:
         return
     resources = container['/Resources']
     if '/XObject' not in resources:
         return
-    xobjs = resources['/XObject'].as_dict()
-    for xobj in xobjs:
-        candidate: Object = xobjs[xobj]
-        if '/Subtype' not in candidate:
+    for key, candidate in resources['/XObject'].items():
+        if candidate is None or '/Subtype' not in candidate:
             continue
         if candidate['/Subtype'] == '/Image':
             pdfimage = candidate
-            yield (pdfimage, xobj)
+            yield (pdfimage, key)
 
 
 def _find_regular_images(
     container: Object, contentsinfo: ContentsInfo
 ) -> Iterator[ImageInfo]:
-    """Find images stored in the container's /Resources /XObject
+    """Find images stored in the container's /Resources /XObject.
 
     Usually the container is a page, but it could also be a Form XObject
     that contains images.
 
     Generates images with their DPI at time of drawing.
     """
-
     for pdfimage, xobj in _image_xobjects(container):
         if xobj not in contentsinfo.name_index:
             continue
@@ -523,7 +530,7 @@ def _find_regular_images(
 
 
 def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: ContentsInfo):
-    """Find any images that are in Form XObjects in the container
+    """Find any images that are in Form XObjects in the container.
 
     The container may be a page, or a parent Form XObject.
 
@@ -536,7 +543,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
     xobjs = resources['/XObject'].as_dict()
     for xobj in xobjs:
         candidate = xobjs[xobj]
-        if candidate['/Subtype'] != '/Form':
+        if candidate is None or candidate['/Subtype'] != '/Form':
             continue
 
         form_xobject = candidate
@@ -557,7 +564,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
 def _process_content_streams(
     *, pdf: Pdf, container: Object, shorthand=None
 ) -> Iterator[VectorMarker | TextMarker | ImageInfo]:
-    """Find all individual instances of images drawn in the container
+    """Find all individual instances of images drawn in the container.
 
     Usually the container is a page, but it may also be a Form XObject.
 
@@ -574,7 +581,6 @@ def _process_content_streams(
     downsampling.
 
     """
-
     if container.get('/Type') == '/Page' and '/Contents' in container:
         initial_shorthand = shorthand or UNIT_SQUARE
     elif container.get('/Type') == '/XObject' and container['/Subtype'] == '/Form':
@@ -606,8 +612,7 @@ def _process_content_streams(
 
 
 def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) -> bool:
-    """Smarter text detection that ignores text in margins"""
-
+    """Smarter text detection that ignores text in margins."""
     pw, ph = float(page_width), float(page_height)  # pylint: disable=invalid-name
 
     margin_ratio = 0.125
@@ -619,10 +624,11 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
     )
 
     def rects_intersect(a: FloatRect, b: FloatRect) -> bool:
-        """
+        """Check if two 4-tuple rects intersect.
+
         Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3)
         https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other
-        Formula assumes all boxes are in first quadrant
+        Formula assumes all boxes are in first quadrant.
         """
         return a[0] < b[2] and a[2] > b[0] and a[1] > b[3] and a[3] < b[1]
 
@@ -635,7 +641,7 @@ def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) ->
 
 
 def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
-    """Extract only limited content from text boxes
+    """Extract only limited content from text boxes.
 
     We do this to save memory and ensure that our objects are pickleable.
     """
@@ -751,6 +757,7 @@ class PageInfo:
         check_pages: Container[int],
         detailed_analysis: bool = False,
     ):
+        """Initialize a PageInfo object."""
         self._pageno = pageno
         self._infile = infile
         self._detailed_analysis = detailed_analysis
@@ -827,40 +834,56 @@ class PageInfo:
 
     @property
     def pageno(self) -> int:
+        """Return page number (0-based)."""
         return self._pageno
 
     @property
     def has_text(self) -> bool:
+        """Return True if page has text, False if not or unknown."""
         return bool(self._has_text)
 
     @property
     def has_corrupt_text(self) -> bool:
+        """Return True if page has corrupt text, False if not or unknown."""
         if not self._detailed_analysis:
             raise NotImplementedError('Did not do detailed analysis')
         return any(tbox.is_corrupt for tbox in self._textboxes)
 
     @property
     def has_vector(self) -> bool:
+        """Return True if page has vector graphics, False if not or unknown.
+
+        Vector graphics are sometimes used to draw fonts, so it may not be
+        obvious on visual inspection whether a page has text or not.
+        """
         return bool(self._has_vector)
 
     @property
     def width_inches(self) -> Decimal:
+        """Return width of page in inches."""
         return self._width_inches
 
     @property
     def height_inches(self) -> Decimal:
+        """Return height of page in inches."""
         return self._height_inches
 
     @property
     def width_pixels(self) -> int:
+        """Return width of page in pixels."""
         return int(round(float(self.width_inches) * self.dpi.x))
 
     @property
     def height_pixels(self) -> int:
+        """Return height of page in pixels."""
         return int(round(float(self.height_inches) * self.dpi.y))
 
     @property
     def rotation(self) -> int:
+        """Return rotation of page in degrees.
+
+        Will only be a multiple of 90.
+        """
         return self._rotate
 
     @rotation.setter
@@ -871,10 +894,13 @@ class PageInfo:
             raise ValueError("rotation must be a cardinal angle")
 
     @property
-    def images(self):
+    def images(self) -> list[ImageInfo]:
+        """Return images."""
         return self._images
 
     def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
+        """Return textareas bounding boxes in PDF coordinates on the page."""
+
         def predicate(obj, want_visible, want_corrupt):
             result = True
             if want_visible is not None:
@@ -894,22 +920,26 @@ class PageInfo:
 
     @property
     def dpi(self) -> Resolution:
+        """Return DPI needed to render all images on the page."""
         if self._dpi is None:
             return Resolution(0.0, 0.0)
         return self._dpi
 
     @property
     def userunit(self) -> Decimal:
+        """Return user unit of page."""
         return self._userunit
 
     @property
     def min_version(self) -> str:
+        """Return minimum PDF version needed to render this page."""
         if self.userunit is not None:
             return '1.6'
         else:
             return '1.5'
 
     def __repr__(self):
+        """Return string representation."""
         return (
             f'<PageInfo '
             f'pageno={self.pageno} {self.width_inches}"x{self.height_inches}" '
@@ -921,7 +951,7 @@ DEFAULT_EXECUTOR = SerialExecutor()
 
 
 class PdfInfo:
-    """Get summary information about a PDF"""
+    """Get summary information about a PDF."""
 
     def __init__(
         self,
@@ -929,10 +959,11 @@ class PdfInfo:
         *,
         detailed_analysis: bool = False,
         progbar: bool = False,
-        max_workers: int = None,
+        max_workers: int | None = None,
         check_pages=None,
         executor: Executor = DEFAULT_EXECUTOR,
     ):
+        """Initialize."""
         self._infile = infile
         if check_pages is None:
             check_pages = range(0, 1_000_000_000)
@@ -959,42 +990,56 @@ class PdfInfo:
 
     @property
     def pages(self) -> Sequence[PageInfo | None]:
+        """Return list of PageInfo objects, one per page in the PDF."""
         return self._pages
 
     @property
     def min_version(self) -> str:
+        """Return minimum PDF version needed to render this PDF."""
         # The minimum PDF is the maximum version that any particular page needs
         return max(page.min_version for page in self.pages if page)
 
     @property
     def has_userunit(self) -> bool:
+        """Return True if any page has a user unit."""
         return any(page.userunit != 1.0 for page in self.pages if page)
 
     @property
     def has_acroform(self) -> bool:
+        """Return True if any page has an AcroForm."""
         return self._has_acroform
 
     @property
     def filename(self) -> str | Path:
+        """Return filename of PDF."""
         if not isinstance(self._infile, (str, Path)):
             raise NotImplementedError("can't get filename from stream")
         return self._infile
 
     @property
     def needs_rendering(self) -> bool:
+        """Return True if PDF contains XFA forms.
+
+        XFA forms are not supported by most standard PDF renderers, so we
+        need to detect and suppress them.
+        """
         return self._needs_rendering
 
     def __getitem__(self, item) -> PageInfo:
+        """Return PageInfo object for page number `item`."""
         return self._pages[item]
 
     def __len__(self):
+        """Return number of pages in PDF."""
         return len(self._pages)
 
     def __repr__(self):
+        """Return string representation."""
         return f"<PdfInfo('...'), page count={len(self)}>"
 
 
 def main():
+    """Run as a script."""
     import argparse  # pylint: disable=import-outside-toplevel
     from pprint import pprint  # pylint: disable=import-outside-toplevel
 

src/ocrmypdf/pdfinfo/layout.py

@@ -1,5 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
+"""Detailed text position and layout analysis, building on pdfminer.six."""
+
 from __future__ import annotations
 
 import re
@@ -23,45 +25,68 @@ from ocrmypdf.exceptions import EncryptedPdfError, InputFileError
 STRIP_NAME = re.compile(r'[0-9]+')
 
 
-original_PDFSimpleFont_init = PDFSimpleFont.__init__
+original_pdfsimplefont_init = PDFSimpleFont.__init__
 
 
-def PDFSimpleFont__init__(self, descriptor, widths, spec):
+def pdfsimplefont__init__(self, descriptor, widths, spec):
+    """Monkeypatch pdfminer.six PDFSimpleFont.__init__.
+
+    If there is no ToUnicode and no Encoding, pdfminer.six assumes that Unicode
+    conversion is possible. This is incorrect, according to PDF Reference Manual
+    9.10.2. This patch fixes that.
+    """
     # Font encoding is specified either by a name of
     # built-in encoding or a dictionary that describes
     # the differences.
-    original_PDFSimpleFont_init(self, descriptor, widths, spec)
-    # pdfminer is incorrect. If there is no ToUnicode and no Encoding, do not
-    # assume Unicode conversion is possible. RM 9.10.2
+    original_pdfsimplefont_init(self, descriptor, widths, spec)
     if not self.unicode_map and 'Encoding' not in spec:
         self.cid2unicode = {}
     return
 
 
-PDFSimpleFont.__init__ = PDFSimpleFont__init__
+PDFSimpleFont.__init__ = pdfsimplefont__init__
 
 #
 # pdfminer patches when creator is PScript5.dll
 #
 
 
-def PDFType3Font__PScript5_get_height(self):
+def pdftype3font__pscript5_get_height(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The height of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the height by
+    using the bbox height if it is available, otherwise using the
+    ascent and descent.
+    """
     h = self.bbox[3] - self.bbox[1]
     if h == 0:
         h = self.ascent - self.descent
     return h * copysign(1.0, self.vscale)
 
 
-def PDFType3Font__PScript5_get_descent(self):
+def pdftype3font__pscript5_get_descent(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The descent of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the descent by
+    using the vscale.
+    """
     return self.descent * copysign(1.0, self.vscale)
 
 
-def PDFType3Font__PScript5_get_ascent(self):
+def pdftype3font__pscript5_get_ascent(self):
+    """Monkeypatch for PScript5.dll PDFs.
+
+    The ascent of Type3 fonts is known to be incorrect in PScript5.dll
+    generated PDFs. This patch attempts to correct the ascent by
+    using the vscale.
+    """
     return self.ascent * copysign(1.0, self.vscale)
 
 
 class LTStateAwareChar(LTChar):
-    """A subclass of LTChar that tracks text render mode at time of drawing"""
+    """A subclass of LTChar that tracks text render mode at time of drawing."""
 
     __slots__ = (
         'rendermode',
@@ -94,6 +119,7 @@ class LTStateAwareChar(LTChar):
         graphicstate,
         textstate,
     ):
+        """Initialize."""
         super().__init__(
             matrix,
             font,
@@ -109,7 +135,7 @@ class LTStateAwareChar(LTChar):
         self.rendermode = textstate.render
 
     def is_compatible(self, obj):
-        """Check if characters can be combined into a textline
+        """Check if characters can be combined into a textline.
 
         We consider characters compatible if:
             - the Unicode mapping is known, and both have the same render mode
@@ -127,36 +153,41 @@ class LTStateAwareChar(LTChar):
             return False
 
     def get_text(self):
+        """Get text from this character."""
         if isinstance(self._text, tuple):
             return '\ufffd'  # standard 'Unknown symbol'
         return self._text
 
     def __repr__(self):
-        return '<{} {} matrix={} rendermode={!r} font={!r} adv={} text={!r}>'.format(
-            self.__class__.__name__,
-            bbox2str(self.bbox),
-            matrix2str(self.matrix),
-            self.rendermode,
-            self.fontname,
-            self.adv,
-            self.get_text(),
+        """Return a string representation of this object."""
+        return (
+            f"<{self.__class__.__name__} "
+            f"{bbox2str(self.bbox)} "
+            f"matrix={matrix2str(self.matrix)} "
+            f"rendermode={self.rendermode!r} "
+            f"font={self.fontname!r} "
+            f"adv={self.adv} "
+            f"text={self.get_text()!r}>"
         )
 
 
 class TextPositionTracker(PDFLayoutAnalyzer):
-    """A page layout analyzer that pays attention to text visibility"""
+    """A page layout analyzer that pays attention to text visibility."""
 
     def __init__(self, rsrcmgr, pageno=1, laparams=None):
+        """Initialize the layout analyzer."""
         super().__init__(rsrcmgr, pageno, laparams)
         self.textstate = None
         self.result = None
         self.cur_item = None  # not defined in pdfminer code as it should be
 
     def begin_page(self, page, ctm):
+        """Begin processing of a page."""
         super().begin_page(page, ctm)
         self.cur_item = LTPage(self.pageno, page.mediabox)
 
     def end_page(self, page):
+        """End processing of a page."""
         assert not self._stack, str(len(self._stack))
         assert isinstance(self.cur_item, LTPage), str(type(self.cur_item))
         if self.laparams is not None:
@@ -165,12 +196,14 @@ class TextPositionTracker(PDFLayoutAnalyzer):
         self.receive_layout(self.cur_item)
 
     def render_string(self, textstate, seq, ncs, graphicstate):
+        """Respond to render string event by updating text state."""
         self.textstate = textstate.copy()
         super().render_string(self.textstate, seq, ncs, graphicstate)
 
     def render_char(
         self, matrix, font, fontsize, scaling, rise, cid, ncs, graphicstate
     ):
+        """Respond to render char event by updating text state."""
         try:
             text = font.to_unichr(cid)
             assert isinstance(text, str), str(type(text))
@@ -195,23 +228,23 @@ class TextPositionTracker(PDFLayoutAnalyzer):
         return item.adv
 
     def handle_undefined_char(self, font, cid):
+        """Handle undefined character."""
         # log.info('undefined: %r, %r', font, cid)
         return (font.fontname, cid)
 
     def receive_layout(self, ltpage):
+        """Receive layout handler."""
         self.result = ltpage
 
     def get_result(self):
+        """Get the result of the analysis."""
         return self.result
 
 
 def get_page_analysis(infile, pageno, pscript5_mode):
+    """Get the page analysis for a given page."""
     rman = pdfminer.pdfinterp.PDFResourceManager(caching=True)
-    if pdfminer.__version__ < '20200402':
-        # Workaround for https://github.com/pdfminer/pdfminer.six/issues/395
-        disable_boxes_flow = 2
-    else:
-        disable_boxes_flow = None
+    disable_boxes_flow = None
     dev = TextPositionTracker(
         rman,
         laparams=LAParams(
@@ -225,9 +258,9 @@ def get_page_analysis(infile, pageno, pscript5_mode):
         patcher = patch.multiple(
             'pdfminer.pdffont.PDFType3Font',
             spec=True,
-            get_ascent=PDFType3Font__PScript5_get_ascent,
-            get_descent=PDFType3Font__PScript5_get_descent,
-            get_height=PDFType3Font__PScript5_get_height,
+            get_ascent=pdftype3font__pscript5_get_ascent,
+            get_descent=pdftype3font__pscript5_get_descent,
+            get_height=pdftype3font__pscript5_get_height,
         )
         patcher.start()
 
@@ -250,6 +283,7 @@ def get_page_analysis(infile, pageno, pscript5_mode):
 
 
 def get_text_boxes(obj):
+    """Get the text boxes attached to the current node."""
     for child in obj:
         if isinstance(child, (LTTextBox)):
             yield child

src/ocrmypdf/pluginspec.py

@@ -28,6 +28,7 @@ if TYPE_CHECKING:
 hookspec = pluggy.HookspecMarker('ocrmypdf')
 
 # pylint: disable=unused-argument
+# mypy: disable-error-code=empty-body
 
 
 @hookspec(firstresult=True)
@@ -43,7 +44,7 @@ def get_logging_console() -> Handler:
 
 
 @hookspec
-def initialize(plugin_manager: pluggy.PluginManager):
+def initialize(plugin_manager: pluggy.PluginManager) -> None:
     """Called when this plugin is first loaded into OCRmyPDF.
 
     The primary intended use of this is for plugins to check compatibility with other
@@ -99,6 +100,8 @@ def check_options(options: Namespace) -> None:
         ocrmypdf.exceptions.ExitCodeException: If options are not acceptable
             and the application should terminate gracefully with an informative
             message and error code.
+
+
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
@@ -127,6 +130,8 @@ def get_executor(progressbar_class) -> Executor:
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
+
+
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -159,7 +164,6 @@ 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:
             ...
@@ -181,6 +185,8 @@ def validate(pdfinfo: PdfInfo, options: Namespace) -> None:
         ocrmypdf.exceptions.ExitCodeException: If options or pdfinfo are not acceptable
             and the application should terminate gracefully with an informative
             message and error code.
+
+
     Note:
         This hook will be called from the main process, and may modify global state
         before child worker processes are forked.
@@ -218,6 +224,8 @@ def rasterize_pdf_page(
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+
+
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -228,23 +236,32 @@ def filter_ocr_image(page: PageContext, image: Image.Image) -> Image.Image:
     """Called to filter the image before it is sent to OCR.
 
     This is the image that OCR sees, not what the user sees when they view the
-    PDF. If ``redo_ocr`` is enabled, portions of the image will be masked so
-    they are not shown to OCR. The main use of this hook is expected to be hiding
-    content from OCR.
+    PDF. In certain modes such as ``--redo-ocr``, portions of the image may be
+    masked out to hide them from OCR.
+
+    The main uses of this hook are expected to be hiding content from OCR,
+    conditioning images to OCR better with filters, and adjusting images to
+    match any constraints imposed by the OCR engine.
 
     The input image may be color, grayscale, or monochrome, and the
-    output image may differ. The pixel width and height of the
-    output image must be identical to the input image, or misalignment between
-    the OCR text layer and visual position of the text will occur. Likewise,
-    the output must be a faithful representation of the input, or alignment
-    errors may occurs.
+    output image may differ. For example, if you know that a custom OCR engine
+    does not care about the color of the text, you could convert the image to
+    it to grayscale or monochrome.
 
-    Tesseract OCR only deals with monochrome images, and internally converts
-    non-monochrome images to OCR.
+    Generally speaking, the output image should be a faithful representation of
+    of the input image. You *may* change the pixel width and height of the
+    the input image, but you must not change the aspect ratio, and you must
+    calculate the DPI of the output image based on the new pixel width and
+    height or the OCR text layer will be misaligned with the visual position.
+
+    The built-in Tesseract OCR engine uses this hook itself to downsample
+    very large images to fit its constraints.
 
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+
+
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -269,7 +286,7 @@ def filter_page_image(page: PageContext, image_filename: Path) -> Path:
     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
-    hook is overriden). If you convert the image to a JPEG, the output page will
+    hook is overridden). If you convert the image to a JPEG, the output page will
     be created as a JPEG, etc. If you change the colorspace, that change will be
     kept. Note that the OCRmyPDF image optimization stage, if enabled, may
     ultimately chose a different format.
@@ -278,13 +295,11 @@ def filter_page_image(page: PageContext, image_filename: Path) -> Path:
     will occur. The return value should be a path to a file in the same folder
     as ``image_filename``.
 
-    Implementation detail: If the value returned is falsy, OCRmyPDF will ignore
-    the return value and assume the input file was unmodified. This is deprecated.
-    To leave the image unmodified, ``image_filename`` should be returned.
-
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+
+
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -327,6 +342,8 @@ def filter_pdf_page(page: PageContext, image_filename: Path, output_pdf: Path) -
     Note:
         This hook will be called from child processes. Modifying global state
         will not affect the main process or other child processes.
+
+
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
     """
@@ -385,7 +402,8 @@ class OcrEngine(ABC):
         """Returns the set of all languages that are supported by the engine.
 
         Languages are typically given in 3-letter ISO 3166-1 codes, but actually
-        can be any value understood by the OCR engine."""
+        can be any value understood by the OCR engine.
+        """
 
     @staticmethod
     @abstractmethod
@@ -417,6 +435,9 @@ class OcrEngine(ABC):
                 a single page PDF with no visible content of any kind, sized
                 to the dimensions implied by the input_file's width, height
                 and DPI. The image will be grafted onto the input PDF page.
+            output_text: The expected name of a text file containing the
+                recognized text.
+            options: The command line options.
         """
 
 
@@ -478,7 +499,7 @@ def generate_pdfa(
     Note:
         This is a :ref:`firstresult hook<firstresult>`.
 
-    See also:
+    See Also:
         https://github.com/tqdm/tqdm
     """
 

src/ocrmypdf/quality.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
-"""Utilities to measure OCR quality"""
+"""Utilities to measure OCR quality."""
 
 
 from __future__ import annotations

src/ocrmypdf/subprocess/__init__.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
-"""Wrappers to manage subprocess calls"""
+"""Wrappers to manage subprocess calls."""
 
 from __future__ import annotations
 
@@ -9,7 +9,6 @@ import os
 import re
 import sys
 from contextlib import suppress
-from functools import lru_cache
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
@@ -35,20 +34,25 @@ def run(
     check: bool = False,
     **kwargs,
 ) -> CompletedProcess:
-    """Wrapper around :py:func:`subprocess.run`
+    """Wrapper around :py:func:`subprocess.run`.
 
     The main purpose of this wrapper is to log subprocess output in an orderly
-    fashion that indentifies the responsible subprocess. An additional
+    fashion that identifies the responsible subprocess. An additional
     task is that this function goes to greater lengths to find possible Windows
     locations of our dependencies when they are not on the system PATH.
 
     Arguments should be identical to ``subprocess.run``, except for following:
 
-    Arguments:
+    Args:
+        args: Positional arguments to pass to ``subprocess.run``.
+        env: A set of environment variables. If None, the OS environment is used.
         logs_errors_to_stdout: If True, indicates that the process writes its error
             messages to stdout rather than stderr, so stdout should be logged
             if there is an error. If False, stderr is logged. Could be used with
             stderr=STDOUT, stdout=PIPE for example.
+        check: If True, raise an exception if the process exits with a non-zero
+            status code. If False, the return value will indicate success or failure.
+        kwargs: Additional arguments to pass to ``subprocess.run``.
     """
     args, env, process_log, _text = _fix_process_args(args, env, kwargs)
 
@@ -135,7 +139,6 @@ def _fix_process_args(
     return args, env, process_log, text
 
 
-@lru_cache(maxsize=None)
 def get_version(
     program: str,
     *,
@@ -143,7 +146,7 @@ def get_version(
     regex=r'(\d+(\.\d+)*)',
     env: OsEnviron | None = None,
 ) -> str:
-    """Get the version of the specified program
+    """Get the version of the specified program.
 
     Arguments:
         program: The program to version check.
@@ -316,7 +319,7 @@ def check_external_program(
         program: The name of the program to test.
         package: The name of a software package that typically supplies this program.
             Usually the same as program.
-        version_check: A callable without arguments that retrieves the installed
+        version_checker: A callable without arguments that retrieves the installed
             version of program.
         need_version: The minimum required version.
         required_for: The name of an argument of feature that requires this program.
@@ -325,12 +328,8 @@ def check_external_program(
         version_parser: A class that should be used to parse and compare version
             numbers. Used when version numbers do not follow standard conventions.
     """
-
     try:
-        if callable(version_checker):
-            found_version = version_checker()
-        else:  # deprecated
-            found_version = version_checker
+        found_version = version_checker()
     except (CalledProcessError, FileNotFoundError) as e:
         _error_missing_program(program, package, required_for, recommended)
         if not recommended:

src/ocrmypdf/subprocess/_windows.py

@@ -6,12 +6,15 @@ from __future__ import annotations
 
 import logging
 import os
+import re
 import shutil
 import sys
 from itertools import chain
 from pathlib import Path
 from typing import Any, Callable, Iterable, Iterator, TypeVar
 
+from packaging.version import InvalidVersion, Version
+
 if sys.version_info >= (3, 10):
     from typing import TypeAlias
 else:
@@ -29,12 +32,13 @@ else:
         spec=['HKEYType', 'EnumKey', 'EnumValue', 'HKEY_LOCAL_MACHINE', 'OpenKey']
     )
     # mypy does not understand winreg.HKeyType where winreg is a Mock (fair enough!)
-    HKEYType: TypeAlias = Any
+    HKEYType: TypeAlias = Any  # type: ignore
 
 
 log = logging.getLogger(__name__)
 
 T = TypeVar('T')
+Tkey = TypeVar('Tkey')
 
 
 def ghostscript_version_key(s: str) -> tuple[int, int, int]:
@@ -99,6 +103,30 @@ def registry_path_tesseract(env=None) -> Iterator[Path]:
         log.warning(e)
 
 
+def _gs_version_in_path_key(path: Path) -> tuple[str, Version | None]:
+    """Key function for comparing Ghostscript and Tesseract paths.
+
+    Ghostscript installs on Windows:
+        %PROGRAMFILES%/gs/gs9.56.1/bin -> ('gs', Version('9.56.1'))
+        %PROGRAMFILES%/gs/9.24/bin -> ('gs', Version('9.24'))
+
+    Tesseract looks like:
+        %PROGRAMFILES%/Tesseract-OCR -> ('Tesseract-OCR', None)
+
+    Thus ensuring the resulting tuple will order the alternatives correctly,
+    e.g. gs10.0 > gs9.99.
+    """
+    match = re.search(r'gs[/\\]?([0-9.]+)[/\\]bin', str(path))
+    if match:
+        try:
+            version_str = match.group(1)
+            version = Version(version_str)
+            return 'gs', version
+        except InvalidVersion:
+            pass
+    return path.name, None
+
+
 def program_files_paths(env=None) -> Iterator[Path]:
     if not env:
         env = os.environ
@@ -116,7 +144,7 @@ def program_files_paths(env=None) -> Iterator[Path]:
     return iter(
         sorted(
             (p for p in path_walker()),
-            key=lambda p: (p.name, p.parent.name),
+            key=_gs_version_in_path_key,
             reverse=True,
         )
     )
@@ -141,13 +169,7 @@ SHIMS = [
 
 
 def fix_windows_args(program: str, args, env):
-    """Adjust our desired program and command line arguments for use on Windows"""
-
-    if sys.version_info < (3, 8):
-        # bpo-33617 - Windows needs manual Path -> str conversion
-        args = [os.fspath(arg) for arg in args]
-        program = os.fspath(program)
-
+    """Adjust our desired program and command line arguments for use on Windows."""
     # If we are running a .py on Windows, ensure we call it with this Python
     # (to support test suite shims)
     if program.lower().endswith('.py'):
@@ -164,11 +186,11 @@ def fix_windows_args(program: str, args, env):
     return args
 
 
-def unique_everseen(iterable: Iterable[T], key: Callable[[T], T]) -> Iterator[T]:
-    "List unique elements, preserving order."
+def unique_everseen(iterable: Iterable[T], key: Callable[[T], Tkey]) -> Iterator[T]:
+    """List unique elements, preserving order."""
     # unique_everseen('AAAABBBCCDAABBB') --> A B C D
     # unique_everseen('ABBCcAD', str.lower) --> A B C D
-    seen: set[T] = set()
+    seen: set[Tkey] = set()
     seen_add = seen.add
     for element in iterable:
         k = key(element)
@@ -177,11 +199,15 @@ def unique_everseen(iterable: Iterable[T], key: Callable[[T], T]) -> Iterator[T]
             yield element
 
 
+def _casefold_path(path: Path) -> str:
+    return str.casefold(str(path))
+
+
 def shim_env_path(env=None):
     if env is None:
         env = os.environ
 
     shim_paths = chain.from_iterable(shim(env) for shim in SHIMS)
     return os.pathsep.join(
-        str(p) for p in unique_everseen(shim_paths, key=lambda p: str.casefold(str(p)))
+        str(p) for p in unique_everseen(shim_paths, key=_casefold_path)
     )

tests/__init__.py

@@ -1,4 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0
 
+"""Tests."""
+
 from __future__ import annotations

tests/conftest.py

@@ -3,12 +3,10 @@
 
 from __future__ import annotations
 
-import os
 import platform
 import sys
 from pathlib import Path
-from subprocess import PIPE, CompletedProcess, run
-from typing import List
+from subprocess import CompletedProcess, run
 
 import pytest
 
@@ -44,7 +42,7 @@ TESTS_ROOT = Path(__file__).parent.resolve()
 PROJECT_ROOT = TESTS_ROOT
 
 
-@pytest.fixture
+@pytest.fixture(scope="session")
 def resources() -> Path:
     return Path(TESTS_ROOT) / 'resources'
 
@@ -71,13 +69,21 @@ def outtxt(tmp_path) -> Path:
 
 @pytest.fixture(scope="function")
 def no_outpdf(tmp_path) -> Path:
-    """This just documents the fact that a test is not expected to produce
+    """Document fact that a test is not expected to produce output.
+
+    This just documents the fact that a test is not expected to produce
     output. Unfortunately an assertion failure inside a test fixture produces
     an error rather than a test failure, so no testing is done. It's up to
-    the test to confirm that no output file was created."""
+    the test to confirm that no output file was created.
+    """
     return tmp_path / 'no_output.pdf'
 
 
+@pytest.fixture(scope="session")
+def multipage(resources):
+    return resources / 'multipage.pdf'
+
+
 def check_ocrmypdf(input_file: Path, output_file: Path, *args) -> Path:
     """Run ocrmypdf and confirm that a valid plausible PDF was created."""
     api_args = [str(input_file), str(output_file)] + [
@@ -105,7 +111,6 @@ def run_ocrmypdf_api(input_file: Path, output_file: Path, *args) -> ExitCode:
     The return code must always be checked or the test may declare a failure
     to be pass.
     """
-
     api_args = [str(input_file), str(output_file)] + [
         str(arg) for arg in args if arg is not None
     ]
@@ -123,7 +128,6 @@ def run_ocrmypdf(
     If an exception is thrown this fact will be returned as part of the result
     text and return code rather than exception objects.
     """
-
     p_args = (
         [sys.executable, '-m', 'ocrmypdf']
         + [str(arg) for arg in args if arg is not None]

tests/plugins/gs_feature_elision.py

@@ -9,13 +9,13 @@ from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins import ghostscript
 from ocrmypdf.subprocess import run_polling_stderr
 
-elision_warning = """GPL Ghostscript 9.20: Setting Overprint Mode to 1
+ELISION_WARNING = """GPL Ghostscript 9.50: Setting Overprint Mode to 1
 not permitted in PDF/A-2, overprint mode not set"""
 
 
 def run_append_stderr(*args, **kwargs):
     proc = run_polling_stderr(*args, **kwargs)
-    proc.stderr += '\n' + elision_warning + '\n'
+    proc.stderr += '\n' + ELISION_WARNING + '\n'
     return proc
 
 

tests/plugins/tesseract_badutf8.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MIT
 
-"""Tesseract bad utf8
+"""Tesseract bad utf8.
 
 In some cases, some versions of Tesseract can output binary gibberish or data
 that is not UTF-8 compatible, so we are forced to check that we can convert it

tests/plugins/tesseract_cache.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MIT
-"""Cache output of tesseract to speed up test suite
+"""Cache output of tesseract to speed up test suite.
 
 The cache is keyed by by the input test file The input arguments are slugged
 into a hideous filename that more or less represents them literally.  Joined
@@ -21,7 +21,7 @@ were produced.
 
 Certain operations are not cached and routed to Tesseract OCR directly.
 
-Assumes Tesseract 4.0.0-alpha or higher.
+Assumes Tesseract 4+.
 
 """
 
@@ -140,18 +140,19 @@ def cached_run(options, run_args, **run_kwargs):
             tessfile = args.outputbase + '.' + configfile
             shutil.copy(tessfile, str(cache_folder / configfile) + '.bin')
 
-    manifest = {}
-    manifest['tesseract_version'] = TesseractOcrEngine.version().replace('\n', ' ')
-    manifest['system'] = platform.system()
-    manifest['python'] = platform.python_version()
-    manifest['argv_slug'] = cache_folder.name
-    manifest['sourcefile'] = str(Path(source_file).relative_to(TESTS_ROOT))
-
     def clean_sys_argv():
         for arg in run_args[1:]:
             yield re.sub(r'.*/ocrmypdf[.]io[.][^/]+[/](.*)', r'$TMPDIR/\1', arg)
 
-    manifest['args'] = list(clean_sys_argv())
+    manifest = {
+        'tesseract_version': TesseractOcrEngine.version().replace('\n', ' '),
+        'system': platform.system(),
+        'python': platform.python_version(),
+        'argv_slug': cache_folder.name,
+        'sourcefile': str(Path(source_file).relative_to(TESTS_ROOT)),
+        'args': list(clean_sys_argv()),
+    }
+
     with (Path(CACHE_ROOT) / 'manifest.jsonl').open('a') as f:
         json.dump(manifest, f)
         f.write('\n')

tests/plugins/tesseract_debug_rotate.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MIT
-"""Tesseract no-op/fixed rotate plugin
+"""Tesseract no-op/fixed rotate plugin.
 
 To quickly run tests where getting OCR output is not necessary and we want to test
 the rotation pipeline.
@@ -27,14 +27,16 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
+  <meta name='ocr-capabilities'
+    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
  </head>
  <body>
   <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
    <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
     <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
-     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}">
+       <span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
      </span>
     </p>
    </div>
@@ -46,7 +48,7 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
 class FixedRotateNoopOcrEngine(OcrEngine):
     @staticmethod
     def version():
-        return '4.0.0'
+        return '4.1.1'
 
     @staticmethod
     def creator_tag(options):

tests/plugins/tesseract_noop.py

@@ -1,6 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MIT
-"""Tesseract no-op plugin
+"""Tesseract no-op plugin.
 
 To quickly run tests where getting OCR output is not necessary.
 
@@ -25,14 +25,16 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
  <head>
   <title></title>
   <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
-  <meta name='ocr-system' content='tesseract 4.0.0' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+  <meta name='ocr-system' content='tesseract 4.1.1' />
+  <meta name='ocr-capabilities'
+    content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
  </head>
  <body>
   <div class='ocr_page' id='page_1' title='image "x.tif"; bbox 0 0 {0} {1}; ppageno 0'>
    <div class='ocr_carea' id='block_1_1' title="bbox 0 1 {0} {1}">
     <p class='ocr_par' dir='ltr' id='par_1' title="bbox 0 1 {0} {1}">
-     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}"><span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
+     <span class='ocr_line' id='line_1' title="bbox 0 1 {0} {1}">
+       <span class='ocrx_word' id='word_1' title="bbox 0 1 {0} {1}"> </span>
      </span>
     </p>
    </div>
@@ -44,7 +46,7 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
 class NoopOcrEngine(OcrEngine):
     @staticmethod
     def version():
-        return '4.0.0'
+        return '4.1.1'
 
     @staticmethod
     def creator_tag(options):

tests/resources/README.rst

@@ -1,168 +1,105 @@
+.. SPDX-FileCopyrightText: 2022 James R. Barlow
+.. SPDX-License-Identifier: CC-BY-SA-4.0
+
 These test files are used in OCRmyPDF's test suite. They do not necessarily produce OCR results
-at all and are not meant as examples of OCR output. Some are even invalid PDFs that might
+at all and are not necessarily meant as examples of OCR output. Some are even invalid PDFs that might
 crash certain PDF viewers.
 
-
-Files derived from free sources
-===============================
-
-These test resources come from free sources, under either public domain or Creative Commons licenses.
-In some cases they were converted from one image format to another without other changes.
+Some of these images were obtained from the public domain. Others are copyrighted and may have
+licenses associated. Refer to ``.reuse/dep5`` file in OCRmyPDF's Git repository for information on
+the copyright holder(s) and license(s) applicable to these resources.
 
 .. list-table::
-    :widths: 20 50 30
+    :widths: 15 35 50
     :header-rows: 1
 
     *   - File
         - Source
-        - License
+        - Purpose
     *   - c02-22.pdf
         - `Project Gutenberg`_, Adventures of Huckleberry Finn, page 22
-        - Public Domain
+        - difficult OCR image (obscure fonts and illustrations)
     *   - congress.jpg
         - `US Congressional Records`_
-        - Public Domain
+        - difficult OCR image (color background)
     *   - graph.pdf
-        - `Wikimedia: Pandas text analysis.png`_
-        - Public Domain
+        - `Wikimedia:Simple_line_graph_of_ACE_2012_results_by_candidate_sj01.png`_
+        - image with slanted text
     *   - lichtenstein.pdf
         - `Wikimedia: JPEG2000 Lichtenstein`_
-        - Creative Commons BY-SA 3.0
+        - JPEG2000 image
     *   - linn.png, linn.pdf, linn.txt
         - `Wikimedia: LinnSequencer`_
-        - Creative Commons BY-SA 3.0
+        - image with two columns
     *   - typewriter.png, 2400dpi.pdf
         - `Wikimedia: Triumph typewrtier text Linzensoep`_
-        - Creative Commons BY-SA 2.5
+        - simple text
     *   - baiona.png
         - `Wikimedia: Baionako udalerri mugakideak`_
-        - Creative Commons BY-SA 4.0
-    *   - enron1.pdf
-        - EnronData.org
-        - Creative Commons BY 3.0
-
-
-Files generated for this project
-================================
-
-The following test resources were crafted specifically for this project, and are
-licensed under the specified license.
-
-.. list-table::
-    :widths: 20 40 15 15 10
-    :header-rows: 1
-
-    *   - File
-        - Purpose
-        - Contributor
-        - Copyright Holder
-        - License
+        - multilingual text and images
     *   - aspect.pdf
+        - synthetic
         - test image with 200 x 100 DPI resolution
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - blank.pdf
+        - synthetic
         - blank PDF generated by Adobe Illustrator CC 17, containing a lot of application-specific metadata/bloat
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - cmyk.pdf
+        - synthetic
         - a CMYK image created in Photoshop
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - crom.png
+        - synthetic
         - test for non-dictionary words
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - enormous.pdf
+        - synthetic
         - very large PDF page
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - epson.pdf
+        - synthetic
         - a linearized PDF containing some unusual indirect objects, created by an Epson printer; printout of a Wikipedia article (CC-BY-SA)
-        - @lowesjam
-        - Wikipedia authors
-        - CC-BY-SA 3.0
     *   - formxobject.pdf
+        - synthetic
         - hand-crafted PDF containing an image inside a Form XObject
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - francais.pdf
+        - synthetic
         - a page containing French accents (diacritics)
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - hugemono.pdf
+        - synthetic
         - large monochrome 35000x35000 image in JBIG2 encoding
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - invalid.pdf
+        - synthetic
         - a PDF file header followed by EOF marker
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - kcs.pdf
+        - synthetic
         - PDF file generated by Kodak Capture Desktop Software 1.2; has invalid table of contents
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - livecycle.pdf
+        - synthetic
         - a minimal PDF that claims to use dynamic XFA forms
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - masks.pdf
+        - synthetic
         - file containing explicit masks and a stencil mask drawn without a proper transformation matrix; printout of a German Wikipedia article (CC-BY-SA)
-        - @supergrobi
-        - Wikipedia authors
-        - CC-BY-SA 3.0
     *   - missing_docinfo.pdf
+        - synthetic
         - PDF file with no /DocumentInfo section
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - overlay.pdf
+        - synthetic
         - PDF file generated by PDFPen pro that triggered content stream parse errors
-        - @maxandersen
-        - @maxandersen
-        - CC-BY-SA 4.0
     *   - negzero.pdf
+        - synthetic
         - copy of formxobject.pdf with token that qpdf doesn't like
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - no_contents.pdf
+        - synthetic
         - synthetic PDF with a blank page that has no /Contents entry
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - truetype_font_nomapping.pdf
+        - synthetic
         - example of a PDF with an embedded subsetted TrueType font with no Unicode mapping
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - trivial.pdf
+        - synthetic
         - smallest possible valid PDF-1.3 with all required fields
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - type3_font_nomapping.pdf
+        - synthetic
         - example of a PDF with an embedded subsetted TrueType font with no Unicode mapping
-        - @jbarlow83
-        - @jbarlow83
-        - CC-BY-SA 4.0
     *   - vector.pdf
+        - synthetic
         - a PDF with vector art and text rendered as curves with no fonts
-        - @Catscratch
-        - @Catscratch
-        - CC-BY-SA 4.0
-
 
 Assemblies
 ==========
@@ -174,14 +111,12 @@ These test resources are assemblies or derivatives from other previously mention
 - baiona_alpha.png (from baiona.png, RGB+A version)
 - cardinal.pdf (four cardinal directions, baked-in rotated copies of linn.png)
 - ccitt.pdf (linn.png, converted to CCITT encoding)
-- encrypted_algo4.pdf (congress.jpg, encrypted with algorithm 4 - not supported by PyPDF2)
 - graph_ocred.pdf (from graph.pdf)
-- jbig2.pdf (congress.jpg, converted to JBIG2 encoding)
+- jbig2.pdf (from linn.png)
 - multipage.pdf (from several other files)
-- palette.pdf (congress.jpg, converted to a 256-color palette)
+- palette.pdf (from baiona_colormapped.png)
 - poster.pdf (from linn.png)
 - rotated_skew.pdf (a /Rotate'd and skewed document from linn.png)
-- skew-encrypted.pdf (skew.pdf with encryption - access supported by PyPDF2, password is "password")
 - skew.pdf (from linn.png, skew simulated by adjusting the transformation matrix)
 - toc.pdf (from formxobject.pdf, trivial.pdf)
 
@@ -192,7 +127,7 @@ These test resources are assemblies or derivatives from other previously mention
 
 .. _`US Congressional Records`: http://www.baxleystamps.com/litho/meiji/courts_1871.jpg
 
-.. _`Wikimedia: Pandas text analysis.png`: https://en.wikipedia.org/wiki/File:Pandas_text_analysis.png
+.. _`Wikimedia: Simple_line_graph_of_ACE_2012_results_by_candidate_sj01.png`: https://en.wikipedia.org/wiki/File:Simple_line_graph_of_ACE_2012_results_by_candidate_sj01.png
 
 .. _`Wikimedia: JPEG2000 Lichtenstein`: https://en.wikipedia.org/wiki/JPEG_2000#/media/File:Jpeg2000_2-level_wavelet_transform-lichtenstein.png
 

tests/test_check_pdf.py

@@ -3,8 +3,6 @@
 
 from __future__ import annotations
 
-import pytest
-
 from ocrmypdf.helpers import check_pdf
 
 

tests/test_completion.py

@@ -4,7 +4,7 @@
 from __future__ import annotations
 
 import os
-from subprocess import PIPE, run
+from subprocess import run
 
 import pytest
 

tests/test_concurrency.py

@@ -14,9 +14,9 @@ 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):
+def test_simulate_oom_killer(multipage, no_outpdf):
     exitcode = run_ocrmypdf_api(
-        resources / 'multipage.pdf',
+        multipage,
         no_outpdf,
         '--force-ocr',
         '--plugin',

tests/test_graft.py

@@ -6,7 +6,6 @@ from __future__ import annotations
 from unittest.mock import patch
 
 import pikepdf
-import pytest
 
 import ocrmypdf
 

tests/test_helpers.py

@@ -6,9 +6,11 @@ from __future__ import annotations
 import logging
 import multiprocessing
 import os
+from pathlib import Path
 from unittest.mock import MagicMock
 
 import pytest
+from packaging.version import Version
 
 from ocrmypdf import helpers
 
@@ -52,15 +54,6 @@ def test_no_cpu_count(monkeypatch):
     assert invoked, "Patched function called during test"
 
 
-def test_deprecated():
-    @helpers.deprecated
-    def old_function():
-        return 42
-
-    with pytest.deprecated_call():
-        assert old_function() == 42
-
-
 skipif_docker = pytest.mark.skipif(running_in_docker(), reason="fails on Docker")
 
 
@@ -100,6 +93,17 @@ class TestFileIsWritable:
         assert not helpers.is_file_writable(pathmock)
 
 
+@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+def test_gs_install_locations():
+    # pylint: disable=import-outside-toplevel
+    from ocrmypdf.subprocess._windows import _gs_version_in_path_key
+
+    assert _gs_version_in_path_key(Path("C:\\Program Files\\gs\\gs9.52\\bin")) == (
+        'gs',
+        Version('9.52'),
+    )
+
+
 @pytest.mark.skipif(os.name != 'nt', reason="Windows test")
 def test_shim_paths(tmp_path):
     # pylint: disable=import-outside-toplevel
@@ -109,7 +113,7 @@ def test_shim_paths(tmp_path):
     progfiles.mkdir()
     (progfiles / 'tesseract-ocr').mkdir()
     (progfiles / 'gs' / '9.51' / 'bin').mkdir(parents=True)
-    (progfiles / 'gs' / '9.52' / 'bin').mkdir(parents=True)
+    (progfiles / 'gs' / 'gs9.52.3' / 'bin').mkdir(parents=True)
     syspath = tmp_path / 'bin'
     env = {'PROGRAMFILES': str(progfiles), 'PATH': str(syspath)}
 
@@ -117,7 +121,7 @@ def test_shim_paths(tmp_path):
     results = result_str.split(os.pathsep)
     assert results[0] == str(syspath), results
     assert results[-3].endswith('tesseract-ocr'), results
-    assert results[-2].endswith(os.path.join('gs', '9.52', 'bin')), results
+    assert results[-2].endswith(os.path.join('gs9.52.3', 'bin')), results
     assert results[-1].endswith(os.path.join('gs', '9.51', 'bin')), results
 
 

tests/test_imageops.py

@@ -0,0 +1,53 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import hypothesis.strategies as st
+from hypothesis import given
+from PIL import Image
+
+from ocrmypdf.imageops import bytes_per_pixel, calculate_downsample, downsample_image
+
+
+def test_bytes_per_pixel():
+    assert bytes_per_pixel('RGB') == 4
+    assert bytes_per_pixel('RGBA') == 4
+    assert bytes_per_pixel('LA') == 2
+    assert bytes_per_pixel('L') == 1
+
+
+def test_calculate_downsample():
+    im = Image.new('RGB', (100, 100))
+    assert calculate_downsample(im, max_size=(50, 50)) == (50, 50)
+    assert calculate_downsample(im, max_pixels=2500) == (50, 50)
+    assert calculate_downsample(im, max_bytes=10000) == (50, 50)
+    assert calculate_downsample(im, max_bytes=100000) == (100, 100)
+
+
+@given(
+    st.one_of(st.just("RGB"), st.just('L')),
+    st.integers(min_value=1, max_value=100000),
+    st.integers(min_value=1, max_value=100000),
+    st.integers(min_value=64, max_value=100000),
+    st.integers(min_value=64, max_value=100000),
+    st.integers(min_value=64 * 64, max_value=1000000),
+)
+def test_calculate_downsample_hypothesis(mode, im_w, im_h, max_x, max_y, max_bytes):
+    result = calculate_downsample(
+        (im_w, im_h),
+        bytes_per_pixel(mode),
+        max_size=(max_x, max_y),
+        max_bytes=max_bytes,
+    )
+    assert result[0] <= max_x
+    assert result[1] <= max_y
+    assert result[0] * result[1] * bytes_per_pixel(mode) <= max_bytes
+
+
+def test_downsample_image():
+    im = Image.new('RGB', (100, 100))
+    im.info['dpi'] = (300, 300)
+    ds = downsample_image(im, (50, 50))
+    assert ds.size == (50, 50)
+    assert ds.info['dpi'] == (150, 150)

tests/test_logging.py

@@ -5,8 +5,6 @@ from __future__ import annotations
 
 import logging
 
-import pytest
-
 from ocrmypdf._sync import configure_debug_logging
 
 

tests/test_main.py

@@ -7,16 +7,15 @@ import os
 import shutil
 from math import isclose
 from pathlib import Path
-from subprocess import PIPE, run
+from subprocess import run
 from unittest.mock import patch
 
 import pikepdf
-import PIL
 import pytest
 from PIL import Image
 
 import ocrmypdf
-from ocrmypdf._exec import ghostscript, tesseract
+from ocrmypdf._exec import tesseract
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 from ocrmypdf.pdfa import file_claims_pdfa
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
@@ -153,9 +152,9 @@ def test_skip_big(resources, outpdf):
 
 @pytest.mark.parametrize('renderer', RENDERERS)
 @pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
-def test_maximum_options(renderer, output_type, resources, outpdf):
+def test_maximum_options(renderer, output_type, multipage, outpdf):
     check_ocrmypdf(
-        resources / 'multipage.pdf',
+        multipage,
         outpdf,
         '-d',
         '-ci' if have_unpaper() else None,
@@ -179,7 +178,8 @@ def test_maximum_options(renderer, output_type, resources, outpdf):
 
 
 @pytest.mark.skipif(
-    tesseract.version() >= '5', reason="tess 5 tries harder to find its files"
+    tesseract.TesseractVersion(tesseract.version()) >= tesseract.TesseractVersion('5'),
+    reason="tess 5 tries harder to find its files",
 )
 def test_tesseract_missing_tessdata(monkeypatch, resources, no_outpdf, tmpdir):
     monkeypatch.setenv("TESSDATA_PREFIX", os.fspath(tmpdir))
@@ -292,12 +292,6 @@ def test_input_file_not_a_pdf(caplog, no_outpdf):
         assert input_file in caplog.text
 
 
-def test_encrypted(resources, caplog, no_outpdf):
-    result = run_ocrmypdf_api(resources / 'skew-encrypted.pdf', no_outpdf)
-    assert result == ExitCode.encrypted_pdf
-    assert 'encryption must be removed' in caplog.text
-
-
 @pytest.mark.parametrize('renderer', RENDERERS)
 def test_pagesegmode(renderer, resources, outpdf):
     check_ocrmypdf(
@@ -398,14 +392,27 @@ def test_tesseract_image_too_big(renderer, resources, outpdf):
     )
 
 
-def test_algo4(resources, outpdf):
-    p = run_ocrmypdf(
-        resources / 'encrypted_algo4.pdf',
+@pytest.mark.parametrize('encryption_level', [2, 3, 4, 6])
+def test_encrypted(resources, outpdf, encryption_level, caplog):
+    encryption = pikepdf.models.encryption.Encryption(
+        owner='ocrmypdf',
+        user='ocrmypdf',
+        R=encryption_level,
+        aes=(encryption_level >= 4),
+        metadata=(encryption_level == 6),
+    )
+
+    with pikepdf.open(resources / 'jbig2.pdf') as pdf:
+        pdf.save(outpdf, encryption=encryption)
+
+    exitcode = run_ocrmypdf_api(
+        outpdf,
         outpdf,
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
-    assert p.returncode == ExitCode.encrypted_pdf
+    assert exitcode == ExitCode.encrypted_pdf
+    assert 'encryption must be removed' in caplog.text
 
 
 def test_jbig2_passthrough(resources, outpdf):
@@ -439,7 +446,7 @@ def test_linearized_pdf_and_indirect_object(resources, outpdf):
 
 
 def test_very_high_dpi(resources, outpdf):
-    "Checks for a Decimal quantize error with high DPI, etc"
+    """Checks for a Decimal quantize error with high DPI, etc."""
     check_ocrmypdf(
         resources / '2400dpi.pdf',
         outpdf,
@@ -539,7 +546,6 @@ def test_tesseract_config_invalid(renderer, resources, invalid_tess_config, outp
     assert p.returncode == ExitCode.invalid_config
 
 
-@pytest.mark.skipif(not tesseract.has_user_words(), reason='not functional until 4.1.0')
 def test_user_words_ocr(resources, outdir):
     # Does not actually test if --user-words causes output to differ
     word_list = outdir / 'wordlist.txt'
@@ -716,11 +722,9 @@ def test_compression_changed(ocrmypdf_exec, resources, image, compression, outpd
     if compression == "jpeg":
         assert pdfimage.enc == Encoding.jpeg
     else:
-        if ghostscript.jpeg_passthrough_available():
-            # Ghostscript 9.23 adds JPEG passthrough, which allows a JPEG to be
-            # copied without transcoding - so report
-            if image.endswith('jpg'):
-                assert pdfimage.enc == Encoding.jpeg
+        if image.endswith('jpg'):
+            # Ghostscript JPEG passthrough - no issue
+            assert pdfimage.enc == Encoding.jpeg
         else:
             assert pdfimage.enc not in (Encoding.jpeg, Encoding.jpeg2000)
 
@@ -774,9 +778,6 @@ def test_sidecar_nonempty(resources, outpdf):
 
 @pytest.mark.parametrize('pdfa_level', ['1', '2', '3'])
 def test_pdfa_n(pdfa_level, resources, outpdf):
-    if pdfa_level == '3' and ghostscript.version() < '9.19':
-        pytest.xfail(reason='Ghostscript >= 9.19 required')
-
     check_ocrmypdf(
         resources / 'ccitt.pdf',
         outpdf,

tests/test_metadata.py

@@ -22,19 +22,9 @@ from ocrmypdf.pdfinfo import PdfInfo
 
 from .conftest import check_ocrmypdf, run_ocrmypdf
 
-try:
-    import fitz
-except ImportError:
-    fitz = None
-
-
-pytestmark = pytest.mark.filterwarnings('ignore:.*XMLParser.*:DeprecationWarning')
-
 
 @pytest.mark.parametrize("output_type", ['pdfa', 'pdf'])
 def test_preserve_docinfo(output_type, resources, outpdf):
-    pdf_before = pikepdf.open(resources / 'graph.pdf')
-
     output = check_ocrmypdf(
         resources / 'graph.pdf',
         outpdf,
@@ -43,14 +33,13 @@ def test_preserve_docinfo(output_type, resources, outpdf):
         '--plugin',
         'tests/plugins/tesseract_noop.py',
     )
-
-    pdf_after = pikepdf.open(output)
-
-    for key in ('/Title', '/Author'):
-        assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
-
-    pdfa_info = file_claims_pdfa(str(output))
-    assert pdfa_info['output'] == output_type
+    with pikepdf.open(resources / 'graph.pdf') as pdf_before, pikepdf.open(
+        output
+    ) as pdf_after:
+        for key in ('/Title', '/Author'):
+            assert pdf_before.docinfo[key] == pdf_after.docinfo[key]
+        pdfa_info = file_claims_pdfa(str(output))
+        assert pdfa_info['output'] == output_type
 
 
 @pytest.mark.parametrize("output_type", ['pdfa', 'pdf'])
@@ -74,23 +63,20 @@ def test_override_metadata(output_type, resources, outpdf):
 
     assert p.returncode == ExitCode.ok, p.stderr
 
-    before = pikepdf.open(input_file)
-    after = pikepdf.open(outpdf)
+    with pikepdf.open(input_file) as before, pikepdf.open(outpdf) as after:
+        assert after.docinfo.Title == german, after.docinfo
+        assert after.docinfo.Author == chinese, after.docinfo
+        assert after.docinfo.get('/Keywords', '') == ''
 
-    assert after.docinfo.Title == german, after.docinfo
-    assert after.docinfo.Author == chinese, after.docinfo
-    assert after.docinfo.get('/Keywords', '') == ''
+        before_date = decode_pdf_date(str(before.docinfo.CreationDate))
+        after_date = decode_pdf_date(str(after.docinfo.CreationDate))
+        assert before_date == after_date
 
-    before_date = decode_pdf_date(str(before.docinfo.CreationDate))
-    after_date = decode_pdf_date(str(after.docinfo.CreationDate))
-    assert before_date == after_date
-
-    pdfa_info = file_claims_pdfa(outpdf)
-    assert pdfa_info['output'] == output_type
+        pdfa_info = file_claims_pdfa(outpdf)
+        assert pdfa_info['output'] == output_type
 
 
 def test_high_unicode(resources, no_outpdf):
-
     # Ghostscript doesn't support high Unicode, so neither do we, to be
     # safe
     input_file = resources / 'c02-22.pdf'
@@ -110,10 +96,10 @@ def test_high_unicode(resources, no_outpdf):
     assert p.returncode == ExitCode.bad_args, p.stderr
 
 
-@pytest.mark.skipif(not fitz, reason="test uses fitz")
 @pytest.mark.parametrize('ocr_option', ['--skip-text', '--force-ocr'])
 @pytest.mark.parametrize('output_type', ['pdf', 'pdfa'])
 def test_bookmarks_preserved(output_type, ocr_option, resources, outpdf):
+    fitz = pytest.importorskip('fitz')
     input_file = resources / 'toc.pdf'
     before_toc = fitz.Document(str(input_file)).get_toc()
 
@@ -151,30 +137,36 @@ def test_creation_date_preserved(output_type, resources, infile, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    pdf_before = pikepdf.open(input_file)
-    pdf_after = pikepdf.open(outpdf)
+    with pikepdf.open(input_file) as pdf_before, pikepdf.open(outpdf) as pdf_after:
+        before = pdf_before.trailer.get('/Info', {})
+        after = pdf_after.trailer.get('/Info', {})
 
-    before = pdf_before.trailer.get('/Info', {})
-    after = pdf_after.trailer.get('/Info', {})
+        if not before:
+            assert after.get('/CreationDate', '') != ''
+        else:
+            # We expect that the creation date stayed the same
+            date_before = decode_pdf_date(str(before['/CreationDate']))
+            date_after = decode_pdf_date(str(after['/CreationDate']))
+            assert seconds_between_dates(date_before, date_after) < 1000
 
-    if not before:
-        assert after.get('/CreationDate', '') != ''
-    else:
-        # We expect that the creation date stayed the same
-        date_before = decode_pdf_date(str(before['/CreationDate']))
-        date_after = decode_pdf_date(str(after['/CreationDate']))
-        assert seconds_between_dates(date_before, date_after) < 1000
-
-    # We expect that the modified date is quite recent
-    date_after = decode_pdf_date(str(after['/ModDate']))
-    assert seconds_between_dates(date_after, datetime.datetime.now(timezone.utc)) < 1000
+        # We expect that the modified date is quite recent
+        date_after = decode_pdf_date(str(after['/ModDate']))
+        assert (
+            seconds_between_dates(date_after, datetime.datetime.now(timezone.utc))
+            < 1000
+        )
 
 
 @pytest.fixture
 def libxmp_file_to_dict():
     try:
         with warnings.catch_warnings():
-            warnings.simplefilter("ignore", DeprecationWarning)
+            # libxmp imports distutils.Version, which is deprecated
+            warnings.filterwarnings(
+                "ignore",
+                category=DeprecationWarning,
+                message=r".*distutils Version classes are deprecated.*",
+            )
             from libxmp.utils import (
                 file_to_dict,  # pylint: disable=import-outside-toplevel
             )
@@ -229,17 +221,6 @@ def test_xml_metadata_preserved(
         'pdf:keywords',
     ]
     acquired_properties = ['dc:format']
-    might_change_properties = [
-        'dc:date',
-        'pdf:pdfversion',
-        'pdf:Producer',
-        'xmp:CreateDate',
-        'xmp:ModifyDate',
-        'xmp:MetadataDate',
-        'xmp:CreatorTool',
-        'xmpMM:DocumentId',
-        'xmpMM:DnstanceId',
-    ]
 
     # Cleanup messy data structure
     # Top level is key-value mapping of namespaces to keys under namespace,
@@ -290,10 +271,9 @@ def test_kodak_toc(resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    p = pikepdf.open(outpdf)
-
-    if pikepdf.Name.First in p.Root.Outlines:
-        assert isinstance(p.Root.Outlines.First, pikepdf.Dictionary)
+    with pikepdf.open(outpdf) as p:
+        if pikepdf.Name.First in p.Root.Outlines:
+            assert isinstance(p.Root.Outlines.First, pikepdf.Dictionary)
 
 
 def test_metadata_fixup_warning(resources, outdir, caplog):
@@ -311,10 +291,10 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
         assert record.levelname != 'WARNING', "Unexpected warning"
 
     # Now add some metadata that will not be copyable
-    graph = pikepdf.open(outdir / 'graph.pdf')
-    with graph.open_metadata() as meta:
-        meta['prism2:publicationName'] = 'OCRmyPDF Test'
-    graph.save(outdir / 'graph_mod.pdf')
+    with pikepdf.open(outdir / 'graph.pdf') as graph:
+        with graph.open_metadata() as meta:
+            meta['prism2:publicationName'] = 'OCRmyPDF Test'
+        graph.save(outdir / 'graph_mod.pdf')
 
     context = PdfContext(
         options, outdir, outdir / 'graph_mod.pdf', None, get_plugin_manager([])

tests/test_optimize.py

@@ -27,10 +27,18 @@ needs_jbig2enc = pytest.mark.skipif(
 )
 
 
+# pylint:disable=redefined-outer-name
+
+
+@pytest.fixture(scope="session")
+def palette(resources):
+    return resources / 'palette.pdf'
+
+
 @needs_pngquant
-@pytest.mark.parametrize('pdf', ['multipage.pdf', 'palette.pdf'])
-def test_basic(resources, pdf, outpdf):
-    infile = resources / pdf
+@pytest.mark.parametrize('pdf', ['multipage', 'palette'])
+def test_basic(multipage, palette, pdf, outpdf):
+    infile = multipage if pdf == 'multipage' else palette
     opt.main(infile, outpdf, level=3)
 
     assert 0.98 * Path(outpdf).stat().st_size <= Path(infile).stat().st_size
@@ -92,14 +100,14 @@ def test_jbig2_lossy(lossy, resources, outpdf):
 
     check_ocrmypdf(*args)
 
-    pdf = pikepdf.open(outpdf)
-    pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
-    assert pim.filters[0] == '/JBIG2Decode'
+    with pikepdf.open(outpdf) as pdf:
+        pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
+        assert pim.filters[0] == '/JBIG2Decode'
 
-    if lossy:
-        assert '/JBIG2Globals' in pim.decode_parms[0]
-    else:
-        assert len(pim.decode_parms) == 0
+        if lossy:
+            assert '/JBIG2Globals' in pim.decode_parms[0]
+        else:
+            assert len(pim.decode_parms) == 0
 
 
 @needs_pngquant
@@ -126,9 +134,9 @@ def test_flate_to_jbig2(resources, outdir):
         'tests/plugins/tesseract_noop.py',
     )
 
-    pdf = pikepdf.open(outdir / 'out.pdf')
-    pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
-    assert pim.filters[0] == '/JBIG2Decode'
+    with pikepdf.open(outdir / 'out.pdf') as pdf:
+        pim = pikepdf.PdfImage(next(iter(pdf.pages[0].images.values())))
+        assert pim.filters[0] == '/JBIG2Decode'
 
 
 @needs_pngquant

tests/test_page_numbers.py

@@ -48,10 +48,9 @@ def test_nonmonotonic_warning(caplog):
     assert 'out of order' in caplog.text
 
 
-def test_limited_pages(resources, outpdf):
-    multi = resources / 'multipage.pdf'
+def test_limited_pages(multipage, outpdf):
     ocrmypdf.ocr(
-        multi,
+        multipage,
         outpdf,
         pages='5-6',
         optimize=0,

tests/test_pipeline.py

@@ -42,7 +42,6 @@ VECTOR_RESOLUTION = Resolution(_pipeline.VECTOR_PAGE_DPI, _pipeline.VECTOR_PAGE_
     ],
 )
 def test_dpi_needed(image, text, vector, result, rgb_image, outdir):
-
     c = Canvas(str(outdir / 'dpi.pdf'), pagesize=(5 * inch, 5 * inch))
     if image:
         c.drawImage(rgb_image, 1 * inch, 1 * inch, width=1 * inch, height=1 * inch)