gh-action-pypi-publish doesn't have a main - use release/v1

Fix some references to master not renamed to main
Merge branch 'main' of github.com:ocrmypdf/OCRmyPDF
2023-06-20 03:11:46 -07:00 · 2023-06-20 01:37:26 -07:00 · 2023-06-20 01:12:53 -07:00 · 2023-06-20 01:12:45 -07:00 · 2023-06-20 01:08:09 -07:00 · 2023-06-20 01:07:23 -07:00
101 changed files with 1953 additions and 735 deletions
@@ -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 \
@@ -57,6 +59,7 @@ RUN add-apt-repository -y ppa:alex-p/tesseract-ocr-devel

 RUN apt-get update && apt-get install -y --no-install-recommends \
  ghostscript \
+  fonts-droid-fallback \
  jbig2dec \
  img2pdf \
  libsm6 libxext6 libxrender-dev \
@@ -0,0 +1,51 @@
+name: General issues
+description: Installation, packages, dependencies, "nothing works", test suite failures...
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report!
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: What were you trying to do?
+      description: Also tell us, what did you expect to happen?
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: Where are you installing from?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Wndows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+    validations:
+      required: true
+  - type: dropdown
+    id: operating-system
+    attributes:
+      label: What operating system are you working on?
+      multiple: true
+      options:
+        - Linux
+        - Windows
+        - macOS
+        - BSD
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: plain text
@@ -0,0 +1,62 @@
+name: Problem with specific file
+description: Something went wrong while trying to OCR a specific file
+title: "[Bug]: "
+labels: ["bug", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to describe this issue with a particular file.
+  - type: textarea
+    id: what-happened
+    attributes:
+      label: Describe the bug
+      description: A clear and concise description of what the bug is.
+      placeholder: Tell us what you see!
+    validations:
+      required: true
+  - type: textarea
+    id: reproduce
+    attributes:
+      label: Steps to reproduce
+      description: Please include steps to reproduce
+      value: |
+        1. Run ocrmypdf -v1 ...arguments... input.pdf output.pdf
+        2. Open output.pdf
+        3. ...
+      render: plain text
+  - type: textarea
+    id: files
+    attributes:
+      label: Files
+      description: Please attach the input and output files, or any screenshots that may be helpful.
+      placeholder: Drag and drop files here
+  - type: dropdown
+    id: packaging-system
+    attributes:
+      label: How did you download and install the software?
+      multiple: true
+      options:
+        - PyPI (pip, poetry, pipx, etc.)
+        - Linux package manager (apt, dnf, etc.)
+        - Windows package manager (chocolatey, etc.)
+        - Homebrew
+        - Docker container
+        - Ubuntu snap
+        - Conda
+        - source build
+  - type: input
+    id: version
+    attributes:
+      label: OCRmyPDF version
+      description: Paste "ocrmypdf --version" here
+      placeholder: ocrmypdf --version
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      placeholder: Run OCRmyPDF with verbosity `-v1` to get more detailed logging output.
+      render: plain text
@@ -0,0 +1,12 @@
+name: Feature request
+description: Suggest an idea for this project
+title: "[Feature]: "
+labels: ["enhancement", "triage"]
+assignees:
+  - jbarlow83
+body:
+  - type: textarea
+    id: feature
+    attributes:
+      label: Describe the proposed feature
+      description: A clear and concise description of what the desired is.
@@ -1,23 +0,0 @@
---
-name: Feature request
-about: Suggest an idea for this project
-title: ''
-labels: ''
-assignees: ''
-
---
-
-**Is your feature request related to a problem? Please describe.**
-A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
-
-**Describe the solution you'd like**
-A clear and concise description of what you want to happen.
-
-**Describe alternatives you've considered**
-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. 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.
@@ -1,33 +0,0 @@
---
-name: General issues
-about: Installation, packages, dependencies, "nothing works", test suite failures...
-title: "[BUG]"
-labels: ''
-assignees: ''
-
---
-
-**Describe the bug**
-What's the problem?
-
-**To Reproduce**
-Steps to reproduce the behavior.
-
-**Expected behavior**
-What did you expected to happen?
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**System (please complete the following information):**
- - OS:
- - Python version:
- - OCRmyPDF version:
- - Platform: x64 or ARM
-
-**Installation**
-How did you install OCRmyPDF? Did you install it from your operating system's
-package manager, or using pip?
-
-**Additional context**
-Add any other context about the problem here.
@@ -1,40 +0,0 @@
---
-name: Problem with specific file
-about: Something went wrong while trying to OCR a specific file
-title: "[BUG]"
-labels: ''
-assignees: ''
-
---
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**To Reproduce**
-What command line or API call were you trying to run?
-
-```bash
-ocrmypdf  ...arguments... input.pdf output.pdf
-```
-
-Run with verbosity or higher `-v1` to see more detailed logging. This information may be helpful.
-
-**Example file**
-If your issue is a problem that affects only certain files, and we will require an input file (PDF or image) that demonstrates your issue.
-
-Please provide an input file with no personal or confidential information. At your option you may [GPG-encrypt the file](https://github.com/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.
-
-*(Issues without example files usually cannot be resolved. It's like reporting an issue against a web browser without providing a URL.)*
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**System**
- - OS: [e.g. Linux, Windows, macOS]
- - OCRmyPDF Version: ``ocrmypdf --version``
- - How did you install ocrmypdf? Did you use a system package manager, `pip`, or a Docker image?
@@ -5,7 +5,7 @@ name: Test and deploy
 on:
  push:
    branches:
-      - master
+      - main
      - ci
      - release/*
      - feature/*
@@ -249,7 +249,7 @@ jobs:
          name: artifact
          path: dist

-      - uses: pypa/gh-action-pypi-publish@master
+      - uses: pypa/gh-action-pypi-publish@release/v1
        with:
          user: __token__
          password: ${{ secrets.TOKEN_PYPI }}
@@ -264,9 +264,9 @@ jobs:
      - name: Set image tag to release or branch
        run: echo "DOCKER_IMAGE_TAG=${GITHUB_REF##*/}" >> $GITHUB_ENV

-      - name: If master, set to latest
+      - name: If main, set to latest
        run: echo 'DOCKER_IMAGE_TAG=latest' >> $GITHUB_ENV
-        if: env.DOCKER_IMAGE_TAG == 'master'
+        if: env.DOCKER_IMAGE_TAG == 'main'

      - name: Set Docker Hub repository to username
        run: echo "DOCKER_REPOSITORY=jbarlow83" >> $GITHUB_ENV
@@ -6,6 +6,7 @@
 .venv*/
 .tox/
 .vscode/
+.hypothesis/
 .ipynb_checkpoints/
 .mypy_cache/
 .pytest_cache/
@@ -3,34 +3,26 @@

 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: ["--py38-plus"]
  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.971
+    rev: v1.2.0
    hooks:
      - id: mypy
        additional_dependencies:
@@ -41,6 +41,7 @@ Files:
 tests/resources/trivial.pdf
 tests/resources/truetype_font_nomapping.pdf
 tests/resources/type3_font_nomapping.pdf
+ misc/screencast/*
 Copyright: (C) 2022 James R. Barlow
 License: CC-BY-SA-4.0

@@ -42,6 +42,8 @@ ocrmypdf                      # it's a scriptable command line program
 - Scales properly to handle files with thousands of pages
 - Battle-tested on millions of PDFs

+<img src="misc/screencast/demo.svg" alt="Demo of OCRmyPDF in a terminal session">
+
 For details: please consult the [documentation](https://ocrmypdf.readthedocs.io/en/latest/).

 ## Motivation
@@ -70,7 +72,7 @@ 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 py-ocrmypdf`` |
+| FreeBSD                       | ``pkg install py-ocrmypdf``   |
 | Conda                         | ``conda install ocrmypdf``    |
 | Ubuntu Snap                   | ``snap install ocrmypdf``     |

@@ -112,7 +114,7 @@ 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

@@ -123,6 +125,7 @@ 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

@@ -10,7 +10,7 @@ Control of unpaper

 OCRmyPDF uses ``unpaper`` to provide the implementation of the
 ``--clean`` and ``--clean-final`` arguments.
-`unpaper <https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md>`__
+`unpaper <https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md>`__
 provides a variety of image processing filters to improve images.

 By default, OCRmyPDF uses only ``unpaper`` arguments that were found to
@@ -104,7 +104,7 @@ was requested, the preprocessed image layer will be inserted.
 If you want to adjust the amount of time spent on OCR, change
 ``--tesseract-timeout``. You can also automatically skip images that
 exceed a certain number of megapixels with ``--skip-big``. (A 300 DPI,
-8.5×11" page is 8.4 megapixels.)
+8.5×11" page image is 8.4 megapixels.)

 .. code-block:: bash

@@ -241,6 +241,17 @@ PDF.js viewer.

 This works in all versions of Tesseract.

+Rendering and rasterizing options
+=================================
+
+.. versionadded:: 14.3.0
+
+The ``--continue-on-soft-render-error`` option allows OCRmyPDF to
+proceed if a page cannot be rasterized rendered. This is useful if you are
+trying to get the best possible OCR from a PDF that is not well-formed,
+and you are willing to accept some pages that may not visually match the
+input, and that may not OCR well.
+
 Return code policy
 ==================

@@ -299,16 +310,31 @@ stable user interface. They may be imported from
        - The program was interrupted by pressing Ctrl+C.


+.. _tmpdir:
+
+Changing temporary storage location
+===================================
+
+OCRmyPDF generates many temporary files during processing.
+
+To change where temporary files are stored, change the ``TMPDIR``
+environment variable for ocrmypdf's environment. (Python's
+``tempfile.gettempdir()`` returns the root directory in which temporary
+files will be stored.) For example, one could redirect ``TMPDIR`` to a
+large RAM disk to avoid wear on HDD/SSD and potentially improve
+performance.
+
+On Windows, the ``TEMP`` environment variable is used instead.
+
 Debugging the intermediate files
 ================================

 OCRmyPDF normally saves its intermediate results to a temporary folder
 and deletes this folder when it exits, whether it succeeded or failed.

-If the ``-k`` argument is issued on the command line, OCRmyPDF will keep
-the temporary folder and print the location, whether it succeeded or
-failed (provided the Python interpreter did not crash). An example
-message is:
+If the ``--keep-temporary-files`` (``-k```) argument is issued on the
+command line, OCRmyPDF will keep the temporary folder and print the location,
+whether it succeeded or failed. An example message is:

 .. code-block:: none

@@ -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}'``."
@@ -151,14 +151,14 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
 .. code-block:: bash

    docker run \
-        -v <path to files to convert>:/input \
-        -v <path to store results>:/output \
-        -v <path to store processed originals>:/archive \
-        -e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
-        -e OCR_ON_SUCCESS_ARCHIVE=1 \
-        -e OCR_DESKEW=1 \
-        -e PYTHONUNBUFFERED=1 \
-        -it --entrypoint python3 \
+        --volume <path to files to convert>:/input \
+        --volume <path to store results>:/output \
+        --volume <path to store processed originals>:/archive \
+        --env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1 \
+        --env OCR_ON_SUCCESS_ARCHIVE=1 \
+        --env OCR_DESKEW=1 \
+        --env PYTHONUNBUFFERED=1 \
+        --interactive --tty --entrypoint python3 \
        jbarlow83/ocrmypdf \
        watcher.py

@@ -170,13 +170,13 @@ original to ``/archive``. The parameters to this image are:
    :header: "Parameter", "Description"
    :widths: 50, 50

-    "``-v <path to files to convert>:/input``", "Files placed in this location will be OCRed"
-    "``-v <path to store results>:/output``", "This is where OCRed files will be stored"
-    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
-    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
-    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"
+    "``--volume <path to files to convert>:/input``", "Files placed in this location will be OCRed"
+    "``--volume <path to store results>:/output``", "This is where OCRed files will be stored"
+    "``--volume <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``--env OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``--env OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``--env OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``--env PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"

 This service relies on polling to check for changes to the filesystem. It
 may not be suitable for some environments, such as filesystems shared on a
@@ -0,0 +1,87 @@
+.. _ocr-service:
+
+==================
+Online deployments
+==================
+
+OCRmyPDF is designed to be used as a command line tool, but it can be
+used in a web service. This document describes some considerations for
+doing so.
+
+A basic web service implementation is provided in the source code
+repository, as ``misc/webservice.py``. It is only demonstration quality
+and is not intended for production use.
+
+OCRmyPDF is not designed for use as a public web service where a
+malicious user could upload a chosen PDF. In particular, it is not
+necessarily secure against PDF malware or PDFs that cause denial of
+service. For further discussino of security, see :ref:`security`.
+
+OCRmyPDF relies on Ghostscript, and therefore, if deployed
+online one should be prepared to comply with Ghostscript's Affero GPL
+license, and any other licenses.
+
+Setting aside these concerns, a side effect of OCRmyPDF is that it may
+incidentally sanitize PDFs containing certain types of malware. It
+repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
+structures that are part of an attack. When PDF/A output is selected
+(the default), the input PDF is partially reconstructed by Ghostscript.
+When ``--force-ocr`` is used, all pages are rasterized and reconverted
+to PDF, which could remove malware in embedded images.
+
+Limiting CPU usage
+------------------
+
+OCRmyPDF will attempt to use all available CPUs and storage, so
+executing ``nice ocrmypdf`` or limiting the number of jobs with the
+``--jobs`` argument may ensure the server remains responsive. Another option
+would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
+or a cloud instance, which can impose its own limits on CPU usage and be
+terminated "from orbit" if it fails to complete.
+
+Temporary storage requirements
+------------------------------
+
+OCRmyPDF will use a large amount of temporary storage for its work,
+proportional to the total number of pixels needed to rasterize the PDF.
+The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
+uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
+means it requires about 9 MB per intermediate based on average
+compression ratios. Multiple intermediates per page are also required,
+depending on the command line given. A rule of thumb would be to allow
+100 MB of temporary storage per page in a file – meaning that a small
+cloud servers or small VM partitions should be provisioned with plenty
+of extra space, if say, a 500 page file might be sent.
+
+To change the temporary directory, see :ref:`tmpdir`.
+
+On Amazon Web Services or other cloud vendors, consider setting your
+temporary directory to `empheral
+storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
+
+Timeouts
+--------
+
+To prevent excessively long OCR jobs consider setting
+``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
+is particularly helpful if your PDFs include documents such as reports
+on standard page sizes with large images attached - often large images
+are not worth OCR'ing anyway.
+
+Document management systems
+---------------------------
+
+If you are looking for a full document management system, consider
+`paperless-ngx <https://github.com/paperless-ngx/paperless-ngx>`__,
+which is a web application that uses OCRmyPDF to automatically OCR and
+archive documents.
+
+Commercial OCR alternatives
+---------------------------
+
+The author also provides professional services that include OCR and
+building databases around PDFs, and is happy to provide consultation.
+
+Abbyy Cloud OCR is viable commercial alternative with a web services
+API. Amazon Textract, Google Cloud Vision, and Microsoft Azure
+Computer Vision provide advanced OCR but have less PDF rendering capability.
@@ -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.
@@ -78,7 +78,6 @@ author = 'James R. Barlow'
 import os
 from importlib.metadata import version as package_version

-
 on_rtd = os.environ.get('READTHEDOCS') == 'True'

 if on_rtd:
@@ -18,7 +18,7 @@ work you're contemplating is already half-done in a development branch.
 Code style
 ==========

-We use PEP8, ``black`` for code formatting and ``isort`` for import sorting. The
+We use PEP8, ``black`` for code formatting and ``ruff`` for everything else. The
 settings for these programs are in ``pyproject.toml`` and ``setup.cfg``. Pull
 requests should follow the style guide. One difference we use from "black" style
 is that strings shown to the user are always in double quotes (``"``) and strings
@@ -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

@@ -20,7 +20,6 @@ image processing and OCR to existing PDFs.
   introduction
   release_notes
   installation
-   optimizer
   languages
   jbig2

@@ -29,9 +28,11 @@ image processing and OCR to existing PDFs.
   :maxdepth: 2

   cookbook
+   optimizer
   docker
   advanced
   batch
+   cloud
   performance
   pdfsecurity
   errors
@@ -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``               |
 +-------------------------------+-----------------------------------------+
@@ -121,7 +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>`__.
@@ -293,7 +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:
@@ -530,7 +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
@@ -637,7 +637,7 @@ system-wide:

 .. code-block:: bash

-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
    python3 -m venv venv
    source venv/bin/activate
    cd OCRmyPDF
@@ -664,7 +664,7 @@ To install all of the development and test requirements:

 .. code-block:: bash

-    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
+    git clone -b main https://github.com/ocrmypdf/OCRmyPDF.git
    python -m venv
    source venv/bin/activate
    cd OCRmyPDF
@@ -193,7 +193,7 @@ Ghostscript also imposes some limitations:
   (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.

@@ -12,7 +12,7 @@ OCRmyPDF uses Tesseract for OCR, and relies on its language packs for all langua
 On most platforms, English is installed with Tesseract by default, but not always.

 Tesseract supports `most
-languages <https://github.com/tesseract-ocr/tesseract/blob/master/doc/tesseract.1.asc#languages>`__.
+languages <https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc#languages>`__.
 Languages are identified by standardized three-letter codes (called ISO 639-2 Alpha-3).
 Tesseract's documentation also lists the three-letter code for your language.
 Some are anglicized, e.g. Spanish is ``spa`` rather than ``esp``, while others
@@ -70,13 +70,13 @@ This enables these languages for all packages (e.g. including aspell).

   # Display a list of all Tesseract language packs
   equery uses app-text/tessdata_fast
-   
+
   # Add English and German language support for Tesseract only
   echo 'app-text/tessdata_fast l10n_de l10n_en' >> /etc/portage/package.use
-   
-   # Add global English and German language support (the `l10n_` from equery has to be omited)
+
+   # 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
   emerge --update --deep --newuse @world

@@ -101,7 +101,7 @@ derived Docker image as
 Windows users
 =============

-The Tesseract installer provided by Chocolatey currently includes only English language. 
-To install other languages, download the respective language pack (``.traineddata`` file) 
-from https://github.com/tesseract-ocr/tessdata/ and place it in 
+The Tesseract installer provided by Chocolatey currently includes only English language.
+To install other languages, download the respective language pack (``.traineddata`` file)
+from https://github.com/tesseract-ocr/tessdata/ and place it in
 ``C:\\Program Files\\Tesseract-OCR\\tessdata`` (or wherever Tesseract OCR is installed).
@@ -13,14 +13,33 @@ tuned. Optimization occurs after OCR, and only if OCR succeeded.  It does not
 perform other possible optimizations such as deduplicating resources,
 consolidating fonts, simplifying vector drawings, or anything of that nature.

-Optimization ranges from ``-O0`` through ``-O3``, where ``0`` disables
-optimization and ``3`` implements all options. ``1``, the default, performs only
-safe and lossless optimizations. (This is similar to GCC's optimization
-parameter.) The exact type of optimizations performed will vary over time.
+.. list-table:: Title
+   :widths: 33 6 60
+   :header-rows: 1

-PDF optimization requires third-party, optional tools for certain optimizations.
-If these are not installed or cannot be found by OCRmyPDF, optimization will not
-be as good.
+    * - Optimization level
+      - Shorthand
+      - Description
+    * - ``--optimize 0``
+      - ``-O0``
+      - Disable most optimizations.
+    * - ``--optimize 1`` (default)
+      - ``-O1``
+      - Safe and lossless optimizations.
+    * - ``--optimize 2``
+      - ``-O2``
+      - Safe and lossy optimizations.
+    * - ``--optimize 3``
+      - ``-O3``
+      - Aggressive lossy optimizations.
+
+The exact type of optimizations performed will vary over time, and depend on
+the availability of third-party tools.
+
+Despite optimizations, OCRmyPDF might still increase the overall file size,
+since it must embed information about the recognized text, and depending on the
+settings chosen, may not be able to represent the output file as compactly as
+the input file.

 Optimizations that always occurs
 ================================
@@ -37,12 +56,14 @@ Fast web view
 OCRmyPDF automatically optimizes PDFs for "fast web view" in Adobe Acrobat's
 parlance, or equivalently, linearizes PDFs so that the resources they reference
 are presented in the order a viewer needs them for sequential display. This
-reduces the latency of viewing a PDF both online and from local storage. This
-actually slightly increases the file size.
+reduces the latency of viewing a PDF both online and from local storage, in
+exchange for a slight increase in file size.

 To disable this optimization and all others, use ``ocrmypdf --optimize 0 ...``
 or the shorthand ``-O0``.

+Adobe Acrobat might not report the file as being "fast web view".
+
 Lossless optimizations
 ======================

@@ -29,13 +29,9 @@ attack vectors.
 In short, PDFs `may contain
 viruses <https://security.stackexchange.com/questions/64052/can-a-pdf-file-contain-a-virus>`__.

-This
-`article <https://theinvisiblethings.blogspot.ca/2013/02/converting-untrusted-pdfs-into-trusted.html>`__
-describes a high-paranoia method which allows potentially hostile PDFs
-to be viewed and rasterized safely in a disposable virtual machine. A
-trusted PDF created in this manner is converted to images and loses all
-information making it searchable and losing all compression. OCRmyPDF
-could be used to restore searchability.
+If you do not trust a PDF or its source, do not open it or use OCRmyPDF
+on it. Consider using a Docker container or virtual machine to isolate
+an untrusted PDF from your system.

 How OCRmyPDF processes PDFs
 ===========================
@@ -43,11 +39,11 @@ How OCRmyPDF processes PDFs
 OCRmyPDF must open and interpret your PDF in order to insert an OCR
 layer. First, it runs all PDFs through
 `pikepdf <https://github.com/pikepdf/pikepdf>`__, a library based on
-`qpdf <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
+`QPDF <https://github.com/qpdf/qpdf>`__, a program that repairs PDFs
 with syntax errors. This is done because, in the author's experience, a
 significant number of PDFs in the wild, especially those created by
-scanners, are not well-formed files. qpdf makes it more likely that
-OCRmyPDF will succeed, but offers no security guarantees. qpdf is also
+scanners, are not well-formed files. QPDF makes it more likely that
+OCRmyPDF will succeed, but offers no security guarantees. QPDF is also
 used to split the PDF into single page PDFs.

 Finally, OCRmyPDF rasterizes each page of the PDF using
@@ -58,84 +54,6 @@ into the existing PDF or it may essentially reconstruct ("re-fry") a
 visually identical PDF that may be quite different at the binary level.
 That said, OCRmyPDF is not a tool designed for sanitizing PDFs.

-.. _ocr-service:
-
-Using OCRmyPDF online or as a service
-=====================================
-
-OCRmyPDF is not designed for use as a public web service where a
-malicious user could upload a chosen PDF. In particular, it is not
-necessarily secure against PDF malware or PDFs that cause denial of
-service. OCRmyPDF relies on Ghostscript, and therefore, if deployed
-online one should be prepared to comply with Ghostscript's Affero GPL
-license, and any other licenses.
-
-Setting aside these concerns, a side effect of OCRmyPDF is that it may
-incidentally sanitize PDFs containing certain types of malware. It
-repairs the PDF with pikepdf/libqpdf, which could correct malformed PDF
-structures that are part of an attack. When PDF/A output is selected
-(the default), the input PDF is partially reconstructed by Ghostscript.
-When ``--force-ocr`` is used, all pages are rasterized and reconverted
-to PDF, which could remove malware in embedded images.
-
-OCRmyPDF should be relatively safe to use in a trusted intranet, with
-some considerations:
-
-Limiting CPU usage
------------------
-
-OCRmyPDF will attempt to use all available CPUs and storage, so
-executing ``nice ocrmypdf`` or limiting the number of jobs with the
-``-j`` argument may ensure the server remains available. Another option
-would be to run OCRmyPDF jobs inside a Docker container, a virtual machine,
-or a cloud instance, which can impose its own limits on CPU usage and be
-terminated "from orbit" if it fails to complete.
-
-Temporary storage requirements
------------------------------
-
-OCRmyPDF will use a large amount of temporary storage for its work,
-proportional to the total number of pixels needed to rasterize the PDF.
-The raster image of a 8.5×11" color page at 300 DPI takes 25 MB
-uncompressed; OCRmyPDF saves its intermediates as PNG, but that still
-means it requires about 9 MB per intermediate based on average
-compression ratios. Multiple intermediates per page are also required,
-depending on the command line given. A rule of thumb would be to allow
-100 MB of temporary storage per page in a file – meaning that a small
-cloud servers or small VM partitions should be provisioned with plenty
-of extra space, if say, a 500 page file might be sent.
-
-To check temporary storage usage on actual files, run
-``ocrmypdf -k ...`` which will preserve and print the path to temporary
-storage when the job is done.
-
-To change where temporary files are stored, change the ``TMPDIR``
-environment variable for ocrmypdf's environment. (Python's
-``tempfile.gettempdir()`` returns the root directory in which temporary
-files will be stored.) For example, one could redirect ``TMPDIR`` to a
-large RAM disk to avoid wear on HDD/SSD and potentially improve
-performance. On Amazon Web Services, ``TMPDIR`` can be set to `empheral
-storage <https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/InstanceStorage.html>`__.
-
-Timeouts
--------
-
-To prevent excessively long OCR jobs consider setting
-``--tesseract-timeout`` and/or ``--skip-big`` arguments. ``--skip-big``
-is particularly helpful if your PDFs include documents such as reports
-on standard page sizes with large images attached - often large images
-are not worth OCR'ing anyway.
-
-Commercial alternatives
-----------------------
-
-The author also provides professional services that include OCR and
-building databases around PDFs, and is happy to provide consultation.
-
-Abbyy Cloud OCR is viable commercial alternative with a web services
-API. Amazon Textract, Google Cloud Vision, and Microsoft Azure 
-Computer Vision provide advanced OCR but have less PDF rendering capability.
-
 Password protection, digital signatures and certification
 =========================================================

@@ -28,6 +28,65 @@ tagged yet.

 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg

+v14.3.0
+=======
+
+-  Renamed master branch to main.
+-  Improve PDF rasterization accuracy by using the ``-dPDFSTOPONERROR`` option
+   to Ghostscript. Use ``--continue-on-soft-render-error`` if you want to render
+   the PDF anyway. The plugin specification was adjusted to support this feature;
+   plugin authors may want to adapt PDF rasterizing and rendering
+   plugins. :issue:`1083`
+-  The calculated deskew angle is now recorded in the logged output. :issue:`1101`
+-  Metadata can now be unset by setting a metadata type such as ``--title`` to an
+   empty string. :issue:`1117,1059`
+-  Fixed random order of languages due to use of a set. This may have caused output
+   to vary when multiple languages were set for OCR. :issue:`1113`
+-  Clarified the optimization ratio reported in the log output.
+-  Documentation improvements.
+
+v14.2.1
+=======
+
+-  Fixed :issue:`977`, where images inside Form XObjects were always excluded
+   from image optimization.
+
+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
 =======

@@ -711,7 +770,7 @@ 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
@@ -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

@@ -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
@@ -0,0 +1,31 @@
+<!-- SPDX-License-Identifier: CC-BY-SA-4.0 -->
+
+To regenerate
+=============
+
+Using asciinema and svg-term (`npm install -g svg-term-cli`).
+
+Create `~/.config/asciinema/config` to disable prompt.
+
+```
+[record]
+
+command = fish --init-command 'alias fish_prompt="echo \>\ "'
+```
+
+Run asciinema
+
+```
+asciinema rec new_input.cast
+```
+
+Re-record faster version with fewer pauses
+
+```
+asciinema rec demo.cast -c "asciinema play new_input.cast --speed 2 --idle-time-limit 0.5"
+```
+
+Convert to SVG
+```
+svg-term --in=misc/screencast/demo.cast --out=misc/screencast/demo.svg --window
+```
@@ -0,0 +1,65 @@
+{"version": 2, "width": 131, "height": 24, "timestamp": 1687247006, "env": {"SHELL": "/usr/bin/fish", "TERM": "xterm-256color"}}
+[0.103649, "o", "\u001b[?2004h\u001b]7; \u0007"]
+[0.104223, "o", "\u001b]0;fish  \u0007\u001b[30m\u001b(B\u001b[m\r> \u001b[K\r\u001b[C\u001b[C"]
+[0.604542, "o", "o\r\u001b[3C\b\u001b[38;2;255;0;0mo\r\u001b[3C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85mcrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[3C\u001b[30m\u001b(B\u001b[m"]
+[0.679571, "o", "\u001b[38;2;255;0;0mc\u001b[38;2;85;85;85mrmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[4C\u001b[30m\u001b(B\u001b[m"]
+[0.767271, "o", "\u001b[38;2;255;0;0mr\u001b[38;2;85;85;85mmypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[5C\u001b[30m\u001b(B\u001b[m"]
+[0.814505, "o", "\u001b[38;2;255;0;0mm\u001b[38;2;85;85;85mypdf multipage.pdf multipage_with_ocr.pdf\r\u001b[6C\u001b[30m\u001b(B\u001b[m"]
+[0.938919, "o", "\u001b[38;2;255;0;0my\u001b[38;2;85;85;85mpdf multipage.pdf multipage_with_ocr.pdf\r\u001b[7C\u001b[30m\u001b(B\u001b[m"]
+[0.967347, "o", "\u001b[38;2;255;0;0mp\u001b[38;2;85;85;85mdf multipage.pdf multipage_with_ocr.pdf\r\u001b[8C\u001b[30m\u001b(B\u001b[m"]
+[1.009954, "o", "\u001b[38;2;255;0;0md\u001b[38;2;85;85;85mf multipage.pdf multipage_with_ocr.pdf\r\u001b[9C\u001b[30m\u001b(B\u001b[m"]
+[1.034488, "o", "\u001b[38;2;255;0;0mf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m\b\b\b\b\b\b\b\b\u001b[38;2;0;95;215mocrmypdf\u001b[38;2;85;85;85m multipage.pdf multipage_with_ocr.pdf\r\u001b[10C\u001b[30m\u001b(B\u001b[m"]
+[1.069226, "o", "\u001b[38;2;0;95;215m \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m\b \u001b[38;2;85;85;85mmultipage.pdf multipage_with_ocr.pdf\r\u001b[11C\u001b[30m\u001b(B\u001b[m"]
+[1.569682, "o", "-\u001b[K\r\u001b[12C\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m\b\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85m-version\r\u001b[12C\u001b[30m\u001b(B\u001b[m"]
+[1.642096, "o", "\u001b[38;2;0;175;255m-\u001b[38;2;85;85;85mversion\r\u001b[13C\u001b[30m\u001b(B\u001b[m"]
+[1.71793, "o", "\u001b[38;2;0;175;255ms\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[14C"]
+[1.771483, "o", "\u001b[38;2;0;175;255mk\r\u001b[15C\u001b[30m\u001b(B\u001b[m"]
+[1.864664, "o", "\u001b[38;2;0;175;255mi\r\u001b[16C\u001b[30m\u001b(B\u001b[m"]
+[1.876085, "o", "\u001b[38;2;0;175;255mp\r\u001b[17C\u001b[30m\u001b(B\u001b[m"]
+[2.092979, "o", "\u001b[38;2;0;175;255m-\r\u001b[18C\u001b[30m\u001b(B\u001b[m"]
+[2.138821, "o", "\u001b[38;2;0;175;255mt\r\u001b[19C\u001b[30m\u001b(B\u001b[m"]
+[2.18017, "o", "\u001b[38;2;0;175;255me\r\u001b[20C\u001b[30m\u001b(B\u001b[m"]
+[2.268222, "o", "\u001b[38;2;0;175;255mx\r\u001b[21C\u001b[30m\u001b(B\u001b[m"]
+[2.277031, "o", "\u001b[38;2;0;175;255mt\r\u001b[22C\u001b[30m\u001b(B\u001b[m"]
+[2.322469, "o", "\u001b[38;2;0;175;255m \r\u001b[23C\u001b[30m\u001b(B\u001b[m\b \r\u001b[23C"]
+[2.824696, "o", "m\r\u001b[24C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[24C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[24C\u001b[30m\u001b(B\u001b[m"]
+[2.923234, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[25C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[25C\u001b[30m\u001b(B\u001b[m"]
+[2.960685, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[26C\u001b[30m\u001b(B\u001b[m"]
+[3.03365, "o", "\u001b[38;2;0;175;255m\u001b[4mt\u001b[38;2;85;85;85m\u001b[24mipage.pdf \r\u001b[27C\u001b[30m\u001b(B\u001b[m"]
+[3.479338, "o", "\u001b[38;2;0;175;255m\u001b[4mipage.pdf \r\u001b[37C\u001b[30m\u001b(B\u001b[m\b \r\u001b[37C"]
+[3.754818, "o", "m\r\u001b[38C\b\u001b[38;2;0;175;255m\u001b[4mm\r\u001b[38C\u001b[30m\u001b(B\u001b[m\u001b[38;2;85;85;85masks.pdf \r\u001b[38C\u001b[30m\u001b(B\u001b[m"]
+[3.873318, "o", "\u001b[38;2;0;175;255m\u001b[4mu\u001b[30m\u001b(B\u001b[m\u001b[K\r\u001b[39C\u001b[38;2;85;85;85mltipage.pdf \r\u001b[39C\u001b[30m\u001b(B\u001b[m"]
+[3.926829, "o", "\u001b[38;2;0;175;255m\u001b[4ml\u001b[38;2;85;85;85m\u001b[24mtipage.pdf \r\u001b[40C\u001b[30m\u001b(B\u001b[m"]
+[4.272251, "o", "\u001b[38;2;0;175;255m\u001b[4mtipage.pdf \r\u001b[51C\u001b[30m\u001b(B\u001b[m\b \r\u001b[51C"]
+[4.343464, "o", "\r\u001b[50C"]
+[4.416286, "o", "\r\u001b[49C"]
+[4.490574, "o", "\r\u001b[48C"]
+[4.564115, "o", "\r\u001b[47C"]
+[4.630398, "o", "\r\u001b[46C"]
+[4.76825, "o", "\u001b[38;2;0;175;255m\u001b[4m_.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[47C\u001b[10D\u001b[38;2;0;175;255mmultipage_.pdf\u001b[30m\u001b(B\u001b[m \r\u001b[47C"]
+[5.012506, "o", "\u001b[38;2;0;175;255mo.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[48C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[48C"]
+[5.053615, "o", "\u001b[38;2;0;175;255mc.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[49C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[49C"]
+[5.103957, "o", "\u001b[38;2;0;175;255mr.pd\u001b[30m\u001b(B\u001b[mf \r\u001b[50C\u001b[3C\u001b[38;2;0;175;255mf\u001b[30m\u001b(B\u001b[m \r\u001b[50C"]
+[5.226183, "o", "\r\u001b[55C"]
+[5.728321, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[?2004l\u001b]0;ocrmypdf --skip-text multipage.pdf multipage_ocr.pdf  /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m\r"]
+[5.801032, "o", "\rScanning contents:   0%|                                                                                   | 0/6 [00:00<?, ?page/s]"]
+[5.802664, "o", "\rScanning contents: 100%|█████████████████████████████████████████████████████████████████████████| 6/6 [00:00<00:00, 1270.68page/s]\r\n"]
+[5.802747, "o", "Start processing 6 pages concurrently\r\n"]
+[5.803488, "o", "\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
+[5.804896, "o", "\r                                                                                                                                   \r    4 skipping all processing on this page\r\n\rOCR:   0%|                                                                                             | 0.0/6.0 [00:00<?, ?page/s]"]
+[5.896969, "o", "\rOCR:  25%|█████████████████████▎                                                               | 1.5/6.0 [00:00<00:00,  8.12page/s]"]
+[6.170021, "o", "\rOCR:  42%|███████████████████████████████████▍                                                 | 2.5/6.0 [00:00<00:01,  3.05page/s]"]
+[6.292338, "o", "\rOCR:  58%|█████████████████████████████████████████████████▌                                   | 3.5/6.0 [00:00<00:00,  3.39page/s]"]
+[6.586017, "o", "\rOCR:  75%|███████████████████████████████████████████████████████████████▊                     | 4.5/6.0 [00:01<00:00,  2.49page/s]"]
+[7.087058, "o", "\rOCR:  92%|█████████████████████████████████████████████████████████████████████████████▉       | 5.5/6.0 [00:06<00:00,  1.98s/page]\rOCR: 100%|█████████████████████████████████████████████████████████████████████████████████████| 6.0/6.0 [00:06<00:00,  1.09s/page]\r\nPostprocessing...\r\n"]
+[7.104927, "o", "\rPDF/A conversion:   0%|                                                                                    | 0/6 [00:00<?, ?page/s]"]
+[7.607392, "o", "\rPDF/A conversion:  50%|██████████████████████████████████████                                      | 3/6 [00:01<00:01,  1.61page/s]"]
+[7.653781, "o", "\rPDF/A conversion:  83%|███████████████████████████████████████████████████████████████▎            | 5/6 [00:01<00:00,  2.90page/s]"]
+[7.774532, "o", "\rPDF/A conversion: 100%|████████████████████████████████████████████████████████████████████████████| 6/6 [00:02<00:00,  2.71page/s]\r\n"]
+[7.778252, "o", "\u001b[33mSome input metadata could not be copied because it is not permitted in PDF/A. You may wish to examine the output PDF's XMP metadata.\u001b[0m\r\n"]
+[8.280789, "o", "\rRecompressing JPEGs: 0image [00:00, ?image/s]\rRecompressing JPEGs: 0image [00:00, ?image/s]\r\n\rDeflating JPEGs:   0%|                                                                                    | 0/4 [00:00<?, ?image/s]\rDeflating JPEGs: 100%|███████████████████████████████████████████████████████████████████████████| 4/4 [00:00<00:00, 238.28image/s]\r\n"]
+[8.28149, "o", "\rJBIG2: 0item [00:00, ?item/s]\rJBIG2: 0item [00:00, ?item/s]\r\n"]
+[8.289998, "o", "Image optimization ratio: 1.01 savings: 1.3%\r\nTotal file size ratio: 1.02 savings: 1.6%\r\n"]
+[8.291209, "o", "Output file is a PDF/A-2B (as expected)\r\n"]
+[8.361316, "o", "\u001b[2m⏎\u001b(B\u001b[m                                                                                                                                  \r⏎ \r\u001b[K\u001b[?2004h\u001b]0;fish /home/jb/src/ocrmypdf/tests/resources\u0007\u001b[30m\u001b(B\u001b[m> \u001b[K\r\u001b[C\u001b[C"]
+[8.862206, "o", "\r\n\u001b[30m\u001b(B\u001b[m\u001b[30m\u001b(B\u001b[m\u001b[?2004l"]
@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: 2017 Enantiomerie
 # SPDX-License-Identifier: MIT

-"""Example OCRmyPDF for Synology NAS"""
+"""Example OCRmyPDF for Synology NAS."""

 from __future__ import annotations

@@ -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)
@@ -142,6 +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}"
    )
@@ -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')
@@ -37,16 +37,12 @@ classifiers = [
  "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 :: MacOS",
+  "Operating System :: Microsoft :: Windows",
  "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",
@@ -69,6 +65,7 @@ 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",
@@ -140,27 +137,6 @@ exclude_lines = [
  "if TYPE_CHECKING:"
 ]

-[tool.isort]
-profile = "black"
-known_first_party = "ocrmypdf"
-known_third_party = [
-  "PIL",
-  "flask",
-  "img2pdf",
-  "ocrmypdf",
-  "pdfminer",
-  "pikepdf",
-  "pkg_resources",
-  "pluggy",
-  "pytest",
-  "reportlab",
-  "setuptools",
-  "sphinx_rtd_theme",
-  "tqdm",
-  "watchdog",
-  "werkzeug"
-]
-
 [tool.pytest.ini_options]
 minversion = "6.0"
 norecursedirs = ["lib", ".pc", ".git", "venv", "output", "cache", "resources"]
@@ -184,7 +160,26 @@ module = [
 ]
 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"]
@@ -1,5 +1,6 @@
 # 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
@@ -54,7 +55,10 @@ parts:

  ocrmypdf:
    plugin: python
-    source: https://github.com/ocrmypdf/OCRmyPDF.git
+    source: .
+
+    build-packages:
+      - python3-pip

    stage-packages:
      - ghostscript
@@ -77,7 +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
@@ -29,3 +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',
+]
@@ -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):
@@ -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:
@@ -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
@@ -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

@@ -30,7 +30,7 @@ except AttributeError:

 log = logging.getLogger(__name__)

-# Most reliable what to get the bitness of Python interpreter, according to Python docs
+# Most reliable way to get the bitness of Python interpreter, according to Python docs
 _IS_64BIT = sys.maxsize > 2**32

 _GSWIN = None
@@ -63,6 +63,7 @@ def rasterize_pdf(
    page_dpi: Resolution | None = None,
    rotation: int | None = None,
    filter_vector: bool = False,
+    stop_on_error: bool = False,
 ):
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
    raster_dpi = raster_dpi.round(6)
@@ -83,6 +84,7 @@ def rasterize_pdf(
            f'-r{raster_dpi.x:f}x{raster_dpi.y:f}',
        ]
        + (['-dFILTERVECTOR'] if filter_vector else [])
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
        + [
            '-o',
            '-',
@@ -161,6 +163,7 @@ def generate_pdfa(
    pdf_version: str = '1.5',
    pdfa_part: str = '2',
    progressbar_class=None,
+    stop_on_error: bool = False,
 ):
    # Ghostscript's compression is all or nothing. We can either force all images
    # to JPEG, force all to Flate/PNG, or let it decide how to encode the images.
@@ -193,6 +196,10 @@ def generate_pdfa(
        # https://bugs.ghostscript.com/show_bug.cgi?id=705187
        compression_args.append('-dNEWPDF=false')

+    if os.name == 'nt':
+        # Windows has lots of fatal "permission denied" errors
+        stop_on_error = False
+
    # nb no need to specify ProcessColorModel when ColorConversionStrategy
    # is set; see:
    # https://bugs.ghostscript.com/show_bug.cgi?id=699392
@@ -207,6 +214,7 @@ def generate_pdfa(
            "-dAutoRotatePages=/None",
            "-sColorConversionStrategy=" + strategy,
        ]
+        + (['-dPDFSTOPONERROR'] if stop_on_error else [])
        + compression_args
        + [
            "-dJPEGQ=95",
@@ -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

@@ -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

@@ -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

@@ -34,10 +34,12 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
  <title></title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8" />
  <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'/>
+  <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
    )
@@ -230,6 +233,7 @@ def get_deskew(
    parsed = _parse_tesseract_output(p.stdout)
    deskew_radians = float(parsed.get('Deskew angle', 0))
    deskew_degrees = 180 / pi * deskew_radians
+    log.debug(f"Deskew angle: {deskew_degrees:.3f}")
    return deskew_degrees


@@ -280,8 +284,10 @@ 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

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

-"""Interface to unpaper executable"""
+"""Interface to unpaper executable."""

 from __future__ import annotations

@@ -21,7 +21,7 @@ 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
+# https://github.com/Flameeyes/unpaper/blob/main/doc/basic-concepts.md


 if sys.version_info >= (3, 10):
@@ -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")
@@ -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__``.
    """

@@ -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
@@ -14,7 +14,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Any, Iterable, Sequence
+from typing import Any, BinaryIO, Iterable, Sequence, cast

 import img2pdf
 import pikepdf
@@ -37,6 +37,7 @@ 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, PageInfo, PdfInfo
+from ocrmypdf.pluginspec import OrientationConfidence

 # Remove this workaround when we require Pillow >= 10
 try:
@@ -51,6 +52,20 @@ VECTOR_PAGE_DPI = 400


 def triage_image_file(input_file: Path, output_file: Path, options) -> None:
+    """Triage the input image file.
+
+    If the input file is an image, check its resolution and convert it to PDF.
+
+    Args:
+        input_file: The path to the input file.
+        output_file: The path to the output file.
+        options: An object containing the options passed to the OCRmyPDF command.
+
+    Raises:
+        UnsupportedImageFormatError: If the input file is not a supported image format.
+        DpiError: If the input image has no resolution (DPI) in its metadata or if the
+            resolution is not credible.
+    """
    log.info("Input file is not a PDF, checking if it is an image...")
    try:
        im = Image.open(input_file)
@@ -121,7 +136,6 @@ def _pdf_guess_version(input_file: Path, search_window=1024) -> str:

    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)
@@ -186,15 +200,6 @@ def validate_pdfinfo_options(context: PdfContext) -> None:
            "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(
@@ -218,11 +223,12 @@ def validate_pdfinfo_options(context: PdfContext) -> None:


 def _vector_page_dpi(pageinfo: PageInfo) -> int:
+    """Get a DPI to use for vector pages, if the page has vector content."""
    return VECTOR_PAGE_DPI if pageinfo.has_vector or pageinfo.has_text else 0


 def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:
-    "Get the DPI when nonsquare DPI is tolerable"
+    """Get the DPI when nonsquare DPI is tolerable."""
    xres = max(
        pageinfo.dpi.x or VECTOR_PAGE_DPI,
        options.oversample or 0.0,
@@ -237,7 +243,10 @@ def get_page_dpi(pageinfo: PageInfo, options) -> Resolution:


 def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    "Get the DPI when we require xres == yres, scaled to physical units"
+    """Get the DPI when we require xres == yres, scaled to physical units.
+
+    Page DPI includes UserUnit scaling.
+    """
    xres = pageinfo.dpi.x or 0.0
    yres = pageinfo.dpi.y or 0.0
    userunit = float(pageinfo.userunit) or 1.0
@@ -253,7 +262,12 @@ def get_page_square_dpi(pageinfo: PageInfo, options) -> Resolution:


 def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:
-    """Get the DPI when we require xres == yres, in Postscript units"""
+    """Get the DPI when we require xres == yres, in Postscript units.
+
+    Canvas DPI is independent of PDF UserUnit scaling, which is
+    used to describe situations where the PDF user space is not 1:1 with
+    the physical units of the page.
+    """
    units = float(
        max(
            (pageinfo.dpi.x) or VECTOR_PAGE_DPI,
@@ -266,6 +280,7 @@ def get_canvas_square_dpi(pageinfo: PageInfo, options) -> Resolution:


 def is_ocr_required(page_context: PageContext) -> bool:
+    """Check if the page needs to be OCR'd."""
    pageinfo = page_context.pageinfo
    options = page_context.options

@@ -315,8 +330,8 @@ def is_ocr_required(page_context: PageContext) -> bool:
            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:
@@ -341,6 +356,7 @@ def is_ocr_required(page_context: PageContext) -> bool:


 def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
+    """Generate a lower quality preview image."""
    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)
@@ -353,14 +369,15 @@ def rasterize_preview(input_file: Path, page_context: PageContext) -> Path:
        page_dpi=page_dpi,
        rotation=0,
        filter_vector=False,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
    )
    return output_file


-def describe_rotation(page_context: PageContext, orient_conf, correction: int) -> str:
-    """
-    Describe the page rotation we are going to perform.
-    """
+def describe_rotation(
+    page_context: PageContext, orient_conf: OrientationConfidence, correction: int
+) -> str:
+    """Describe the page rotation we are going to perform (or not perform)."""
    direction = {0: '⇧', 90: '⇨', 180: '⇩', 270: '⇦'}
    turns = {0: ' ', 90: '⬏', 180: '↻', 270: '⬑'}

@@ -387,7 +404,7 @@ def describe_rotation(page_context: PageContext, orient_conf, correction: int) -


 def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
-    """Work out orientation correct for each page.
+    """Work out orientation correction for each page.

    We ask Ghostscript to draw a preview page, which will rasterize with the
    current /Rotate applied, and then ask OCR which way the page is
@@ -401,7 +418,6 @@ def get_orientation_correction(preview: Path, page_context: PageContext) -> int:
    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
    )
@@ -422,8 +438,22 @@ def rasterize(
    page_context: PageContext,
    correction: int = 0,
    output_tag: str = '',
-    remove_vectors=None,
-):
+    remove_vectors: bool | None = None,
+) -> Path:
+    """Rasterize a PDF page to a PNG image.
+
+    Args:
+        input_file: The input PDF file path.
+        page_context: The page context object.
+        correction: The orientation correction angle. Defaults to 0.
+        output_tag: The output tag. Defaults to ''.
+        remove_vectors: Whether to remove vectors. Defaults to None, which means
+            the value from the page context options will be used. If the value
+            is True or False, it will override the page context options.
+
+    Returns:
+        Path: The output PNG file path.
+    """
    colorspaces = ['pngmono', 'pnggray', 'png256', 'png16m']
    device_idx = 0

@@ -468,6 +498,7 @@ def rasterize(
        pageno=pageinfo.pageno + 1,
        rotation=correction,
        filter_vector=remove_vectors,
+        stop_on_soft_error=not page_context.options.continue_on_soft_render_error,
    )
    return output_file

@@ -483,6 +514,15 @@ def preprocess_remove_background(input_file: Path, page_context: PageContext) ->


 def preprocess_deskew(input_file: Path, page_context: PageContext) -> Path:
+    """Deskews the input image using the OCR engine and saves the output to a file.
+
+    Args:
+        input_file: The input image file to deskew.
+        page_context: The context of the page being processed.
+
+    Returns:
+        Path: The path to the deskewed image file.
+    """
    output_file = page_context.get_path('pp_deskew.png')
    dpi = get_page_square_dpi(page_context.pageinfo, page_context.options)

@@ -514,10 +554,11 @@ def preprocess_clean(input_file: Path, page_context: PageContext) -> Path:


 def create_ocr_image(image: Path, page_context: PageContext) -> Path:
-    """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."""
+    """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:
@@ -577,8 +618,19 @@ def ocr_engine_hocr(input_file: Path, page_context: PageContext) -> tuple[Path,


 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)
+    """Determines whether the visible page image should be saved as a JPEG.
+
+    If all images were JPEGs originally, permit a JPEG as output.
+
+    Args:
+        pageinfo: The PageInfo object containing information about the page.
+
+    Returns:
+        A boolean indicating whether the visible page image should be saved as a JPEG.
+    """
+    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:
@@ -746,6 +798,7 @@ def convert_to_pdfa(input_pdf: Path, input_ps_stub: Path, context: PdfContext) -
            if options.progress_bar
            else None
        ),
+        stop_on_soft_error=not options.continue_on_soft_render_error,
    )

    return output_file
@@ -799,24 +852,43 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:

    with pikepdf.open(context.origin) as original, pikepdf.open(working_file) as pdf:
        docinfo = get_docinfo(original, context)
-        with pdf.open_metadata() as meta:
-            meta.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
+        with pdf.open_metadata() as meta_pdf:
+            meta_pdf.load_from_docinfo(docinfo, delete_missing=False, raise_failure=False)
            # If xmp:CreateDate is missing, set it to the modify date to
-            # match Ghostscript, for consistency
-            if 'xmp:CreateDate' not in meta:
-                meta['xmp:CreateDate'] = meta.get('xmp:ModifyDate', '')
+            # ensure consistency with Ghostscript.
+            if 'xmp:CreateDate' not in meta_pdf:
+                meta_pdf['xmp:CreateDate'] = meta_pdf.get('xmp:ModifyDate', '')

            with original.open_metadata(
                set_pikepdf_as_editor=False, update_docinfo=False, strict=False
            ) as meta_original:
-                if meta.get('dc:title') == 'Untitled':
+                if meta_pdf.get('dc:title') == 'Untitled':
                    # Ghostscript likes to set title to Untitled if omitted from input.
                    # Reverse this, because PDF/A TechNote 0003:Metadata in PDF/A-1
                    # and the XMP Spec do not make this recommendation.
                    if 'dc:title' not in meta_original:
-                        del meta['dc:title']
-                missing = set(meta_original.keys()) - set(meta.keys())
-                report_on_metadata(missing)
+                        del meta_pdf['dc:title']
+                # If the user explicitly specified an empty string for any of the
+                # following, they should be unset and not reported as missing in
+                # the output pdf. Note that some metadata fields use differing names
+                # between PDF-A and PDF.
+                for meta in [meta_pdf, meta_original]:
+                    if options.title == '' and 'dc:title' in meta:
+                        del meta['dc:title']  # PDF-A and PDF
+                    if options.author == '':
+                        if 'dc:creator' in meta:
+                            del meta['dc:creator']  # PDF-A (Not xmp:CreatorTool)
+                        if 'pdf:Author' in meta:
+                            del meta['pdf:Author']  # PDF
+                    if options.subject == '':
+                        if 'dc:description' in meta:
+                            del meta['dc:description']  # PDF-A
+                        if 'dc:subject' in meta:
+                            del meta['dc:subject']  # PDF
+                    if options.keywords == '' and 'pdf:Keywords' in meta:
+                        del meta['pdf:Keywords']  # PDF-A and PDF
+                meta_missing = set(meta_original.keys()) - set(meta_pdf.keys())
+                report_on_metadata(meta_missing)

        optimizing = context.plugin_manager.hook.is_optimization_enabled(
            context=context
@@ -832,6 +904,18 @@ def metadata_fixup(working_file: Path, context: PdfContext) -> Path:
    return output_file


+def _file_size_ratio(
+    input_file: Path, output_file: Path
+) -> tuple[float | None, float | None]:
+    input_size = input_file.stat().st_size
+    output_size = output_file.stat().st_size
+    if output_size == 0:
+        return None, None
+    ratio = input_size / output_size
+    savings = 1 - output_size / input_size
+    return ratio, savings
+
+
 def optimize_pdf(
    input_file: Path, context: PdfContext, executor: Executor
 ) -> tuple[Path, Sequence[str]]:
@@ -844,13 +928,12 @@ def optimize_pdf(
        linearize=should_linearize(input_file, context),
    )

-    input_size = input_file.stat().st_size
-    output_size = output_file.stat().st_size
-    if output_size > 0:
-        ratio = input_size / output_size
-        savings = 1 - output_size / input_size
-        log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
-
+    ratio, savings = _file_size_ratio(input_file, output_file)
+    if ratio:
+        log.info(f"Image optimization ratio: {ratio:.2f} savings: {(savings):.1%}")
+    ratio, savings = _file_size_ratio(context.origin, output_file)
+    if ratio:
+        log.info(f"Total file size ratio: {ratio:.2f} savings: {(savings):.1%}")
    return output_pdf, messages


@@ -895,15 +978,17 @@ def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext) -> Pat
    return output_file


-def copy_final(input_file, output_file, _context: PdfContext) -> None:
+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:
@@ -251,8 +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)
@@ -316,8 +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.
@@ -420,13 +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")
@@ -435,7 +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 "
@@ -453,7 +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:
@@ -51,27 +51,38 @@ def check_platform() -> None:
        )


-def check_options_languages(options: Namespace, ocr_engine_languages: set[str]) -> None:
+def check_options_languages(
+    options: Namespace, ocr_engine_languages: list[str]
+) -> None:
    if not options.languages:
-        options.languages = {DEFAULT_LANGUAGE}
+        options.languages = [DEFAULT_LANGUAGE]
        system_lang = locale.getlocale()[0]
        if system_lang and not system_lang.startswith('en'):
            log.debug("No language specified; assuming --language %s", DEFAULT_LANGUAGE)
    if not ocr_engine_languages:
        return
-    missing_languages = options.languages - ocr_engine_languages
+    missing_languages = set(options.languages) - set(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-letter ISO 639-2 Code.\n"
+            "For example, English is 'eng', German is 'deu', and Spanish is 'spa'.\n"
+            "Simplified Chinese is 'chi_sim' and Traditional Chinese is 'chi_tra'."
+            "\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)


 def check_options_output(options: Namespace) -> None:
-    is_latin = options.languages.issubset(HOCR_OK_LANGS)
+    is_latin = set(options.languages).issubset(HOCR_OK_LANGS)

    if options.pdf_renderer.startswith('hocr') and not is_latin:
        log.warning(
@@ -109,12 +120,10 @@ 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:
@@ -276,7 +285,8 @@ 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 +343,7 @@ 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)
@@ -86,7 +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)
@@ -143,6 +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 = []

@@ -203,59 +203,73 @@ 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,
+    continue_on_soft_render_error: bool | 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:
@@ -277,6 +291,7 @@ 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.MissingDependencyError: If a required dependency program is missing or
            was not found on PATH.
@@ -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
@@ -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))
@@ -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

@@ -17,6 +16,7 @@ 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',
@@ -45,7 +45,9 @@ def rasterize_pdf_page(
    page_dpi,
    rotation,
    filter_vector,
+    stop_on_soft_error,
 ):
+    """Rasterize a single page of a PDF file using Ghostscript."""
    ghostscript.rasterize_pdf(
        input_file,
        output_file,
@@ -55,6 +57,7 @@ def rasterize_pdf_page(
        page_dpi=page_dpi,
        rotation=rotation,
        filter_vector=filter_vector,
+        stop_on_error=stop_on_soft_error,
    )
    return output_file

@@ -68,7 +71,9 @@ def generate_pdfa(
    pdf_version,
    pdfa_part,
    progressbar_class,
+    stop_on_soft_error,
 ):
+    """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,
@@ -76,5 +81,6 @@ def generate_pdfa(
        pdf_version=pdf_version,
        pdfa_part=pdfa_part,
        progressbar_class=progressbar_class,
+        stop_on_error=stop_on_soft_error,
    )
    return output_file
@@ -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

@@ -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',
@@ -132,6 +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."""

@@ -156,7 +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
@@ -165,7 +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
@@ -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
@@ -74,19 +82,22 @@ 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()
+            default = list()
        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('+'))
+            [dest.append(lang) for lang in values.split('+')]
        else:
-            dest.add(values)
+            dest.append(values)


 def get_parser():
+    """Get the main CLI parser."""
    parser = ArgumentParser(
        prog=_PROGRAM_NAME,
        allow_abbrev=True,
@@ -409,6 +420,14 @@ Online documentation is located at:
        "which do not benefit. If the threshold is 0 it will be apply to all files. "
        "Set the threshold very high to disable.",
    )
+    advanced.add_argument(
+        '--continue-on-soft-render-error',
+        action='store_true',
+        help="Continue processing pages after a recoverable PDF rendering error. "
+        "A recoverable error is one that does not prevent the page from being "
+        "rendered, but may result in visual differences compared to the input "
+        "file. Missing fonts are a typical source of these errors.",
+    )
    advanced.add_argument(
        '--plugin',
        dest='plugins',
@@ -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)
@@ -94,7 +95,7 @@ class EncryptedPdfError(ExitCodeException):

    exit_code = ExitCode.encrypted_pdf
    message = dedent(
-        '''\
+        """\
        Input PDF is encrypted. The encryption must be removed to
        perform OCR.

@@ -103,7 +104,7 @@ class EncryptedPdfError(ExitCodeException):

        You can remove the encryption using
            qpdf --decrypt [--password=[password]] infilename
-        '''
+        """
    )


@@ -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 ...
+"""
@@ -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
@@ -49,6 +49,7 @@ class Resolution(Generic[T]):
    __slots__ = ('x', 'y')

    def __init__(self, x: T, y: T):
+        """Construct a Resolution object."""
        self.x = x
        self.y = y

@@ -57,9 +58,11 @@ class Resolution(Generic[T]):
    CONVERSION_ERROR = 0.002

    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) -> Resolution[int]:
+        """Round to nearest integer."""
        return Resolution(int(round(self.x)), int(round(self.y)))

    @classmethod
@@ -68,10 +71,12 @@ class Resolution(Generic[T]):

    @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:
+        """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
@@ -79,6 +84,7 @@ class Resolution(Generic[T]):
    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
@@ -88,18 +94,23 @@ class Resolution(Generic[T]):
        return Resolution(max_x, max_y)

    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):
@@ -108,7 +119,7 @@ class Resolution(Generic[T]):


 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):
@@ -153,6 +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:
@@ -170,7 +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])


@@ -199,7 +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,
@@ -273,13 +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")
@@ -99,11 +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})')
@@ -119,6 +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))

@@ -143,9 +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'))
@@ -155,9 +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
@@ -169,10 +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'])
@@ -183,9 +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:
@@ -193,9 +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:
@@ -206,21 +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,
        *,
@@ -231,8 +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
@@ -323,6 +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(
@@ -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
@@ -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
@@ -224,13 +230,72 @@ def extract_image_generic(
    return None


+def _find_image_xrefs_container(
+    pdf: Pdf,
+    container: Object,
+    pageno: int,
+    include_xrefs: MutableSet[Xref],
+    exclude_xrefs: MutableSet[Xref],
+    pageno_for_xref: dict[Xref, int],
+    depth: int = 0,
+):
+    """Find all image XRefs in a page or Form XObject and add to the include/exclude sets."""
+    if depth > 10:
+        log.warning("Recursion depth exceeded in _find_image_xrefs_page")
+        return
+    try:
+        xobjs = container.Resources.XObject
+    except AttributeError:
+        return
+    for _imname, image in dict(xobjs).items():
+        if image.objgen[1] != 0:
+            continue  # Ignore images in an incremental PDF
+        if Name.Subtype in image and image.Subtype == Name.Form:
+            # Recurse into Form XObjects
+            log.debug(f"Recursing into Form XObject {_imname} in page {pageno}")
+            _find_image_xrefs_container(
+                pdf,
+                image,
+                pageno,
+                include_xrefs,
+                exclude_xrefs,
+                pageno_for_xref,
+                depth + 1,
+            )
+            continue
+        xref = Xref(image.objgen[0])
+        if Name.SMask in image:
+            # Ignore soft masks
+            smask_xref = Xref(image.SMask.objgen[0])
+            exclude_xrefs.add(smask_xref)
+            log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
+        include_xrefs.add(xref)
+        log.debug(f"xref {xref}: treating as an optimization candidate")
+        if xref not in pageno_for_xref:
+            pageno_for_xref[xref] = pageno
+
+
+def _find_image_xrefs(pdf: Pdf):
+    include_xrefs: MutableSet[Xref] = set()
+    exclude_xrefs: MutableSet[Xref] = set()
+    pageno_for_xref: dict[Xref, int] = {}
+
+    for pageno, page in enumerate(pdf.pages):
+        _find_image_xrefs_container(
+            pdf, page, pageno, include_xrefs, exclude_xrefs, pageno_for_xref
+        )
+
+    working_xrefs = include_xrefs - exclude_xrefs
+    return working_xrefs, pageno_for_xref
+
+
 def extract_images(
    pike: Pdf,
    root: Path,
    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).
@@ -244,31 +309,8 @@ 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 = {}
    errors = 0
-    for pageno, page in enumerate(pike.pages):
-        try:
-            xobjs = page.Resources.XObject
-        except AttributeError:
-            continue
-        for _imname, image in dict(xobjs).items():
-            if image.objgen[1] != 0:
-                continue  # Ignore images in an incremental PDF
-            xref = Xref(image.objgen[0])
-            if Name.SMask in image:
-                # Ignore soft masks
-                smask_xref = Xref(image.SMask.objgen[0])
-                exclude_xrefs.add(smask_xref)
-                log.debug(f"xref {smask_xref}: skipping image because it is an SMask")
-            include_xrefs.add(xref)
-            log.debug(f"xref {xref}: treating as an optimization candidate")
-            if xref not in pageno_for_xref:
-                pageno_for_xref[xref] = pageno
-
-    working_xrefs = include_xrefs - exclude_xrefs
+    working_xrefs, pageno_for_xref = _find_image_xrefs(pike)
    for xref in working_xrefs:
        image = pike.get_object((xref, 0))
        try:
@@ -289,8 +331,7 @@ 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 +345,7 @@ 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 +358,7 @@ 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 +463,8 @@ 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 +523,12 @@ 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 +616,7 @@ def transcode_pngs(
    options,
    executor,
 ) -> None:
+    """Apply lossy transcoding to PNGs."""
    modified: MutableSet[Xref] = set()
    if options.optimize >= 2:
        png_quality = (
@@ -614,6 +663,7 @@ 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 +720,12 @@ 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
@@ -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:
@@ -7,3 +7,5 @@
 from __future__ import annotations

 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PageInfo, PdfInfo
+
+__all__ = ["Colorspace", "Encoding", "PageInfo", "PdfInfo"]
@@ -164,7 +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
@@ -200,7 +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] = []
@@ -307,7 +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
@@ -324,7 +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')

@@ -339,6 +342,7 @@ class ImageInfo:
        inline: PdfInlineImage | None = None,
        shorthand=None,
    ):
+        """Initialize an ImageInfo."""
        self._name = str(name)
        self._shorthand = shorthand

@@ -405,45 +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}>"
@@ -451,8 +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
@@ -460,7 +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
@@ -471,7 +491,6 @@ 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']
@@ -488,14 +507,13 @@ def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
 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
@@ -512,7 +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.

@@ -525,7 +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
@@ -546,7 +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.

@@ -563,7 +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':
@@ -595,8 +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
@@ -608,10 +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]

@@ -624,7 +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.
    """
@@ -740,6 +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
@@ -816,40 +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
@@ -860,10 +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:
@@ -883,22 +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}" '
@@ -910,7 +951,7 @@ DEFAULT_EXECUTOR = SerialExecutor()


 class PdfInfo:
-    """Get summary information about a PDF"""
+    """Get summary information about a PDF."""

    def __init__(
        self,
@@ -918,10 +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)
@@ -948,42 +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

@@ -29,12 +29,16 @@ original_pdfsimplefont_init = PDFSimpleFont.__init__


 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
    if not self.unicode_map and 'Encoding' not in spec:
        self.cid2unicode = {}
    return
@@ -48,6 +52,13 @@ PDFSimpleFont.__init__ = pdfsimplefont__init__


 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
@@ -55,15 +66,27 @@ def pdftype3font__pscript5_get_height(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):
+    """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',
@@ -96,6 +119,7 @@ class LTStateAwareChar(LTChar):
        graphicstate,
        textstate,
    ):
+        """Initialize."""
        super().__init__(
            matrix,
            font,
@@ -111,7 +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
@@ -129,11 +153,13 @@ 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 a string representation of this object."""
        return (
            f"<{self.__class__.__name__} "
            f"{bbox2str(self.bbox)} "
@@ -146,19 +172,22 @@ class LTStateAwareChar(LTChar):


 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:
@@ -167,12 +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))
@@ -197,17 +228,21 @@ 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)
    disable_boxes_flow = None
    dev = TextPositionTracker(
@@ -248,6 +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
@@ -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.
@@ -197,6 +203,7 @@ def rasterize_pdf_page(
    page_dpi: Resolution | None,
    rotation: int | None,
    filter_vector: bool,
+    stop_on_soft_error: bool,
 ) -> Path:
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units.

@@ -207,17 +214,26 @@ def rasterize_pdf_page(
    Args:
        input_file: The PDF to rasterize.
        output_file: The desired name of the rasterized image.
-        raster_device: Type of image to produce at output_file
-        raster_dpi: Resolution at which to rasterize page
-        pageno: Page number to rasterize (beginning at page 1)
-        page_dpi: Resolution, overriding output image DPI
-        rotation: Cardinal angle, clockwise, to rotate page
-        filter_vector: If True, remove vector graphics objects
+        raster_device: Type of image to produce at output_file.
+        raster_dpi: Resolution in dots per inch at which to rasterize page.
+        pageno: Page number to rasterize (beginning at page 1).
+        page_dpi: Resolution, overriding output image DPI.
+        rotation: Cardinal angle, clockwise, to rotate page.
+        filter_vector: If True, remove vector graphics objects.
+        stop_on_soft_error: If there is an "soft error" such that PDF page image
+            generation can proceed, but may visually differ from the original,
+            the implementer of this hook should raise a detailed exception. If
+            ``False``, continue processing and report by logging it. If the hook
+            cannot proceed, it should always raise an exception, regardless of
+            this setting. One "soft error" would be a missing font that is
+            required to properly rasterize the PDF.
+
    Returns:
        Path: output_file if successful
    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 +244,32 @@ 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 +294,7 @@ 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.
@@ -281,6 +306,8 @@ def filter_page_image(page: PageContext, image_filename: Path) -> 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>`.
    """
@@ -323,6 +350,8 @@ 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>`.
    """
@@ -381,7 +410,8 @@ 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
@@ -413,6 +443,9 @@ 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.
        """


@@ -437,6 +470,7 @@ def generate_pdfa(
    pdf_version: str,
    pdfa_part: str,
    progressbar_class,
+    stop_on_soft_error: bool,
 ) -> Path:
    """Generate a PDF/A.

@@ -467,6 +501,12 @@ def generate_pdfa(
            and the name of the work units ("page"). Then ``instance.update()``
            will be called when a work unit is completed. If ``None``, no
            progress information is reported.
+        stop_on_soft_error: If there is an "soft error" such that PDF/A generation
+            can proceed and produce a valid PDF/A, but output may be invalid or
+            may not visually resemble the original, the implementer of this hook
+            should raise a detailed exception. If ``False``, continue processing
+            and report by logging it. If the hook cannot proceed, it should always
+            raise an exception, regardless of this setting.

    Returns:
        Path: If successful, the hook should return ``output_file``.
@@ -474,7 +514,7 @@ def generate_pdfa(
    Note:
        This is a :ref:`firstresult hook<firstresult>`.

-    See also:
+    See Also:
        https://github.com/tqdm/tqdm
    """

@@ -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
@@ -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

@@ -34,20 +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)

@@ -113,8 +118,6 @@ def run_polling_stderr(
 def _fix_process_args(
    args: Args, env: OsEnviron | None, kwargs
 ) -> tuple[Args, OsEnviron, logging.Logger, bool]:
-    assert 'universal_newlines' not in kwargs, "Use text= instead of universal_newlines"
-
    if not env:
        env = os.environ

@@ -141,7 +144,7 @@ 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.
@@ -323,7 +326,6 @@ 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:
        found_version = version_checker()
    except (CalledProcessError, FileNotFoundError) as e:
@@ -32,7 +32,7 @@ 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__)
@@ -169,8 +169,7 @@ SHIMS = [


 def fix_windows_args(program: str, args, env):
-    """Adjust our desired program and command line arguments for use on Windows"""
-
+    """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'):
@@ -188,7 +187,7 @@ def fix_windows_args(program: str, args, env):


 def unique_everseen(iterable: Iterable[T], key: Callable[[T], Tkey]) -> Iterator[T]:
-    "List unique elements, preserving order."
+    """List unique elements, preserving order."""
    # unique_everseen('AAAABBBCCDAABBB') --> A B C D
    # unique_everseen('ABBCcAD', str.lower) --> A B C D
    seen: set[Tkey] = set()
@@ -1,4 +1,6 @@
 # SPDX-FileCopyrightText: 2022 James R. Barlow
 # SPDX-License-Identifier: MPL-2.0

+"""Tests."""
+
 from __future__ import annotations
@@ -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

@@ -71,10 +69,13 @@ 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'


@@ -110,7 +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
    ]
@@ -128,7 +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]
@@ -31,6 +31,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
            pdf_version=pdf_version,
            pdfa_part=pdfa_part,
            progressbar_class=None,
+            stop_on_soft_error=True,
        )
        mock.assert_called_once()
    return output_file
@@ -33,6 +33,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
            pdf_version=pdf_version,
            pdfa_part=pdfa_part,
            progressbar_class=None,
+            stop_on_soft_error=True,
        )
        mock.assert_called()
        return output_file
@@ -39,6 +39,7 @@ def rasterize_pdf_page(
            page_dpi=page_dpi,
            rotation=rotation,
            filter_vector=filter_vector,
+            stop_on_soft_error=True,
        )
        mock.assert_called()
        return output_file
@@ -0,0 +1,47 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+from __future__ import annotations
+
+from pathlib import Path
+from subprocess import CalledProcessError
+from unittest.mock import patch
+
+from ocrmypdf import hookimpl
+from ocrmypdf.builtin_plugins import ghostscript
+from ocrmypdf.subprocess import run
+
+
+def fail_if_stoponerror(args, **kwargs):
+    if '-dPDFSTOPONERROR' in args:
+        raise CalledProcessError(1, 'gs', output=b"", stderr=b"PDF STOP ON ERROR")
+    return run(args, **kwargs)
+
+
+@hookimpl
+def rasterize_pdf_page(
+    input_file,
+    output_file,
+    raster_device,
+    raster_dpi,
+    pageno,
+    page_dpi,
+    rotation,
+    filter_vector,
+    stop_on_soft_error,
+) -> Path:
+    with patch('ocrmypdf._exec.ghostscript.run') as mock:
+        mock.side_effect = fail_if_stoponerror
+        ghostscript.rasterize_pdf_page(
+            input_file=input_file,
+            output_file=output_file,
+            raster_device=raster_device,
+            raster_dpi=raster_dpi,
+            pageno=pageno,
+            page_dpi=page_dpi,
+            rotation=rotation,
+            filter_vector=filter_vector,
+            stop_on_soft_error=stop_on_soft_error,
+        )
+        mock.assert_called()
+        return output_file
@@ -28,6 +28,7 @@ def generate_pdfa(pdf_pages, pdfmark, output_file, compression, pdf_version, pdf
            pdf_version=pdf_version,
            pdfa_part=pdfa_part,
            progressbar_class=None,
+            stop_on_soft_error=True,
        )
        mock.assert_called()
        return output_file
@@ -0,0 +1,44 @@
+# SPDX-FileCopyrightText: 2022 James R. Barlow
+# SPDX-License-Identifier: MIT
+
+from __future__ import annotations
+
+from pathlib import Path
+from subprocess import CalledProcessError
+from unittest.mock import patch
+
+from ocrmypdf import hookimpl
+from ocrmypdf.builtin_plugins import ghostscript
+from ocrmypdf.subprocess import run_polling_stderr
+
+
+def fail_if_stoponerror(args, **kwargs):
+    if '-dPDFSTOPONERROR' in args:
+        raise CalledProcessError(1, 'gs', output=b"", stderr=b"PDF STOP ON ERROR")
+    return run_polling_stderr(args, **kwargs)
+
+
+@hookimpl
+def generate_pdfa(
+    pdf_pages,
+    pdfmark,
+    output_file,
+    compression,
+    pdf_version,
+    pdfa_part,
+    stop_on_soft_error,
+):
+    with patch('ocrmypdf._exec.ghostscript.run_polling_stderr') as mock:
+        mock.side_effect = fail_if_stoponerror
+        ghostscript.generate_pdfa(
+            pdf_pages=pdf_pages,
+            pdfmark=pdfmark,
+            output_file=output_file,
+            compression=compression,
+            pdf_version=pdf_version,
+            pdfa_part=pdfa_part,
+            progressbar_class=None,
+            stop_on_soft_error=stop_on_soft_error,
+        )
+        mock.assert_called()
+        return output_file
@@ -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
@@ -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
@@ -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.
@@ -28,13 +28,15 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
  <title></title>
  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  <meta name='ocr-system' content='tesseract 4.1.1' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+  <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>
@@ -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.

@@ -26,13 +26,15 @@ HOCR_TEMPLATE = '''<?xml version="1.0" encoding="UTF-8"?>
  <title></title>
  <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  <meta name='ocr-system' content='tesseract 4.1.1' />
-  <meta name='ocr-capabilities' content='ocr_page ocr_carea ocr_par ocr_line ocrx_word'/>
+  <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>
@@ -0,0 +1,115 @@
+%PDF-1.3
+%¿÷¢þ
+1 0 obj
+<< /Pages 2 0 R /Type /Catalog >>
+endobj
+2 0 obj
+<< /Count 1 /Kids [ 3 0 R ] /Type /Pages >>
+endobj
+3 0 obj
+<< /MediaBox [ 0 0 720 720 ] /Parent 2 0 R /Resources << >> /Type /Page >>
+endobj
+xref
+0 4
+0000000000 65535 f 
+0000000015 00000 n 
+0000000064 00000 n 
+0000000123 00000 n 
+trailer << /Root 1 0 R /Size 4 /ID [<52bba3c78160d0c6e851b59110e5d076><52bba3c78160d0c6e851b59110e5d076>] >>
+startxref
+213
+%%EOF
+%BeginExifToolUpdate
+1 0 obj
+<<
+/Pages 2 0 R
+/Type /Catalog
+/Metadata 5 0 R
+>>
+endobj
+4 0 obj
+<<
+/Author (yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp)
+/Keywords (s9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh)
+/Subject (t49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr)
+/Title (NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd)
+>>
+endobj
+5 0 obj
+<<
+/Type /Metadata
+/Subtype /XML
+/Length 3232
+>>
+stream
+<?xpacket begin='ï»¿' id='W5M0MpCehiHzreSzNTczkc9d'?>
+<x:xmpmeta xmlns:x='adobe:ns:meta/' x:xmptk='Image::ExifTool 12.60'>
+<rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>
+
+ <rdf:Description rdf:about=''
+  xmlns:dc='http://purl.org/dc/elements/1.1/'>
+  <dc:subject>
+   <rdf:Bag>
+    <rdf:li>t49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr</rdf:li>
+   </rdf:Bag>
+  </dc:subject>
+  <dc:title>
+   <rdf:Alt>
+    <rdf:li xml:lang='x-default'>NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd</rdf:li>
+   </rdf:Alt>
+  </dc:title>
+ </rdf:Description>
+
+ <rdf:Description rdf:about=''
+  xmlns:pdf='http://ns.adobe.com/pdf/1.3/'>
+  <pdf:Author>yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp</pdf:Author>
+  <pdf:Keywords>s9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh</pdf:Keywords>
+ </rdf:Description>
+</rdf:RDF>
+</x:xmpmeta>
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+                                                                                                    
+<?xpacket end='w'?>
+endstream
+endobj
+xref
+0 2
+0000000000 65535 f 
+0000000452 00000 n 
+4 2
+0000000517 00000 n 
+0000000728 00000 n 
+trailer
+<<
+/Root 1 0 R
+/Size 6
+/ID [ <52bba3c78160d0c6e851b59110e5d076> <54bba3c78160d0c6e851b59110e5d076> ]
+/Info 4 0 R
+/Prev 213
+>>
+%EndExifToolUpdate 431
+startxref
+4043
+%%EOF
@@ -3,8 +3,6 @@

 from __future__ import annotations

-import pytest
-
 from ocrmypdf.helpers import check_pdf


@@ -4,7 +4,7 @@
 from __future__ import annotations

 import os
-from subprocess import PIPE, run
+from subprocess import run

 import pytest

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

 import pikepdf
-import pytest

 import ocrmypdf

@@ -17,6 +17,7 @@ from ocrmypdf import helpers
 from .conftest import running_in_docker

 needs_symlink = pytest.mark.skipif(os.name == 'nt', reason='needs posix symlink')
+windows_only = pytest.mark.skipif(os.name != 'nt', reason="Windows test")


 class TestSafeSymlink:
@@ -93,7 +94,7 @@ class TestFileIsWritable:
        assert not helpers.is_file_writable(pathmock)


-@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+@windows_only
 def test_gs_install_locations():
    # pylint: disable=import-outside-toplevel
    from ocrmypdf.subprocess._windows import _gs_version_in_path_key
@@ -104,7 +105,7 @@ def test_gs_install_locations():
    )


-@pytest.mark.skipif(os.name != 'nt', reason="Windows test")
+@windows_only
 def test_shim_paths(tmp_path):
    # pylint: disable=import-outside-toplevel
    from ocrmypdf.subprocess._windows import shim_env_path
@@ -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)
@@ -5,8 +5,6 @@ from __future__ import annotations

 import logging

-import pytest
-
 from ocrmypdf._sync import configure_debug_logging


@@ -446,7 +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,
@@ -22,16 +22,9 @@ from ocrmypdf.pdfinfo import PdfInfo

 from .conftest import check_ocrmypdf, run_ocrmypdf

-try:
-    import fitz
-except ImportError:
-    fitz = None
-

@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,
@@ -40,14 +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'])
@@ -71,23 +63,64 @@ 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
+
+@pytest.mark.parametrize('output_type', ['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'])
+@pytest.mark.parametrize('field', ['title', 'author', 'subject', 'keywords'])
+def test_unset_metadata(output_type, field, resources, outpdf):
+    input_file = resources / 'meta.pdf'
+
+    # magic strings contained in the input pdf metadata
+    meta = {
+        'title': b'NFY5f7Ft2DWMkxLhXwxvFf7eWR2KeK3vEDcd',
+        'author': b'yXaryipxyRk9dVjWjSSaVaNCKeLRgEVzPRMp',
+        'subject': b't49vimctvnuH7ZeAjAkv52ACvWFjcnm5MPJr',
+        'keywords': b's9EeALwUg7urA7fnnhm5EtUyC54sW2WPUzqh'}
+
+    p = run_ocrmypdf(
+        input_file,
+        outpdf,
+        f'--{field}',
+        '',
+        '--output-type',
+        output_type,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+    )
+
+    assert p.returncode == ExitCode.ok, p.stderr
+
+    # We mainly want to ensure that when '' is passed, the corresponding
+    # metadata is unset in the output pdf. Since metedata is not compressed,
+    # the best way to gaurentee the metadata of interest didn't carry
+    # forward is to just check to ensure the corresponding magic string
+    # isn't contained anywhere in the output pdf. We'll also check to ensure
+    # it's in the input pdf and that any values not unset are still in the
+    # output pdf.
+    with open(input_file, 'rb') as before, open(outpdf, 'rb') as after:
+        before_data = before.read()
+        after_data = after.read()
+
+    for k, v in meta.items():
+        assert v in before_data
+        if k == field:
+            assert v not in after_data
+        else:
+            assert v in after_data


 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'
@@ -107,10 +140,10 @@ 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()

@@ -148,23 +181,24 @@ 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
@@ -231,17 +265,6 @@ 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,
@@ -292,10 +315,9 @@ 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):
@@ -313,10 +335,10 @@ 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([])
@@ -372,7 +394,15 @@ def test_malformed_docinfo(caplog, resources, outdir):
        pike.save(outdir / 'layers.rendered.pdf', fix_metadata_version=False)

    options = get_parser().parse_args(
-        args=['-j', '1', '--output-type', 'pdfa-2', 'a.pdf', 'b.pdf']
+        args=[
+            '-j',
+            '1',
+            '--continue-on-soft-render-error',
+            '--output-type',
+            'pdfa-2',
+            'a.pdf',
+            'b.pdf',
+        ]
    )
    pdfinfo = PdfInfo(outdir / 'layers.rendered.pdf')
    context = PdfContext(
@@ -100,14 +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
@@ -134,9 +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
@@ -204,3 +204,11 @@ def test_group3(resources, outdir):
        assert (
            opt.extract_image_filter(pdf, outdir, im, im.objgen[0]) is None
        ), "Group 3 should be disallowed"
+
+
+def test_find_formx(resources, outdir):
+    with pikepdf.open(resources / 'formxobject.pdf') as pdf:
+        working, pagenos = opt._find_image_xrefs(pdf)
+        assert len(working) == 1
+        xref = next(iter(working))
+        assert pagenos[xref] == 0
@@ -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)
@@ -3,8 +3,6 @@

 from __future__ import annotations

-import pytest
-
 from ocrmypdf import quality as qual


@@ -153,13 +153,14 @@ def test_autorotate_threshold(threshold, op, comparison_threshold, resources, ou


 def test_rotated_skew_timeout(resources, outpdf):
-    """This document contains an image that is rotated 90 into place with a
+    """Check rotated skew timeout.
+
+    This document contains an image that is rotated 90 into place with a
    /Rotate tag and intentionally skewed by altering the transformation matrix.

    This tests for a bug where the combination of preprocessing and a tesseract
    timeout produced a page whose dimensions did not match the original's.
    """
-
    input_file = resources / 'rotated_skew.pdf'
    in_pageinfo = PdfInfo(input_file)[0]

@@ -190,8 +191,7 @@ def test_rotated_skew_timeout(resources, outpdf):
    ), "Expected page rotation to be baked in"


-@pytest.mark.xfail(reason="tesseract timeout blocks tesseract based deskew")
-def test_rotate_deskew_timeout(resources, outdir):
+def test_rotate_deskew_ocr_timeout(resources, outdir):
    check_ocrmypdf(
        resources / 'rotated_skew.pdf',
        outdir / 'deskewed.pdf',
@@ -237,11 +237,11 @@ def test_rotate_page_level(image_angle, page_angle, resources, outdir):
            **IMG2PDF_KWARGS,
        )
        mempdf.seek(0)
-        pike = pikepdf.open(mempdf)
-        pike.pages[0].Rotate = page_angle
-        target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
-        pike.save(target)
-        return target
+        with pikepdf.open(mempdf) as pdf:
+            pdf.pages[0].Rotate = page_angle
+            target = outdir / f'{prefix}_{image_angle}_{page_angle}.pdf'
+            pdf.save(target)
+            return target

    reference = make_rotate_test('ref', 0, 0)
    test = make_rotate_test('test', image_angle, page_angle)
@@ -275,6 +275,7 @@ def test_rasterize_rotates(resources, tmp_path):
        pageno=1,
        rotation=90,
        filter_vector=False,
+        stop_on_soft_error=True,
    )
    with Image.open(img) as im:
        assert im.size == (83, 200), "Image not rotated"
@@ -289,6 +290,7 @@ def test_rasterize_rotates(resources, tmp_path):
        pageno=1,
        rotation=180,
        filter_vector=False,
+        stop_on_soft_error=True,
    )
    assert Image.open(img).size == (200, 83), "Image not rotated"

@@ -0,0 +1,63 @@
+# SPDX-FileCopyrightText: 2023 James R. Barlow
+# SPDX-License-Identifier: MPL-2.0
+
+from __future__ import annotations
+
+import os
+
+import pytest
+
+from ocrmypdf.exceptions import ExitCode
+
+from .conftest import run_ocrmypdf
+
+
+def test_raster_continue_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--continue-on-soft-render-error',
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_raster_soft_error.py',
+    )
+    assert p.returncode == ExitCode.ok
+
+
+def test_raster_stop_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_raster_soft_error.py',
+    )
+    assert p.returncode == ExitCode.child_process_error
+
+
+def test_render_continue_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--continue-on-soft-render-error',
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_render_soft_error.py',
+    )
+    assert p.returncode == ExitCode.ok
+
+
+@pytest.mark.skipif(os.name == 'nt', reason='Ghostscript on Windows errors out')
+def test_render_stop_on_soft_error(resources, outpdf):
+    p = run_ocrmypdf(
+        resources / 'francais.pdf',
+        outpdf,
+        '--plugin',
+        'tests/plugins/tesseract_noop.py',
+        '--plugin',
+        'tests/plugins/gs_render_soft_error.py',
+    )
+    assert p.returncode == ExitCode.child_process_error
@@ -4,13 +4,10 @@
 from __future__ import annotations

 import os
-import sys
-from pathlib import Path
-from subprocess import DEVNULL, PIPE, Popen, run
+from subprocess import DEVNULL, PIPE, run

 import pytest

-from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.helpers import check_pdf

 from .conftest import run_ocrmypdf
@@ -8,14 +8,13 @@ from os import fspath
 from unittest.mock import patch

 import pytest
-from PIL import Image

 from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError

-from .conftest import check_ocrmypdf, have_unpaper, ocrmypdf_exec, run_ocrmypdf
+from .conftest import check_ocrmypdf, have_unpaper, run_ocrmypdf

 # pylint: disable=redefined-outer-name

@@ -20,18 +20,13 @@ def poster(resources):
    return resources / 'poster.pdf'


-def test_userunit_ghostscript_fails(poster, no_outpdf, caplog):
-    result = run_ocrmypdf_api(poster, no_outpdf, '--output-type=pdfa')
-    assert result == ExitCode.input_file
-    assert 'not supported by Ghostscript' in caplog.text
-
-
-def test_userunit_pdf_passes(poster, outpdf):
+@pytest.mark.parametrize("mode", ['pdf', 'pdfa'])
+def test_userunit_pdf_passes(mode, poster, outpdf):
    before = PdfInfo(poster)
    check_ocrmypdf(
        poster,
        outpdf,
-        '--output-type=pdf',
+        f'--output-type={mode}',
        '--plugin',
        'tests/plugins/tesseract_cache.py',
    )
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
James R. Barlow	7c38c71794	gh-action-pypi-publish doesn't have a main - use release/v1	2023-06-20 03:11:46 -07:00
James R. Barlow	a80e7a127b	Fix some references to master not renamed to main	2023-06-20 01:37:26 -07:00
James R. Barlow	cf3309555f	Merge branch 'main' of github.com:ocrmypdf/OCRmyPDF	2023-06-20 01:12:53 -07:00
James R. Barlow	f80dd0d86a	v14.3.0 release notes	2023-06-20 01:12:45 -07:00
James R. Barlow	1ba2bce486	Merge branch 'docs'	2023-06-20 01:08:09 -07:00
f-hansen GitHub Frederick D. Hansen	050dd1f5a8	Allow title, subject, author, and keywords to be unset with an empty string argument (#1117 ) Co-authored-by: Frederick D. Hansen <frederick.hansen@gmail.com>	2023-06-20 01:07:23 -07:00
James R. Barlow	e44a57aec0	Try a screencast/terminal demo	2023-06-20 00:48:42 -07:00
James R. Barlow	d94d2671c3	Merge branch 'abwiersma-fix_random_ordering_languages'	2023-06-19 23:27:03 -07:00
James R. Barlow	5124daa79f	Fix test failures from preceding	2023-06-19 23:25:31 -07:00
James R. Barlow	7293847da7	Merge branch 'fix_random_ordering_languages' of github.com:abwiersma/OCRmyPDF into abwiersma-fix_random_ordering_languages	2023-06-19 23:21:04 -07:00
Abe	59fd0ac587	Fix randomly ordered languages from set()	2023-06-16 22:14:40 +02:00
James R. Barlow	90619b308c	pipeline: improve documentation	2023-06-12 19:50:23 -07:00
James R. Barlow	d0d49ce989	docs: Prefer long arguments	2023-06-12 01:00:01 -07:00
James R. Barlow	bf0224faa4	Remove final bits of isort	2023-06-11 16:44:09 -07:00
James R. Barlow	ae2f8ed8f1	pipeline: describe page/canvas DPI	2023-06-11 13:40:14 -07:00
James R. Barlow	14ac9b0560	docs: some reorganizing	2023-06-11 13:37:53 -07:00
James R. Barlow	dbe6148d41	Update release notes Closes #1083 Closes #1101	2023-06-03 00:27:42 -07:00
James R. Barlow	36d4c2dbbc	Merge commit '6eadd65dfba3f983702087605d582f880efc020b'	2023-06-03 00:23:18 -07:00
James R. Barlow	adbffb7bd9	Merge branch 'feature/soft-error'	2023-06-03 00:23:10 -07:00
James R. Barlow	05ecb6ca46	Resolve Windows errors with -dPDFSTOPONERROR	2023-06-02 02:48:38 -07:00
James R. Barlow	0a7b60cda5	Fix error on metadata block	2023-06-02 02:47:41 -07:00
James R. Barlow	5f211ecf6f	Add test cases for soft errors	2023-06-02 02:47:41 -07:00
James R. Barlow	417ee067a2	Remove obsolete universal_newlines check	2023-06-02 02:47:41 -07:00
James R. Barlow	c4649dabef	Clarify optimization ratio Fixes #1070	2023-06-02 01:34:07 -07:00
James R. Barlow	6eadd65dfb	Log deskew angle Closes #1101	2023-06-02 01:12:49 -07:00
James R. Barlow	e8ed510543	Add stop on soft render errors and option to override	2023-06-01 23:49:34 -07:00
James R. Barlow	22d35c199d	Add Windows package manager to list	2023-06-01 22:57:31 -07:00
James R. Barlow	5a82ad63c9	Modernize issue templates	2023-06-01 22:55:33 -07:00
James R. Barlow	4769a6c50b	Merge branches 'master' and 'master' of github.com:ocrmypdf/OCRmyPDF	2023-06-01 16:53:25 -07:00
jbarlow83andGitHub	9004009adc	Create bug-report-general.yml	2023-06-01 16:52:08 -07:00
James R. Barlow	11221f9912	Improve rasterization by including more fonts	2023-05-23 13:24:09 -07:00
James R. Barlow	177349cc84	v14.2.1 release notes	2023-05-23 13:21:46 -07:00
James R. Barlow	070c9772ce	Add test to confirm we can find formx optimizable images	2023-05-23 00:33:54 -07:00
James R. Barlow	1bc09045a5	optimize: Add recursion into Form XObjects	2023-05-23 00:07:15 -07:00
James R. Barlow	e46a18dd2f	Refactor searching for optimizable images	2023-05-22 23:42:10 -07:00
James R. Barlow	c64871c2ed	pyproject: Make classifiers more generic	2023-05-22 23:37:42 -07:00
James R. Barlow	de909fb99a	Docker arm64 needs to build pycairo; add its dependencies	2023-05-10 01:31:31 -07:00
James R. Barlow	731b2fc477	Fix interaction with old Python and singledispatch and typing	2023-05-10 00:15:34 -07:00
James R. Barlow	214f6ec759	v14.2.0 release notes	2023-05-09 23:32:57 -07:00
James R. Barlow	080aa4dbd1	imageops: fix rare assert failure	2023-05-09 23:27:08 -07:00
James R. Barlow	7af5dcd4a4	Improve directions about install other languages	2023-05-05 13:35:27 -07:00
James R. Barlow	fe9f52fbe7	Remove Ghostscript UserUnit warning All supported Ghostscript versions have proper UserUnit support.	2023-04-29 00:42:38 -07:00
James R. Barlow	fcbdeb8dbe	Fix resampling attributeerror when Pillow < 9.1.0	2023-04-25 15:17:45 -07:00
James R. Barlow	cb251a8d03	Merge branches 'feature/better-imageops' and 'feature/cleanup-fitz'	2023-04-16 01:41:46 -07:00
James R. Barlow	3731fdfd72	Add --tesseract-downsample-above X	2023-04-16 01:41:19 -07:00
James R. Barlow	b2e6a6431e	Tidy use of pikepdf.open without with	2023-04-15 20:17:44 -07:00
James R. Barlow	9ff1e56bf6	Tidy test_metadata - importorskip idiom	2023-04-15 17:56:13 -07:00
James R. Barlow	2b30f74fce	Improve imageops Fix issues and add better tests. Require hypothesis.	2023-04-15 17:48:33 -07:00
James R. Barlow	10f4c48e0b	Fix mypy errors	2023-04-14 13:49:14 -07:00
James R. Barlow	37d5c086bb	Fix things not caught by ruff	2023-04-14 13:44:47 -07:00
James R. Barlow	91830627e5	v14.1.0	2023-04-14 13:11:10 -07:00
James R. Barlow	f2fc37b257	Merge feature to downsample very large images	2023-04-14 13:09:15 -07:00
James R. Barlow	a99e40fa84	Update notes about ocrmypdf.ocr usage	2023-04-14 11:54:58 -07:00
James R. Barlow	9ce692a6f1	ruff: further fixes	2023-04-14 02:39:36 -07:00
James R. Barlow	a3c49b8f31	ruff: more lint	2023-04-14 02:19:19 -07:00
James R. Barlow	33b70be7d5	ruff: more fixes, mainly missing docstrings	2023-04-14 02:16:38 -07:00
James R. Barlow	4924b11b6b	Additional ruff fixes	2023-04-14 01:25:16 -07:00
James R. Barlow	1d0e4e7c9f	ruff: fix from __future__ and drop isort	2023-04-14 00:49:02 -07:00
James R. Barlow	9b8d14d16e	Accept most of ruff's delinting	2023-04-14 00:45:34 -07:00
James R. Barlow	b7eb93eb79	Adopt ruff and fix prelim lints	2023-04-14 00:19:17 -07:00
James R. Barlow	42c0d0f48f	Update pre-commit	2023-04-14 00:06:13 -07:00
James R. Barlow	5fce50ff7c	Change linter to ruff	2023-04-14 00:05:43 -07:00
James R. Barlow	765ed4c386	Remove older linters	2023-04-14 00:03:12 -07:00
James R. Barlow	1b2849ec0a	Add different timeout control for non-OCR This is mainly to permit the use of --tesseract-timeout 0 as a way of disabling OCR but still allowing deskew and orientation detection to work. The better solution will be introducing an explicit argument to "don't ocr my pdf", but that will take more rework.	2023-04-13 23:59:58 -07:00
James R. Barlow	4f604591b4	Convert to image size based	2023-04-13 23:49:12 -07:00
James R. Barlow	01dc8e23ff	As you were	2023-04-13 23:27:58 -07:00
James R. Barlow	b432770cfc	Add different timeout control for non-OCR This is mainly to permit the use of --tesseract-timeout 0 as a way of disabling OCR but still allowing deskew and orientation detection to work. The better solution will be introducing an explicit argument to "don't ocr my pdf", but that will take more rework.	2023-04-13 22:58:12 -07:00
James R. Barlow	5502fb8d9f	jobcontext: typo	2023-04-13 16:04:46 -07:00
林博仁(Buo-ren, Lin)andGitHub	e66922b030	Fix snap package building (#1082 ) (#1089 ) * Fix snap package building (#1082) Currently the snap package no longer contains the main Python package of OCRmyPDF due to the fact that [Snapcraft doesn't run the `pip install .` command when the setup.py isn't detected in the source tree][1]. This patch incorporates a workaround from [@cjp256 at the Snapcraft Forum][2] to generate a setup.py file from the pyproject.toml to make the package works again. [1]: [Line 143 of snapcraft/python.py at 0e2cf91 · snapcore/snapcraft · GitHub](https://github.com/snapcore/snapcraft/blob/0e2cf91/snapcraft_legacy/plugins/v2/python.py#L143) [2]: [Ian Johnson's reply in "Building a core20 python snap using pyproject.toml - snapcraft - snapcraft.io"](https://forum.snapcraft.io/t/building-a-core20-python-snap-using-pyproject-toml/22028/2) Fixes #1082. Signed-off-by: 林博仁(Buo-ren Lin) <Buo.Ren.Lin@gmail.com> * Remove unnecessary cloning of own source tree to build the snap package Signed-off-by: 林博仁(Buo-ren Lin) <Buo.Ren.Lin@gmail.com> --------- Signed-off-by: 林博仁(Buo-ren Lin) <Buo.Ren.Lin@gmail.com>	2023-04-13 00:06:19 -07:00
James R. Barlow	00e9759b16	readme: improve	2023-04-12 23:56:50 -07:00
Kian-Meng AngandGitHub	ba10c5345b	Fix typos (#1087 ) Found via `codespell -S tests,LICENSES -L flate`	2023-03-29 21:57:32 -07:00
James R. Barlow	8a5f94988a	v14.0.4 release notes	2023-03-17 14:32:04 -07:00
Frederick RobinsonandGitHub	aa73e3c69f	handle case when candidate is None (#1066 )	2023-03-17 14:27:27 -07:00
James R. Barlow	9d5fa05a00	v14.0.3	2023-02-15 12:00:26 -08:00
jbarlow83 GitHub Andrew Wood	997380e567	Avoid deleting /dev/null when run as root (#1068 ) Co-authored-by: Andrew Wood <andrew@fluidgravity.co.uk>	2023-01-31 16:20:24 -08:00
comzineandGitHub	2685f910b1	watcher: added setting RETRIES_LOADING_FILE to avoid giving up to early (#1063 )	2023-01-25 17:36:54 -08:00
Natanael ArndtandGitHub	bfcc586032	tesseract-osd is also required on fedora (#1064 )	2023-01-25 17:36:23 -08:00
Lucas LarsonandGitHub	2d77b95fd9	substitute broken link (#1057 ) (#1058 ) use `formulae.brew.sh` as seen in other repositories¹ instead of `brewformulas.org`, which has been offline since 2020,² to fix #1057. 1. https://github.com/search?type=code&q=/shields.io\/homebrew/+language:reStructuredText 2. https://gitlab.com/zedtux/brewformulas.org/issues/223#note_322019672 Signed-off-by: Lucas Larson <LucasLarson@riseup.net> Signed-off-by: Lucas Larson <LucasLarson@riseup.net>	2023-01-15 13:13:41 -08:00