v13.6.2 release notes

Bumps [docker/setup-buildx-action](https://github.com/docker/setup-buildx-action) from 1 to 2.
- [Release notes](https://github.com/docker/setup-buildx-action/releases)
- [Commits](https://github.com/docker/setup-buildx-action/compare/v1...v2)

---
updated-dependencies:
- dependency-name: docker/setup-buildx-action
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>

Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

.docker/Dockerfile

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

.git_archival.txt

@@ -1 +1,4 @@
-ref-names: $Format:%D$
+node: $Format:%H$
+node-date: $Format:%cI$
+describe-name: $Format:%(describe:tags=true)$
+ref-names: $Format:%D$

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

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

.github/ISSUE_TEMPLATE/3-feature_request.md

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

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions" # See documentation for possible values
+    directory: "/" # Location of package manifests
+    schedule:
+      interval: "weekly"

.github/workflows/build.yml

@@ -31,7 +31,7 @@ jobs:
           - os: ubuntu-latest
             python: "3.9"
           - os: ubuntu-latest
-            python: "pypy-3.7"
+            python: "pypy-3.8"
           - os: ubuntu-latest
             python: "3.9"
             tesseract5: true
@@ -41,11 +41,11 @@ jobs:
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: ${{ matrix.python }}
@@ -111,7 +111,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -129,11 +129,11 @@ jobs:
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: ${{ matrix.python }}
@@ -166,7 +166,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -184,11 +184,11 @@ jobs:
       PYTHON: ${{ matrix.python }}
 
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: ${{ matrix.python }}
@@ -196,7 +196,7 @@ jobs:
       - name: Install system packages
         run: |
           choco install --yes --no-progress --pre tesseract
-          choco install --yes --no-progress --ignore-checksums ghostscript pngquant
+          choco install --yes --no-progress --ignore-checksums ghostscript
 
       - name: Install Python packages
         run: |
@@ -208,7 +208,7 @@ jobs:
           python -m pytest --cov-report xml --cov=ocrmypdf --cov=tests/ -n0 tests/
 
       - name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
           files: ./coverage.xml
           env_vars: OS,PYTHON
@@ -217,11 +217,11 @@ jobs:
     name: Build sdist and wheels
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         name: Install Python
         with:
           python-version: "3.7"
@@ -232,7 +232,7 @@ jobs:
           python setup.py sdist
           python setup.py bdist_wheel
 
-      - uses: actions/upload-artifact@v2
+      - uses: actions/upload-artifact@v3
         with:
           path: |
             ./dist/*.whl
@@ -244,7 +244,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.event_name == 'push' && startsWith(github.event.ref, 'refs/tags/v')
     steps:
-      - uses: actions/download-artifact@v2
+      - uses: actions/download-artifact@v3
         with:
           name: artifact
           path: dist
@@ -274,22 +274,22 @@ jobs:
       - name: Set image name
         run: echo "DOCKER_IMAGE_NAME=ocrmypdf" >> $GITHUB_ENV
 
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v3
         with:
           fetch-depth: "0" # 0=all, needed for setuptools-scm to resolve version tags
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v1
+        uses: docker/login-action@v2
         with:
           username: jbarlow83
           password: ${{ secrets.DOCKERHUB_TOKEN }}
 
       - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
+        uses: docker/setup-qemu-action@v2
 
       - name: Set up Docker Buildx
         id: buildx
-        uses: docker/setup-buildx-action@v1
+        uses: docker/setup-buildx-action@v2
 
       - name: Print image tag
         run: echo "Building image ${DOCKER_REPOSITORY}/${DOCKER_IMAGE_NAME}:${DOCKER_IMAGE_TAG}"

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.1.0
+    rev: v4.3.0
     hooks:
       - id: check-case-conflict
       - id: check-merge-conflict
@@ -11,23 +11,23 @@ repos:
     rev: 5.10.1
     hooks:
       - id: isort
-        args: ["--profile", "black"]
+        args: ["--profile", "black", "-a", "from __future__ import annotations"]
   - repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 22.6.0
     hooks:
       - id: black
         language_version: python
   - repo: https://github.com/asottile/setup-cfg-fmt
-    rev: v1.20.1
+    rev: v1.20.2
     hooks:
       - id: setup-cfg-fmt
   - repo: https://github.com/asottile/pyupgrade
-    rev: v2.31.1
+    rev: v2.37.2
     hooks:
       - id: pyupgrade
         args: ["--py37-plus"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.942
+    rev: v0.971
     hooks:
       - id: mypy
         additional_dependencies:

README.md

@@ -1,9 +1,7 @@
 <img src="docs/images/logo.svg" width="240" alt="OCRmyPDF">
 
-[![Build Status](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/jbarlow83/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
+[![Build Status](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml/badge.svg)](https://github.com/ocrmypdf/OCRmyPDF/actions/workflows/build.yml) [![PyPI version][pypi]](https://pypi.org/project/ocrmypdf/) ![Homebrew version][homebrew] ![ReadTheDocs][docs] ![Python versions][pyversions]
 
-[azure]: https://dev.azure.com/jim0585/ocrmypdf/_apis/build/status/jbarlow83.OCRmyPDF?branchName=master
-[travis]: https://travis-ci.org/jbarlow83/OCRmyPDF.svg?branch=master "Travis build status"
 [pypi]: https://img.shields.io/pypi/v/ocrmypdf.svg "PyPI version"
 [homebrew]: https://img.shields.io/homebrew/v/ocrmypdf.svg "Homebrew version"
 [docs]: https://readthedocs.org/projects/ocrmypdf/badge/?version=latest "RTD"
@@ -64,7 +62,8 @@ Linux, Windows, macOS and FreeBSD are supported. Docker images are also availabl
 | Debian, Ubuntu                | ``apt install ocrmypdf``      |
 | Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
 | Fedora                        | ``dnf install ocrmypdf``      |
-| macOS                         | ``brew install ocrmypdf``     |
+| macOS (Homebrew)              | ``brew install ocrmypdf``     |
+| macOS (nix)                   | ``nix-env -i  ocrmypdf``      |
 | LinuxBrew                     | ``brew install ocrmypdf``     |
 | FreeBSD                       | ``pkg install py37-ocrmypdf`` |
 | Conda                         | ``conda install ocrmypdf``    |
@@ -106,7 +105,7 @@ ocrmypdf --help
 
 Our [documentation is served on Read the Docs](https://ocrmypdf.readthedocs.io/en/latest/index.html).
 
-Please report issues on our [GitHub issues](https://github.com/jbarlow83/OCRmyPDF/issues) page, and follow the issue template for quick response.
+Please report issues on our [GitHub issues](https://github.com/ocrmypdf/OCRmyPDF/issues) page, and follow the issue template for quick response.
 
 ## Requirements
 

debian/copyright

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

docs/advanced.rst

@@ -67,11 +67,11 @@ without modifying the PDF. This is to ensure that PDFs that were
 previously OCRed or were "born digital" rather than scanned are not
 processed.
 
-If ``--skip-text`` is issued, then no OCR will be performed on pages
+If ``--skip-text`` is issued, then no image processing or OCR will be
-that already have text. The page will be copied to the output. This may
+performed on pages that already have text. The page will be copied to
-be useful for documents that contain both "born digital" and scanned
+the output. This may be useful for documents that contain both "born
-content, or to use OCRmyPDF to normalize and convert to PDF/A regardless
+digital" and scanned content, or to use OCRmyPDF to normalize and
-of their contents.
+convert to PDF/A regardless of their contents.
 
 If ``--redo-ocr`` is issued, then a detailed text analysis is performed.
 Text is categorized as either visible or invisible. Invisible text (OCR)
@@ -223,7 +223,9 @@ The ``hocr`` renderer
 The ``hocr`` renderer works with older versions of Tesseract. The image
 layer is copied from the original PDF page if possible, avoiding
 potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF.
+preprocessing is specified, then the image layer is a new PDF. (You may
+need to disable PDF/A conversion nad optimization to eliminate all
+lossy transformations.)
 
 Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major

docs/batch.rst

@@ -36,18 +36,21 @@ Directory trees
 ===============
 
 This will walk through a directory tree and run OCR on all files in
-place, printing the output in a way that makes
+place, and printing each filename in between runs:
 
 .. code-block:: bash
 
-   find . -printf '%p' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
+   find . -printf '%p\n' -name '*.pdf' -exec ocrmypdf '{}' '{}' \;
 
-Alternatively, with a docker container (mounts a volume to the container
+Alternatively, with a Docker container and streaming the file through
-where the PDFs are stored):
+standard input and output:
 
 .. code-block:: bash
 
-   find . -printf '%p' -name '*.pdf' -exec docker run --rm -v <host dir>:<container dir> jbarlow83/ocrmypdf '<container dir>/{}' '<container dir>/{}' \;
+   find . -name '*.pdf' -print0 | xargs -0 | while read pdf; do
+       pdfout=$(mktemp)
+       docker run --rm -i jbarlow83/ocrmypdf - - <$pdf >$pdfout && cp $pdfout $pdf
+   done
 
 This only runs one ``ocrmypdf`` process at a time. This variation uses
 ``find`` to create a directory list and ``parallel`` to parallelize runs
@@ -124,7 +127,9 @@ Users may need to customize the script to meet their requirements.
 
     "OCR_INPUT_DIRECTORY", "Set input directory to monitor (recursive)"
     "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_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}'``."
@@ -144,16 +149,18 @@ The watcher service is included in the OCRmyPDF Docker image. To run it:
     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_DELETE=1 \
+        -e OCR_ON_SUCCESS_ARCHIVE=1 \
         -e OCR_DESKEW=1 \
         -e PYTHONUNBUFFERED=1 \
         -it --entrypoint python3 \
         jbarlow83/ocrmypdf \
         watcher.py
 
-This service will watch for a file that matches ``/input/\*.pdf`` and will
+This service will watch for a file that matches ``/input/\*.pdf``,
-convert it to a OCRed PDF in ``/output/``. The parameters to this image are:
+convert it to a OCRed PDF in ``/output/``, and move the processed
+original to ``/archive``. The parameters to this image are:
 
 .. csv-table:: watcher.py parameters for Docker
     :header: "Parameter", "Description"
@@ -161,10 +168,11 @@ convert it to a OCRed PDF in ``/output/``. The parameters to this image are:
 
     "``-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"
-    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1"
+    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
-    "``-e OCR_ON_SUCCESS_DELETE=1``", "Define environment variable"
+    "``-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_DESKEW=1``", "Define environment variable"
+    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
-    "``-e PYTHONBUFFERED=1``", "This will force STDOUT to be unbuffered and allow you to see messages in docker logs"
+    "``-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"
 
 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

docs/conf.py

@@ -42,7 +42,7 @@ extensions = [
 # Extension settings
 intersphinx_mapping = {'https://docs.python.org/': None}
 napoleon_use_rtype = False
-issues_github_path = "jbarlow83/OCRmyPDF"
+issues_github_path = "ocrmypdf/OCRmyPDF"
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
@@ -63,7 +63,7 @@ master_doc = 'index'
 # General information about the project.
 project = 'ocrmypdf'
 copyright = (
-    '2021, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
+    '2022, James R. Barlow. Licensed under Creative Commons Attribution-ShareAlike 4.0.'
 )
 author = 'James R. Barlow'
 

docs/cookbook.rst

@@ -200,7 +200,7 @@ might remove desirable content, especially from poor quality scans.
 
 .. warning::
 
-   ``--clean-final`` and ``-remove-background`` may leave undesirable
+   ``--clean-final`` and ``--remove-background`` may leave undesirable
    visual artifacts in some images where their algorithms have
    shortcomings. Files should be visually reviewed after using these
    options.
@@ -243,10 +243,11 @@ You can also optimize all images without performing any OCR:
 
     ocrmypdf --tesseract-timeout=0 --optimize 3 --skip-text input.pdf output.pdf
 
-Perform OCR only certain pages
+Process only certain pages
-------------------------------
+--------------------------
 
-You can ask OCRmyPDF to only apply OCR to certain pages.
+You can ask OCRmyPDF to only apply `image processing <#image-processing>`__
+and OCR to certain pages.
 
 .. code-block:: bash
 
@@ -260,10 +261,10 @@ overlap pages. OCRmyPDF does not currently account for document page numbers,
 such as an introduction section of a book that uses Roman numerals. It simply
 counts the number of virtual pieces of paper since the start.
 
-Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages in
+Regardless of the argument to ``--pages``, OCRmyPDF will optimize all pages/images
-the file and convert it to PDF/A, unless you disable those options. In this
+in the file and convert it to PDF/A, unless you disable those options. Both of these
-example, we want to OCR only the title and otherwise change the PDF as little
+steps are "whole file" operations. In this example, we want to OCR only the title
-as possible:
+and otherwise change the PDF as little as possible:
 
 .. code-block:: bash
 
@@ -339,6 +340,9 @@ levels in the GCC compiler.
         - Enables lossless optimizations, such as transcoding images to more
           efficient formats. Also compress other uncompressed objects in the
           PDF and enables the more efficient "object streams" within the PDF.
+          (If ``--jbig2-lossy`` is issued, then lossy JBIG2 optimization is used.
+          The decision to use lossy JBIG2 is separate from standard optimization
+          settings.)
     *   - ``--optimize 2``
         - All of the above, and enables lossy optimizations and color quantization.
     *   - ``--optimize 3``
@@ -359,3 +363,8 @@ fo a PDF.
     ocrmypdf --optimize 3 in.pdf out.pdf  # Make it small
 
 Some users may consider enabling lossy JBIG2. See: :ref:`jbig2-lossy`.
+
+.. note::
+
+    Image processing and PDF/A conversion can also introduce lossy transformations
+    to your PDF images, even when ``--optimize 1`` is in use.

docs/images/logo-square-256.svg

@@ -0,0 +1,239 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<svg
+   width="256"
+   height="256"
+   viewBox="0 0 256 256.00001"
+   version="1.1"
+   xml:space="preserve"
+   style="clip-rule:evenodd;fill-rule:evenodd;stroke-linecap:round;stroke-linejoin:round;stroke-miterlimit:1.5"
+   id="svg270"
+   sodipodi:docname="logo-square-256.svg"
+   inkscape:export-filename="/home/jb/src/ocrmypdf/docs/images/logo-square.png"
+   inkscape:export-xdpi="96"
+   inkscape:export-ydpi="96"
+   inkscape:version="1.1.2 (0a00cf5339, 2022-02-04)"
+   xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
+   xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
+   xmlns="http://www.w3.org/2000/svg"
+   xmlns:svg="http://www.w3.org/2000/svg"
+   xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+   xmlns:cc="http://creativecommons.org/ns#"
+   xmlns:dc="http://purl.org/dc/elements/1.1/"
+   xmlns:serif="http://www.serif.com/"><metadata
+   id="metadata276"><rdf:RDF><cc:Work
+       rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type
+         rdf:resource="http://purl.org/dc/dcmitype/StillImage" /></cc:Work></rdf:RDF></metadata><defs
+   id="defs274" /><sodipodi:namedview
+   pagecolor="#ffffff"
+   bordercolor="#666666"
+   borderopacity="1"
+   objecttolerance="10"
+   gridtolerance="10"
+   guidetolerance="10"
+   inkscape:pageopacity="0"
+   inkscape:pageshadow="2"
+   inkscape:window-width="2396"
+   inkscape:window-height="1691"
+   id="namedview272"
+   showgrid="false"
+   lock-margins="false"
+   inkscape:zoom="2.0079523"
+   inkscape:cx="189.74554"
+   inkscape:cy="54.533168"
+   inkscape:window-x="26"
+   inkscape:window-y="23"
+   inkscape:window-maximized="0"
+   inkscape:current-layer="svg270"
+   inkscape:pagecheckerboard="0"
+   width="256px"
+   fit-margin-top="0"
+   fit-margin-left="0"
+   fit-margin-right="0"
+   fit-margin-bottom="0" />
+    <g
+   id="svg"
+   transform="matrix(0.48534351,0,0,0.4057699,1.8106874,71.192214)">
+        <rect
+   x="0"
+   y="0"
+   width="520"
+   height="280"
+   style="fill:#ffffff"
+   id="rect188" />
+        <g
+   transform="matrix(1.03522,0,0,1.23823,-69.7528,-83.422)"
+   id="g267">
+            <g
+   transform="translate(243.977,20.0703)"
+   id="g218">
+                <g
+   id="Page">
+                    <g
+   transform="matrix(0.961773,0,0,1.05962,6.19811,-3.01071)"
+   id="g192">
+                        <path
+   d="m 328.5,97.682 c 0,-1.217 -0.517,-2.386 -1.444,-3.264 -7.03,-6.66 -37.614,-35.638 -44.828,-42.474 -0.977,-0.925 -2.327,-1.448 -3.738,-1.448 -13.997,0 -90.407,0 -111.151,0 -2.871,0 -5.198,2.113 -5.198,4.718 0,27.837 0,170.351 0,198.186 0,2.605 2.327,4.717 5.197,4.717 24.904,0 131.821,0 156.2,0 2.74,0 4.962,-2.016 4.962,-4.504 0,-24.345 0,-139.717 0,-155.931 z"
+   style="fill:#fdfdfd;stroke:#333333;stroke-width:3.95px"
+   id="path190" />
+                    </g>
+                    <g
+   id="Dog-ear"
+   serif:id="Dog ear"
+   transform="translate(-4,2)">
+                        <path
+   d="m 277.072,48.496 v 45.352 c 0,1.324 0.526,2.593 1.462,3.529 0.936,0.936 2.205,1.462 3.529,1.462 12.485,0 44.078,0 44.078,0"
+   style="fill:#f5f5f5;stroke:#333333;stroke-width:4px"
+   id="path194" />
+                    </g>
+                </g>
+                <g
+   transform="translate(-29.6816,-0.395178)"
+   id="g216">
+                    <g
+   transform="matrix(1.00243,0,0,1.11818,-144.72,-8.80181)"
+   id="g200">
+                        <path
+   d="m 465.73,119.654 c 0,-2.049 -1.856,-3.713 -4.142,-3.713 H 310.259 c -2.286,0 -4.142,1.664 -4.142,3.713 v 63.454 c 0,2.049 1.856,3.713 4.142,3.713 h 151.329 c 2.286,0 4.142,-1.664 4.142,-3.713 z"
+   style="fill:#f80000;stroke:#ffffff;stroke-width:3.77px"
+   id="path198" />
+                    </g>
+                    <g
+   transform="matrix(1.24571,0,0,1.35864,116.812,84.3924)"
+   id="g214">
+                        <g
+   transform="matrix(64,0,0,64,42.1437,77.6203)"
+   id="g204">
+                            <path
+   d="m 0.084,0 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.05 0.053,0.034 0.079,0.09 0.079,0.168 0,0.077 -0.028,0.134 -0.085,0.17 -0.057,0.037 -0.121,0.055 -0.193,0.055 H 0.213 V 0 Z m 0.209,-0.572 h -0.08 v 0.228 h 0.082 c 0.039,0 0.07,-0.009 0.094,-0.027 0.024,-0.017 0.037,-0.045 0.04,-0.083 0,-0.044 -0.012,-0.075 -0.036,-0.092 -0.024,-0.017 -0.057,-0.026 -0.1,-0.026 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path202" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,79.7117,77.6203)"
+   id="g208">
+                            <path
+   d="M 0.332,0 H 0.084 v -0.68 h 0.252 c 0.105,0 0.182,0.032 0.233,0.095 0.051,0.063 0.076,0.144 0.076,0.241 0,0.105 -0.027,0.189 -0.082,0.251 C 0.508,-0.031 0.431,0 0.332,0 Z M 0.337,-0.57 H 0.213 v 0.461 H 0.33 c 0.055,0 0.099,-0.018 0.132,-0.054 C 0.495,-0.199 0.511,-0.259 0.511,-0.344 0.511,-0.415 0.497,-0.47 0.469,-0.51 0.441,-0.55 0.397,-0.57 0.337,-0.57 Z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path206" />
+                        </g>
+                        <g
+   transform="matrix(64,0,0,64,123.424,77.6203)"
+   id="g212">
+                            <path
+   d="M 0.405,-0.288 H 0.213 V 0 H 0.084 v -0.68 h 0.385 l 0.02,0.102 H 0.213 v 0.189 h 0.173 z"
+   style="fill:#ffffff;fill-rule:nonzero"
+   id="path210" />
+                        </g>
+                    </g>
+                </g>
+            </g>
+            <g
+   transform="matrix(1,0,0,1.52217,67.3796,10.7507)"
+   id="g222">
+                <rect
+   x="23.500999"
+   y="81.300003"
+   width="162.30499"
+   height="61.77"
+   style="fill:#b4d5ff"
+   id="rect220" />
+            </g>
+            <g
+   transform="matrix(0.967536,0,0,0.961535,5.90498,47.9703)"
+   id="g236">
+                <g
+   transform="matrix(90.4804,0,0,90.4804,82.6698,167.705)"
+   id="g226">
+                    <path
+   d="m 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.082,-0.257 0.055,-0.066 0.132,-0.1 0.231,-0.102 0.107,0 0.186,0.034 0.237,0.103 0.051,0.069 0.077,0.152 0.077,0.249 0,0.105 -0.027,0.191 -0.082,0.258 -0.055,0.067 -0.133,0.1 -0.232,0.1 C 0.264,0.014 0.185,-0.02 0.134,-0.089 0.083,-0.157 0.057,-0.24 0.057,-0.337 Z m 0.135,-0.001 c 0,0.071 0.014,0.13 0.043,0.175 0.029,0.045 0.073,0.068 0.134,0.068 0.055,0 0.098,-0.02 0.131,-0.061 0.033,-0.041 0.049,-0.103 0.049,-0.188 0,-0.071 -0.014,-0.129 -0.043,-0.174 -0.029,-0.045 -0.073,-0.068 -0.134,-0.068 -0.053,0 -0.097,0.022 -0.13,0.067 -0.033,0.045 -0.05,0.105 -0.05,0.181 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path224" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,147.906,167.705)"
+   id="g230">
+                    <path
+   d="M 0.505,-0.557 C 0.473,-0.567 0.448,-0.574 0.429,-0.579 0.41,-0.583 0.388,-0.585 0.361,-0.585 c -0.054,0 -0.096,0.022 -0.125,0.066 -0.029,0.044 -0.044,0.104 -0.044,0.181 0,0.066 0.012,0.123 0.037,0.171 0.025,0.048 0.066,0.072 0.124,0.072 0.029,0 0.056,-0.003 0.081,-0.009 0.025,-0.006 0.047,-0.013 0.068,-0.022 L 0.551,-0.03 C 0.525,-0.017 0.494,-0.006 0.457,0.002 0.42,0.01 0.388,0.014 0.36,0.014 0.254,0.014 0.177,-0.02 0.129,-0.088 0.081,-0.156 0.057,-0.239 0.057,-0.337 c 0,-0.105 0.027,-0.19 0.08,-0.257 0.053,-0.067 0.129,-0.1 0.228,-0.1 0.02,0 0.048,0.003 0.083,0.01 0.035,0.007 0.068,0.018 0.097,0.034 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path228" />
+                </g>
+                <g
+   transform="matrix(90.4804,0,0,90.4804,199.751,167.705)"
+   id="g234">
+                    <path
+   d="m 0.293,-0.572 h -0.08 v 0.208 h 0.082 c 0.039,0 0.071,-0.008 0.096,-0.024 0.025,-0.015 0.038,-0.041 0.038,-0.077 0,-0.038 -0.012,-0.065 -0.036,-0.082 -0.024,-0.017 -0.057,-0.025 -0.1,-0.025 z M 0.479,0 0.335,-0.26 C 0.328,-0.259 0.32,-0.259 0.312,-0.259 0.304,-0.258 0.296,-0.258 0.288,-0.258 H 0.213 V 0 H 0.084 v -0.68 h 0.213 c 0.074,0 0.137,0.017 0.19,0.051 0.053,0.034 0.079,0.087 0.079,0.158 0,0.042 -0.011,0.078 -0.032,0.108 -0.022,0.031 -0.05,0.054 -0.084,0.071 L 0.617,0 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path232" />
+                </g>
+            </g>
+            <g
+   transform="matrix(0.916882,0,0,1,121.475,-32.6535)"
+   id="g246">
+                <g
+   transform="matrix(86.953,0,0,86.953,152.996,241.878)"
+   id="g240">
+                    <path
+   d="M 0.479,-0.428 C 0.5,-0.451 0.527,-0.47 0.562,-0.484 c 0.034,-0.013 0.065,-0.02 0.092,-0.02 0.066,0 0.113,0.019 0.141,0.058 0.027,0.039 0.041,0.086 0.041,0.142 V 0 H 0.705 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.064,-0.024 -0.019,0 -0.038,0.005 -0.059,0.015 -0.021,0.01 -0.039,0.021 -0.056,0.034 0.001,0.007 0.001,0.013 0.002,0.02 0.001,0.007 0.001,0.013 0.001,0.02 V 0 H 0.376 v -0.298 c 0,-0.031 -0.007,-0.054 -0.022,-0.071 -0.015,-0.016 -0.036,-0.024 -0.063,-0.024 -0.017,0 -0.033,0.003 -0.05,0.01 -0.017,0.007 -0.034,0.016 -0.049,0.027 V 0 H 0.062 V -0.485 H 0.13 l 0.032,0.044 c 0.022,-0.02 0.049,-0.035 0.08,-0.047 0.031,-0.011 0.058,-0.016 0.083,-0.016 0.038,0 0.07,0.007 0.095,0.02 0.025,0.014 0.045,0.033 0.059,0.056 z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path238" />
+                </g>
+                <g
+   transform="matrix(86.953,0,0,86.953,228.906,241.878)"
+   id="g244">
+                    <path
+   d="M 0.156,0.023 0.179,-0.034 0.006,-0.467 0.14,-0.485 0.252,-0.191 0.358,-0.485 H 0.495 L 0.278,0.064 C 0.263,0.103 0.236,0.137 0.197,0.165 0.158,0.193 0.118,0.212 0.075,0.222 L 0.029,0.115 C 0.052,0.105 0.077,0.093 0.104,0.079 0.13,0.064 0.147,0.046 0.156,0.023 Z"
+   style="fill:#333333;fill-rule:nonzero"
+   id="path242" />
+                </g>
+            </g>
+            <g
+   id="Selectors"
+   transform="matrix(0.965977,0,0,0.807602,67.3796,67.3718)">
+                <g
+   id="Right-selector"
+   serif:id="Right selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,2.07044,0)"
+   id="g250">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path248" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,161.788,169.469)"
+   id="g254">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle252" />
+                    </g>
+                </g>
+                <g
+   id="Left-selector"
+   serif:id="Left selector">
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-170.092,0)"
+   id="g259">
+                        <path
+   d="M 185.806,161.156 V 67.132"
+   style="fill:none;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="path257" />
+                    </g>
+                    <g
+   transform="matrix(1.03522,0,0,1.23823,-10.3742,28.2274)"
+   id="g263">
+                        <circle
+   cx="31.523001"
+   cy="34.313999"
+   r="10.021"
+   style="fill:#4c9fff;stroke:#4c9fff;stroke-width:4px;stroke-linecap:butt"
+   id="circle261" />
+                    </g>
+                </g>
+            </g>
+        </g>
+    </g>
+</svg>

docs/installation.rst

@@ -12,21 +12,23 @@ system/platform. This version may be out of date, however.
 
 These platforms have one-liner installs:
 
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Debian, Ubuntu                | ``apt install ocrmypdf``      |
+| Debian, Ubuntu                | ``apt install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Windows Subsystem for Linux   | ``apt install ocrmypdf``      |
+| Windows Subsystem for Linux   | ``apt install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Fedora                        | ``dnf install ocrmypdf``      |
+| Fedora                        | ``dnf install ocrmypdf``                |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| macOS                         | ``brew install ocrmypdf``     |
+| macOS                         | ``brew install ocrmypdf``               |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| LinuxBrew                     | ``brew install ocrmypdf``     |
+| LinuxBrew                     | ``brew install ocrmypdf``               |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| FreeBSD                       | ``pkg install py38-ocrmypdf`` |
+| FreeBSD                       | ``pkg install textproc/py-ocrmypdf``    |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
-| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``    |
+| Conda (WSL, macOS, Linux)     | ``conda install ocrmypdf``              |
-+-------------------------------+-------------------------------+
++-------------------------------+-----------------------------------------+
+| Snap (snapcraft packaging)    | ``snap install ocrmypdf``               |
++-------------------------------+-----------------------------------------+
 
 More detailed procedures are outlined below. If you want to do a manual
 install, or install a more recent version than your platform provides, read on.
@@ -41,11 +43,11 @@ Installing on Linux
 Debian and Ubuntu 18.04 or newer
 --------------------------------
 
-.. |deb-stable| image:: https://repology.org/badge/version-for-repo/debian_stable/ocrmypdf.svg
+.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
-    :alt: Debian 9 stable ("stretch")
+    :alt: Debian 11
 
-.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
+.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
-    :alt: Debian 10 testing ("buster")
+    :alt: Debian 12
 
 .. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
     :alt: Debian unstable
@@ -56,17 +58,17 @@ Debian and Ubuntu 18.04 or newer
 .. |ubu-2004| image:: https://repology.org/badge/version-for-repo/ubuntu_20_04/ocrmypdf.svg
     :alt: Ubuntu 20.04 LTS
 
-.. |ubu-2110| image:: https://repology.org/badge/version-for-repo/ubuntu_21_10/ocrmypdf.svg
+.. |ubu-2204| image:: https://repology.org/badge/version-for-repo/ubuntu_22_04/ocrmypdf.svg
-    :alt: Ubuntu 21.10
+    :alt: Ubuntu 22.04 LTS
 
 +-----------------------------------------------+
 | **OCRmyPDF versions in Debian & Ubuntu**      |
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |deb-stable| |deb-testing| |deb-unstable|     |
+| |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
-| |ubu-1804| |ubu-2004| |ubu-2110|              |
+| |ubu-1804| |ubu-2004| |ubu-2204|              |
 +-----------------------------------------------+
 
 Users of Debian 9 ("stretch") or later, or Ubuntu 18.04 or later, including users
@@ -80,8 +82,7 @@ As indicated in the table above, Debian and Ubuntu releases may lag
 behind the latest version. If the version available for your platform is
 out of date, you could opt to install the latest version from source.
 See `Installing HEAD revision from
-sources <#installing-head-revision-from-sources>`__. Ubuntu 16.10 to 17.10
+sources <#installing-head-revision-from-sources>`__.
-inclusive also had ocrmypdf, but these versions are end of life.
 
 For full details on version availability for your platform, check the
 `Debian Package Tracker <https://tracker.debian.org/pkg/ocrmypdf>`__ or
@@ -91,19 +92,19 @@ For full details on version availability for your platform, check the
 
    OCRmyPDF for Debian and Ubuntu currently omit the JBIG2 encoder.
    OCRmyPDF works fine without it but will produce larger output files.
-   If you build jbig2enc from source, ocrmypdf 7.0.0 and later will
+   If you build jbig2enc from source, ocrmypdf will
    automatically detect it (specifically the ``jbig2`` binary) on the
    ``PATH``. To add JBIG2 encoding, see :ref:`jbig2`.
 
 Fedora
 ------
 
-.. |fedora-34| image:: https://repology.org/badge/version-for-repo/fedora_34/ocrmypdf.svg
-    :alt: Fedora 34
-
 .. |fedora-35| image:: https://repology.org/badge/version-for-repo/fedora_35/ocrmypdf.svg
     :alt: Fedora 35
 
+.. |fedora-36| image:: https://repology.org/badge/version-for-repo/fedora_36/ocrmypdf.svg
+    :alt: Fedora 36
+
 .. |fedora-rawhide| image:: https://repology.org/badge/version-for-repo/fedora_rawhide/ocrmypdf.svg
     :alt: Fedore Rawhide
 
@@ -112,7 +113,7 @@ Fedora
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |fedora-34| |fedora-35| |fedora-rawhide|      |
+| |fedora-35| |fedora-36| |fedora-rawhide|      |
 +-----------------------------------------------+
 
 Users of Fedora 29 or later may simply
@@ -138,9 +139,29 @@ from sources <#installing-head-revision-from-sources>`__.
 
 .. _ubuntu-lts-latest:
 
-Installing the latest version on Ubuntu 20.04 LTS
+Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------
 
+Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with
+``apt install ocrmypdf``. To install a more recent version for the current
+user, follow these steps:
+
+.. code-block:: bash
+
+    sudo apt-get update
+    sudo apt-get -y install ocrmypdf python3-pip
+
+    pip install --user --upgrade ocrmypdf
+
+If you get the message ``WARNING: The script ocrmypdf is installed in
+'/home/$USER/.local/bin' which is not on PATH.``, you may need to re-login
+or open a new shell, or manually add this to your user's PATH.
+
+To add JBIG2 encoding, see :ref:`jbig2`.
+
+Ubuntu 20.04 LTS
+----------------
+
 Ubuntu 20.04 includes ocrmypdf 9.6.0 - you can install that with ``apt``. To
 install a more recent version, uninstall the system-provided version of
 ocrmypdf, and install the following dependencies:
@@ -171,6 +192,8 @@ To install for the current user only:
     export PATH=$HOME/.local/bin:$PATH
     pip3 install --user ocrmypdf
 
+To add JBIG2 encoding, see :ref:`jbig2`.
+
 Ubuntu 18.04 LTS
 ----------------
 
@@ -291,46 +314,6 @@ To install OCRmyPDF for Alpine Linux:
 
     apk add ocrmypdf
 
-Mageia 7
---------
-
-There is no OS-level packaging available for Mageia, so you must install the
-dependencies:
-
-.. code-block:: bash
-
-    # As root user
-    urpmi.update -a
-    urpmi \
-        ghostscript \
-        icc-profiles-openicc \
-        jbig2dec \
-        pngquant \
-        python3-pip \
-        python3-distutils-extra \
-        python3-pkg-resources \
-        python3-reportlab \
-        qpdf \
-        tesseract \
-        tesseract-osd \
-        tesseract-eng \
-        tesseract-fra
-
-To install ocrmypdf for the system:
-
-.. code-block:: bash
-
-    # As root user
-    pip3 install ocrmypdf
-    ldconfig
-
-Or, to install for the current user only:
-
-.. code-block:: bash
-
-    export PATH=$HOME/.local/bin:$PATH
-    pip3 install --user ocrmypdf
-
 Other Linux packages
 --------------------
 
@@ -365,19 +348,6 @@ languages you can optionally install them all:
 
     brew install tesseract-lang  # Optional: Install all language packs
 
-.. note::
-
-   Users who previously installed OCRmyPDF on macOS using
-   ``pip install ocrmypdf`` should remove the pip version
-   (``pip3 uninstall ocrmypdf``) before switching to the Homebrew
-   version.
-
-.. note::
-
-   Users who previously installed OCRmyPDF from the private tap should
-   switch to the mainline version (``brew untap jbarlow83/ocrmypdf``)
-   and install from there.
-
 Manual installation on macOS
 ----------------------------
 
@@ -411,19 +381,19 @@ Update the homebrew pip:
 
 .. code-block:: bash
 
-    pip3 install --upgrade pip
+    pip install --upgrade pip
 
 You can then install OCRmyPDF from PyPI, for the current user:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
+    pip install --user ocrmypdf
 
 or system-wide:
 
 .. code-block:: bash
 
-    pip3 install ocrmypdf
+    pip install ocrmypdf
 
 The command line program should now be available:
 
@@ -485,8 +455,8 @@ to change the PATH.
 Windows Subsystem for Linux
 ---------------------------
 
-#. Install Ubuntu 20.04 for Windows Subsystem for Linux, if not already installed.
+#. Install Ubuntu 22.04 for Windows Subsystem for Linux, if not already installed.
-#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 20.04 <ubuntu-lts-latest>`.
+#. Follow the procedure to install :ref:`OCRmyPDF on Ubuntu 22.04 <ubuntu-lts-latest>`.
 #. Open the Windows command prompt and create a symlink:
 
 .. code-block:: powershell
@@ -558,16 +528,13 @@ your command prompt can run the docker "hello world" container.
 Installing on FreeBSD
 =====================
 
-.. image:: https://repology.org/badge/version-for-repo/freebsd/python:ocrmypdf.svg
+.. image:: https://repology.org/badge/version-for-repo/freebsd/ocrmypdf.svg
     :alt: FreeBSD
-    :target: https://repology.org/project/python:ocrmypdf/versions
+    :target: https://repology.org/project/ocrmypdf/versions
-
-FreeBSD 11.3, 12.0, 12.1-RELEASE and 13.0-CURRENT are supported. Other
-versions likely work but have not been tested.
 
 .. code-block:: bash
 
-    pkg install py38-ocrmypdf
+    pkg install textproc/py-ocrmypdf
 
 To install a more recent version, you could attempt to first install the system
 version with ``pkg``, then use ``pip install --user ocrmypdf``.
@@ -616,18 +583,18 @@ try:
 
 .. code-block:: bash
 
-    pip3 install --user ocrmypdf
+    pip install --user ocrmypdf
 
 You should then be able to run ``ocrmypdf --version`` and see that the
 latest version was located.
 
-Since ``pip3 install --user`` does not work correctly on some platforms,
+Since ``pip install --user`` does not work correctly on some platforms,
 notably Ubuntu 16.04 and older, and the Homebrew version of Python,
 instead use this for a system wide installation:
 
 .. code-block:: bash
 
-    pip3 install ocrmypdf
+    pip install ocrmypdf
 
 .. note::
 
@@ -643,13 +610,9 @@ OCRmyPDF currently requires these external programs and libraries to be
 installed, and must be satisfied using the operating system package
 manager. ``pip`` cannot provide them.
 
+The following versions are required:
+
 -  Python 3.7 or newer
--  Ghostscript 9.15 or newer
--  Tesseract 4.0.0-beta or newer
-
-As of ocrmypdf 7.2.1, the following versions are recommended:
-
--  Python 3.9 or newer
 -  Ghostscript 9.23 or newer
 -  Tesseract 4.0.0 or newer
 -  jbig2enc 0.29 or newer
@@ -696,7 +659,7 @@ environment:
 
 .. code-block:: bash
 
-    pip3 install git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 Or, to install in `development
 mode <https://pythonhosted.org/setuptools/setuptools.html#development-mode>`__,
@@ -704,18 +667,18 @@ allowing customization of OCRmyPDF, use the ``-e`` flag:
 
 .. code-block:: bash
 
-    pip3 install -e git+https://github.com/jbarlow83/OCRmyPDF.git
+    pip install -e git+https://github.com/ocrmypdf/OCRmyPDF.git
 
 You may find it easiest to install in a virtual environment, rather than
 system-wide:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
     python3 -m venv
     source venv/bin/activate
     cd OCRmyPDF
-    pip3 install .
+    pip install .
 
 However, ``ocrmypdf`` will only be accessible on the system PATH when
 you activate the virtual environment.
@@ -738,8 +701,8 @@ To install all of the development and test requirements:
 
 .. code-block:: bash
 
-    git clone -b master https://github.com/jbarlow83/OCRmyPDF.git
+    git clone -b master https://github.com/ocrmypdf/OCRmyPDF.git
-    python3 -m venv
+    python -m venv
     source venv/bin/activate
     cd OCRmyPDF
     pip install -e .[test]

docs/jbig2.rst

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

docs/languages.rst

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

docs/maintainers.rst

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

docs/plugins.rst

@@ -162,6 +162,11 @@ Examples
   management system.
 
 
+Suppressing or overriding other plugins
+---------------------------------------
+
+.. autofunction:: ocrmypdf.pluginspec.initialize
+
 Custom command line arguments
 -----------------------------
 
@@ -172,7 +177,7 @@ Custom command line arguments
 Execution and progress reporting
 --------------------------------
 
-.. autoclass: ocrmypdf.pluginspec.Executor
+.. autoclass:: ocrmypdf.pluginspec.Executor
     :members:
 
 .. autofunction:: ocrmypdf.pluginspec.get_logging_console
@@ -216,3 +221,10 @@ PDF/A production
 ----------------
 
 .. autofunction:: ocrmypdf.pluginspec.generate_pdfa
+
+PDF optimization
+----------------
+
+.. autofunction:: ocrmypdf.pluginspec.optimize_pdf
+
+.. autofunction:: ocrmypdf.pluginspec.is_optimization_enabled

docs/release_notes.rst

@@ -16,8 +16,81 @@ The most recent release of OCRmyPDF is |OCRmyPDF PyPI|. Any newer versions
 referred to in these notes may exist the main branch but have not been
 tagged yet.
 
+.. note::
+
+   Attention maintainers: that these release notes may be updated with information
+   about a forthcoming release that has not been tagged yet. A release is only
+   official when it's tagged and posted to PyPI.
+
 .. |OCRmyPDF PyPI| image:: https://img.shields.io/pypi/v/ocrmypdf.svg
 
+v13.6.2
+=======
+
+-  Added a shim to prevent an "error during error handling" for Python 3.7 and 3.8.
+-  Modernized some type annotations.
+-  Improved annotations on our _windows module to help IDEs and mypy figure out what
+   we're doing.
+
+v13.6.1
+=======
+
+-  Require setuptools-scm 7.0.5 to avoid possible issues with source distributions in
+   earlier versions of setuptools-scm.
+-  Suppress a spurious warning, improve tests, improve typing and other miscellany.
+
+v13.6.0
+=======
+
+-  Added a new ``initialize`` plugin hook, making it possible to suppress built-in
+   plugins more easily, among other possibilities.
+-  Fixed an issue where unpaper would exit with a "wrong stream" error, probably
+   related to images with an odd integer width. :issue:`887, 665`
+
+v13.5.0
+=======
+
+-  Added a new ``optimize_pdf`` plugin hook, making it possible to create plugins that
+   replace or enhance OCRmyPDF's PDF optimizer.
+-  Removed all max version restrictions. Our new policy is to blacklist known-bad releases
+   and only block known-bad versions of dependencies.
+-  The naming schema for object that holds all OCR text that OCRmyPDF inserts has
+   changed. This has always been an implementation detail (and remains so), but possibly,
+   someone was relying on it and would appreciate the heads-up.
+-  Cleanup.
+
+v13.4.7
+=======
+
+-  Fixed PermissionError when cleaning up temporary files in rare cases. :issue:`974`
+-  Fixed PermissionError when calling ``os.nice`` on platforms that lack it. :issue:`973`
+-  Suppressed some warnings from libxmp during tests.
+
+v13.4.6
+=======
+
+-  Convert error on corrupt ICC profiles into a warning. Thanks to @oscherler.
+
+v13.4.5
+=======
+
+-  Remove upper bound on pdfminer.six version.
+-  Documentation.
+
+v13.4.4
+=======
+
+-  Updated pdfminer.six version.
+-  Docker image changed to Ubuntu 22.04 now that it is released and provides the
+   dependencies we need. This seems more consistent than our recent change to
+   Debian.
+
+v13.4.3
+=======
+
+-  Fix error on pytest.skip() with older versions of pytest.
+-  Documentation updates.
+
 v13.4.2
 =======
 

misc/batch.py

@@ -19,8 +19,9 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
-# This script must be edited to meet your needs.
+from __future__ import annotations
 
+# This script must be edited to meet your needs.
 import logging
 import os
 import sys

misc/example_plugin.py

@@ -37,6 +37,8 @@ To use this as an API:
     )
 """
 
+from __future__ import annotations
+
 import logging
 
 from PIL import Image

misc/synology.py

@@ -19,8 +19,9 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
-# This script must be edited to meet your needs.
+from __future__ import annotations
 
+# This script must be edited to meet your needs.
 import logging
 import os
 import shutil

misc/watcher.py

@@ -20,9 +20,12 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
+from __future__ import annotations
+
 import json
 import logging
 import os
+import shutil
 import sys
 import time
 from datetime import datetime
@@ -44,8 +47,10 @@ def getenv_bool(name: str, default: str = 'False'):
 
 INPUT_DIRECTORY = os.getenv('OCR_INPUT_DIRECTORY', '/input')
 OUTPUT_DIRECTORY = os.getenv('OCR_OUTPUT_DIRECTORY', '/output')
+ARCHIVE_DIRECTORY = os.getenv('OCR_ARCHIVE_DIRECTORY', '/processed')
 OUTPUT_DIRECTORY_YEAR_MONTH = getenv_bool('OCR_OUTPUT_DIRECTORY_YEAR_MONTH')
 ON_SUCCESS_DELETE = getenv_bool('OCR_ON_SUCCESS_DELETE')
+ON_SUCCESS_ARCHIVE = getenv_bool('OCR_ON_SUCCESS_ARCHIVE')
 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'))
@@ -108,9 +113,13 @@ def execute_ocrmypdf(file_path):
         deskew=DESKEW,
         **OCR_JSON_SETTINGS,
     )
-    if exit_code == 0 and ON_SUCCESS_DELETE:
+    if exit_code == 0:
-        log.info(f'OCR is done. Deleting: {file_path}')
+        if ON_SUCCESS_DELETE:
-        file_path.unlink()
+            log.info(f'OCR is done. Deleting: {file_path}')
+            file_path.unlink()
+        elif ON_SUCCESS_ARCHIVE:
+            log.info(f'OCR is done. Archiving {file_path.name} to {ARCHIVE_DIRECTORY}')
+            shutil.move(file_path, f'{ARCHIVE_DIRECTORY}/{file_path.name}')
     else:
         log.info('OCR is done')
 
@@ -135,13 +144,16 @@ def main():
         f"Starting OCRmyPDF watcher with config:\n"
         f"Input Directory: {INPUT_DIRECTORY}\n"
         f"Output Directory: {OUTPUT_DIRECTORY}\n"
-        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}"
+        f"Output Directory Year & Month: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"Archive Directory: {ARCHIVE_DIRECTORY}"
     )
     log.debug(
         f"INPUT_DIRECTORY: {INPUT_DIRECTORY}\n"
         f"OUTPUT_DIRECTORY: {OUTPUT_DIRECTORY}\n"
         f"OUTPUT_DIRECTORY_YEAR_MONTH: {OUTPUT_DIRECTORY_YEAR_MONTH}\n"
+        f"ARCHIVE_DIRECTORY: {ARCHIVE_DIRECTORY}\n"
         f"ON_SUCCESS_DELETE: {ON_SUCCESS_DELETE}\n"
+        f"ON_SUCCESS_ARCHIVE: {ON_SUCCESS_ARCHIVE}\n"
         f"DESKEW: {DESKEW}\n"
         f"ARGS: {OCR_JSON_SETTINGS}\n"
         f"POLL_NEW_FILE_SECONDS: {POLL_NEW_FILE_SECONDS}\n"

misc/webservice.py

@@ -24,6 +24,8 @@ to emphasize that SaaS deployments should make sure they comply with
 Ghostscript's license as well as OCRmyPDF's.
 """
 
+from __future__ import annotations
+
 import os
 import shlex
 from subprocess import PIPE, run

pyproject.toml

@@ -1,14 +1,12 @@
 [build-system]
 requires = [
-  "setuptools >= 30.3.0",
+  "setuptools >= 52",
-  "wheel",
+  "setuptools_scm[toml] >= 7.0.5",
-  "setuptools_scm[toml] >= 3.4",
+  "wheel"
-  "setuptools_scm_git_archive"
 ]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools_scm]
-version_scheme = "post-release"
 
 [tool.black]
 line-length = 88
@@ -96,6 +94,12 @@ module = [
   'pdfminer.*',
   'reportlab.*',
   'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
+  'importlib_metadata'
 ]
 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"]

setup.cfg

@@ -3,7 +3,7 @@ name = ocrmypdf
 description = OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
 long_description = file: README.md
 long_description_content_type = text/markdown
-url = https://github.com/jbarlow83/OCRmyPDF
+url = https://github.com/ocrmypdf/OCRmyPDF
 author = James R. Barlow
 author_email = james@purplerock.ca
 license = MPL-2.0
@@ -39,23 +39,24 @@ keywords =
     scanning
 project_urls =
     Documentation = https://ocrmypdf.readthedocs.io/
-    Source = https://github.com/jbarlow83/ocrmypdf
+    Source = https://github.com/ocrmypdf/OCRmyPDF
-    Tracker = https://github.com/jbarlow83/ocrmypdf/issues
+    Tracker = https://github.com/ocrmypdf/OCRmyPDF/issues
 
 [options]
 packages = find:
 install_requires =
     Pillow>=8.2.0
     coloredlogs>=14.0  # strictly optional
-    img2pdf>=0.3.0,<0.5  # pure Python
+    img2pdf>=0.3.0  # pure Python
     packaging>=20
-    pdfminer.six!=20200720,>=20191110,<=20220319
+    pdfminer.six!=20200720,>=20191110
     pikepdf!=5.0.0,>=4.0.0
-    pluggy>=0.13.0,<2
+    pluggy>=0.13.0
     reportlab>=3.5.66
     tqdm>=4
     importlib-metadata>=4;python_version<'3.8'  # until Python 3.8
     importlib-resources>=5;python_version<'3.9'  # until Python 3.9
+    typing-extensions>=4;python_version<'3.10'
 python_requires = >=3.7
 include_package_data = True
 package_dir =
@@ -86,10 +87,12 @@ test =
     pytest-cov>=2.11.1
     pytest-xdist>=2.2.0
     python-xmp-toolkit==2.0.1  # also requires apt-get install libexempi3
+    types-Pillow
+    types-humanfriendly
 watcher =
-    watchdog>=1.0.2,<3
+    watchdog>=1.0.2
 webservice =
-    Flask>=1,<3
+    Flask>=1
 
 [options.package_data]
 ocrmypdf =

setup.py

@@ -4,14 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""setup.py to support older setuptools and pip."""
+
+from __future__ import annotations
 
 from setuptools import setup
 
-# Minimal setup to support older setuptools/setuptools_scm
+setup()
-setup(
-    setup_requires=[  # can be removed whenever we can drop pip 9 support
-        'setuptools_scm',  # so that version will work
-        'setuptools_scm_git_archive',  # enable version from github tarballs
-    ],
-    use_scm_version={'version_scheme': 'post-release'},
-)

snapcraft.yaml

@@ -0,0 +1,72 @@
+name: ocrmypdf
+title: OCRmyPDF
+base: core20
+version: git
+summary: OCRmyPDF adds optical character recognition (OCR) to PDFs
+description: OCRmyPDF packaged for snap
+grade: stable
+confinement: strict
+icon: docs/images/logo-square-256.svg
+license: MPL-2.0
+
+architectures: [amd64]
+
+environment:
+  TESSDATA_PREFIX: $SNAP/usr/share/tesseract-ocr/4.00/tessdata
+  GS_LIB: $SNAP/usr/share/ghostscript/9.50/Resource/Init
+  GS_FONTPATH: $SNAP/usr/share/ghostscript/9.50/Resource/Font
+  LD_LIBRARY_PATH: $SNAP/usr/lib/x86_64-linux-gnu
+
+apps:
+  ocrmypdf:
+    command: usr/bin/snapcraft-preload python3 -m ocrmypdf
+    plugs:
+      - desktop
+      - desktop-legacy
+      - wayland
+      - x11
+      - home
+      - removable-media
+
+parts:
+  snapcraft-preload:
+    source: https://github.com/sergiusens/snapcraft-preload.git
+    plugin: cmake
+    cmake-parameters:
+      - -DCMAKE_INSTALL_PREFIX=/usr -DLIBPATH=/usr/lib
+    build-packages:
+      - on amd64:
+          - gcc-multilib
+          - g++-multilib
+    stage-packages:
+      - lib32stdc++6
+
+  ocrmypdf:
+    plugin: python
+    source: https://github.com/ocrmypdf/OCRmyPDF.git
+
+    stage-packages:
+      - ghostscript
+      - icc-profiles-free
+      - liblept5
+      - libxml2
+      - pngquant
+      - tesseract-ocr-all
+      - unpaper
+      - qpdf
+      - zlib1g
+
+    python-packages:
+      - cffi
+      - pdfminer.six
+      - pikepdf
+      - Pillow
+      - pluggy
+      - reportlab
+      - setuptools
+      - tqdm
+      - pipe
+
+    override-build: |
+      snapcraftctl build
+      ln -sf ../usr/lib/libsnapcraft-preload.so $SNAPCRAFT_PART_INSTALL/lib/libsnapcraft-preload.so

src/ocrmypdf/__init__.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Adds OCR layer to PDFs."""
+
+from __future__ import annotations
 
 from pluggy import HookimplMarker as _HookimplMarker
 

src/ocrmypdf/__main__.py

@@ -5,11 +5,15 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""ocrmypdf command line entrypoint."""
+
+from __future__ import annotations
 
 import logging
 import os
 import signal
 import sys
+from contextlib import suppress
 from multiprocessing import set_start_method
 
 from ocrmypdf import __version__
@@ -34,7 +38,7 @@ def sigbus(*args):
 def run(args=None):
     _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
-    if hasattr(os, 'nice'):
+    with suppress(AttributeError, PermissionError):
         os.nice(5)
 
     verbosity = options.verbose
@@ -62,7 +66,7 @@ def run(args=None):
         log.error(e)
         return ExitCode.missing_dependency
 
-    if hasattr(signal, 'SIGBUS'):
+    with suppress(AttributeError, OSError):
         signal.signal(signal.SIGBUS, sigbus)
 
     result = run_pipeline(options=options, plugin_manager=plugin_manager)

src/ocrmypdf/_concurrent.py

@@ -4,9 +4,13 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF concurrency abstractions."""
+
+from __future__ import annotations
+
 import threading
 from abc import ABC, abstractmethod
-from typing import Callable, Iterable, Optional
+from typing import Callable, Iterable
 
 
 def _task_noop(*_args, **_kwargs):
@@ -14,6 +18,8 @@ def _task_noop(*_args, **_kwargs):
 
 
 class NullProgressBar:
+    """Progress bar API that takes no actions."""
+
     def __init__(self, **kwargs):
         pass
 
@@ -28,6 +34,8 @@ class NullProgressBar:
 
 
 class Executor(ABC):
+    """Abstract concurrent executor."""
+
     pool_lock = threading.Lock()
     pbar_class = NullProgressBar
 
@@ -41,10 +49,10 @@ class Executor(ABC):
         use_threads: bool,
         max_workers: int,
         tqdm_kwargs: dict,
-        worker_initializer: Optional[Callable] = None,
+        worker_initializer: Callable | None = None,
-        task: Optional[Callable] = None,
+        task: Callable | None = None,
-        task_arguments: Optional[Iterable] = None,
+        task_arguments: Iterable | None = None,
-        task_finished: Optional[Callable] = None,
+        task_finished: Callable | None = None,
     ) -> None:
         """
         Set up parallel execution and progress reporting.

src/ocrmypdf/_exec/__init__.py

@@ -6,3 +6,5 @@
 
 
 """Manage third party executables"""
+
+from __future__ import annotations

src/ocrmypdf/_exec/ghostscript.py

@@ -7,6 +7,8 @@
 
 """Interface to Ghostscript executable"""
 
+from __future__ import annotations
+
 import logging
 import os
 import re
@@ -14,13 +16,11 @@ import sys
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from shutil import which
 from subprocess import PIPE, CalledProcessError
-from typing import Optional
 
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
@@ -33,29 +33,18 @@ except AttributeError:
 
 log = logging.getLogger(__name__)
 
-missing_gs_error = """
----------------------------------------------------------------------
-This error normally occurs when ocrmypdf find can't Ghostscript.
-Please ensure Ghostscript is installed and its location is added to
-the system PATH environment variable.
-
-For details see:
-    https://ocrmypdf.readthedocs.io/en/latest/installation.html
----------------------------------------------------------------------
-"""
-
 # Most reliable what to get the bitness of Python interpreter, according to Python docs
-_is_64bit = sys.maxsize > 2 ** 32
+_IS_64BIT = sys.maxsize > 2**32
 
-_gswin = None
+_GSWIN = None
 if os.name == 'nt':
-    if _is_64bit:
+    if _IS_64BIT:
-        _gswin = 'gswin64c'
+        _GSWIN = 'gswin64c'
     else:
-        _gswin = 'gswin32c'
+        _GSWIN = 'gswin32c'
 
-GS = _gswin if _gswin else 'gs'
+GS = _GSWIN if _GSWIN else 'gs'
-del _gswin
+del _GSWIN
 
 
 def version():
@@ -89,8 +78,8 @@ def rasterize_pdf(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int = 1,
-    page_dpi: Optional[Resolution] = None,
+    page_dpi: Resolution | None = None,
-    rotation: Optional[int] = None,
+    rotation: int | None = None,
     filter_vector: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
@@ -115,7 +104,7 @@ def rasterize_pdf(
         + [
             '-o',
             '-',
-            '-sstdout=%stderr',
+            '-sstdout=%stderr',  # Literal %s, not string interpolation
             '-dAutoRotatePages=/None',  # Probably has no effect on raster
             '-f',
             fspath(input_file),
@@ -126,7 +115,7 @@ def rasterize_pdf(
         p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
     except CalledProcessError as e:
         log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript rasterizing failed')
+        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
     else:
         stderr = p.stderr.decode(errors='replace')
         if _gs_error_reported(stderr):
@@ -156,6 +145,8 @@ def rasterize_pdf(
 
 
 class GhostscriptFollower:
+    """Parses the output of Ghostscript and uses it to update the progress bar."""
+
     re_process = re.compile(r"Processing pages \d+ through (\d+).")
     re_page = re.compile(r"Page (\d+)")
 
@@ -251,7 +242,7 @@ def generate_pdfa(
             "-dPDFACompatibilityPolicy=1",
             "-o",
             "-",
-            "-sstdout=%stderr",
+            "-sstdout=%stderr",  # Literal %s, not string interpolation
         ]
     )
     args_gs.extend(fspath(s) for s in pdf_pages)  # Stringify Path objs

src/ocrmypdf/_exec/jbig2enc.py

@@ -7,6 +7,8 @@
 
 """Interface to jbig2 executable"""
 
+from __future__ import annotations
+
 from subprocess import PIPE
 
 from ocrmypdf.exceptions import MissingDependencyError

src/ocrmypdf/_exec/pngquant.py

@@ -7,6 +7,8 @@
 
 """Interface to pngquant executable"""
 
+from __future__ import annotations
+
 from contextlib import contextmanager
 from io import BytesIO
 from pathlib import Path

src/ocrmypdf/_exec/tesseract.py

@@ -7,13 +7,14 @@
 
 """Interface to Tesseract executable"""
 
+from __future__ import annotations
+
 import logging
 import re
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import Dict, Iterator, List, Optional
 
 from packaging.version import Version
 from PIL import Image
@@ -46,7 +47,7 @@ HOCR_TEMPLATE = """<?xml version="1.0" encoding="UTF-8"?>
 </html>
 """
 
-TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
+TESSERACT_THRESHOLDING_METHODS: dict[str, int] = {
     'auto': 0,
     'otsu': 0,
     'adaptive-otsu': 1,
@@ -55,9 +56,11 @@ TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
+    "Prepend [tesseract] to messages emitted from tesseract"
+
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
-        return '[tesseract] %s' % (msg), kwargs
+        return f'[tesseract] {msg}', kwargs
 
 
 TESSERACT_VERSION_PATTERN = r"""
@@ -105,6 +108,7 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
+    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
     _regex = re.compile(
         r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
     )
@@ -159,7 +163,7 @@ def get_languages():
     return {lang.strip() for lang in rest}
 
 
-def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
+def tess_base_args(langs: list[str], engine_mode: int | None) -> list[str]:
     args = ['tesseract']
     if langs:
         args.extend(['-l', '+'.join(langs)])
@@ -168,19 +172,19 @@ def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
     return args
 
 
-def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:
+def _parse_tesseract_output(binary_output: bytes) -> dict[str, str]:
-    def g():
+    def gen():
         for line in binary_output.decode().splitlines():
             line = line.strip()
             parts = line.split(':', maxsplit=2)
             if len(parts) == 2:
                 yield parts[0].strip(), parts[1].strip()
 
-    return {k: v for k, v in g()}
+    return dict(gen())
 
 
 def get_orientation(
-    input_file: Path, engine_mode: Optional[int], timeout: float
+    input_file: Path, engine_mode: int | None, timeout: float
 ) -> OrientationConfidence:
     args_tesseract = tess_base_args(['osd'], engine_mode) + [
         '--psm',
@@ -205,14 +209,14 @@ def get_orientation(
 
     osd = _parse_tesseract_output(p.stdout)
     angle = int(osd.get('Orientation in degrees', 0))
-    oc = OrientationConfidence(
+    orient_conf = OrientationConfidence(
         angle=angle, confidence=float(osd.get('Orientation confidence', 0))
     )
-    return oc
+    return orient_conf
 
 
 def get_deskew(
-    input_file: Path, languages: List[str], engine_mode: Optional[int], timeout: float
+    input_file: Path, languages: list[str], engine_mode: int | None, timeout: float
 ) -> float:
     """Gets angle to deskew this page, in degrees."""
     args_tesseract = tess_base_args(languages, engine_mode) + [
@@ -303,9 +307,9 @@ def generate_hocr(
     input_file: Path,
     output_hocr: Path,
     output_text: Path,
-    languages: List[str],
+    languages: list[str],
     engine_mode: int,
-    tessconfig: List[str],
+    tessconfig: list[str],
     timeout: float,
     pagesegmode: int,
     thresholding: int,
@@ -369,9 +373,9 @@ def generate_pdf(
     input_file: Path,
     output_pdf: Path,
     output_text: Path,
-    languages: List[str],
+    languages: list[str],
     engine_mode: int,
-    tessconfig: List[str],
+    tessconfig: list[str],
     timeout: float,
     pagesegmode: int,
     thresholding: int,

src/ocrmypdf/_exec/unpaper.py

@@ -5,26 +5,48 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 # unpaper documentation:
 # https://github.com/Flameeyes/unpaper/blob/master/doc/basic-concepts.md
-
 """Interface to unpaper executable"""
 
 import logging
 import os
 import shlex
+import sys
 from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from tempfile import TemporaryDirectory
+from typing import Iterator, Union
-from typing import Iterator, List, Optional, Tuple, Union
 
 from PIL import Image
 
 from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
 from ocrmypdf.subprocess import get_version, run
 
+if sys.version_info >= (3, 10):
+    from tempfile import TemporaryDirectory
+else:
+    from tempfile import TemporaryDirectory as _TemporaryDirectory
+
+    class TemporaryDirectory(_TemporaryDirectory):
+        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
+
+        The argument is consumed without action. If users are getting errors related
+        to temporary file cleanup, they should upgrade to Python 3.10 which properly
+        cleans up temporary directories on Windows.
+
+        See: https://github.com/python/cpython/pull/24793
+        """
+
+        def __init__(self, ignore_cleanup_errors=False, **kwargs):
+            super().__init__(**kwargs)
+
+    del _TemporaryDirectory
+
+
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
 DecFloat = Union[Decimal, float]
@@ -33,6 +55,8 @@ log = logging.getLogger(__name__)
 
 
 class UnpaperImageTooLargeError(Exception):
+    """To capture details when an image is too large for unpaper."""
+
     def __init__(
         self,
         w,
@@ -49,11 +73,13 @@ def version() -> str:
     return get_version('unpaper')
 
 
-def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
+SUPPORTED_MODES = {'1', 'L', 'RGB'}
-    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
+
+def _convert_image(im: Image.Image) -> tuple[Image.Image, bool]:
     im_modified = False
 
-    if im.mode not in SUFFIXES:
+    if im.mode not in SUPPORTED_MODES:
         log.info("Converting image to other colorspace")
         try:
             if im.mode == 'P' and len(im.getcolors()) == 2:
@@ -66,41 +92,41 @@ def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
             ) from e
         else:
             im_modified = True
-    try:
+        if im.mode not in SUPPORTED_MODES:
-        suffix = SUFFIXES[im.mode]
+            raise MissingDependencyError(
-    except KeyError:
+                "Failed to convert image to a supported format."
-        raise MissingDependencyError(
+            ) from None
-            "Failed to convert image to a supported format."
+    return im, im_modified
-        ) from None
-    return im, im_modified, suffix
 
 
 @contextmanager
-def _setup_unpaper_io(input_file: Path) -> Iterator[Tuple[Path, Path, Path]]:
+def _setup_unpaper_io(input_file: Path) -> Iterator[tuple[Path, Path, Path]]:
     with Image.open(input_file) as im:
         if im.width * im.height >= UNPAPER_IMAGE_PIXEL_LIMIT:
             raise UnpaperImageTooLargeError(w=im.width, h=im.height)
-        im, im_modified, suffix = _convert_image(im)
+        im, im_modified = _convert_image(im)
 
-        with TemporaryDirectory() as tmpdir:
+        with TemporaryDirectory(ignore_cleanup_errors=True) as tmpdir:
             tmppath = Path(tmpdir)
-            if im_modified or input_file.suffix != '.pnm':
+            if im_modified or input_file.suffix != '.png':
-                input_pnm = tmppath / 'input.pnm'
+                input_png = tmppath / 'input.png'
-                im.save(input_pnm, format='PPM')
+                im.save(input_png, format='PNG')
             else:
                 # No changes, PNG input, just use the file we already have
-                input_pnm = input_file
+                input_png = input_file
 
-            output_pnm = tmppath / f'output{suffix}'
+            # unpaper can write .png too, but it seems to write them slowly
-            yield input_pnm, output_pnm, tmppath
+            # adds a few seconds to test suite - so just use pnm
+            output_pnm = tmppath / 'output.pnm'
+            yield input_png, output_pnm, tmppath
 
 
 def run_unpaper(
-    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: List[str]
+    input_file: Path, output_file: Path, *, dpi: DecFloat, mode_args: list[str]
 ) -> None:
     args_unpaper = ['unpaper', '-v', '--dpi', str(round(dpi, 6))] + mode_args
 
-    with _setup_unpaper_io(input_file) as (input_pnm, output_pnm, tmpdir):
+    with _setup_unpaper_io(input_file) as (input_png, output_pnm, tmpdir):
         # To prevent any shenanigans from accepting arbitrary parameters in
         # --unpaper-args, we:
         # 1) run with cwd set to a tmpdir with only unpaper's files
@@ -108,7 +134,7 @@ def run_unpaper(
         # 3) append absolute paths for the input and output file
         # This should ensure that a user cannot clobber some other file with
         # their unpaper arguments (whether intentionally or otherwise)
-        args_unpaper.extend([os.fspath(input_pnm), os.fspath(output_pnm)])
+        args_unpaper.extend([os.fspath(input_png), os.fspath(output_pnm)])
         run(
             args_unpaper,
             close_fds=True,
@@ -129,7 +155,7 @@ def run_unpaper(
             ) from e
 
 
-def validate_custom_args(args: str) -> List[str]:
+def validate_custom_args(args: str) -> list[str]:
     unpaper_args = shlex.split(args)
     if any(('/' in arg or arg == '.' or arg == '..') for arg in unpaper_args):
         raise ValueError('No filenames allowed in --unpaper-args')
@@ -141,7 +167,7 @@ def clean(
     output_file: Path,
     *,
     dpi: DecFloat,
-    unpaper_args: Optional[List[str]] = None,
+    unpaper_args: list[str] | None = None,
 ) -> Path:
     default_args = [
         '--layout',

src/ocrmypdf/_graft.py

@@ -4,19 +4,19 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""For grafting text-only PDF pages onto freeform PDF pages."""
+
+from __future__ import annotations
 
 import logging
-import uuid
 from contextlib import suppress
 from pathlib import Path
-from typing import Optional
 
 from pikepdf import (
     Dictionary,
     Name,
     Object,
     Operator,
-    Page,
     Pdf,
     PdfError,
     PdfMatrix,
@@ -81,6 +81,8 @@ def strip_invisible_text(pdf, page):
 
 
 class OcrGrafter:
+    """Manages grafting text-only PDFs onto regular PDFs."""
+
     def __init__(self, context):
         self.context = context
         self.path_base = context.origin
@@ -102,8 +104,8 @@ class OcrGrafter:
         self,
         *,
         pageno: int,
-        image: Optional[Path],
+        image: Path | None,
-        textpdf: Optional[Path],
+        textpdf: Path | None,
         autorotate_correction: int,
     ):
         if textpdf and not self.font:
@@ -236,6 +238,8 @@ class OcrGrafter:
     ):
         """Insert the text layer from text page 0 on to pdf_base at page_num"""
 
+        # pylint: disable=invalid-name
+
         log.debug("Grafting")
         if Path(textpdf).stat().st_size == 0:
             return
@@ -282,7 +286,7 @@ class OcrGrafter:
 
             base_resources = _ensure_dictionary(base_page, Name.Resources)
             base_xobjs = _ensure_dictionary(base_resources, Name.XObject)
-            text_xobj_name = Name('/' + str(uuid.uuid4()))
+            text_xobj_name = Name.random(prefix="OCR-")
             xobj = self.pdf_base.make_stream(pdf_text_contents)
             base_xobjs[text_xobj_name] = xobj
             xobj.Type = Name.XObject

src/ocrmypdf/_jobcontext.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Defines context objects that are passed to child processes/threads."""
+
+from __future__ import annotations
 
 import os
 import shutil
@@ -49,7 +52,7 @@ class PdfContext:
         """
         return self.work_folder / name
 
-    def get_page_contexts(self) -> Iterator['PageContext']:
+    def get_page_contexts(self) -> Iterator[PageContext]:
         """Get all ``PageContext`` for this PDF."""
         npages = len(self.pdfinfo)
         for n in range(npages):
@@ -83,7 +86,7 @@ class PageContext:
         The path will be based in a common temporary folder and have a prefix based
         on the page number.
         """
-        return self.work_folder / ("%06d_%s" % (self.pageno + 1, name))
+        return self.work_folder / f"{(self.pageno + 1):06d}_{name}"
 
     def __getstate__(self):
         state = self.__dict__.copy()

src/ocrmypdf/_logging.py

@@ -4,15 +4,19 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Logging support classes."""
+
+from __future__ import annotations
 
 import logging
-import sys
 from contextlib import suppress
 
 from tqdm import tqdm
 
 
 class PageNumberFilter(logging.Filter):
+    """Insert PDF page number that emitted log message to log record."""
+
     def filter(self, record):
         pageno = getattr(record, 'pageno', None)
         if isinstance(pageno, int):

src/ocrmypdf/_pipeline.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF page processing pipeline functions."""
+
+from __future__ import annotations
 
 import logging
 import os
@@ -13,7 +16,7 @@ from contextlib import suppress
 from datetime import datetime, timezone
 from pathlib import Path
 from shutil import copyfileobj
-from typing import Dict, Iterable, Optional
+from typing import Iterable
 
 import img2pdf
 import pikepdf
@@ -34,14 +37,13 @@ from ocrmypdf.exceptions import (
 )
 from ocrmypdf.helpers import IMG2PDF_KWARGS, Resolution, safe_symlink
 from ocrmypdf.hocrtransform import HocrTransform
-from ocrmypdf.optimize import optimize
 from ocrmypdf.pdfa import generate_pdfa_ps
 from ocrmypdf.pdfinfo import Colorspace, Encoding, PdfInfo
 
 # Remove this workaround when we require Pillow >= 10
 try:
     BICUBIC = Image.Resampling.BICUBIC  # type: ignore
-except AttributeError:
+except AttributeError:  # pragma: no cover
     # Pillow 9 shim
     BICUBIC = Image.BICUBIC  # type: ignore
 
@@ -332,7 +334,8 @@ def is_ocr_required(page_context: PageContext):
             ocr_required = False
             log.warning(
                 "page too big, skipping OCR "
-                f"({(pixel_count / 1_000_000):.1f} MPixels > {options.skip_big:.1f} MPixels --skip-big)"
+                f"({(pixel_count / 1_000_000):.1f} MPixels > "
+                f"{options.skip_big:.1f} MPixels --skip-big)"
             )
     return ocr_required
 
@@ -430,8 +433,8 @@ def rasterize(
     output_file = page_context.get_path(f'rasterize{output_tag}.png')
     pageinfo = page_context.pageinfo
 
-    def at_least(cs):
+    def at_least(colorspace):
-        return max(device_idx, colorspaces.index(cs))
+        return max(device_idx, colorspaces.index(colorspace))
 
     for image in pageinfo.images:
         if image.type_ != 'image':
@@ -471,10 +474,10 @@ def rasterize(
 
 def preprocess_remove_background(input_file: Path, page_context: PageContext):
     if any(image.bpc > 1 for image in page_context.pageinfo.images):
-        output_file = page_context.get_path('pp_rm_bg.png')
-        # leptonica.remove_background(input_file, output_file)
         raise NotImplementedError("--remove-background is temporarily not implemented")
-        return output_file
+        # output_file = page_context.get_path('pp_rm_bg.png')
+        # leptonica.remove_background(input_file, output_file)
+        # return output_file
     else:
         log.info("background removal skipped on mono page")
         return input_file
@@ -493,7 +496,7 @@ def preprocess_deskew(input_file: Path, page_context: PageContext):
         deskewed = im.rotate(
             deskew_angle_degrees,
             resample=BICUBIC,
-            fillcolor=ImageColor.getcolor('white', mode=im.mode),
+            fillcolor=ImageColor.getcolor('white', mode=im.mode),  # type: ignore
         )
         deskewed.save(output_file, dpi=dpi)
 
@@ -664,7 +667,7 @@ def ocr_engine_textonly_pdf(input_image: Path, page_context: PageContext):
     return (output_pdf, output_text)
 
 
-def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
+def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> dict[str, str]:
     options = context.options
 
     def from_document_info(key):
@@ -678,15 +681,14 @@ def get_docinfo(base_pdf: pikepdf.Pdf, context: PdfContext) -> Dict[str, str]:
         k: from_document_info(k)
         for k in ('/Title', '/Author', '/Keywords', '/Subject', '/CreationDate')
     }
-    if options is not None:
+    if options.title:
-        if options.title:
+        pdfmark['/Title'] = options.title
-            pdfmark['/Title'] = options.title
+    if options.author:
-        if options.author:
+        pdfmark['/Author'] = options.author
-            pdfmark['/Author'] = options.author
+    if options.keywords:
-        if options.keywords:
+        pdfmark['/Keywords'] = options.keywords
-            pdfmark['/Keywords'] = options.keywords
+    if options.subject:
-        if options.subject:
+        pdfmark['/Subject'] = options.subject
-            pdfmark['/Subject'] = options.subject
 
     creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
 
@@ -816,13 +818,14 @@ def metadata_fixup(working_file: Path, context: PdfContext):
                 missing = set(meta_original.keys()) - set(meta.keys())
                 report_on_metadata(missing)
 
+        optimizing = context.plugin_manager.hook.is_optimization_enabled(
+            context=context
+        )
         pdf.save(
             output_file,
             **get_pdf_save_settings(options.output_type),
             linearize=(  # Don't linearize if optimize() will be linearizing too
-                should_linearize(working_file, context)
+                not optimizing and should_linearize(working_file, context)
-                if options.optimize == 0
-                else False
             ),
         )
 
@@ -831,12 +834,22 @@ def metadata_fixup(working_file: Path, context: PdfContext):
 
 def optimize_pdf(input_file: Path, context: PdfContext, executor: Executor):
     output_file = context.get_path('optimize.pdf')
-    save_settings = dict(
+    output_pdf, messages = context.plugin_manager.hook.optimize_pdf(
+        input_pdf=input_file,
+        output_pdf=output_file,
+        context=context,
+        executor=executor,
         linearize=should_linearize(input_file, context),
-        **get_pdf_save_settings(context.options.output_type),
     )
-    optimize(input_file, output_file, context, save_settings, executor)
+
-    return output_file
+    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%}")
+
+    return output_pdf, messages
 
 
 def enumerate_compress_ranges(iterable):
@@ -855,11 +868,11 @@ def enumerate_compress_ranges(iterable):
         yield (skipped_from, index), None
 
 
-def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
+def merge_sidecars(txt_files: Iterable[Path | None], context: PdfContext):
     output_file = context.get_path('sidecar.txt')
     with open(output_file, 'w', encoding="utf-8") as stream:
-        for (frm, to), txt_file in enumerate_compress_ranges(txt_files):
+        for (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
-            if frm != 1:
+            if from_ != 1:
                 stream.write('\f')  # Form feed between pages
             if txt_file:
                 with open(txt_file, encoding="utf-8") as in_:
@@ -872,10 +885,10 @@ def merge_sidecars(txt_files: Iterable[Optional[Path]], context: PdfContext):
                     else:
                         stream.write(txt)
             else:
-                if frm != to:
+                if from_ != to_:
-                    pages = f'{frm}-{to}'
+                    pages = f'{from_}-{to_}'
                 else:
-                    pages = f'{frm}'
+                    pages = f'{from_}'
                 stream.write(f'[OCR skipped on page(s) {pages}]')
     return output_file
 

src/ocrmypdf/_plugin_manager.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Plugin manager using pluggy."""
+
+from __future__ import annotations
 
 import argparse
 import importlib
@@ -11,7 +14,7 @@ import importlib.util
 import pkgutil
 import sys
 from pathlib import Path
-from typing import List, Sequence, Tuple, Union
+from typing import Sequence
 
 import pluggy
 
@@ -33,7 +36,7 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
     def __init__(
         self,
         *args,
-        plugins: List[Union[str, Path]],
+        plugins: list[str | Path],
         builtins: bool = True,
         **kwargs,
     ):
@@ -100,23 +103,28 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
             self.register(module)
 
 
-def get_plugin_manager(plugins: List[Union[str, Path]], builtins=True):
+def get_plugin_manager(plugins: list[str | Path], builtins=True):
-    pm = OcrmypdfPluginManager(
+    return OcrmypdfPluginManager(
         project_name='ocrmypdf',
         plugins=plugins,
         builtins=builtins,
     )
-    return pm
 
 
 def get_parser_options_plugins(
     args: Sequence[str],
-) -> Tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
+) -> tuple[argparse.ArgumentParser, argparse.Namespace, pluggy.PluginManager]:
     pre_options, _unused = plugins_only_parser.parse_known_args(args=args)
     plugin_manager = get_plugin_manager(pre_options.plugins)
 
     parser = get_parser()
+    plugin_manager.hook.initialize(  # pylint: disable=no-member
+        plugin_manager=plugin_manager
+    )
     plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
 
     options = parser.parse_args(args=args)
     return parser, options, plugin_manager
+
+
+__all__ = ['OcrmypdfPluginManager', 'get_plugin_manager', 'get_parser_options_plugins']

src/ocrmypdf/_sync.py

@@ -4,6 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Implements the concurrent and page synchronous parts of the pipeline."""
+
+
+from __future__ import annotations
 
 import argparse
 import logging
@@ -16,7 +20,7 @@ from concurrent.futures.thread import BrokenThreadPool
 from functools import partial
 from pathlib import Path
 from tempfile import mkdtemp
-from typing import List, NamedTuple, Optional, Tuple, cast
+from typing import NamedTuple, Sequence, cast
 
 import PIL
 
@@ -68,11 +72,13 @@ from ocrmypdf.pdfa import file_claims_pdfa
 log = logging.getLogger(__name__)
 
 
-class PageResult(NamedTuple):  # pylint: disable=inherit-non-class
+class PageResult(NamedTuple):
+    """Result when a page is finished processing."""
+
     pageno: int
-    pdf_page_from_image: Optional[Path]
+    pdf_page_from_image: Path | None
-    ocr: Optional[Path]
+    ocr: Path | None
-    text: Optional[Path]
+    text: Path | None
     orientation_correction: int
 
 
@@ -111,7 +117,7 @@ def preprocess(
 
 def make_intermediate_images(
     page_context: PageContext, orientation_correction: int
-) -> Tuple[Path, Optional[Path]]:
+) -> tuple[Path, Path | None]:
     options = page_context.options
 
     ocr_image = preprocess_out = None
@@ -226,7 +232,9 @@ def exec_page_sync(page_context: PageContext) -> PageResult:
     )
 
 
-def post_process(pdf_file: Path, context: PdfContext, executor: Executor) -> Path:
+def post_process(
+    pdf_file: Path, context: PdfContext, executor: Executor
+) -> tuple[Path, Sequence[str]]:
     pdf_out = pdf_file
     if context.options.output_type.startswith('pdfa'):
         ps_stub_out = generate_postscript_stub(context)
@@ -244,7 +252,7 @@ def worker_init(max_pixels: int) -> None:
     pikepdf_enable_mmap()
 
 
-def exec_concurrent(context: PdfContext, executor: Executor) -> None:
+def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
     """Execute the pipeline concurrently"""
 
     # Run exec_page_sync on every page context
@@ -253,7 +261,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> None:
     if max_workers > 1:
         log.info("Start processing %d pages concurrently", max_workers)
 
-    sidecars: List[Optional[Path]] = [None] * len(context.pdfinfo)
+    sidecars: list[Path | None] = [None] * len(context.pdfinfo)
     ocrgraft = OcrGrafter(context)
 
     def update_page(result: PageResult, pbar):
@@ -296,13 +304,15 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> None:
     # Merge layers to one single pdf
     pdf = ocrgraft.finalize()
 
+    messages: Sequence[str] = []
     if options.output_type != 'none':
         # PDF/A and metadata
         log.info("Postprocessing...")
-        pdf = post_process(pdf, context, executor)
+        pdf, messages = post_process(pdf, context, executor)
 
         # Copy PDF file to destination
         copy_final(pdf, options.output_file, context)
+    return messages
 
 
 def configure_debug_logging(
@@ -329,7 +339,7 @@ def configure_debug_logging(
 def run_pipeline(
     options: argparse.Namespace,
     *,
-    plugin_manager: Optional[OcrmypdfPluginManager],
+    plugin_manager: OcrmypdfPluginManager | None,
     api: bool = False,
 ) -> ExitCode:
     # Any changes to options will not take effect for options that are already
@@ -382,7 +392,7 @@ def run_pipeline(
         validate_pdfinfo_options(context)
 
         # Execute the pipeline
-        exec_concurrent(context, executor)
+        optimize_messages = exec_concurrent(context, executor)
 
         if options.output_file == '-':
             log.info("Output sent to stdout")
@@ -408,7 +418,9 @@ def run_pipeline(
             if not check_pdf(options.output_file):
                 log.warning('Output file: The generated PDF is INVALID')
                 return ExitCode.invalid_output_pdf
-            report_output_file_size(options, start_input_file, options.output_file)
+            report_output_file_size(
+                options, start_input_file, options.output_file, optimize_messages
+            )
 
     except (KeyboardInterrupt if not api else NeverRaise):
         if options.verbose >= 1:
@@ -425,7 +437,7 @@ def run_pipeline(
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (PIL.Image.DecompressionBombError if not api else NeverRaise) as e:
+    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 "
@@ -435,7 +447,7 @@ def run_pipeline(
     except (
         BrokenProcessPool if not api else NeverRaise,
         BrokenThreadPool if not api else NeverRaise,
-    ) as e:
+    ):
         log.exception(
             "A worker process was terminated unexpectedly. This is known to occur if "
             "processing your file takes all available swap space and RAM. It may "

src/ocrmypdf/_validation.py

@@ -5,6 +5,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Validate a work order from API or command line."""
+
+from __future__ import annotations
 
 import locale
 import logging
@@ -13,19 +16,19 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
-from typing import List, Set, Tuple
+from typing import Sequence
 
 import pikepdf
 import PIL
 
-from ocrmypdf._exec import jbig2enc, pngquant, unpaper
+from ocrmypdf._exec import unpaper
 from ocrmypdf.exceptions import (
     BadArgsError,
     InputFileError,
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink, samefile
+from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
 from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
@@ -143,16 +146,16 @@ def check_options_preprocessing(options):
             raise BadArgsError("--unpaper-args: " + str(e)) from e
 
 
-def _pages_from_ranges(ranges: str) -> Set[int]:
+def _pages_from_ranges(ranges: str) -> set[int]:
-    pages: List[int] = []
+    pages: list[int] = []
     page_groups = ranges.replace(' ', '').split(',')
-    for g in page_groups:
+    for group in page_groups:
-        if not g:
+        if not group:
             continue
         try:
-            start, end = g.split('-')
+            start, end = group.split('-')
         except ValueError:
-            pages.append(int(g) - 1)
+            pages.append(int(group) - 1)
         else:
             try:
                 new_pages = list(range(int(start) - 1, int(end)))
@@ -162,7 +165,7 @@ def _pages_from_ranges(ranges: str) -> Set[int]:
                     ) from None
                 pages.extend(new_pages)
             except ValueError:
-                raise BadArgsError(f"invalid page subrange '{g}'") from None
+                raise BadArgsError(f"invalid page subrange '{group}'") from None
 
     if not pages:
         raise BadArgsError(
@@ -193,37 +196,6 @@ def check_options_ocr_behavior(options):
         options.pages = _pages_from_ranges(options.pages)
 
 
-def check_options_optimizing(options):
-    if options.optimize >= 2:
-        check_external_program(
-            program='pngquant',
-            package='pngquant',
-            version_checker=pngquant.version,
-            need_version='2.0.1',
-            required_for='--optimize {2,3}',
-        )
-
-    if options.optimize >= 2:
-        # Although we use JBIG2 for optimize=1, don't nag about it unless the
-        # user is asking for more optimization
-        check_external_program(
-            program='jbig2',
-            package='jbig2enc',
-            version_checker=jbig2enc.version,
-            need_version='0.28',
-            required_for='--optimize {2,3} | --jbig2-lossy',
-            recommended=True if not options.jbig2_lossy else False,
-        )
-
-    if options.optimize == 0 and any(
-        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
-    ):
-        log.warning(
-            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
-            "will be ignored because --optimize=0."
-        )
-
-
 def check_options_advanced(options):
     if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
         'pdfa'
@@ -237,13 +209,13 @@ def check_options_advanced(options):
 def check_options_metadata(options):
     docinfo = [options.title, options.author, options.keywords, options.subject]
     for s in (m for m in docinfo if m):
-        for c in s:
+        for char in s:
-            if unicodedata.category(c) == 'Co' or ord(c) >= 0x10000:
+            if unicodedata.category(char) == 'Co' or ord(char) >= 0x10000:
+                hexchar = hex(ord(char))[2:].upper()
                 raise ValueError(
                     "One of the metadata strings contains "
-                    "an unsupported Unicode character: '{}' (U+{})".format(
+                    "an unsupported Unicode character: "
-                        c, hex(ord(c))[2:].upper()
+                    f"{char} (U+{hexchar})"
-                    )
                 )
 
 
@@ -261,7 +233,6 @@ def _check_options(options, plugin_manager, ocr_engine_languages):
     check_options_sidecar(options)
     check_options_preprocessing(options)
     check_options_ocr_behavior(options)
-    check_options_optimizing(options)
     check_options_advanced(options)
     check_options_pillow(options)
     plugin_manager.hook.check_options(options=options)
@@ -272,7 +243,7 @@ def check_options(options, plugin_manager):
     _check_options(options, plugin_manager, ocr_engine_languages)
 
 
-def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
+def create_input_file(options, work_folder: Path) -> tuple[Path, str]:
     if options.input_file == '-':
         # stdin
         log.info('reading file from standard input')
@@ -293,7 +264,7 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
             target = work_folder / 'origin'
             safe_symlink(options.input_file, target)
             return target, os.fspath(options.input_file)
-        except FileNotFoundError:
+        except FileNotFoundError as e:
             msg = f"File not found - {options.input_file}"
             if Path('/.dockerenv').exists():  # pragma: no cover
                 msg += (
@@ -304,7 +275,7 @@ def create_input_file(options, work_folder: Path) -> Tuple[Path, str]:
                     "\n"
                     "\tdocker run -i --rm jbarlow83/ocrmypdf - - <input.pdf >output.pdf\n"
                 )
-            raise InputFileError(msg)
+            raise InputFileError(msg) from e
 
 
 def check_requested_output_file(options):
@@ -324,7 +295,16 @@ def check_requested_output_file(options):
         )
 
 
-def report_output_file_size(options, input_file, output_file):
+def report_output_file_size(
+    options,
+    input_file: Path,
+    output_file: Path,
+    optimize_messages: Sequence[str] | None = None,
+    file_overhead: int = 4000,
+    page_overhead: int = 3000,
+):
+    if optimize_messages is None:
+        optimize_messages = []
     try:
         output_size = Path(output_file).stat().st_size
         input_size = Path(input_file).stat().st_size
@@ -333,9 +313,7 @@ def report_output_file_size(options, input_file, output_file):
     with pikepdf.open(output_file) as p:
         # Overhead constants obtained by estimating amount of data added by OCR
         # PDF/A conversion, and possible XMP metadata addition, with compression
-        FILE_OVERHEAD = 4000
+        reasonable_overhead = file_overhead + page_overhead * len(p.pages)
-        OCR_PER_PAGE_OVERHEAD = 3000
-        reasonable_overhead = FILE_OVERHEAD + OCR_PER_PAGE_OVERHEAD * len(p.pages)
     ratio = output_size / input_size
     reasonable_ratio = output_size / (input_size + reasonable_overhead)
     if reasonable_ratio < 1.35 or input_size < 25000:
@@ -355,19 +333,8 @@ def report_output_file_size(options, input_file, output_file):
                 f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
             )
 
-    if options.optimize == 0:
+    reasons.extend(optimize_messages)
-        reasons.append("Optimization was disabled.")
+
-    else:
-        image_optimizers = {
-            'jbig2': jbig2enc.available(),
-            'pngquant': pngquant.available(),
-        }
-        for name, available in image_optimizers.items():
-            if not available:
-                reasons.append(
-                    f"The optional dependency '{name}' was not found, so some image "
-                    f"optimizations could not be attempted."
-                )
     if options.output_type.startswith('pdfa'):
         reasons.append("PDF/A conversion was enabled. (Try `--output-type pdf`.)")
     if options.plugins:

src/ocrmypdf/_version.py

@@ -4,11 +4,17 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Get version by introspecting package information.
+
+OCRmyPDF uses setuptools_scm to derive version from git tags.
+"""
+
+from __future__ import annotations
 
 try:
-    from importlib_metadata import version as _package_version
-except ImportError:
     from importlib.metadata import version as _package_version
+except ImportError:
+    from importlib_metadata import version as _package_version  # type: ignore
 
 PROGRAM_NAME = 'ocrmypdf'
 

src/ocrmypdf/api.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Functions for using ocrmypdf as an API."""
+
+from __future__ import annotations
 
 import logging
 import os
@@ -12,7 +15,7 @@ import threading
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Iterable, Optional, Union
+from typing import AnyStr, BinaryIO, Iterable, Union
 from warnings import warn
 
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
@@ -25,7 +28,10 @@ from ocrmypdf.helpers import is_iterable_notstr
 try:
     import coloredlogs
 except ModuleNotFoundError:
-    coloredlogs = None
+    coloredlogs = None  # pylint: disable=invalid-name
+
+if coloredlogs:
+    from humanfriendly.terminal import enable_ansi_support
 
 
 StrPath = Union[Path, AnyStr]
@@ -37,6 +43,7 @@ _api_lock = threading.Lock()
 class Verbosity(IntEnum):
     """Verbosity level for configure_logging."""
 
+    # pylint: disable=invalid-name
     quiet = -1  #: Suppress most messages
     default = 0  #: Default level of logging
     debug = 1  #: Output ocrmypdf debug messages
@@ -116,16 +123,15 @@ def configure_logging(
         fmt = '%(pageno)s%(message)s'
 
     use_colors = progress_bar_friendly
-    if not coloredlogs:
+    formatter = None
-        use_colors = False
+    if coloredlogs and use_colors:
-    if use_colors:
+        use_colors = enable_ansi_support()
-        if os.name == 'nt':
-            use_colors = coloredlogs.enable_ansi_support()
         if use_colors:
             use_colors = coloredlogs.terminal_supports_colors()
-    if use_colors:
+        if use_colors:
-        formatter = coloredlogs.ColoredFormatter(fmt=fmt)
+            formatter = coloredlogs.ColoredFormatter(fmt=fmt)
-    else:
+
+    if not formatter:
         formatter = logging.Formatter(fmt=fmt)
 
     console.setFormatter(formatter)
@@ -193,7 +199,7 @@ def create_options(
     else:
         cmdline.append(os.fspath(output_file))
 
-    parser._api_mode = True
+    parser.enable_api_mode()
     options = parser.parse_args(cmdline)
     for keyword, val in deferred:
         setattr(options, keyword, val)
@@ -213,7 +219,7 @@ def ocr(  # pylint: disable=unused-argument
     language: Iterable[str] = None,
     image_dpi: int = None,
     output_type=None,
-    sidecar: Optional[StrPath] = None,
+    sidecar: StrPath | None = None,
     jobs: int = None,
     use_threads: bool = None,
     title: str = None,
@@ -295,7 +301,7 @@ def ocr(  # pylint: disable=unused-argument
             text already, and settings did not tell us to proceed.
         ocrmypdf.InputFileError: Any other problem with the input file.
         ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess.
-        ocrmypdf.EncryptedPdfERror: If the input PDF is encrypted (password protected).
+        ocrmypdf.EncryptedPdfError: If the input PDF is encrypted (password protected).
             OCRmyPDF does not remove passwords.
         ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not
             valid.

src/ocrmypdf/builtin_plugins/__init__.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 # 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.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -4,12 +4,15 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 # © 2020 James R. Barlow: github.com/jbarlow83
 #
 # This Source Code Form is subject to the terms of the Mozilla Public
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF's multiprocessing/multithreading abstraction layer."""
 
 import logging
 import logging.handlers
@@ -21,7 +24,6 @@ import sys
 import threading
 from concurrent.futures import ProcessPoolExecutor, ThreadPoolExecutor, as_completed
 from contextlib import suppress
-from multiprocessing.pool import Pool, ThreadPool
 from typing import Callable, Iterable, Type, Union
 
 from tqdm import tqdm
@@ -44,7 +46,8 @@ def log_listener(q: Queue):
     should actually write to sys.stderr or whatever we're using, so if this is
     made into a process the main application needs to be directed to it.
 
-    See https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
+    See:
+    https://docs.python.org/3/howto/logging-cookbook.html#logging-to-a-single-file-from-multiple-processes
     """
 
     while True:
@@ -89,6 +92,8 @@ def process_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
+    del q  # unused but required argument
+    del loglevel  # unused but required argument
     # As a thread, block SIGBUS so the main thread deals with it...
     with suppress(AttributeError):
         signal.pthread_sigmask(signal.SIG_BLOCK, {signal.SIGBUS})
@@ -98,6 +103,17 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
 
 
 class StandardExecutor(Executor):
+    """Standard OCRmyPDF concurrent task executor."""
+
+    def _cancel_futures_kwargs(self):
+        """Shim older Pythons that do not have Executor.shutdown(...cancel_futures=).
+
+        Remove this code when support for Python 3.8 is dropped.
+        """
+        if sys.version_info[:2] < (3, 9):
+            return {}
+        return dict(cancel_futures=True)
+
     def _execute(
         self,
         *,
@@ -136,7 +152,7 @@ class StandardExecutor(Executor):
                     task_finished(result, pbar)
             except KeyboardInterrupt:
                 # Terminate pool so we exit instantly
-                executor.shutdown(wait=False, cancel_futures=True)
+                executor.shutdown(wait=False, **self._cancel_futures_kwargs())
                 raise
             except Exception:
                 if not os.environ.get("PYTEST_CURRENT_TEST", ""):
@@ -145,7 +161,7 @@ class StandardExecutor(Executor):
                     # results will be discard. But if the condition above is True,
                     # then we are running in pytest, and we want everything to exit
                     # as cleanly as possible so that we get good error messages.
-                    executor.shutdown(wait=False, cancel_futures=True)
+                    executor.shutdown(wait=False, **self._cancel_futures_kwargs())
                 raise
             finally:
                 # Terminate log listener

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -4,6 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF automatically installs these filters as plugins."""
+
+from __future__ import annotations
+
 from ocrmypdf import hookimpl
 
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -5,6 +5,10 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""Built-in plugin to implement PDF page rasterization and PDF/A production."""
+
+from __future__ import annotations
+
 import logging
 
 from ocrmypdf import hookimpl

src/ocrmypdf/builtin_plugins/optimize.py

@@ -0,0 +1,160 @@
+# © 2022 James R. Barlow: github.com/jbarlow83
+#
+# This Source Code Form is subject to the terms of the Mozilla Public
+# License, v. 2.0. If a copy of the MPL was not distributed with this
+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
+
+
+"""Built-in plugin to implement PDF page optimization."""
+
+from __future__ import annotations
+
+import argparse
+import logging
+from pathlib import Path
+from typing import Sequence
+
+from ocrmypdf import Executor, PdfContext, hookimpl
+from ocrmypdf._exec import jbig2enc, pngquant
+from ocrmypdf._pipeline import get_pdf_save_settings
+from ocrmypdf.cli import numeric
+from ocrmypdf.optimize import optimize
+from ocrmypdf.subprocess import check_external_program
+
+log = logging.getLogger(__name__)
+
+
+@hookimpl
+def add_options(parser):
+    optimizing = parser.add_argument_group(
+        "Optimization options", "Control how the PDF is optimized after OCR"
+    )
+    optimizing.add_argument(
+        '-O',
+        '--optimize',
+        type=int,
+        choices=range(0, 4),
+        default=1,
+        help=(
+            "Control how PDF is optimized after processing:"
+            "0 - do not optimize; "
+            "1 - do safe, lossless optimizations (default); "
+            "2 - do lossy JPEG and JPEG2000 optimizations; "
+            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
+            "To enable lossy JBIG2, see --jbig2-lossy."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpeg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust JPEG quality level for JPEG optimization. "
+            "100 is best quality and largest output size; "
+            "1 is lowest quality and smallest output; "
+            "0 uses the default."
+        ),
+    )
+    optimizing.add_argument(
+        '--jpg-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        dest='jpeg_quality',
+        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
+    )
+    optimizing.add_argument(
+        '--png-quality',
+        type=numeric(int, 0, 100),
+        default=0,
+        metavar='Q',
+        help=(
+            "Adjust PNG quality level to use when quantizing PNGs. "
+            "Values have same meaning as with --jpeg-quality"
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-lossy',
+        action='store_true',
+        help=(
+            "Enable JBIG2 lossy mode (better compression, not suitable for some "
+            "use cases - see documentation). Only takes effect if --optimize 1 or "
+            "higher is also enabled."
+        ),
+    )
+    optimizing.add_argument(
+        '--jbig2-page-group-size',
+        type=numeric(int, 1, 10000),
+        default=0,
+        metavar='N',
+        # Adjust number of pages to consider at once for JBIG2 compression
+        help=argparse.SUPPRESS,
+    )
+
+
+@hookimpl
+def check_options(options):
+    if options.optimize >= 2:
+        check_external_program(
+            program='pngquant',
+            package='pngquant',
+            version_checker=pngquant.version,
+            need_version='2.0.1',
+            required_for='--optimize {2,3}',
+        )
+
+    if options.optimize >= 2:
+        # Although we use JBIG2 for optimize=1, don't nag about it unless the
+        # user is asking for more optimization
+        check_external_program(
+            program='jbig2',
+            package='jbig2enc',
+            version_checker=jbig2enc.version,
+            need_version='0.28',
+            required_for='--optimize {2,3} | --jbig2-lossy',
+            recommended=True if not options.jbig2_lossy else False,
+        )
+
+    if options.optimize == 0 and any(
+        [options.jbig2_lossy, options.png_quality, options.jpeg_quality]
+    ):
+        log.warning(
+            "The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
+            "will be ignored because --optimize=0."
+        )
+
+
+@hookimpl
+def optimize_pdf(
+    input_pdf: Path,
+    output_pdf: Path,
+    context: PdfContext,
+    executor: Executor,
+    linearize: bool,
+) -> tuple[Path, Sequence[str]]:
+    save_settings = dict(
+        linearize=linearize,
+        **get_pdf_save_settings(context.options.output_type),
+    )
+    result_path = optimize(input_pdf, output_pdf, context, save_settings, executor)
+    messages = []
+    if context.options.optimize == 0:
+        messages.append("Optimization was disabled.")
+    else:
+        image_optimizers = {
+            'jbig2': jbig2enc.available(),
+            'pngquant': pngquant.available(),
+        }
+        for name, available in image_optimizers.items():
+            if not available:
+                messages.append(
+                    f"The optional dependency '{name}' was not found, so some image "
+                    f"optimizations could not be attempted."
+                )
+    return result_path, messages
+
+
+@hookimpl
+def is_optimization_enabled(context: PdfContext) -> bool:
+    return context.options.optimize != 0

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -4,6 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Built-in plugin to implement OCR using Tesseract."""
+
+
+from __future__ import annotations
 
 import logging
 import os
@@ -138,6 +142,8 @@ def validate(pdfinfo, options):
 
 
 class TesseractOcrEngine(OcrEngine):
+    """Implements OCR with Tesseract."""
+
     @staticmethod
     def version():
         return tesseract.version()

src/ocrmypdf/cli.py

@@ -4,9 +4,12 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Command line interface customization and validation."""
+
+from __future__ import annotations
 
 import argparse
-from typing import Any, Callable, Mapping, Optional, TypeVar
+from typing import Any, Callable, Mapping, TypeVar
 
 from ocrmypdf._version import PROGRAM_NAME as _PROGRAM_NAME
 from ocrmypdf._version import __version__ as _VERSION
@@ -14,9 +17,7 @@ from ocrmypdf._version import __version__ as _VERSION
 T = TypeVar('T', int, float)
 
 
-def numeric(
+def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    basetype: Callable[[Any], T], min_: Optional[T] = None, max_: Optional[T] = None
-):
     """Validator for numeric params"""
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None
@@ -42,7 +43,7 @@ def str_to_int(mapping: Mapping[str, int]):
         except KeyError:
             raise argparse.ArgumentTypeError(
                 f"{s!r} must be one of: {', '.join(mapping.keys())}"
-            )
+            ) from None
 
     return _str_to_int
 
@@ -51,12 +52,20 @@ class ArgumentParser(argparse.ArgumentParser):
     """Override parser's default behavior of calling sys.exit()
 
     https://stackoverflow.com/questions/5943249/python-argparse-and-controlling-overriding-the-exit-status-code
+
+    OCRmyPDF began as a CLI but eventually acquired an API. The API works inside out,
+    by synthesizing a command line argument. So we subclass the standard parser with
+    one that doesn't call sys.exit(). Obviously this is not the ideal way to do things
+    but it works for us.
     """
 
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
         self._api_mode = False
 
+    def enable_api_mode(self):
+        self._api_mode = True
+
     def error(self, message):
         if not self._api_mode:
             super().error(message)
@@ -65,6 +74,8 @@ class ArgumentParser(argparse.ArgumentParser):
 
 
 class LanguageSetAction(argparse.Action):
+    """Manages a list of languages."""
+
     def __init__(self, option_strings, dest, default=None, **kwargs):
         if default is None:
             default = set()
@@ -341,72 +352,6 @@ Online documentation is located at:
         "but include skipped pages in final output",
     )
 
-    optimizing = parser.add_argument_group(
-        "Optimization options", "Control how the PDF is optimized after OCR"
-    )
-    optimizing.add_argument(
-        '-O',
-        '--optimize',
-        type=int,
-        choices=range(0, 4),
-        default=1,
-        help=(
-            "Control how PDF is optimized after processing:"
-            "0 - do not optimize; "
-            "1 - do safe, lossless optimizations (default); "
-            "2 - do lossy JPEG and JPEG2000 optimizations; "
-            "3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
-            "To enable lossy JBIG2, see --jbig2-lossy."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpeg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust JPEG quality level for JPEG optimization. "
-            "100 is best quality and largest output size; "
-            "1 is lowest quality and smallest output; "
-            "0 uses the default."
-        ),
-    )
-    optimizing.add_argument(
-        '--jpg-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        dest='jpeg_quality',
-        help=argparse.SUPPRESS,  # Alias for --jpeg-quality
-    )
-    optimizing.add_argument(
-        '--png-quality',
-        type=numeric(int, 0, 100),
-        default=0,
-        metavar='Q',
-        help=(
-            "Adjust PNG quality level to use when quantizing PNGs. "
-            "Values have same meaning as with --jpeg-quality"
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-lossy',
-        action='store_true',
-        help=(
-            "Enable JBIG2 lossy mode (better compression, not suitable for some "
-            "use cases - see documentation). Only takes effect if --optimize 1 or "
-            "higher is also enabled."
-        ),
-    )
-    optimizing.add_argument(
-        '--jbig2-page-group-size',
-        type=numeric(int, 1, 10000),
-        default=0,
-        metavar='N',
-        # Adjust number of pages to consider at once for JBIG2 compression
-        help=argparse.SUPPRESS,
-    )
-
     advanced = parser.add_argument_group(
         "Advanced", "Advanced options to control OCRmyPDF"
     )

src/ocrmypdf/data/__init__.py

@@ -6,3 +6,5 @@
 
 
 """Data files used to generate certain PDFs."""
+
+from __future__ import annotations

src/ocrmypdf/exceptions.py

@@ -4,12 +4,18 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF's exceptions."""
+
+from __future__ import annotations
 
 from enum import IntEnum
 from textwrap import dedent
 
 
 class ExitCode(IntEnum):
+    """OCRmyPDF's exit codes."""
+
+    # pylint: disable=invalid-name
     ok = 0
     bad_args = 1
     input_file = 2
@@ -26,6 +32,8 @@ class ExitCode(IntEnum):
 
 
 class ExitCodeException(Exception):
+    """An exception which should return an exit code with sys.exit()."""
+
     exit_code = ExitCode.other_error
     message = ""
 
@@ -37,17 +45,24 @@ class ExitCodeException(Exception):
 
 
 class BadArgsError(ExitCodeException):
+    """Invalid arguments on the command line or API."""
+
     exit_code = ExitCode.bad_args
 
 
-class PdfMergeFailedError(ExitCodeException):
+class PdfMergeFailedError(ExitCodeException):  # deprecated
+    """An intermediate PDF can't be merged.
+
+    No longer in use.
+    """
+
     exit_code = ExitCode.input_file
     message = dedent(
         '''\
         Failed to merge PDF image layer with OCR layer
 
         Usually this happens because the input PDF file is malformed and
-        ocrmypdf cannot automatically correct the problem on its own.
+        ocrmypdf cannot correct the problem on its own.
 
         Try using
             ocrmypdf --pdf-renderer sandwich  [..other args..]
@@ -56,34 +71,50 @@ class PdfMergeFailedError(ExitCodeException):
 
 
 class MissingDependencyError(ExitCodeException):
+    """A third-party dependency is missing."""
+
     exit_code = ExitCode.missing_dependency
 
 
 class UnsupportedImageFormatError(ExitCodeException):
+    """The image format is not supported."""
+
     exit_code = ExitCode.input_file
 
 
 class DpiError(ExitCodeException):
+    """Missing information about input image DPI."""
+
     exit_code = ExitCode.input_file
 
 
 class OutputFileAccessError(ExitCodeException):
+    """Cannot access the intended output file path."""
+
     exit_code = ExitCode.file_access_error
 
 
 class PriorOcrFoundError(ExitCodeException):
+    """This file already has OCR."""
+
     exit_code = ExitCode.already_done_ocr
 
 
 class InputFileError(ExitCodeException):
+    """Something is wrong with the input file."""
+
     exit_code = ExitCode.input_file
 
 
 class SubprocessOutputError(ExitCodeException):
+    """A subprocess returned an unexpected error."""
+
     exit_code = ExitCode.child_process_error
 
 
 class EncryptedPdfError(ExitCodeException):
+    """Input PDF is encrypted."""
+
     exit_code = ExitCode.encrypted_pdf
     message = dedent(
         '''\
@@ -100,5 +131,7 @@ class EncryptedPdfError(ExitCodeException):
 
 
 class TesseractConfigError(ExitCodeException):
+    """Tesseract config can't be parsed."""
+
     exit_code = ExitCode.invalid_config
     message = "Error occurred while parsing a Tesseract configuration file"

src/ocrmypdf/extra_plugins/semfree.py

@@ -20,6 +20,8 @@ be guaranteed, some workers may end up with too much work while others are idle.
 It is less efficient than the standard implementation, so not th edefault.
 """
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import signal
@@ -28,7 +30,7 @@ from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable, Iterable, Iterator, List
+from typing import Callable, Iterable, Iterator
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -37,9 +39,11 @@ from ocrmypdf.helpers import remove_all_log_handlers
 
 
 class MessageType(Enum):
-    exception = auto()
+    """Implement basic IPC messaging."""
-    result = auto()
+
-    complete = auto()
+    exception = auto()  # pylint: disable=invalid-name
+    result = auto()  # pylint: disable=invalid-name
+    complete = auto()  # pylint: disable=invalid-name
 
 
 def split_every(n: int, iterable: Iterable) -> Iterator:
@@ -59,6 +63,8 @@ def process_sigbus(*args):
 
 
 class ConnectionLogHandler(logging.handlers.QueueHandler):
+    """Handler used by child processes to forward log messages to parent."""
+
     def __init__(self, conn: Connection) -> None:
         # sets the parent's queue to None - parent only touches queue
         # in enqueue() which we override
@@ -91,7 +97,7 @@ def process_loop(
     for args in task_args:
         try:
             result = task(args)
-        except Exception as e:
+        except Exception as e:  # pylint: disable=broad-except
             conn.send((MessageType.exception, e))
             break
         else:
@@ -103,6 +109,8 @@ def process_loop(
 
 
 class LambdaExecutor(Executor):
+    """Executor for AWS Lambda or similar environments that lack semaphores."""
+
     def _execute(
         self,
         *,
@@ -128,8 +136,8 @@ class LambdaExecutor(Executor):
         if not grouped_args:
             return
 
-        processes: List[Process] = []
+        processes: list[Process] = []
-        connections: List[Connection] = []
+        connections: list[Connection] = []
         for chunk in grouped_args:
             parent_conn, child_conn = Pipe()
 
@@ -153,13 +161,13 @@ class LambdaExecutor(Executor):
 
         with self.pbar_class(**tqdm_kwargs) as pbar:
             while connections:
-                for r in wait(connections):
+                for result in wait(connections):
-                    if not isinstance(r, Connection):
+                    if not isinstance(result, Connection):
                         raise NotImplementedError("We only support Connection()")
                     try:
-                        msg_type, msg = r.recv()
+                        msg_type, msg = result.recv()
                     except EOFError:
-                        connections.remove(r)
+                        connections.remove(result)
                         continue
 
                     if msg_type == MessageType.result:
@@ -170,7 +178,7 @@ class LambdaExecutor(Executor):
                         logger = logging.getLogger(record.name)
                         logger.handle(record)
                     elif msg_type == MessageType.complete:
-                        connections.remove(r)
+                        connections.remove(result)
                     elif msg_type == MessageType.exception:
                         for process in processes:
                             process.terminate()

src/ocrmypdf/helpers.py

@@ -4,6 +4,9 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Support functions."""
+
+from __future__ import annotations
 
 import logging
 import multiprocessing
@@ -137,11 +140,11 @@ def safe_symlink(input_file: os.PathLike, soft_link_name: os.PathLike):
     os.symlink(os.path.abspath(input_file), soft_link_name)
 
 
-def samefile(f1: os.PathLike, f2: os.PathLike):
+def samefile(file1: os.PathLike, file2: os.PathLike):
     if os.name == 'nt':
-        return f1 == f2
+        return file1 == file2
     else:
-        return os.path.samefile(f1, f2)
+        return os.path.samefile(file1, file2)
 
 
 def is_iterable_notstr(thing: Any) -> bool:
@@ -149,9 +152,9 @@ def is_iterable_notstr(thing: Any) -> bool:
     return isinstance(thing, Iterable) and not isinstance(thing, str)
 
 
-def monotonic(L: Sequence) -> bool:
+def monotonic(seq: Sequence) -> bool:
     """Does this sequence increase monotonically?"""
-    return all(b > a for a, b in zip(L, L[1:]))
+    return all(b > a for a, b in zip(seq, seq[1:]))
 
 
 def page_number(input_file: os.PathLike) -> int:
@@ -166,7 +169,7 @@ def available_cpu_count() -> int:
     except NotImplementedError:
         pass
     warnings.warn(
-        "Could not get CPU count.  Assuming one (1) CPU." "Use -j N to set manually."
+        "Could not get CPU count. Assuming one (1) CPU. Use -j N to set manually."
     )
     return 1
 
@@ -190,16 +193,16 @@ def is_file_writable(test_file: os.PathLike) -> bool:
                 os.W_OK,
                 effective_ids=(os.access in os.supports_effective_ids),
             )
+
+        try:
+            fp = p.open('wb')
+        except OSError:
+            return False
         else:
-            try:
+            fp.close()
-                fp = p.open('wb')
+            with suppress(OSError):
-            except OSError:
+                p.unlink()
-                return False
+        return True
-            else:
-                fp.close()
-                with suppress(OSError):
-                    p.unlink()
-            return True
     except (OSError, RuntimeError) as e:
         log.debug(e)
         log.error(str(e))

src/ocrmypdf/hocrtransform.py

@@ -28,17 +28,26 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+"""Transform .hocr and page image to text PDF."""
+
+from __future__ import annotations
+
 import argparse
 import os
 import re
+import warnings
 from math import atan, cos, sin
 from pathlib import Path
 from typing import Any, NamedTuple, Optional, Tuple, Union
 from xml.etree import ElementTree
 
-from reportlab.lib.colors import black, cyan, magenta, red
+with warnings.catch_warnings():
-from reportlab.lib.units import inch
+    warnings.filterwarnings(
-from reportlab.pdfgen.canvas import Canvas
+        'ignore', category=DeprecationWarning, message=r".*load_module.*"
+    )
+    from reportlab.lib.colors import black, cyan, magenta, red
+    from reportlab.lib.units import inch
+    from reportlab.pdfgen.canvas import Canvas
 
 # According to Wikipedia these languages are supported in the ISO-8859-1 character
 # set, meaning reportlab can generate them and they are compatible with hocr,
@@ -99,7 +108,7 @@ HOCR_OK_LANGS = frozenset(
 Element = ElementTree.Element
 
 
-class Rect(NamedTuple):  # pylint: disable=inherit-non-class
+class Rect(NamedTuple):
     """A rectangle for managing PDF coordinates."""
 
     x1: Any
@@ -109,7 +118,7 @@ class Rect(NamedTuple):  # pylint: disable=inherit-non-class
 
 
 class HocrTransformError(Exception):
-    pass
+    """Error while applying hOCR transform."""
 
 
 class HocrTransform:
@@ -132,7 +141,7 @@ class HocrTransform:
         {'ff': 'ff', 'ffi': 'f‌f‌i', 'ffl': 'f‌f‌l', 'fi': 'fi', 'fl': 'fl'}
     )
 
-    def __init__(self, *, hocr_filename: Union[str, Path], dpi: float):
+    def __init__(self, *, hocr_filename: str | Path, dpi: float):
         self.dpi = dpi
         self.hocr = ElementTree.parse(os.fspath(hocr_filename))
 
@@ -196,7 +205,7 @@ class HocrTransform:
         return out
 
     @classmethod
-    def baseline(cls, element: Element) -> Tuple[float, float]:
+    def baseline(cls, element: Element) -> tuple[float, float]:
         """
         Returns a tuple containing the baseline slope and intercept.
         """
@@ -212,7 +221,7 @@ class HocrTransform:
         """
         return Rect._make((c / self.dpi * inch) for c in pxl)
 
-    def _child_xpath(self, html_tag: str, html_class: Optional[str] = None) -> str:
+    def _child_xpath(self, html_tag: str, html_class: str | None = None) -> str:
         xpath = f".//{self.xmlns}{html_tag}"
         if html_class:
             xpath += f"[@class='{html_class}']"
@@ -239,7 +248,7 @@ class HocrTransform:
         self,
         *,
         out_filename: Path,
-        image_filename: Optional[Path] = None,
+        image_filename: Path | None = None,
         show_bounding_boxes: bool = False,
         fontname: str = "Helvetica",
         invisible_text: bool = False,
@@ -287,7 +296,7 @@ class HocrTransform:
                 continue
 
             pxl_coords = self.element_coordinates(elem)
-            pt = self.pt_from_pixel(pxl_coords)
+            pt = self.pt_from_pixel(pxl_coords)  # pylint: disable=invalid-name
 
             # draw the bbox border
             if show_bounding_boxes:  # pragma: no cover
@@ -342,7 +351,7 @@ class HocrTransform:
     def _do_line(
         self,
         pdf: Canvas,
-        line: Optional[Element],
+        line: Element | None,
         elemclass: str,
         fontname: str,
         invisible_text: bool,

src/ocrmypdf/optimize.py

@@ -4,6 +4,10 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""Post-processing image optimization of OCR PDFs."""
+
+
+from __future__ import annotations
 
 import logging
 import sys
@@ -12,18 +16,7 @@ import threading
 from collections import defaultdict
 from os import fspath
 from pathlib import Path
-from typing import (
+from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
-    Callable,
-    Dict,
-    Iterator,
-    List,
-    MutableSet,
-    NamedTuple,
-    NewType,
-    Optional,
-    Sequence,
-    Tuple,
-)
 from zlib import compress
 
 import img2pdf
@@ -55,7 +48,9 @@ DEFAULT_PNG_QUALITY = 70
 Xref = NewType('Xref', int)
 
 
-class XrefExt(NamedTuple):  # pylint: disable=inherit-non-class
+class XrefExt(NamedTuple):
+    """A PDF xref and image extension pair."""
+
     xref: Xref
     ext: str
 
@@ -74,7 +69,7 @@ def jpg_name(root: Path, xref: Xref) -> Path:
 
 def extract_image_filter(
     pike: Pdf, root: Path, image: Stream, xref: Xref
-) -> Optional[Tuple[PdfImage, Tuple[Name, Object]]]:
+) -> tuple[PdfImage, tuple[Name, Object]] | None:
     del pike  # unused args
     del root
 
@@ -131,7 +126,7 @@ def extract_image_filter(
 
 def extract_image_jbig2(
     *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
-) -> Optional[XrefExt]:
+) -> XrefExt | None:
     del options  # unused arg
 
     result = extract_image_filter(pike, root, image, xref)
@@ -172,7 +167,7 @@ def extract_image_jbig2(
 
 def extract_image_generic(
     *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
-) -> Optional[XrefExt]:
+) -> XrefExt | None:
     result = extract_image_filter(pike, root, image, xref)
     if result is None:
         return None
@@ -236,8 +231,8 @@ def extract_images(
     pike: Pdf,
     root: Path,
     options,
-    extract_fn: Callable[..., Optional[XrefExt]],
+    extract_fn: Callable[..., XrefExt | None],
-) -> Iterator[Tuple[int, XrefExt]]:
+) -> Iterator[tuple[int, XrefExt]]:
     """Extract image using extract_fn
 
     Enumerate images on each page, lookup their xref/ID number in the PDF.
@@ -266,7 +261,7 @@ def extract_images(
             if image.objgen[1] != 0:
                 continue  # Ignore images in an incremental PDF
             xref = Xref(image.objgen[0])
-            if hasattr(image, 'SMask'):
+            if Name.SMask in image:
                 # Ignore soft masks
                 smask_xref = Xref(image.SMask.objgen[0])
                 exclude_xrefs.add(smask_xref)
@@ -296,7 +291,7 @@ def extract_images(
 
 def extract_images_generic(
     pike: Pdf, root: Path, options
-) -> Tuple[List[Xref], List[Xref]]:
+) -> tuple[list[Xref], list[Xref]]:
     """Extract any >=2bpp image we think we can improve"""
 
     jpegs = []
@@ -311,7 +306,7 @@ def extract_images_generic(
     return jpegs, pngs
 
 
-def extract_images_jbig2(pike: Pdf, root: Path, options) -> Dict[int, List[XrefExt]]:
+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"""
 
     jbig2_groups = defaultdict(list)
@@ -324,11 +319,11 @@ 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
+    jbig2_groups: dict[int, list[XrefExt]], root: Path, options, executor: Executor
 ) -> None:
     """Produce JBIG2 images from their groups"""
 
-    def jbig2_group_args(root: Path, groups: Dict[int, List[XrefExt]]):
+    def jbig2_group_args(root: Path, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             yield (
@@ -337,7 +332,7 @@ def _produce_jbig2_images(
                 prefix,  # =out_prefix
             )
 
-    def jbig2_single_args(root, groups: Dict[int, List[XrefExt]]):
+    def jbig2_single_args(root, groups: dict[int, list[XrefExt]]):
         for group, xref_exts in groups.items():
             prefix = f'group{group:08d}'
             # Second loop is to ensure multiple images per page are unpacked
@@ -372,7 +367,7 @@ def _produce_jbig2_images(
 
 def convert_to_jbig2(
     pike: Pdf,
-    jbig2_groups: Dict[int, List[XrefExt]],
+    jbig2_groups: dict[int, list[XrefExt]],
     root: Path,
     options,
     executor: Executor,
@@ -389,7 +384,7 @@ def convert_to_jbig2(
     When the JBIG2 symbolic coder is not used, each JBIG2 stands on its own
     and needs no dictionary. Currently this must be lossless JBIG2.
     """
-    jbig2_globals_dict: Optional[Dictionary]
+    jbig2_globals_dict: Dictionary | None
 
     _produce_jbig2_images(jbig2_groups, root, options, executor)
 
@@ -415,7 +410,7 @@ def convert_to_jbig2(
             )
 
 
-def _optimize_jpeg(args: Tuple[Xref, Path, Path, int]) -> Tuple[Xref, Optional[Path]]:
+def _optimize_jpeg(args: tuple[Xref, Path, Path, int]) -> tuple[Xref, Path | None]:
     xref, in_jpg, opt_jpg, jpeg_quality = args
 
     with Image.open(in_jpg) as im:
@@ -431,13 +426,13 @@ def _optimize_jpeg(args: Tuple[Xref, Path, Path, int]) -> Tuple[Xref, Optional[P
 def transcode_jpegs(
     pike: Pdf, jpegs: Sequence[Xref], root: Path, options, executor: Executor
 ) -> None:
-    def jpeg_args() -> Iterator[Tuple[Xref, Path, Path, int]]:
+    def jpeg_args() -> Iterator[tuple[Xref, Path, Path, int]]:
         for xref in jpegs:
             in_jpg = jpg_name(root, xref)
             opt_jpg = in_jpg.with_suffix('.opt.jpg')
             yield xref, in_jpg, opt_jpg, options.jpeg_quality
 
-    def finish_jpeg(result: Tuple[Xref, Optional[Path]], pbar):
+    def finish_jpeg(result: tuple[Xref, Path | None], pbar):
         xref, opt_jpg = result
         if opt_jpg:
             compdata = opt_jpg.read_bytes()  # JPEG can inserted into PDF as is
@@ -462,11 +457,11 @@ def transcode_jpegs(
 
 def _find_deflatable_jpeg(
     *, pike: Pdf, root: Path, image: Stream, xref: Xref, options
-) -> Optional[XrefExt]:
+) -> XrefExt | None:
     result = extract_image_filter(pike, root, image, xref)
     if result is None:
         return None
-    pim, filtdp = result
+    _pim, filtdp = result
 
     if filtdp[0] == Name.DCTDecode and not filtdp[1] and options.optimize >= 1:
         return XrefExt(xref, '.memory')
@@ -474,7 +469,7 @@ def _find_deflatable_jpeg(
     return None
 
 
-def _deflate_jpeg(args: Tuple[Pdf, threading.Lock, Xref, int]) -> Tuple[Xref, bytes]:
+def _deflate_jpeg(args: tuple[Pdf, threading.Lock, Xref, int]) -> tuple[Xref, bytes]:
     pike, lock, xref, complevel = args
     with lock:
         xobj = pike.get_object(xref, 0)
@@ -621,11 +616,11 @@ def optimize(
     context,
     save_settings,
     executor: Executor = DEFAULT_EXECUTOR,
-) -> None:
+) -> Path:
     options = context.options
     if options.optimize == 0:
         safe_symlink(input_file, output_file)
-        return
+        return output_file
 
     if options.jpeg_quality == 0:
         options.jpeg_quality = DEFAULT_JPEG_QUALITY if options.optimize < 3 else 40
@@ -660,9 +655,7 @@ def optimize(
             f"Output file not created after optimizing. We probably ran "
             f"out of disk space in the temporary folder: {tempfile.gettempdir()}."
         )
-    ratio = input_size / output_size
     savings = 1 - output_size / input_size
-    log.info(f"Optimize ratio: {ratio:.2f} savings: {(savings):.1%}")
 
     if savings < 0:
         log.info(
@@ -676,6 +669,8 @@ def optimize(
     else:
         safe_symlink(target_file, output_file)
 
+    return output_file
+
 
 def main(infile, outfile, level, jobs=1):
     from shutil import copy  # pylint: disable=import-outside-toplevel
@@ -707,9 +702,9 @@ def main(infile, outfile, level, jobs=1):
         jb2lossy=False,
     )
 
-    with TemporaryDirectory() as td:
+    with TemporaryDirectory() as tmpdir:
-        context = PdfContext(options, td, infile, None, None)
+        context = PdfContext(options, tmpdir, infile, None, None)
-        tmpout = Path(td) / 'out.pdf'
+        tmpout = Path(tmpdir) / 'out.pdf'
         optimize(
             infile,
             tmpout,

src/ocrmypdf/pdfa.py

@@ -9,14 +9,16 @@
 Utilities for PDF/A production and confirmation with Ghostspcript.
 """
 
+from __future__ import annotations
+
 import base64
 from pathlib import Path
-from typing import Dict, Iterator, Union
+from typing import Iterator
 
 try:
-    from importlib_resources import files as package_files
-except ImportError:
     from importlib.resources import files as package_files
+except ImportError:
+    from importlib_resources import files as package_files  # type: ignore
 
 import pikepdf
 
@@ -25,7 +27,7 @@ SRGB_ICC_PROFILE_NAME = 'sRGB.icc'
 
 def _postscript_objdef(
     alias: str,
-    dictionary: Dict[str, str],
+    dictionary: dict[str, str],
     *,
     stream_name: str = None,
     stream_data: bytes = None,
@@ -97,7 +99,8 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
         target_filename: filename to save
         icc: ICC identifier such as 'sRGB'
     References:
-        Adobe PDFMARK Reference: https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
+        Adobe PDFMARK Reference:
+        https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/pdfmark_reference.pdf
     """
     if icc != 'sRGB':
         raise NotImplementedError("Only supporting sRGB")
@@ -105,11 +108,11 @@ def generate_pdfa_ps(target_filename: Path, icc: str = 'sRGB'):
     bytes_icc_profile = (
         package_files('ocrmypdf.data') / SRGB_ICC_PROFILE_NAME
     ).read_bytes()
-    ps = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))
+    postscript = '\n'.join(_make_postscript(icc, bytes_icc_profile, 3))
 
     # We should have encoded everything to pure ASCII by this point, and
     # to be safe, only allow ASCII in PostScript
-    Path(target_filename).write_text(ps, encoding='ascii')
+    Path(target_filename).write_text(postscript, encoding='ascii')
     return target_filename
 
 
@@ -130,7 +133,7 @@ def file_claims_pdfa(filename: Path):
             }
         valid_part_conforms = {'1A', '1B', '2A', '2B', '2U', '3A', '3B', '3U'}
         conformance = f'PDF/A-{pdfmeta.pdfa_status}'
-        pdfa_dict: Dict[str, Union[str, bool]] = {}
+        pdfa_dict: dict[str, str | bool] = {}
         if pdfmeta.pdfa_status in valid_part_conforms:
             pdfa_dict['pass'] = True
             pdfa_dict['output'] = 'pdfa'

src/ocrmypdf/pdfinfo/__init__.py

@@ -6,4 +6,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""For extracting information about PDFs prior to OCR."""
+
+from __future__ import annotations
+
 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo

src/ocrmypdf/pdfinfo/info.py

@@ -6,28 +6,30 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+"""Extract information about the content of a PDF."""
+
+from __future__ import annotations
+
 import atexit
 import logging
 import re
 from collections import defaultdict
 from contextlib import ExitStack
 from decimal import Decimal
-from enum import Enum
+from enum import Enum, auto
 from functools import partial
 from math import hypot, inf, isclose
 from os import PathLike
 from pathlib import Path
 from typing import (
     Container,
-    Dict,
+    Iterable,
     Iterator,
-    List,
     Mapping,
     NamedTuple,
     Optional,
     Sequence,
     Tuple,
-    Union,
 )
 from warnings import warn
 
@@ -37,6 +39,7 @@ from pikepdf import (
     PdfImage,
     PdfInlineImage,
     PdfMatrix,
+    UnsupportedImageTypeError,
     parse_content_stream,
 )
 
@@ -47,13 +50,41 @@ from ocrmypdf.pdfinfo.layout import get_page_analysis, get_text_boxes
 
 logger = logging.getLogger()
 
-Colorspace = Enum('Colorspace', 'gray rgb cmyk lab icc index sep devn pattern jpeg2000')
 
-Encoding = Enum(
+class Colorspace(Enum):
-    'Encoding', 'ccitt jpeg jpeg2000 jbig2 asciihex ascii85 lzw flate runlength'
+    """Description of common image colorspaces in a PDF."""
-)
 
-FRIENDLY_COLORSPACE: Dict[str, Colorspace] = {
+    # pylint: disable=invalid-name
+    gray = auto()
+    rgb = auto()
+    cmyk = auto()
+    lab = auto()
+    icc = auto()
+    index = auto()
+    sep = auto()
+    devn = auto()
+    pattern = auto()
+    jpeg2000 = auto()
+
+
+class Encoding(Enum):
+    """Description of common image encodings in a PDF."""
+
+    # pylint: disable=invalid-name
+    ccitt = auto()
+    jpeg = auto()
+    jpeg2000 = auto()
+    jbig2 = auto()
+    asciihex = auto()
+    ascii85 = auto()
+    lzw = auto()
+    flate = auto()
+    runlength = auto()
+
+
+FloatRect = Tuple[float, float, float, float]
+
+FRIENDLY_COLORSPACE: dict[str, Colorspace] = {
     '/DeviceGray': Colorspace.gray,
     '/CalGray': Colorspace.gray,
     '/DeviceRGB': Colorspace.rgb,
@@ -71,7 +102,7 @@ FRIENDLY_COLORSPACE: Dict[str, Colorspace] = {
     '/I': Colorspace.index,
 }
 
-FRIENDLY_ENCODING: Dict[str, Encoding] = {
+FRIENDLY_ENCODING: dict[str, Encoding] = {
     '/CCITTFaxDecode': Encoding.ccitt,
     '/DCTDecode': Encoding.jpeg,
     '/JPXDecode': Encoding.jpeg2000,
@@ -85,7 +116,7 @@ FRIENDLY_ENCODING: Dict[str, Encoding] = {
     '/RL': Encoding.runlength,
 }
 
-FRIENDLY_COMP: Dict[Colorspace, int] = {
+FRIENDLY_COMP: dict[Colorspace, int] = {
     Colorspace.gray: 1,
     Colorspace.rgb: 3,
     Colorspace.cmyk: 4,
@@ -104,37 +135,45 @@ def _is_unit_square(shorthand):
 
 
 class XobjectSettings(NamedTuple):
+    """Info about an XObject found in a PDF."""
+
     name: str
-    shorthand: Tuple[float, float, float, float, float, float]
+    shorthand: tuple[float, float, float, float, float, float]
     stack_depth: int
 
 
 class InlineSettings(NamedTuple):
+    """Info about an inline image found in a PDF."""
+
     iimage: PdfInlineImage
-    shorthand: Tuple[float, float, float, float, float, float]
+    shorthand: tuple[float, float, float, float, float, float]
     stack_depth: int
 
 
 class ContentsInfo(NamedTuple):
-    xobject_settings: List[XobjectSettings]
+    """Info about various objects found in a PDF."""
-    inline_images: List[InlineSettings]
+
+    xobject_settings: list[XobjectSettings]
+    inline_images: list[InlineSettings]
     found_vector: bool
     found_text: bool
-    name_index: Mapping[str, List[XobjectSettings]]
+    name_index: Mapping[str, list[XobjectSettings]]
 
 
 class TextboxInfo(NamedTuple):
-    bbox: Tuple[float, float, float, float]
+    """Info about a text box found in a PDF."""
+
+    bbox: tuple[float, float, float, float]
     is_visible: bool
     is_corrupt: bool
 
 
 class VectorMarker:
-    pass
+    """Sentinel indicating vector drawing operations were found on a page."""
 
 
 class TextMarker:
-    pass
+    """Sentinel indicating text drawing operations were found on a page."""
 
 
 def _normalize_stack(graphobjs):
@@ -177,8 +216,8 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
 
     stack = []
     ctm = PdfMatrix(initial_shorthand)
-    xobject_settings: List[XobjectSettings] = []
+    xobject_settings: list[XobjectSettings] = []
-    inline_images: List[InlineSettings] = []
+    inline_images: list[InlineSettings] = []
     name_index = defaultdict(lambda: [])
     found_vector = False
     found_text = False
@@ -196,7 +235,7 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):
             if len(stack) > 32:  # See docstring
                 if len(stack) > 128:
                     raise RuntimeError(
-                        "PDF graphics stack overflowed hard limit, operator %i" % n
+                        f"PDF graphics stack overflowed hard limit at operator {n}"
                     )
                 warn("PDF graphics stack overflowed spec limit")
         elif operator == 'Q':
@@ -282,7 +321,7 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
 
     """
 
-    a, b, c, d, _, _ = ctm_shorthand
+    a, b, c, d, _, _ = ctm_shorthand  # pylint: disable=invalid-name
 
     # Calculate the width and height of the image in PDF units
     image_drawn = hypot(a, b), hypot(c, d)
@@ -298,23 +337,25 @@ def _get_dpi(ctm_shorthand, image_size) -> Resolution:
 
 
 class ImageInfo:
+    """Information about an image found in a PDF."""
+
     DPI_PREC = Decimal('1.000')
 
-    _comp: Optional[int]
+    _comp: int | None
     _name: str
 
     def __init__(
         self,
         *,
         name='',
-        pdfimage: Optional[Object] = None,
+        pdfimage: Object | None = None,
-        inline: Optional[PdfInlineImage] = None,
+        inline: PdfInlineImage | None = None,
         shorthand=None,
     ):
         self._name = str(name)
         self._shorthand = shorthand
 
-        pim: Union[PdfInlineImage, PdfImage]
+        pim: PdfInlineImage | PdfImage
 
         if inline is not None:
             self._origin = 'inline'
@@ -350,13 +391,20 @@ class ImageInfo:
 
         if self._color == Colorspace.icc:
             # Check the ICC profile to determine actual colorspace
-            pim_icc = pim.icc
+            try:
-            if pim_icc.profile.xcolor_space == 'GRAY':
+                pim_icc = pim.icc
-                self._comp = 1
+                if pim_icc.profile.xcolor_space == 'GRAY':
-            elif pim_icc.profile.xcolor_space == 'CMYK':
+                    self._comp = 1
-                self._comp = 4
+                elif pim_icc.profile.xcolor_space == 'CMYK':
-            else:
+                    self._comp = 4
-                self._comp = 3
+                else:
+                    self._comp = 3
+            except (AttributeError, UnsupportedImageTypeError) as ex:
+                self._comp = None
+                logger.warning(
+                    f"An image with a corrupt or unreadable ICC profile was found. "
+                    f"The output PDF may not match the input PDF visually: {ex}. {self}"
+                )
         else:
             if isinstance(self._color, Colorspace):
                 self._comp = FRIENDLY_COMP.get(self._color)
@@ -409,15 +457,10 @@ class ImageInfo:
         return _get_dpi(self._shorthand, (self._width, self._height))
 
     def __repr__(self):
-        class_locals = {
-            attr: getattr(self, attr, None)
-            for attr in dir(self)
-            if not attr.startswith('_')
-        }
         return (
-            "<ImageInfo '{name}' {type_} {width}x{height} {color} "
+            f"<ImageInfo '{self.name}' {self.type_} {self.width}x{self.height} "
-            "{comp} {bpc} {enc} {dpi}>"
+            f"{self.color} {self.comp} {self.bpc} {self.enc} {self.dpi}>"
-        ).format(**class_locals)
+        )
 
 
 def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
@@ -425,11 +468,11 @@ def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
 
     for n, inline in enumerate(contentsinfo.inline_images):
         yield ImageInfo(
-            name='inline-%02d' % n, shorthand=inline.shorthand, inline=inline.iimage
+            name=f'inline-{n:02d}', shorthand=inline.shorthand, inline=inline.iimage
         )
 
 
-def _image_xobjects(container) -> Iterator[Tuple[Object, str]]:
+def _image_xobjects(container) -> Iterator[tuple[Object, str]]:
     """Search for all XObject-based images in the container
 
     Usually the container is a page, but it could also be a Form XObject
@@ -517,7 +560,7 @@ def _find_form_xobject_images(pdf: Pdf, container: Object, contentsinfo: Content
 
 def _process_content_streams(
     *, pdf: Pdf, container: Object, shorthand=None
-) -> Iterator[Union[VectorMarker, TextMarker, ImageInfo]]:
+) -> Iterator[VectorMarker | TextMarker | ImageInfo]:
     """Find all individual instances of images drawn in the container
 
     Usually the container is a page, but it may also be a Form XObject.
@@ -566,10 +609,10 @@ def _process_content_streams(
     yield from _find_form_xobject_images(pdf, container, contentsinfo)
 
 
-def _page_has_text(text_blocks, page_width, page_height) -> bool:
+def _page_has_text(text_blocks: Iterable[FloatRect], page_width, page_height) -> bool:
     """Smarter text detection that ignores text in margins"""
 
-    pw, ph = float(page_width), float(page_height)
+    pw, ph = float(page_width), float(page_height)  # pylint: disable=invalid-name
 
     margin_ratio = 0.125
     interior_bbox = (
@@ -579,7 +622,7 @@ def _page_has_text(text_blocks, page_width, page_height) -> bool:
         margin_ratio * ph,  # bottom  (first quadrant: bottom < top)
     )
 
-    def rects_intersect(a, b) -> bool:
+    def rects_intersect(a: FloatRect, b: FloatRect) -> bool:
         """
         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
@@ -601,19 +644,19 @@ def simplify_textboxes(miner, textbox_getter) -> Iterator[TextboxInfo]:
     We do this to save memory and ensure that our objects are pickleable.
     """
     for box in textbox_getter(miner):
-        first_line = box._objs[0]
+        first_line = box._objs[0]  # pylint: disable=protected-access
-        first_char = first_line._objs[0]
+        first_char = first_line._objs[0]  # pylint: disable=protected-access
 
         visible = first_char.rendermode != 3
         corrupt = first_char.get_text() == '\ufffd'
         yield TextboxInfo(box.bbox, visible, corrupt)
 
 
-worker_pdf = None
+worker_pdf = None  # pylint: disable=invalid-name
 
 
 def _pdf_pageinfo_sync_init(pdf: Pdf, infile: Path, pdfminer_loglevel):
-    global worker_pdf  # pylint: disable=global-statement
+    global worker_pdf  # pylint: disable=global-statement,invalid-name
     pikepdf_enable_mmap()
 
     logging.getLogger('pdfminer').setLevel(pdfminer_loglevel)
@@ -647,8 +690,8 @@ def _pdf_pageinfo_concurrent(
     max_workers,
     check_pages,
     detailed_analysis=False,
-) -> Sequence[Optional['PageInfo']]:
+) -> Sequence[PageInfo | None]:
-    pages: Sequence[Optional['PageInfo']] = [None] * len(pdf.pages)
+    pages: Sequence[PageInfo | None] = [None] * len(pdf.pages)
 
     def update_pageinfo(result, pbar):
         page = result
@@ -698,9 +741,11 @@ def _pdf_pageinfo_concurrent(
 
 
 class PageInfo:
-    _has_text: Optional[bool]
+    """Information about type of contents on each page in a PDF."""
-    _has_vector: Optional[bool]
+
-    _images: List[ImageInfo]
+    _has_text: bool | None
+    _has_vector: bool | None
+    _images: list[ImageInfo]
 
     def __init__(
         self,
@@ -759,15 +804,15 @@ class PageInfo:
             self._has_vector = False
             self._has_text = False
             self._images = []
-            for ci in _process_content_streams(
+            for info in _process_content_streams(
                 pdf=pdf, container=page, shorthand=userunit_shorthand
             ):
-                if isinstance(ci, VectorMarker):
+                if isinstance(info, VectorMarker):
                     self._has_vector = True
-                elif isinstance(ci, TextMarker):
+                elif isinstance(info, TextMarker):
                     self._has_text = True
-                elif isinstance(ci, ImageInfo):
+                elif isinstance(info, ImageInfo):
-                    self._images.append(ci)
+                    self._images.append(info)
                 else:
                     raise NotImplementedError()
         else:
@@ -833,9 +878,7 @@ class PageInfo:
     def images(self):
         return self._images
 
-    def get_textareas(
+    def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
-        self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
-    ):
         def predicate(obj, want_visible, want_corrupt):
             result = True
             if want_visible is not None:
@@ -919,7 +962,7 @@ class PdfInfo:
                     self._has_acroform = True
 
     @property
-    def pages(self) -> Sequence[Optional[PageInfo]]:
+    def pages(self) -> Sequence[PageInfo | None]:
         return self._pages
 
     @property
@@ -936,7 +979,7 @@ class PdfInfo:
         return self._has_acroform
 
     @property
-    def filename(self) -> Union[str, Path]:
+    def filename(self) -> str | Path:
         if not isinstance(self._infile, (str, Path)):
             raise NotImplementedError("can't get filename from stream")
         return self._infile

src/ocrmypdf/pdfinfo/layout.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import re
 from math import copysign
 from pathlib import Path

src/ocrmypdf/pluginspec.py

@@ -4,16 +4,19 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+"""OCRmyPDF pluggy plugin specification."""
+
+from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from argparse import ArgumentParser, Namespace
 from logging import Handler
 from pathlib import Path
-from typing import TYPE_CHECKING, AbstractSet, List, NamedTuple, Optional
+from typing import TYPE_CHECKING, AbstractSet, NamedTuple, Sequence
 
 import pluggy
 
-from ocrmypdf._concurrent import Executor
+from ocrmypdf import Executor, PdfContext
 from ocrmypdf.helpers import Resolution
 
 if TYPE_CHECKING:
@@ -42,6 +45,33 @@ def get_logging_console() -> Handler:
     """
 
 
+@hookspec
+def initialize(plugin_manager: pluggy.PluginManager):
+    """Called when this plugin is first loaded into OCRmyPDF.
+
+    The primary intended use of this is for plugins to check compatibility with other
+    plugins and possibly block other blocks, a plugin that wishes to block ocrmypdf's
+    built-in optimize plugin could do:
+
+    .. code-block::
+
+        plugin_manager.set_blocked('ocrmypdf.builtin_plugins.optimize')
+
+    It would also be reasonable for an plugin implementation to check if it is unable
+    to proceed, for example, because a required dependency is missing. (If the plugin's
+    ability to proceed depends on options and arguments, use ``validate`` instead.)
+
+    Raises:
+        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.
+    """
+
+
 @hookspec
 def add_options(parser: ArgumentParser) -> None:
     """Allows the plugin to add its own command line and API arguments.
@@ -141,7 +171,7 @@ def get_progressbar_class():
 
 
 @hookspec
-def validate(pdfinfo: 'PdfInfo', options: Namespace) -> None:
+def validate(pdfinfo: PdfInfo, options: Namespace) -> None:
     """Called to give a plugin an opportunity to review *options* and *pdfinfo*.
 
     *options* contains the "work order" to process a particular file. *pdfinfo*
@@ -167,8 +197,8 @@ def rasterize_pdf_page(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int,
-    page_dpi: Optional[Resolution],
+    page_dpi: Resolution | None,
-    rotation: Optional[int],
+    rotation: int | None,
     filter_vector: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
@@ -197,7 +227,7 @@ def rasterize_pdf_page(
 
 
 @hookspec(firstresult=True)
-def filter_ocr_image(page: 'PageContext', image: 'Image.Image') -> 'Image.Image':
+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
@@ -224,7 +254,7 @@ def filter_ocr_image(page: 'PageContext', image: 'Image.Image') -> 'Image.Image'
 
 
 @hookspec(firstresult=True)
-def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
+def filter_page_image(page: PageContext, image_filename: Path) -> Path:
     """Called to filter the whole page before it is inserted into the PDF.
 
     A whole page image is only produced when preprocessing command line arguments
@@ -264,9 +294,7 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
 
 
 @hookspec(firstresult=True)
-def filter_pdf_page(
+def filter_pdf_page(page: PageContext, image_filename: Path, output_pdf: Path) -> Path:
-    page: 'PageContext', image_filename: Path, output_pdf: Path
-) -> Path:
     """Called to convert a filtered whole page image into a PDF.
 
     A whole page image is only produced when preprocessing command line arguments
@@ -409,7 +437,7 @@ def get_ocr_engine() -> OcrEngine:
 
 @hookspec(firstresult=True)
 def generate_pdfa(
-    pdf_pages: List[Path],
+    pdf_pages: list[Path],
     pdfmark: Path,
     output_file: Path,
     compression: str,
@@ -456,3 +484,63 @@ def generate_pdfa(
     See also:
         https://github.com/tqdm/tqdm
     """
+
+
+@hookspec(firstresult=True)
+def optimize_pdf(
+    input_pdf: Path,
+    output_pdf: Path,
+    context: PdfContext,
+    executor: Executor,
+    linearize: bool,
+) -> tuple[Path, Sequence[str]]:
+    """Optimize a PDF after image, OCR and metadata processing.
+
+    If the input_pdf is a PDF/A, the plugin should modify input_pdf in a way
+    that preserves the PDF/A status, or report to the user when this is not possible.
+
+    If the implementation fails to produce a smaller file than the input file, it
+    should return input_pdf instead.
+
+    A plugin that implements a new optimizer may need to suppress the built-in
+    optimizer by implementing an ``initialize`` hook.
+
+    Arguments:
+        input_pdf: The input PDF, which has OCR added.
+        output_pdf: The requested filename of the output PDF which should be created
+            by this optimization hook.
+        context: The current context.
+        executor: An initialized executor which may be used during optimization,
+            to distribute optimization tasks.
+        linearize: If True, OCRmyPDF requires ``optimize_pdf`` to return a linearized,
+            also known as fast web view PDF.
+
+    Returns:
+        Path: If optimization is successful, the hook should return ``output_file``.
+            If optimization does not produce a smaller file, the hook should return
+            ``input_file``.
+        Sequence[str]: Any comments that the plugin wishes to report to the user,
+            especially reasons it was not able to further optimize the file. For
+            example, the plugin could report that a required third party was not
+            installed, so a specific optimization was not attempted.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """
+
+
+@hookspec(firstresult=True)
+def is_optimization_enabled(context: PdfContext) -> bool:
+    """For a given PdfContext, OCRmyPDF asks the plugin if optimization is enabled.
+
+    An optimization plugin might be installed and active but could be disabled by
+    user settings.
+
+    If this returns False, OCRmyPDF will take certain actions to finalize the PDF.
+
+    Returns:
+        True if the plugin's optimization is enabled.
+
+    Note:
+        This is a :ref:`firstresult hook<firstresult>`.
+    """

src/ocrmypdf/quality.py

@@ -8,6 +8,8 @@
 """Utilities to measure OCR quality"""
 
 
+from __future__ import annotations
+
 import re
 from typing import Iterable
 

src/ocrmypdf/subprocess/__init__.py

@@ -7,16 +7,18 @@
 
 """Wrappers to manage subprocess calls"""
 
+from __future__ import annotations
+
 import logging
 import os
 import re
 import sys
-from collections.abc import Mapping
 from contextlib import suppress
 from functools import lru_cache
+from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Optional, Type, Union
+from typing import Callable, Mapping, Sequence, Union
 
 from packaging.version import Version
 
@@ -26,9 +28,17 @@ from ocrmypdf.exceptions import MissingDependencyError
 
 log = logging.getLogger(__name__)
 
+Args = Sequence[Union[Path, str]]
+OsEnviron = os._Environ  # pylint: disable=protected-access
+
 
 def run(
-    args, *, env=None, logs_errors_to_stdout: bool = False, **kwargs
+    args: Args,
+    *,
+    env: OsEnviron | None = None,
+    logs_errors_to_stdout: bool = False,
+    check: bool = False,
+    **kwargs,
 ) -> CompletedProcess:
     """Wrapper around :py:func:`subprocess.run`
 
@@ -50,7 +60,7 @@ def run(
     stderr = None
     stderr_name = 'stderr' if not logs_errors_to_stdout else 'stdout'
     try:
-        proc = subprocess_run(args, env=env, **kwargs)
+        proc = subprocess_run(args, env=env, check=check, **kwargs)
     except CalledProcessError as e:
         stderr = getattr(e, stderr_name, None)
         raise
@@ -68,7 +78,12 @@ def run(
 
 
 def run_polling_stderr(
-    args, *, callback: Callable[[str], None], check: bool = False, env=None, **kwargs
+    args: Args,
+    *,
+    callback: Callable[[str], None],
+    check: bool = False,
+    env: OsEnviron | None = None,
+    **kwargs,
 ) -> CompletedProcess:
     """Run a process like ``ocrmypdf.subprocess.run``, and poll stderr.
 
@@ -101,7 +116,9 @@ def run_polling_stderr(
         return CompletedProcess(args, proc.returncode, None, stderr=stderr)
 
 
-def _fix_process_args(args, env, kwargs):
+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:
@@ -110,21 +127,26 @@ def _fix_process_args(args, env, kwargs):
     # Search in spoof path if necessary
     program = str(args[0])
 
-    if os.name == 'nt':
+    if sys.platform == 'win32':
+        # pylint: disable=import-outside-toplevel
         from ocrmypdf.subprocess._windows import fix_windows_args
 
         args = fix_windows_args(program, args, env)
 
     log.debug("Running: %s", args)
     process_log = log.getChild(os.path.basename(program))
-    text = kwargs.get('text', False)
+    text = bool(kwargs.get('text', False))
 
     return args, env, process_log, text
 
 
 @lru_cache(maxsize=None)
 def get_version(
-    program: str, *, version_arg: str = '--version', regex=r'(\d+(\.\d+)*)', env=None
+    program: str,
+    *,
+    version_arg: str = '--version',
+    regex=r'(\d+(\.\d+)*)',
+    env: OsEnviron | None = None,
 ) -> str:
     """Get the version of the specified program
 
@@ -171,42 +193,42 @@ def get_version(
     return version
 
 
-missing_program = '''
+MISSING_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.
 '''
 
-missing_optional_program = '''
+MISSING_OPTIONAL_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.  This program is required when you use the
 {required_for} arguments.  You could try omitting these arguments, or install
 the package.
 '''
 
-missing_recommend_program = '''
+MISSING_RECOMMEND_PROGRAM = '''
 The program '{program}' could not be executed or was not found on your
 system PATH.  This program is recommended when using the {required_for} arguments,
 but not required, so we will proceed.  For best results, install the program.
 '''
 
-old_version = '''
+OLD_VERSION = '''
 OCRmyPDF requires '{program}' {need_version} or higher.  Your system appears
 to have {found_version}.  Please update this program.
 '''
 
-old_version_required_for = '''
+OLD_VERSION_REQUIRED_FOR = '''
 OCRmyPDF requires '{program}' {need_version} or higher when run with the
 {required_for} arguments.  If you omit these arguments, OCRmyPDF may be able to
 proceed.  For best results, install the program.
 '''
 
-osx_install_advice = '''
+OSX_INSTALL_ADVICE = '''
 If you have homebrew installed, try these command to install the missing
 package:
     brew install {package}
 '''
 
-linux_install_advice = '''
+LINUX_INSTALL_ADVICE = '''
 On systems with the aptitude package manager (Debian, Ubuntu), try these
 commands:
     sudo apt-get update
@@ -216,14 +238,14 @@ On RPM-based systems (Red Hat, Fedora), search for instructions on
 installing the RPM for {program}.
 '''
 
-windows_install_advice = '''
+WINDOWS_INSTALL_ADVICE = '''
 If not already installed, install the Chocolatey package manager. Then use
 a command prompt to install the missing package:
     choco install {package}
 '''
 
 
-def _get_platform():
+def _get_platform() -> str:
     if sys.platform.startswith('freebsd'):
         return 'freebsd'
     elif sys.platform.startswith('linux'):
@@ -233,46 +255,66 @@ def _get_platform():
     return sys.platform
 
 
-def _error_trailer(program, package, **kwargs):
+def _error_trailer(program: str, package: str | Mapping[str, str], **kwargs) -> None:
+    del kwargs
     if isinstance(package, Mapping):
         package = package.get(_get_platform(), program)
 
     if _get_platform() == 'darwin':
-        log.info(osx_install_advice.format(**locals()))
+        log.info(OSX_INSTALL_ADVICE.format(**locals()))
     elif _get_platform() == 'linux':
-        log.info(linux_install_advice.format(**locals()))
+        log.info(LINUX_INSTALL_ADVICE.format(**locals()))
     elif _get_platform() == 'windows':
-        log.info(windows_install_advice.format(**locals()))
+        log.info(WINDOWS_INSTALL_ADVICE.format(**locals()))
 
 
-def _error_missing_program(program, package, required_for, recommended):
+def _error_missing_program(
+    program: str, package: str, required_for: str | None, recommended: bool
+) -> None:
+    # pylint: disable=unused-argument
     if recommended:
-        log.warning(missing_recommend_program.format(**locals()))
+        log.warning(MISSING_RECOMMEND_PROGRAM.format(**locals()))
     elif required_for:
-        log.error(missing_optional_program.format(**locals()))
+        log.error(MISSING_OPTIONAL_PROGRAM.format(**locals()))
     else:
-        log.error(missing_program.format(**locals()))
+        log.error(MISSING_PROGRAM.format(**locals()))
     _error_trailer(**locals())
 
 
-def _error_old_version(program, package, need_version, found_version, required_for):
+def _error_old_version(
+    program: str,
+    package: str,
+    need_version: str,
+    found_version: str,
+    required_for: str | None,
+) -> None:
+    # pylint: disable=unused-argument
     if required_for:
-        log.error(old_version_required_for.format(**locals()))
+        log.error(OLD_VERSION_REQUIRED_FOR.format(**locals()))
     else:
-        log.error(old_version.format(**locals()))
+        log.error(OLD_VERSION.format(**locals()))
     _error_trailer(**locals())
 
 
+def _remove_leading_v(s: str) -> str:
+    if sys.version_info >= (3, 9):
+        return s.removeprefix('v')
+
+    if s.startswith('v'):
+        return s[1:]
+    return s
+
+
 def check_external_program(
     *,
     program: str,
     package: str,
-    version_checker: Callable,
+    version_checker: Callable[[], str],
     need_version: str,
-    required_for: Optional[str] = None,
+    required_for: str | None = None,
-    recommended=False,
+    recommended: bool = False,
-    version_parser: Type[Version] = Version,
+    version_parser: type[Version] = Version,
-):
+) -> None:
     """Check for required version of external program and raise exception if not.
 
     Args:
@@ -294,19 +336,19 @@ def check_external_program(
             found_version = version_checker()
         else:  # deprecated
             found_version = version_checker
-    except (CalledProcessError, FileNotFoundError, MissingDependencyError):
+    except (CalledProcessError, FileNotFoundError) as e:
         _error_missing_program(program, package, required_for, recommended)
         if not recommended:
-            raise MissingDependencyError(program)
+            raise MissingDependencyError(program) from e
+        return
+    except MissingDependencyError:
+        _error_missing_program(program, package, required_for, recommended)
+        if not recommended:
+            raise
         return
 
-    def remove_leading_v(s):
+    found_version = _remove_leading_v(found_version)
-        if s.startswith('v'):
+    need_version = _remove_leading_v(need_version)
-            return s[1:]
-        return s
-
-    found_version = remove_leading_v(found_version)
-    need_version = remove_leading_v(need_version)
 
     if found_version and version_parser(found_version) < version_parser(need_version):
         _error_old_version(program, package, need_version, found_version, required_for)

src/ocrmypdf/subprocess/_windows.py

@@ -3,9 +3,9 @@
 # This Source Code Form is subject to the terms of the Mozilla Public
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
+"""Find Tesseract and Ghostscript binaries on Windows using the registry."""
 
-# type: ignore
+from __future__ import annotations
-# Non-Windows mypy now breaks when trying to typecheck winreg
 
 import logging
 import os
@@ -13,12 +13,26 @@ import shutil
 import sys
 from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
+from typing import Any, Callable, Iterable, Iterator, TypeVar
 
-try:
+if sys.version_info >= (3, 10):
-    import winreg
+    from typing import TypeAlias
-except ModuleNotFoundError as e:
+else:
-    raise ModuleNotFoundError("This module is for Windows only") from e
+    from typing_extensions import TypeAlias  # pragma: no cover
+
+if sys.platform == 'win32':
+    # mypy understands 'if sys.platform' better than try/except ModuleNotFoundError
+    import winreg  # pylint: disable=import-error
+
+    HKEYType: TypeAlias = winreg.HKEYType
+else:
+    from unittest.mock import Mock
+
+    winreg = Mock(
+        spec=['HKEYType', 'EnumKey', 'EnumValue', 'HKEY_LOCAL_MACHINE', 'OpenKey']
+    )
+    # mypy does not understand winreg.HKeyType where winreg is a Mock (fair enough!)
+    HKEYType: TypeAlias = Any
 
 
 log = logging.getLogger(__name__)
@@ -26,7 +40,7 @@ log = logging.getLogger(__name__)
 T = TypeVar('T')
 
 
-def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
+def ghostscript_version_key(s: str) -> tuple[int, int, int]:
     """Compare Ghostscript version numbers."""
     try:
         release = [int(elem) for elem in s.split('.', maxsplit=3)]
@@ -37,30 +51,29 @@ def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
         return (0, 0, 0)
 
 
-def registry_enum(
+def registry_enum(key: HKEYType, enum_fn: Callable[[HKEYType, int], T]) -> Iterator[T]:
-    key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
+    limit = 999
-) -> Iterator[T]:
-    LIMIT = 999
     n = 0
-    while n < LIMIT:
+    while n < limit:
         try:
             yield enum_fn(key, n)
             n += 1
         except OSError:
             break
-    if n == LIMIT:
+    if n == limit:
         raise ValueError(f"Too many registry keys under {key}")
 
 
-def registry_subkeys(key: winreg.HKEYType) -> Iterator[str]:
+def registry_subkeys(key: HKEYType) -> Iterator[str]:
     return registry_enum(key, winreg.EnumKey)
 
 
-def registry_values(key: winreg.HKEYType) -> Iterator[Tuple[str, Any, int]]:
+def registry_values(key: HKEYType) -> Iterator[tuple[str, Any, int]]:
     return registry_enum(key, winreg.EnumValue)
 
 
 def registry_path_ghostscript(env=None) -> Iterator[Path]:
+    del env  # unused (but needed for protocol)
     try:
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Artifex\GPL Ghostscript"
@@ -71,13 +84,14 @@ def registry_path_ghostscript(env=None) -> Iterator[Path]:
         with winreg.OpenKey(
             winreg.HKEY_LOCAL_MACHINE, fr"SOFTWARE\Artifex\GPL Ghostscript\{latest_gs}"
         ) as k:
-            _, gs_path, _ = next(registry_values(k))
+            for _, gs_path, _ in registry_values(k):
-            yield Path(gs_path) / 'bin'
+                yield Path(gs_path) / 'bin'
     except OSError as e:
         log.warning(e)
 
 
 def registry_path_tesseract(env=None) -> Iterator[Path]:
+    del env  # unused (but needed for protocol)
     try:
         with winreg.OpenKey(winreg.HKEY_LOCAL_MACHINE, r"SOFTWARE\Tesseract-OCR") as k:
             for subkey, val, _valtype in registry_values(k):
@@ -157,7 +171,7 @@ def unique_everseen(iterable: Iterable[T], key: Callable[[T], T]) -> Iterator[T]
     "List unique elements, preserving order."
     # unique_everseen('AAAABBBCCDAABBB') --> A B C D
     # unique_everseen('ABBCcAD', str.lower) --> A B C D
-    seen: Set[T] = set()
+    seen: set[T] = set()
     seen_add = seen.add
     for element in iterable:
         k = key(element)

tests/__init__.py

@@ -4,4 +4,6 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 # Empty __init__.py file

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt/stderr.bin

@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica

tests/cache/francais/__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt/txt.bin

@@ -0,0 +1,13 @@
+Portez ce vieux whisky au juge
+blond qui fume sur son Ile
+interieure, a cöte de l'alcöve
+ovoide, oU les büches se
+consument dans l'ätre, ce qui
+lui permet de penser & la
+caenogenese de |'etre dont il
+est question dans la cause
+ambigu& entendue a MoY, dans
+un capharnaüm qui, pense-t-il,
+diminue ca et la la qualite de son
+ceuvre.
+

tests/cache/manifest.jsonl

@@ -82,3 +82,4 @@
 {"tesseract_version": "4.1.1", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__--oem__1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "--oem", "1", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=1__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
 {"tesseract_version": "5.0.0", "system": "Linux", "python": "3.9.5", "argv_slug": "__-l__eng__thresholding_method=2__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/trivial.pdf", "args": ["-l", "eng", "-c", "textonly_pdf=1", "-c", "thresholding_method=2", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}
+{"tesseract_version": "4.1.1", "system": "Linux", "python": "3.10.4", "argv_slug": "__-l__deu__000001_ocr.png__000001_ocr_tess__pdf__txt", "sourcefile": "resources/francais.pdf", "args": ["-l", "deu", "-c", "textonly_pdf=1", "$TMPDIR/000001_ocr.png", "$TMPDIR/000001_ocr_tess", "pdf", "txt"]}

tests/conftest.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import os
 import platform
 import sys
@@ -52,7 +54,7 @@ def resources() -> Path:
 
 
 @pytest.fixture
-def ocrmypdf_exec() -> List[str]:
+def ocrmypdf_exec() -> list[str]:
     return [sys.executable, '-m', 'ocrmypdf']
 
 

tests/plugins/gs_feature_elision.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 from unittest.mock import patch
 
 from ocrmypdf import hookimpl

tests/plugins/gs_pdfa_failure.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 from unittest.mock import patch
 
 from ocrmypdf import hookimpl

tests/plugins/gs_raster_failure.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 from pathlib import Path
 from subprocess import CalledProcessError
 from unittest.mock import patch

tests/plugins/gs_render_failure.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 from subprocess import CalledProcessError
 from unittest.mock import patch
 

tests/plugins/tesseract_badutf8.py

@@ -26,6 +26,8 @@ that is not UTF-8 compatible, so we are forced to check that we can convert it
 and present it to the user.
 """
 
+from __future__ import annotations
+
 from contextlib import contextmanager
 from subprocess import CalledProcessError
 from unittest.mock import patch

tests/plugins/tesseract_big_image_error.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 from contextlib import contextmanager
 from subprocess import CalledProcessError
 from unittest.mock import patch

tests/plugins/tesseract_cache.py

@@ -44,17 +44,19 @@ Assumes Tesseract 4.0.0-alpha or higher.
 
 """
 
+from __future__ import annotations
+
 import argparse
 import json
 import logging
 import platform
 import re
 import shutil
+import threading
 from functools import partial
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError, CompletedProcess
 from unittest.mock import patch
-import threading
 
 from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins.tesseract_ocr import TesseractOcrEngine
@@ -177,28 +179,40 @@ def cached_run(options, run_args, **run_kwargs):
 
 
 class CacheOcrEngine(TesseractOcrEngine):
+    # Concurrent threads (with --use-threads) might try to use different parts
+    # of the OcrEngine, so we need a lock to protect the state of patched
+    # module whenever it's patched. Should refactor ocrmypdf._exec.tesseract so that
+    # it does not to be patched at all for testing.
     lock = threading.Lock()
 
     @staticmethod
     def get_orientation(input_file, options):
-        with CacheOcrEngine.lock, patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
-                return TesseractOcrEngine.get_orientation(input_file, options)
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
+            return TesseractOcrEngine.get_orientation(input_file, options)
 
     @staticmethod
     def get_deskew(input_file, options) -> float:
-        with CacheOcrEngine.lock, patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             return TesseractOcrEngine.get_deskew(input_file, options)
 
     @staticmethod
     def generate_hocr(input_file, output_hocr, output_text, options):
-        with CacheOcrEngine.lock, patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_hocr(
                 input_file, output_hocr, output_text, options
             )
 
     @staticmethod
     def generate_pdf(input_file, output_pdf, output_text, options):
-        with CacheOcrEngine.lock, patch('ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)):
+        with CacheOcrEngine.lock, patch(
+            'ocrmypdf._exec.tesseract.run', new=partial(cached_run, options)
+        ):
             TesseractOcrEngine.generate_pdf(
                 input_file, output_pdf, output_text, options
             )

tests/plugins/tesseract_crash.py

@@ -19,6 +19,8 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
+from __future__ import annotations
+
 import signal
 from contextlib import contextmanager
 from subprocess import CalledProcessError

tests/plugins/tesseract_debug_rotate.py

@@ -31,6 +31,8 @@ In 'pdf' mode, convert the image to PDF using another program.
 In orientation check mode, report 0, 90, 180, 270... based on page number.
 """
 
+from __future__ import annotations
+
 import pikepdf
 from PIL import Image
 

tests/plugins/tesseract_noop.py

@@ -30,6 +30,8 @@ In 'pdf' mode, convert the image to PDF using another program.
 In orientation check mode, report the orientation is upright.
 """
 
+from __future__ import annotations
+
 import pikepdf
 from PIL import Image
 

tests/plugins/tesseract_simulate_oom_killer.py

@@ -19,8 +19,6 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-# type: ignore
-
 """Tesseract no-op plugin that simulates the OOM killer on page 4.
 
 OCRmyPDF can use a lot of memory, even that it might trigger the
@@ -30,14 +28,18 @@ ensure we fail with an error rather than deadlock in such cases.
 Page 4 was chosen because of this number's association with bad luck
 in many East Asian cultures.
 """
+# type: ignore
+from __future__ import annotations
 
 import os
 import signal
-import sys
 from pathlib import Path
 
 from ocrmypdf import hookimpl
 
+# type: ignore
+
+
 # Ugly hack that let us use the NoopOcrEngine without setting up packaging for our
 # tests.
 # This hack also requires us to set type: ignore
@@ -47,7 +49,7 @@ exec(parent)
 NoopOcrEngine = locals()['NoopOcrEngine']
 
 
-class Page4Engine(NoopOcrEngine):
+class Page4Engine(NoopOcrEngine):  # type: ignore
     def __str__(self):
         return f"NO-OP Page 4 {NoopOcrEngine.version()}"
 

tests/test_acroform.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import logging
 
 import pytest

tests/test_api.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import logging
 from io import BytesIO, StringIO
 

tests/test_check_pdf.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import pytest
 
 from ocrmypdf.helpers import check_pdf

tests/test_completion.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import os
 from subprocess import PIPE, run
 

tests/test_concurrency.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 import os
 
 import pytest

tests/test_ghostscript.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import logging
 import subprocess
 from decimal import Decimal

tests/test_graft.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 from unittest.mock import patch
 
 import pikepdf

tests/test_helpers.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import logging
 import multiprocessing
 import os

tests/test_hocrtransform.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import re
 from io import StringIO
 

tests/test_image_input.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 from unittest.mock import patch
 
 import img2pdf

tests/test_logging.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 import logging
 
 import pytest

tests/test_main.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import os
 import shutil
 from math import isclose
@@ -465,12 +467,18 @@ def test_overlay(resources, outpdf):
     )
 
 
-def test_destination_not_writable(resources, outdir):
+@pytest.fixture
-    if os.name != 'nt' and (os.getuid() == 0 or os.geteuid() == 0):
+def protected_file(outdir):
-        pytest.xfail(reason="root can write to anything")
     protected_file = outdir / 'protected.pdf'
     protected_file.touch()
     protected_file.chmod(0o400)  # Read-only
+    yield protected_file
+
+
+@pytest.mark.skipif(
+    os.name == 'nt' or os.geteuid() == 0, reason="root can write to anything"
+)
+def test_destination_not_writable(resources, protected_file):
     p = run_ocrmypdf(
         resources / 'jbig2.pdf',
         protected_file,
@@ -480,7 +488,8 @@ def test_destination_not_writable(resources, outdir):
     assert p.returncode == ExitCode.file_access_error, "Expected error"
 
 
-def test_tesseract_config_valid(resources, outdir):
+@pytest.fixture
+def valid_tess_config(outdir):
     cfg_file = outdir / 'test.cfg'
     with cfg_file.open('w') as f:
         f.write(
@@ -490,20 +499,22 @@ language_model_penalty_non_dict_word 0
 language_model_penalty_non_freq_dict_word 0
 '''
         )
+    yield cfg_file
 
+
+def test_tesseract_config_valid(resources, valid_tess_config, outpdf):
     check_ocrmypdf(
         resources / '3small.pdf',
-        outdir / 'out.pdf',
+        outpdf,
         '--tesseract-config',
-        cfg_file,
+        valid_tess_config,
         '--pages',
         '1',
     )
 
 
-@pytest.mark.slow  # This test sometimes times out in CI
+@pytest.fixture
-@pytest.mark.parametrize('renderer', RENDERERS)
+def invalid_tess_config(outdir):
-def test_tesseract_config_invalid(renderer, resources, outdir):
     cfg_file = outdir / 'test.cfg'
     with cfg_file.open('w') as f:
         f.write(
@@ -511,14 +522,19 @@ def test_tesseract_config_invalid(renderer, resources, outdir):
 THIS FILE IS INVALID
 '''
         )
+    yield cfg_file
 
+
+@pytest.mark.slow  # This test sometimes times out in CI
+@pytest.mark.parametrize('renderer', RENDERERS)
+def test_tesseract_config_invalid(renderer, resources, invalid_tess_config, outpdf):
     p = run_ocrmypdf(
         resources / 'ccitt.pdf',
-        outdir / 'out.pdf',
+        outpdf,
         '--pdf-renderer',
         renderer,
         '--tesseract-config',
-        cfg_file,
+        invalid_tess_config,
     )
     assert (
         "parameter not found" in p.stderr.lower()
@@ -801,6 +817,9 @@ def test_text_curves(resources, outpdf):
         info = PdfInfo(outpdf)
         assert len(info.pages[0].images) == 0, "added images to the vector PDF"
 
+
+def test_text_curves_force(resources, outpdf):
+    with patch('ocrmypdf._pipeline.VECTOR_PAGE_DPI', 100):
         check_ocrmypdf(
             resources / 'vector.pdf',
             outpdf,
@@ -922,3 +941,25 @@ def test_outputtype_none(resources, outtxt):
         'tests/plugins/tesseract_noop.py',
     )
     assert p.returncode == ExitCode.ok
+
+
+@pytest.fixture
+def graph_bad_icc(resources, outdir):
+    synth_input_file = outdir / 'graph-bad-icc.pdf'
+    with pikepdf.open(resources / 'graph.pdf') as pdf:
+        icc = pdf.make_stream(
+            b'invalid icc profile', N=3, Alternate=pikepdf.Name.DeviceRGB
+        )
+        pdf.pages[0].Resources.XObject['/Im0'].ColorSpace = pikepdf.Array(
+            [pikepdf.Name.ICCBased, icc]
+        )
+        pdf.save(synth_input_file)
+        yield synth_input_file
+
+
+def test_corrupt_icc(graph_bad_icc, outpdf, caplog):
+    result = run_ocrmypdf_api(graph_bad_icc, outpdf)
+    assert result == ExitCode.ok
+    assert any(
+        'corrupt or unreadable ICC profile' in rec.message for rec in caplog.records
+    )

tests/test_metadata.py

@@ -5,11 +5,12 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 import datetime
+import warnings
 from datetime import timezone
-from os import fspath
 from shutil import copyfile
-from unittest.mock import patch
 
 import pikepdf
 import pytest
@@ -17,7 +18,7 @@ from pikepdf.models.metadata import decode_pdf_date
 
 from ocrmypdf._jobcontext import PdfContext
 from ocrmypdf._pipeline import convert_to_pdfa, metadata_fixup
-from ocrmypdf._plugin_manager import get_plugin_manager
+from ocrmypdf._plugin_manager import get_parser_options_plugins, get_plugin_manager
 from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfa import file_claims_pdfa, generate_pdfa_ps
@@ -173,6 +174,19 @@ def test_creation_date_preserved(output_type, resources, infile, outpdf):
     assert seconds_between_dates(date_after, datetime.datetime.now(timezone.utc)) < 1000
 
 
+@pytest.fixture
+def libxmp_file_to_dict():
+    try:
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", DeprecationWarning)
+            from libxmp.utils import (
+                file_to_dict,  # pylint: disable=import-outside-toplevel
+            )
+    except Exception:  # pylint: disable=broad-except
+        pytest.skip("libxmp not available or libexempi3 not installed")
+    return file_to_dict
+
+
 @pytest.mark.parametrize(
     'test_file,output_type',
     [
@@ -182,15 +196,12 @@ def test_creation_date_preserved(output_type, resources, infile, outpdf):
         ('3small.pdf', 'pdfa'),
     ],
 )
-def test_xml_metadata_preserved(test_file, output_type, resources, outpdf):
+def test_xml_metadata_preserved(
+    libxmp_file_to_dict, test_file, output_type, resources, outpdf
+):
     input_file = resources / test_file
 
-    try:
+    before = libxmp_file_to_dict(str(input_file))
-        from libxmp.utils import file_to_dict  # pylint: disable=import-outside-toplevel
-    except Exception:  # pylint: disable=broad-except
-        pytest.skip(reason="libxmp not available or libexempi3 not installed")
-
-    before = file_to_dict(str(input_file))
 
     check_ocrmypdf(
         input_file,
@@ -202,7 +213,7 @@ def test_xml_metadata_preserved(test_file, output_type, resources, outpdf):
         'tests/plugins/tesseract_noop.py',
     )
 
-    after = file_to_dict(str(outpdf))
+    after = libxmp_file_to_dict(str(outpdf))
 
     equal_properties = [
         'dc:contributor',
@@ -290,8 +301,8 @@ def test_kodak_toc(resources, outpdf):
 
 
 def test_metadata_fixup_warning(resources, outdir, caplog):
-    options = get_parser().parse_args(
+    _parser, options, _pm = get_parser_options_plugins(
-        args=['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
+        ['--output-type', 'pdfa-2', 'graph.pdf', 'out.pdf']
     )
 
     copyfile(resources / 'graph.pdf', outdir / 'graph.pdf')
@@ -316,6 +327,9 @@ def test_metadata_fixup_warning(resources, outdir, caplog):
     assert any(record.levelname == 'WARNING' for record in caplog.records)
 
 
+XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
+
+
 def test_prevent_gs_invalid_xml(resources, outdir):
     generate_pdfa_ps(outdir / 'pdfa.ps')
     copyfile(resources / 'trivial.pdf', outdir / 'layers.rendered.pdf')
@@ -342,7 +356,7 @@ def test_prevent_gs_invalid_xml(resources, outdir):
     contents = (outdir / 'pdfa.pdf').read_bytes()
     # Since the XML may be invalid, we scan instead of actually feeding it
     # to a parser.
-    XMP_MAGIC = b'W5M0MpCehiHzreSzNTczkc9d'
+
     xmp_start = contents.find(XMP_MAGIC)
     xmp_end = contents.rfind(b'<?xpacket end', xmp_start)
     assert 0 < xmp_start < xmp_end

tests/test_optimize.py

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
 
+from __future__ import annotations
+
 from os import fspath
 from pathlib import Path
 from unittest.mock import patch