v13.6.2 release notes

Fix missing TypeAlias on <3.10
_windows: Avoid messy next()/StopIteration in generator
2022-07-25 23:48:22 -07:00 · 2022-07-25 16:32:55 -07:00 · 2022-07-23 15:40:05 -07:00 · 2022-07-23 15:32:14 -07:00 · 2022-07-23 00:39:24 -07:00 · 2022-07-23 00:07:50 -07:00
103 changed files with 630 additions and 317 deletions
@@ -1 +1,4 @@
-ref-names: $Format:%D$
+node: $Format:%H$
+node-date: $Format:%cI$
+describe-name: $Format:%(describe:tags=true)$
+ref-names: $Format:%D$
@@ -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"
@@ -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 }}
@@ -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}"
@@ -1,6 +1,6 @@
 repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.2.0
+    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: v2.32.1
+    rev: v2.37.2
    hooks:
      - id: pyupgrade
        args: ["--py37-plus"]
  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.950
+    rev: v0.971
    hooks:
      - id: mypy
        additional_dependencies:
@@ -62,7 +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``    |
@@ -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
@@ -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
-where the PDFs are stored):
+Alternatively, with a Docker container and streaming the file through
+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
-convert it to a OCRed PDF in ``/output/``. The parameters to this image are:
+This service will watch for a file that matches ``/input/\*.pdf``,
+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"
-    "``-e OCR_ON_SUCCESS_DELETE=1``", "Define environment variable"
-    "``-e OCR_DESKEW=1``", "Define environment variable"
-    "``-e PYTHONBUFFERED=1``", "This will force STDOUT to be unbuffered and allow you to see messages in docker logs"
+    "``-v <path to store processed originals>:/archive``", "Archive processed originals here"
+    "``-e OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1``", "Define environment variable ``OCR_OUTPUT_DIRECTORY_YEAR_MONTH=1`` to place files in the output in ``{output}/{year}/{month}/{filename}``"
+    "``-e OCR_ON_SUCCESS_ARCHIVE=1``", "Define environment variable ``OCR_ON_SUCCESS_ARCHIVE`` to move processed originals"
+    "``-e OCR_DESKEW=1``", "Define environment variable ``OCR_DESKEW``  to apply deskew to crooked input PDFs"
+    "``-e PYTHONBUFFERED=1``", "This will force ``STDOUT`` to be unbuffered and allow you to see messages in docker logs"

 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
@@ -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.
@@ -340,6 +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``
@@ -360,3 +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.
@@ -43,11 +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
-    :alt: Debian stable
+.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
+    :alt: Debian 11

-.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
-    :alt: Debian testing
+.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
+    :alt: Debian 12

 .. |deb-unstable| image:: https://repology.org/badge/version-for-repo/debian_unstable/ocrmypdf.svg
    :alt: Debian unstable
@@ -66,7 +66,7 @@ Debian and Ubuntu 18.04 or newer
 +-----------------------------------------------+
 | |latest|                                      |
 +-----------------------------------------------+
-| |deb-stable| |deb-testing| |deb-unstable|     |
+| |deb-11| |deb-12| |deb-unstable|              |
 +-----------------------------------------------+
 | |ubu-1804| |ubu-2004| |ubu-2204|              |
 +-----------------------------------------------+
@@ -142,7 +142,7 @@ from sources <#installing-head-revision-from-sources>`__.
 Installing the latest version on Ubuntu 22.04 LTS
 -------------------------------------------------

-Ubuntu 22.04 includes ocrmypdf 13.4.0 - you can install that with 
+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:

@@ -153,7 +153,7 @@ user, follow these steps:

    pip install --user --upgrade ocrmypdf

-If you get the message ``WARNING: The script ocrmypdf is installed in 
+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.

@@ -32,7 +32,7 @@ For all other Linux, you must build a JBIG2 encoder from source:

 .. _jbig2-lossy:

-Dependencies include libtoolize and libleptonica, which on Ubuntu systems 
+Dependencies include libtoolize and libleptonica, which on Ubuntu systems
 are packaged as libtool and libleptonica-dev.

 Lossy mode JBIG2
@@ -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
@@ -24,10 +24,33 @@ tagged yet.

 .. |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`` pluginhook, making it possible to create plugins that
+-  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.
@@ -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
@@ -37,6 +37,8 @@ To use this as an API:
    )
 """

+from __future__ import annotations
+
 import logging

 from PIL import Image
@@ -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
@@ -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:
-        log.info(f'OCR is done. Deleting: {file_path}')
-        file_path.unlink()
+    if exit_code == 0:
+        if ON_SUCCESS_DELETE:
+            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"
@@ -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
@@ -1,14 +1,12 @@
 [build-system]
 requires = [
-  "setuptools >= 30.3.0",
-  "wheel",
-  "setuptools_scm[toml] >= 3.4",
-  "setuptools_scm_git_archive"
+  "setuptools >= 52",
+  "setuptools_scm[toml] >= 7.0.5",
+  "wheel"
 ]
 build-backend = "setuptools.build_meta"

 [tool.setuptools_scm]
-version_scheme = "post-release"

 [tool.black]
 line-length = 88
@@ -96,7 +94,8 @@ module = [
  'pdfminer.*',
  'reportlab.*',
  'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
+  'importlib_metadata'
 ]
 ignore_missing_imports = true

@@ -56,6 +56,7 @@ install_requires =
    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 =
@@ -86,6 +87,8 @@ 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
 webservice =
@@ -6,13 +6,8 @@

 """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_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'},
-)
+setup()
@@ -6,6 +6,8 @@

 """Adds OCR layer to PDFs."""

+from __future__ import annotations
+
 from pluggy import HookimplMarker as _HookimplMarker

 from ocrmypdf import helpers, hocrtransform, pdfa, pdfinfo
@@ -7,6 +7,8 @@

 """ocrmypdf command line entrypoint."""

+from __future__ import annotations
+
 import logging
 import os
 import signal
@@ -6,9 +6,11 @@

 """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):
@@ -47,10 +49,10 @@ class Executor(ABC):
        use_threads: bool,
        max_workers: int,
        tqdm_kwargs: dict,
-        worker_initializer: Optional[Callable] = None,
-        task: Optional[Callable] = None,
-        task_arguments: Optional[Iterable] = None,
-        task_finished: Optional[Callable] = None,
+        worker_initializer: Callable | None = None,
+        task: Callable | None = None,
+        task_arguments: Iterable | None = None,
+        task_finished: Callable | None = None,
    ) -> None:
        """
        Set up parallel execution and progress reporting.
@@ -6,3 +6,5 @@


 """Manage third party executables"""
+
+from __future__ import annotations
@@ -7,6 +7,8 @@

 """Interface to Ghostscript executable"""

+from __future__ import annotations
+
 import logging
 import os
 import re
@@ -15,7 +17,6 @@ from io import BytesIO
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, CalledProcessError
-from typing import Optional

 from PIL import Image, UnidentifiedImageError

@@ -77,8 +78,8 @@ def rasterize_pdf(
    raster_device: str,
    raster_dpi: Resolution,
    pageno: int = 1,
-    page_dpi: Optional[Resolution] = None,
-    rotation: Optional[int] = None,
+    page_dpi: Resolution | None = None,
+    rotation: int | None = None,
    filter_vector: bool = False,
 ):
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""
@@ -7,6 +7,8 @@

 """Interface to jbig2 executable"""

+from __future__ import annotations
+
 from subprocess import PIPE

 from ocrmypdf.exceptions import MissingDependencyError
@@ -7,6 +7,8 @@

 """Interface to pngquant executable"""

+from __future__ import annotations
+
 from contextlib import contextmanager
 from io import BytesIO
 from pathlib import Path
@@ -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, 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,
@@ -162,7 +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)])
@@ -171,7 +172,7 @@ 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 gen():
        for line in binary_output.decode().splitlines():
            line = line.strip()
@@ -183,7 +184,7 @@ def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:


 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',
@@ -215,7 +216,7 @@ def get_orientation(


 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) + [
@@ -306,9 +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,
@@ -372,9 +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,
@@ -5,9 +5,10 @@
 # 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
@@ -18,7 +19,7 @@ from contextlib import contextmanager
 from decimal import Decimal
 from pathlib import Path
 from subprocess import PIPE, STDOUT
-from typing import Iterator, List, Optional, Tuple, Union
+from typing import Iterator, Union

 from PIL import Image

@@ -72,13 +73,13 @@ def version() -> str:
    return get_version('unpaper')


-SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+SUPPORTED_MODES = {'1', 'L', 'RGB'}


-def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
+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:
@@ -91,41 +92,41 @@ def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
            ) from e
        else:
            im_modified = True
-    try:
-        suffix = SUFFIXES[im.mode]
-    except KeyError:
-        raise MissingDependencyError(
-            "Failed to convert image to a supported format."
-        ) from None
-    return im, im_modified, suffix
+        if im.mode not in SUPPORTED_MODES:
+            raise MissingDependencyError(
+                "Failed to convert image to a supported format."
+            ) from None
+    return im, im_modified


@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(ignore_cleanup_errors=True) as tmpdir:
            tmppath = Path(tmpdir)
-            if im_modified or input_file.suffix != '.pnm':
-                input_pnm = tmppath / 'input.pnm'
-                im.save(input_pnm, format='PPM')
+            if im_modified or input_file.suffix != '.png':
+                input_png = tmppath / 'input.png'
+                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}'
-            yield input_pnm, output_pnm, tmppath
+            # unpaper can write .png too, but it seems to write them slowly
+            # 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
@@ -133,7 +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,
@@ -154,7 +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')
@@ -166,7 +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',
@@ -6,10 +6,11 @@

 """For grafting text-only PDF pages onto freeform PDF pages."""

+from __future__ import annotations
+
 import logging
 from contextlib import suppress
 from pathlib import Path
-from typing import Optional

 from pikepdf import (
    Dictionary,
@@ -103,8 +104,8 @@ class OcrGrafter:
        self,
        *,
        pageno: int,
-        image: Optional[Path],
-        textpdf: Optional[Path],
+        image: Path | None,
+        textpdf: Path | None,
        autorotate_correction: int,
    ):
        if textpdf and not self.font:
@@ -6,6 +6,8 @@

 """Defines context objects that are passed to child processes/threads."""

+from __future__ import annotations
+
 import os
 import shutil
 import sys
@@ -50,7 +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):
@@ -6,6 +6,8 @@

 """Logging support classes."""

+from __future__ import annotations
+
 import logging
 from contextlib import suppress

@@ -6,6 +6,8 @@

 """OCRmyPDF page processing pipeline functions."""

+from __future__ import annotations
+
 import logging
 import os
 import re
@@ -14,7 +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
@@ -41,7 +43,7 @@ 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

@@ -494,7 +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)

@@ -665,7 +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):
@@ -679,15 +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:
-            pdfmark['/Title'] = options.title
-        if options.author:
-            pdfmark['/Author'] = options.author
-        if options.keywords:
-            pdfmark['/Keywords'] = options.keywords
-        if options.subject:
-            pdfmark['/Subject'] = options.subject
+    if options.title:
+        pdfmark['/Title'] = options.title
+    if options.author:
+        pdfmark['/Author'] = options.author
+    if options.keywords:
+        pdfmark['/Keywords'] = options.keywords
+    if options.subject:
+        pdfmark['/Subject'] = options.subject

    creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)

@@ -867,7 +868,7 @@ 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 (from_, to_), txt_file in enumerate_compress_ranges(txt_files):
@@ -6,13 +6,15 @@

 """Plugin manager using pluggy."""

+from __future__ import annotations
+
 import argparse
 import importlib
 import importlib.util
 import pkgutil
 import sys
 from pathlib import Path
-from typing import List, Sequence, Tuple, Union
+from typing import Sequence

 import pluggy

@@ -34,7 +36,7 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
    def __init__(
        self,
        *args,
-        plugins: List[Union[str, Path]],
+        plugins: list[str | Path],
        builtins: bool = True,
        **kwargs,
    ):
@@ -101,7 +103,7 @@ 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):
    return OcrmypdfPluginManager(
        project_name='ocrmypdf',
        plugins=plugins,
@@ -111,11 +113,14 @@ def get_plugin_manager(plugins: List[Union[str, Path]], builtins=True):

 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)
@@ -7,6 +7,8 @@
 """Implements the concurrent and page synchronous parts of the pipeline."""


+from __future__ import annotations
+
 import argparse
 import logging
 import logging.handlers
@@ -18,7 +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, Sequence, Tuple, cast
+from typing import NamedTuple, Sequence, cast

 import PIL

@@ -74,9 +76,9 @@ class PageResult(NamedTuple):
    """Result when a page is finished processing."""

    pageno: int
-    pdf_page_from_image: Optional[Path]
-    ocr: Optional[Path]
-    text: Optional[Path]
+    pdf_page_from_image: Path | None
+    ocr: Path | None
+    text: Path | None
    orientation_correction: int


@@ -115,7 +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
@@ -232,7 +234,7 @@ def exec_page_sync(page_context: PageContext) -> PageResult:

 def post_process(
    pdf_file: Path, context: PdfContext, executor: Executor
-) -> Tuple[Path, Sequence[str]]:
+) -> tuple[Path, Sequence[str]]:
    pdf_out = pdf_file
    if context.options.output_type.startswith('pdfa'):
        ps_stub_out = generate_postscript_stub(context)
@@ -259,7 +261,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
    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):
@@ -302,7 +304,7 @@ def exec_concurrent(context: PdfContext, executor: Executor) -> Sequence[str]:
    # Merge layers to one single pdf
    pdf = ocrgraft.finalize()

-    messages: List[str] = []
+    messages: Sequence[str] = []
    if options.output_type != 'none':
        # PDF/A and metadata
        log.info("Postprocessing...")
@@ -337,7 +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
@@ -7,6 +7,8 @@

 """Validate a work order from API or command line."""

+from __future__ import annotations
+
 import locale
 import logging
 import os
@@ -14,7 +16,7 @@ import sys
 import unicodedata
 from pathlib import Path
 from shutil import copyfileobj
-from typing import List, Optional, Sequence, Set, Tuple
+from typing import Sequence

 import pikepdf
 import PIL
@@ -144,8 +146,8 @@ def check_options_preprocessing(options):
            raise BadArgsError("--unpaper-args: " + str(e)) from e


-def _pages_from_ranges(ranges: str) -> Set[int]:
-    pages: List[int] = []
+def _pages_from_ranges(ranges: str) -> set[int]:
+    pages: list[int] = []
    page_groups = ranges.replace(' ', '').split(',')
    for group in page_groups:
        if not group:
@@ -241,7 +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')
@@ -297,7 +299,7 @@ def report_output_file_size(
    options,
    input_file: Path,
    output_file: Path,
-    optimize_messages: Optional[Sequence[str]] = None,
+    optimize_messages: Sequence[str] | None = None,
    file_overhead: int = 4000,
    page_overhead: int = 3000,
 ):
@@ -9,10 +9,12 @@
 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'

@@ -6,6 +6,8 @@

 """Functions for using ocrmypdf as an API."""

+from __future__ import annotations
+
 import logging
 import os
 import sys
@@ -13,7 +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
@@ -217,7 +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,
@@ -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.
@@ -4,13 +4,14 @@
 # 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
@@ -104,6 +105,15 @@ 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,
        *,
@@ -142,7 +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", ""):
@@ -151,7 +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
@@ -6,6 +6,8 @@

 """OCRmyPDF automatically installs these filters as plugins."""

+from __future__ import annotations
+
 from ocrmypdf import hookimpl


@@ -7,6 +7,8 @@

 """Built-in plugin to implement PDF page rasterization and PDF/A production."""

+from __future__ import annotations
+
 import logging

 from ocrmypdf import hookimpl
@@ -7,13 +7,14 @@

 """Built-in plugin to implement PDF page optimization."""

+from __future__ import annotations
+
 import argparse
 import logging
 from pathlib import Path
-from typing import Sequence, Tuple
+from typing import Sequence

-from ocrmypdf import PdfContext, hookimpl
-from ocrmypdf._concurrent import Executor
+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
@@ -131,7 +132,7 @@ def optimize_pdf(
    context: PdfContext,
    executor: Executor,
    linearize: bool,
-) -> Tuple[Path, Sequence[str]]:
+) -> tuple[Path, Sequence[str]]:
    save_settings = dict(
        linearize=linearize,
        **get_pdf_save_settings(context.options.output_type),
@@ -7,6 +7,8 @@
 """Built-in plugin to implement OCR using Tesseract."""


+from __future__ import annotations
+
 import logging
 import os

@@ -6,8 +6,10 @@

 """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
@@ -15,9 +17,7 @@ from ocrmypdf._version import __version__ as _VERSION
 T = TypeVar('T', int, float)


-def numeric(
-    basetype: Callable[[Any], T], min_: Optional[T] = None, max_: Optional[T] = None
-):
+def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = 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
@@ -6,3 +6,5 @@


 """Data files used to generate certain PDFs."""
+
+from __future__ import annotations
@@ -6,6 +6,8 @@

 """OCRmyPDF's exceptions."""

+from __future__ import annotations
+
 from enum import IntEnum
 from textwrap import dedent

@@ -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
@@ -134,8 +136,8 @@ class LambdaExecutor(Executor):
        if not grouped_args:
            return

-        processes: List[Process] = []
-        connections: List[Connection] = []
+        processes: list[Process] = []
+        connections: list[Connection] = []
        for chunk in grouped_args:
            parent_conn, child_conn = Pipe()

@@ -6,6 +6,8 @@

 """Support functions."""

+from __future__ import annotations
+
 import logging
 import multiprocessing
 import os
@@ -30,17 +30,24 @@

 """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
-from reportlab.lib.units import inch
-from reportlab.pdfgen.canvas import Canvas
+with warnings.catch_warnings():
+    warnings.filterwarnings(
+        '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,
@@ -134,7 +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))

@@ -198,7 +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.
        """
@@ -214,7 +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}']"
@@ -241,7 +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,
@@ -344,7 +351,7 @@ class HocrTransform:
    def _do_line(
        self,
        pdf: Canvas,
-        line: Optional[Element],
+        line: Element | None,
        elemclass: str,
        fontname: str,
        invisible_text: bool,
@@ -7,6 +7,8 @@
 """Post-processing image optimization of OCR PDFs."""


+from __future__ import annotations
+
 import logging
 import sys
 import tempfile
@@ -14,18 +16,7 @@ import threading
 from collections import defaultdict
 from os import fspath
 from pathlib import Path
-from typing import (
-    Callable,
-    Dict,
-    Iterator,
-    List,
-    MutableSet,
-    NamedTuple,
-    NewType,
-    Optional,
-    Sequence,
-    Tuple,
-)
+from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
 from zlib import compress

 import img2pdf
@@ -78,7 +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

@@ -135,7 +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)
@@ -176,7 +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
@@ -240,8 +231,8 @@ def extract_images(
    pike: Pdf,
    root: Path,
    options,
-    extract_fn: Callable[..., Optional[XrefExt]],
-) -> Iterator[Tuple[int, XrefExt]]:
+    extract_fn: Callable[..., XrefExt | None],
+) -> Iterator[tuple[int, XrefExt]]:
    """Extract image using extract_fn

    Enumerate images on each page, lookup their xref/ID number in the PDF.
@@ -300,7 +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 = []
@@ -315,7 +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)
@@ -328,11 +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 (
@@ -341,7 +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
@@ -376,7 +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,
@@ -393,7 +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)

@@ -419,7 +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:
@@ -435,13 +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
@@ -466,7 +457,7 @@ 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
@@ -478,7 +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)
@@ -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,
@@ -131,7 +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'
@@ -8,4 +8,6 @@

 """For extracting information about PDFs prior to OCR."""

+from __future__ import annotations
+
 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo
@@ -8,6 +8,8 @@

 """Extract information about the content of a PDF."""

+from __future__ import annotations
+
 import atexit
 import logging
 import re
@@ -21,16 +23,13 @@ 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

@@ -85,7 +84,7 @@ class Encoding(Enum):

 FloatRect = Tuple[float, float, float, float]

-FRIENDLY_COLORSPACE: Dict[str, Colorspace] = {
+FRIENDLY_COLORSPACE: dict[str, Colorspace] = {
    '/DeviceGray': Colorspace.gray,
    '/CalGray': Colorspace.gray,
    '/DeviceRGB': Colorspace.rgb,
@@ -103,7 +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,
@@ -117,7 +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,
@@ -139,7 +138,7 @@ 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


@@ -147,24 +146,24 @@ 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):
    """Info about various objects found in a PDF."""

-    xobject_settings: List[XobjectSettings]
-    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):
    """Info about a text box found in a PDF."""

-    bbox: Tuple[float, float, float, float]
+    bbox: tuple[float, float, float, float]
    is_visible: bool
    is_corrupt: bool

@@ -217,8 +216,8 @@ def _interpret_contents(contentstream: Object, initial_shorthand=UNIT_SQUARE):

    stack = []
    ctm = PdfMatrix(initial_shorthand)
-    xobject_settings: List[XobjectSettings] = []
-    inline_images: List[InlineSettings] = []
+    xobject_settings: list[XobjectSettings] = []
+    inline_images: list[InlineSettings] = []
    name_index = defaultdict(lambda: [])
    found_vector = False
    found_text = False
@@ -342,21 +341,21 @@ class ImageInfo:

    DPI_PREC = Decimal('1.000')

-    _comp: Optional[int]
+    _comp: int | None
    _name: str

    def __init__(
        self,
        *,
        name='',
-        pdfimage: Optional[Object] = None,
-        inline: Optional[PdfInlineImage] = None,
+        pdfimage: Object | None = 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'
@@ -400,7 +399,7 @@ class ImageInfo:
                    self._comp = 4
                else:
                    self._comp = 3
-            except UnsupportedImageTypeError as ex:
+            except (AttributeError, UnsupportedImageTypeError) as ex:
                self._comp = None
                logger.warning(
                    f"An image with a corrupt or unreadable ICC profile was found. "
@@ -473,7 +472,7 @@ def _find_inline_images(contentsinfo: ContentsInfo) -> Iterator[ImageInfo]:
        )


-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
@@ -561,7 +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.
@@ -691,8 +690,8 @@ def _pdf_pageinfo_concurrent(
    max_workers,
    check_pages,
    detailed_analysis=False,
-) -> Sequence[Optional['PageInfo']]:
-    pages: Sequence[Optional['PageInfo']] = [None] * len(pdf.pages)
+) -> Sequence[PageInfo | None]:
+    pages: Sequence[PageInfo | None] = [None] * len(pdf.pages)

    def update_pageinfo(result, pbar):
        page = result
@@ -744,9 +743,9 @@ def _pdf_pageinfo_concurrent(
 class PageInfo:
    """Information about type of contents on each page in a PDF."""

-    _has_text: Optional[bool]
-    _has_vector: Optional[bool]
-    _images: List[ImageInfo]
+    _has_text: bool | None
+    _has_vector: bool | None
+    _images: list[ImageInfo]

    def __init__(
        self,
@@ -879,9 +878,7 @@ class PageInfo:
    def images(self):
        return self._images

-    def get_textareas(
-        self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
-    ):
+    def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
        def predicate(obj, want_visible, want_corrupt):
            result = True
            if want_visible is not None:
@@ -965,7 +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
@@ -982,7 +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
@@ -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
@@ -6,24 +6,17 @@

 """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,
-    Sequence,
-    Tuple,
-)
+from typing import TYPE_CHECKING, AbstractSet, NamedTuple, Sequence

 import pluggy

-from ocrmypdf import PdfContext
-from ocrmypdf._concurrent import Executor
+from ocrmypdf import Executor, PdfContext
 from ocrmypdf.helpers import Resolution

 if TYPE_CHECKING:
@@ -52,6 +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.
@@ -151,7 +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*
@@ -177,8 +197,8 @@ def rasterize_pdf_page(
    raster_device: str,
    raster_dpi: Resolution,
    pageno: int,
-    page_dpi: Optional[Resolution],
-    rotation: Optional[int],
+    page_dpi: Resolution | None,
+    rotation: int | None,
    filter_vector: bool,
 ) -> Path:
    """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
@@ -207,7 +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
@@ -234,7 +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
@@ -274,9 +294,7 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:


@hookspec(firstresult=True)
-def filter_pdf_page(
-    page: 'PageContext', image_filename: Path, output_pdf: Path
-) -> Path:
+def filter_pdf_page(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
@@ -419,7 +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,
@@ -475,7 +493,7 @@ def optimize_pdf(
    context: PdfContext,
    executor: Executor,
    linearize: bool,
-) -> Tuple[Path, Sequence[str]]:
+) -> 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
@@ -484,6 +502,9 @@ def optimize_pdf(
    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
@@ -512,8 +533,8 @@ def optimize_pdf(
 def is_optimization_enabled(context: PdfContext) -> bool:
    """For a given PdfContext, OCRmyPDF asks the plugin if optimization is enabled.

-    It is assumed that an optimization plugin might be installed but could be
-    disabled by user settings.
+    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.

@@ -8,6 +8,8 @@
 """Utilities to measure OCR quality"""


+from __future__ import annotations
+
 import re
 from typing import Iterable

@@ -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

@@ -26,11 +28,14 @@ from ocrmypdf.exceptions import MissingDependencyError

 log = logging.getLogger(__name__)

+Args = Sequence[Union[Path, str]]
+OsEnviron = os._Environ  # pylint: disable=protected-access
+

 def run(
-    args,
+    args: Args,
    *,
-    env=None,
+    env: OsEnviron | None = None,
    logs_errors_to_stdout: bool = False,
    check: bool = False,
    **kwargs,
@@ -73,7 +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.

@@ -106,7 +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:
@@ -115,7 +127,7 @@ 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

@@ -123,14 +135,18 @@ def _fix_process_args(args, env, kwargs):

    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

@@ -229,7 +245,7 @@ a command prompt to install the missing package:
 '''


-def _get_platform():
+def _get_platform() -> str:
    if sys.platform.startswith('freebsd'):
        return 'freebsd'
    elif sys.platform.startswith('linux'):
@@ -239,7 +255,7 @@ 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)
@@ -252,7 +268,9 @@ def _error_trailer(program, package, **kwargs):
        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()))
@@ -263,7 +281,13 @@ def _error_missing_program(program, package, required_for, recommended):
    _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()))
@@ -272,7 +296,7 @@ def _error_old_version(program, package, need_version, found_version, required_f
    _error_trailer(**locals())


-def _remove_leading_v(s):
+def _remove_leading_v(s: str) -> str:
    if sys.version_info >= (3, 9):
        return s.removeprefix('v')

@@ -285,12 +309,12 @@ def check_external_program(
    *,
    program: str,
    package: str,
-    version_checker: Callable,
+    version_checker: Callable[[], str],
    need_version: str,
-    required_for: Optional[str] = None,
-    recommended=False,
-    version_parser: Type[Version] = Version,
-):
+    required_for: str | None = None,
+    recommended: bool = False,
+    version_parser: type[Version] = Version,
+) -> None:
    """Check for required version of external program and raise exception if not.

    Args:
@@ -3,31 +3,44 @@
 # 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/.
-
-# type: ignore
-# Non-Windows mypy now breaks when trying to typecheck winreg
-
 """Find Tesseract and Ghostscript binaries on Windows using the registry."""

+from __future__ import annotations
+
 import logging
 import os
 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
+
+if sys.version_info >= (3, 10):
+    from typing import TypeAlias
+else:
+    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

-try:
-    import winreg
-except ModuleNotFoundError as _notfound_ex:
-    raise ModuleNotFoundError("This module is for Windows only") from _notfound_ex

 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)]
@@ -38,9 +51,7 @@ def ghostscript_version_key(s: str) -> Tuple[int, int, int]:
        return (0, 0, 0)


-def registry_enum(
-    key: winreg.HKEYType, enum_fn: Callable[[winreg.HKEYType, int], T]
-) -> Iterator[T]:
+def registry_enum(key: HKEYType, enum_fn: Callable[[HKEYType, int], T]) -> Iterator[T]:
    limit = 999
    n = 0
    while n < limit:
@@ -53,11 +64,11 @@ def registry_enum(
        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)


@@ -73,8 +84,8 @@ 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))
-            yield Path(gs_path) / 'bin'
+            for _, gs_path, _ in registry_values(k):
+                yield Path(gs_path) / 'bin'
    except OSError as e:
        log.warning(e)

@@ -160,7 +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)
@@ -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
@@ -0,0 +1 @@
+Tesseract Open Source OCR Engine v4.1.1 with Leptonica
@@ -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.
+
@@ -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"]}
@@ -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']


@@ -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
@@ -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
@@ -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
@@ -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

@@ -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
@@ -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
@@ -44,6 +44,8 @@ Assumes Tesseract 4.0.0-alpha or higher.

 """

+from __future__ import annotations
+
 import argparse
 import json
 import logging
@@ -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
@@ -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

@@ -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

@@ -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()}"

@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.


+from __future__ import annotations
+
 import logging

 import pytest
@@ -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

@@ -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
@@ -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

@@ -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
@@ -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
@@ -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
@@ -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
@@ -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

@@ -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
@@ -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
@@ -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
@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.


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


+from __future__ import annotations
+
 import pytest

 import ocrmypdf
@@ -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 pikepdf
@@ -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 pickle
 from io import BytesIO
 from math import isclose
@@ -24,20 +26,24 @@ from ocrmypdf.pdfinfo.layout import PDFPage
 # pylint: disable=protected-access


-def test_single_page_text(outdir):
+@pytest.fixture
+def single_page_text(outdir):
    filename = outdir / 'text.pdf'
    pdf = Canvas(str(filename), pagesize=(8 * inch, 6 * inch))
    text = pdf.beginText()
    text.setFont('Helvetica', 12)
    text.setTextOrigin(1 * inch, 3 * inch)
    text.textLine(
-        "Methink'st thou art a general offence and every" " man should beat thee."
+        "Methink'st thou art a general offence and every man should beat thee."
    )
    pdf.drawText(text)
    pdf.showPage()
    pdf.save()
+    return filename

-    info = pdfinfo.PdfInfo(filename)
+
+def test_single_page_text(single_page_text):
+    info = pdfinfo.PdfInfo(single_page_text)

    assert len(info) == 1
    page = info[0]
@@ -54,7 +60,8 @@ def eight_by_eight():
    return im


-def test_single_page_image(eight_by_eight, outpdf):
+@pytest.fixture
+def eight_by_eight_regular_image(eight_by_eight, outpdf):
    im = eight_by_eight
    bio = BytesIO()
    im.save(bio, format='PNG')
@@ -71,7 +78,11 @@ def test_single_page_image(eight_by_eight, outpdf):
            outputstream=f,
            **IMG2PDF_KWARGS,
        )
-    info = pdfinfo.PdfInfo(outpdf)
+    return outpdf
+
+
+def test_single_page_image(eight_by_eight_regular_image):
+    info = pdfinfo.PdfInfo(eight_by_eight_regular_image)

    assert len(info) == 1
    page = info[0]
@@ -88,16 +99,18 @@ def test_single_page_image(eight_by_eight, outpdf):
    assert isclose(pdfimage.dpi.y, 8)


-def test_single_page_inline_image(eight_by_eight, outdir):
-    filename = outdir / 'image-mono-inline.pdf'
-    pdf = Canvas(str(filename), pagesize=(8 * 72, 6 * 72))
-
+@pytest.fixture
+def eight_by_eight_inline_image(eight_by_eight, outpdf):
+    pdf = Canvas(str(outpdf), pagesize=(8 * 72, 6 * 72))
    # Draw image in a 72x72 pt or 1"x1" area
    pdf.drawInlineImage(eight_by_eight, 0, 0, width=72, height=72)
    pdf.showPage()
    pdf.save()
+    return outpdf

-    info = pdfinfo.PdfInfo(filename)
+
+def test_single_page_inline_image(eight_by_eight_inline_image):
+    info = pdfinfo.PdfInfo(eight_by_eight_inline_image)
    print(info)
    pdfimage = info[0].images[0]
    assert isclose(pdfimage.dpi.x, 8)
@@ -177,7 +190,7 @@ def test_stack_abuse():
        pdfinfo.info._interpret_contents(stream)

    stream = pikepdf.Stream(p, b'q Q Q Q Q')
-    with pytest.warns(UserWarning, match="underflowed") as record:
+    with pytest.warns(UserWarning, match="underflowed"):
        pdfinfo.info._interpret_contents(stream)

    stream = pikepdf.Stream(p, b'q ' * 135)
@@ -201,7 +214,8 @@ def test_pages_issue700(monkeypatch, resources):
        )


-def test_image_scale0(resources, outpdf):
+@pytest.fixture
+def image_scale0(resources, outpdf):
    with pikepdf.open(resources / 'cmyk.pdf') as cmyk:
        xobj = cmyk.pages[0].as_form_xobject()

@@ -215,7 +229,12 @@ def test_image_scale0(resources, outpdf):
            p, b"q 0 0 0 0 0 0 cm %s Do Q" % bytes(objname)
        )
        p.save(outpdf)
+    return outpdf

-    pi = pdfinfo.PdfInfo(outpdf, detailed_analysis=True, progbar=False, max_workers=1)
+
+def test_image_scale0(image_scale0):
+    pi = pdfinfo.PdfInfo(
+        image_scale0, detailed_analysis=True, progbar=False, max_workers=1
+    )
    assert not pi.pages[0]._images[0].dpi.is_finite
    assert pi.pages[0].dpi == Resolution(0, 0)
@@ -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
+
 from unittest.mock import Mock

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


+from __future__ import annotations
+
 from math import isclose

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


+from __future__ import annotations
+
 import pytest

 from ocrmypdf import quality as qual
@@ -5,6 +5,8 @@
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.


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


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


+from __future__ import annotations
+
 import logging
 import os
 import subprocess
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
James R. Barlow	21fb6c82ca	v13.6.2 release notes	2022-07-25 23:48:22 -07:00
James R. Barlow	27f7b9f255	Fix missing TypeAlias on <3.10	2022-07-25 16:32:55 -07:00
James R. Barlow	6f31a92ffb	_windows: Avoid messy next()/StopIteration in generator	2022-07-23 15:40:05 -07:00
James R. Barlow	da2276788c	Fix _windows module typing	2022-07-23 15:32:14 -07:00
James R. Barlow	dc6f1a266a	Modernize type annotations	2022-07-23 00:39:24 -07:00
James R. Barlow	9c8ddd853d	Typing adjustments	2022-07-23 00:07:50 -07:00
James R. Barlow	014d0302f2	Pre-commit: update	2022-07-22 23:49:51 -07:00
James R. Barlow	65568b3dbc	Merge commit '05e2b6698dacce898abc356222124c7a1609f569'	2022-07-18 14:12:01 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	05e2b6698d	build(deps): bump docker/setup-buildx-action from 1 to 2 (#994 ) 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>	2022-07-18 14:10:45 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2f8e0f7d95	build(deps): bump actions/download-artifact from 2 to 3 (#995 ) Bumps [actions/download-artifact](https://github.com/actions/download-artifact) from 2 to 3. - [Release notes](https://github.com/actions/download-artifact/releases) - [Commits](https://github.com/actions/download-artifact/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/download-artifact 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>	2022-07-18 14:10:33 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	7e7553fc6b	build(deps): bump actions/setup-python from 2 to 4 (#996 ) Bumps [actions/setup-python](https://github.com/actions/setup-python) from 2 to 4. - [Release notes](https://github.com/actions/setup-python/releases) - [Commits](https://github.com/actions/setup-python/compare/v2...v4) --- updated-dependencies: - dependency-name: actions/setup-python 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>	2022-07-18 14:10:19 -07:00
James R. BarlowandH. Felix Wittmann	6b425aaebe	Add shim for cancel_futures in older Pythons Thanks @hfwittmann Closes #993 Co-authored-by: H. Felix Wittmann <hfwittmann@users.noreply.github.com>	2022-07-17 16:02:45 -07:00
James R. Barlow	725af43bc3	docs: fix badges for debian	2022-07-12 14:56:00 -07:00
James R. Barlow	5c60309609	Merge remote-tracking branch 'origin/master'	2022-07-12 02:23:17 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	7d5cd55909	build(deps): bump codecov/codecov-action from 1 to 3 (#990 ) Bumps [codecov/codecov-action](https://github.com/codecov/codecov-action) from 1 to 3. - [Release notes](https://github.com/codecov/codecov-action/releases) - [Changelog](https://github.com/codecov/codecov-action/blob/master/CHANGELOG.md) - [Commits](https://github.com/codecov/codecov-action/compare/v1...v3) --- updated-dependencies: - dependency-name: codecov/codecov-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>	2022-07-12 02:23:02 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	ec4a06fad2	build(deps): bump docker/login-action from 1 to 2 (#988 ) Bumps [docker/login-action](https://github.com/docker/login-action) from 1 to 2. - [Release notes](https://github.com/docker/login-action/releases) - [Commits](https://github.com/docker/login-action/compare/v1...v2) --- updated-dependencies: - dependency-name: docker/login-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>	2022-07-12 02:22:53 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	48c6e2318e	build(deps): bump docker/setup-qemu-action from 1 to 2 (#987 ) Bumps [docker/setup-qemu-action](https://github.com/docker/setup-qemu-action) from 1 to 2. - [Release notes](https://github.com/docker/setup-qemu-action/releases) - [Commits](https://github.com/docker/setup-qemu-action/compare/v1...v2) --- updated-dependencies: - dependency-name: docker/setup-qemu-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>	2022-07-12 02:22:38 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	2eafa5e070	build(deps): bump actions/upload-artifact from 2 to 3 (#989 ) Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 2 to 3. - [Release notes](https://github.com/actions/upload-artifact/releases) - [Commits](https://github.com/actions/upload-artifact/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/upload-artifact 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>	2022-07-12 02:21:27 -07:00
dependabot[bot]GitHubdependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>	6aa04d7569	build(deps): bump actions/checkout from 2 to 3 (#991 ) Bumps [actions/checkout](https://github.com/actions/checkout) from 2 to 3. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](https://github.com/actions/checkout/compare/v2...v3) --- updated-dependencies: - dependency-name: actions/checkout 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>	2022-07-12 02:21:12 -07:00
James R. Barlow	b9bffa97ba	Fix ABCMeta typing	2022-07-12 02:20:22 -07:00
James R. Barlow	777ba99ccc	v13.6.1 release notes	2022-07-12 02:11:26 -07:00
James R. Barlow	001b3324f1	Require setuptools-scm 7.0.5 to ensure sdists work alright	2022-07-12 02:09:37 -07:00
James R. Barlow	b1f2d257e2	Typing improvements	2022-07-09 02:24:19 -07:00
James R. Barlow	24a08e5170	hocrtransform: suppress deprecation warning from importing reportlab	2022-07-07 02:09:47 -07:00
James R. Barlow	adf97fd82c	pipeline: eliminate useless test	2022-07-07 02:08:14 -07:00
James R. Barlow	a60ea72517	docs: improve remarks about lossy JBIG2 and lossy image transformations	2022-07-04 23:01:20 -07:00
James R. Barlow	59f967cdcd	Activate GHA dependabot	2022-07-04 22:43:19 -07:00
James R. Barlow	6e439ee89e	Modernize setuptools usage and setuptools_scm	2022-07-04 02:26:14 -07:00
James R. Barlow	da38e1b035	docs: adding missing plugins	2022-07-04 02:16:20 -07:00
James R. Barlow	28c60c4f82	v13.6.0 release notes	2022-07-03 15:35:22 -07:00
James R. Barlow	a5efc4af9b	unpaper: replace input pnm with png Unpaper or its underlying libraries don't seem to accept pnms with an odd integer width. Although it's not clear if this is the issue at all. In any case, keeping the image a PNG works around the issue. unpaper only accepted PNM input in the past, which is why we send it PNM. Since it now accepts PNG, we might as well use PNG. Unpaper can write PNG as output too, but this added a few seconds to the test suite was not committed. Related issues: https://github.com/ocrmypdf/OCRmyPDF/issues/887 https://github.com/ocrmypdf/OCRmyPDF/issues/665 https://github.com/unpaper/unpaper/issues/82	2022-07-03 15:32:16 -07:00
James R. Barlow	1141235c42	Merge remote-tracking branch 'origin/master'	2022-06-24 01:05:08 -07:00
xave GitHub xave	2b6b7a4975	Update README to show nix package manager install option (#904 ) ocrmypdf now works on M1 Mac (aarch64-darwin) Co-authored-by: xave <xavieking@gmail.com>	2022-06-19 01:47:10 -07:00
James R. Barlow	b062c9e8c0	pluginspec: hint that optimize may need to implement initialize [ci skip]	2022-06-19 01:35:30 -07:00
James R. Barlow	ed632ae366	docs: update batch to avoid suggesting Docker volumes [ci skip]	2022-06-19 01:01:39 -07:00
James R. Barlow	af742229e7	docs: fix sentence fragment in batch page Closes #980 [ci skip]	2022-06-19 00:41:58 -07:00
Alexander JaustandGitHub	e2d998245d	Fix type in cookbook.rst (#978 ) Add missing dash in warning about `--clean-final` and `--remove-background` commands.	2022-06-19 00:32:35 -07:00
James R. Barlow	8c58e95c3a	Add new initialize hookspec to make suppress plugins easier	2022-06-19 00:31:42 -07:00
James R. Barlow	61600111d3	test_pdfinfo: refactor by extracting fixtures	2022-06-18 16:29:57 -07:00
James R. Barlow	e4c45e3d3b	Plugins should ideally not import from ocrmypdf._*	2022-06-18 16:03:55 -07:00
Julius BullingerandGitHub	7cabbb125f	watcher: Add an option to archive processed originals (#951 ) * watcher: Add an option to archive processed originals This adds a feature from existing OCRmyPDF watchdog Docker containers like meyay/ocrmypdf-batch and unze/ocrmypdf-watchdog. With this option, the input directory can be kept clean from already processed files, without losing the originals. * docs: Improve watcher.py's Docker parameters documentation	2022-06-17 15:17:03 -07:00
				`@@ -0,0 +1 @@`
				`Tesseract Open Source OCR Engine v4.1.1 with Leptonica`