v13.6.2 release notes

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

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

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

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

.git_archival.txt

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

.github/dependabot.yml

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

.github/workflows/build.yml

@@ -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}"

.pre-commit-config.yaml

@@ -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:

docs/advanced.rst

@@ -223,7 +223,9 @@ The ``hocr`` renderer
 The ``hocr`` renderer works with older versions of Tesseract. The image
 layer is copied from the original PDF page if possible, avoiding
 potentially lossy transcoding or loss of other PDF information. If
-preprocessing is specified, then the image layer is a new PDF.
+preprocessing is specified, then the image layer is a new PDF. (You may
+need to disable PDF/A conversion nad optimization to eliminate all
+lossy transformations.)
 
 Unlike ``sandwich`` this renderer is implemented within OCRmyPDF; anyone
 looking to customize how OCR is presented should look here. A major

docs/cookbook.rst

@@ -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.

docs/installation.rst

@@ -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
+.. |deb-11| image:: https://repology.org/badge/version-for-repo/debian_11/ocrmypdf.svg
-    :alt: Debian stable
+    :alt: Debian 11
 
-.. |deb-testing| image:: https://repology.org/badge/version-for-repo/debian_testing/ocrmypdf.svg
+.. |deb-12| image:: https://repology.org/badge/version-for-repo/debian_12/ocrmypdf.svg
-    :alt: Debian testing
+    :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|              |
 +-----------------------------------------------+

docs/plugins.rst

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

docs/release_notes.rst

@@ -24,6 +24,21 @@ 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
 =======
 

misc/batch.py

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

misc/example_plugin.py

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

misc/synology.py

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

misc/watcher.py

@@ -20,6 +20,8 @@
 # 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

misc/webservice.py

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

pyproject.toml

@@ -1,14 +1,12 @@
 [build-system]
 requires = [
-  "setuptools >= 30.3.0",
+  "setuptools >= 52",
-  "wheel",
+  "setuptools_scm[toml] >= 7.0.5",
-  "setuptools_scm[toml] >= 3.4",
+  "wheel"
-  "setuptools_scm_git_archive"
 ]
 build-backend = "setuptools.build_meta"
 
 [tool.setuptools_scm]
-version_scheme = "post-release"
 
 [tool.black]
 line-length = 88
@@ -96,7 +94,8 @@ module = [
   'pdfminer.*',
   'reportlab.*',
   'fitz',
-  'libxmp.utils'
+  'libxmp.utils',
+  'importlib_metadata'
 ]
 ignore_missing_imports = true
 

setup.cfg

@@ -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 =

setup.py

@@ -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(
-    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'},
-)

src/ocrmypdf/__init__.py

@@ -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

src/ocrmypdf/__main__.py

@@ -7,6 +7,8 @@
 
 """ocrmypdf command line entrypoint."""
 
+from __future__ import annotations
+
 import logging
 import os
 import signal

src/ocrmypdf/_concurrent.py

@@ -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,
+        worker_initializer: Callable | None = None,
-        task: Optional[Callable] = None,
+        task: Callable | None = None,
-        task_arguments: Optional[Iterable] = None,
+        task_arguments: Iterable | None = None,
-        task_finished: Optional[Callable] = None,
+        task_finished: Callable | None = None,
     ) -> None:
         """
         Set up parallel execution and progress reporting.

src/ocrmypdf/_exec/__init__.py

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

src/ocrmypdf/_exec/ghostscript.py

@@ -7,6 +7,8 @@
 
 """Interface to Ghostscript executable"""
 
+from __future__ import annotations
+
 import logging
 import os
 import re
@@ -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,
+    page_dpi: Resolution | None = None,
-    rotation: Optional[int] = None,
+    rotation: int | None = None,
     filter_vector: bool = False,
 ):
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units."""

src/ocrmypdf/_exec/jbig2enc.py

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

src/ocrmypdf/_exec/pngquant.py

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

src/ocrmypdf/_exec/tesseract.py

@@ -7,13 +7,14 @@
 
 """Interface to Tesseract executable"""
 
+from __future__ import annotations
+
 import logging
 import re
 from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import Dict, 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,

src/ocrmypdf/_exec/unpaper.py

@@ -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
 
@@ -75,7 +76,7 @@ def version() -> str:
 SUPPORTED_MODES = {'1', 'L', 'RGB'}
 
 
-def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool]:
+def _convert_image(im: Image.Image) -> tuple[Image.Image, bool]:
     im_modified = False
 
     if im.mode not in SUPPORTED_MODES:
@@ -99,7 +100,7 @@ def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool]:
 
 
 @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)
@@ -121,7 +122,7 @@ def _setup_unpaper_io(input_file: Path) -> Iterator[Tuple[Path, Path, Path]]:
 
 
 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
 
@@ -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',

src/ocrmypdf/_graft.py

@@ -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],
+        image: Path | None,
-        textpdf: Optional[Path],
+        textpdf: Path | None,
         autorotate_correction: int,
     ):
         if textpdf and not self.font:

src/ocrmypdf/_jobcontext.py

@@ -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):

src/ocrmypdf/_logging.py

@@ -6,6 +6,8 @@
 
 """Logging support classes."""
 
+from __future__ import annotations
+
 import logging
 from contextlib import suppress
 

src/ocrmypdf/_pipeline.py

@@ -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:
-        if options.title:
+        pdfmark['/Title'] = options.title
-            pdfmark['/Title'] = options.title
+    if options.author:
-        if options.author:
+        pdfmark['/Author'] = options.author
-            pdfmark['/Author'] = options.author
+    if options.keywords:
-        if options.keywords:
+        pdfmark['/Keywords'] = options.keywords
-            pdfmark['/Keywords'] = options.keywords
+    if options.subject:
-        if options.subject:
+        pdfmark['/Subject'] = options.subject
-            pdfmark['/Subject'] = options.subject
 
     creator_tag = context.plugin_manager.hook.get_ocr_engine().creator_tag(options)
 
@@ -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):

src/ocrmypdf/_plugin_manager.py

@@ -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,
@@ -111,7 +113,7 @@ 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)
 

src/ocrmypdf/_sync.py

@@ -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]
+    pdf_page_from_image: Path | None
-    ocr: Optional[Path]
+    ocr: Path | None
-    text: Optional[Path]
+    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

src/ocrmypdf/_validation.py

@@ -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]:
+def _pages_from_ranges(ranges: str) -> set[int]:
-    pages: List[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,
 ):

src/ocrmypdf/_version.py

@@ -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'
 

src/ocrmypdf/api.py

@@ -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,

src/ocrmypdf/builtin_plugins/__init__.py

@@ -4,6 +4,8 @@
 # License, v. 2.0. If a copy of the MPL was not distributed with this
 # file, You can obtain one at http://mozilla.org/MPL/2.0/.
 
+from __future__ import annotations
+
 # This file exists only mark builtin_plugins as a package.
 # The plugin manager will not load it, so anything defined here may not be
 # processed as a module.

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -4,13 +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

src/ocrmypdf/builtin_plugins/default_filters.py

@@ -6,6 +6,8 @@
 
 """OCRmyPDF automatically installs these filters as plugins."""
 
+from __future__ import annotations
+
 from ocrmypdf import hookimpl
 
 

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -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

src/ocrmypdf/builtin_plugins/optimize.py

@@ -7,10 +7,12 @@
 
 """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 Executor, PdfContext, hookimpl
 from ocrmypdf._exec import jbig2enc, pngquant
@@ -130,7 +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),

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -7,6 +7,8 @@
 """Built-in plugin to implement OCR using Tesseract."""
 
 
+from __future__ import annotations
+
 import logging
 import os
 

src/ocrmypdf/cli.py

@@ -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(
+def numeric(basetype: Callable[[Any], T], min_: T | None = None, max_: T | None = None):
-    basetype: Callable[[Any], T], min_: Optional[T] = None, max_: Optional[T] = None
-):
     """Validator for numeric params"""
     min_ = basetype(min_) if min_ is not None else None
     max_ = basetype(max_) if max_ is not None else None

src/ocrmypdf/data/__init__.py

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

src/ocrmypdf/exceptions.py

@@ -6,6 +6,8 @@
 
 """OCRmyPDF's exceptions."""
 
+from __future__ import annotations
+
 from enum import IntEnum
 from textwrap import dedent
 

src/ocrmypdf/extra_plugins/semfree.py

@@ -20,6 +20,8 @@ be guaranteed, some workers may end up with too much work while others are idle.
 It is less efficient than the standard implementation, so not th edefault.
 """
 
+from __future__ import annotations
+
 import logging
 import logging.handlers
 import signal
@@ -28,7 +30,7 @@ from enum import Enum, auto
 from itertools import islice, repeat, takewhile, zip_longest
 from multiprocessing import Pipe, Process
 from multiprocessing.connection import Connection, wait
-from typing import Callable, Iterable, Iterator, List
+from typing import Callable, Iterable, Iterator
 
 from ocrmypdf import Executor, hookimpl
 from ocrmypdf._concurrent import NullProgressBar
@@ -134,8 +136,8 @@ class LambdaExecutor(Executor):
         if not grouped_args:
             return
 
-        processes: List[Process] = []
+        processes: list[Process] = []
-        connections: List[Connection] = []
+        connections: list[Connection] = []
         for chunk in grouped_args:
             parent_conn, child_conn = Pipe()
 

src/ocrmypdf/helpers.py

@@ -6,6 +6,8 @@
 
 """Support functions."""
 
+from __future__ import annotations
+
 import logging
 import multiprocessing
 import os

src/ocrmypdf/hocrtransform.py

@@ -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
+with warnings.catch_warnings():
-from reportlab.lib.units import inch
+    warnings.filterwarnings(
-from reportlab.pdfgen.canvas import Canvas
+        'ignore', category=DeprecationWarning, message=r".*load_module.*"
+    )
+    from reportlab.lib.colors import black, cyan, magenta, red
+    from reportlab.lib.units import inch
+    from reportlab.pdfgen.canvas import Canvas
 
 # According to Wikipedia these languages are supported in the ISO-8859-1 character
 # set, meaning reportlab can generate them and they are compatible with hocr,
@@ -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,

src/ocrmypdf/optimize.py

@@ -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 (
+from typing import Callable, Iterator, MutableSet, NamedTuple, NewType, Sequence
-    Callable,
-    Dict,
-    Iterator,
-    List,
-    MutableSet,
-    NamedTuple,
-    NewType,
-    Optional,
-    Sequence,
-    Tuple,
-)
 from zlib import compress
 
 import img2pdf
@@ -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]],
+    extract_fn: Callable[..., XrefExt | None],
-) -> Iterator[Tuple[int, XrefExt]]:
+) -> Iterator[tuple[int, XrefExt]]:
     """Extract image using extract_fn
 
     Enumerate images on each page, lookup their xref/ID number in the PDF.
@@ -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)

src/ocrmypdf/pdfa.py

@@ -9,14 +9,16 @@
 Utilities for PDF/A production and confirmation with Ghostspcript.
 """
 
+from __future__ import annotations
+
 import base64
 from pathlib import Path
-from typing import Dict, Iterator, Union
+from typing import Iterator
 
 try:
-    from importlib_resources import files as package_files
-except ImportError:
     from importlib.resources import files as package_files
+except ImportError:
+    from importlib_resources import files as package_files  # type: ignore
 
 import pikepdf
 
@@ -25,7 +27,7 @@ SRGB_ICC_PROFILE_NAME = 'sRGB.icc'
 
 def _postscript_objdef(
     alias: str,
-    dictionary: Dict[str, str],
+    dictionary: dict[str, str],
     *,
     stream_name: str = None,
     stream_data: bytes = None,
@@ -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'

src/ocrmypdf/pdfinfo/__init__.py

@@ -8,4 +8,6 @@
 
 """For extracting information about PDFs prior to OCR."""
 
+from __future__ import annotations
+
 from ocrmypdf.pdfinfo.info import Colorspace, Encoding, PdfInfo

src/ocrmypdf/pdfinfo/info.py

@@ -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]
+    xobject_settings: list[XobjectSettings]
-    inline_images: List[InlineSettings]
+    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] = []
+    xobject_settings: list[XobjectSettings] = []
-    inline_images: List[InlineSettings] = []
+    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,
+        pdfimage: Object | None = None,
-        inline: Optional[PdfInlineImage] = None,
+        inline: PdfInlineImage | None = None,
         shorthand=None,
     ):
         self._name = str(name)
         self._shorthand = shorthand
 
-        pim: Union[PdfInlineImage, PdfImage]
+        pim: PdfInlineImage | PdfImage
 
         if inline is not None:
             self._origin = 'inline'
@@ -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']]:
+) -> Sequence[PageInfo | None]:
-    pages: Sequence[Optional['PageInfo']] = [None] * len(pdf.pages)
+    pages: Sequence[PageInfo | None] = [None] * len(pdf.pages)
 
     def update_pageinfo(result, pbar):
         page = result
@@ -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_text: bool | None
-    _has_vector: Optional[bool]
+    _has_vector: bool | None
-    _images: List[ImageInfo]
+    _images: list[ImageInfo]
 
     def __init__(
         self,
@@ -879,9 +878,7 @@ class PageInfo:
     def images(self):
         return self._images
 
-    def get_textareas(
+    def get_textareas(self, visible: bool | None = None, corrupt: bool | None = None):
-        self, visible: Optional[bool] = None, corrupt: Optional[bool] = None
-    ):
         def predicate(obj, want_visible, want_corrupt):
             result = True
             if want_visible is not None:
@@ -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

src/ocrmypdf/pdfinfo/layout.py

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

src/ocrmypdf/pluginspec.py

@@ -6,19 +6,13 @@
 
 """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 (
+from typing import TYPE_CHECKING, AbstractSet, NamedTuple, Sequence
-    TYPE_CHECKING,
-    AbstractSet,
-    List,
-    NamedTuple,
-    Optional,
-    Sequence,
-    Tuple,
-)
 
 import pluggy
 
@@ -177,7 +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*
@@ -203,8 +197,8 @@ def rasterize_pdf_page(
     raster_device: str,
     raster_dpi: Resolution,
     pageno: int,
-    page_dpi: Optional[Resolution],
+    page_dpi: Resolution | None,
-    rotation: Optional[int],
+    rotation: int | None,
     filter_vector: bool,
 ) -> Path:
     """Rasterize one page of a PDF at resolution raster_dpi in canvas units.
@@ -233,7 +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
@@ -260,7 +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
@@ -300,9 +294,7 @@ def filter_page_image(page: 'PageContext', image_filename: Path) -> Path:
 
 
 @hookspec(firstresult=True)
-def filter_pdf_page(
+def filter_pdf_page(page: PageContext, image_filename: Path, output_pdf: Path) -> Path:
-    page: 'PageContext', image_filename: Path, output_pdf: Path
-) -> Path:
     """Called to convert a filtered whole page image into a PDF.
 
     A whole page image is only produced when preprocessing command line arguments
@@ -445,7 +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,
@@ -501,7 +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

src/ocrmypdf/quality.py

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

src/ocrmypdf/subprocess/__init__.py

@@ -7,16 +7,18 @@
 
 """Wrappers to manage subprocess calls"""
 
+from __future__ import annotations
+
 import logging
 import os
 import re
 import sys
-from collections.abc import Mapping
 from contextlib import suppress
 from functools import lru_cache
+from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, CompletedProcess, Popen
 from subprocess import run as subprocess_run
-from typing import Callable, Optional, Type, Union
+from typing import Callable, Mapping, Sequence, Union
 
 from packaging.version import Version
 
@@ -26,11 +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,
+    required_for: str | None = None,
-    recommended=False,
+    recommended: bool = False,
-    version_parser: Type[Version] = Version,
+    version_parser: type[Version] = Version,
-):
+) -> None:
     """Check for required version of external program and raise exception if not.
 
     Args:

src/ocrmypdf/subprocess/_windows.py

@@ -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(
+def registry_enum(key: HKEYType, enum_fn: Callable[[HKEYType, int], T]) -> Iterator[T]:
-    key: winreg.HKEYType, enum_fn: Callable[[winreg.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))
+            for _, gs_path, _ in registry_values(k):
-            yield Path(gs_path) / 'bin'
+                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)

tests/__init__.py

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

tests/conftest.py

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

tests/plugins/gs_feature_elision.py

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

tests/plugins/gs_pdfa_failure.py

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

tests/plugins/gs_raster_failure.py

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

tests/plugins/gs_render_failure.py

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

tests/plugins/tesseract_badutf8.py

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

tests/plugins/tesseract_big_image_error.py

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

tests/plugins/tesseract_cache.py

@@ -44,6 +44,8 @@ Assumes Tesseract 4.0.0-alpha or higher.
 
 """
 
+from __future__ import annotations
+
 import argparse
 import json
 import logging

tests/plugins/tesseract_crash.py

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

tests/plugins/tesseract_debug_rotate.py

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

tests/plugins/tesseract_noop.py

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

tests/plugins/tesseract_simulate_oom_killer.py

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

tests/test_acroform.py

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

tests/test_api.py

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

tests/test_check_pdf.py

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

tests/test_completion.py

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

tests/test_concurrency.py

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

tests/test_ghostscript.py

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

tests/test_graft.py

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

tests/test_helpers.py

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

tests/test_hocrtransform.py

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

tests/test_image_input.py

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

tests/test_logging.py

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

tests/test_main.py

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

tests/test_metadata.py

@@ -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

tests/test_optimize.py

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

tests/test_page_numbers.py

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

tests/test_pdfa.py

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

tests/test_pdfinfo.py

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

tests/test_pipeline.py

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

tests/test_preprocessing.py

@@ -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

tests/test_quality.py

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

tests/test_rotation.py

@@ -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

tests/test_stdio.py

@@ -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

tests/test_tesseract.py

@@ -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

tests/test_unpaper.py

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

tests/test_userunit.py

@@ -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

tests/test_validation.py

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