Python 3.10 cleanup, manual fixes

misc/watcher.py

@@ -8,6 +8,7 @@
 # Do not enable annotations!
 # https://github.com/tiangolo/typer/discussions/598
 # from __future__ import annotations
+from __future__ import annotations
 
 import json
 import logging
@@ -131,7 +132,7 @@ def execute_ocrmypdf(
 
 
 class HandleObserverEvent(PatternMatchingEventHandler):
-    def __init__(
+    def __init__(  # noqa: D107
         self,
         patterns=None,
         ignore_patterns=None,
@@ -191,7 +192,7 @@ def main(
         bool,
         typer.Option(
             envvar='OCR_OUTPUT_DIRECTORY_YEAR_MONTH',
-            help='Create a subdirectory in the output directory for each year and month',
+            help='Create a subdirectory in the output directory for each year/month',
         ),
     ] = False,
     on_success_delete: Annotated[

src/ocrmypdf/_exec/unpaper.py

@@ -14,7 +14,6 @@
 from pathlib import Path
 from subprocess import PIPE, STDOUT
 from tempfile import TemporaryDirectory
-from typing import Union
 
 from packaging.version import Version
 from PIL import Image
@@ -28,7 +27,7 @@
 
 UNPAPER_IMAGE_PIXEL_LIMIT = 256 * 1024 * 1024
 
-DecFloat = Union[Decimal, float]
+DecFloat = Decimal | float
 
 log = logging.getLogger(__name__)
 

src/ocrmypdf/api.py

@@ -14,7 +14,7 @@
 from enum import IntEnum
 from io import IOBase
 from pathlib import Path
-from typing import AnyStr, BinaryIO, Union
+from typing import AnyStr, BinaryIO
 from warnings import warn
 
 import pluggy
@@ -28,8 +28,8 @@
 from ocrmypdf.cli import ArgumentParser, get_parser
 from ocrmypdf.helpers import is_iterable_notstr
 
-StrPath = Union[Path, AnyStr]
-PathOrIO = Union[BinaryIO, StrPath]
+StrPath = Path | AnyStr
+PathOrIO = BinaryIO | StrPath
 
 # Installing plugins affects the global state of the Python interpreter,
 # so we need to use a lock to prevent multiple threads from installing
@@ -169,7 +169,7 @@ def _kwargs_to_cmdline(
 
         # We have a parameter
         cmdline.append(f"--{cmd_style_arg}")
-        if isinstance(val, (int, float)):
+        if isinstance(val, int | float):
             cmdline.append(str(val))
         elif isinstance(val, str):
             cmdline.append(val)
@@ -201,11 +201,11 @@ def create_options(
         defer_kwargs={'progress_bar', 'plugins', 'parser', 'input_file', 'output_file'},
         **kwargs,
     )
-    if isinstance(input_file, (BinaryIO, IOBase)):
+    if isinstance(input_file, BinaryIO | IOBase):
         cmdline.append('stream://input_file')
     else:
         cmdline.append(os.fspath(input_file))
-    if isinstance(output_file, (BinaryIO, IOBase)):
+    if isinstance(output_file, BinaryIO | IOBase):
         cmdline.append('stream://output_file')
     else:
         cmdline.append(os.fspath(output_file))
@@ -343,7 +343,7 @@ def ocr(  # noqa: D417
 
     if not plugins:
         plugins = []
-    elif isinstance(plugins, (str, Path)):
+    elif isinstance(plugins, str | Path):
         plugins = [plugins]
     else:
         plugins = list(plugins)

src/ocrmypdf/pdfinfo/info.py

@@ -10,7 +10,6 @@
 import logging
 import re
 import statistics
-import sys
 from collections import defaultdict
 from collections.abc import Callable, Container, Iterable, Iterator, Mapping, Sequence
 from contextlib import contextmanager
@@ -1060,12 +1059,7 @@ def page_dpi_profile(self) -> PageResolutionProfile | None:
 
         weights = [area / total_drawn_area for area in image_areas]
         # Calculate harmonic mean of DPIs weighted by area
-        if sys.version_info >= (3, 10):
-            weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
-        else:
-            weighted_dpi = sum(weights) / sum(
-                weight / dpi for weight, dpi in zip(weights, image_dpis)
-            )
+        weighted_dpi = statistics.harmonic_mean(image_dpis, weights)
         max_dpi = max(image_dpis)
         dpi_average_max_ratio = weighted_dpi / max_dpi
 
@@ -1176,7 +1170,7 @@ def is_tagged(self) -> bool:
     @property
     def filename(self) -> str | Path:
         """Return filename of PDF."""
-        if not isinstance(self._infile, (str, Path)):
+        if not isinstance(self._infile, str | Path):
             raise NotImplementedError("can't get filename from stream")
         return self._infile