flake8 delinting

src/ocrmypdf/_exec/tesseract.py

@@ -20,7 +20,6 @@ from typing import List, Optional
 
 from PIL import Image
 
-from ocrmypdf.api import StrPath
 from ocrmypdf.exceptions import (
     MissingDependencyError,
     SubprocessOutputError,

src/ocrmypdf/_exec/unpaper.py

@@ -96,12 +96,12 @@ def run(
         try:
             with Image.open(output_pnm) as imout:
                 imout.save(output_file, dpi=(dpi, dpi))
-        except (FileNotFoundError, OSError):
+        except OSError as e:
             raise SubprocessOutputError(
                 "unpaper: failed to produce the expected output file. "
                 + " Called with: "
                 + str(args_unpaper)
-            ) from None
+            ) from e
 
 
 def validate_custom_args(args: str) -> List[str]:

src/ocrmypdf/_sync.py

@@ -399,7 +399,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
                 return ExitCode.invalid_output_pdf
             report_output_file_size(options, start_input_file, options.output_file)
 
-    except (KeyboardInterrupt if not api else NeverRaise) as e:
+    except (KeyboardInterrupt if not api else NeverRaise):
         if options.verbose >= 1:
             log.exception("KeyboardInterrupt")
         else:
@@ -413,7 +413,7 @@ def run_pipeline(options, *, plugin_manager, api=False):
         else:
             log.error(type(e).__name__)
         return e.exit_code
-    except (Exception if not api else NeverRaise) as e:  # pylint: disable=broad-except
+    except (Exception if not api else NeverRaise):  # pylint: disable=broad-except
         log.exception("An exception occurred while executing the pipeline")
         return ExitCode.other_error
     finally:

src/ocrmypdf/_validation.py

@@ -26,12 +26,7 @@ from ocrmypdf.exceptions import (
     MissingDependencyError,
     OutputFileAccessError,
 )
-from ocrmypdf.helpers import (
-    is_file_writable,
-    is_iterable_notstr,
-    monotonic,
-    safe_symlink,
-)
+from ocrmypdf.helpers import is_file_writable, monotonic, safe_symlink
 from ocrmypdf.hocrtransform import HOCR_OK_LANGS
 from ocrmypdf.subprocess import check_external_program
 
@@ -68,7 +63,7 @@ def check_options_languages(options, ocr_engine_languages):
     missing_languages = options.languages - ocr_engine_languages
     if missing_languages:
         msg = (
-            f"OCR engine does not have language data for the following "
+            "OCR engine does not have language data for the following "
             "requested languages: \n"
         )
         msg += '\n'.join(lang for lang in missing_languages)

src/ocrmypdf/api.py

@@ -15,10 +15,7 @@ from pathlib import Path
 from typing import AnyStr, BinaryIO, Iterable, Optional, Union
 from warnings import warn
 
-from ocrmypdf._logging import (  # pylint: disable=unused-import
-    PageNumberFilter,
-    TqdmConsole,
-)
+from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_options
@@ -338,3 +335,17 @@ def ocr(  # pylint: disable=unused-argument
         options = create_options(**create_options_kwargs)
         check_options(options, plugin_manager)
         return run_pipeline(options=options, plugin_manager=plugin_manager, api=True)
+
+
+__all__ = [
+    'PageNumberFilter',
+    'TqdmConsole',
+    'Verbosity',
+    'check_options',
+    'configure_logging',
+    'create_options',
+    'get_parser',
+    'get_plugin_manager',
+    'ocr',
+    'run_pipeline',
+]

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -21,7 +21,7 @@ import sys
 import threading
 from contextlib import suppress
 from multiprocessing.pool import Pool, ThreadPool
-from typing import Callable, Iterable, Optional, Tuple, Type, Union
+from typing import Callable, Iterable, Type, Union
 
 from tqdm import tqdm
 

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -11,7 +11,6 @@ import os
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import tesseract
 from ocrmypdf.cli import numeric
-from ocrmypdf.exceptions import MissingDependencyError
 from ocrmypdf.helpers import clamp
 from ocrmypdf.pluginspec import OcrEngine
 from ocrmypdf.subprocess import check_external_program

src/ocrmypdf/helpers.py

@@ -226,7 +226,7 @@ def check_pdf(input_file: Path) -> bool:
             except (
                 # Workaround for a problematic pikepdf version
                 # pragma: no cover
-                getattr(pikepdf, 'ForeignObjectError')
+                pikepdf.ForeignObjectError
                 if pikepdf.__version__ == '2.1.0'
                 else NeverRaise
             ):

src/ocrmypdf/optimize.py

@@ -533,12 +533,15 @@ def transcode_pngs(
         _transcode_png(pike, filename, xref)
 
 
+DEFAULT_EXECUTOR = SerialExecutor()
+
+
 def optimize(
     input_file: Path,
     output_file: Path,
     context,
     save_settings,
-    executor: Executor = SerialExecutor(),
+    executor: Executor = DEFAULT_EXECUTOR,
 ) -> None:
     options = context.options
     if options.optimize == 0:

src/ocrmypdf/pdfinfo/info.py

@@ -9,7 +9,7 @@
 import atexit
 import logging
 import re
-from collections import defaultdict, namedtuple
+from collections import defaultdict
 from contextlib import ExitStack
 from decimal import Decimal
 from enum import Enum
@@ -449,7 +449,7 @@ def _image_xobjects(container) -> Iterator[Tuple[Object, str]]:
     xobjs = resources['/XObject'].as_dict()
     for xobj in xobjs:
         candidate: Object = xobjs[xobj]
-        if not '/Subtype' in candidate:
+        if '/Subtype' not in candidate:
             continue
         if candidate['/Subtype'] == '/Image':
             pdfimage = candidate
@@ -877,6 +877,9 @@ class PageInfo:
         )
 
 
+DEFAULT_EXECUTOR = SerialExecutor()
+
+
 class PdfInfo:
     """Get summary information about a PDF"""
 
@@ -888,7 +891,7 @@ class PdfInfo:
         progbar: bool = False,
         max_workers: int = None,
         check_pages=None,
-        executor: Executor = SerialExecutor(),
+        executor: Executor = DEFAULT_EXECUTOR,
     ):
         self._infile = infile
         if check_pages is None:

src/ocrmypdf/subprocess/__init__.py

@@ -15,7 +15,6 @@ from collections.abc import Mapping
 from contextlib import suppress
 from distutils.version import LooseVersion, Version
 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

src/ocrmypdf/subprocess/_windows.py

@@ -9,9 +9,9 @@ import os
 import shutil
 import sys
 from distutils.version import LooseVersion
-from itertools import chain, filterfalse
+from itertools import chain
 from pathlib import Path
-from typing import Any, Callable, Iterator, Optional, Tuple, TypeVar, cast
+from typing import Any, Callable, Iterable, Iterator, Set, Tuple, TypeVar
 
 try:
     import winreg
@@ -137,14 +137,12 @@ def fix_windows_args(program, args, env):
     return args
 
 
-def unique_everseen(iterable, key=None):
-    "List unique elements, preserving order. Remember all elements ever seen."
+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()
+    seen: Set[T] = set()
     seen_add = seen.add
-    if key is None:
-        key = lambda x: x
     for element in iterable:
         k = key(element)
         if k not in seen: