Configure pylint in pyproject and delint

src/ocrmypdf/_exec/ghostscript.py

@@ -14,13 +14,12 @@ import sys
 from io import BytesIO
 from os import fspath
 from pathlib import Path
-from shutil import which
 from subprocess import PIPE, CalledProcessError
 from typing import Optional
 
 from PIL import Image, UnidentifiedImageError
 
-from ocrmypdf.exceptions import MissingDependencyError, SubprocessOutputError
+from ocrmypdf.exceptions import SubprocessOutputError
 from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import get_version, run, run_polling_stderr
 
@@ -33,29 +32,18 @@ except AttributeError:
 
 log = logging.getLogger(__name__)
 
-missing_gs_error = """
----------------------------------------------------------------------
-This error normally occurs when ocrmypdf find can't Ghostscript.
-Please ensure Ghostscript is installed and its location is added to
-the system PATH environment variable.
-
-For details see:
-    https://ocrmypdf.readthedocs.io/en/latest/installation.html
----------------------------------------------------------------------
-"""
-
 # Most reliable what to get the bitness of Python interpreter, according to Python docs
-_is_64bit = sys.maxsize > 2**32
+_IS_64BIT = sys.maxsize > 2**32
 
-_gswin = None
+_GSWIN = None
 if os.name == 'nt':
-    if _is_64bit:
-        _gswin = 'gswin64c'
+    if _IS_64BIT:
+        _GSWIN = 'gswin64c'
     else:
-        _gswin = 'gswin32c'
+        _GSWIN = 'gswin32c'
 
-GS = _gswin if _gswin else 'gs'
-del _gswin
+GS = _GSWIN if _GSWIN else 'gs'
+del _GSWIN
 
 
 def version():
@@ -126,7 +114,7 @@ def rasterize_pdf(
         p = run(args_gs, stdout=PIPE, stderr=PIPE, check=True)
     except CalledProcessError as e:
         log.error(e.stderr.decode(errors='replace'))
-        raise SubprocessOutputError('Ghostscript rasterizing failed')
+        raise SubprocessOutputError('Ghostscript rasterizing failed') from e
     else:
         stderr = p.stderr.decode(errors='replace')
         if _gs_error_reported(stderr):
@@ -156,6 +144,8 @@ def rasterize_pdf(
 
 
 class GhostscriptFollower:
+    """Parses the output of Ghostscript and uses it to update the progress bar."""
+
     re_process = re.compile(r"Processing pages \d+ through (\d+).")
     re_page = re.compile(r"Page (\d+)")
 

src/ocrmypdf/_exec/tesseract.py

@@ -13,7 +13,7 @@ from math import pi
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import Dict, Iterator, List, Optional
+from typing import Dict, List, Optional
 
 from packaging.version import Version
 from PIL import Image
@@ -55,6 +55,8 @@ TESSERACT_THRESHOLDING_METHODS: Dict[str, int] = {
 
 
 class TesseractLoggerAdapter(logging.LoggerAdapter):
+    "Prepend [tesseract] to messages emitted from tesseract"
+
     def process(self, msg, kwargs):
         kwargs['extra'] = self.extra
         return f'[tesseract] {msg}', kwargs
@@ -105,6 +107,7 @@ TESSERACT_VERSION_PATTERN = r"""
 
 
 class TesseractVersion(Version):
+    "Modify standard packaging.Version regex to support Tesseract idiosyncracies."
     _regex = re.compile(
         r"^\s*" + TESSERACT_VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE
     )
@@ -169,14 +172,14 @@ def tess_base_args(langs: List[str], engine_mode: Optional[int]) -> List[str]:
 
 
 def _parse_tesseract_output(binary_output: bytes) -> Dict[str, str]:
-    def g():
+    def gen():
         for line in binary_output.decode().splitlines():
             line = line.strip()
             parts = line.split(':', maxsplit=2)
             if len(parts) == 2:
                 yield parts[0].strip(), parts[1].strip()
 
-    return {k: v for k, v in g()}
+    return dict(gen())
 
 
 def get_orientation(
@@ -205,10 +208,10 @@ def get_orientation(
 
     osd = _parse_tesseract_output(p.stdout)
     angle = int(osd.get('Orientation in degrees', 0))
-    oc = OrientationConfidence(
+    orient_conf = OrientationConfidence(
         angle=angle, confidence=float(osd.get('Orientation confidence', 0))
     )
-    return oc
+    return orient_conf
 
 
 def get_deskew(

src/ocrmypdf/_exec/unpaper.py

@@ -30,12 +30,16 @@ if sys.version_info >= (3, 10):
 else:
     from tempfile import TemporaryDirectory as _TemporaryDirectory
 
-    # Consume the ignore_cleanup_errors kwarg in Python 3.9 and older, without acting
-    # on this keyword. Users who need this issue full resolved should upgrade to Python
-    # 3.10.
-    # See: https://github.com/python/cpython/pull/24793
-
     class TemporaryDirectory(_TemporaryDirectory):
+        """Shim to consume ignore_cleanup_errors kwarg on Python 3.9 and older.
+
+        The argument is consumed without action. If users are getting errors related
+        to temporary file cleanup, they should upgrade to Python 3.10 which properly
+        cleans up temporary directories on Windows.
+
+        See: https://github.com/python/cpython/pull/24793
+        """
+
         def __init__(self, ignore_cleanup_errors=False, **kwargs):
             super().__init__(**kwargs)
 
@@ -50,6 +54,8 @@ log = logging.getLogger(__name__)
 
 
 class UnpaperImageTooLargeError(Exception):
+    """To capture details when an image is too large for unpaper."""
+
     def __init__(
         self,
         w,
@@ -66,8 +72,10 @@ def version() -> str:
     return get_version('unpaper')
 
 
+SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
+
+
 def _convert_image(im: Image.Image) -> Tuple[Image.Image, bool, str]:
-    SUFFIXES = {'1': '.pbm', 'L': '.pgm', 'RGB': '.ppm'}
     im_modified = False
 
     if im.mode not in SUFFIXES: