Pre-release delinting

misc/watcher.py

@@ -38,7 +38,7 @@ ON_SUCCESS_DELETE = bool(os.getenv('OCR_ON_SUCCESS_DELETE', ''))
 DESKEW = bool(os.getenv('OCR_DESKEW', ''))
 OCR_JSON_SETTINGS = json.loads(os.getenv('OCR_JSON_SETTINGS', '{}'))
 POLL_NEW_FILE_SECONDS = int(os.getenv('OCR_POLL_NEW_FILE_SECONDS', '1'))
-USE_POLLING = bool(os.getenv('OCR_USE_POLLING', False))
+USE_POLLING = bool(os.getenv('OCR_USE_POLLING', ''))
 LOGLEVEL = os.getenv('OCR_LOGLEVEL', 'INFO').upper()
 PATTERNS = ['*.pdf']
 

src/ocrmypdf/__main__.py

@@ -26,14 +26,13 @@ from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._sync import run_pipeline
 from ocrmypdf._validation import check_closed_streams, check_options
 from ocrmypdf.api import Verbosity, configure_logging
-from ocrmypdf.cli import get_parser, plugins_only_parser
 from ocrmypdf.exceptions import BadArgsError, ExitCode, MissingDependencyError
 
 log = logging.getLogger('ocrmypdf')
 
 
 def run(args=None):
-    parser, options, plugin_manager = get_parser_options_plugins(args=args)
+    _parser, options, plugin_manager = get_parser_options_plugins(args=args)
 
     if not check_closed_streams(options):
         return ExitCode.bad_args

src/ocrmypdf/_exec/tesseract.py

@@ -21,11 +21,10 @@ import logging
 import os
 import shutil
 from collections import namedtuple
-from contextlib import suppress
 from os import fspath
 from pathlib import Path
 from subprocess import PIPE, STDOUT, CalledProcessError, TimeoutExpired
-from typing import List, Optional
+from typing import List
 
 from PIL import Image
 
@@ -34,7 +33,6 @@ from ocrmypdf.exceptions import (
     SubprocessOutputError,
     TesseractConfigError,
 )
-from ocrmypdf.helpers import safe_symlink
 from ocrmypdf.subprocess import get_version, run
 
 log = logging.getLogger(__name__)

src/ocrmypdf/_pipeline.py

@@ -28,7 +28,7 @@ from pikepdf.models.metadata import encode_pdf_date
 from PIL import Image, ImageColor, ImageDraw
 
 from ocrmypdf import leptonica
-from ocrmypdf._exec import ghostscript, unpaper
+from ocrmypdf._exec import unpaper
 from ocrmypdf._version import PROGRAM_NAME
 from ocrmypdf._version import __version__ as VERSION
 from ocrmypdf.exceptions import (

src/ocrmypdf/_plugin_manager.py

@@ -61,7 +61,7 @@ def get_parser_options_plugins(
     plugin_manager = get_plugin_manager(pre_options.plugins)
 
     parser = get_parser()
-    plugin_manager.hook.add_options(parser=parser)
+    plugin_manager.hook.add_options(parser=parser)  # pylint: disable=no-member
 
     options = parser.parse_args(args=args)
     return parser, options, plugin_manager

src/ocrmypdf/api.py

@@ -15,14 +15,13 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import inspect
 import logging
 import os
 import sys
 from argparse import ArgumentParser
 from enum import IntEnum
 from pathlib import Path
-from typing import Dict, Iterable
+from typing import Iterable
 
 from ocrmypdf._logging import PageNumberFilter, TqdmConsole
 from ocrmypdf._plugin_manager import get_plugin_manager

src/ocrmypdf/builtin_plugins/ghostscript.py

@@ -16,13 +16,11 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 import logging
-from pathlib import Path
 
 from ocrmypdf import hookimpl
 from ocrmypdf._exec import ghostscript
 from ocrmypdf._validation import HOCR_OK_LANGS
 from ocrmypdf.exceptions import MissingDependencyError
-from ocrmypdf.helpers import Resolution
 from ocrmypdf.subprocess import check_external_program
 
 log = logging.getLogger(__name__)

src/ocrmypdf/builtin_plugins/tesseract_ocr.py

@@ -15,7 +15,6 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import argparse
 import logging
 import os
 

src/ocrmypdf/pluginspec.py

@@ -15,7 +15,7 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from abc import ABC, abstractstaticmethod
+from abc import ABC, abstractmethod, abstractstaticmethod
 from argparse import ArgumentParser, Namespace
 from collections import namedtuple
 from pathlib import Path
@@ -134,7 +134,7 @@ class OcrEngine(ABC):
     def creator_tag(options: Namespace) -> str:
         """Returns the creator tag to identify this software's role in creating the PDF."""
 
-    @abstractstaticmethod
+    @abstractmethod
     def __str__(self):
         """Returns name of OCR engine and version."""
 

tests/conftest.py

@@ -15,7 +15,6 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import ast
 import os
 import platform
 import sys
@@ -24,7 +23,7 @@ from subprocess import PIPE, run
 
 import pytest
 
-from ocrmypdf import api, cli, pdfinfo
+from ocrmypdf import api, pdfinfo
 from ocrmypdf._exec import unpaper
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 

tests/plugins/gs_raster_failure.py

@@ -25,7 +25,6 @@ from unittest.mock import patch
 
 from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins import ghostscript
-from ocrmypdf.subprocess import run
 
 
 def raise_gs_fail(*args, **kwargs):

tests/plugins/gs_render_failure.py

@@ -19,13 +19,11 @@
 # TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
-from pathlib import Path
 from subprocess import CalledProcessError
 from unittest.mock import patch
 
 from ocrmypdf import hookimpl
 from ocrmypdf.builtin_plugins import ghostscript
-from ocrmypdf.subprocess import run
 
 
 def raise_gs_fail(*args, **kwargs):

tests/plugins/tesseract_crash.py

@@ -20,7 +20,6 @@
 # SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 import signal
-import sys
 from subprocess import CalledProcessError
 from unittest.mock import patch
 

tests/test_ghostscript.py

@@ -26,9 +26,11 @@ from ocrmypdf._exec.ghostscript import rasterize_pdf
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.helpers import Resolution
 
-check_ocrmypdf = pytest.helpers.check_ocrmypdf
-run_ocrmypdf = pytest.helpers.run_ocrmypdf
-run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api
+check_ocrmypdf = pytest.helpers.check_ocrmypdf  # pylint: disable=no-member
+run_ocrmypdf = pytest.helpers.run_ocrmypdf  # pylint: disable=no-member
+run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api  # pylint: disable=no-member
+
+# pylint: disable=redefined-outer-name
 
 
 @pytest.fixture
@@ -37,7 +39,7 @@ def francais(resources):
     return path, pikepdf.open(path)
 
 
-def test_rasterize_size(francais, outdir, caplog):
+def test_rasterize_size(francais, outdir):
     path, pdf = francais
     page_size_pts = (pdf.pages[0].MediaBox[2], pdf.pages[0].MediaBox[3])
     assert pdf.pages[0].MediaBox[0] == pdf.pages[0].MediaBox[1] == 0
@@ -86,7 +88,7 @@ def test_rasterize_rotated(francais, outdir, caplog):
 
 
 def test_gs_render_failure(resources, outpdf):
-    p, out, err = run_ocrmypdf(
+    p, _out, err = run_ocrmypdf(
         resources / 'blank.pdf',
         outpdf,
         '--plugin',
@@ -99,7 +101,7 @@ def test_gs_render_failure(resources, outpdf):
 
 
 def test_gs_raster_failure(resources, outpdf):
-    p, out, err = run_ocrmypdf(
+    p, _out, err = run_ocrmypdf(
         resources / 'francais.pdf',
         outpdf,
         '--plugin',
@@ -112,7 +114,7 @@ def test_gs_raster_failure(resources, outpdf):
 
 
 def test_ghostscript_pdfa_failure(resources, outpdf):
-    p, out, err = run_ocrmypdf(
+    p, _out, _err = run_ocrmypdf(
         resources / 'francais.pdf',
         outpdf,
         '--plugin',

tests/test_helpers.py

@@ -18,7 +18,6 @@
 import logging
 import multiprocessing
 import os
-from pathlib import Path
 from unittest.mock import MagicMock
 
 import pytest

tests/test_hocrtransform.py

@@ -15,8 +15,6 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-from pathlib import Path
-
 import pytest
 from PIL import Image
 

tests/test_pdfinfo.py

@@ -17,7 +17,6 @@
 
 import pickle
 from math import isclose
-from tempfile import NamedTemporaryFile
 
 import img2pdf
 import pikepdf
@@ -26,7 +25,6 @@ from PIL import Image
 from reportlab.pdfgen.canvas import Canvas
 
 from ocrmypdf import pdfinfo
-from ocrmypdf._exec import ghostscript
 from ocrmypdf.pdfinfo import Colorspace, Encoding
 
 # pylint: disable=protected-access
@@ -110,7 +108,7 @@ def test_single_page_inline_image(outdir):
     assert pdfimage.width == 8
 
 
-def test_jpeg(resources, outdir):
+def test_jpeg(resources):
     filename = resources / 'c02-22.pdf'
 
     pdf = pdfinfo.PdfInfo(filename)
@@ -133,7 +131,7 @@ def test_no_contents(resources):
 
     pdf = pdfinfo.PdfInfo(filename)
     assert len(pdf[0].images) == 0
-    assert pdf[0].has_text == False
+    assert not pdf[0].has_text
 
 
 def test_oversized_page(resources):

tests/test_rotation.py

@@ -15,10 +15,8 @@
 # You should have received a copy of the GNU General Public License
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
-import logging
 from io import BytesIO
 from os import fspath
-from unittest.mock import Mock
 
 import img2pdf
 import pikepdf

tests/test_stdio.py

@@ -18,7 +18,7 @@
 import os
 import sys
 from pathlib import Path
-from subprocess import DEVNULL, PIPE, CalledProcessError, Popen, run
+from subprocess import DEVNULL, PIPE, Popen, run
 
 import pytest
 
@@ -95,7 +95,7 @@ def test_closed_streams(ocrmypdf_exec, resources, outpdf):
         stdin=None,
         preexec_fn=evil_closer,
     )
-    out, err = p.communicate()
+    _out, err = p.communicate()
     print(err.decode())
     assert p.returncode == ExitCode.ok
 
@@ -121,7 +121,7 @@ def test_dev_null(resources):
     if 'COV_CORE_DATAFILE' in os.environ:
         pytest.skip(msg="Coverage uses stdout")
 
-    p, out, err = run_ocrmypdf(
+    p, out, _err = run_ocrmypdf(
         resources / 'trivial.pdf',
         os.devnull,
         '--force-ocr',

tests/test_unpaper.py

@@ -22,7 +22,6 @@ import pytest
 
 from ocrmypdf._plugin_manager import get_parser_options_plugins
 from ocrmypdf._validation import check_options
-from ocrmypdf.cli import get_parser
 from ocrmypdf.exceptions import ExitCode, MissingDependencyError
 
 # pytest.helpers is dynamic

tests/test_userunit.py

@@ -22,9 +22,11 @@ import pytest
 from ocrmypdf.exceptions import ExitCode
 from ocrmypdf.pdfinfo import PdfInfo
 
-check_ocrmypdf = pytest.helpers.check_ocrmypdf
-run_ocrmypdf = pytest.helpers.run_ocrmypdf
-run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api
+check_ocrmypdf = pytest.helpers.check_ocrmypdf  # pylint: disable=no-member
+run_ocrmypdf = pytest.helpers.run_ocrmypdf  # pylint: disable=no-member
+run_ocrmypdf_api = pytest.helpers.run_ocrmypdf_api  # pylint: disable=no-member
+
+# pylint: disable=redefined-outer-name
 
 
 @pytest.fixture

tests/test_validation.py

@@ -16,7 +16,6 @@
 # along with OCRmyPDF.  If not, see <http://www.gnu.org/licenses/>.
 
 import logging
-import os
 from unittest.mock import patch
 
 import pikepdf
@@ -35,7 +34,7 @@ def make_opts_pm(input_file='a.pdf', output_file='b.pdf', language='eng', **kwar
         kwargs['language'] = language
     parser = get_parser()
     pm = get_plugin_manager(kwargs.get('plugins', []))
-    pm.hook.add_options(parser=parser)
+    pm.hook.add_options(parser=parser)  # pylint: disable=no-member
     return (
         create_options(
             input_file=input_file, output_file=output_file, parser=parser, **kwargs