Cleaning up the testing and coverage more

src/documents/classifier.py

@@ -52,7 +52,7 @@ def load_classifier() -> Optional["DocumentClassifier"]:
     except OSError:
         logger.exception("IO error while loading document classification model")
         classifier = None
-    except Exception:  # pragma: nocover
+    except Exception:  # pragma: no cover
         logger.exception("Unknown error while loading document classification model")
         classifier = None
 
@@ -318,7 +318,7 @@ class DocumentClassifier:
 
         return True
 
-    def preprocess_content(self, content: str) -> str:  # pragma: nocover
+    def preprocess_content(self, content: str) -> str:  # pragma: no cover
         """
         Process to contents of a document, distilling it down into
         words which are meaningful to the content

src/documents/management/commands/document_consumer.py

@@ -26,7 +26,7 @@ from documents.tasks import consume_file
 try:
     from inotifyrecursive import INotify
     from inotifyrecursive import flags
-except ImportError:  # pragma: nocover
+except ImportError:  # pragma: no cover
     INotify = flags = None
 
 logger = logging.getLogger("paperless.management.consumer")

src/documents/management/commands/loaddata_stdin.py

@@ -5,7 +5,7 @@ from django.core.management.commands.loaddata import Command as LoadDataCommand
 
 # This class is used to migrate data between databases
 # That's difficult to test
-class Command(LoadDataCommand):  # pragma: nocover
+class Command(LoadDataCommand):  # pragma: no cover
     """
     Allow the loading of data from standard in.  Sourced originally from:
     https://gist.github.com/bmispelon/ad5a2c333443b3a1d051 (MIT licensed)

src/documents/parsers.py

@@ -333,7 +333,7 @@ class DocumentParser(LoggingMixin):
         if self.progress_callback:
             self.progress_callback(current_progress, max_progress)
 
-    def get_settings(self):
+    def get_settings(self):  # pragma: no cover
         """
         A parser must implement this
         """

src/paperless/models.py

@@ -169,5 +169,5 @@ class ApplicationConfiguration(AbstractSingletonModel):
     class Meta:
         verbose_name = _("paperless application settings")
 
-    def __str__(self) -> str:
+    def __str__(self) -> str:  # pragma: no cover
         return "ApplicationConfiguration"

src/paperless/settings.py

@@ -51,6 +51,9 @@ def __get_boolean(key: str, default: str = "NO") -> bool:
 
 
 def __get_optional_boolean(key: str) -> Optional[bool]:
+    """
+    Returns None if the environment key is not present, otherwise a boolean
+    """
     if key in os.environ:
         return __get_boolean(key)
     return None
@@ -64,6 +67,9 @@ def __get_int(key: str, default: int) -> int:
 
 
 def __get_optional_int(key: str) -> Optional[int]:
+    """
+    Returns None if the environment key is not present, otherwise an integer
+    """
     if key in os.environ:
         return __get_int(key, -1)
     return None
@@ -76,26 +82,26 @@ def __get_float(key: str, default: float) -> float:
     return float(os.getenv(key, default))
 
 
-def __get_optional_float(key: str) -> Optional[float]:
-    if key in os.environ:
-        return __get_float(key, -1)
-    return None
-
-
 def __get_path(
     key: str,
-    default: Optional[Union[PathLike, str]] = None,
+    default: Union[PathLike, str],
-) -> Optional[Path]:
+) -> Path:
     """
     Return a normalized, absolute path based on the environment variable or a default,
-    if provided.  If not set and no default, returns None
+    if provided
     """
     if key in os.environ:
         return Path(os.environ[key]).resolve()
-    elif default is not None:
+    return Path(default).resolve()
-        return Path(default).resolve()
+
-    else:
+
-        return None
+def __get_optional_path(key: str) -> Optional[Path]:
+    """
+    Returns None if the environment key is not present, otherwise an integer
+    """
+    if key in os.environ:
+        return __get_path(key, "")
+    return None
 
 
 def __get_list(
@@ -345,7 +351,7 @@ MIDDLEWARE = [
 ]
 
 # Optional to enable compression
-if __get_boolean("PAPERLESS_ENABLE_COMPRESSION", "yes"):  # pragma: nocover
+if __get_boolean("PAPERLESS_ENABLE_COMPRESSION", "yes"):  # pragma: no cover
     MIDDLEWARE.insert(0, "compression_middleware.middleware.CompressionMiddleware")
 
 ROOT_URLCONF = "paperless.urls"
@@ -513,7 +519,7 @@ CSRF_COOKIE_NAME = f"{COOKIE_PREFIX}csrftoken"
 SESSION_COOKIE_NAME = f"{COOKIE_PREFIX}sessionid"
 LANGUAGE_COOKIE_NAME = f"{COOKIE_PREFIX}django_language"
 
-EMAIL_CERTIFICATE_FILE = __get_path("PAPERLESS_EMAIL_CERTIFICATE_LOCATION")
+EMAIL_CERTIFICATE_FILE = __get_optional_path("PAPERLESS_EMAIL_CERTIFICATE_LOCATION")
 
 
 ###############################################################################

src/paperless/views.py

@@ -73,7 +73,7 @@ class StandardPagination(PageNumberPagination):
 
 
 class FaviconView(View):
-    def get(self, request, *args, **kwargs):  # pragma: nocover
+    def get(self, request, *args, **kwargs):  # pragma: no cover
         favicon = os.path.join(
             os.path.dirname(__file__),
             "static",

src/paperless_mail/mail.py

@@ -92,7 +92,7 @@ class BaseMailAction:
         M: MailBox,
         message_uid: str,
         parameter: str,
-    ):  # pragma: nocover
+    ):  # pragma: no cover
         """
         Perform mail action on the given mail uid in the mailbox.
         """
@@ -171,7 +171,7 @@ class TagMailAction(BaseMailAction):
                 return AND(NOT(gmail_label=self.keyword), no_keyword=self.keyword)
             else:
                 return {"no_keyword": self.keyword}
-        else:  # pragma: nocover
+        else:  # pragma: no cover
             raise ValueError("This should never happen.")
 
     def post_consume(self, M: MailBox, message_uid: str, parameter: str):
@@ -361,7 +361,7 @@ def get_rule_action(rule: MailRule, supports_gmail_labels: bool) -> BaseMailActi
     elif rule.action == MailRule.MailAction.TAG:
         return TagMailAction(rule.action_parameter, supports_gmail_labels)
     else:
-        raise NotImplementedError("Unknown action.")  # pragma: nocover
+        raise NotImplementedError("Unknown action.")  # pragma: no cover
 
 
 def make_criterias(rule: MailRule, supports_gmail_labels: bool):
@@ -397,7 +397,7 @@ def get_mailbox(server, port, security) -> MailBox:
     Returns the correct MailBox instance for the given configuration.
     """
     ssl_context = ssl.create_default_context()
-    if settings.EMAIL_CERTIFICATE_FILE is not None:  # pragma: nocover
+    if settings.EMAIL_CERTIFICATE_FILE is not None:  # pragma: no cover
         ssl_context.load_verify_locations(cafile=settings.EMAIL_CERTIFICATE_FILE)
 
     if security == MailAccount.ImapSecurity.NONE:
@@ -407,7 +407,7 @@ def get_mailbox(server, port, security) -> MailBox:
     elif security == MailAccount.ImapSecurity.SSL:
         mailbox = MailBox(server, port, ssl_context=ssl_context)
     else:
-        raise NotImplementedError("Unknown IMAP security")  # pragma: nocover
+        raise NotImplementedError("Unknown IMAP security")  # pragma: no cover
     return mailbox
 
 
@@ -450,7 +450,7 @@ class MailAccountHandler(LoggingMixin):
         else:
             raise NotImplementedError(
                 "Unknown title selector.",
-            )  # pragma: nocover
+            )  # pragma: no cover
 
     def _get_correspondent(
         self,
@@ -478,7 +478,7 @@ class MailAccountHandler(LoggingMixin):
         else:
             raise NotImplementedError(
                 "Unknown correspondent selector",
-            )  # pragma: nocover
+            )  # pragma: no cover
 
     def handle_mail_account(self, account: MailAccount):
         """

src/paperless_tesseract/parsers.py

@@ -213,7 +213,7 @@ class RasterisedDocumentParser(DocumentParser):
             ocrmypdf_args["skip_text"] = True
         elif self.settings.mode == ModeChoices.REDO:
             ocrmypdf_args["redo_ocr"] = True
-        else:
+        else:  # pragma: no cover
             raise ParseError(f"Invalid ocr mode: {self.settings.mode}")
 
         if self.settings.clean == CleanChoices.CLEAN:

src/paperless_tesseract/tests/test_parser_custom_settings.py

@@ -1,3 +1,5 @@
+import json
+
 from django.test import TestCase
 from django.test import override_settings
 
@@ -14,6 +16,9 @@ from paperless_tesseract.parsers import RasterisedDocumentParser
 class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     @staticmethod
     def get_params():
+        """
+        Helper to get just the OCRMyPDF parameters from the parser
+        """
         return RasterisedDocumentParser(None).construct_ocrmypdf_parameters(
             input_file="input.pdf",
             output_file="output.pdf",
@@ -23,6 +28,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         )
 
     def test_db_settings_ocr_pages(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_PAGES than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_PAGES=10):
             instance = ApplicationConfiguration.objects.all().first()
             instance.pages = 5
@@ -32,6 +46,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertEqual(params["pages"], "1-5")
 
     def test_db_settings_ocr_language(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_LANGUAGE than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_LANGUAGE="eng+deu"):
             instance = ApplicationConfiguration.objects.all().first()
             instance.language = "fra+ita"
@@ -41,7 +64,16 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertEqual(params["language"], "fra+ita")
 
     def test_db_settings_ocr_output_type(self):
-        with override_settings(OCR_LANGUAGE="pdfa-3"):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_OUTPUT_TYPE than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
+        with override_settings(OCR_OUTPUT_TYPE="pdfa-3"):
             instance = ApplicationConfiguration.objects.all().first()
             instance.output_type = OutputTypeChoices.PDF_A
             instance.save()
@@ -50,6 +82,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertEqual(params["output_type"], "pdfa")
 
     def test_db_settings_ocr_mode(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_MODE than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_MODE="redo"):
             instance = ApplicationConfiguration.objects.all().first()
             instance.mode = ModeChoices.SKIP
@@ -61,6 +102,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertNotIn("force_ocr", params)
 
     def test_db_settings_ocr_clean(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_CLEAN than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_CLEAN="clean-final"):
             instance = ApplicationConfiguration.objects.all().first()
             instance.unpaper_clean = CleanChoices.CLEAN
@@ -80,6 +130,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertNotIn("clean", params)
 
     def test_db_settings_ocr_deskew(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_DESKEW than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_DESKEW=False):
             instance = ApplicationConfiguration.objects.all().first()
             instance.deskew = True
@@ -89,6 +148,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertTrue(params["deskew"])
 
     def test_db_settings_ocr_rotate(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_ROTATE_PAGES
+              and OCR_ROTATE_PAGES_THRESHOLD than configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_ROTATE_PAGES=False, OCR_ROTATE_PAGES_THRESHOLD=30.0):
             instance = ApplicationConfiguration.objects.all().first()
             instance.rotate_pages = True
@@ -100,6 +168,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertAlmostEqual(params["rotate_pages_threshold"], 15.0)
 
     def test_db_settings_ocr_max_pixels(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_MAX_IMAGE_PIXELS than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_MAX_IMAGE_PIXELS=2_000_000.0):
             instance = ApplicationConfiguration.objects.all().first()
             instance.max_image_pixels = 1_000_000.0
@@ -109,6 +186,15 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
         self.assertAlmostEqual(params["max_image_mpixels"], 1.0)
 
     def test_db_settings_ocr_color_convert(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_COLOR_CONVERSION_STRATEGY than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
         with override_settings(OCR_COLOR_CONVERSION_STRATEGY="LeaveColorUnchanged"):
             instance = ApplicationConfiguration.objects.all().first()
             instance.color_conversion_strategy = ColorConvertChoices.INDEPENDENT
@@ -119,3 +205,28 @@ class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCas
             params["color_conversion_strategy"],
             "UseDeviceIndependentColor",
         )
+
+    def test_ocr_user_args(self):
+        """
+        GIVEN:
+            - Django settings defines different value for OCR_USER_ARGS than
+              configuration object
+        WHEN:
+            - OCR parameters are constructed
+        THEN:
+            - Configuration from database is utilized
+        """
+        with override_settings(
+            OCR_USER_ARGS=json.dumps({"continue_on_soft_render_error": True}),
+        ):
+            instance = ApplicationConfiguration.objects.all().first()
+            instance.user_args = {"unpaper_args": "--pre-rotate 90"}
+            instance.save()
+
+            params = self.get_params()
+
+        self.assertIn("unpaper_args", params)
+        self.assertEqual(
+            params["unpaper_args"],
+            "--pre-rotate 90",
+        )

src/paperless_tika/parsers.py

@@ -65,7 +65,7 @@ class TikaDocumentParser(DocumentParser):
                             document_path.read_bytes(),
                             mime_type,
                         )
-                    else:  # pragma: nocover
+                    else:  # pragma: no cover
                         raise
         except Exception as err:
             raise ParseError(