Performance: Precompile scoped bytecode cache once per container start

docker/rootfs/etc/s6-overlay/s6-rc.d/init-compile-bytecode/run

@@ -0,0 +1,51 @@
+#!/command/with-contenv /usr/bin/bash
+# shellcheck shell=bash
+declare -r log_prefix="[init-compile-bytecode]"
+
+# PYTHONDONTWRITEBYTECODE=1 is set for the whole container. This unit compiles a
+# scoped set of libraries anyway, to speed up startup without bloating image size.
+
+# Handle the people using a read only file system
+if [[ "${S6_READ_ONLY_ROOT}" == "1" ]]; then
+	echo "${log_prefix} S6_READ_ONLY_ROOT=1, skipping (nothing to write bytecode to)"
+	exit 0
+fi
+
+declare -r site_packages="$(python3 -c 'import site; print(site.getsitepackages()[0])')"
+
+# Deliberately scoped to packages that paperless.settings/paperless/__init__.py import
+# unconditionally on every manage.py invocation (Django itself, the always-loaded
+# INSTALLED_APPS, and celery). This is NOT "compile everything" - the optional AI stack
+# (torch, llama-index, sentence-transformers, ...) is intentionally excluded since it is
+# lazy-imported and large.
+declare -a scope=(
+	"${PAPERLESS_SRC_DIR}"
+	"${site_packages}/django"
+	"${site_packages}/celery"
+	"${site_packages}/kombu"
+	"${site_packages}/rest_framework"
+	"${site_packages}/django_filters"
+	"${site_packages}/whitenoise"
+	"${site_packages}/corsheaders"
+	"${site_packages}/django_extensions"
+	"${site_packages}/guardian"
+	"${site_packages}/allauth"
+	"${site_packages}/drf_spectacular"
+	"${site_packages}/drf_spectacular_sidecar"
+	"${site_packages}/treenode"
+	"${site_packages}/compression_middleware"
+)
+
+declare -a existing_scope=()
+for path in "${scope[@]}"; do
+	[[ -d "${path}" ]] && existing_scope+=("${path}")
+done
+
+echo "${log_prefix} Compiling bytecode for: ${existing_scope[*]}"
+declare -r start_seconds=${SECONDS}
+
+if ! PYTHONDONTWRITEBYTECODE= python3 -m compileall -q "${existing_scope[@]}"; then
+	echo "${log_prefix} WARNING: compileall reported errors (read-only filesystem or unwritable site-packages?); continuing without a bytecode cache"
+fi
+
+echo "${log_prefix} Done in $((SECONDS - start_seconds))s"

docker/rootfs/etc/s6-overlay/s6-rc.d/init-compile-bytecode/type

@@ -0,0 +1 @@
+oneshot

docker/rootfs/etc/s6-overlay/s6-rc.d/init-compile-bytecode/up

@@ -0,0 +1 @@
+/etc/s6-overlay/s6-rc.d/init-compile-bytecode/run

pyproject.toml

@@ -186,110 +186,29 @@ line-ending = "lf"
 # https://docs.astral.sh/ruff/rules/
 select = [ "E4", "E7", "E9", "F" ]
 extend-select = [
-  "ASYNC",   # https://docs.astral.sh/ruff/rules/#flake8-async-async
-  "B002",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B003",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B004",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B005",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B006",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B008",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B009",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B010",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B012",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B013",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B014",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B015",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B016",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B017",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B018",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B019",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B020",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B021",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B022",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B023",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B025",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B026",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B029",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B030",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B031",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B032",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B033",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B035",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "B039",    # https://docs.astral.sh/ruff/rules/#flake8-bugbear-b
-  "C4",      # https://docs.astral.sh/ruff/rules/#flake8-comprehensions-c4
   "COM",  # https://docs.astral.sh/ruff/rules/#flake8-commas-com
-  "D419",    # https://docs.astral.sh/ruff/rules/#pydocstyle-d
   "DJ",   # https://docs.astral.sh/ruff/rules/#flake8-django-dj
-  "DTZ",     # https://docs.astral.sh/ruff/rules/#flake8-datetimez-dtz
   "EXE",  # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
-  "FA",      # https://docs.astral.sh/ruff/rules/#flake8-future-annotations-fa
   "FBT",  # https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt
   "FLY",  # https://docs.astral.sh/ruff/rules/#flynt-fly
-  "FURB",    # https://docs.astral.sh/ruff/rules/#refurb-furb
-  "G010",    # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
-  "G101",    # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
   "G201", # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
-  "G202",    # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
   "I",    # https://docs.astral.sh/ruff/rules/#isort-i
   "ICN",  # https://docs.astral.sh/ruff/rules/#flake8-import-conventions-icn
   "INP",  # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
-  "INT001",  # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
-  "INT002",  # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
-  "INT003",  # https://docs.astral.sh/ruff/rules/#flake8-gettext-int
   "ISC",  # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
-  "LOG001",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
-  "LOG002",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
-  "LOG009",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
-  "LOG014",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
-  "LOG015",  # https://docs.astral.sh/ruff/rules/#flake8-logging-log
-  "N999",    # https://docs.astral.sh/ruff/rules/#pep8-naming-n
-  "PERF101", # https://docs.astral.sh/ruff/rules/#perflint-perf
-  "PERF102", # https://docs.astral.sh/ruff/rules/#perflint-perf
-  "PERF402", # https://docs.astral.sh/ruff/rules/#perflint-perf
-  "PGH005",  # https://docs.astral.sh/ruff/rules/#pygrep-hooks-pgh
   "PIE",  # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
   "PLC",  # https://docs.astral.sh/ruff/rules/#pylint-pl
   "PLE",  # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR0124", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR0133", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR0206", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR0402", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1704", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1708", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1711", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1716", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1722", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1730", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1733", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR1736", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLR2044", # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PLW",     # https://docs.astral.sh/ruff/rules/#pylint-pl
-  "PT010",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
-  "PT014",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
-  "PT020",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
-  "PT025",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
-  "PT026",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
-  "PT031",   # https://docs.astral.sh/ruff/rules/#flake8-pytest-style-pt
   "PTH",  # https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
   "Q",    # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
   "RSE",  # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
   "RUF",  # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
-  "S102",    # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
-  "S110",    # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
-  "S112",    # https://docs.astral.sh/ruff/rules/#flake8-bandit-s
   "SIM",  # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
-  "T100",    # https://docs.astral.sh/ruff/rules/#flake8-debugger-t10
   "T20",  # https://docs.astral.sh/ruff/rules/#flake8-print-t20
   "TC",   # https://docs.astral.sh/ruff/rules/#flake8-type-checking-tc
   "TID",  # https://docs.astral.sh/ruff/rules/#flake8-tidy-imports-tid
-  "TRY002",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
-  "TRY004",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
-  "TRY201",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
-  "TRY203",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
-  "TRY401",  # https://docs.astral.sh/ruff/rules/#tryceratops-try
   "UP",   # https://docs.astral.sh/ruff/rules/#pyupgrade-up
   "W",    # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
-  "YTT",     # https://docs.astral.sh/ruff/rules/#flake8-2020-ytt
 ]
 ignore = [
   "DJ001",
@@ -305,7 +224,6 @@ per-file-ignores."*/migrations/*.py" = [
 ]
 # Testing
 per-file-ignores."*/tests/*.py" = [
-  "DTZ",
   "E501",
   "SIM117",
 ]

src/documents/bulk_edit.py

@@ -507,8 +507,8 @@ def rotate(
             logger.info(
                 f"Queued new rotated version for document {pair.root_doc.id} by {degrees} degrees",
             )
-        except Exception:
+        except Exception as e:
-            logger.exception(f"Error rotating document {pair.root_doc.id}")
+            logger.exception(f"Error rotating document {pair.root_doc.id}: {e}")
 
     return "OK"
 
@@ -554,9 +554,9 @@ def merge(
             affected_docs.append(doc.id)
             if handoff_asn is None and doc.archive_serial_number is not None:
                 handoff_asn = doc.archive_serial_number
-        except Exception:
+        except Exception as e:
             logger.exception(
-                f"Error merging document {doc.id}, it will not be included in the merge",
+                f"Error merging document {doc.id}, it will not be included in the merge: {e}",
             )
     if len(affected_docs) == 0:
         logger.warning("No documents were merged")
@@ -805,8 +805,8 @@ def split(
             else:
                 group(consume_tasks).delay()
 
-    except Exception:
+    except Exception as e:
-        logger.exception(f"Error splitting document {doc.id}")
+        logger.exception(f"Error splitting document {doc.id}: {e}")
 
     return "OK"
 
@@ -858,8 +858,8 @@ def delete_pages(
         logger.info(
             f"Queued new version for document {pair.root_doc.id} after deleting pages {pages}",
         )
-    except Exception:
+    except Exception as e:
-        logger.exception(f"Error deleting pages from document {pair.root_doc.id}")
+        logger.exception(f"Error deleting pages from document {pair.root_doc.id}: {e}")
 
     return "OK"
 
@@ -986,7 +986,7 @@ def edit_pdf(
                 group(consume_tasks).delay()
 
     except Exception as e:
-        logger.exception(f"Error editing document {pair.root_doc.id}")
+        logger.exception(f"Error editing document {pair.root_doc.id}: {e}")
         raise ValueError(
             f"An error occurred while editing the document: {e}",
         ) from e
@@ -1097,7 +1097,7 @@ def remove_password(
 
         except Exception as e:
             logger.exception(
-                f"Error removing password from document {pair.root_doc.id}",
+                f"Error removing password from document {pair.root_doc.id}: {e}",
             )
             raise ValueError(
                 f"An error occurred while removing the password: {e}",

src/documents/classifier.py

@@ -69,8 +69,8 @@ def load_classifier(*, raise_exception: bool = False) -> DocumentClassifier | No
         Path(settings.MODEL_FILE).unlink()
         classifier = None
         if raise_exception:
-            raise
+            raise e
-    except ClassifierModelCorruptError:
+    except ClassifierModelCorruptError as e:
         # there's something wrong with the model file.
         logger.exception(
             "Unrecoverable error while loading document "
@@ -79,17 +79,17 @@ def load_classifier(*, raise_exception: bool = False) -> DocumentClassifier | No
         Path(settings.MODEL_FILE).unlink()
         classifier = None
         if raise_exception:
-            raise
+            raise e
-    except OSError:
+    except OSError as e:
         logger.exception("IO error while loading document classification model")
         classifier = None
         if raise_exception:
-            raise
+            raise e
-    except Exception:  # pragma: no cover
+    except Exception as e:  # pragma: no cover
         logger.exception("Unknown error while loading document classification model")
         classifier = None
         if raise_exception:
-            raise
+            raise e
 
     return classifier
 

src/documents/consumer.py

@@ -216,7 +216,7 @@ class ConsumerPluginMixin:
             current_progress,
             max_progress,
             document_id=document_id,
-            owner_id=self.metadata.owner_id or None,
+            owner_id=self.metadata.owner_id if self.metadata.owner_id else None,
             users_can_view=(self.metadata.view_users or [])
             + (self.metadata.change_users or []),
             groups_can_view=(self.metadata.view_groups or [])
@@ -674,7 +674,9 @@ class ConsumerPlugin(
                             document=document,
                             logging_group=self.logging_group,
                             classifier=classifier,
-                            original_file=self.unmodified_original or self.working_copy,
+                            original_file=self.unmodified_original
+                            if self.unmodified_original
+                            else self.working_copy,
                         )
 
                         # After everything is in the database, copy the files into
@@ -847,7 +849,7 @@ class ConsumerPlugin(
         else:
             stats = Path(self.input_doc.original_file).stat()
             create_date = timezone.make_aware(
-                datetime.datetime.fromtimestamp(stats.st_mtime),  # noqa: DTZ006 - make_aware() requires a naive datetime
+                datetime.datetime.fromtimestamp(stats.st_mtime),
             )
             self.log.debug(f"Creation date from st_mtime: {create_date}")
 
@@ -961,7 +963,7 @@ class ConsumerPlugin(
         try:
             copy_basic_file_stats(source, target)
         except Exception:  # pragma: no cover
-            self.log.debug("Unable to copy file stats from %s to %s", source, target)
+            pass
 
 
 class ConsumerPreflightPlugin(

src/documents/double_sided.py

@@ -78,9 +78,7 @@ class CollatePlugin(NoCleanupPluginMixin, NoSetupPluginMixin, ConsumeTaskPlugin)
             stats = staging.stat()
             # if the file is older than the timeout, we don't consider
             # it valid
-            if (
+            if (dt.datetime.now().timestamp() - stats.st_mtime) > TIMEOUT_SECONDS:
-                dt.datetime.now(tz=dt.UTC).timestamp() - stats.st_mtime
-            ) > TIMEOUT_SECONDS:
                 logger.warning("Outdated double sided staging file exists, deleting it")
                 staging.unlink()
             else:
@@ -136,7 +134,7 @@ class CollatePlugin(NoCleanupPluginMixin, NoSetupPluginMixin, ConsumeTaskPlugin)
             shutil.move(pdf_file, staging)
             # update access to modification time so we know if the file
             # is outdated when another file gets uploaded
-            timestamp = dt.datetime.now(tz=dt.UTC).timestamp()
+            timestamp = dt.datetime.now().timestamp()
             os.utime(staging, (timestamp, timestamp))
             logger.info(
                 "Got scan with odd numbered pages of double-sided scan, moved it to %s",

src/documents/filters.py

@@ -734,7 +734,7 @@ class CustomFieldQueryParser:
         )
 
         # Check if any of the requested IDs are missing.
-        missing_ids = set(value) - {link.document_id for link in links}
+        missing_ids = set(value) - set(link.document_id for link in links)
         if missing_ids:
             # The result should be an empty set in this case.
             return Q(id__in=[])

src/documents/management/commands/document_consumer.py

@@ -631,25 +631,23 @@ class Command(BaseCommand):
                 ):
                     # Process each change
                     for change_type, path in changes:
-                        resolved_path = Path(path).resolve()
+                        path = Path(path).resolve()
                         if change_type == Change.deleted:
                             # Consumed (or otherwise removed); a later file
                             # reusing this name must not be skipped as
                             # already-queued.
-                            queued.discard(resolved_path)
+                            queued.discard(path)
-                        if not resolved_path.is_file():
+                        if not path.is_file():
                             continue
-                        if resolved_path in queued:
+                        if path in queued:
                             # Already queued and awaiting consumption; a stray
                             # event (NAS metadata touch, AV scan, etc.) while
                             # the file sits on disk mid-consumption must not
                             # cause it to be queued a second time (GH #13511).
-                            logger.debug(
+                            logger.debug(f"Ignoring event for queued file: {path}")
-                                f"Ignoring event for queued file: {resolved_path}",
-                            )
                             continue
-                        logger.debug(f"Event: {change_type.name} for {resolved_path}")
+                        logger.debug(f"Event: {change_type.name} for {path}")
-                        tracker.track(resolved_path, change_type)
+                        tracker.track(path, change_type)
 
                     # Check for stable files
                     for stable_path in tracker.get_stable_files():

src/documents/matching.py

@@ -30,10 +30,6 @@ if TYPE_CHECKING:
 logger = logging.getLogger("paperless.matching")
 
 
-class UnsupportedWorkflowTriggerTypeError(Exception):
-    pass
-
-
 def log_reason(
     matching_model: MatchingModel | WorkflowTrigger,
     document: Document,
@@ -695,9 +691,7 @@ def document_matches_workflow(
                 )
             else:
                 # New trigger types need to be explicitly checked above
-                raise UnsupportedWorkflowTriggerTypeError(
+                raise Exception(f"Trigger type {trigger_type} not yet supported")
-                    f"Trigger type {trigger_type} not yet supported",
-                )
 
             if trigger_matched:
                 logger.info(f"Document matched {trigger} from {workflow}")

src/documents/models.py

@@ -377,7 +377,7 @@ class Document(SoftDeleteModel, ModelWithOwner):  # type: ignore[django-manager-
         from documents.versioning import versions_newest_first
 
         if hasattr(self, "effective_content"):
-            return self.effective_content
+            return getattr(self, "effective_content")
 
         if self.root_document_id is not None or self.pk is None:
             return self.content

src/documents/parsers.py

@@ -41,7 +41,7 @@ def get_default_file_extension(mime_type: str) -> str:
             return supported[mime_type]
 
     ext = mimetypes.guess_extension(mime_type)
-    return ext or ""
+    return ext if ext else ""
 
 
 def is_file_ext_supported(ext: str) -> bool:

src/documents/plugins/date_parsing/__init__.py

@@ -43,8 +43,8 @@ def _discover_parser_class() -> type[DateParserPluginBase]:
                 valid_plugins.append(ep)
             else:
                 logger.warning(f"Plugin {ep.name} does not subclass DateParser.")
-        except Exception:
+        except Exception as e:
-            logger.exception(f"Unable to load date parser plugin {ep.name}")
+            logger.exception(f"Unable to load date parser plugin {ep.name}: {e}")
 
     if not valid_plugins:
         return RegexDateParserPlugin

src/documents/plugins/date_parsing/base.py

@@ -91,8 +91,8 @@ class DateParserPluginBase(ABC):
                 },
                 locales=self.config.languages,
             )
-        except Exception:
+        except Exception as e:
-            logger.exception(f"Error while parsing date string '{date_string}'")
+            logger.exception(f"Error while parsing date string '{date_string}': {e}")
             return None
 
     def _filter_date(

src/documents/regex.py

@@ -59,10 +59,11 @@ def safe_regex_match(pattern: str, text: str, *, flags: int = 0):
     try:
         validate_regex_pattern(pattern)
         compiled = regex.compile(pattern, flags=flags)
-    except (regex.error, ValueError):
+    except (regex.error, ValueError) as exc:
         logger.exception(
-            "Error while processing regular expression %s",
+            "Error while processing regular expression %s: %s",
             textwrap.shorten(pattern, width=80, placeholder="…"),
+            exc,
         )
         return None
 
@@ -85,10 +86,11 @@ def safe_regex_sub(pattern: str, repl: str, text: str, *, flags: int = 0) -> str
     try:
         validate_regex_pattern(pattern)
         compiled = regex.compile(pattern, flags=flags)
-    except (regex.error, ValueError):
+    except (regex.error, ValueError) as exc:
         logger.exception(
-            "Error while processing regular expression %s",
+            "Error while processing regular expression %s: %s",
             textwrap.shorten(pattern, width=80, placeholder="…"),
+            exc,
         )
         return None
 

src/documents/search/_backend.py

@@ -1142,7 +1142,7 @@ def get_backend() -> TantivyBackend:
     Returns:
         Thread-safe singleton TantivyBackend instance
     """
-    global _backend, _backend_path  # noqa: PLW0603 - module-level singleton, no class to hold this state
+    global _backend, _backend_path
 
     current_path: Path = settings.INDEX_DIR
 
@@ -1173,7 +1173,7 @@ def reset_backend() -> None:
     Forces creation of a new backend instance on the next get_backend() call.
     Used for test isolation and when switching between different index directories.
     """
-    global _backend, _backend_path  # noqa: PLW0603 - module-level singleton, no class to hold this state
+    global _backend, _backend_path
 
     with _backend_lock:
         if _backend is not None:

src/documents/search/_query.py

@@ -240,7 +240,7 @@ def parse_user_query(
             DEFAULT_SEARCH_FIELDS,
             field_boosts=_FIELD_BOOSTS,
             # (prefix=True, distance=1, transposition_cost_one=True) — edit-distance fuzziness
-            fuzzy_fields=dict.fromkeys(DEFAULT_SEARCH_FIELDS, (True, 1, True)),
+            fuzzy_fields={f: (True, 1, True) for f in DEFAULT_SEARCH_FIELDS},
         )
         # 0.1 boost keeps fuzzy hits ranked below exact matches (intentional)
         clauses.append((tantivy.Occur.Should, tantivy.Query.boost_query(fuzzy, 0.1)))

src/documents/serialisers.py

@@ -433,7 +433,7 @@ class OwnedObjectSerializer(
             return set()
 
         ctype = ContentType.objects.get_for_model(first_obj)
-        object_pks = [obj.pk for obj in objects]
+        object_pks = list(obj.pk for obj in objects)
         pk_type = type(first_obj.pk)
 
         def get_pks_for_permission_type(model):
@@ -727,7 +727,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 self.instance.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise
+                raise e
             finally:
                 self.instance.tn_parent = original_parent
         else:
@@ -737,7 +737,7 @@ class TagSerializer(MatchingModelSerializer, OwnedObjectSerializer):
                 temp.clean()
             except ValidationError as e:
                 logger.debug("Tag parent validation failed: %s", e)
-                raise
+                raise e
 
         return super().validate(attrs)
 
@@ -1147,7 +1147,7 @@ class DocumentSerializer(
     def to_representation(self, instance):
         doc = super().to_representation(instance)
         if "content" in self.fields and hasattr(instance, "effective_content"):
-            doc["content"] = instance.effective_content or ""
+            doc["content"] = getattr(instance, "effective_content") or ""
         if self.truncate_content and "content" in self.fields:
             doc["content"] = doc.get("content")[0:550]
         return doc
@@ -1857,8 +1857,8 @@ class BulkEditSerializer(
         if isinstance(custom_fields, dict):
             try:
                 ids = [int(i[0]) for i in custom_fields.items()]
-            except Exception:
+            except Exception as e:
-                logger.exception("Error validating custom fields")
+                logger.exception(f"Error validating custom fields: {e}")
                 raise serializers.ValidationError(
                     f"{name} must be a list of integers or a dict of id:value pairs, see the log for details",
                 )
@@ -2056,12 +2056,13 @@ class BulkEditSerializer(
             for doc in docs:
                 if "-" in doc:
                     pages.append(
-                        list(
+                        [
-                            range(
+                            x
+                            for x in range(
                                 int(doc.split("-")[0]),
                                 int(doc.split("-")[1]) + 1,
-                            ),
+                            )
-                        ),
+                        ],
                     )
                 else:
                     pages.append([int(doc)])
@@ -2922,7 +2923,7 @@ class ShareLinkBundleSerializer(OwnedObjectSerializer):
         return share_link_bundle
 
     def get_document_count(self, obj: ShareLinkBundle) -> int:
-        return obj.document_total or obj.documents.count()
+        return getattr(obj, "document_total") or obj.documents.count()
 
 
 class BulkEditObjectsSerializer(SerializerWithPerms, SetPermissionsMixin):

src/documents/signals/handlers.py

@@ -636,7 +636,7 @@ def update_filename_and_move_files(
                 #  so this is not the end of the world.
                 # B: if moving the original file failed, nothing has changed
                 #  anyway.
-                logger.exception("Error reverting document changes")
+                pass
 
             # restore old values on the instance
             instance.filename = old_filename
@@ -1101,10 +1101,9 @@ def _extract_input_data(
                 if v is None or k.startswith("_"):
                     continue
                 if isinstance(v, datetime.date):
-                    override_dict[k] = v.isoformat()
+                    v = v.isoformat()
                 elif isinstance(v, Path):
-                    override_dict[k] = str(v)
+                    v = str(v)
-                else:
                 override_dict[k] = v
             if override_dict:
                 data["overrides"] = override_dict

src/documents/tasks.py

@@ -217,9 +217,9 @@ def consume_file(
                 overrides.filename or input_doc.original_file.name,
                 self.request.id,
             ) as status_mgr,
-            TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir_name,
+            TemporaryDirectory(dir=settings.SCRATCH_DIR) as tmp_dir,
         ):
-            tmp_dir = Path(tmp_dir_name)
+            tmp_dir = Path(tmp_dir)
             msg = None
             for plugin_class in plugins:
                 plugin_name = plugin_class.NAME
@@ -261,7 +261,7 @@ def consume_file(
                     )
 
                 except Exception as e:
-                    logger.exception(f"{plugin_name} failed")
+                    logger.exception(f"{plugin_name} failed: {e}")
                     status_mgr.send_progress(
                         ProgressStatusOptions.FAILED,
                         f"{e}",
@@ -495,8 +495,8 @@ def empty_trash(doc_ids=None) -> None:
                 content_type=ContentType.objects.get_for_model(Document),
                 object_id__in=deleted_document_ids,
             ).delete()
-    except Exception:  # pragma: no cover
+    except Exception as e:  # pragma: no cover
-        logger.exception("Error while emptying trash")
+        logger.exception(f"Error while emptying trash: {e}")
     finally:
         models.signals.post_delete.disconnect(
             cleanup_document_deletion,
@@ -832,8 +832,9 @@ def build_share_link_bundle(bundle_id: int) -> None:
         logger.info("Built share link bundle %s", bundle.pk)
     except Exception as exc:
         logger.exception(
-            "Failed to build share link bundle %s",
+            "Failed to build share link bundle %s: %s",
             bundle_id,
+            exc,
         )
         bundle.status = ShareLinkBundle.Status.FAILED
         bundle.last_error = {

src/documents/templating/filepath.py

@@ -78,10 +78,6 @@ class PlaceholderString(str):
     def __ne__(self, other) -> bool:
         return not self.__eq__(other)
 
-    def __hash__(self) -> int:
-        # Equal to both "-none-" and "none", so hash to a single canonical value
-        return hash("-none-")
-
 
 NO_VALUE_PLACEHOLDER = PlaceholderString("-none-")
 

src/documents/templating/workflows.py

@@ -138,9 +138,9 @@ def parse_w_workflow_placeholders(
 
         # We're good!
         return rendered_template
-    except UndefinedError:
+    except UndefinedError as e:
         # The undefined class logs this already for us
-        raise
+        raise e
     except TemplateSyntaxError as e:
         logger.warning(f"Template syntax error in title generation: {e}")
     except SecurityError as e:
@@ -150,5 +150,5 @@ def parse_w_workflow_placeholders(
         logger.warning(
             f"Invalid title format '{text}', workflow not applied: {e}",
         )
-        raise
+        raise e
     return None

src/documents/tests/date_parsing/test_date_parsing.py

@@ -296,7 +296,7 @@ class TestRegexDateParser:
 
             # simulate parse failure for malformed input
             if "99/99/9999" in date_string or "bad date" in date_string:
-                raise Exception("parse failed for malformed date")  # noqa: TRY002 - simulates a generic parser failure
+                raise Exception("parse failed for malformed date")
 
             return None
 

src/documents/tests/management/test_management_base_cmd.py

@@ -57,13 +57,13 @@ class MultiprocessCommand(PaperlessCommand):
 
     def handle(self, *args, **options):
         items = list(range(5))
-        results = list(
+        results = []
-            self.process_parallel(
+        for result in self.process_parallel(
             _double_value,
             items,
             description="Processing...",
-            ),
+        ):
-        )
+            results.append(result)
         successes = sum(1 for r in results if r.success)
         self.stdout.write(f"Successes: {successes}")
 

src/documents/tests/search/test_lock_backoff.py

@@ -66,7 +66,7 @@ class TestWriteBatchLockRetry:
         )
         mock_sleep = mocker.patch(
             "documents.search._backend.time.sleep",
-            side_effect=sleep_values.append,
+            side_effect=lambda s: sleep_values.append(s),
         )
 
         # Should not raise — 4th attempt succeeds
@@ -111,7 +111,7 @@ class TestWriteBatchLockRetry:
         sleep_values: list[float] = []
         mocker.patch(
             "documents.search._backend.time.sleep",
-            side_effect=sleep_values.append,
+            side_effect=lambda s: sleep_values.append(s),
         )
         for _ in range(50):
             sleep_values.clear()

src/documents/tests/test_api_bulk_edit.py

@@ -1003,8 +1003,8 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
             for correspondent in response.data[field]:
                 self.assertEqual(correspondent["document_count"], 0)
             self.assertCountEqual(
-                (c["id"] for c in response.data[field]),
+                map(lambda c: c["id"], response.data[field]),
-                (c["id"] for c in Entity.objects.values("id")),
+                map(lambda c: c["id"], Entity.objects.values("id")),
             )
 
     def test_api_selection_data(self) -> None:

src/documents/tests/test_api_profile.py

@@ -18,8 +18,8 @@ class MockOpenIDProvider:
 
     def get_brands(self):
         default_servers = [
-            {"id": "yahoo", "name": "Yahoo", "openid_url": "http://me.yahoo.com"},
+            dict(id="yahoo", name="Yahoo", openid_url="http://me.yahoo.com"),
-            {"id": "hyves", "name": "Hyves", "openid_url": "http://hyves.nl"},
+            dict(id="hyves", name="Hyves", openid_url="http://hyves.nl"),
         ]
         return default_servers
 

src/documents/tests/test_barcodes.py

@@ -205,12 +205,12 @@ class TestBarcode(
             - Barcode is detected on page 1 (zero indexed)
         """
 
-        for test_filename in [
+        for test_file in [
             "patch-code-t-middle-reverse.pdf",
             "patch-code-t-middle-distorted.pdf",
             "patch-code-t-middle-fuzzy.pdf",
         ]:
-            test_file = self.BARCODE_SAMPLE_DIR / test_filename
+            test_file = self.BARCODE_SAMPLE_DIR / test_file
 
             with self.get_reader(test_file) as reader:
                 reader.detect()

src/documents/tests/test_bulk_edit.py

@@ -777,7 +777,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         sig.set.return_value.apply_async.side_effect = Exception("boom")
         mock_consume_file.return_value = sig
 
-        with self.assertRaises(Exception):  # noqa: B017 - mock injects a bare Exception
+        with self.assertRaises(Exception):
             bulk_edit.merge(doc_ids, delete_originals=True)
 
         self.doc1.refresh_from_db()
@@ -1318,7 +1318,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         sig.apply_async.side_effect = Exception("boom")
         mock_chord.return_value = sig
 
-        with self.assertRaises(Exception):  # noqa: B017 - mock injects a bare Exception
+        with self.assertRaises(Exception):
             bulk_edit.edit_pdf(doc_ids, operations, delete_original=True)
 
         self.doc2.refresh_from_db()
@@ -1430,7 +1430,7 @@ class TestPDFActions(DirectoriesMixin, TestCase):
             {"page": 9999},  # invalid page, forces error during PDF load
         ]
         with self.assertLogs("paperless.bulk_edit", level="ERROR"):
-            with self.assertRaises(ValueError):
+            with self.assertRaises(Exception):
                 bulk_edit.edit_pdf(doc_ids, operations)
         mock_group.assert_not_called()
         mock_consume_file.assert_not_called()

src/documents/tests/test_classifier.py

@@ -783,7 +783,7 @@ class TestClassifier(DirectoriesMixin, TestCase):
 
         Path(settings.MODEL_FILE).touch()
         mock_load.side_effect = Exception()
-        with self.assertRaises(Exception):  # noqa: B017 - mock injects a bare Exception
+        with self.assertRaises(Exception):
             load_classifier(raise_exception=True)
 
 

src/documents/tests/test_consumer.py

@@ -137,7 +137,7 @@ class FaultyParser(_BaseNewStyleParser):
 
 class FaultyGenericExceptionParser(_BaseNewStyleParser):
     def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
-        raise Exception("Generic exception.")  # noqa: TRY002 - deliberately not a ParseError
+        raise Exception("Generic exception.")
 
 
 def fake_magic_from_file(file, *, mime=False):  # NOSONAR
@@ -1333,7 +1333,7 @@ class PreConsumeTestCase(DirectoriesMixin, GetConsumerMixin, TestCase):
             script_calls = [
                 call
                 for call in m.call_args_list
-                if call.args and call.args[0] and call.args[0][0] != "pdftotext"
+                if call.args and call.args[0] and call.args[0][0] not in ("pdftotext",)
             ]
             self.assertEqual(script_calls, [])
 

src/documents/tests/test_workflows.py

@@ -44,7 +44,6 @@ from documents import tasks
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentMetadataOverrides
 from documents.data_models import DocumentSource
-from documents.matching import UnsupportedWorkflowTriggerTypeError
 from documents.matching import document_matches_workflow
 from documents.matching import existing_document_matches_workflow
 from documents.matching import prefilter_documents_by_workflowtrigger
@@ -2852,13 +2851,7 @@ class TestWorkflows(
         doc = Document.objects.create(
             title="test",
         )
-        self.assertRaises(
+        self.assertRaises(Exception, document_matches_workflow, doc, w, 99)
-            UnsupportedWorkflowTriggerTypeError,
-            document_matches_workflow,
-            doc,
-            w,
-            99,
-        )
 
     def test_removal_action_document_updated_workflow(self) -> None:
         """

src/documents/validators.py

@@ -21,32 +21,28 @@ def uri_validator(value: str, allowed_schemes: set[str] | None = None) -> None:
         parts = urlparse(value)
         if not parts.scheme:
             raise ValidationError(
-                _("Unable to parse URI %(value)s, missing scheme"),
+                _(f"Unable to parse URI {value}, missing scheme"),
                 params={"value": value},
             )
         elif not parts.netloc and not parts.path:
             raise ValidationError(
-                _("Unable to parse URI %(value)s, missing net location or path"),
+                _(f"Unable to parse URI {value}, missing net location or path"),
                 params={"value": value},
             )
 
         if allowed_schemes and parts.scheme not in allowed_schemes:
             raise ValidationError(
                 _(
-                    "URI scheme '%(scheme)s' is not allowed. Allowed schemes: %(allowed_schemes)s",
+                    f"URI scheme '{parts.scheme}' is not allowed. Allowed schemes: {', '.join(allowed_schemes)}",
                 ),
-                params={
+                params={"value": value, "scheme": parts.scheme},
-                    "value": value,
-                    "scheme": parts.scheme,
-                    "allowed_schemes": ", ".join(allowed_schemes),
-                },
             )
 
     except ValidationError:
         raise
     except Exception as e:
         raise ValidationError(
-            _("Unable to parse URI %(value)s"),
+            _(f"Unable to parse URI {value}"),
             params={"value": value},
         ) from e
 

src/documents/views.py

@@ -1440,7 +1440,7 @@ class DocumentViewSet(
         try:
             lang = detect(doc.content)
         except Exception:
-            logger.debug("Unable to detect language for document %s", doc.pk)
+            pass
         meta["lang"] = lang
 
         return Response(meta)
@@ -1478,12 +1478,13 @@ class DocumentViewSet(
             with get_date_parser() as date_parser:
                 gen = date_parser.parse(doc.filename, doc.content)
                 dates = sorted(
-                    set(
+                    {
-                        itertools.islice(
+                        i
+                        for i in itertools.islice(
                             gen,
                             settings.NUMBER_OF_SUGGESTED_DATES,
-                        ),
+                        )
-                    ),
+                    },
                 )
 
         resp_data = {
@@ -1567,16 +1568,21 @@ class DocumentViewSet(
             except ValueError as exc:
                 logger.exception(
                     "Invalid AI configuration while generating suggestions for "
-                    "document %s",
+                    "document %s: %s",
                     doc.pk,
+                    exc,
+                    exc_info=True,
                 )
                 raise ValidationError(
                     {"ai": [_("Invalid AI configuration.")]},
                 ) from exc
-            except LLMTimeoutError:
+            except LLMTimeoutError as exc:
                 logger.exception(
-                    "AI backend timed out while generating suggestions for document %s",
+                    "AI backend timed out while generating suggestions for "
+                    "document %s: %s",
                     doc.pk,
+                    exc,
+                    exc_info=True,
                 )
                 return Response(
                     {"ai": [_("AI backend request timed out.")]},
@@ -2049,7 +2055,7 @@ class DocumentViewSet(
             doc_name, doc_data = serializer.validated_data.get("document")
             version_label = serializer.validated_data.get("version_label")
 
-            t = int(mktime(datetime.now().timetuple()))  # noqa: DTZ005 - mktime() requires a local time tuple
+            t = int(mktime(datetime.now().timetuple()))
 
             settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
 
@@ -3319,7 +3325,7 @@ class PostDocumentView(GenericAPIView[Any]):
         cf = serializer.validated_data.get("custom_fields")
         from_webui = serializer.validated_data.get("from_webui")
 
-        t = int(mktime(datetime.now().timetuple()))  # noqa: DTZ005 - mktime() requires a local time tuple
+        t = int(mktime(datetime.now().timetuple()))
 
         settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
 
@@ -4129,7 +4135,7 @@ class UiSettingsView(GenericAPIView[Any]):
             user_resp["last_name"] = user.last_name
 
         # strip <app_label>.
-        roles = (re.sub(r"^\w+.", "", perm) for perm in user.get_all_permissions())
+        roles = map(lambda perm: re.sub(r"^\w+.", "", perm), user.get_all_permissions())
         return Response(
             {
                 "user": user_resp,
@@ -5156,11 +5162,11 @@ class SystemStatusView(PassUserMixin):
                 f"{m.app}.{m.name}"
                 for m in MigrationRecorder.Migration.objects.all().order_by("id")
             ]
-        except Exception:  # pragma: no cover
+        except Exception as e:  # pragma: no cover
             applied_migrations = []
             db_status = "ERROR"
             logger.exception(
-                "System status detected a possible problem while connecting to the database",
+                f"System status detected a possible problem while connecting to the database: {e}",
             )
             db_error = "Error connecting to database, check logs for more detail."
 
@@ -5176,10 +5182,10 @@ class SystemStatusView(PassUserMixin):
             try:
                 client.ping()
                 redis_status = "OK"
-            except Exception:
+            except Exception as e:
                 redis_status = "ERROR"
                 logger.exception(
-                    "System status detected a possible problem while connecting to redis",
+                    f"System status detected a possible problem while connecting to redis: {e}",
                 )
                 redis_error = "Error connecting to redis, check logs for more detail."
 
@@ -5209,10 +5215,10 @@ class SystemStatusView(PassUserMixin):
                 else:
                     celery_active = "WARNING"
                     celery_error = "Celery worker responded unexpectedly."
-        except Exception:
+        except Exception as e:
             celery_active = "ERROR"
             logger.exception(
-                "System status detected a possible problem while connecting to celery",
+                f"System status detected a possible problem while connecting to celery: {e}",
             )
             celery_error = "Error connecting to celery, check logs for more detail."
 
@@ -5227,15 +5233,13 @@ class SystemStatusView(PassUserMixin):
             index_dir = settings.INDEX_DIR
             mtimes = [p.stat().st_mtime for p in index_dir.iterdir() if p.is_file()]
             index_last_modified = (
-                make_aware(datetime.fromtimestamp(max(mtimes)))  # noqa: DTZ006 - make_aware() requires a naive datetime
+                make_aware(datetime.fromtimestamp(max(mtimes))) if mtimes else None
-                if mtimes
-                else None
             )
-        except Exception:
+        except Exception as e:
             index_status = "ERROR"
             index_error = "Error opening index, check logs for more detail."
             logger.exception(
-                "System status detected a possible problem while opening the index",
+                f"System status detected a possible problem while opening the index: {e}",
             )
             index_last_modified = None
 

src/documents/workflows/actions.py

@@ -66,7 +66,7 @@ def build_workflow_action_context(
         else None
     )
 
-    filename = document.original_file or ""
+    filename = document.original_file if document.original_file else ""
     return {
         "title": overrides.title
         if overrides and overrides.title
@@ -179,9 +179,9 @@ def execute_email_action(
             f"Sent {n_messages} notification email(s) to {action.email.to}",
             extra={"group": logging_group},
         )
-    except Exception:
+    except Exception as e:
         logger.exception(
-            "Error occurred sending notification email",
+            f"Error occurred sending notification email: {e}",
             extra={"group": logging_group},
         )
 
@@ -265,9 +265,9 @@ def execute_webhook_action(
             f"Webhook to {action.webhook.url} queued",
             extra={"group": logging_group},
         )
-    except Exception:
+    except Exception as e:
         logger.exception(
-            "Error occurred sending webhook",
+            f"Error occurred sending webhook: {e}",
             extra={"group": logging_group},
         )
 

src/documents/workflows/ai.py

@@ -47,7 +47,7 @@ def resolve_date(dates: list[str]) -> date | None:
     """
     for value in dates:
         try:
-            return datetime.strptime(value, "%Y-%m-%d").date()  # noqa: DTZ007 - only the calendar date is used, time/tz is discarded
+            return datetime.strptime(value, "%Y-%m-%d").date()
         except (TypeError, ValueError):
             logger.debug("Ignoring unparsable suggested date %s", value)
     return None

src/documents/workflows/webhooks.py

@@ -70,6 +70,6 @@ def send_webhook(
         logger.error(
             f"Failed attempt sending webhook to {url}: {e}",
         )
-        raise
+        raise e
     finally:
         transport.close()

src/paperless/checks.py

@@ -241,7 +241,7 @@ def check_v3_minimum_upgrade_version(
         return []
 
     logger = logging.getLogger(__name__)
-    last_applied = max(applied) if applied else "(none)"
+    last_applied = sorted(applied)[-1] if applied else "(none)"
     logger.error(
         "V3 upgrade check failed: last applied documents migration is %r. "
         "Expected '1075_workflowaction_order' (v2.20.15). "
@@ -341,7 +341,6 @@ def get_tesseract_langs():
     proc = subprocess.run(
         [shutil.which("tesseract"), "--list-langs"],
         capture_output=True,
-        check=False,
     )
 
     # Decode bytes to string, split on newlines, trim out the header

src/paperless/parsers/registry.py

@@ -84,7 +84,7 @@ def get_parser_registry() -> ParserRegistry:
     ParserRegistry
         The shared registry singleton.
     """
-    global _registry, _discovery_complete  # noqa: PLW0603 - module-level singleton, no class to hold this state
+    global _registry, _discovery_complete
 
     with _lock:
         if _registry is None:
@@ -113,7 +113,7 @@ def init_builtin_parsers() -> None:
     -------
     None
     """
-    global _registry  # noqa: PLW0603 - module-level singleton, no class to hold this state
+    global _registry
 
     with _lock:
         if _registry is None:
@@ -137,7 +137,7 @@ def reset_parser_registry() -> None:
     -------
     None
     """
-    global _registry, _discovery_complete  # noqa: PLW0603 - module-level singleton, no class to hold this state
+    global _registry, _discovery_complete
 
     _registry = None
     _discovery_complete = False

src/paperless/parsers/remote.py

@@ -76,7 +76,7 @@ class RemoteEngineConfig:
     def engine_is_valid(self) -> bool:
         """Return True when the engine is known and fully configured."""
         return (
-            self.engine == "azureai"
+            self.engine in ("azureai",)
             and self.api_key is not None
             and not (self.engine == "azureai" and self.endpoint is None)
         )
@@ -467,7 +467,7 @@ class RemoteDocumentParser:
             return result.content
 
         except Exception as e:
-            logger.exception("Azure AI Vision parsing failed")
+            logger.exception("Azure AI Vision parsing failed: %s", e)
             raise ParseError(f"Azure AI Vision parsing failed: {e}") from e
 
         finally:

src/paperless/parsers/utils.py

@@ -306,9 +306,8 @@ def extract_pdf_metadata(
 
     for key, value in meta.items():
         if isinstance(value, list):
-            str_value = " ".join(str(e) for e in value)
+            value = " ".join(str(e) for e in value)
-        else:
+        value = str(value)
-            str_value = str(value)
 
         try:
             m = namespace_pattern.match(key)
@@ -330,7 +329,7 @@ def extract_pdf_metadata(
                     namespace=namespace,
                     prefix=meta.REVERSE_NS[namespace],
                     key=key_value,
-                    value=str_value,
+                    value=value,
                 ),
             )
         except Exception as e:

src/paperless/settings/__init__.py

@@ -294,7 +294,7 @@ if _CHANNELS_BACKEND.startswith("channels_redis."):
 ###############################################################################
 
 EMAIL_HOST: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST", "localhost")
-EMAIL_PORT: Final[int] = get_int_from_env("PAPERLESS_EMAIL_PORT", 25)
+EMAIL_PORT: Final[int] = int(os.getenv("PAPERLESS_EMAIL_PORT", 25))
 EMAIL_HOST_USER: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_USER", "")
 EMAIL_HOST_PASSWORD: Final[str] = os.getenv("PAPERLESS_EMAIL_HOST_PASSWORD", "")
 DEFAULT_FROM_EMAIL: Final[str] = os.getenv("PAPERLESS_EMAIL_FROM", EMAIL_HOST_USER)
@@ -381,9 +381,8 @@ ACCOUNT_SESSION_REMEMBER = get_bool_from_env(
     "True",
 )
 SESSION_EXPIRE_AT_BROWSER_CLOSE = not ACCOUNT_SESSION_REMEMBER
-SESSION_COOKIE_AGE = get_int_from_env(
+SESSION_COOKIE_AGE = int(
-    "PAPERLESS_SESSION_COOKIE_AGE",
+    os.getenv("PAPERLESS_SESSION_COOKIE_AGE", 60 * 60 * 24 * 7 * 3),
-    60 * 60 * 24 * 7 * 3,
 )
 # https://docs.djangoproject.com/en/5.1/ref/settings/#std-setting-SESSION_ENGINE
 SESSION_ENGINE = "django.contrib.sessions.backends.cached_db"
@@ -396,6 +395,7 @@ if AUTO_LOGIN_USERNAME:
 
 
 def _parse_remote_user_settings() -> str:
+    global MIDDLEWARE, AUTHENTICATION_BACKENDS, REST_FRAMEWORK
     enable = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER")
     enable_api = get_bool_from_env("PAPERLESS_ENABLE_HTTP_REMOTE_USER_API")
     if enable or enable_api:
@@ -454,6 +454,7 @@ if ALLOWED_HOSTS != ["*"]:
 
 
 def _parse_paperless_url():
+    global CSRF_TRUSTED_ORIGINS, CORS_ALLOWED_ORIGINS, ALLOWED_HOSTS
     url = os.getenv("PAPERLESS_URL")
     if url:
         CSRF_TRUSTED_ORIGINS.append(url)
@@ -613,8 +614,8 @@ USE_TZ = True
 
 LOGGING_DIR.mkdir(parents=True, exist_ok=True)
 
-LOGROTATE_MAX_SIZE = get_int_from_env("PAPERLESS_LOGROTATE_MAX_SIZE", 1024 * 1024)
+LOGROTATE_MAX_SIZE = os.getenv("PAPERLESS_LOGROTATE_MAX_SIZE", 1024 * 1024)
-LOGROTATE_MAX_BACKUPS = get_int_from_env("PAPERLESS_LOGROTATE_MAX_BACKUPS", 20)
+LOGROTATE_MAX_BACKUPS = os.getenv("PAPERLESS_LOGROTATE_MAX_BACKUPS", 20)
 
 LOGGING = {
     "version": 1,
@@ -810,15 +811,9 @@ IGNORABLE_FILES: Final[list[str]] = [
     "Thumbs.db",
 ]
 
-CONSUMER_POLLING_INTERVAL = get_float_from_env(
+CONSUMER_POLLING_INTERVAL = float(os.getenv("PAPERLESS_CONSUMER_POLLING_INTERVAL", 0))
-    "PAPERLESS_CONSUMER_POLLING_INTERVAL",
-    0.0,
-)
 
-CONSUMER_STABILITY_DELAY = get_float_from_env(
+CONSUMER_STABILITY_DELAY = float(os.getenv("PAPERLESS_CONSUMER_STABILITY_DELAY", 5))
-    "PAPERLESS_CONSUMER_STABILITY_DELAY",
-    5.0,
-)
 
 CONSUMER_DELETE_DUPLICATES = get_bool_from_env("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
 

src/paperless/settings/parsers.py

@@ -111,7 +111,7 @@ def parse_dict_from_str(
             return False
 
     settings: dict[str, Any] = copy.deepcopy(defaults) if defaults else {}
-    _type_map = type_map or {}
+    _type_map = type_map if type_map else {}
 
     if not env_str:
         return settings

src/paperless/tests/settings/test_db_cache.py

@@ -114,17 +114,17 @@ def test_cache_hit_when_enabled() -> None:
     assert settings.CACHALOT_TIMEOUT == 1
 
     # Read a table to populate the cache
-    list(Tag.objects.values_list("id", flat=True))
+    list(list(Tag.objects.values_list("id", flat=True)))
 
     # Invalidate the cache then read the database, there should be DB hit
     invalidate_db_cache()
     with CaptureQueriesContext(connection) as ctx:
-        list(Tag.objects.values_list("id", flat=True))
+        list(list(Tag.objects.values_list("id", flat=True)))
     assert len(ctx)
 
     # Doing the same request again should hit the cache, not the DB
     with CaptureQueriesContext(connection) as ctx:
-        list(Tag.objects.values_list("id", flat=True))
+        list(list(Tag.objects.values_list("id", flat=True)))
     assert not len(ctx)
 
     # Wait the end of TTL
@@ -133,7 +133,7 @@ def test_cache_hit_when_enabled() -> None:
 
     # Read the DB again. The DB should be hit because the cache has expired
     with CaptureQueriesContext(connection) as ctx:
-        list(Tag.objects.values_list("id", flat=True))
+        list(list(Tag.objects.values_list("id", flat=True)))
     assert len(ctx)
 
     # Invalidate the cache at the end of test
@@ -149,7 +149,7 @@ def test_cache_is_disabled_by_default() -> None:
     # Read the table multiple times: the DB should always be hit without cache
     for _ in range(3):
         with CaptureQueriesContext(connection) as ctx:
-            list(Tag.objects.values_list("id", flat=True))
+            list(list(Tag.objects.values_list("id", flat=True)))
         assert len(ctx)
 
     # Invalidate the cache at the end of test

src/paperless/tests/test_utils.py

@@ -59,7 +59,7 @@ def test_ocr_to_dateparser_languages_exception(
             raise RuntimeError("Simulated error")
 
     with caplog.at_level(logging.WARNING):
-        monkeypatch.setattr(utils, "LocaleDataLoader", DummyLoader)
+        monkeypatch.setattr(utils, "LocaleDataLoader", lambda: DummyLoader())
         result = utils.ocr_to_dateparser_languages("eng+fra")
         assert result == []
         assert (

src/paperless_ai/chat.py

@@ -103,8 +103,8 @@ def stream_chat_with_documents(
             documents,
             output_language=output_language,
         )
-    except Exception:
+    except Exception as e:
-        logger.exception("Failed to stream document chat response")
+        logger.exception("Failed to stream document chat response: %s", e)
         yield CHAT_ERROR_MESSAGE
 
 

src/paperless_ai/tests/test_ai_classifier.py

@@ -167,7 +167,7 @@ def test_get_ai_document_classification_failure(mock_run_llm_query, mock_documen
     """
     mock_run_llm_query.side_effect = Exception("LLM query failed")
 
-    with pytest.raises(Exception):  # noqa: B017 - mock injects a bare Exception
+    with pytest.raises(Exception):
         get_ai_document_classification(mock_document)
 
 

src/paperless_ai/tests/test_lazy_imports.py

@@ -21,6 +21,5 @@ class TestLazyAiImports:
             capture_output=True,
             text=True,
             cwd=_SRC_DIR,
-            check=False,
         )
         assert result.returncode == 0, result.stdout + result.stderr

src/paperless_mail/mail.py

@@ -7,6 +7,7 @@ import ssl
 import tempfile
 import traceback
 import unicodedata
+from datetime import date
 from datetime import timedelta
 from fnmatch import fnmatch
 from pathlib import Path
@@ -405,7 +406,7 @@ def make_criterias(rule: MailRule, *, supports_gmail_labels: bool):
     Returns criteria to be applied to MailBox.fetch for the given rule.
     """
 
-    maximum_age = timezone.localdate() - timedelta(days=rule.maximum_age)
+    maximum_age = date.today() - timedelta(days=rule.maximum_age)
     criterias = {}
     if rule.maximum_age > 0:
         criterias["date_gte"] = maximum_age
@@ -722,9 +723,9 @@ class MailAccountHandler(LoggingMixin):
                                 f"Rule {rule}: Stopping processing rules due to stop_processing flag",
                             )
                             break
-                    except Exception:
+                    except Exception as e:
                         self.log.exception(
-                            f"Rule {rule}: Error while processing rule",
+                            f"Rule {rule}: Error while processing rule: {e}",
                         )
         except MailError:
             raise
@@ -873,9 +874,9 @@ class MailAccountHandler(LoggingMixin):
 
                 total_processed_files += processed_files
                 mails_processed += 1
-            except Exception:
+            except Exception as e:
                 self.log.exception(
-                    f"Rule {rule}: Error while processing mail {message.uid}",
+                    f"Rule {rule}: Error while processing mail {message.uid}: {e}",
                 )
 
         self.log.debug(f"Rule {rule}: Processed {mails_processed} matching mail(s)")

src/paperless_mail/preprocessor.py

@@ -11,10 +11,6 @@ from imap_tools import MailMessage
 from documents.loggers import LoggingMixin
 
 
-class MailDecryptionError(Exception):
-    pass
-
-
 class MailMessagePreprocessor(abc.ABC):
     """
     Defines the interface for preprocessors that alter messages before they are handled in MailAccountHandler
@@ -73,7 +69,7 @@ class MailMessageDecryptor(MailMessagePreprocessor, LoggingMixin):
                 f"Message decryption failed with status message "
                 f"{decrypted_raw_message.status}",
             )
-            raise MailDecryptionError(
+            raise Exception(
                 f"Decryption failed: {decrypted_raw_message.status}, {decrypted_raw_message.stderr}",
             )
         self.log.debug("Message decrypted successfully.")

src/paperless_mail/tests/factories.py

@@ -50,7 +50,7 @@ class ProcessedMailFactory(DjangoModelFactory[ProcessedMail]):
 
     rule = factory.SubFactory(MailRuleFactory)
     folder = "INBOX"
-    uid = factory.Sequence(str)
+    uid = factory.Sequence(lambda n: str(n))
     subject = factory.Faker("sentence", nb_words=4)
     received = factory.LazyFunction(timezone.now)
     processed = factory.LazyFunction(timezone.now)

src/paperless_mail/tests/test_mail.py

@@ -214,7 +214,7 @@ class BogusMailBox(AbstractContextManager):
             )
             self.messages = list(filter(lambda m: m.uid not in uid_list, self.messages))
         else:
-            raise Exception  # noqa: TRY002 - test double simulating a generic mailbox failure
+            raise Exception
 
 
 def fake_magic_from_buffer(buffer, *, mime=False):

src/paperless_mail/tests/test_preprocessor.py

@@ -14,7 +14,6 @@ from imap_tools import MailMessage
 
 from paperless_mail.mail import MailAccountHandler
 from paperless_mail.models import MailRule
-from paperless_mail.preprocessor import MailDecryptionError
 from paperless_mail.preprocessor import MailMessageDecryptor
 from paperless_mail.tests.factories import MailAccountFactory
 from paperless_mail.tests.test_mail import TestMail
@@ -83,9 +82,7 @@ class MessageEncryptor:
             armor=True,
         )
         if not encrypted_data.ok:
-            raise Exception(  # noqa: TRY002 - test fixture setup, not production code
+            raise Exception(f"Encryption failed: {encrypted_data.stderr}")
-                f"Encryption failed: {encrypted_data.stderr}",
-            )
         encrypted_email_content = encrypted_data.data
 
         new_email = MIMEMultipart("encrypted", protocol="application/pgp-encrypted")
@@ -187,11 +184,7 @@ class TestMailMessageGpgDecryptor(TestMail):
                 EMAIL_GNUPG_HOME=empty_gpg_home,
             ):
                 message_decryptor = MailMessageDecryptor()
-                self.assertRaises(
+                self.assertRaises(Exception, message_decryptor.run, encrypted_message)
-                    MailDecryptionError,
-                    message_decryptor.run,
-                    encrypted_message,
-                )
         finally:
             # Clean up the temporary GPG home used only by this test
             try:

src/paperless_mail/views.py

@@ -1,3 +1,4 @@
+import datetime
 import logging
 from datetime import timedelta
 from http import HTTPStatus
@@ -86,7 +87,7 @@ class MailAccountViewSet(PassUserMixin, ModelViewSet[MailAccount]):
     @action(methods=["post"], detail=False)
     def test(self, request):
         logger = logging.getLogger("paperless_mail")
-        request.data["name"] = timezone.now().isoformat()
+        request.data["name"] = datetime.datetime.now().isoformat()
         serializer = self.get_serializer(data=request.data)
         serializer.is_valid(raise_exception=True)
         existing_account = None