Account for the Python 3.14 changes

.github/workflows/ci-backend.yml

@@ -31,7 +31,7 @@ jobs:
     runs-on: ubuntu-24.04
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.11', '3.12', '3.13', '3.14']
       fail-fast: false
     steps:
       - name: Checkout

pyproject.toml

@@ -3,10 +3,9 @@ name = "paperless-ngx"
 version = "2.20.8"
 description = "A community-supported supercharged document management system: scan, index and archive all your physical documents"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 classifiers = [
   "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
@@ -37,7 +36,6 @@ dependencies = [
   "django-filter~=25.1",
   "django-guardian~=3.3.0",
   "django-multiselectfield~=1.0.1",
-  "django-rich~=2.2.0",
   "django-soft-delete~=1.0.18",
   "django-treenode>=0.23.2",
   "djangorestframework~=3.16",
@@ -77,6 +75,7 @@ dependencies = [
   "setproctitle~=1.3.4",
   "tika-client~=0.10.0",
   "torch~=2.10.0",
+  "tqdm~=4.67.1",
   "watchfiles>=1.1.1",
   "whitenoise~=6.11",
   "whoosh-reloaded>=2.7.5",
@@ -149,6 +148,7 @@ typing = [
   "types-pytz",
   "types-redis",
   "types-setuptools",
+  "types-tqdm",
 ]
 
 [tool.uv]
@@ -176,7 +176,7 @@ torch = [
 ]
 
 [tool.ruff]
-target-version = "py310"
+target-version = "py311"
 line-length = 88
 src = [
   "src",
@@ -303,7 +303,6 @@ markers = [
   "tika: Tests requiring Tika service",
   "greenmail: Tests requiring Greenmail service",
   "date_parsing: Tests which cover date parsing from content or filename",
-  "management: Tests which cover management commands/functionality",
 ]
 
 [tool.pytest_env]

src/documents/conditionals.py

@@ -1,5 +1,5 @@
+from datetime import UTC
 from datetime import datetime
-from datetime import timezone
 from typing import Any
 
 from django.conf import settings
@@ -139,7 +139,7 @@ def thumbnail_last_modified(request: Any, pk: int) -> datetime | None:
         # No cache, get the timestamp and cache the datetime
         last_modified = datetime.fromtimestamp(
             doc.thumbnail_path.stat().st_mtime,
-            tz=timezone.utc,
+            tz=UTC,
         )
         cache.set(doc_key, last_modified, CACHE_50_MINUTES)
         return last_modified

src/documents/consumer.py

@@ -2,7 +2,7 @@ import datetime
 import hashlib
 import os
 import tempfile
-from enum import Enum
+from enum import StrEnum
 from pathlib import Path
 from typing import TYPE_CHECKING
 from typing import Final
@@ -80,7 +80,7 @@ class ConsumerError(Exception):
     pass
 
 
-class ConsumerStatusShortMessage(str, Enum):
+class ConsumerStatusShortMessage(StrEnum):
     DOCUMENT_ALREADY_EXISTS = "document_already_exists"
     DOCUMENT_ALREADY_EXISTS_IN_TRASH = "document_already_exists_in_trash"
     ASN_ALREADY_EXISTS = "asn_already_exists"

src/documents/index.py

@@ -5,10 +5,10 @@ import math
 import re
 from collections import Counter
 from contextlib import contextmanager
+from datetime import UTC
 from datetime import datetime
 from datetime import time
 from datetime import timedelta
-from datetime import timezone
 from shutil import rmtree
 from time import sleep
 from typing import TYPE_CHECKING
@@ -437,7 +437,7 @@ class ManualResults:
 class LocalDateParser(English):
     def reverse_timezone_offset(self, d):
         return (d.replace(tzinfo=django_timezone.get_current_timezone())).astimezone(
-            timezone.utc,
+            UTC,
         )
 
     def date_from(self, *args, **kwargs):
@@ -641,8 +641,8 @@ def rewrite_natural_date_keywords(query_string: str) -> str:
                 end = datetime(local_now.year - 1, 12, 31, 23, 59, 59, tzinfo=tz)
 
         # Convert to UTC and format
-        start_str = start.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
-        end_str = end.astimezone(timezone.utc).strftime("%Y%m%d%H%M%S")
+        start_str = start.astimezone(UTC).strftime("%Y%m%d%H%M%S")
+        end_str = end.astimezone(UTC).strftime("%Y%m%d%H%M%S")
         return f"{field}:[{start_str} TO {end_str}]"
 
     return re.sub(pattern, repl, query_string, flags=re.IGNORECASE)

src/documents/management/commands/base.py

@@ -1,320 +0,0 @@
-"""
-Base command class for Paperless-ngx management commands.
-
-Provides automatic progress bar and multiprocessing support with minimal boilerplate.
-"""
-
-from __future__ import annotations
-
-import os
-from collections.abc import Iterable
-from collections.abc import Sized
-from concurrent.futures import ProcessPoolExecutor
-from concurrent.futures import as_completed
-from dataclasses import dataclass
-from typing import TYPE_CHECKING
-from typing import Any
-from typing import ClassVar
-from typing import Generic
-from typing import TypeVar
-
-from django import db
-from django.core.management import CommandError
-from django.db.models import QuerySet
-from django_rich.management import RichCommand
-from rich.console import Console
-from rich.progress import BarColumn
-from rich.progress import MofNCompleteColumn
-from rich.progress import Progress
-from rich.progress import SpinnerColumn
-from rich.progress import TextColumn
-from rich.progress import TimeElapsedColumn
-from rich.progress import TimeRemainingColumn
-
-if TYPE_CHECKING:
-    from collections.abc import Callable
-    from collections.abc import Generator
-    from collections.abc import Iterable
-    from collections.abc import Sequence
-
-    from django.core.management import CommandParser
-
-T = TypeVar("T")
-R = TypeVar("R")
-
-
-@dataclass(frozen=True, slots=True)
-class ProcessResult(Generic[T, R]):
-    """
-    Result of processing a single item in parallel.
-
-    Attributes:
-        item: The input item that was processed.
-        result: The return value from the processing function, or None if an error occurred.
-        error: The exception if processing failed, or None on success.
-    """
-
-    item: T
-    result: R | None
-    error: BaseException | None
-
-    @property
-    def success(self) -> bool:
-        """Return True if the item was processed successfully."""
-        return self.error is None
-
-
-class PaperlessCommand(RichCommand):
-    """
-    Base command class with automatic progress bar and multiprocessing support.
-
-    Features are opt-in via class attributes:
-        supports_progress_bar: Adds --no-progress-bar argument (default: True)
-        supports_multiprocessing: Adds --processes argument (default: False)
-
-    Example usage:
-
-        class Command(PaperlessCommand):
-            help = "Process all documents"
-
-            def handle(self, *args, **options):
-                documents = Document.objects.all()
-                for doc in self.track(documents, description="Processing..."):
-                    process_document(doc)
-
-        class Command(PaperlessCommand):
-            help = "Regenerate thumbnails"
-            supports_multiprocessing = True
-
-            def handle(self, *args, **options):
-                ids = list(Document.objects.values_list("id", flat=True))
-                for result in self.process_parallel(process_doc, ids):
-                    if result.error:
-                        self.console.print(f"[red]Failed: {result.error}[/red]")
-    """
-
-    supports_progress_bar: ClassVar[bool] = True
-    supports_multiprocessing: ClassVar[bool] = False
-
-    # Instance attributes set by execute() before handle() runs
-    no_progress_bar: bool
-    process_count: int
-
-    def add_arguments(self, parser: CommandParser) -> None:
-        """Add arguments based on supported features."""
-        super().add_arguments(parser)
-
-        if self.supports_progress_bar:
-            parser.add_argument(
-                "--no-progress-bar",
-                default=False,
-                action="store_true",
-                help="Disable the progress bar",
-            )
-
-        if self.supports_multiprocessing:
-            default_processes = max(1, (os.cpu_count() or 1) // 4)
-            parser.add_argument(
-                "--processes",
-                default=default_processes,
-                type=int,
-                help=f"Number of processes to use (default: {default_processes})",
-            )
-
-    def execute(self, *args: Any, **options: Any) -> str | None:
-        """
-        Set up instance state before handle() is called.
-
-        This is called by Django's command infrastructure after argument parsing
-        but before handle(). We use it to set instance attributes from options.
-        """
-        # Set progress bar state
-        if self.supports_progress_bar:
-            self.no_progress_bar = options.get("no_progress_bar", False)
-        else:
-            self.no_progress_bar = True
-
-        # Set multiprocessing state
-        if self.supports_multiprocessing:
-            self.process_count = options.get("processes", 1)
-            if self.process_count < 1:
-                raise CommandError("--processes must be at least 1")
-        else:
-            self.process_count = 1
-
-        return super().execute(*args, **options)
-
-    def _create_progress(self, description: str) -> Progress:
-        """
-        Create a configured Progress instance.
-
-        Progress output is directed to stderr to match the convention that
-        progress bars are transient UI feedback, not command output. This
-        mirrors tqdm's default behavior and prevents progress bar rendering
-        from interfering with stdout-based assertions in tests or piped
-        command output.
-
-        Args:
-            description: Text to display alongside the progress bar.
-
-        Returns:
-            A Progress instance configured with appropriate columns.
-        """
-        return Progress(
-            SpinnerColumn(),
-            TextColumn("[progress.description]{task.description}"),
-            BarColumn(),
-            MofNCompleteColumn(),
-            TimeElapsedColumn(),
-            TimeRemainingColumn(),
-            console=Console(stderr=True),
-            transient=False,
-        )
-
-    def _get_iterable_length(self, iterable: Iterable[object]) -> int | None:
-        """
-        Attempt to determine the length of an iterable without consuming it.
-
-        Tries .count() first (for Django querysets - executes SELECT COUNT(*)),
-        then falls back to len() for sequences.
-
-        Args:
-            iterable: The iterable to measure.
-
-        Returns:
-            The length if determinable, None otherwise.
-        """
-        if isinstance(iterable, QuerySet):
-            return iterable.count()
-
-        if isinstance(iterable, Sized):
-            return len(iterable)
-
-        return None
-
-    def track(
-        self,
-        iterable: Iterable[T],
-        *,
-        description: str = "Processing...",
-        total: int | None = None,
-    ) -> Generator[T, None, None]:
-        """
-        Iterate over items with an optional progress bar.
-
-        Respects --no-progress-bar flag. When disabled, simply yields items
-        without any progress display.
-
-        Args:
-            iterable: The items to iterate over.
-            description: Text to display alongside the progress bar.
-            total: Total number of items. If None, attempts to determine
-                automatically via .count() (for querysets) or len().
-
-        Yields:
-            Items from the iterable.
-
-        Example:
-            for doc in self.track(documents, description="Renaming..."):
-                process(doc)
-        """
-        if self.no_progress_bar:
-            yield from iterable
-            return
-
-        # Attempt to determine total if not provided
-        if total is None:
-            total = self._get_iterable_length(iterable)
-
-        with self._create_progress(description) as progress:
-            task_id = progress.add_task(description, total=total)
-            for item in iterable:
-                yield item
-                progress.advance(task_id)
-
-    def process_parallel(
-        self,
-        fn: Callable[[T], R],
-        items: Sequence[T],
-        *,
-        description: str = "Processing...",
-    ) -> Generator[ProcessResult[T, R], None, None]:
-        """
-        Process items in parallel with progress tracking.
-
-        When --processes=1, runs sequentially in the main process without
-        spawning subprocesses. This is critical for testing, as multiprocessing
-        breaks fixtures, mocks, and database transactions.
-
-        When --processes > 1, uses ProcessPoolExecutor and automatically closes
-        database connections before spawning workers (required for PostgreSQL).
-
-        Args:
-            fn: Function to apply to each item. Must be picklable for parallel
-                execution (i.e., defined at module level, not a lambda or closure).
-            items: Sequence of items to process.
-            description: Text to display alongside the progress bar.
-
-        Yields:
-            ProcessResult for each item, containing the item, result, and any error.
-
-        Example:
-            def regenerate_thumbnail(doc_id: int) -> Path:
-                ...
-
-            for result in self.process_parallel(regenerate_thumbnail, doc_ids):
-                if result.error:
-                    self.console.print(f"[red]Failed {result.item}[/red]")
-        """
-        total = len(items)
-
-        if self.process_count == 1:
-            # Sequential execution in main process - critical for testing
-            yield from self._process_sequential(fn, items, description, total)
-        else:
-            # Parallel execution with ProcessPoolExecutor
-            yield from self._process_parallel(fn, items, description, total)
-
-    def _process_sequential(
-        self,
-        fn: Callable[[T], R],
-        items: Sequence[T],
-        description: str,
-        total: int,
-    ) -> Generator[ProcessResult[T, R], None, None]:
-        """Process items sequentially in the main process."""
-        for item in self.track(items, description=description, total=total):
-            try:
-                result = fn(item)
-                yield ProcessResult(item=item, result=result, error=None)
-            except Exception as e:
-                yield ProcessResult(item=item, result=None, error=e)
-
-    def _process_parallel(
-        self,
-        fn: Callable[[T], R],
-        items: Sequence[T],
-        description: str,
-        total: int,
-    ) -> Generator[ProcessResult[T, R], None, None]:
-        """Process items in parallel using ProcessPoolExecutor."""
-        # Close database connections before forking - required for PostgreSQL
-        db.connections.close_all()
-
-        with self._create_progress(description) as progress:
-            task_id = progress.add_task(description, total=total)
-
-            with ProcessPoolExecutor(max_workers=self.process_count) as executor:
-                # Submit all tasks and map futures back to items
-                future_to_item = {executor.submit(fn, item): item for item in items}
-
-                # Yield results as they complete
-                for future in as_completed(future_to_item):
-                    item = future_to_item[future]
-                    try:
-                        result = future.result()
-                        yield ProcessResult(item=item, result=result, error=None)
-                    except Exception as e:
-                        yield ProcessResult(item=item, result=None, error=e)
-                    finally:
-                        progress.advance(task_id)

src/documents/management/commands/document_archiver.py

@@ -1,15 +1,20 @@
 import logging
+import multiprocessing
 
+import tqdm
+from django import db
 from django.conf import settings
+from django.core.management.base import BaseCommand
 
-from documents.management.commands.base import PaperlessCommand
+from documents.management.commands.mixins import MultiProcessMixin
+from documents.management.commands.mixins import ProgressBarMixin
 from documents.models import Document
 from documents.tasks import update_document_content_maybe_archive_file
 
 logger = logging.getLogger("paperless.management.archiver")
 
 
-class Command(PaperlessCommand):
+class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
     help = (
         "Using the current classification model, assigns correspondents, tags "
         "and document types to all documents, effectively allowing you to "
@@ -17,10 +22,7 @@ class Command(PaperlessCommand):
         "modified) after their initial import."
     )
 
-    supports_multiprocessing = True
-
     def add_arguments(self, parser):
-        super().add_arguments(parser)
         parser.add_argument(
             "-f",
             "--overwrite",
@@ -42,8 +44,13 @@ class Command(PaperlessCommand):
                 "run on this specific document."
             ),
         )
+        self.add_argument_progress_bar_mixin(parser)
+        self.add_argument_processes_mixin(parser)
 
     def handle(self, *args, **options):
+        self.handle_processes_mixin(**options)
+        self.handle_progress_bar_mixin(**options)
+
         settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
 
         overwrite = options["overwrite"]
@@ -53,21 +60,35 @@ class Command(PaperlessCommand):
         else:
             documents = Document.objects.all()
 
-        document_ids = [
-            doc.id for doc in documents if overwrite or not doc.has_archive_version
-        ]
+        document_ids = list(
+            map(
+                lambda doc: doc.id,
+                filter(lambda d: overwrite or not d.has_archive_version, documents),
+            ),
+        )
+
+        # Note to future self: this prevents django from reusing database
+        # connections between processes, which is bad and does not work
+        # with postgres.
+        db.connections.close_all()
 
         try:
             logging.getLogger().handlers[0].level = logging.ERROR
 
-            for result in self.process_parallel(
-                update_document_content_maybe_archive_file,
-                document_ids,
-                description="Archiving...",
-            ):
-                if result.error:
-                    self.console.print(
-                        f"[red]Failed document {result.item}: {result.error}[/red]",
+            if self.process_count == 1:
+                for doc_id in document_ids:
+                    update_document_content_maybe_archive_file(doc_id)
+            else:  # pragma: no cover
+                with multiprocessing.Pool(self.process_count) as pool:
+                    list(
+                        tqdm.tqdm(
+                            pool.imap_unordered(
+                                update_document_content_maybe_archive_file,
+                                document_ids,
+                            ),
+                            total=len(document_ids),
+                            disable=self.no_progress_bar,
+                        ),
                     )
-        except KeyboardInterrupt:  # pragma: no cover
-            self.console.print("[yellow]Aborting...[/yellow]")
+        except KeyboardInterrupt:
+            self.stdout.write(self.style.NOTICE("Aborting..."))

src/documents/management/commands/document_fuzzy_match.py

@@ -1,20 +1,24 @@
 import dataclasses
+import multiprocessing
 from typing import Final
 
 import rapidfuzz
+import tqdm
+from django.core.management import BaseCommand
 from django.core.management import CommandError
 
-from documents.management.commands.base import PaperlessCommand
+from documents.management.commands.mixins import MultiProcessMixin
+from documents.management.commands.mixins import ProgressBarMixin
 from documents.models import Document
 
 
-@dataclasses.dataclass(frozen=True, slots=True)
+@dataclasses.dataclass(frozen=True)
 class _WorkPackage:
     first_doc: Document
     second_doc: Document
 
 
-@dataclasses.dataclass(frozen=True, slots=True)
+@dataclasses.dataclass(frozen=True)
 class _WorkResult:
     doc_one_pk: int
     doc_two_pk: int
@@ -27,23 +31,22 @@ class _WorkResult:
 def _process_and_match(work: _WorkPackage) -> _WorkResult:
     """
     Does basic processing of document content, gets the basic ratio
-    and returns the result package.
+    and returns the result package
     """
+    # Normalize the string some, lower case, whitespace, etc
     first_string = rapidfuzz.utils.default_process(work.first_doc.content)
     second_string = rapidfuzz.utils.default_process(work.second_doc.content)
 
+    # Basic matching ratio
     match = rapidfuzz.fuzz.ratio(first_string, second_string)
 
     return _WorkResult(work.first_doc.pk, work.second_doc.pk, match)
 
 
-class Command(PaperlessCommand):
+class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
     help = "Searches for documents where the content almost matches"
 
-    supports_multiprocessing = True
-
     def add_arguments(self, parser):
-        super().add_arguments(parser)
         parser.add_argument(
             "--ratio",
             default=85.0,
@@ -56,11 +59,16 @@ class Command(PaperlessCommand):
             action="store_true",
             help="If set, one document of matches above the ratio WILL BE DELETED",
         )
+        self.add_argument_progress_bar_mixin(parser)
+        self.add_argument_processes_mixin(parser)
 
     def handle(self, *args, **options):
         RATIO_MIN: Final[float] = 0.0
         RATIO_MAX: Final[float] = 100.0
 
+        self.handle_processes_mixin(**options)
+        self.handle_progress_bar_mixin(**options)
+
         if options["delete"]:
             self.stdout.write(
                 self.style.WARNING(
@@ -72,58 +80,66 @@ class Command(PaperlessCommand):
         checked_pairs: set[tuple[int, int]] = set()
         work_pkgs: list[_WorkPackage] = []
 
+        # Ratio is a float from 0.0 to 100.0
         if opt_ratio < RATIO_MIN or opt_ratio > RATIO_MAX:
             raise CommandError("The ratio must be between 0 and 100")
 
         all_docs = Document.objects.all().order_by("id")
 
+        # Build work packages for processing
         for first_doc in all_docs:
             for second_doc in all_docs:
+                # doc to doc is obviously not useful
                 if first_doc.pk == second_doc.pk:
                     continue
+                # Skip empty documents (e.g. password-protected)
                 if first_doc.content.strip() == "" or second_doc.content.strip() == "":
                     continue
+                # Skip matching which have already been matched together
+                # doc 1 to doc 2 is the same as doc 2 to doc 1
                 doc_1_to_doc_2 = (first_doc.pk, second_doc.pk)
                 doc_2_to_doc_1 = doc_1_to_doc_2[::-1]
                 if doc_1_to_doc_2 in checked_pairs or doc_2_to_doc_1 in checked_pairs:
                     continue
                 checked_pairs.update([doc_1_to_doc_2, doc_2_to_doc_1])
+                # Actually something useful to work on now
                 work_pkgs.append(_WorkPackage(first_doc, second_doc))
 
-        results: list[_WorkResult] = []
+        # Don't spin up a pool of 1 process
         if self.process_count == 1:
-            for work in self.track(work_pkgs, description="Matching..."):
+            results = []
+            for work in tqdm.tqdm(work_pkgs, disable=self.no_progress_bar):
                 results.append(_process_and_match(work))
         else:  # pragma: no cover
-            for proc_result in self.process_parallel(
-                _process_and_match,
-                work_pkgs,
-                description="Matching...",
-            ):
-                if proc_result.error:
-                    self.console.print(
-                        f"[red]Failed: {proc_result.error}[/red]",
-                    )
-                elif proc_result.result is not None:
-                    results.append(proc_result.result)
-
-        messages: list[str] = []
-        maybe_delete_ids: list[int] = []
-        for match_result in sorted(results):
-            if match_result.ratio >= opt_ratio:
-                messages.append(
-                    self.style.NOTICE(
-                        f"Document {match_result.doc_one_pk} fuzzy match"
-                        f" to {match_result.doc_two_pk}"
-                        f" (confidence {match_result.ratio:.3f})\n",
+            with multiprocessing.Pool(processes=self.process_count) as pool:
+                results = list(
+                    tqdm.tqdm(
+                        pool.imap_unordered(_process_and_match, work_pkgs),
+                        total=len(work_pkgs),
+                        disable=self.no_progress_bar,
                     ),
                 )
-                maybe_delete_ids.append(match_result.doc_two_pk)
+
+        # Check results
+        messages = []
+        maybe_delete_ids = []
+        for result in sorted(results):
+            if result.ratio >= opt_ratio:
+                messages.append(
+                    self.style.NOTICE(
+                        f"Document {result.doc_one_pk} fuzzy match"
+                        f" to {result.doc_two_pk} (confidence {result.ratio:.3f})\n",
+                    ),
+                )
+                maybe_delete_ids.append(result.doc_two_pk)
 
         if len(messages) == 0:
-            messages.append(self.style.SUCCESS("No matches found\n"))
-        self.stdout.writelines(messages)
-
+            messages.append(
+                self.style.SUCCESS("No matches found\n"),
+            )
+        self.stdout.writelines(
+            messages,
+        )
         if options["delete"]:
             self.stdout.write(
                 self.style.NOTICE(

src/documents/management/commands/document_renamer.py

@@ -1,12 +1,25 @@
+import logging
+
+import tqdm
+from django.core.management.base import BaseCommand
 from django.db.models.signals import post_save
 
-from documents.management.commands.base import PaperlessCommand
+from documents.management.commands.mixins import ProgressBarMixin
 from documents.models import Document
 
 
-class Command(PaperlessCommand):
-    help = "Rename all documents"
+class Command(ProgressBarMixin, BaseCommand):
+    help = "This will rename all documents to match the latest filename format."
+
+    def add_arguments(self, parser):
+        self.add_argument_progress_bar_mixin(parser)
 
     def handle(self, *args, **options):
-        for document in self.track(Document.objects.all(), description="Renaming..."):
+        self.handle_progress_bar_mixin(**options)
+        logging.getLogger().handlers[0].level = logging.ERROR
+
+        for document in tqdm.tqdm(
+            Document.objects.all(),
+            disable=self.no_progress_bar,
+        ):
             post_save.send(Document, instance=document, created=False)

src/documents/management/commands/document_retagger.py

@@ -1,7 +1,10 @@
 import logging
 
+import tqdm
+from django.core.management.base import BaseCommand
+
 from documents.classifier import load_classifier
-from documents.management.commands.base import PaperlessCommand
+from documents.management.commands.mixins import ProgressBarMixin
 from documents.models import Document
 from documents.signals.handlers import set_correspondent
 from documents.signals.handlers import set_document_type
@@ -11,7 +14,7 @@ from documents.signals.handlers import set_tags
 logger = logging.getLogger("paperless.management.retagger")
 
 
-class Command(PaperlessCommand):
+class Command(ProgressBarMixin, BaseCommand):
     help = (
         "Using the current classification model, assigns correspondents, tags "
         "and document types to all documents, effectively allowing you to "
@@ -20,7 +23,6 @@ class Command(PaperlessCommand):
     )
 
     def add_arguments(self, parser):
-        super().add_arguments(parser)
         parser.add_argument("-c", "--correspondent", default=False, action="store_true")
         parser.add_argument("-T", "--tags", default=False, action="store_true")
         parser.add_argument("-t", "--document_type", default=False, action="store_true")
@@ -32,7 +34,7 @@ class Command(PaperlessCommand):
             action="store_true",
             help=(
                 "By default this command won't try to assign a correspondent "
-                "if more than one matches the document. Use this flag if "
+                "if more than one matches the document.  Use this flag if "
                 "you'd rather it just pick the first one it finds."
             ),
         )
@@ -47,6 +49,7 @@ class Command(PaperlessCommand):
                 "and tags that do not match anymore due to changed rules."
             ),
         )
+        self.add_argument_progress_bar_mixin(parser)
         parser.add_argument(
             "--suggest",
             default=False,
@@ -65,6 +68,8 @@ class Command(PaperlessCommand):
         )
 
     def handle(self, *args, **options):
+        self.handle_progress_bar_mixin(**options)
+
         if options["inbox_only"]:
             queryset = Document.objects.filter(tags__is_inbox_tag=True)
         else:
@@ -79,7 +84,7 @@ class Command(PaperlessCommand):
 
         classifier = load_classifier()
 
-        for document in self.track(documents, description="Retagging..."):
+        for document in tqdm.tqdm(documents, disable=self.no_progress_bar):
             if options["correspondent"]:
                 set_correspondent(
                     sender=None,
@@ -117,7 +122,6 @@ class Command(PaperlessCommand):
                     stdout=self.stdout,
                     style_func=self.style,
                 )
-
             if options["storage_path"]:
                 set_storage_path(
                     sender=None,

src/documents/management/commands/document_thumbnails.py

@@ -1,45 +1,43 @@
 import logging
+import multiprocessing
 import shutil
 
-from documents.management.commands.base import PaperlessCommand
+import tqdm
+from django import db
+from django.core.management.base import BaseCommand
+
+from documents.management.commands.mixins import MultiProcessMixin
+from documents.management.commands.mixins import ProgressBarMixin
 from documents.models import Document
 from documents.parsers import get_parser_class_for_mime_type
 
-logger = logging.getLogger("paperless.management.thumbnails")
 
-
-def _process_document(doc_id: int) -> None:
+def _process_document(doc_id) -> None:
     document: Document = Document.objects.get(id=doc_id)
     parser_class = get_parser_class_for_mime_type(document.mime_type)
 
-    if parser_class is None:
-        logger.warning(
-            "%s: No parser for mime type %s",
-            document,
-            document.mime_type,
-        )
+    if parser_class:
+        parser = parser_class(logging_group=None)
+    else:
+        print(f"{document} No parser for mime type {document.mime_type}")  # noqa: T201
         return
 
-    parser = parser_class(logging_group=None)
-
     try:
         thumb = parser.get_thumbnail(
             document.source_path,
             document.mime_type,
             document.get_public_filename(),
         )
+
         shutil.move(thumb, document.thumbnail_path)
     finally:
         parser.cleanup()
 
 
-class Command(PaperlessCommand):
+class Command(MultiProcessMixin, ProgressBarMixin, BaseCommand):
     help = "This will regenerate the thumbnails for all documents."
 
-    supports_multiprocessing = True
-
     def add_arguments(self, parser) -> None:
-        super().add_arguments(parser)
         parser.add_argument(
             "-d",
             "--document",
@@ -51,23 +49,36 @@ class Command(PaperlessCommand):
                 "run on this specific document."
             ),
         )
+        self.add_argument_progress_bar_mixin(parser)
+        self.add_argument_processes_mixin(parser)
 
     def handle(self, *args, **options):
         logging.getLogger().handlers[0].level = logging.ERROR
 
+        self.handle_processes_mixin(**options)
+        self.handle_progress_bar_mixin(**options)
+
         if options["document"]:
             documents = Document.objects.filter(pk=options["document"])
         else:
             documents = Document.objects.all()
 
-        ids = list(documents.values_list("id", flat=True))
+        ids = [doc.id for doc in documents]
 
-        for result in self.process_parallel(
-            _process_document,
-            ids,
-            description="Regenerating thumbnails...",
-        ):
-            if result.error:  # pragma: no cover
-                self.console.print(
-                    f"[red]Failed document {result.item}: {result.error}[/red]",
+        # Note to future self: this prevents django from reusing database
+        # connections between processes, which is bad and does not work
+        # with postgres.
+        db.connections.close_all()
+
+        if self.process_count == 1:
+            for doc_id in ids:
+                _process_document(doc_id)
+        else:  # pragma: no cover
+            with multiprocessing.Pool(processes=self.process_count) as pool:
+                list(
+                    tqdm.tqdm(
+                        pool.imap_unordered(_process_document, ids),
+                        total=len(ids),
+                        disable=self.no_progress_bar,
+                    ),
                 )

src/documents/management/commands/mixins.py

@@ -21,6 +21,26 @@ class CryptFields(TypedDict):
     fields: list[str]
 
 
+class MultiProcessMixin:
+    """
+    Small class to handle adding an argument and validating it
+    for the use of multiple processes
+    """
+
+    def add_argument_processes_mixin(self, parser: ArgumentParser) -> None:
+        parser.add_argument(
+            "--processes",
+            default=max(1, os.cpu_count() // 4),
+            type=int,
+            help="Number of processes to distribute work amongst",
+        )
+
+    def handle_processes_mixin(self, *args, **options) -> None:
+        self.process_count = options["processes"]
+        if self.process_count < 1:
+            raise CommandError("There must be at least 1 process")
+
+
 class ProgressBarMixin:
     """
     Many commands use a progress bar, which can be disabled

src/documents/management/commands/prune_audit_logs.py

@@ -1,21 +1,27 @@
 from auditlog.models import LogEntry
+from django.core.management.base import BaseCommand
 from django.db import transaction
+from tqdm import tqdm
 
-from documents.management.commands.base import PaperlessCommand
+from documents.management.commands.mixins import ProgressBarMixin
 
 
-class Command(PaperlessCommand):
-    """Prune the audit logs of objects that no longer exist."""
+class Command(BaseCommand, ProgressBarMixin):
+    """
+    Prune the audit logs of objects that no longer exist.
+    """
 
     help = "Prunes the audit logs of objects that no longer exist."
 
-    def handle(self, *args, **options):
+    def add_arguments(self, parser):
+        self.add_argument_progress_bar_mixin(parser)
+
+    def handle(self, **options):
+        self.handle_progress_bar_mixin(**options)
         with transaction.atomic():
-            for log_entry in self.track(
-                LogEntry.objects.all(),
-                description="Pruning audit logs...",
-            ):
+            for log_entry in tqdm(LogEntry.objects.all(), disable=self.no_progress_bar):
                 model_class = log_entry.content_type.model_class()
+                # use global_objects for SoftDeleteModel
                 objects = (
                     model_class.global_objects
                     if hasattr(model_class, "global_objects")
@@ -26,8 +32,8 @@ class Command(PaperlessCommand):
                     and not objects.filter(pk=log_entry.object_id).exists()
                 ):
                     log_entry.delete()
-                    self.console.print(
-                        f"Deleted audit log entry for "
-                        f"{model_class.__name__} #{log_entry.object_id}",
-                        style="yellow",
+                    tqdm.write(
+                        self.style.NOTICE(
+                            f"Deleted audit log entry for {model_class.__name__} #{log_entry.object_id}",
+                        ),
                     )

src/documents/plugins/date_parsing/base.py

@@ -9,7 +9,7 @@ from types import TracebackType
 try:
     from typing import Self
 except ImportError:
-    from typing_extensions import Self
+    from typing import Self
 
 import dateparser
 

src/documents/plugins/helpers.py

@@ -8,7 +8,7 @@ if TYPE_CHECKING:
     from channels_redis.pubsub import RedisPubSubChannelLayer
 
 
-class ProgressStatusOptions(str, enum.Enum):
+class ProgressStatusOptions(enum.StrEnum):
     STARTED = "STARTED"
     WORKING = "WORKING"
     SUCCESS = "SUCCESS"

src/documents/tests/date_parsing/conftest.py

@@ -24,7 +24,7 @@ def base_config() -> DateParserConfig:
             12,
             0,
             0,
-            tzinfo=datetime.timezone.utc,
+            tzinfo=datetime.UTC,
         ),
         filename_date_order="YMD",
         content_date_order="DMY",
@@ -45,7 +45,7 @@ def config_with_ignore_dates() -> DateParserConfig:
             12,
             0,
             0,
-            tzinfo=datetime.timezone.utc,
+            tzinfo=datetime.UTC,
         ),
         filename_date_order="DMY",
         content_date_order="MDY",

src/documents/tests/date_parsing/test_date_parsing.py

@@ -101,50 +101,50 @@ class TestFilterDate:
         [
             # Valid Dates
             pytest.param(
-                datetime.datetime(2024, 1, 10, tzinfo=datetime.timezone.utc),
-                datetime.datetime(2024, 1, 10, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 1, 10, tzinfo=datetime.UTC),
+                datetime.datetime(2024, 1, 10, tzinfo=datetime.UTC),
                 id="valid_past_date",
             ),
             pytest.param(
-                datetime.datetime(2024, 1, 15, 12, 0, 0, tzinfo=datetime.timezone.utc),
-                datetime.datetime(2024, 1, 15, 12, 0, 0, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 1, 15, 12, 0, 0, tzinfo=datetime.UTC),
+                datetime.datetime(2024, 1, 15, 12, 0, 0, tzinfo=datetime.UTC),
                 id="exactly_at_reference",
             ),
             pytest.param(
-                datetime.datetime(1901, 1, 1, tzinfo=datetime.timezone.utc),
-                datetime.datetime(1901, 1, 1, tzinfo=datetime.timezone.utc),
+                datetime.datetime(1901, 1, 1, tzinfo=datetime.UTC),
+                datetime.datetime(1901, 1, 1, tzinfo=datetime.UTC),
                 id="year_1901_valid",
             ),
             # Date is > reference_time
             pytest.param(
-                datetime.datetime(2024, 1, 16, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 1, 16, tzinfo=datetime.UTC),
                 None,
                 id="future_date_day_after",
             ),
             # date.date() in ignore_dates
             pytest.param(
-                datetime.datetime(2024, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 1, 1, 0, 0, 0, tzinfo=datetime.UTC),
                 None,
                 id="ignored_date_midnight_jan1",
             ),
             pytest.param(
-                datetime.datetime(2024, 1, 1, 10, 30, 0, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 1, 1, 10, 30, 0, tzinfo=datetime.UTC),
                 None,
                 id="ignored_date_midday_jan1",
             ),
             pytest.param(
-                datetime.datetime(2024, 12, 25, 15, 0, 0, tzinfo=datetime.timezone.utc),
+                datetime.datetime(2024, 12, 25, 15, 0, 0, tzinfo=datetime.UTC),
                 None,
                 id="ignored_date_dec25_future",
             ),
             # date.year <= 1900
             pytest.param(
-                datetime.datetime(1899, 12, 31, tzinfo=datetime.timezone.utc),
+                datetime.datetime(1899, 12, 31, tzinfo=datetime.UTC),
                 None,
                 id="year_1899",
             ),
             pytest.param(
-                datetime.datetime(1900, 1, 1, tzinfo=datetime.timezone.utc),
+                datetime.datetime(1900, 1, 1, tzinfo=datetime.UTC),
                 None,
                 id="year_1900_boundary",
             ),
@@ -176,7 +176,7 @@ class TestFilterDate:
             1,
             12,
             0,
-            tzinfo=datetime.timezone.utc,
+            tzinfo=datetime.UTC,
         )
         another_ignored = datetime.datetime(
             2024,
@@ -184,7 +184,7 @@ class TestFilterDate:
             25,
             15,
             30,
-            tzinfo=datetime.timezone.utc,
+            tzinfo=datetime.UTC,
         )
         allowed_date = datetime.datetime(
             2024,
@@ -192,7 +192,7 @@ class TestFilterDate:
             2,
             12,
             0,
-            tzinfo=datetime.timezone.utc,
+            tzinfo=datetime.UTC,
         )
 
         assert parser._filter_date(ignored_date) is None
@@ -204,7 +204,7 @@ class TestFilterDate:
         regex_parser: RegexDateParserPlugin,
     ) -> None:
         """Should work with timezone-aware datetimes."""
-        date_utc = datetime.datetime(2024, 1, 10, 12, 0, tzinfo=datetime.timezone.utc)
+        date_utc = datetime.datetime(2024, 1, 10, 12, 0, tzinfo=datetime.UTC)
 
         result = regex_parser._filter_date(date_utc)
 
@@ -221,8 +221,8 @@ class TestRegexDateParser:
                 "report-2023-12-25.txt",
                 "Event recorded on 25/12/2022.",
                 [
-                    datetime.datetime(2023, 12, 25, tzinfo=datetime.timezone.utc),
-                    datetime.datetime(2022, 12, 25, tzinfo=datetime.timezone.utc),
+                    datetime.datetime(2023, 12, 25, tzinfo=datetime.UTC),
+                    datetime.datetime(2022, 12, 25, tzinfo=datetime.UTC),
                 ],
                 id="filename-y-m-d_and_content-d-m-y",
             ),
@@ -230,8 +230,8 @@ class TestRegexDateParser:
                 "img_2023.01.02.jpg",
                 "Taken on 01/02/2023",
                 [
-                    datetime.datetime(2023, 1, 2, tzinfo=datetime.timezone.utc),
-                    datetime.datetime(2023, 2, 1, tzinfo=datetime.timezone.utc),
+                    datetime.datetime(2023, 1, 2, tzinfo=datetime.UTC),
+                    datetime.datetime(2023, 2, 1, tzinfo=datetime.UTC),
                 ],
                 id="ambiguous-dates-respect-orders",
             ),
@@ -239,7 +239,7 @@ class TestRegexDateParser:
                 "notes.txt",
                 "bad date 99/99/9999 and 25/12/2022",
                 [
-                    datetime.datetime(2022, 12, 25, tzinfo=datetime.timezone.utc),
+                    datetime.datetime(2022, 12, 25, tzinfo=datetime.UTC),
                 ],
                 id="parse-exception-skips-bad-and-yields-good",
             ),
@@ -275,24 +275,24 @@ class TestRegexDateParser:
                 or "2023.12.25" in date_string
                 or "2023-12-25" in date_string
             ):
-                return datetime.datetime(2023, 12, 25, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 12, 25, tzinfo=datetime.UTC)
 
             # content DMY 25/12/2022
             if "25/12/2022" in date_string or "25-12-2022" in date_string:
-                return datetime.datetime(2022, 12, 25, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2022, 12, 25, tzinfo=datetime.UTC)
 
             # filename YMD 2023.01.02
             if "2023.01.02" in date_string or "2023-01-02" in date_string:
-                return datetime.datetime(2023, 1, 2, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 1, 2, tzinfo=datetime.UTC)
 
             # ambiguous 01/02/2023 -> respect DATE_ORDER setting
             if "01/02/2023" in date_string:
                 if date_order == "DMY":
-                    return datetime.datetime(2023, 2, 1, tzinfo=datetime.timezone.utc)
+                    return datetime.datetime(2023, 2, 1, tzinfo=datetime.UTC)
                 if date_order == "YMD":
-                    return datetime.datetime(2023, 1, 2, tzinfo=datetime.timezone.utc)
+                    return datetime.datetime(2023, 1, 2, tzinfo=datetime.UTC)
                 # fallback
-                return datetime.datetime(2023, 2, 1, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 2, 1, tzinfo=datetime.UTC)
 
             # simulate parse failure for malformed input
             if "99/99/9999" in date_string or "bad date" in date_string:
@@ -328,7 +328,7 @@ class TestRegexDateParser:
                 12,
                 0,
                 0,
-                tzinfo=datetime.timezone.utc,
+                tzinfo=datetime.UTC,
             ),
             filename_date_order="YMD",
             content_date_order="DMY",
@@ -344,13 +344,13 @@ class TestRegexDateParser:
         ) -> datetime.datetime | None:
             if "10/12/2023" in date_string or "10-12-2023" in date_string:
                 # ignored date
-                return datetime.datetime(2023, 12, 10, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 12, 10, tzinfo=datetime.UTC)
             if "01/02/2024" in date_string or "01-02-2024" in date_string:
                 # future relative to reference_time -> filtered
-                return datetime.datetime(2024, 2, 1, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2024, 2, 1, tzinfo=datetime.UTC)
             if "05/01/2023" in date_string or "05-01-2023" in date_string:
                 # valid
-                return datetime.datetime(2023, 1, 5, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 1, 5, tzinfo=datetime.UTC)
             return None
 
         mocker.patch(target, side_effect=fake_parse)
@@ -358,7 +358,7 @@ class TestRegexDateParser:
         content = "Ignored: 10/12/2023, Future: 01/02/2024, Keep: 05/01/2023"
         results = list(parser.parse("whatever.txt", content))
 
-        assert results == [datetime.datetime(2023, 1, 5, tzinfo=datetime.timezone.utc)]
+        assert results == [datetime.datetime(2023, 1, 5, tzinfo=datetime.UTC)]
 
     def test_parse_handles_no_matches_and_returns_empty_list(
         self,
@@ -392,7 +392,7 @@ class TestRegexDateParser:
                 12,
                 0,
                 0,
-                tzinfo=datetime.timezone.utc,
+                tzinfo=datetime.UTC,
             ),
             filename_date_order=None,
             content_date_order="DMY",
@@ -409,9 +409,9 @@ class TestRegexDateParser:
         ) -> datetime.datetime | None:
             # return distinct datetimes so we can tell which source was parsed
             if "25/12/2022" in date_string:
-                return datetime.datetime(2022, 12, 25, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2022, 12, 25, tzinfo=datetime.UTC)
             if "2023-12-25" in date_string:
-                return datetime.datetime(2023, 12, 25, tzinfo=datetime.timezone.utc)
+                return datetime.datetime(2023, 12, 25, tzinfo=datetime.UTC)
             return None
 
         mock = mocker.patch(target, side_effect=fake_parse)
@@ -429,5 +429,5 @@ class TestRegexDateParser:
         assert "25/12/2022" in called_date_string
         # And the parser should have yielded the corresponding datetime
         assert results == [
-            datetime.datetime(2022, 12, 25, tzinfo=datetime.timezone.utc),
+            datetime.datetime(2022, 12, 25, tzinfo=datetime.UTC),
         ]

src/documents/tests/management/test_management_base_cmd.py

@@ -1,518 +0,0 @@
-"""Tests for PaperlessCommand base class."""
-
-from __future__ import annotations
-
-import io
-from typing import TYPE_CHECKING
-
-import pytest
-from django.core.management import CommandError
-from django.db.models import QuerySet
-from rich.console import Console
-
-from documents.management.commands.base import PaperlessCommand
-from documents.management.commands.base import ProcessResult
-
-if TYPE_CHECKING:
-    from pytest_mock import MockerFixture
-
-
-# --- Test Commands ---
-# These simulate real command implementations for testing
-
-
-class SimpleCommand(PaperlessCommand):
-    """Command with default settings (progress bar, no multiprocessing)."""
-
-    help = "Simple test command"
-
-    def handle(self, *args, **options):
-        items = list(range(5))
-        results = []
-        for item in self.track(items, description="Processing..."):
-            results.append(item * 2)
-        self.stdout.write(f"Results: {results}")
-
-
-class NoProgressBarCommand(PaperlessCommand):
-    """Command with progress bar disabled."""
-
-    help = "No progress bar command"
-    supports_progress_bar = False
-
-    def handle(self, *args, **options):
-        items = list(range(3))
-        for _ in self.track(items):
-            # We don't need to actually work
-            pass
-        self.stdout.write("Done")
-
-
-class MultiprocessCommand(PaperlessCommand):
-    """Command with multiprocessing support."""
-
-    help = "Multiprocess test command"
-    supports_multiprocessing = True
-
-    def handle(self, *args, **options):
-        items = list(range(5))
-        results = []
-        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}")
-
-
-# --- Helper Functions for Multiprocessing ---
-# Must be at module level to be picklable
-
-
-def _double_value(x: int) -> int:
-    """Double the input value."""
-    return x * 2
-
-
-def _divide_ten_by(x: int) -> float:
-    """Divide 10 by x. Raises ZeroDivisionError if x is 0."""
-    return 10 / x
-
-
-# --- Fixtures ---
-
-
-@pytest.fixture
-def console() -> Console:
-    """Create a non-interactive console for testing."""
-    return Console(force_terminal=False, force_interactive=False)
-
-
-@pytest.fixture
-def simple_command(console: Console) -> SimpleCommand:
-    """Create a SimpleCommand instance configured for testing."""
-    command = SimpleCommand()
-    command.stdout = io.StringIO()
-    command.stderr = io.StringIO()
-    command.console = console
-    command.no_progress_bar = True
-    command.process_count = 1
-    return command
-
-
-@pytest.fixture
-def multiprocess_command(console: Console) -> MultiprocessCommand:
-    """Create a MultiprocessCommand instance configured for testing."""
-    command = MultiprocessCommand()
-    command.stdout = io.StringIO()
-    command.stderr = io.StringIO()
-    command.console = console
-    command.no_progress_bar = True
-    command.process_count = 1
-    return command
-
-
-@pytest.fixture
-def mock_queryset():
-    """
-    Create a mock Django QuerySet that tracks method calls.
-
-    This verifies we use .count() instead of len() for querysets.
-    """
-
-    class MockQuerySet(QuerySet):
-        def __init__(self, items: list):
-            self._items = items
-            self.count_called = False
-
-        def count(self) -> int:
-            self.count_called = True
-            return len(self._items)
-
-        def __iter__(self):
-            return iter(self._items)
-
-        def __len__(self):
-            raise AssertionError("len() should not be called on querysets")
-
-    return MockQuerySet
-
-
-# --- Test Classes ---
-
-
-@pytest.mark.management
-class TestProcessResult:
-    """Tests for the ProcessResult dataclass."""
-
-    def test_success_result(self):
-        result = ProcessResult(item=1, result=2, error=None)
-
-        assert result.item == 1
-        assert result.result == 2
-        assert result.error is None
-        assert result.success is True
-
-    def test_error_result(self):
-        error = ValueError("test error")
-        result = ProcessResult(item=1, result=None, error=error)
-
-        assert result.item == 1
-        assert result.result is None
-        assert result.error is error
-        assert result.success is False
-
-
-@pytest.mark.management
-class TestPaperlessCommandArguments:
-    """Tests for argument parsing behavior."""
-
-    def test_progress_bar_argument_added_by_default(self):
-        command = SimpleCommand()
-        parser = command.create_parser("manage.py", "simple")
-
-        options = parser.parse_args(["--no-progress-bar"])
-        assert options.no_progress_bar is True
-
-        options = parser.parse_args([])
-        assert options.no_progress_bar is False
-
-    def test_progress_bar_argument_not_added_when_disabled(self):
-        command = NoProgressBarCommand()
-        parser = command.create_parser("manage.py", "noprogress")
-
-        options = parser.parse_args([])
-        assert not hasattr(options, "no_progress_bar")
-
-    def test_processes_argument_added_when_multiprocessing_enabled(self):
-        command = MultiprocessCommand()
-        parser = command.create_parser("manage.py", "multiprocess")
-
-        options = parser.parse_args(["--processes", "4"])
-        assert options.processes == 4
-
-        options = parser.parse_args([])
-        assert options.processes >= 1
-
-    def test_processes_argument_not_added_when_multiprocessing_disabled(self):
-        command = SimpleCommand()
-        parser = command.create_parser("manage.py", "simple")
-
-        options = parser.parse_args([])
-        assert not hasattr(options, "processes")
-
-
-@pytest.mark.management
-class TestPaperlessCommandExecute:
-    """Tests for the execute() setup behavior."""
-
-    @pytest.fixture
-    def base_options(self) -> dict:
-        """Base options required for execute()."""
-        return {
-            "verbosity": 1,
-            "no_color": True,
-            "force_color": False,
-            "skip_checks": True,
-        }
-
-    @pytest.mark.parametrize(
-        ("no_progress_bar_flag", "expected"),
-        [
-            pytest.param(False, False, id="progress-bar-enabled"),
-            pytest.param(True, True, id="progress-bar-disabled"),
-        ],
-    )
-    def test_no_progress_bar_state_set(
-        self,
-        base_options: dict,
-        *,
-        no_progress_bar_flag: bool,
-        expected: bool,
-    ):
-        command = SimpleCommand()
-        command.stdout = io.StringIO()
-        command.stderr = io.StringIO()
-
-        options = {**base_options, "no_progress_bar": no_progress_bar_flag}
-        command.execute(**options)
-
-        assert command.no_progress_bar is expected
-
-    def test_no_progress_bar_always_true_when_not_supported(self, base_options: dict):
-        command = NoProgressBarCommand()
-        command.stdout = io.StringIO()
-        command.stderr = io.StringIO()
-
-        command.execute(**base_options)
-
-        assert command.no_progress_bar is True
-
-    @pytest.mark.parametrize(
-        ("processes", "expected"),
-        [
-            pytest.param(1, 1, id="single-process"),
-            pytest.param(4, 4, id="four-processes"),
-        ],
-    )
-    def test_process_count_set(
-        self,
-        base_options: dict,
-        processes: int,
-        expected: int,
-    ):
-        command = MultiprocessCommand()
-        command.stdout = io.StringIO()
-        command.stderr = io.StringIO()
-
-        options = {**base_options, "processes": processes, "no_progress_bar": True}
-        command.execute(**options)
-
-        assert command.process_count == expected
-
-    @pytest.mark.parametrize(
-        "invalid_count",
-        [
-            pytest.param(0, id="zero"),
-            pytest.param(-1, id="negative"),
-        ],
-    )
-    def test_process_count_validation_rejects_invalid(
-        self,
-        base_options: dict,
-        invalid_count: int,
-    ):
-        command = MultiprocessCommand()
-        command.stdout = io.StringIO()
-        command.stderr = io.StringIO()
-
-        options = {**base_options, "processes": invalid_count, "no_progress_bar": True}
-
-        with pytest.raises(CommandError, match="--processes must be at least 1"):
-            command.execute(**options)
-
-    def test_process_count_defaults_to_one_when_not_supported(self, base_options: dict):
-        command = SimpleCommand()
-        command.stdout = io.StringIO()
-        command.stderr = io.StringIO()
-
-        options = {**base_options, "no_progress_bar": True}
-        command.execute(**options)
-
-        assert command.process_count == 1
-
-
-@pytest.mark.management
-class TestGetIterableLength:
-    """Tests for the _get_iterable_length() method."""
-
-    def test_uses_count_for_querysets(
-        self,
-        simple_command: SimpleCommand,
-        mock_queryset,
-    ):
-        """Should call .count() on Django querysets rather than len()."""
-        queryset = mock_queryset([1, 2, 3, 4, 5])
-
-        result = simple_command._get_iterable_length(queryset)
-
-        assert result == 5
-        assert queryset.count_called is True
-
-    def test_uses_len_for_sized(self, simple_command: SimpleCommand):
-        """Should use len() for sequences and other Sized types."""
-        result = simple_command._get_iterable_length([1, 2, 3, 4])
-
-        assert result == 4
-
-    def test_returns_none_for_unsized_iterables(self, simple_command: SimpleCommand):
-        """Should return None for generators and other iterables without len()."""
-        result = simple_command._get_iterable_length(x for x in [1, 2, 3])
-
-        assert result is None
-
-
-@pytest.mark.management
-class TestTrack:
-    """Tests for the track() method."""
-
-    def test_with_progress_bar_disabled(self, simple_command: SimpleCommand):
-        simple_command.no_progress_bar = True
-        items = ["a", "b", "c"]
-
-        result = list(simple_command.track(items, description="Test..."))
-
-        assert result == items
-
-    def test_with_progress_bar_enabled(self, simple_command: SimpleCommand):
-        simple_command.no_progress_bar = False
-        items = [1, 2, 3]
-
-        result = list(simple_command.track(items, description="Processing..."))
-
-        assert result == items
-
-    def test_with_explicit_total(self, simple_command: SimpleCommand):
-        simple_command.no_progress_bar = False
-
-        def gen():
-            yield from [1, 2, 3]
-
-        result = list(simple_command.track(gen(), total=3))
-
-        assert result == [1, 2, 3]
-
-    def test_with_generator_no_total(self, simple_command: SimpleCommand):
-        def gen():
-            yield from [1, 2, 3]
-
-        result = list(simple_command.track(gen()))
-
-        assert result == [1, 2, 3]
-
-    def test_empty_iterable(self, simple_command: SimpleCommand):
-        result = list(simple_command.track([]))
-
-        assert result == []
-
-    def test_uses_queryset_count(
-        self,
-        simple_command: SimpleCommand,
-        mock_queryset,
-        mocker: MockerFixture,
-    ):
-        """Verify track() uses .count() for querysets."""
-        simple_command.no_progress_bar = False
-        queryset = mock_queryset([1, 2, 3])
-
-        spy = mocker.spy(simple_command, "_get_iterable_length")
-
-        result = list(simple_command.track(queryset))
-
-        assert result == [1, 2, 3]
-        spy.assert_called_once_with(queryset)
-        assert queryset.count_called is True
-
-
-@pytest.mark.management
-class TestProcessParallel:
-    """Tests for the process_parallel() method."""
-
-    def test_sequential_processing_single_process(
-        self,
-        multiprocess_command: MultiprocessCommand,
-    ):
-        multiprocess_command.process_count = 1
-        items = [1, 2, 3, 4, 5]
-
-        results = list(multiprocess_command.process_parallel(_double_value, items))
-
-        assert len(results) == 5
-        assert all(r.success for r in results)
-
-        result_map = {r.item: r.result for r in results}
-        assert result_map == {1: 2, 2: 4, 3: 6, 4: 8, 5: 10}
-
-    def test_sequential_processing_handles_errors(
-        self,
-        multiprocess_command: MultiprocessCommand,
-    ):
-        multiprocess_command.process_count = 1
-        items = [1, 2, 0, 4]  # 0 causes ZeroDivisionError
-
-        results = list(multiprocess_command.process_parallel(_divide_ten_by, items))
-
-        assert len(results) == 4
-
-        successes = [r for r in results if r.success]
-        failures = [r for r in results if not r.success]
-
-        assert len(successes) == 3
-        assert len(failures) == 1
-        assert failures[0].item == 0
-        assert isinstance(failures[0].error, ZeroDivisionError)
-
-    def test_parallel_closes_db_connections(
-        self,
-        multiprocess_command: MultiprocessCommand,
-        mocker: MockerFixture,
-    ):
-        multiprocess_command.process_count = 2
-        items = [1, 2, 3]
-
-        mock_connections = mocker.patch(
-            "documents.management.commands.base.db.connections",
-        )
-
-        results = list(multiprocess_command.process_parallel(_double_value, items))
-
-        mock_connections.close_all.assert_called_once()
-        assert len(results) == 3
-
-    def test_parallel_processing_handles_errors(
-        self,
-        multiprocess_command: MultiprocessCommand,
-        mocker: MockerFixture,
-    ):
-        multiprocess_command.process_count = 2
-        items = [1, 2, 0, 4]
-
-        mocker.patch("documents.management.commands.base.db.connections")
-
-        results = list(multiprocess_command.process_parallel(_divide_ten_by, items))
-
-        failures = [r for r in results if not r.success]
-        assert len(failures) == 1
-        assert failures[0].item == 0
-
-    def test_empty_items(self, multiprocess_command: MultiprocessCommand):
-        results = list(multiprocess_command.process_parallel(_double_value, []))
-
-        assert results == []
-
-    def test_result_contains_original_item(
-        self,
-        multiprocess_command: MultiprocessCommand,
-    ):
-        items = [10, 20, 30]
-
-        results = list(multiprocess_command.process_parallel(_double_value, items))
-
-        for result in results:
-            assert result.item in items
-            assert result.result == result.item * 2
-
-    def test_sequential_path_used_for_single_process(
-        self,
-        multiprocess_command: MultiprocessCommand,
-        mocker: MockerFixture,
-    ):
-        """Verify single process uses sequential path (important for testing)."""
-        multiprocess_command.process_count = 1
-
-        spy_sequential = mocker.spy(multiprocess_command, "_process_sequential")
-        spy_parallel = mocker.spy(multiprocess_command, "_process_parallel")
-
-        list(multiprocess_command.process_parallel(_double_value, [1, 2, 3]))
-
-        spy_sequential.assert_called_once()
-        spy_parallel.assert_not_called()
-
-    def test_parallel_path_used_for_multiple_processes(
-        self,
-        multiprocess_command: MultiprocessCommand,
-        mocker: MockerFixture,
-    ):
-        """Verify multiple processes uses parallel path."""
-        multiprocess_command.process_count = 2
-
-        mocker.patch("documents.management.commands.base.db.connections")
-        spy_sequential = mocker.spy(multiprocess_command, "_process_sequential")
-        spy_parallel = mocker.spy(multiprocess_command, "_process_parallel")
-
-        list(multiprocess_command.process_parallel(_double_value, [1, 2, 3]))
-
-        spy_parallel.assert_called_once()
-        spy_sequential.assert_not_called()

src/documents/tests/test_file_handling.py

@@ -336,7 +336,11 @@ class TestFileHandling(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             added=d1,
         )
 
-        self.assertEqual(generate_filename(doc1), Path("232-01-09.pdf"))
+        # Account for 3.14 padding changes
+        expected_year: str = d1.strftime("%Y")
+        expected_filename: Path = Path(f"{expected_year}-01-09.pdf")
+
+        self.assertEqual(generate_filename(doc1), expected_filename)
 
         doc1.added = timezone.make_aware(datetime.datetime(2020, 11, 16, 1, 1, 1))
 

src/documents/tests/test_filters.py

@@ -21,7 +21,7 @@ class TestDateLocalization:
         14,
         30,
         5,
-        tzinfo=datetime.timezone.utc,
+        tzinfo=datetime.UTC,
     )
 
     TEST_DATETIME_STRING: str = "2023-10-26T14:30:05+00:00"

src/documents/tests/test_management.py

@@ -4,7 +4,6 @@ from io import StringIO
 from pathlib import Path
 from unittest import mock
 
-import pytest
 from auditlog.models import LogEntry
 from django.contrib.contenttypes.models import ContentType
 from django.core.management import call_command
@@ -20,7 +19,6 @@ from documents.tests.utils import FileSystemAssertsMixin
 sample_file: Path = Path(__file__).parent / "samples" / "simple.pdf"
 
 
-@pytest.mark.management
 @override_settings(FILENAME_FORMAT="{correspondent}/{title}")
 class TestArchiver(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def make_models(self):
@@ -96,7 +94,6 @@ class TestArchiver(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
         self.assertEqual(doc2.archive_filename, "document_01.pdf")
 
 
-@pytest.mark.management
 class TestMakeIndex(TestCase):
     @mock.patch("documents.management.commands.document_index.index_reindex")
     def test_reindex(self, m) -> None:
@@ -109,7 +106,6 @@ class TestMakeIndex(TestCase):
         m.assert_called_once()
 
 
-@pytest.mark.management
 class TestRenamer(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     @override_settings(FILENAME_FORMAT="")
     def test_rename(self) -> None:
@@ -144,7 +140,6 @@ class TestCreateClassifier(TestCase):
         m.assert_called_once()
 
 
-@pytest.mark.management
 class TestSanityChecker(DirectoriesMixin, TestCase):
     def test_no_issues(self) -> None:
         with self.assertLogs() as capture:
@@ -170,7 +165,6 @@ class TestSanityChecker(DirectoriesMixin, TestCase):
         self.assertIn("Checksum mismatch. Stored: abc, actual:", capture.output[1])
 
 
-@pytest.mark.management
 class TestConvertMariaDBUUID(TestCase):
     @mock.patch("django.db.connection.schema_editor")
     def test_convert(self, m) -> None:
@@ -184,7 +178,6 @@ class TestConvertMariaDBUUID(TestCase):
         self.assertIn("Successfully converted", stdout.getvalue())
 
 
-@pytest.mark.management
 class TestPruneAuditLogs(TestCase):
     def test_prune_audit_logs(self) -> None:
         LogEntry.objects.create(

src/documents/tests/test_management_consumer.py

@@ -577,7 +577,6 @@ class TestTagsFromPath:
         assert len(tag_ids) == 0
 
 
-@pytest.mark.management
 class TestCommandValidation:
     """Tests for command argument validation."""
 
@@ -606,7 +605,6 @@ class TestCommandValidation:
             cmd.handle(directory=str(sample_pdf), oneshot=True, testing=False)
 
 
-@pytest.mark.management
 @pytest.mark.usefixtures("mock_supported_extensions")
 class TestCommandOneshot:
     """Tests for oneshot mode."""
@@ -777,7 +775,6 @@ def start_consumer(
             )
 
 
-@pytest.mark.management
 @pytest.mark.django_db
 class TestCommandWatch:
     """Integration tests for the watch loop."""
@@ -899,7 +896,6 @@ class TestCommandWatch:
         assert not thread.is_alive()
 
 
-@pytest.mark.management
 @pytest.mark.django_db
 class TestCommandWatchPolling:
     """Tests for polling mode."""
@@ -932,7 +928,6 @@ class TestCommandWatchPolling:
         mock_consume_file_delay.delay.assert_called()
 
 
-@pytest.mark.management
 @pytest.mark.django_db
 class TestCommandWatchRecursive:
     """Tests for recursive watching."""
@@ -996,7 +991,6 @@ class TestCommandWatchRecursive:
         assert len(overrides.tag_ids) == 2
 
 
-@pytest.mark.management
 @pytest.mark.django_db
 class TestCommandWatchEdgeCases:
     """Tests for edge cases and error handling."""

src/documents/tests/test_management_exporter.py

@@ -7,7 +7,6 @@ from pathlib import Path
 from unittest import mock
 from zipfile import ZipFile
 
-import pytest
 from allauth.socialaccount.models import SocialAccount
 from allauth.socialaccount.models import SocialApp
 from allauth.socialaccount.models import SocialToken
@@ -46,7 +45,6 @@ from documents.tests.utils import paperless_environment
 from paperless_mail.models import MailAccount
 
 
-@pytest.mark.management
 class TestExportImport(
     DirectoriesMixin,
     FileSystemAssertsMixin,
@@ -848,7 +846,6 @@ class TestExportImport(
         self.assertEqual(Document.objects.all().count(), 4)
 
 
-@pytest.mark.management
 class TestCryptExportImport(
     DirectoriesMixin,
     FileSystemAssertsMixin,

src/documents/tests/test_management_fuzzy.py

@@ -1,6 +1,5 @@
 from io import StringIO
 
-import pytest
 from django.core.management import CommandError
 from django.core.management import call_command
 from django.test import TestCase
@@ -8,7 +7,6 @@ from django.test import TestCase
 from documents.models import Document
 
 
-@pytest.mark.management
 class TestFuzzyMatchCommand(TestCase):
     MSG_REGEX = r"Document \d fuzzy match to \d \(confidence \d\d\.\d\d\d\)"
 
@@ -51,6 +49,19 @@ class TestFuzzyMatchCommand(TestCase):
             self.call_command("--ratio", "101")
         self.assertIn("The ratio must be between 0 and 100", str(e.exception))
 
+    def test_invalid_process_count(self) -> None:
+        """
+        GIVEN:
+            - Invalid process count less than 0 above upper
+        WHEN:
+            - Command is called
+        THEN:
+            - Error is raised indicating issue
+        """
+        with self.assertRaises(CommandError) as e:
+            self.call_command("--processes", "0")
+        self.assertIn("There must be at least 1 process", str(e.exception))
+
     def test_no_matches(self) -> None:
         """
         GIVEN:
@@ -140,7 +151,7 @@ class TestFuzzyMatchCommand(TestCase):
             mime_type="application/pdf",
             filename="final_test.pdf",
         )
-        stdout, _ = self.call_command("--no-progress-bar")
+        stdout, _ = self.call_command()
         lines = [x.strip() for x in stdout.splitlines() if x.strip()]
         self.assertEqual(len(lines), 3)
         for line in lines:
@@ -183,7 +194,7 @@ class TestFuzzyMatchCommand(TestCase):
 
         self.assertEqual(Document.objects.count(), 3)
 
-        stdout, _ = self.call_command("--delete", "--no-progress-bar")
+        stdout, _ = self.call_command("--delete")
 
         self.assertIn(
             "The command is configured to delete documents.  Use with caution",

src/documents/tests/test_management_importer.py

@@ -4,7 +4,6 @@ from io import StringIO
 from pathlib import Path
 from zipfile import ZipFile
 
-import pytest
 from django.contrib.auth.models import User
 from django.core.management import call_command
 from django.core.management.base import CommandError
@@ -19,7 +18,6 @@ from documents.tests.utils import FileSystemAssertsMixin
 from documents.tests.utils import SampleDirMixin
 
 
-@pytest.mark.management
 class TestCommandImport(
     DirectoriesMixin,
     FileSystemAssertsMixin,

src/documents/tests/test_management_retagger.py

@@ -1,4 +1,3 @@
-import pytest
 from django.core.management import call_command
 from django.core.management.base import CommandError
 from django.test import TestCase
@@ -11,7 +10,6 @@ from documents.models import Tag
 from documents.tests.utils import DirectoriesMixin
 
 
-@pytest.mark.management
 class TestRetagger(DirectoriesMixin, TestCase):
     def make_models(self) -> None:
         self.sp1 = StoragePath.objects.create(

src/documents/tests/test_management_superuser.py

@@ -2,7 +2,6 @@ import os
 from io import StringIO
 from unittest import mock
 
-import pytest
 from django.contrib.auth.models import User
 from django.core.management import call_command
 from django.test import TestCase
@@ -10,7 +9,6 @@ from django.test import TestCase
 from documents.tests.utils import DirectoriesMixin
 
 
-@pytest.mark.management
 class TestManageSuperUser(DirectoriesMixin, TestCase):
     def call_command(self, environ):
         out = StringIO()

src/documents/tests/test_management_thumbnails.py

@@ -2,7 +2,6 @@ import shutil
 from pathlib import Path
 from unittest import mock
 
-import pytest
 from django.core.management import call_command
 from django.test import TestCase
 
@@ -13,7 +12,6 @@ from documents.tests.utils import DirectoriesMixin
 from documents.tests.utils import FileSystemAssertsMixin
 
 
-@pytest.mark.management
 class TestMakeThumbnails(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
     def make_models(self) -> None:
         self.d1 = Document.objects.create(

src/documents/tests/test_workflows.py

@@ -4570,7 +4570,7 @@ class TestDateWorkflowLocalization(
         14,
         30,
         5,
-        tzinfo=datetime.timezone.utc,
+        tzinfo=datetime.UTC,
     )
 
     @pytest.mark.parametrize(

src/documents/versioning.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from dataclasses import dataclass
-from enum import Enum
+from enum import StrEnum
 from typing import TYPE_CHECKING
 from typing import Any
 
@@ -11,7 +11,7 @@ if TYPE_CHECKING:
     from django.http import HttpRequest
 
 
-class VersionResolutionError(str, Enum):
+class VersionResolutionError(StrEnum):
     INVALID = "invalid"
     NOT_FOUND = "not_found"