Removes support for Python 3.8 and lower from the code base

src/documents/barcodes.py

@@ -2,9 +2,7 @@ import logging
 import tempfile
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Dict
 from typing import Final
-from typing import List
 from typing import Optional
 
 from django.conf import settings
@@ -53,7 +51,7 @@ class BarcodeReader:
         self.file: Final[Path] = filepath
         self.mime: Final[str] = mime_type
         self.pdf_file: Path = self.file
-        self.barcodes: List[Barcode] = []
+        self.barcodes: list[Barcode] = []
         self.temp_dir: Optional[tempfile.TemporaryDirectory] = None
 
         if settings.CONSUMER_BARCODE_TIFF_SUPPORT:
@@ -111,7 +109,7 @@ class BarcodeReader:
         return asn
 
     @staticmethod
-    def read_barcodes_zxing(image: Image) -> List[str]:
+    def read_barcodes_zxing(image: Image) -> list[str]:
         barcodes = []
 
         import zxingcpp
@@ -127,7 +125,7 @@ class BarcodeReader:
         return barcodes
 
     @staticmethod
-    def read_barcodes_pyzbar(image: Image) -> List[str]:
+    def read_barcodes_pyzbar(image: Image) -> list[str]:
         barcodes = []
 
         from pyzbar import pyzbar
@@ -209,7 +207,7 @@ class BarcodeReader:
                 f"Exception during barcode scanning: {e}",
             )
 
-    def get_separation_pages(self) -> Dict[int, bool]:
+    def get_separation_pages(self) -> dict[int, bool]:
         """
         Search the parsed barcodes for separators and returns a dict of page
         numbers, which separate the file into new files, together with the
@@ -228,7 +226,7 @@ class BarcodeReader:
             **{bc.page: True for bc in self.barcodes if bc.is_asn and bc.page != 0},
         }
 
-    def separate_pages(self, pages_to_split_on: Dict[int, bool]) -> List[Path]:
+    def separate_pages(self, pages_to_split_on: dict[int, bool]) -> list[Path]:
         """
         Separate the provided pdf file on the pages_to_split_on.
         The pages which are defined by the keys in page_numbers
@@ -241,9 +239,9 @@ class BarcodeReader:
         fname = self.file.with_suffix("").name
         with Pdf.open(self.pdf_file) as input_pdf:
             # Start with an empty document
-            current_document: List[Page] = []
+            current_document: list[Page] = []
             # A list of documents, ie a list of lists of pages
-            documents: List[List[Page]] = [current_document]
+            documents: list[list[Page]] = [current_document]
 
             for idx, page in enumerate(input_pdf.pages):
                 # Keep building the new PDF as long as it is not a

src/documents/classifier.py

@@ -3,11 +3,10 @@ import os
 import pickle
 import re
 import warnings
+from collections.abc import Iterator
 from datetime import datetime
 from hashlib import sha256
 from pathlib import Path
-from typing import Iterator
-from typing import List
 from typing import Optional
 
 from django.conf import settings
@@ -357,7 +356,7 @@ class DocumentClassifier:
 
                 # Tokenize
                 # This splits the content into tokens, roughly words
-                words: List[str] = word_tokenize(
+                words: list[str] = word_tokenize(
                     content,
                     language=settings.NLTK_LANGUAGE,
                 )
@@ -404,7 +403,7 @@ class DocumentClassifier:
         else:
             return None
 
-    def predict_tags(self, content: str) -> List[int]:
+    def predict_tags(self, content: str) -> list[int]:
         from sklearn.utils.multiclass import type_of_target
 
         if self.tags_classifier:

src/documents/consumer.py

@@ -8,7 +8,6 @@ from pathlib import Path
 from subprocess import CompletedProcess
 from subprocess import run
 from typing import Optional
-from typing import Type
 
 import magic
 from asgiref.sync import async_to_sync
@@ -372,7 +371,7 @@ class Consumer(LoggingMixin):
         self.log.debug(f"Detected mime type: {mime_type}")
 
         # Based on the mime type, get the parser for that type
-        parser_class: Optional[Type[DocumentParser]] = get_parser_class_for_mime_type(
+        parser_class: Optional[type[DocumentParser]] = get_parser_class_for_mime_type(
             mime_type,
         )
         if not parser_class:

src/documents/data_models.py

@@ -2,7 +2,6 @@ import dataclasses
 import datetime
 import enum
 from pathlib import Path
-from typing import List
 from typing import Optional
 
 import magic
@@ -20,7 +19,7 @@ class DocumentMetadataOverrides:
     title: Optional[str] = None
     correspondent_id: Optional[int] = None
     document_type_id: Optional[int] = None
-    tag_ids: Optional[List[int]] = None
+    tag_ids: Optional[list[int]] = None
     created: Optional[datetime.datetime] = None
     asn: Optional[int] = None
     owner_id: Optional[int] = None

src/documents/double_sided.py

@@ -115,12 +115,10 @@ def collate(input_doc: ConsumableDocument) -> str:
             staging.unlink()
 
     else:
-        # In Python 3.9 move supports Path objects directly,
-        # but for now we have to be compatible with 3.8
-        shutil.move(str(pdf_file), str(staging))
+        shutil.move(pdf_file, staging)
         # update access to modification time so we know if the file
         # is outdated when another file gets uploaded
-        os.utime(str(staging), (dt.datetime.now().timestamp(),) * 2)
+        os.utime(staging, (dt.datetime.now().timestamp(),) * 2)
         logger.info(
             "Got scan with odd numbered pages of double-sided scan, moved it to %s",
             staging,

src/documents/management/commands/document_consumer.py

@@ -8,7 +8,6 @@ from threading import Event
 from time import monotonic
 from time import sleep
 from typing import Final
-from typing import Set
 
 from django.conf import settings
 from django.core.management.base import BaseCommand
@@ -32,7 +31,7 @@ except ImportError:  # pragma: nocover
 logger = logging.getLogger("paperless.management.consumer")
 
 
-def _tags_from_path(filepath) -> Set[Tag]:
+def _tags_from_path(filepath) -> set[Tag]:
     """
     Walk up the directory tree from filepath to CONSUMPTION_DIR
     and get or create Tag IDs for every directory.

src/documents/management/commands/document_exporter.py

@@ -5,8 +5,6 @@ import shutil
 import tempfile
 import time
 from pathlib import Path
-from typing import List
-from typing import Set
 
 import tqdm
 from django.conf import settings
@@ -138,8 +136,8 @@ class Command(BaseCommand):
         BaseCommand.__init__(self, *args, **kwargs)
         self.target: Path = None
         self.split_manifest = False
-        self.files_in_export_dir: Set[Path] = set()
-        self.exported_files: List[Path] = []
+        self.files_in_export_dir: set[Path] = set()
+        self.exported_files: list[Path] = []
         self.compare_checksums = False
         self.use_filename_format = False
         self.use_folder_prefix = False

src/documents/parsers.py

@@ -6,12 +6,11 @@ import re
 import shutil
 import subprocess
 import tempfile
+from collections.abc import Iterator
 from functools import lru_cache
 from pathlib import Path
-from typing import Iterator
-from typing import Match
+from re import Match
 from typing import Optional
-from typing import Set
 
 from django.conf import settings
 from django.utils import timezone
@@ -90,7 +89,7 @@ def is_file_ext_supported(ext: str) -> bool:
         return False
 
 
-def get_supported_file_extensions() -> Set[str]:
+def get_supported_file_extensions() -> set[str]:
     extensions = set()
     for response in document_consumer_declaration.send(None):
         parser_declaration = response[1]

src/documents/serialisers.py

@@ -1,14 +1,10 @@
 import datetime
 import math
 import re
+import zoneinfo
 
-from celery import states
-
-try:
-    import zoneinfo
-except ImportError:
-    from backports import zoneinfo
 import magic
+from celery import states
 from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User

src/documents/tasks.py

@@ -3,7 +3,6 @@ import logging
 import shutil
 import uuid
 from typing import Optional
-from typing import Type
 
 import tqdm
 from asgiref.sync import async_to_sync
@@ -216,7 +215,7 @@ def update_document_archive_file(document_id):
 
     mime_type = document.mime_type
 
-    parser_class: Type[DocumentParser] = get_parser_class_for_mime_type(mime_type)
+    parser_class: type[DocumentParser] = get_parser_class_for_mime_type(mime_type)
 
     if not parser_class:
         logger.error(

src/documents/tests/test_api.py

@@ -7,18 +7,13 @@ import tempfile
 import urllib.request
 import uuid
 import zipfile
+import zoneinfo
 from datetime import timedelta
 from pathlib import Path
 from unittest import mock
 from unittest.mock import MagicMock
 
 import celery
-
-try:
-    import zoneinfo
-except ImportError:
-    from backports import zoneinfo
-
 import pytest
 from dateutil.relativedelta import relativedelta
 from django.conf import settings

src/documents/tests/test_consumer.py

@@ -5,16 +5,11 @@ import shutil
 import stat
 import tempfile
 import uuid
+import zoneinfo
 from unittest import mock
 from unittest.mock import MagicMock
 
 from dateutil import tz
-
-try:
-    import zoneinfo
-except ImportError:
-    from backports import zoneinfo
-
 from django.conf import settings
 from django.test import TestCase
 from django.test import override_settings

src/documents/tests/test_document_model.py

@@ -1,13 +1,9 @@
 import shutil
 import tempfile
+import zoneinfo
 from pathlib import Path
 from unittest import mock
 
-try:
-    import zoneinfo
-except ImportError:
-    from backports import zoneinfo
-
 from django.test import TestCase
 from django.test import override_settings
 from django.utils import timezone

src/documents/tests/test_matchables.py

@@ -1,7 +1,7 @@
 import shutil
 import tempfile
+from collections.abc import Iterable
 from random import randint
-from typing import Iterable
 
 from django.contrib.admin.models import LogEntry
 from django.contrib.auth.models import User

src/documents/tests/test_migration_encrypted_webp_conversion.py

@@ -1,9 +1,9 @@
 import importlib
 import shutil
 import tempfile
+from collections.abc import Iterable
 from pathlib import Path
 from typing import Callable
-from typing import Iterable
 from typing import Union
 from unittest import mock
 

src/documents/tests/test_migration_webp_conversion.py

@@ -1,9 +1,9 @@
 import importlib
 import shutil
 import tempfile
+from collections.abc import Iterable
 from pathlib import Path
 from typing import Callable
-from typing import Iterable
 from typing import Union
 from unittest import mock
 

src/documents/tests/utils.py

@@ -3,14 +3,12 @@ import tempfile
 import time
 import warnings
 from collections import namedtuple
+from collections.abc import Iterator
 from contextlib import contextmanager
 from os import PathLike
 from pathlib import Path
 from typing import Any
 from typing import Callable
-from typing import Iterator
-from typing import List
-from typing import Tuple
 from typing import Union
 from unittest import mock
 
@@ -88,10 +86,10 @@ def paperless_environment():
 
 def util_call_with_backoff(
     method_or_callable: Callable,
-    args: Union[List, Tuple],
+    args: Union[list, tuple],
     *,
     skip_on_50x_err=True,
-) -> Tuple[bool, Any]:
+) -> tuple[bool, Any]:
     """
     For whatever reason, the images started during the test pipeline like to
     segfault sometimes, crash and otherwise fail randomly, when run with the
@@ -219,7 +217,7 @@ class DocumentConsumeDelayMixin:
 
     def get_last_consume_delay_call_args(
         self,
-    ) -> Tuple[ConsumableDocument, DocumentMetadataOverrides]:
+    ) -> tuple[ConsumableDocument, DocumentMetadataOverrides]:
         """
         Returns the most recent arguments to the async task
         """
@@ -233,7 +231,7 @@ class DocumentConsumeDelayMixin:
 
     def get_all_consume_delay_call_args(
         self,
-    ) -> Iterator[Tuple[ConsumableDocument, DocumentMetadataOverrides]]:
+    ) -> Iterator[tuple[ConsumableDocument, DocumentMetadataOverrides]]:
         """
         Iterates over all calls to the async task and returns the arguments
         """
@@ -246,7 +244,7 @@ class DocumentConsumeDelayMixin:
     def get_specific_consume_delay_call_args(
         self,
         index: int,
-    ) -> Iterator[Tuple[ConsumableDocument, DocumentMetadataOverrides]]:
+    ) -> Iterator[tuple[ConsumableDocument, DocumentMetadataOverrides]]:
         """
         Returns the arguments of a specific call to the async task
         """

src/documents/utils.py

@@ -1,14 +1,13 @@
 import shutil
 from os import utime
 from pathlib import Path
-from typing import Tuple
 from typing import Union
 
 
 def _coerce_to_path(
     source: Union[Path, str],
     dest: Union[Path, str],
-) -> Tuple[Path, Path]:
+) -> tuple[Path, Path]:
     return Path(source).resolve(), Path(dest).resolve()
 
 

src/paperless/checks.py

@@ -155,10 +155,8 @@ def settings_values_check(app_configs, **kwargs):
         """
         Validates the user provided timezone is a valid timezone
         """
-        try:
-            import zoneinfo
-        except ImportError:  # pragma: nocover
-            from backports import zoneinfo
+        import zoneinfo
+
         msgs = []
         if settings.TIME_ZONE not in zoneinfo.available_timezones():
             msgs.append(

src/paperless/settings.py

@@ -7,12 +7,8 @@ import re
 import tempfile
 from os import PathLike
 from pathlib import Path
-from typing import Dict
 from typing import Final
-from typing import List
 from typing import Optional
-from typing import Set
-from typing import Tuple
 from typing import Union
 from urllib.parse import urlparse
 
@@ -85,9 +81,9 @@ def __get_path(
 
 def __get_list(
     key: str,
-    default: Optional[List[str]] = None,
+    default: Optional[list[str]] = None,
     sep: str = ",",
-) -> List[str]:
+) -> list[str]:
     """
     Return a list of elements from the environment, as separated by the given
     string, or the default if the key does not exist
@@ -100,7 +96,7 @@ def __get_list(
         return []
 
 
-def _parse_redis_url(env_redis: Optional[str]) -> Tuple[str]:
+def _parse_redis_url(env_redis: Optional[str]) -> tuple[str]:
     """
     Gets the Redis information from the environment or a default and handles
     converting from incompatible django_channels and celery formats.
@@ -138,7 +134,7 @@ def _parse_redis_url(env_redis: Optional[str]) -> Tuple[str]:
     return (env_redis, env_redis)
 
 
-def _parse_beat_schedule() -> Dict:
+def _parse_beat_schedule() -> dict:
     """
     Configures the scheduled tasks, according to default or
     environment variables.  Task expiration is configured so the task will
@@ -492,7 +488,7 @@ EMAIL_CERTIFICATE_FILE = __get_path("PAPERLESS_EMAIL_CERTIFICATE_FILE")
 ###############################################################################
 # Database                                                                    #
 ###############################################################################
-def _parse_db_settings() -> Dict:
+def _parse_db_settings() -> dict:
     databases = {
         "default": {
             "ENGINE": "django.db.backends.sqlite3",
@@ -928,7 +924,7 @@ if TIKA_ENABLED:
 def _parse_ignore_dates(
     env_ignore: str,
     date_order: str = DATE_ORDER,
-) -> Set[datetime.datetime]:
+) -> set[datetime.datetime]:
     """
     If the PAPERLESS_IGNORE_DATES environment variable is set, parse the
     user provided string(s) into dates
@@ -957,7 +953,7 @@ def _parse_ignore_dates(
 
 
 # List dates that should be ignored when trying to parse date from document text
-IGNORE_DATES: Set[datetime.date] = set()
+IGNORE_DATES: set[datetime.date] = set()
 
 if os.getenv("PAPERLESS_IGNORE_DATES") is not None:
     IGNORE_DATES = _parse_ignore_dates(os.getenv("PAPERLESS_IGNORE_DATES"))

src/paperless/version.py

@@ -1,7 +1,6 @@
 from typing import Final
-from typing import Tuple
 
-__version__: Final[Tuple[int, int, int]] = (1, 17, 4)
+__version__: Final[tuple[int, int, int]] = (1, 17, 4)
 # Version string like X.Y.Z
 __full_version_str__: Final[str] = ".".join(map(str, __version__))
 # Version string like X.Y

src/paperless_mail/mail.py

@@ -8,8 +8,6 @@ import traceback
 from datetime import date
 from datetime import timedelta
 from fnmatch import fnmatch
-from typing import Dict
-from typing import List
 from typing import Union
 
 import magic
@@ -80,7 +78,7 @@ class BaseMailAction:
     read mails when the action is to mark mails as read).
     """
 
-    def get_criteria(self) -> Union[Dict, LogicOperator]:
+    def get_criteria(self) -> Union[dict, LogicOperator]:
         """
         Returns filtering criteria/query for this mail action.
         """
@@ -232,7 +230,7 @@ def mailbox_login(mailbox: MailBox, account: MailAccount):
 
 @shared_task
 def apply_mail_action(
-    result: List[str],
+    result: list[str],
     rule_id: int,
     message_uid: str,
     message_subject: str,
@@ -319,7 +317,7 @@ def error_callback(
 
 def queue_consumption_tasks(
     *,
-    consume_tasks: List[Signature],
+    consume_tasks: list[Signature],
     rule: MailRule,
     message: MailMessage,
 ):

src/paperless_mail/parsers.py

@@ -1,7 +1,6 @@
 import re
 from html import escape
 from pathlib import Path
-from typing import List
 
 import httpx
 from bleach import clean
@@ -355,7 +354,7 @@ class MailDocumentParser(DocumentParser):
     def generate_pdf_from_html(
         self,
         orig_html: str,
-        attachments: List[MailAttachment],
+        attachments: list[MailAttachment],
     ) -> Path:
         """
         Generates a PDF file based on the HTML and attachments of the email

src/paperless_mail/tests/test_mail.py

@@ -3,8 +3,7 @@ import email.contentmanager
 import random
 import uuid
 from collections import namedtuple
-from typing import ContextManager
-from typing import List
+from contextlib import AbstractContextManager
 from typing import Optional
 from typing import Union
 from unittest import mock
@@ -53,8 +52,8 @@ class BogusFolderManager:
 
 class BogusClient:
     def __init__(self, messages):
-        self.messages: List[MailMessage] = messages
-        self.capabilities: List[str] = []
+        self.messages: list[MailMessage] = messages
+        self.capabilities: list[str] = []
 
     def __enter__(self):
         return self
@@ -78,7 +77,7 @@ class BogusClient:
                         MailMessage.flags.fget.cache_clear()
 
 
-class BogusMailBox(ContextManager):
+class BogusMailBox(AbstractContextManager):
     # Common values so tests don't need to remember an accepted login
     USERNAME: str = "admin"
     ASCII_PASSWORD: str = "secret"
@@ -88,8 +87,8 @@ class BogusMailBox(ContextManager):
     ACCESS_TOKEN = "ea7e075cd3acf2c54c48e600398d5d5a"
 
     def __init__(self):
-        self.messages: List[MailMessage] = []
-        self.messages_spam: List[MailMessage] = []
+        self.messages: list[MailMessage] = []
+        self.messages_spam: list[MailMessage] = []
         self.folder = BogusFolderManager()
         self.client = BogusClient(self.messages)
         self._host = ""
@@ -221,11 +220,11 @@ class TestMail(
 
     def create_message(
         self,
-        attachments: Union[int, List[_AttachmentDef]] = 1,
+        attachments: Union[int, list[_AttachmentDef]] = 1,
         body: str = "",
         subject: str = "the subject",
         from_: str = "noone@mail.com",
-        to: Optional[List[str]] = None,
+        to: Optional[list[str]] = None,
         seen: bool = False,
         flagged: bool = False,
         processed: bool = False,
@@ -1056,6 +1055,7 @@ class TestMail(
             ],
         )
 
+    @pytest.mark.flaky(reruns=4)
     def test_filters(self):
         account = MailAccount.objects.create(
             name="test3",
@@ -1203,7 +1203,7 @@ class TestMail(
         self.assertEqual(len(self.bogus_mailbox.fetch("UNSEEN", False)), 0)
         self.assertEqual(len(self.bogus_mailbox.messages), 3)
 
-    def assert_queue_consumption_tasks_call_args(self, expected_call_args: List):
+    def assert_queue_consumption_tasks_call_args(self, expected_call_args: list):
         """
         Verifies that queue_consumption_tasks has been called with the expected arguments.
 

src/paperless_tesseract/tests/test_parser.py

@@ -2,8 +2,8 @@ import os
 import shutil
 import tempfile
 import uuid
+from contextlib import AbstractContextManager
 from pathlib import Path
-from typing import ContextManager
 from unittest import mock
 
 from django.test import TestCase
@@ -29,7 +29,7 @@ def fake_convert(input_file, output_file, **kwargs):
             f2.write(line.strip())
 
 
-class FakeImageFile(ContextManager):
+class FakeImageFile(AbstractContextManager):
     def __init__(self, fname):
         self.fname = fname
 

src/paperless_tika/tests/test_tika_parser.py

@@ -1,13 +1,9 @@
 import datetime
 import os
+import zoneinfo
 from pathlib import Path
 from unittest import mock
 
-try:
-    import zoneinfo
-except ImportError:
-    from backports import zoneinfo
-
 from django.test import TestCase
 from django.test import override_settings
 from httpx import Request