Chore: Adds additional rules for Ruff linter (#5660)

.ruff.toml

@@ -1,7 +1,29 @@
-# https://beta.ruff.rs/docs/settings/
+# https://docs.astral.sh/ruff/settings/
-# https://beta.ruff.rs/docs/rules/
+# https://docs.astral.sh/ruff/rules/
-extend-select = ["I", "W", "UP", "COM", "DJ", "EXE", "ISC", "ICN", "G201", "INP", "PIE", "RSE", "SIM", "TID", "PLC", "PLE", "RUF"]
+extend-select = [
-# TODO PTH
+  "W",     # https://docs.astral.sh/ruff/rules/#pycodestyle-e-w
+  "I",     # https://docs.astral.sh/ruff/rules/#isort-i
+  "UP",    # https://docs.astral.sh/ruff/rules/#pyupgrade-up
+  "COM",   # https://docs.astral.sh/ruff/rules/#flake8-commas-com
+  "DJ",    # https://docs.astral.sh/ruff/rules/#flake8-django-dj
+  "EXE",   # https://docs.astral.sh/ruff/rules/#flake8-executable-exe
+  "ISC",   # https://docs.astral.sh/ruff/rules/#flake8-implicit-str-concat-isc
+  "ICN",   # https://docs.astral.sh/ruff/rules/#flake8-import-conventions-icn
+  "G201",  # https://docs.astral.sh/ruff/rules/#flake8-logging-format-g
+  "INP",   # https://docs.astral.sh/ruff/rules/#flake8-no-pep420-inp
+  "PIE",   # https://docs.astral.sh/ruff/rules/#flake8-pie-pie
+  "Q",     # https://docs.astral.sh/ruff/rules/#flake8-quotes-q
+  "RSE",   # https://docs.astral.sh/ruff/rules/#flake8-raise-rse
+  "T20",   # https://docs.astral.sh/ruff/rules/#flake8-print-t20
+  "SIM",   # https://docs.astral.sh/ruff/rules/#flake8-simplify-sim
+  "TID",   # https://docs.astral.sh/ruff/rules/#flake8-tidy-imports-tid
+  "TCH",   # https://docs.astral.sh/ruff/rules/#flake8-type-checking-tch
+  "PLC",   # https://docs.astral.sh/ruff/rules/#pylint-pl
+  "PLE",   # https://docs.astral.sh/ruff/rules/#pylint-pl
+  "RUF",   # https://docs.astral.sh/ruff/rules/#ruff-specific-rules-ruf
+  "FLY",   # https://docs.astral.sh/ruff/rules/#flynt-fly
+]
+# TODO PTH https://docs.astral.sh/ruff/rules/#flake8-use-pathlib-pth
 ignore = ["DJ001", "SIM105", "RUF012"]
 fix = true
 line-length = 88
@@ -13,9 +35,9 @@ show-fixes = true
 
 [per-file-ignores]
 ".github/scripts/*.py" = ["E501", "INP001", "SIM117"]
-"docker/wait-for-redis.py" = ["INP001"]
+"docker/wait-for-redis.py" = ["INP001", "T201"]
 "*/tests/*.py" = ["E501", "SIM117"]
-"*/migrations/*.py" = ["E501", "SIM"]
+"*/migrations/*.py" = ["E501", "SIM", "T201"]
 "src/paperless_tesseract/tests/test_parser.py" = ["RUF001"]
 "src/documents/models.py" = ["SIM115"]
 

src/documents/caching.py

@@ -90,7 +90,6 @@ def set_suggestions_cache(
     """
     if classifier is not None:
         doc_key = get_suggestion_cache_key(document_id)
-        print(classifier.last_auto_type_hash)
         cache.set(
             doc_key,
             SuggestionCacheData(

src/documents/classifier.py

@@ -4,11 +4,14 @@ 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 TYPE_CHECKING
 from typing import Optional
 
+if TYPE_CHECKING:
+    from datetime import datetime
+    from pathlib import Path
+
 from django.conf import settings
 from django.core.cache import cache
 from sklearn.exceptions import InconsistentVersionWarning

src/documents/management/commands/document_retagger.py

@@ -69,8 +69,6 @@ class Command(ProgressBarMixin, BaseCommand):
 
     def handle(self, *args, **options):
         self.handle_progress_bar_mixin(**options)
-        # Detect if we support color
-        color = self.style.ERROR("test") != "test"
 
         if options["inbox_only"]:
             queryset = Document.objects.filter(tags__is_inbox_tag=True)
@@ -96,7 +94,8 @@ class Command(ProgressBarMixin, BaseCommand):
                     use_first=options["use_first"],
                     suggest=options["suggest"],
                     base_url=options["base_url"],
-                    color=color,
+                    stdout=self.stdout,
+                    style_func=self.style,
                 )
 
             if options["document_type"]:
@@ -108,7 +107,8 @@ class Command(ProgressBarMixin, BaseCommand):
                     use_first=options["use_first"],
                     suggest=options["suggest"],
                     base_url=options["base_url"],
-                    color=color,
+                    stdout=self.stdout,
+                    style_func=self.style,
                 )
 
             if options["tags"]:
@@ -119,7 +119,8 @@ class Command(ProgressBarMixin, BaseCommand):
                     replace=options["overwrite"],
                     suggest=options["suggest"],
                     base_url=options["base_url"],
-                    color=color,
+                    stdout=self.stdout,
+                    style_func=self.style,
                 )
             if options["storage_path"]:
                 set_storage_path(
@@ -130,5 +131,6 @@ class Command(ProgressBarMixin, BaseCommand):
                     use_first=options["use_first"],
                     suggest=options["suggest"],
                     base_url=options["base_url"],
-                    color=color,
+                    stdout=self.stdout,
+                    style_func=self.style,
                 )

src/documents/management/commands/document_thumbnails.py

@@ -19,7 +19,7 @@ def _process_document(doc_id):
     if parser_class:
         parser = parser_class(logging_group=None)
     else:
-        print(f"{document} No parser for mime type {document.mime_type}")
+        print(f"{document} No parser for mime type {document.mime_type}")  # noqa: T201
         return
 
     try:

src/documents/plugins/helpers.py

@@ -5,7 +5,9 @@ from typing import Union
 
 from asgiref.sync import async_to_sync
 from channels.layers import get_channel_layer
-from channels_redis.pubsub import RedisPubSubChannelLayer
+
+if TYPE_CHECKING:
+    from channels_redis.pubsub import RedisPubSubChannelLayer
 
 
 class ProgressStatusOptions(str, enum.Enum):

src/documents/signals/handlers.py

@@ -18,7 +18,6 @@ from django.db import close_old_connections
 from django.db import models
 from django.db.models import Q
 from django.dispatch import receiver
-from django.utils import termcolors
 from django.utils import timezone
 from filelock import FileLock
 
@@ -54,6 +53,26 @@ def add_inbox_tags(sender, document: Document, logging_group=None, **kwargs):
     document.tags.add(*inbox_tags)
 
 
+def _suggestion_printer(
+    stdout,
+    style_func,
+    suggestion_type: str,
+    document: Document,
+    selected: MatchingModel,
+    base_url: Optional[str] = None,
+):
+    """
+    Smaller helper to reduce duplication when just outputting suggestions to the console
+    """
+    doc_str = str(document)
+    if base_url is not None:
+        stdout.write(style_func.SUCCESS(doc_str))
+        stdout.write(style_func.SUCCESS(f"{base_url}/documents/{document.pk}"))
+    else:
+        stdout.write(style_func.SUCCESS(f"{doc_str} [{document.pk}]"))
+    stdout.write(f"Suggest {suggestion_type}: {selected}")
+
+
 def set_correspondent(
     sender,
     document: Document,
@@ -63,7 +82,8 @@ def set_correspondent(
     use_first=True,
     suggest=False,
     base_url=None,
-    color=False,
+    stdout=None,
+    style_func=None,
     **kwargs,
 ):
     if document.correspondent and not replace:
@@ -90,23 +110,14 @@ def set_correspondent(
 
     if selected or replace:
         if suggest:
-            if base_url:
+            _suggestion_printer(
-                print(
+                stdout,
-                    termcolors.colorize(str(document), fg="green")
+                style_func,
-                    if color
+                "correspondent",
-                    else str(document),
+                document,
-                )
+                selected,
-                print(f"{base_url}/documents/{document.pk}")
+                base_url,
-            else:
+            )
-                print(
-                    (
-                        termcolors.colorize(str(document), fg="green")
-                        if color
-                        else str(document)
-                    )
-                    + f" [{document.pk}]",
-                )
-            print(f"Suggest correspondent {selected}")
         else:
             logger.info(
                 f"Assigning correspondent {selected} to {document}",
@@ -126,7 +137,8 @@ def set_document_type(
     use_first=True,
     suggest=False,
     base_url=None,
-    color=False,
+    stdout=None,
+    style_func=None,
     **kwargs,
 ):
     if document.document_type and not replace:
@@ -154,23 +166,14 @@ def set_document_type(
 
     if selected or replace:
         if suggest:
-            if base_url:
+            _suggestion_printer(
-                print(
+                stdout,
-                    termcolors.colorize(str(document), fg="green")
+                style_func,
-                    if color
+                "document type",
-                    else str(document),
+                document,
-                )
+                selected,
-                print(f"{base_url}/documents/{document.pk}")
+                base_url,
-            else:
+            )
-                print(
-                    (
-                        termcolors.colorize(str(document), fg="green")
-                        if color
-                        else str(document)
-                    )
-                    + f" [{document.pk}]",
-                )
-            print(f"Suggest document type {selected}")
         else:
             logger.info(
                 f"Assigning document type {selected} to {document}",
@@ -189,7 +192,8 @@ def set_tags(
     replace=False,
     suggest=False,
     base_url=None,
-    color=False,
+    stdout=None,
+    style_func=None,
     **kwargs,
 ):
     if replace:
@@ -212,26 +216,16 @@ def set_tags(
         ]
         if not relevant_tags and not extra_tags:
             return
+        doc_str = style_func.SUCCESS(str(document))
         if base_url:
-            print(
+            stdout.write(doc_str)
-                termcolors.colorize(str(document), fg="green")
+            stdout.write(f"{base_url}/documents/{document.pk}")
-                if color
-                else str(document),
-            )
-            print(f"{base_url}/documents/{document.pk}")
         else:
-            print(
+            stdout.write(doc_str + style_func.SUCCESS(f" [{document.pk}]"))
-                (
-                    termcolors.colorize(str(document), fg="green")
-                    if color
-                    else str(document)
-                )
-                + f" [{document.pk}]",
-            )
         if relevant_tags:
-            print("Suggest tags: " + ", ".join([t.name for t in relevant_tags]))
+            stdout.write("Suggest tags: " + ", ".join([t.name for t in relevant_tags]))
         if extra_tags:
-            print("Extra tags: " + ", ".join([t.name for t in extra_tags]))
+            stdout.write("Extra tags: " + ", ".join([t.name for t in extra_tags]))
     else:
         if not relevant_tags:
             return
@@ -254,7 +248,8 @@ def set_storage_path(
     use_first=True,
     suggest=False,
     base_url=None,
-    color=False,
+    stdout=None,
+    style_func=None,
     **kwargs,
 ):
     if document.storage_path and not replace:
@@ -285,23 +280,14 @@ def set_storage_path(
 
     if selected or replace:
         if suggest:
-            if base_url:
+            _suggestion_printer(
-                print(
+                stdout,
-                    termcolors.colorize(str(document), fg="green")
+                style_func,
-                    if color
+                "storage directory",
-                    else str(document),
+                document,
-                )
+                selected,
-                print(f"{base_url}/documents/{document.pk}")
+                base_url,
-            else:
+            )
-                print(
-                    (
-                        termcolors.colorize(str(document), fg="green")
-                        if color
-                        else str(document)
-                    )
-                    + f" [{document.pk}]",
-                )
-            print(f"Suggest storage directory {selected}")
         else:
             logger.info(
                 f"Assigning storage path {selected} to {document}",

src/documents/tests/test_api_bulk_download.py

@@ -246,8 +246,6 @@ class TestBulkDownload(DirectoriesMixin, APITestCase):
 
         self.doc3.title = "Title 2 - Doc 3"
         self.doc3.save()
-        print(self.doc3.archive_path)
-        print(self.doc3.archive_filename)
 
         response = self.client.post(
             self.ENDPOINT,

src/documents/tests/test_management_consumer.py

@@ -88,10 +88,10 @@ class ConsumerThreadMixin(DocumentConsumeDelayMixin):
     ):
         eq = filecmp.cmp(input_doc.original_file, self.sample_file, shallow=False)
         if not eq:
-            print("Consumed an INVALID file.")
+            print("Consumed an INVALID file.")  # noqa: T201
             raise ConsumerError("Incomplete File READ FAILED")
         else:
-            print("Consumed a perfectly valid file.")
+            print("Consumed a perfectly valid file.")  # noqa: T201
 
     def slow_write_file(self, target, incomplete=False):
         with open(self.sample_file, "rb") as f:
@@ -102,11 +102,11 @@ class ConsumerThreadMixin(DocumentConsumeDelayMixin):
 
         with open(target, "wb") as f:
             # this will take 2 seconds, since the file is about 20k.
-            print("Start writing file.")
+            print("Start writing file.")  # noqa: T201
             for b in chunked(1000, pdf_bytes):
                 f.write(b)
                 sleep(0.1)
-            print("file completed.")
+            print("file completed.")  # noqa: T201
 
 
 @override_settings(

src/documents/tests/test_management_fuzzy.py

@@ -196,7 +196,7 @@ class TestFuzzyMatchCommand(TestCase):
         self.assertEqual(Document.objects.count(), 3)
 
         stdout, _ = self.call_command("--delete")
-        print(stdout)
+
         lines = [x.strip() for x in stdout.split("\n") if len(x.strip())]
         self.assertEqual(len(lines), 3)
         self.assertEqual(

src/documents/tests/test_workflows.py

@@ -1,16 +1,19 @@
 from datetime import timedelta
 from pathlib import Path
+from typing import TYPE_CHECKING
 from unittest import mock
 
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import User
-from django.db.models import QuerySet
 from django.utils import timezone
 from guardian.shortcuts import assign_perm
 from guardian.shortcuts import get_groups_with_perms
 from guardian.shortcuts import get_users_with_perms
 from rest_framework.test import APITestCase
 
+if TYPE_CHECKING:
+    from django.db.models import QuerySet
+
 from documents import tasks
 from documents.data_models import ConsumableDocument
 from documents.data_models import DocumentSource

src/documents/tests/utils.py

@@ -340,7 +340,6 @@ class DummyProgressManager:
     def __init__(self, filename: str, task_id: Optional[str] = None) -> None:
         self.filename = filename
         self.task_id = task_id
-        print("hello world")
         self.payloads = []
 
     def __enter__(self):

src/paperless/auth.py

@@ -1,3 +1,5 @@
+import logging
+
 from django.conf import settings
 from django.contrib import auth
 from django.contrib.auth.middleware import PersistentRemoteUserMiddleware
@@ -6,6 +8,8 @@ from django.http import HttpRequest
 from django.utils.deprecation import MiddlewareMixin
 from rest_framework import authentication
 
+logger = logging.getLogger("paperless.auth")
+
 
 class AutoLoginMiddleware(MiddlewareMixin):
     def process_request(self, request: HttpRequest):
@@ -35,7 +39,7 @@ class AngularApiAuthenticationOverride(authentication.BaseAuthentication):
             and request.headers["Referer"].startswith("http://localhost:4200/")
         ):
             user = User.objects.filter(is_staff=True).first()
-            print(f"Auto-Login with user {user}")
+            logger.debug(f"Auto-Login with user {user}")
             return (user, None)
         else:
             return None