Fix: text parser get_parser forwards logging_group, drops progress_callback

TextDocumentParser.__init__ accepts logging_group: object = None, same
as RemoteDocumentParser. The old shim incorrectly dropped it; fix to
forward it as a positional arg and only drop progress_callback.
Add type annotations and from __future__ import annotations for
consistency with the remote parser signals shim.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

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

@@ -10,12 +10,10 @@ cd "${PAPERLESS_SRC_DIR}"
 
 # The whole migrate, with flock, needs to run as the right user
 if [[ -n "${USER_IS_NON_ROOT}" ]]; then
-	exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py check --tag compatibility paperless
+	python3 manage.py check --tag compatibility paperless || exit 1
 	exec s6-setlock -n "${data_dir}/migration_lock" python3 manage.py migrate --skip-checks --no-input
 else
-	exec s6-setuidgid paperless \
-		s6-setlock -n "${data_dir}/migration_lock" \
-		python3 manage.py check --tag compatibility paperless
+	s6-setuidgid paperless python3 manage.py check --tag compatibility paperless  || exit 1
 	exec s6-setuidgid paperless \
 		s6-setlock -n "${data_dir}/migration_lock" \
 		python3 manage.py migrate --skip-checks --no-input

docs/configuration.md

@@ -1947,12 +1947,6 @@ current backend. If not supplied, defaults to "gpt-3.5-turbo" for OpenAI and "ll
 
     Defaults to None.
 
-#### [`PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS=<bool>`](#PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS) {#PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS}
-
-: If set to false, Paperless blocks AI endpoint URLs that resolve to non-public addresses (e.g., localhost, etc).
-
-    Defaults to true, which allows internal endpoints.
-
 #### [`PAPERLESS_AI_LLM_INDEX_TASK_CRON=<cron expression>`](#PAPERLESS_AI_LLM_INDEX_TASK_CRON) {#PAPERLESS_AI_LLM_INDEX_TASK_CRON}
 
 : Configures the schedule to update the AI embeddings of text content and metadata for all documents. Only performed if

pyproject.toml

@@ -42,10 +42,10 @@ dependencies = [
   "djangorestframework~=3.16",
   "djangorestframework-guardian~=0.4.0",
   "drf-spectacular~=0.28",
-  "drf-spectacular-sidecar~=2026.1.1",
+  "drf-spectacular-sidecar~=2026.3.1",
   "drf-writable-nested~=0.7.1",
   "faiss-cpu>=1.10",
-  "filelock~=3.20.3",
+  "filelock~=3.25.2",
   "flower~=2.0.1",
   "gotenberg-client~=0.13.1",
   "httpx-oauth~=0.16",
@@ -60,7 +60,7 @@ dependencies = [
   "llama-index-llms-openai>=0.6.13",
   "llama-index-vector-stores-faiss>=0.5.2",
   "nltk~=3.9.1",
-  "ocrmypdf~=16.13.0",
+  "ocrmypdf~=17.3.0",
   "openai>=1.76",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",
@@ -72,7 +72,7 @@ dependencies = [
   "rapidfuzz~=3.14.0",
   "redis[hiredis]~=5.2.1",
   "regex>=2025.9.18",
-  "scikit-learn~=1.7.0",
+  "scikit-learn~=1.8.0",
   "sentence-transformers>=4.1",
   "setproctitle~=1.3.4",
   "tika-client~=0.10.0",
@@ -111,7 +111,7 @@ docs = [
 testing = [
   "daphne",
   "factory-boy~=3.3.1",
-  "faker~=40.5.1",
+  "faker~=40.8.0",
   "imagehash",
   "pytest~=9.0.0",
   "pytest-cov~=7.0.0",

src/documents/consumer.py

@@ -51,11 +51,29 @@ from documents.templating.workflows import parse_w_workflow_placeholders
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.text import TextDocumentParser
 from paperless_mail.parsers import MailDocumentParser
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
 
 
+def _parser_cleanup(parser: DocumentParser) -> None:
+    """
+    Call cleanup on a parser, handling the new-style context-manager parsers.
+
+    New-style parsers (e.g. TextDocumentParser) use __exit__ for teardown
+    instead of a cleanup() method.  This shim will be removed once all existing parsers
+    have switched to the new style and this consumer is updated to use it
+
+    TODO(stumpylog): Remove me in the future
+    """
+    if isinstance(parser, (TextDocumentParser, RemoteDocumentParser)):
+        parser.__exit__(None, None, None)
+    else:
+        parser.cleanup()
+
+
 class WorkflowTriggerPlugin(
     NoCleanupPluginMixin,
     NoSetupPluginMixin,
@@ -459,6 +477,12 @@ class ConsumerPlugin(
                     self.filename,
                     self.input_doc.mailrule_id,
                 )
+            elif isinstance(
+                document_parser,
+                (TextDocumentParser, RemoteDocumentParser),
+            ):
+                # TODO(stumpylog): Remove me in the future
+                document_parser.parse(self.working_copy, mime_type)
             else:
                 document_parser.parse(self.working_copy, mime_type, self.filename)
 
@@ -469,11 +493,15 @@ class ConsumerPlugin(
                 ProgressStatusOptions.WORKING,
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
-            thumbnail = document_parser.get_thumbnail(
-                self.working_copy,
-                mime_type,
-                self.filename,
-            )
+            if isinstance(document_parser, (TextDocumentParser, RemoteDocumentParser)):
+                # TODO(stumpylog): Remove me in the future
+                thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
+            else:
+                thumbnail = document_parser.get_thumbnail(
+                    self.working_copy,
+                    mime_type,
+                    self.filename,
+                )
 
             text = document_parser.get_text()
             date = document_parser.get_date()
@@ -490,7 +518,7 @@ class ConsumerPlugin(
             page_count = document_parser.get_page_count(self.working_copy, mime_type)
 
         except ParseError as e:
-            document_parser.cleanup()
+            _parser_cleanup(document_parser)
             if tempdir:
                 tempdir.cleanup()
             self._fail(
@@ -500,7 +528,7 @@ class ConsumerPlugin(
                 exception=e,
             )
         except Exception as e:
-            document_parser.cleanup()
+            _parser_cleanup(document_parser)
             if tempdir:
                 tempdir.cleanup()
             self._fail(
@@ -702,7 +730,7 @@ class ConsumerPlugin(
                 exception=e,
             )
         finally:
-            document_parser.cleanup()
+            _parser_cleanup(document_parser)
             tempdir.cleanup()
 
         self.run_post_consume_script(document)

src/documents/management/commands/document_thumbnails.py

@@ -30,6 +30,7 @@ def _process_document(doc_id: int) -> None:
         )
         shutil.move(thumb, document.thumbnail_path)
     finally:
+        # TODO(stumpylog): Cleanup once all parsers are handled
         parser.cleanup()
 
 

src/documents/tasks.py

@@ -399,6 +399,7 @@ def update_document_content_maybe_archive_file(document_id) -> None:
             f"Error while parsing document {document} (ID: {document_id})",
         )
     finally:
+        # TODO(stumpylog): Cleanup once all parsers are handled
         parser.cleanup()
 
 

src/documents/tests/test_api_app_config.py

@@ -5,7 +5,6 @@ from unittest.mock import patch
 
 from django.contrib.auth.models import User
 from django.core.files.uploadedfile import SimpleUploadedFile
-from django.test import override_settings
 from rest_framework import status
 from rest_framework.test import APITestCase
 
@@ -694,17 +693,3 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
                 content_type="application/json",
             )
             mock_update.assert_called_once()
-
-    @override_settings(LLM_ALLOW_INTERNAL_ENDPOINTS=False)
-    def test_update_llm_endpoint_blocks_internal_endpoint_when_disallowed(self) -> None:
-        response = self.client.patch(
-            f"{self.ENDPOINT}1/",
-            json.dumps(
-                {
-                    "llm_endpoint": "http://127.0.0.1:11434",
-                },
-            ),
-            content_type="application/json",
-        )
-        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
-        self.assertIn("non-public address", str(response.data).lower())

src/documents/tests/test_parsers.py

@@ -9,8 +9,8 @@ from documents.parsers import get_default_file_extension
 from documents.parsers import get_parser_class_for_mime_type
 from documents.parsers import get_supported_file_extensions
 from documents.parsers import is_file_ext_supported
+from paperless.parsers.text import TextDocumentParser
 from paperless_tesseract.parsers import RasterisedDocumentParser
-from paperless_text.parsers import TextDocumentParser
 from paperless_tika.parsers import TikaDocumentParser
 
 

src/documents/workflows/webhooks.py

@@ -1,14 +1,12 @@
+import ipaddress
 import logging
+import socket
+from urllib.parse import urlparse
 
 import httpx
 from celery import shared_task
 from django.conf import settings
 
-from paperless.network import format_host_for_url
-from paperless.network import is_public_ip
-from paperless.network import resolve_hostname_ips
-from paperless.network import validate_outbound_http_url
-
 logger = logging.getLogger("paperless.workflows.webhooks")
 
 
@@ -36,19 +34,23 @@ class WebhookTransport(httpx.HTTPTransport):
             raise httpx.ConnectError("No hostname in request URL")
 
         try:
-            ips = resolve_hostname_ips(hostname)
-        except ValueError as e:
-            raise httpx.ConnectError(str(e)) from e
+            addr_info = socket.getaddrinfo(hostname, None)
+        except socket.gaierror as e:
+            raise httpx.ConnectError(f"Could not resolve hostname: {hostname}") from e
+
+        ips = [info[4][0] for info in addr_info if info and info[4]]
+        if not ips:
+            raise httpx.ConnectError(f"Could not resolve hostname: {hostname}")
 
         if not self.allow_internal:
             for ip_str in ips:
-                if not is_public_ip(ip_str):
+                if not WebhookTransport.is_public_ip(ip_str):
                     raise httpx.ConnectError(
                         f"Connection blocked: {hostname} resolves to a non-public address",
                     )
 
         ip_str = ips[0]
-        formatted_ip = format_host_for_url(ip_str)
+        formatted_ip = self._format_ip_for_url(ip_str)
 
         new_headers = httpx.Headers(request.headers)
         if "host" in new_headers:
@@ -67,6 +69,40 @@ class WebhookTransport(httpx.HTTPTransport):
 
         return super().handle_request(request)
 
+    def _format_ip_for_url(self, ip: str) -> str:
+        """
+        Format IP address for use in URL (wrap IPv6 in brackets)
+        """
+        try:
+            ip_obj = ipaddress.ip_address(ip)
+            if ip_obj.version == 6:
+                return f"[{ip}]"
+            return ip
+        except ValueError:
+            return ip
+
+    @staticmethod
+    def is_public_ip(ip: str | int) -> bool:
+        try:
+            obj = ipaddress.ip_address(ip)
+            return not (
+                obj.is_private
+                or obj.is_loopback
+                or obj.is_link_local
+                or obj.is_multicast
+                or obj.is_unspecified
+            )
+        except ValueError:  # pragma: no cover
+            return False
+
+    @staticmethod
+    def resolve_first_ip(host: str) -> str | None:
+        try:
+            info = socket.getaddrinfo(host, None)
+            return info[0][4][0] if info else None
+        except Exception:  # pragma: no cover
+            return None
+
 
 @shared_task(
     retry_backoff=True,
@@ -82,24 +118,21 @@ def send_webhook(
     *,
     as_json: bool = False,
 ):
-    try:
-        parsed = validate_outbound_http_url(
-            url,
-            allowed_schemes=settings.WEBHOOKS_ALLOWED_SCHEMES,
-            allowed_ports=settings.WEBHOOKS_ALLOWED_PORTS,
-            # Internal-address checks happen in transport to preserve ConnectError behavior.
-            allow_internal=True,
-        )
-    except ValueError as e:
-        logger.warning("Webhook blocked: %s", e)
-        raise
-
-    hostname = parsed.hostname
-    if hostname is None:  # pragma: no cover
+    p = urlparse(url)
+    if p.scheme.lower() not in settings.WEBHOOKS_ALLOWED_SCHEMES or not p.hostname:
+        logger.warning("Webhook blocked: invalid scheme/hostname")
         raise ValueError("Invalid URL scheme or hostname.")
 
+    port = p.port or (443 if p.scheme == "https" else 80)
+    if (
+        len(settings.WEBHOOKS_ALLOWED_PORTS) > 0
+        and port not in settings.WEBHOOKS_ALLOWED_PORTS
+    ):
+        logger.warning("Webhook blocked: port not permitted")
+        raise ValueError("Destination port not permitted.")
+
     transport = WebhookTransport(
-        hostname=hostname,
+        hostname=p.hostname,
         allow_internal=settings.WEBHOOKS_ALLOW_INTERNAL_REQUESTS,
     )
 

src/paperless/celery.py

@@ -1,6 +1,7 @@
 import os
 
 from celery import Celery
+from celery.signals import worker_process_init
 
 # Set the default Django settings module for the 'celery' program.
 os.environ.setdefault("DJANGO_SETTINGS_MODULE", "paperless.settings")
@@ -15,3 +16,19 @@ app.config_from_object("django.conf:settings", namespace="CELERY")
 
 # Load task modules from all registered Django apps.
 app.autodiscover_tasks()
+
+
+@worker_process_init.connect
+def on_worker_process_init(**kwargs) -> None:  # pragma: no cover
+    """
+    Register built-in parsers eagerly in each Celery worker process.
+
+    This registers only the built-in parsers (no entrypoint discovery) so
+    that workers can begin consuming documents immediately.  Entrypoint
+    discovery for third-party parsers is deferred to the first call of
+    get_parser_registry() inside a task, keeping worker_process_init
+    well within its 4-second timeout budget.
+    """
+    from paperless.parsers.registry import init_builtin_parsers
+
+    init_builtin_parsers()

src/paperless/config.py

@@ -188,7 +188,6 @@ class AIConfig(BaseConfig):
     llm_model: str = dataclasses.field(init=False)
     llm_api_key: str = dataclasses.field(init=False)
     llm_endpoint: str = dataclasses.field(init=False)
-    llm_allow_internal_endpoints: bool = dataclasses.field(init=False)
 
     def __post_init__(self) -> None:
         app_config = self._get_config_instance()
@@ -204,7 +203,6 @@ class AIConfig(BaseConfig):
         self.llm_model = app_config.llm_model or settings.LLM_MODEL
         self.llm_api_key = app_config.llm_api_key or settings.LLM_API_KEY
         self.llm_endpoint = app_config.llm_endpoint or settings.LLM_ENDPOINT
-        self.llm_allow_internal_endpoints = settings.LLM_ALLOW_INTERNAL_ENDPOINTS
 
     @property
     def llm_index_enabled(self) -> bool:

src/paperless/consumers.py

@@ -1,62 +1,51 @@
 import json
 from typing import Any
 
-from asgiref.sync import async_to_sync
-from channels.exceptions import AcceptConnection
-from channels.exceptions import DenyConnection
-from channels.generic.websocket import WebsocketConsumer
+from channels.generic.websocket import AsyncWebsocketConsumer
 
 
-class StatusConsumer(WebsocketConsumer):
-    def _authenticated(self):
-        return "user" in self.scope and self.scope["user"].is_authenticated
+class StatusConsumer(AsyncWebsocketConsumer):
+    def _authenticated(self) -> bool:
+        user: Any = self.scope.get("user")
+        return user is not None and user.is_authenticated
 
-    def _can_view(self, data):
-        user = self.scope.get("user") if self.scope.get("user") else None
+    async def _can_view(self, data: dict[str, Any]) -> bool:
+        user: Any = self.scope.get("user")
+        if user is None:
+            return False
         owner_id = data.get("owner_id")
         users_can_view = data.get("users_can_view", [])
         groups_can_view = data.get("groups_can_view", [])
-        return (
-            user.is_superuser
-            or user.id == owner_id
-            or user.id in users_can_view
-            or any(
-                user.groups.filter(pk=group_id).exists() for group_id in groups_can_view
-            )
-        )
 
-    def connect(self):
+        if user.is_superuser or user.id == owner_id or user.id in users_can_view:
+            return True
+
+        return await user.groups.filter(pk__in=groups_can_view).aexists()
+
+    async def connect(self) -> None:
         if not self._authenticated():
-            raise DenyConnection
-        else:
-            async_to_sync(self.channel_layer.group_add)(
-                "status_updates",
-                self.channel_name,
-            )
-            raise AcceptConnection
+            await self.close()
+            return
+        await self.channel_layer.group_add("status_updates", self.channel_name)
+        await self.accept()
 
-    def disconnect(self, close_code) -> None:
-        async_to_sync(self.channel_layer.group_discard)(
-            "status_updates",
-            self.channel_name,
-        )
+    async def disconnect(self, code: int) -> None:
+        await self.channel_layer.group_discard("status_updates", self.channel_name)
 
-    def status_update(self, event) -> None:
+    async def status_update(self, event: dict[str, Any]) -> None:
         if not self._authenticated():
-            self.close()
-        else:
-            if self._can_view(event["data"]):
-                self.send(json.dumps(event))
+            await self.close()
+        elif await self._can_view(event["data"]):
+            await self.send(json.dumps(event))
 
-    def documents_deleted(self, event) -> None:
+    async def documents_deleted(self, event: dict[str, Any]) -> None:
         if not self._authenticated():
-            self.close()
+            await self.close()
         else:
-            self.send(json.dumps(event))
+            await self.send(json.dumps(event))
 
-    def document_updated(self, event: Any) -> None:
+    async def document_updated(self, event: dict[str, Any]) -> None:
         if not self._authenticated():
-            self.close()
-        else:
-            if self._can_view(event["data"]):
-                self.send(json.dumps(event))
+            await self.close()
+        elif await self._can_view(event["data"]):
+            await self.send(json.dumps(event))

src/paperless/network.py

@@ -1,76 +0,0 @@
-import ipaddress
-import socket
-from collections.abc import Collection
-from urllib.parse import ParseResult
-from urllib.parse import urlparse
-
-
-def is_public_ip(ip: str | int) -> bool:
-    try:
-        obj = ipaddress.ip_address(ip)
-        return not (
-            obj.is_private
-            or obj.is_loopback
-            or obj.is_link_local
-            or obj.is_multicast
-            or obj.is_unspecified
-        )
-    except ValueError:  # pragma: no cover
-        return False
-
-
-def resolve_hostname_ips(hostname: str) -> list[str]:
-    try:
-        addr_info = socket.getaddrinfo(hostname, None)
-    except socket.gaierror as e:
-        raise ValueError(f"Could not resolve hostname: {hostname}") from e
-
-    ips = [info[4][0] for info in addr_info if info and info[4]]
-    if not ips:
-        raise ValueError(f"Could not resolve hostname: {hostname}")
-    return ips
-
-
-def format_host_for_url(host: str) -> str:
-    """
-    Format IP address for URL use (wrap IPv6 in brackets).
-    """
-    try:
-        ip_obj = ipaddress.ip_address(host)
-        if ip_obj.version == 6:
-            return f"[{host}]"
-        return host
-    except ValueError:
-        return host
-
-
-def validate_outbound_http_url(
-    url: str,
-    *,
-    allowed_schemes: Collection[str] = ("http", "https"),
-    allowed_ports: Collection[int] | None = None,
-    allow_internal: bool = False,
-) -> ParseResult:
-    parsed = urlparse(url)
-    scheme = parsed.scheme.lower()
-
-    if scheme not in allowed_schemes or not parsed.hostname:
-        raise ValueError("Invalid URL scheme or hostname.")
-
-    default_port = 443 if scheme == "https" else 80
-    try:
-        port = parsed.port or default_port
-    except ValueError as e:
-        raise ValueError("Invalid URL scheme or hostname.") from e
-
-    if allowed_ports and port not in allowed_ports:
-        raise ValueError("Destination port not permitted.")
-
-    if not allow_internal:
-        for ip_str in resolve_hostname_ips(parsed.hostname):
-            if not is_public_ip(ip_str):
-                raise ValueError(
-                    f"Connection blocked: {parsed.hostname} resolves to a non-public address",
-                )
-
-    return parsed

src/paperless/parsers/__init__.py

@@ -0,0 +1,379 @@
+"""
+Public interface for the Paperless-ngx parser plugin system.
+
+This module defines ParserProtocol — the structural contract that every
+document parser must satisfy, whether it is a built-in parser shipped with
+Paperless-ngx or a third-party parser installed via a Python entrypoint.
+
+Phase 1/2 scope: only the Protocol is defined here. The transitional
+DocumentParser ABC (Phase 3) and concrete built-in parsers (Phase 3+) will
+be added in later phases, so there are intentionally no imports of parser
+implementations here.
+
+Usage example (third-party parser)::
+
+    from paperless.parsers import ParserProtocol
+
+    class MyParser:
+        name = "my-parser"
+        version = "1.0.0"
+        author = "Acme Corp"
+        url = "https://example.com/my-parser"
+
+        @classmethod
+        def supported_mime_types(cls) -> dict[str, str]:
+            return {"application/x-my-format": ".myf"}
+
+        @classmethod
+        def score(cls, mime_type, filename, path=None):
+            return 10
+
+        # … implement remaining protocol methods …
+
+    assert isinstance(MyParser(), ParserProtocol)
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+from typing import Protocol
+from typing import Self
+from typing import TypedDict
+from typing import runtime_checkable
+
+if TYPE_CHECKING:
+    import datetime
+    from pathlib import Path
+    from types import TracebackType
+
+__all__ = [
+    "MetadataEntry",
+    "ParserProtocol",
+]
+
+
+class MetadataEntry(TypedDict):
+    """A single metadata field extracted from a document.
+
+    All four keys are required. Values are always serialised to strings —
+    type-specific conversion (dates, integers, lists) is the responsibility
+    of the parser before returning.
+    """
+
+    namespace: str
+    """URI of the metadata namespace (e.g. 'http://ns.adobe.com/pdf/1.3/')."""
+
+    prefix: str
+    """Conventional namespace prefix (e.g. 'pdf', 'xmp', 'dc')."""
+
+    key: str
+    """Field name within the namespace (e.g. 'Author', 'CreateDate')."""
+
+    value: str
+    """String representation of the field value."""
+
+
+@runtime_checkable
+class ParserProtocol(Protocol):
+    """Structural contract for all Paperless-ngx document parsers.
+
+    Both built-in parsers and third-party plugins (discovered via the
+    "paperless_ngx.parsers" entrypoint group) must satisfy this Protocol.
+    Because it is decorated with runtime_checkable, isinstance(obj,
+    ParserProtocol) works at runtime based on method presence, which is
+    useful for validation in ParserRegistry.discover.
+
+    Parsers must expose four string attributes at the class level so the
+    registry can log attribution information without instantiating the parser:
+
+    name : str
+        Human-readable parser name (e.g. "Tesseract OCR").
+    version : str
+        Semantic version string (e.g. "1.2.3").
+    author : str
+        Author or organisation name.
+    url : str
+        URL for documentation, source code, or issue tracker.
+    """
+
+    # ------------------------------------------------------------------
+    # Class-level identity (checked by the registry, not Protocol methods)
+    # ------------------------------------------------------------------
+
+    name: str
+    version: str
+    author: str
+    url: str
+
+    # ------------------------------------------------------------------
+    # Class methods
+    # ------------------------------------------------------------------
+
+    @classmethod
+    def supported_mime_types(cls) -> dict[str, str]:
+        """Return a mapping of supported MIME types to preferred file extensions.
+
+        The keys are MIME type strings (e.g. "application/pdf"), and the
+        values are the preferred file extension including the leading dot
+        (e.g. ".pdf").  The registry uses this mapping both to decide whether
+        a parser is a candidate for a given file and to determine the default
+        extension when creating archive copies.
+
+        Returns
+        -------
+        dict[str, str]
+            {mime_type: extension} mapping — may be empty if the parser
+            has been temporarily disabled.
+        """
+        ...
+
+    @classmethod
+    def score(
+        cls,
+        mime_type: str,
+        filename: str,
+        path: Path | None = None,
+    ) -> int | None:
+        """Return a priority score for handling this file, or None to decline.
+
+        The registry calls this after confirming that the MIME type is in
+        supported_mime_types. Parsers may inspect filename and optionally
+        the file at path to refine their confidence level.
+
+        A higher score wins. Return None to explicitly decline handling a file
+        even though the MIME type is listed as supported (e.g. when a feature
+        flag is disabled, or a required service is not configured).
+
+        Parameters
+        ----------
+        mime_type:
+            The detected MIME type of the file to be parsed.
+        filename:
+            The original filename, including extension.
+        path:
+            Optional filesystem path to the file. Parsers that need to
+            inspect file content (e.g. magic-byte sniffing) may use this.
+            May be None when scoring happens before the file is available locally.
+
+        Returns
+        -------
+        int | None
+            Priority score (higher wins), or None to decline.
+        """
+        ...
+
+    # ------------------------------------------------------------------
+    # Properties
+    # ------------------------------------------------------------------
+
+    @property
+    def can_produce_archive(self) -> bool:
+        """Whether this parser can produce a searchable PDF archive copy.
+
+        If True, the consumption pipeline may request an archive version when
+        processing the document, subject to the ARCHIVE_FILE_GENERATION
+        setting. If False, only thumbnail and text extraction are performed.
+        """
+        ...
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        """Whether the parser must produce a PDF for the frontend to display.
+
+        True for formats the browser cannot display natively (e.g. DOCX, ODT).
+        When True, the pipeline always stores the PDF output regardless of the
+        ARCHIVE_FILE_GENERATION setting, since the original format cannot be
+        shown to the user.
+        """
+        ...
+
+    # ------------------------------------------------------------------
+    # Core parsing interface
+    # ------------------------------------------------------------------
+
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
+        """Parse document_path and populate internal state.
+
+        After a successful call, callers retrieve results via get_text,
+        get_date, and get_archive_path.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the document file to parse.
+        mime_type:
+            Detected MIME type of the document.
+        produce_archive:
+            When True (the default) and can_produce_archive is also True,
+            the parser should produce a searchable PDF at the path returned
+            by get_archive_path. Pass False when only text extraction and
+            thumbnail generation are required and disk I/O should be minimised.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If parsing fails for any reason.
+        """
+        ...
+
+    # ------------------------------------------------------------------
+    # Result accessors
+    # ------------------------------------------------------------------
+
+    def get_text(self) -> str | None:
+        """Return the plain-text content extracted during parse.
+
+        Returns
+        -------
+        str | None
+            Extracted text, or None if no text could be found.
+        """
+        ...
+
+    def get_date(self) -> datetime.datetime | None:
+        """Return the document date detected during parse.
+
+        Returns
+        -------
+        datetime.datetime | None
+            Detected document date, or None if no date was found.
+        """
+        ...
+
+    def get_archive_path(self) -> Path | None:
+        """Return the path to the generated archive PDF, or None.
+
+        Returns
+        -------
+        Path | None
+            Path to the searchable PDF archive, or None if no archive was
+            produced (e.g. because produce_archive=False or the parser does
+            not support archive generation).
+        """
+        ...
+
+    # ------------------------------------------------------------------
+    # Thumbnail and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+        """Generate and return the path to a thumbnail image for the document.
+
+        May be called independently of parse. The returned path must point to
+        an existing WebP image file inside the parser's temporary working
+        directory.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        Path
+            Path to the generated thumbnail image (WebP format preferred).
+        """
+        ...
+
+    def get_page_count(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> int | None:
+        """Return the number of pages in the document, if determinable.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        int | None
+            Page count, or None if the parser cannot determine it.
+        """
+        ...
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        """Extract format-specific metadata from the document.
+
+        Called by the API view layer on demand — not during the consumption
+        pipeline. Results are returned to the frontend for per-file display.
+
+        For documents with an archive version, this method is called twice:
+        once for the original file (with its native MIME type) and once for
+        the archive file (with ``"application/pdf"``). Parsers that produce
+        archives should handle both cases.
+
+        Implementations must not raise. A failure to read metadata is not
+        fatal — log a warning and return whatever partial results were
+        collected, or ``[]`` if none.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the file to extract metadata from.
+        mime_type:
+            MIME type of the file at ``document_path``. May be
+            ``"application/pdf"`` when called for the archive version.
+
+        Returns
+        -------
+        list[MetadataEntry]
+            Zero or more metadata entries. Returns ``[]`` if no metadata
+            could be extracted or the format does not support it.
+        """
+        ...
+
+    # ------------------------------------------------------------------
+    # Context manager
+    # ------------------------------------------------------------------
+
+    def __enter__(self) -> Self:
+        """Enter the parser context, returning the parser instance.
+
+        Implementations should perform any resource allocation here if not
+        done in __init__ (e.g. creating API clients or temp directories).
+
+        Returns
+        -------
+        Self
+            The parser instance itself.
+        """
+        ...
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        """Exit the parser context and release all resources.
+
+        Implementations must clean up all temporary files and other resources
+        regardless of whether an exception occurred.
+
+        Parameters
+        ----------
+        exc_type:
+            The exception class, or None if no exception was raised.
+        exc_val:
+            The exception instance, or None.
+        exc_tb:
+            The traceback, or None.
+        """
+        ...

src/paperless/parsers/registry.py

@@ -0,0 +1,366 @@
+"""
+Singleton registry that tracks all document parsers available to
+Paperless-ngx — both built-ins shipped with the application and third-party
+plugins installed via Python entrypoints.
+
+Public surface
+--------------
+get_parser_registry
+    Lazy-initialise and return the shared ParserRegistry. This is the primary
+    entry point for production code.
+
+init_builtin_parsers
+    Register built-in parsers only, without entrypoint discovery. Safe to
+    call from Celery worker_process_init where importing all entrypoints
+    would be wasteful or cause side effects.
+
+reset_parser_registry
+    Reset module-level state. For tests only.
+
+Entrypoint group
+----------------
+Third-party parsers must advertise themselves under the
+"paperless_ngx.parsers" entrypoint group in their pyproject.toml::
+
+    [project.entry-points."paperless_ngx.parsers"]
+    my_parser = "my_package.parsers:MyParser"
+
+The loaded class must expose the following attributes at the class level
+(not just on instances) for the registry to accept it:
+name, version, author, url, supported_mime_types (callable), score (callable).
+"""
+
+from __future__ import annotations
+
+import logging
+from importlib.metadata import entry_points
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from paperless.parsers import ParserProtocol
+
+logger = logging.getLogger("paperless.parsers.registry")
+
+# ---------------------------------------------------------------------------
+# Module-level singleton state
+# ---------------------------------------------------------------------------
+
+_registry: ParserRegistry | None = None
+_discovery_complete: bool = False
+
+# Attribute names that every registered external parser class must expose.
+_REQUIRED_ATTRS: tuple[str, ...] = (
+    "name",
+    "version",
+    "author",
+    "url",
+    "supported_mime_types",
+    "score",
+)
+
+
+# ---------------------------------------------------------------------------
+# Module-level accessor functions
+# ---------------------------------------------------------------------------
+
+
+def get_parser_registry() -> ParserRegistry:
+    """Return the shared ParserRegistry instance.
+
+    On the first call this function:
+
+    1. Creates a new ParserRegistry.
+    2. Calls register_defaults to install built-in parsers.
+    3. Calls discover to load third-party plugins via importlib.metadata entrypoints.
+    4. Calls log_summary to emit a startup summary.
+
+    Subsequent calls return the same instance immediately.
+
+    Returns
+    -------
+    ParserRegistry
+        The shared registry singleton.
+    """
+    global _registry, _discovery_complete
+
+    if _registry is None:
+        _registry = ParserRegistry()
+        _registry.register_defaults()
+
+    if not _discovery_complete:
+        _registry.discover()
+        _registry.log_summary()
+        _discovery_complete = True
+
+    return _registry
+
+
+def init_builtin_parsers() -> None:
+    """Register built-in parsers without performing entrypoint discovery.
+
+    Intended for use in Celery worker_process_init handlers where importing
+    all installed entrypoints would be wasteful, slow, or could produce
+    undesirable side effects. Entrypoint discovery (third-party plugins) is
+    deliberately not performed.
+
+    Safe to call multiple times — subsequent calls are no-ops.
+
+    Returns
+    -------
+    None
+    """
+    global _registry
+
+    if _registry is None:
+        _registry = ParserRegistry()
+        _registry.register_defaults()
+
+
+def reset_parser_registry() -> None:
+    """Reset the module-level registry state to its initial values.
+
+    Resets _registry and _discovery_complete so the next call to
+    get_parser_registry will re-initialise everything from scratch.
+
+    FOR TESTS ONLY. Do not call this in production code — resetting the
+    registry mid-request causes all subsequent parser lookups to go through
+    discovery again, which is expensive and may have unexpected side effects
+    in multi-threaded environments.
+
+    Returns
+    -------
+    None
+    """
+    global _registry, _discovery_complete
+
+    _registry = None
+    _discovery_complete = False
+
+
+# ---------------------------------------------------------------------------
+# Registry class
+# ---------------------------------------------------------------------------
+
+
+class ParserRegistry:
+    """Registry that maps MIME types to the best available parser class.
+
+    Parsers are partitioned into two lists:
+
+    _builtins
+        Parser classes registered via register_builtin (populated by
+        register_defaults in Phase 3+).
+
+    _external
+        Parser classes loaded from installed Python entrypoints via discover.
+
+    When resolving a parser for a file, external parsers are evaluated
+    alongside built-in parsers using a uniform scoring mechanism. Both lists
+    are iterated together; the class with the highest score wins. If an
+    external parser wins, its attribution details are logged so users can
+    identify which third-party package handled their document.
+    """
+
+    def __init__(self) -> None:
+        self._external: list[type[ParserProtocol]] = []
+        self._builtins: list[type[ParserProtocol]] = []
+
+    # ------------------------------------------------------------------
+    # Registration
+    # ------------------------------------------------------------------
+
+    def register_builtin(self, parser_class: type[ParserProtocol]) -> None:
+        """Register a built-in parser class.
+
+        Built-in parsers are shipped with Paperless-ngx and are appended to
+        the _builtins list. They are never overridden by external parsers;
+        instead, scoring determines which parser wins for any given file.
+
+        Parameters
+        ----------
+        parser_class:
+            The parser class to register. Must satisfy ParserProtocol.
+        """
+        self._builtins.append(parser_class)
+
+    def register_defaults(self) -> None:
+        """Register the built-in parsers that ship with Paperless-ngx.
+
+        Each parser that has been migrated to the new ParserProtocol interface
+        is registered here.  Parsers are added in ascending weight order so
+        that log output is predictable; scoring determines which parser wins
+        at runtime regardless of registration order.
+        """
+        from paperless.parsers.remote import RemoteDocumentParser
+        from paperless.parsers.text import TextDocumentParser
+
+        self.register_builtin(TextDocumentParser)
+        self.register_builtin(RemoteDocumentParser)
+
+    # ------------------------------------------------------------------
+    # Discovery
+    # ------------------------------------------------------------------
+
+    def discover(self) -> None:
+        """Load third-party parsers from the "paperless_ngx.parsers" entrypoint group.
+
+        For each advertised entrypoint the method:
+
+        1. Calls ep.load() to import the class.
+        2. Validates that the class exposes all required attributes.
+        3. On success, appends the class to _external and logs an info message.
+        4. On failure (import error or missing attributes), logs an appropriate
+           warning/error and continues to the next entrypoint.
+
+        Errors during discovery of a single parser do not prevent other parsers
+        from being loaded.
+
+        Returns
+        -------
+        None
+        """
+        eps = entry_points(group="paperless_ngx.parsers")
+
+        for ep in eps:
+            try:
+                parser_class = ep.load()
+            except Exception:
+                logger.exception(
+                    "Failed to load parser entrypoint '%s' — skipping.",
+                    ep.name,
+                )
+                continue
+
+            missing = [
+                attr for attr in _REQUIRED_ATTRS if not hasattr(parser_class, attr)
+            ]
+            if missing:
+                logger.warning(
+                    "Parser loaded from entrypoint '%s' is missing required "
+                    "attributes %r — skipping.",
+                    ep.name,
+                    missing,
+                )
+                continue
+
+            self._external.append(parser_class)
+            logger.info(
+                "Loaded third-party parser '%s' v%s by %s (entrypoint: '%s').",
+                parser_class.name,
+                parser_class.version,
+                parser_class.author,
+                ep.name,
+            )
+
+    # ------------------------------------------------------------------
+    # Summary logging
+    # ------------------------------------------------------------------
+
+    def log_summary(self) -> None:
+        """Log a startup summary of all registered parsers.
+
+        Built-in parsers are listed first, followed by any external parsers
+        discovered from entrypoints.  If no external parsers were found a
+        short informational message is logged instead of an empty list.
+
+        Returns
+        -------
+        None
+        """
+        logger.info(
+            "Built-in parsers (%d):",
+            len(self._builtins),
+        )
+        for cls in self._builtins:
+            logger.info(
+                "  [built-in] %s v%s — %s",
+                getattr(cls, "name", repr(cls)),
+                getattr(cls, "version", "unknown"),
+                getattr(cls, "url", "built-in"),
+            )
+
+        if not self._external:
+            logger.info("No third-party parsers discovered.")
+            return
+
+        logger.info(
+            "Third-party parsers (%d):",
+            len(self._external),
+        )
+        for cls in self._external:
+            logger.info(
+                "  [external] %s v%s by %s — report issues at %s",
+                getattr(cls, "name", repr(cls)),
+                getattr(cls, "version", "unknown"),
+                getattr(cls, "author", "unknown"),
+                getattr(cls, "url", "unknown"),
+            )
+
+    # ------------------------------------------------------------------
+    # Parser resolution
+    # ------------------------------------------------------------------
+
+    def get_parser_for_file(
+        self,
+        mime_type: str,
+        filename: str,
+        path: Path | None = None,
+    ) -> type[ParserProtocol] | None:
+        """Return the best parser class for the given file, or None.
+
+        All registered parsers (external first, then built-ins) are evaluated
+        against the file. A parser is eligible if mime_type appears in the dict
+        returned by its supported_mime_types classmethod, and its score
+        classmethod returns a non-None integer.
+
+        The parser with the highest score wins. When two parsers return the
+        same score, the one that appears earlier in the evaluation order wins
+        (external parsers are evaluated before built-ins, giving third-party
+        packages a chance to override defaults at equal priority).
+
+        When an external parser is selected, its identity is logged at INFO
+        level so operators can trace which package handled a document.
+
+        Parameters
+        ----------
+        mime_type:
+            The detected MIME type of the file.
+        filename:
+            The original filename, including extension.
+        path:
+            Optional filesystem path to the file. Forwarded to each
+            parser's score method.
+
+        Returns
+        -------
+        type[ParserProtocol] | None
+            The winning parser class, or None if no parser can handle the file.
+        """
+        best_score: int | None = None
+        best_parser: type[ParserProtocol] | None = None
+
+        # External parsers are placed first so that, at equal scores, an
+        # external parser wins over a built-in (first-seen policy).
+        for parser_class in (*self._external, *self._builtins):
+            if mime_type not in parser_class.supported_mime_types():
+                continue
+
+            score = parser_class.score(mime_type, filename, path)
+            if score is None:
+                continue
+
+            if best_score is None or score > best_score:
+                best_score = score
+                best_parser = parser_class
+
+        if best_parser is not None and best_parser in self._external:
+            logger.info(
+                "Document handled by third-party parser '%s' v%s — %s",
+                getattr(best_parser, "name", repr(best_parser)),
+                getattr(best_parser, "version", "unknown"),
+                getattr(best_parser, "url", "unknown"),
+            )
+
+        return best_parser

src/paperless/parsers/remote.py

@@ -0,0 +1,429 @@
+"""
+Built-in remote-OCR document parser.
+
+Handles documents by sending them to a configured remote OCR engine
+(currently Azure AI Vision / Document Intelligence) and retrieving both
+the extracted text and a searchable PDF with an embedded text layer.
+
+When no engine is configured, ``score()`` returns ``None`` so the parser
+is effectively invisible to the registry — the tesseract parser handles
+these MIME types instead.
+"""
+
+from __future__ import annotations
+
+import logging
+import shutil
+import tempfile
+from pathlib import Path
+from typing import TYPE_CHECKING
+from typing import Self
+
+from django.conf import settings
+
+from paperless.version import __full_version_str__
+
+if TYPE_CHECKING:
+    import datetime
+    from types import TracebackType
+
+    from paperless.parsers import MetadataEntry
+
+logger = logging.getLogger("paperless.parsing.remote")
+
+_SUPPORTED_MIME_TYPES: dict[str, str] = {
+    "application/pdf": ".pdf",
+    "image/png": ".png",
+    "image/jpeg": ".jpg",
+    "image/tiff": ".tiff",
+    "image/bmp": ".bmp",
+    "image/gif": ".gif",
+    "image/webp": ".webp",
+}
+
+
+class RemoteEngineConfig:
+    """Holds and validates the remote OCR engine configuration."""
+
+    def __init__(
+        self,
+        engine: str | None,
+        api_key: str | None = None,
+        endpoint: str | None = None,
+    ) -> None:
+        self.engine = engine
+        self.api_key = api_key
+        self.endpoint = endpoint
+
+    def engine_is_valid(self) -> bool:
+        """Return True when the engine is known and fully configured."""
+        return (
+            self.engine in ("azureai",)
+            and self.api_key is not None
+            and not (self.engine == "azureai" and self.endpoint is None)
+        )
+
+
+class RemoteDocumentParser:
+    """Parse documents via a remote OCR API (currently Azure AI Vision).
+
+    This parser sends documents to a remote engine that returns both
+    extracted text and a searchable PDF with an embedded text layer.
+    It does not depend on Tesseract or ocrmypdf.
+
+    Class attributes
+    ----------------
+    name : str
+        Human-readable parser name.
+    version : str
+        Semantic version string, kept in sync with Paperless-ngx releases.
+    author : str
+        Maintainer name.
+    url : str
+        Issue tracker / source URL.
+    """
+
+    name: str = "Paperless-ngx Remote OCR Parser"
+    version: str = __full_version_str__
+    author: str = "Paperless-ngx Contributors"
+    url: str = "https://github.com/paperless-ngx/paperless-ngx"
+
+    # ------------------------------------------------------------------
+    # Class methods
+    # ------------------------------------------------------------------
+
+    @classmethod
+    def supported_mime_types(cls) -> dict[str, str]:
+        """Return the MIME types this parser can handle.
+
+        The full set is always returned regardless of whether a remote
+        engine is configured.  The ``score()`` method handles the
+        "am I active?" logic by returning ``None`` when not configured.
+
+        Returns
+        -------
+        dict[str, str]
+            Mapping of MIME type to preferred file extension.
+        """
+        return _SUPPORTED_MIME_TYPES
+
+    @classmethod
+    def score(
+        cls,
+        mime_type: str,
+        filename: str,
+        path: Path | None = None,
+    ) -> int | None:
+        """Return the priority score for handling this file, or None.
+
+        Returns ``None`` when no valid remote engine is configured,
+        making the parser invisible to the registry for this file.
+        When configured, returns 20 — higher than the Tesseract parser's
+        default of 10 — so the remote engine takes priority.
+
+        Parameters
+        ----------
+        mime_type:
+            Detected MIME type of the file.
+        filename:
+            Original filename including extension.
+        path:
+            Optional filesystem path. Not inspected by this parser.
+
+        Returns
+        -------
+        int | None
+            20 when the remote engine is configured and the MIME type is
+            supported, otherwise None.
+        """
+        config = RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+        if not config.engine_is_valid():
+            return None
+        if mime_type not in _SUPPORTED_MIME_TYPES:
+            return None
+        return 20
+
+    # ------------------------------------------------------------------
+    # Properties
+    # ------------------------------------------------------------------
+
+    @property
+    def can_produce_archive(self) -> bool:
+        """Whether this parser can produce a searchable PDF archive copy.
+
+        Returns
+        -------
+        bool
+            Always True — the remote engine always returns a PDF with an
+            embedded text layer that serves as the archive copy.
+        """
+        return True
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        """Whether the parser must produce a PDF for the frontend to display.
+
+        Returns
+        -------
+        bool
+            Always False — all supported originals are displayable by
+            the browser (PDF) or handled via the archive copy (images).
+        """
+        return False
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def __init__(self, logging_group: object = None) -> None:
+        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
+        self._tempdir = Path(
+            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
+        )
+        self._logging_group = logging_group
+        self._text: str | None = None
+        self._archive_path: Path | None = None
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        logger.debug("Cleaning up temporary directory %s", self._tempdir)
+        shutil.rmtree(self._tempdir, ignore_errors=True)
+
+    # ------------------------------------------------------------------
+    # Core parsing interface
+    # ------------------------------------------------------------------
+
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
+        """Send the document to the remote engine and store results.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the document file to parse.
+        mime_type:
+            Detected MIME type of the document.
+        produce_archive:
+            Ignored — the remote engine always returns a searchable PDF,
+            which is stored as the archive copy regardless of this flag.
+        """
+        config = RemoteEngineConfig(
+            engine=settings.REMOTE_OCR_ENGINE,
+            api_key=settings.REMOTE_OCR_API_KEY,
+            endpoint=settings.REMOTE_OCR_ENDPOINT,
+        )
+
+        if not config.engine_is_valid():
+            logger.warning(
+                "No valid remote parser engine is configured, content will be empty.",
+            )
+            self._text = ""
+            return
+
+        if config.engine == "azureai":
+            self._text = self._azure_ai_vision_parse(document_path, config)
+
+    # ------------------------------------------------------------------
+    # Result accessors
+    # ------------------------------------------------------------------
+
+    def get_text(self) -> str | None:
+        """Return the plain-text content extracted during parse."""
+        return self._text
+
+    def get_date(self) -> datetime.datetime | None:
+        """Return the document date detected during parse.
+
+        Returns
+        -------
+        datetime.datetime | None
+            Always None — the remote parser does not detect dates.
+        """
+        return None
+
+    def get_archive_path(self) -> Path | None:
+        """Return the path to the generated archive PDF, or None."""
+        return self._archive_path
+
+    # ------------------------------------------------------------------
+    # Thumbnail and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+        """Generate a thumbnail image for the document.
+
+        Uses the archive PDF produced by the remote engine when available,
+        otherwise falls back to the original document path (PDF inputs).
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        Path
+            Path to the generated WebP thumbnail inside the temp directory.
+        """
+        # make_thumbnail_from_pdf lives in documents.parsers for now;
+        # it will move to paperless.parsers.utils when the tesseract
+        # parser is migrated in a later phase.
+        from documents.parsers import make_thumbnail_from_pdf
+
+        return make_thumbnail_from_pdf(
+            self._archive_path or document_path,
+            self._tempdir,
+            self._logging_group,
+        )
+
+    def get_page_count(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> int | None:
+        """Return the number of pages in a PDF document.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        int | None
+            Page count for PDF inputs, or ``None`` for other MIME types.
+        """
+        if mime_type != "application/pdf":
+            return None
+
+        from paperless.parsers.utils import get_page_count_for_pdf
+
+        return get_page_count_for_pdf(document_path, log=logger)
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        """Extract format-specific metadata from the document.
+
+        Delegates to the shared pikepdf-based extractor for PDF files.
+        Returns ``[]`` for all other MIME types.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the file to extract metadata from.
+        mime_type:
+            MIME type of the file.  May be ``"application/pdf"`` when
+            called for the archive version of an image original.
+
+        Returns
+        -------
+        list[MetadataEntry]
+            Zero or more metadata entries.
+        """
+        if mime_type != "application/pdf":
+            return []
+
+        from paperless.parsers.utils import extract_pdf_metadata
+
+        return extract_pdf_metadata(document_path, log=logger)
+
+    # ------------------------------------------------------------------
+    # Private helpers
+    # ------------------------------------------------------------------
+
+    def _azure_ai_vision_parse(
+        self,
+        file: Path,
+        config: RemoteEngineConfig,
+    ) -> str | None:
+        """Send ``file`` to Azure AI Document Intelligence and return text.
+
+        Downloads the searchable PDF output from Azure and stores it at
+        ``self._archive_path``.  Returns the extracted text content, or
+        ``None`` on failure (the error is logged).
+
+        Parameters
+        ----------
+        file:
+            Absolute path to the document to analyse.
+        config:
+            Validated remote engine configuration.
+
+        Returns
+        -------
+        str | None
+            Extracted text, or None if the Azure call failed.
+        """
+        if TYPE_CHECKING:
+            # Callers must have already validated config via engine_is_valid():
+            # engine_is_valid() asserts api_key is not None and (for azureai)
+            # endpoint is not None, so these casts are provably safe.
+            assert config.endpoint is not None
+            assert config.api_key is not None
+
+        from azure.ai.documentintelligence import DocumentIntelligenceClient
+        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
+        from azure.ai.documentintelligence.models import AnalyzeOutputOption
+        from azure.ai.documentintelligence.models import DocumentContentFormat
+        from azure.core.credentials import AzureKeyCredential
+
+        client = DocumentIntelligenceClient(
+            endpoint=config.endpoint,
+            credential=AzureKeyCredential(config.api_key),
+        )
+
+        try:
+            with file.open("rb") as f:
+                analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
+                poller = client.begin_analyze_document(
+                    model_id="prebuilt-read",
+                    body=analyze_request,
+                    output_content_format=DocumentContentFormat.TEXT,
+                    output=[AnalyzeOutputOption.PDF],
+                    content_type="application/json",
+                )
+
+            poller.wait()
+            result_id = poller.details["operation_id"]
+            result = poller.result()
+
+            self._archive_path = self._tempdir / "archive.pdf"
+            with self._archive_path.open("wb") as f:
+                for chunk in client.get_analyze_result_pdf(
+                    model_id="prebuilt-read",
+                    result_id=result_id,
+                ):
+                    f.write(chunk)
+
+            return result.content
+
+        except Exception as e:
+            logger.error("Azure AI Vision parsing failed: %s", e)
+
+        finally:
+            client.close()
+
+        return None

src/paperless/parsers/text.py

@@ -0,0 +1,320 @@
+"""
+Built-in plain-text document parser.
+
+Handles text/plain, text/csv, and application/csv MIME types by reading the
+file content directly.  Thumbnails are generated by rendering a page-sized
+WebP image from the first 100,000 characters using Pillow.
+"""
+
+from __future__ import annotations
+
+import logging
+import shutil
+import tempfile
+from pathlib import Path
+from typing import TYPE_CHECKING
+from typing import Self
+
+from django.conf import settings
+from PIL import Image
+from PIL import ImageDraw
+from PIL import ImageFont
+
+from paperless.version import __full_version_str__
+
+if TYPE_CHECKING:
+    import datetime
+    from types import TracebackType
+
+    from paperless.parsers import MetadataEntry
+
+logger = logging.getLogger("paperless.parsing.text")
+
+_SUPPORTED_MIME_TYPES: dict[str, str] = {
+    "text/plain": ".txt",
+    "text/csv": ".csv",
+    "application/csv": ".csv",
+}
+
+
+class TextDocumentParser:
+    """Parse plain-text documents (txt, csv) for Paperless-ngx.
+
+    This parser reads the file content directly as UTF-8 text and renders a
+    simple thumbnail using Pillow.  It does not perform OCR and does not
+    produce a searchable PDF archive copy.
+
+    Class attributes
+    ----------------
+    name : str
+        Human-readable parser name.
+    version : str
+        Semantic version string, kept in sync with Paperless-ngx releases.
+    author : str
+        Maintainer name.
+    url : str
+        Issue tracker / source URL.
+    """
+
+    name: str = "Paperless-ngx Text Parser"
+    version: str = __full_version_str__
+    author: str = "Paperless-ngx Contributors"
+    url: str = "https://github.com/paperless-ngx/paperless-ngx"
+
+    # ------------------------------------------------------------------
+    # Class methods
+    # ------------------------------------------------------------------
+
+    @classmethod
+    def supported_mime_types(cls) -> dict[str, str]:
+        """Return the MIME types this parser handles.
+
+        Returns
+        -------
+        dict[str, str]
+            Mapping of MIME type to preferred file extension.
+        """
+        return _SUPPORTED_MIME_TYPES
+
+    @classmethod
+    def score(
+        cls,
+        mime_type: str,
+        filename: str,
+        path: Path | None = None,
+    ) -> int | None:
+        """Return the priority score for handling this file.
+
+        Parameters
+        ----------
+        mime_type:
+            Detected MIME type of the file.
+        filename:
+            Original filename including extension.
+        path:
+            Optional filesystem path. Not inspected by this parser.
+
+        Returns
+        -------
+        int | None
+            10 if the MIME type is supported, otherwise None.
+        """
+        if mime_type in _SUPPORTED_MIME_TYPES:
+            return 10
+        return None
+
+    # ------------------------------------------------------------------
+    # Properties
+    # ------------------------------------------------------------------
+
+    @property
+    def can_produce_archive(self) -> bool:
+        """Whether this parser can produce a searchable PDF archive copy.
+
+        Returns
+        -------
+        bool
+            Always False — the text parser does not produce a PDF archive.
+        """
+        return False
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        """Whether the parser must produce a PDF for the frontend to display.
+
+        Returns
+        -------
+        bool
+            Always False — plain text files are displayable as-is.
+        """
+        return False
+
+    # ------------------------------------------------------------------
+    # Lifecycle
+    # ------------------------------------------------------------------
+
+    def __init__(self, logging_group: object = None) -> None:
+        settings.SCRATCH_DIR.mkdir(parents=True, exist_ok=True)
+        self._tempdir = Path(
+            tempfile.mkdtemp(prefix="paperless-", dir=settings.SCRATCH_DIR),
+        )
+        self._text: str | None = None
+
+    def __enter__(self) -> Self:
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        logger.debug("Cleaning up temporary directory %s", self._tempdir)
+        shutil.rmtree(self._tempdir, ignore_errors=True)
+
+    # ------------------------------------------------------------------
+    # Core parsing interface
+    # ------------------------------------------------------------------
+
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
+        """Read the document and store its text content.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the text file.
+        mime_type:
+            Detected MIME type of the document.
+        produce_archive:
+            Ignored — this parser never produces a PDF archive.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If the file cannot be read.
+        """
+        self._text = self._read_text(document_path)
+
+    # ------------------------------------------------------------------
+    # Result accessors
+    # ------------------------------------------------------------------
+
+    def get_text(self) -> str | None:
+        """Return the plain-text content extracted during parse.
+
+        Returns
+        -------
+        str | None
+            Extracted text, or None if parse has not been called yet.
+        """
+        return self._text
+
+    def get_date(self) -> datetime.datetime | None:
+        """Return the document date detected during parse.
+
+        Returns
+        -------
+        datetime.datetime | None
+            Always None — the text parser does not detect dates.
+        """
+        return None
+
+    def get_archive_path(self) -> Path | None:
+        """Return the path to a generated archive PDF, or None.
+
+        Returns
+        -------
+        Path | None
+            Always None — the text parser does not produce a PDF archive.
+        """
+        return None
+
+    # ------------------------------------------------------------------
+    # Thumbnail and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+        """Render the first portion of the document as a WebP thumbnail.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        Path
+            Path to the generated WebP thumbnail inside the temporary directory.
+        """
+        max_chars = 100_000
+        file_size_limit = 50 * 1024 * 1024
+
+        if document_path.stat().st_size > file_size_limit:
+            text = "[File too large to preview]"
+        else:
+            with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
+                text = f.read(max_chars)
+
+        img = Image.new("RGB", (500, 700), color="white")
+        draw = ImageDraw.Draw(img)
+        font = ImageFont.truetype(
+            font=settings.THUMBNAIL_FONT_NAME,
+            size=20,
+            layout_engine=ImageFont.Layout.BASIC,
+        )
+        draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
+
+        out_path = self._tempdir / "thumb.webp"
+        img.save(out_path, format="WEBP")
+
+        return out_path
+
+    def get_page_count(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> int | None:
+        """Return the number of pages in the document.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+
+        Returns
+        -------
+        int | None
+            Always None — page count is not meaningful for plain text.
+        """
+        return None
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        """Extract format-specific metadata from the document.
+
+        Returns
+        -------
+        list[MetadataEntry]
+            Always ``[]`` — plain text files carry no structured metadata.
+        """
+        return []
+
+    # ------------------------------------------------------------------
+    # Private helpers
+    # ------------------------------------------------------------------
+
+    def _read_text(self, filepath: Path) -> str:
+        """Read file content, replacing invalid UTF-8 bytes rather than failing.
+
+        Parameters
+        ----------
+        filepath:
+            Path to the file to read.
+
+        Returns
+        -------
+        str
+            File content as a string.
+        """
+        try:
+            return filepath.read_text(encoding="utf-8")
+        except UnicodeDecodeError as exc:
+            logger.warning(
+                "Unicode error reading %s, replacing bad bytes: %s",
+                filepath,
+                exc,
+            )
+            return filepath.read_bytes().decode("utf-8", errors="replace")

src/paperless/parsers/utils.py

@@ -0,0 +1,130 @@
+"""
+Shared utilities for Paperless-ngx document parsers.
+
+Functions here are format-neutral helpers that multiple parsers need.
+Keeping them here avoids parsers inheriting from each other just to
+share implementation.
+"""
+
+from __future__ import annotations
+
+import logging
+import re
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from pathlib import Path
+
+    from paperless.parsers import MetadataEntry
+
+logger = logging.getLogger("paperless.parsers.utils")
+
+
+def get_page_count_for_pdf(
+    document_path: Path,
+    log: logging.Logger | None = None,
+) -> int | None:
+    """Return the number of pages in a PDF file using pikepdf.
+
+    Parameters
+    ----------
+    document_path:
+        Absolute path to the PDF file.
+    log:
+        Logger to use for warnings.  Falls back to the module-level logger
+        when omitted.
+
+    Returns
+    -------
+    int | None
+        Page count, or ``None`` if the file cannot be opened or is not a
+        valid PDF.
+    """
+    import pikepdf
+
+    _log = log or logger
+
+    try:
+        with pikepdf.Pdf.open(document_path) as pdf:
+            return len(pdf.pages)
+    except Exception as e:
+        _log.warning("Unable to determine PDF page count for %s: %s", document_path, e)
+        return None
+
+
+def extract_pdf_metadata(
+    document_path: Path,
+    log: logging.Logger | None = None,
+) -> list[MetadataEntry]:
+    """Extract XMP/PDF metadata from a PDF file using pikepdf.
+
+    Reads all XMP metadata entries from the document and returns them as a
+    list of ``MetadataEntry`` dicts.  The method never raises — any failure
+    to open the file or read a specific key is logged and skipped.
+
+    Parameters
+    ----------
+    document_path:
+        Absolute path to the PDF file.
+    log:
+        Logger to use for warnings and debug messages.  Falls back to the
+        module-level logger when omitted.
+
+    Returns
+    -------
+    list[MetadataEntry]
+        Zero or more metadata entries.  Returns ``[]`` if the file cannot
+        be opened or contains no readable XMP metadata.
+    """
+    import pikepdf
+
+    from paperless.parsers import MetadataEntry
+
+    _log = log or logger
+    result: list[MetadataEntry] = []
+    namespace_pattern = re.compile(r"\{(.*)\}(.*)")
+
+    try:
+        pdf = pikepdf.open(document_path)
+        meta = pdf.open_metadata()
+    except Exception as e:
+        _log.warning("Could not open PDF metadata for %s: %s", document_path, e)
+        return []
+
+    for key, value in meta.items():
+        if isinstance(value, list):
+            value = " ".join(str(e) for e in value)
+        value = str(value)
+
+        try:
+            m = namespace_pattern.match(key)
+            if m is None:
+                continue
+
+            namespace = m.group(1)
+            key_value = m.group(2)
+
+            try:
+                namespace.encode("utf-8")
+                key_value.encode("utf-8")
+            except UnicodeEncodeError as enc_err:
+                _log.debug("Skipping metadata key %s: %s", key, enc_err)
+                continue
+
+            result.append(
+                MetadataEntry(
+                    namespace=namespace,
+                    prefix=meta.REVERSE_NS[namespace],
+                    key=key_value,
+                    value=value,
+                ),
+            )
+        except Exception as e:
+            _log.warning(
+                "Error reading metadata key %s value %s: %s",
+                key,
+                value,
+                e,
+            )
+
+    return result

src/paperless/serialisers.py

@@ -6,7 +6,6 @@ from allauth.mfa.models import Authenticator
 from allauth.mfa.totp.internal.auth import TOTP
 from allauth.socialaccount.models import SocialAccount
 from allauth.socialaccount.models import SocialApp
-from django.conf import settings
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
@@ -16,7 +15,6 @@ from rest_framework import serializers
 from rest_framework.authtoken.serializers import AuthTokenSerializer
 
 from paperless.models import ApplicationConfiguration
-from paperless.network import validate_outbound_http_url
 from paperless.validators import reject_dangerous_svg
 from paperless_mail.serialisers import ObfuscatedPasswordField
 
@@ -238,20 +236,6 @@ class ApplicationConfigurationSerializer(serializers.ModelSerializer):
             reject_dangerous_svg(file)
         return file
 
-    def validate_llm_endpoint(self, value: str | None) -> str | None:
-        if not value:
-            return value
-
-        try:
-            validate_outbound_http_url(
-                value,
-                allow_internal=settings.LLM_ALLOW_INTERNAL_ENDPOINTS,
-            )
-        except ValueError as e:
-            raise serializers.ValidationError(str(e)) from e
-
-        return value
-
     class Meta:
         model = ApplicationConfiguration
         fields = "__all__"

src/paperless/settings/__init__.py

@@ -1112,7 +1112,3 @@ LLM_BACKEND = os.getenv("PAPERLESS_AI_LLM_BACKEND")  # "ollama" or "openai"
 LLM_MODEL = os.getenv("PAPERLESS_AI_LLM_MODEL")
 LLM_API_KEY = os.getenv("PAPERLESS_AI_LLM_API_KEY")
 LLM_ENDPOINT = os.getenv("PAPERLESS_AI_LLM_ENDPOINT")
-LLM_ALLOW_INTERNAL_ENDPOINTS = get_bool_from_env(
-    "PAPERLESS_AI_LLM_ALLOW_INTERNAL_ENDPOINTS",
-    "true",
-)

src/paperless/tests/conftest.py

@@ -0,0 +1,48 @@
+"""
+Fixtures defined here are available to every test module under
+src/paperless/tests/ (including sub-packages such as parsers/).
+
+Session-scoped fixtures for the shared samples directory live here so
+sub-package conftest files can reference them without duplicating path logic.
+Parser-specific fixtures (concrete parser instances, format-specific sample
+files) live in paperless/tests/parsers/conftest.py.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+import pytest
+
+from paperless.parsers.registry import reset_parser_registry
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+
+
+@pytest.fixture(scope="session")
+def samples_dir() -> Path:
+    """Absolute path to the shared parser sample files directory.
+
+    Sub-package conftest files derive format-specific paths from this root,
+    e.g. ``samples_dir / "text" / "test.txt"``.
+
+    Returns
+    -------
+    Path
+        Directory containing all sample documents used by parser tests.
+    """
+    return (Path(__file__).parent / "samples").resolve()
+
+
+@pytest.fixture(autouse=True)
+def clean_registry() -> Generator[None, None, None]:
+    """Reset the parser registry before and after every test.
+
+    This prevents registry state from leaking between tests that call
+    get_parser_registry() or init_builtin_parsers().
+    """
+    reset_parser_registry()
+    yield
+    reset_parser_registry()

src/paperless/tests/parsers/conftest.py

@@ -0,0 +1,165 @@
+"""
+Parser fixtures that are used across multiple test modules in this package
+are defined here.  Format-specific sample-file fixtures are grouped by parser
+so it is easy to see which files belong to which test module.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.text import TextDocumentParser
+
+if TYPE_CHECKING:
+    from collections.abc import Generator
+    from pathlib import Path
+
+    from pytest_django.fixtures import SettingsWrapper
+
+
+# ------------------------------------------------------------------
+# Text parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def text_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the text parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/text/``
+    """
+    return samples_dir / "text"
+
+
+@pytest.fixture(scope="session")
+def sample_txt_file(text_samples_dir: Path) -> Path:
+    """Path to a valid UTF-8 plain-text sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``text/test.txt``.
+    """
+    return text_samples_dir / "test.txt"
+
+
+@pytest.fixture(scope="session")
+def malformed_txt_file(text_samples_dir: Path) -> Path:
+    """Path to a text file containing invalid UTF-8 bytes.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``text/decode_error.txt``.
+    """
+    return text_samples_dir / "decode_error.txt"
+
+
+# ------------------------------------------------------------------
+# Text parser instance
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def text_parser() -> Generator[TextDocumentParser, None, None]:
+    """Yield a TextDocumentParser and clean up its temporary directory afterwards.
+
+    Yields
+    ------
+    TextDocumentParser
+        A ready-to-use parser instance.
+    """
+    with TextDocumentParser() as parser:
+        yield parser
+
+
+# ------------------------------------------------------------------
+# Remote parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def remote_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the remote parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/remote/``
+    """
+    return samples_dir / "remote"
+
+
+@pytest.fixture(scope="session")
+def sample_pdf_file(remote_samples_dir: Path) -> Path:
+    """Path to a simple digital PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``remote/simple-digital.pdf``.
+    """
+    return remote_samples_dir / "simple-digital.pdf"
+
+
+# ------------------------------------------------------------------
+# Remote parser instance
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def remote_parser() -> Generator[RemoteDocumentParser, None, None]:
+    """Yield a RemoteDocumentParser and clean up its temporary directory afterwards.
+
+    Yields
+    ------
+    RemoteDocumentParser
+        A ready-to-use parser instance.
+    """
+    with RemoteDocumentParser() as parser:
+        yield parser
+
+
+# ------------------------------------------------------------------
+# Remote parser settings helpers
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def azure_settings(settings: SettingsWrapper) -> SettingsWrapper:
+    """Configure Django settings for a valid Azure AI OCR engine.
+
+    Sets ``REMOTE_OCR_ENGINE``, ``REMOTE_OCR_API_KEY``, and
+    ``REMOTE_OCR_ENDPOINT`` to test values.  Settings are restored
+    automatically after the test by pytest-django.
+
+    Returns
+    -------
+    SettingsWrapper
+        The modified settings object (for chaining further overrides).
+    """
+    settings.REMOTE_OCR_ENGINE = "azureai"
+    settings.REMOTE_OCR_API_KEY = "test-api-key"
+    settings.REMOTE_OCR_ENDPOINT = "https://test.cognitiveservices.azure.com"
+    return settings
+
+
+@pytest.fixture()
+def no_engine_settings(settings: SettingsWrapper) -> SettingsWrapper:
+    """Configure Django settings with no remote engine configured.
+
+    Returns
+    -------
+    SettingsWrapper
+        The modified settings object.
+    """
+    settings.REMOTE_OCR_ENGINE = None
+    settings.REMOTE_OCR_API_KEY = None
+    settings.REMOTE_OCR_ENDPOINT = None
+    return settings

src/paperless/tests/parsers/test_remote_parser.py

@@ -0,0 +1,490 @@
+"""
+Tests for paperless.parsers.remote.RemoteDocumentParser.
+
+All tests use the context-manager protocol for parser lifecycle.
+
+Fixture layout
+--------------
+make_azure_mock  — factory (defined here; specific to this module)
+azure_client     — composes azure_settings + make_azure_mock + patch;
+                   use when a test needs the client to succeed
+failing_azure_client
+                 — composes azure_settings + patch with RuntimeError;
+                   use when a test needs the client to fail
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+from unittest.mock import Mock
+
+import pytest
+
+from paperless.parsers import ParserProtocol
+from paperless.parsers.remote import RemoteDocumentParser
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+    from pathlib import Path
+
+    from pytest_django.fixtures import SettingsWrapper
+    from pytest_mock import MockerFixture
+
+
+# ---------------------------------------------------------------------------
+# Module-local fixtures
+# ---------------------------------------------------------------------------
+
+_AZURE_CLIENT_TARGET = "azure.ai.documentintelligence.DocumentIntelligenceClient"
+_DEFAULT_TEXT = "Extracted text."
+
+
+@pytest.fixture()
+def make_azure_mock() -> Callable[[str], Mock]:
+    """Return a factory that builds a mock Azure DocumentIntelligenceClient.
+
+    Usage::
+
+        mock_client = make_azure_mock()            # default extracted text
+        mock_client = make_azure_mock("My text.")  # custom extracted text
+    """
+
+    def _factory(text: str = _DEFAULT_TEXT) -> Mock:
+        mock_client = Mock()
+        mock_poller = Mock()
+        mock_poller.wait.return_value = None
+        mock_poller.details = {"operation_id": "fake-op-id"}
+        mock_poller.result.return_value.content = text
+        mock_client.begin_analyze_document.return_value = mock_poller
+        mock_client.get_analyze_result_pdf.return_value = [b"%PDF-1.4 FAKE"]
+        return mock_client
+
+    return _factory
+
+
+@pytest.fixture()
+def azure_client(
+    azure_settings: SettingsWrapper,
+    make_azure_mock: Callable[[str], Mock],
+    mocker: MockerFixture,
+) -> Mock:
+    """Patch the Azure DI client with a succeeding mock and return the instance.
+
+    Implicitly applies ``azure_settings`` so tests using this fixture do not
+    also need ``@pytest.mark.usefixtures("azure_settings")``.
+    """
+    mock_client = make_azure_mock()
+    mocker.patch(_AZURE_CLIENT_TARGET, return_value=mock_client)
+    return mock_client
+
+
+@pytest.fixture()
+def failing_azure_client(
+    azure_settings: SettingsWrapper,
+    mocker: MockerFixture,
+) -> Mock:
+    """Patch the Azure DI client to raise RuntimeError on every call.
+
+    Implicitly applies ``azure_settings``.  Returns the mock instance so
+    tests can assert on calls such as ``close()``.
+    """
+    mock_client = Mock()
+    mock_client.begin_analyze_document.side_effect = RuntimeError("network failure")
+    mocker.patch(_AZURE_CLIENT_TARGET, return_value=mock_client)
+    return mock_client
+
+
+# ---------------------------------------------------------------------------
+# Protocol contract
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserProtocol:
+    """Verify that RemoteDocumentParser satisfies the ParserProtocol contract."""
+
+    def test_isinstance_satisfies_protocol(
+        self,
+        remote_parser: RemoteDocumentParser,
+    ) -> None:
+        assert isinstance(remote_parser, ParserProtocol)
+
+    def test_class_attributes_present(self) -> None:
+        assert isinstance(RemoteDocumentParser.name, str) and RemoteDocumentParser.name
+        assert (
+            isinstance(RemoteDocumentParser.version, str)
+            and RemoteDocumentParser.version
+        )
+        assert (
+            isinstance(RemoteDocumentParser.author, str) and RemoteDocumentParser.author
+        )
+        assert isinstance(RemoteDocumentParser.url, str) and RemoteDocumentParser.url
+
+
+# ---------------------------------------------------------------------------
+# supported_mime_types
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserSupportedMimeTypes:
+    """supported_mime_types() always returns the full set regardless of config."""
+
+    def test_returns_dict(self) -> None:
+        mime_types = RemoteDocumentParser.supported_mime_types()
+        assert isinstance(mime_types, dict)
+
+    def test_includes_all_expected_types(self) -> None:
+        mime_types = RemoteDocumentParser.supported_mime_types()
+        expected = {
+            "application/pdf",
+            "image/png",
+            "image/jpeg",
+            "image/tiff",
+            "image/bmp",
+            "image/gif",
+            "image/webp",
+        }
+        assert expected == set(mime_types.keys())
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_returns_full_set_when_not_configured(self) -> None:
+        """
+        GIVEN: No remote engine is configured
+        WHEN:  supported_mime_types() is called
+        THEN:  The full MIME type dict is still returned (score() handles activation)
+        """
+        mime_types = RemoteDocumentParser.supported_mime_types()
+        assert len(mime_types) == 7
+
+
+# ---------------------------------------------------------------------------
+# score()
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserScore:
+    """score() encodes the activation logic: None when unconfigured, 20 when active."""
+
+    @pytest.mark.usefixtures("azure_settings")
+    @pytest.mark.parametrize(
+        "mime_type",
+        [
+            pytest.param("application/pdf", id="pdf"),
+            pytest.param("image/png", id="png"),
+            pytest.param("image/jpeg", id="jpeg"),
+            pytest.param("image/tiff", id="tiff"),
+            pytest.param("image/bmp", id="bmp"),
+            pytest.param("image/gif", id="gif"),
+            pytest.param("image/webp", id="webp"),
+        ],
+    )
+    def test_score_returns_20_when_configured(self, mime_type: str) -> None:
+        result = RemoteDocumentParser.score(mime_type, "doc.pdf")
+        assert result == 20
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    @pytest.mark.parametrize(
+        "mime_type",
+        [
+            pytest.param("application/pdf", id="pdf"),
+            pytest.param("image/png", id="png"),
+            pytest.param("image/jpeg", id="jpeg"),
+        ],
+    )
+    def test_score_returns_none_when_no_engine(self, mime_type: str) -> None:
+        result = RemoteDocumentParser.score(mime_type, "doc.pdf")
+        assert result is None
+
+    def test_score_returns_none_when_api_key_missing(
+        self,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.REMOTE_OCR_ENGINE = "azureai"
+        settings.REMOTE_OCR_API_KEY = None
+        settings.REMOTE_OCR_ENDPOINT = "https://test.cognitiveservices.azure.com"
+        result = RemoteDocumentParser.score("application/pdf", "doc.pdf")
+        assert result is None
+
+    def test_score_returns_none_when_endpoint_missing(
+        self,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.REMOTE_OCR_ENGINE = "azureai"
+        settings.REMOTE_OCR_API_KEY = "key"
+        settings.REMOTE_OCR_ENDPOINT = None
+        result = RemoteDocumentParser.score("application/pdf", "doc.pdf")
+        assert result is None
+
+    @pytest.mark.usefixtures("azure_settings")
+    def test_score_returns_none_for_unsupported_mime_type(self) -> None:
+        result = RemoteDocumentParser.score("text/plain", "doc.txt")
+        assert result is None
+
+    @pytest.mark.usefixtures("azure_settings")
+    def test_score_higher_than_tesseract_default(self) -> None:
+        """Remote parser (20) outranks the tesseract default (10) when configured."""
+        score = RemoteDocumentParser.score("application/pdf", "doc.pdf")
+        assert score is not None and score > 10
+
+
+# ---------------------------------------------------------------------------
+# Properties
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserProperties:
+    def test_can_produce_archive_is_true(
+        self,
+        remote_parser: RemoteDocumentParser,
+    ) -> None:
+        assert remote_parser.can_produce_archive is True
+
+    def test_requires_pdf_rendition_is_false(
+        self,
+        remote_parser: RemoteDocumentParser,
+    ) -> None:
+        assert remote_parser.requires_pdf_rendition is False
+
+
+# ---------------------------------------------------------------------------
+# Lifecycle
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserLifecycle:
+    def test_context_manager_cleans_up_tempdir(self) -> None:
+        with RemoteDocumentParser() as parser:
+            tempdir = parser._tempdir
+            assert tempdir.exists()
+        assert not tempdir.exists()
+
+    def test_context_manager_cleans_up_after_exception(self) -> None:
+        tempdir: Path | None = None
+        with pytest.raises(RuntimeError):
+            with RemoteDocumentParser() as parser:
+                tempdir = parser._tempdir
+                raise RuntimeError("boom")
+        assert tempdir is not None
+        assert not tempdir.exists()
+
+
+# ---------------------------------------------------------------------------
+# parse() — happy path
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserParse:
+    def test_parse_returns_text_from_azure(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        assert remote_parser.get_text() == _DEFAULT_TEXT
+
+    def test_parse_sets_archive_path(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        archive = remote_parser.get_archive_path()
+        assert archive is not None
+        assert archive.exists()
+        assert archive.suffix == ".pdf"
+
+    def test_parse_closes_client_on_success(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        azure_client.close.assert_called_once()
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_parse_sets_empty_text_when_not_configured(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        assert remote_parser.get_text() == ""
+        assert remote_parser.get_archive_path() is None
+
+    def test_get_text_none_before_parse(
+        self,
+        remote_parser: RemoteDocumentParser,
+    ) -> None:
+        assert remote_parser.get_text() is None
+
+    def test_get_date_always_none(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        assert remote_parser.get_date() is None
+
+
+# ---------------------------------------------------------------------------
+# parse() — Azure failure path
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserParseError:
+    def test_parse_returns_none_on_azure_error(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        failing_azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        assert remote_parser.get_text() is None
+
+    def test_parse_closes_client_on_error(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        failing_azure_client: Mock,
+    ) -> None:
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        failing_azure_client.close.assert_called_once()
+
+    def test_parse_logs_error_on_azure_failure(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+        failing_azure_client: Mock,
+        mocker: MockerFixture,
+    ) -> None:
+        mock_log = mocker.patch("paperless.parsers.remote.logger")
+
+        remote_parser.parse(sample_pdf_file, "application/pdf")
+
+        mock_log.error.assert_called_once()
+        assert "Azure AI Vision parsing failed" in mock_log.error.call_args[0][0]
+
+
+# ---------------------------------------------------------------------------
+# get_page_count()
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserPageCount:
+    def test_page_count_for_pdf(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        count = remote_parser.get_page_count(sample_pdf_file, "application/pdf")
+        assert isinstance(count, int)
+        assert count >= 1
+
+    def test_page_count_returns_none_for_image_mime(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        count = remote_parser.get_page_count(sample_pdf_file, "image/png")
+        assert count is None
+
+    def test_page_count_returns_none_for_invalid_pdf(
+        self,
+        remote_parser: RemoteDocumentParser,
+        tmp_path: Path,
+    ) -> None:
+        bad_pdf = tmp_path / "bad.pdf"
+        bad_pdf.write_bytes(b"not a pdf at all")
+        count = remote_parser.get_page_count(bad_pdf, "application/pdf")
+        assert count is None
+
+
+# ---------------------------------------------------------------------------
+# extract_metadata()
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserMetadata:
+    def test_extract_metadata_non_pdf_returns_empty(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        result = remote_parser.extract_metadata(sample_pdf_file, "image/png")
+        assert result == []
+
+    def test_extract_metadata_pdf_returns_list(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        assert isinstance(result, list)
+
+    def test_extract_metadata_pdf_entries_have_required_keys(
+        self,
+        remote_parser: RemoteDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        for entry in result:
+            assert "namespace" in entry
+            assert "prefix" in entry
+            assert "key" in entry
+            assert "value" in entry
+            assert isinstance(entry["value"], str)
+
+    def test_extract_metadata_does_not_raise_on_invalid_pdf(
+        self,
+        remote_parser: RemoteDocumentParser,
+        tmp_path: Path,
+    ) -> None:
+        bad_pdf = tmp_path / "bad.pdf"
+        bad_pdf.write_bytes(b"not a pdf at all")
+        result = remote_parser.extract_metadata(bad_pdf, "application/pdf")
+        assert result == []
+
+
+# ---------------------------------------------------------------------------
+# Registry integration
+# ---------------------------------------------------------------------------
+
+
+class TestRemoteParserRegistry:
+    def test_registered_in_defaults(self) -> None:
+        from paperless.parsers.registry import ParserRegistry
+
+        registry = ParserRegistry()
+        registry.register_defaults()
+
+        assert RemoteDocumentParser in registry._builtins
+
+    @pytest.mark.usefixtures("azure_settings")
+    def test_get_parser_returns_remote_when_configured(self) -> None:
+        from paperless.parsers.registry import get_parser_registry
+
+        registry = get_parser_registry()
+        parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
+
+        assert parser_cls is RemoteDocumentParser
+
+    @pytest.mark.usefixtures("no_engine_settings")
+    def test_get_parser_returns_none_for_pdf_when_not_configured(self) -> None:
+        """With no tesseract parser registered yet, PDF has no handler if remote is off."""
+        from paperless.parsers.registry import ParserRegistry
+
+        registry = ParserRegistry()
+        registry.register_defaults()
+        parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
+
+        assert parser_cls is None

src/paperless/tests/parsers/test_text_parser.py

@@ -0,0 +1,256 @@
+"""
+Tests for paperless.parsers.text.TextDocumentParser.
+
+All tests use the context-manager protocol for parser lifecycle.  Sample
+files are provided by session-scoped fixtures defined in conftest.py.
+"""
+
+from __future__ import annotations
+
+import tempfile
+from pathlib import Path
+
+import pytest
+
+from paperless.parsers import ParserProtocol
+from paperless.parsers.text import TextDocumentParser
+
+
+class TestTextParserProtocol:
+    """Verify that TextDocumentParser satisfies the ParserProtocol contract."""
+
+    def test_isinstance_satisfies_protocol(
+        self,
+        text_parser: TextDocumentParser,
+    ) -> None:
+        assert isinstance(text_parser, ParserProtocol)
+
+    def test_class_attributes_present(self) -> None:
+        assert isinstance(TextDocumentParser.name, str) and TextDocumentParser.name
+        assert (
+            isinstance(TextDocumentParser.version, str) and TextDocumentParser.version
+        )
+        assert isinstance(TextDocumentParser.author, str) and TextDocumentParser.author
+        assert isinstance(TextDocumentParser.url, str) and TextDocumentParser.url
+
+    def test_supported_mime_types_returns_dict(self) -> None:
+        mime_types = TextDocumentParser.supported_mime_types()
+        assert isinstance(mime_types, dict)
+        assert "text/plain" in mime_types
+        assert "text/csv" in mime_types
+        assert "application/csv" in mime_types
+
+    @pytest.mark.parametrize(
+        ("mime_type", "expected"),
+        [
+            ("text/plain", 10),
+            ("text/csv", 10),
+            ("application/csv", 10),
+            ("application/pdf", None),
+            ("image/png", None),
+        ],
+    )
+    def test_score(self, mime_type: str, expected: int | None) -> None:
+        assert TextDocumentParser.score(mime_type, "file.txt") == expected
+
+    def test_can_produce_archive_is_false(
+        self,
+        text_parser: TextDocumentParser,
+    ) -> None:
+        assert text_parser.can_produce_archive is False
+
+    def test_requires_pdf_rendition_is_false(
+        self,
+        text_parser: TextDocumentParser,
+    ) -> None:
+        assert text_parser.requires_pdf_rendition is False
+
+
+class TestTextParserLifecycle:
+    """Verify context-manager behaviour and temporary directory cleanup."""
+
+    def test_context_manager_cleans_up_tempdir(self) -> None:
+        with TextDocumentParser() as parser:
+            tempdir = parser._tempdir
+            assert tempdir.exists()
+        assert not tempdir.exists()
+
+    def test_context_manager_cleans_up_after_exception(self) -> None:
+        tempdir: Path | None = None
+        with pytest.raises(RuntimeError):
+            with TextDocumentParser() as parser:
+                tempdir = parser._tempdir
+                raise RuntimeError("boom")
+        assert tempdir is not None
+        assert not tempdir.exists()
+
+
+class TestTextParserParse:
+    """Verify parse() and the result accessors."""
+
+    def test_parse_valid_utf8(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        text_parser.parse(sample_txt_file, "text/plain")
+
+        assert text_parser.get_text() == "This is a test file.\n"
+
+    def test_parse_returns_none_for_archive_path(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        text_parser.parse(sample_txt_file, "text/plain")
+
+        assert text_parser.get_archive_path() is None
+
+    def test_parse_returns_none_for_date(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        text_parser.parse(sample_txt_file, "text/plain")
+
+        assert text_parser.get_date() is None
+
+    def test_parse_invalid_utf8_bytes_replaced(
+        self,
+        text_parser: TextDocumentParser,
+        malformed_txt_file: Path,
+    ) -> None:
+        """
+        GIVEN:
+            - A text file containing invalid UTF-8 byte sequences
+        WHEN:
+            - The file is parsed
+        THEN:
+            - Parsing succeeds
+            - Invalid bytes are replaced with the Unicode replacement character
+        """
+        text_parser.parse(malformed_txt_file, "text/plain")
+
+        assert text_parser.get_text() == "Pantothens\ufffdure\n"
+
+    def test_get_text_none_before_parse(
+        self,
+        text_parser: TextDocumentParser,
+    ) -> None:
+        assert text_parser.get_text() is None
+
+
+class TestTextParserThumbnail:
+    """Verify thumbnail generation."""
+
+    def test_thumbnail_exists_and_is_file(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        thumb = text_parser.get_thumbnail(sample_txt_file, "text/plain")
+
+        assert thumb.exists()
+        assert thumb.is_file()
+
+    def test_thumbnail_large_file_does_not_read_all(
+        self,
+        text_parser: TextDocumentParser,
+    ) -> None:
+        """
+        GIVEN:
+            - A text file larger than 50 MB
+        WHEN:
+            - A thumbnail is requested
+        THEN:
+            - The thumbnail is generated without loading the full file
+        """
+        with tempfile.NamedTemporaryFile(
+            delete=False,
+            mode="w",
+            encoding="utf-8",
+            suffix=".txt",
+        ) as tmp:
+            tmp.write("A" * (51 * 1024 * 1024))
+            large_file = Path(tmp.name)
+
+        try:
+            thumb = text_parser.get_thumbnail(large_file, "text/plain")
+            assert thumb.exists()
+            assert thumb.is_file()
+        finally:
+            large_file.unlink(missing_ok=True)
+
+    def test_get_page_count_returns_none(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        assert text_parser.get_page_count(sample_txt_file, "text/plain") is None
+
+
+class TestTextParserMetadata:
+    """Verify extract_metadata behaviour."""
+
+    def test_extract_metadata_returns_empty_list(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        result = text_parser.extract_metadata(sample_txt_file, "text/plain")
+
+        assert result == []
+
+    def test_extract_metadata_returns_list_type(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        result = text_parser.extract_metadata(sample_txt_file, "text/plain")
+
+        assert isinstance(result, list)
+
+    def test_extract_metadata_ignores_mime_type(
+        self,
+        text_parser: TextDocumentParser,
+        sample_txt_file: Path,
+    ) -> None:
+        """extract_metadata returns [] regardless of the mime_type argument."""
+        assert text_parser.extract_metadata(sample_txt_file, "application/pdf") == []
+        assert text_parser.extract_metadata(sample_txt_file, "text/csv") == []
+
+
+class TestTextParserRegistry:
+    """Verify that TextDocumentParser is registered by default."""
+
+    def test_registered_in_defaults(self) -> None:
+        from paperless.parsers.registry import ParserRegistry
+
+        registry = ParserRegistry()
+        registry.register_defaults()
+
+        assert TextDocumentParser in registry._builtins
+
+    def test_get_parser_for_text_plain(self) -> None:
+        from paperless.parsers.registry import get_parser_registry
+
+        registry = get_parser_registry()
+        parser_cls = registry.get_parser_for_file("text/plain", "doc.txt")
+
+        assert parser_cls is TextDocumentParser
+
+    def test_get_parser_for_text_csv(self) -> None:
+        from paperless.parsers.registry import get_parser_registry
+
+        registry = get_parser_registry()
+        parser_cls = registry.get_parser_for_file("text/csv", "data.csv")
+
+        assert parser_cls is TextDocumentParser
+
+    def test_get_parser_for_unknown_type_returns_none(self) -> None:
+        from paperless.parsers.registry import get_parser_registry
+
+        registry = get_parser_registry()
+        parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
+
+        assert parser_cls is None

src/paperless/tests/test_registry.py

@@ -0,0 +1,714 @@
+"""
+Tests for :mod:`paperless.parsers` (ParserProtocol) and
+:mod:`paperless.parsers.registry` (ParserRegistry + module-level helpers).
+
+All tests use pytest-style functions/classes — no unittest.TestCase.
+The ``clean_registry`` fixture ensures complete isolation between tests by
+resetting the module-level singleton before and after every test.
+"""
+
+from __future__ import annotations
+
+import logging
+from importlib.metadata import EntryPoint
+from pathlib import Path
+from typing import Self
+from unittest.mock import MagicMock
+from unittest.mock import patch
+
+import pytest
+
+from paperless.parsers import ParserProtocol
+from paperless.parsers.registry import ParserRegistry
+from paperless.parsers.registry import get_parser_registry
+from paperless.parsers.registry import init_builtin_parsers
+from paperless.parsers.registry import reset_parser_registry
+
+
+@pytest.fixture()
+def dummy_parser_cls() -> type:
+    """Return a class that fully satisfies :class:`ParserProtocol`.
+
+    GIVEN: A need to exercise registry and Protocol logic with a minimal
+           but complete parser.
+    WHEN:  A test requests this fixture.
+    THEN:  A class with all required attributes and methods is returned.
+    """
+
+    class DummyParser:
+        name = "dummy-parser"
+        version = "0.1.0"
+        author = "Test Author"
+        url = "https://example.com/dummy-parser"
+
+        @classmethod
+        def supported_mime_types(cls) -> dict[str, str]:
+            return {"text/plain": ".txt"}
+
+        @classmethod
+        def score(
+            cls,
+            mime_type: str,
+            filename: str,
+            path: Path | None = None,
+        ) -> int | None:
+            return 10
+
+        @property
+        def can_produce_archive(self) -> bool:
+            return False
+
+        @property
+        def requires_pdf_rendition(self) -> bool:
+            return False
+
+        def parse(
+            self,
+            document_path: Path,
+            mime_type: str,
+            *,
+            produce_archive: bool = True,
+        ) -> None:
+            """
+            Required to exist, but doesn't need to do anything
+            """
+
+        def get_text(self) -> str | None:
+            return None
+
+        def get_date(self) -> None:
+            return None
+
+        def get_archive_path(self) -> Path | None:
+            return None
+
+        def get_thumbnail(
+            self,
+            document_path: Path,
+            mime_type: str,
+        ) -> Path:
+            return Path("/tmp/thumbnail.webp")
+
+        def get_page_count(
+            self,
+            document_path: Path,
+            mime_type: str,
+        ) -> int | None:
+            return None
+
+        def extract_metadata(
+            self,
+            document_path: Path,
+            mime_type: str,
+        ) -> list:
+            return []
+
+        def __enter__(self) -> Self:
+            return self
+
+        def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+            """
+            Required to exist, but doesn't need to do anything
+            """
+
+    return DummyParser
+
+
+class TestParserProtocol:
+    """Verify runtime isinstance() checks against ParserProtocol."""
+
+    def test_compliant_class_instance_passes_isinstance(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A class that implements every method required by ParserProtocol.
+        WHEN:  isinstance() is called with the Protocol.
+        THEN:  The check passes (returns True).
+        """
+        instance = dummy_parser_cls()
+        assert isinstance(instance, ParserProtocol)
+
+    def test_non_compliant_class_instance_fails_isinstance(self) -> None:
+        """
+        GIVEN: A plain class with no parser-related methods.
+        WHEN:  isinstance() is called with ParserProtocol.
+        THEN:  The check fails (returns False).
+        """
+
+        class Unrelated:
+            pass
+
+        assert not isinstance(Unrelated(), ParserProtocol)
+
+    @pytest.mark.parametrize(
+        "missing_method",
+        [
+            pytest.param("parse", id="missing-parse"),
+            pytest.param("get_text", id="missing-get_text"),
+            pytest.param("get_thumbnail", id="missing-get_thumbnail"),
+            pytest.param("__enter__", id="missing-__enter__"),
+            pytest.param("__exit__", id="missing-__exit__"),
+        ],
+    )
+    def test_partial_compliant_fails_isinstance(
+        self,
+        dummy_parser_cls: type,
+        missing_method: str,
+    ) -> None:
+        """
+        GIVEN: A class that satisfies ParserProtocol except for one method.
+        WHEN:  isinstance() is called with ParserProtocol.
+        THEN:  The check fails because the Protocol is not fully satisfied.
+        """
+        # Create a subclass and delete the specified method to break compliance.
+        partial_cls = type(
+            "PartialParser",
+            (dummy_parser_cls,),
+            {missing_method: None},  # Replace with None — not callable
+        )
+        assert not isinstance(partial_cls(), ParserProtocol)
+
+
+class TestRegistrySingleton:
+    """Verify the module-level singleton lifecycle functions."""
+
+    def test_get_parser_registry_returns_instance(self) -> None:
+        """
+        GIVEN: No registry has been created yet.
+        WHEN:  get_parser_registry() is called.
+        THEN:  A ParserRegistry instance is returned.
+        """
+        registry = get_parser_registry()
+        assert isinstance(registry, ParserRegistry)
+
+    def test_get_parser_registry_same_instance_on_repeated_calls(self) -> None:
+        """
+        GIVEN: A registry instance was created by a prior call.
+        WHEN:  get_parser_registry() is called a second time.
+        THEN:  The exact same object (identity) is returned.
+        """
+        first = get_parser_registry()
+        second = get_parser_registry()
+        assert first is second
+
+    def test_reset_parser_registry_gives_fresh_instance(self) -> None:
+        """
+        GIVEN: A registry instance already exists.
+        WHEN:  reset_parser_registry() is called and then get_parser_registry()
+               is called again.
+        THEN:  A new, distinct registry instance is returned.
+        """
+        first = get_parser_registry()
+        reset_parser_registry()
+        second = get_parser_registry()
+        assert first is not second
+
+    def test_init_builtin_parsers_does_not_run_discover(
+        self,
+        monkeypatch: pytest.MonkeyPatch,
+    ) -> None:
+        """
+        GIVEN: discover() would raise an exception if called.
+        WHEN:  init_builtin_parsers() is called.
+        THEN:  No exception is raised, confirming discover() was not invoked.
+        """
+
+        def exploding_discover(self) -> None:
+            raise RuntimeError(
+                "discover() must not be called from init_builtin_parsers",
+            )
+
+        monkeypatch.setattr(ParserRegistry, "discover", exploding_discover)
+
+        # Should complete without raising.
+        init_builtin_parsers()
+
+    def test_init_builtin_parsers_idempotent(self) -> None:
+        """
+        GIVEN: init_builtin_parsers() has already been called once.
+        WHEN:  init_builtin_parsers() is called a second time.
+        THEN:  No error is raised and the same registry instance is reused.
+        """
+        init_builtin_parsers()
+        # Capture the registry created by the first call.
+        import paperless.parsers.registry as reg_module
+
+        first_registry = reg_module._registry
+
+        init_builtin_parsers()
+
+        assert reg_module._registry is first_registry
+
+
+class TestParserRegistryGetParserForFile:
+    """Verify parser selection logic in get_parser_for_file()."""
+
+    def test_returns_none_when_no_parsers_registered(self) -> None:
+        """
+        GIVEN: A registry with no parsers registered.
+        WHEN:  get_parser_for_file() is called for any MIME type.
+        THEN:  None is returned.
+        """
+        registry = ParserRegistry()
+        result = registry.get_parser_for_file("text/plain", "doc.txt")
+        assert result is None
+
+    def test_returns_none_for_unsupported_mime_type(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A registry with a parser that supports only 'text/plain'.
+        WHEN:  get_parser_for_file() is called with 'application/pdf'.
+        THEN:  None is returned.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        result = registry.get_parser_for_file("application/pdf", "file.pdf")
+        assert result is None
+
+    def test_returns_parser_for_supported_mime_type(
+        self,
+        dummy_parser_cls: type,
+    ) -> None:
+        """
+        GIVEN: A registry with a parser registered for 'text/plain'.
+        WHEN:  get_parser_for_file() is called with 'text/plain'.
+        THEN:  The registered parser class is returned.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+        result = registry.get_parser_for_file("text/plain", "readme.txt")
+        assert result is dummy_parser_cls
+
+    def test_highest_score_wins(self) -> None:
+        """
+        GIVEN: Two parsers both supporting 'text/plain' with scores 5 and 20.
+        WHEN:  get_parser_for_file() is called for 'text/plain'.
+        THEN:  The parser with score 20 is returned.
+        """
+
+        class LowScoreParser:
+            name = "low"
+            version = "1.0"
+            author = "A"
+            url = "https://example.com/low"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 5
+
+        class HighScoreParser:
+            name = "high"
+            version = "1.0"
+            author = "B"
+            url = "https://example.com/high"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 20
+
+        registry = ParserRegistry()
+        registry.register_builtin(LowScoreParser)
+        registry.register_builtin(HighScoreParser)
+        result = registry.get_parser_for_file("text/plain", "readme.txt")
+        assert result is HighScoreParser
+
+    def test_parser_returning_none_score_is_skipped(self) -> None:
+        """
+        GIVEN: A parser that returns None from score() for the given file.
+        WHEN:  get_parser_for_file() is called.
+        THEN:  That parser is skipped and None is returned (no other candidates).
+        """
+
+        class DecliningParser:
+            name = "declining"
+            version = "1.0"
+            author = "A"
+            url = "https://example.com"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return None  # Explicitly declines
+
+        registry = ParserRegistry()
+        registry.register_builtin(DecliningParser)
+        result = registry.get_parser_for_file("text/plain", "readme.txt")
+        assert result is None
+
+    def test_all_parsers_decline_returns_none(self) -> None:
+        """
+        GIVEN: Multiple parsers that all return None from score().
+        WHEN:  get_parser_for_file() is called.
+        THEN:  None is returned.
+        """
+
+        class AlwaysDeclines:
+            name = "declines"
+            version = "1.0"
+            author = "A"
+            url = "https://example.com"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return None
+
+        registry = ParserRegistry()
+        registry.register_builtin(AlwaysDeclines)
+        registry._external.append(AlwaysDeclines)
+        result = registry.get_parser_for_file("text/plain", "file.txt")
+        assert result is None
+
+    def test_external_parser_beats_builtin_same_score(self) -> None:
+        """
+        GIVEN: An external and a built-in parser both returning score 10.
+        WHEN:  get_parser_for_file() is called.
+        THEN:  The external parser wins because externals are evaluated first
+               and the first-seen-wins policy applies at equal scores.
+        """
+
+        class BuiltinParser:
+            name = "builtin"
+            version = "1.0"
+            author = "Core"
+            url = "https://example.com/builtin"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 10
+
+        class ExternalParser:
+            name = "external"
+            version = "2.0"
+            author = "Third Party"
+            url = "https://example.com/external"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 10
+
+        registry = ParserRegistry()
+        registry.register_builtin(BuiltinParser)
+        registry._external.append(ExternalParser)
+        result = registry.get_parser_for_file("text/plain", "file.txt")
+        assert result is ExternalParser
+
+    def test_builtin_wins_when_external_declines(self) -> None:
+        """
+        GIVEN: An external parser that declines (score None) and a built-in
+               that returns score 5.
+        WHEN:  get_parser_for_file() is called.
+        THEN:  The built-in parser is returned.
+        """
+
+        class DecliningExternal:
+            name = "declining-external"
+            version = "1.0"
+            author = "Third Party"
+            url = "https://example.com/declining"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return None
+
+        class AcceptingBuiltin:
+            name = "accepting-builtin"
+            version = "1.0"
+            author = "Core"
+            url = "https://example.com/accepting"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 5
+
+        registry = ParserRegistry()
+        registry.register_builtin(AcceptingBuiltin)
+        registry._external.append(DecliningExternal)
+        result = registry.get_parser_for_file("text/plain", "file.txt")
+        assert result is AcceptingBuiltin
+
+
+class TestDiscover:
+    """Verify entrypoint discovery in ParserRegistry.discover()."""
+
+    def test_discover_with_no_entrypoints(self) -> None:
+        """
+        GIVEN: No entrypoints are registered under 'paperless_ngx.parsers'.
+        WHEN:  discover() is called.
+        THEN:  _external remains empty and no errors are raised.
+        """
+        registry = ParserRegistry()
+
+        with patch(
+            "paperless.parsers.registry.entry_points",
+            return_value=[],
+        ):
+            registry.discover()
+
+        assert registry._external == []
+
+    def test_discover_adds_valid_external_parser(self) -> None:
+        """
+        GIVEN: One valid entrypoint whose loaded class has all required attrs.
+        WHEN:  discover() is called.
+        THEN:  The class is appended to _external.
+        """
+
+        class ValidExternal:
+            name = "valid-external"
+            version = "3.0.0"
+            author = "Someone"
+            url = "https://example.com/valid"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"application/pdf": ".pdf"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 5
+
+        mock_ep = MagicMock(spec=EntryPoint)
+        mock_ep.name = "valid_external"
+        mock_ep.load.return_value = ValidExternal
+
+        registry = ParserRegistry()
+
+        with patch(
+            "paperless.parsers.registry.entry_points",
+            return_value=[mock_ep],
+        ):
+            registry.discover()
+
+        assert ValidExternal in registry._external
+
+    def test_discover_skips_entrypoint_with_load_error(
+        self,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: An entrypoint whose load() method raises ImportError.
+        WHEN:  discover() is called.
+        THEN:  The entrypoint is skipped, an error is logged, and _external
+               remains empty.
+        """
+        mock_ep = MagicMock(spec=EntryPoint)
+        mock_ep.name = "broken_ep"
+        mock_ep.load.side_effect = ImportError("missing dependency")
+
+        registry = ParserRegistry()
+
+        with caplog.at_level(logging.ERROR, logger="paperless.parsers.registry"):
+            with patch(
+                "paperless.parsers.registry.entry_points",
+                return_value=[mock_ep],
+            ):
+                registry.discover()
+
+        assert registry._external == []
+        assert any(
+            "broken_ep" in record.message
+            for record in caplog.records
+            if record.levelno >= logging.ERROR
+        )
+
+    def test_discover_skips_entrypoint_with_missing_attrs(
+        self,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: A class loaded from an entrypoint that is missing the 'score'
+               attribute.
+        WHEN:  discover() is called.
+        THEN:  The entrypoint is skipped, a warning is logged, and _external
+               remains empty.
+        """
+
+        class MissingScore:
+            name = "missing-score"
+            version = "1.0"
+            author = "Someone"
+            url = "https://example.com"
+
+            # 'score' classmethod is intentionally absent.
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"text/plain": ".txt"}
+
+        mock_ep = MagicMock(spec=EntryPoint)
+        mock_ep.name = "missing_score_ep"
+        mock_ep.load.return_value = MissingScore
+
+        registry = ParserRegistry()
+
+        with caplog.at_level(logging.WARNING, logger="paperless.parsers.registry"):
+            with patch(
+                "paperless.parsers.registry.entry_points",
+                return_value=[mock_ep],
+            ):
+                registry.discover()
+
+        assert registry._external == []
+        assert any(
+            "missing_score_ep" in record.message
+            for record in caplog.records
+            if record.levelno >= logging.WARNING
+        )
+
+    def test_discover_logs_loaded_parser_info(
+        self,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: A valid entrypoint that loads successfully.
+        WHEN:  discover() is called.
+        THEN:  An INFO log message is emitted containing the parser name,
+               version, author, and entrypoint name.
+        """
+
+        class LoggableParser:
+            name = "loggable"
+            version = "4.2.0"
+            author = "Log Tester"
+            url = "https://example.com/loggable"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {"image/png": ".png"}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return 1
+
+        mock_ep = MagicMock(spec=EntryPoint)
+        mock_ep.name = "loggable_ep"
+        mock_ep.load.return_value = LoggableParser
+
+        registry = ParserRegistry()
+
+        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
+            with patch(
+                "paperless.parsers.registry.entry_points",
+                return_value=[mock_ep],
+            ):
+                registry.discover()
+
+        info_messages = " ".join(
+            r.message for r in caplog.records if r.levelno == logging.INFO
+        )
+        assert "loggable" in info_messages
+        assert "4.2.0" in info_messages
+        assert "Log Tester" in info_messages
+        assert "loggable_ep" in info_messages
+
+
+class TestLogSummary:
+    """Verify log output from ParserRegistry.log_summary()."""
+
+    def test_log_summary_with_no_external_parsers(
+        self,
+        dummy_parser_cls: type,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: A registry with one built-in parser and no external parsers.
+        WHEN:  log_summary() is called.
+        THEN:  The built-in parser name appears in the logs.
+        """
+        registry = ParserRegistry()
+        registry.register_builtin(dummy_parser_cls)
+
+        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
+            registry.log_summary()
+
+        all_messages = " ".join(r.message for r in caplog.records)
+        assert dummy_parser_cls.name in all_messages
+
+    def test_log_summary_with_external_parsers(
+        self,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: A registry with one external parser registered.
+        WHEN:  log_summary() is called.
+        THEN:  The external parser name, version, author, and url appear in
+               the log output.
+        """
+
+        class ExtParser:
+            name = "ext-parser"
+            version = "9.9.9"
+            author = "Ext Corp"
+            url = "https://ext.example.com"
+
+            @classmethod
+            def supported_mime_types(cls):
+                return {}
+
+            @classmethod
+            def score(cls, mime_type, filename, path=None):
+                return None
+
+        registry = ParserRegistry()
+        registry._external.append(ExtParser)
+
+        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
+            registry.log_summary()
+
+        all_messages = " ".join(r.message for r in caplog.records)
+        assert "ext-parser" in all_messages
+        assert "9.9.9" in all_messages
+        assert "Ext Corp" in all_messages
+        assert "https://ext.example.com" in all_messages
+
+    def test_log_summary_logs_no_third_party_message_when_none(
+        self,
+        caplog: pytest.LogCaptureFixture,
+    ) -> None:
+        """
+        GIVEN: A registry with no external parsers.
+        WHEN:  log_summary() is called.
+        THEN:  A message containing 'No third-party parsers discovered.' is
+               logged.
+        """
+        registry = ParserRegistry()
+
+        with caplog.at_level(logging.INFO, logger="paperless.parsers.registry"):
+            registry.log_summary()
+
+        all_messages = " ".join(r.message for r in caplog.records)
+        assert "No third-party parsers discovered." in all_messages

src/paperless/tests/test_websockets.py

@@ -1,186 +1,175 @@
-from unittest import mock
-
+import pytest
 from channels.layers import get_channel_layer
 from channels.testing import WebsocketCommunicator
-from django.test import TestCase
-from django.test import override_settings
+from pytest_mock import MockerFixture
 
 from documents.plugins.helpers import DocumentsStatusManager
 from documents.plugins.helpers import ProgressManager
 from documents.plugins.helpers import ProgressStatusOptions
 from paperless.asgi import application
 
-TEST_CHANNEL_LAYERS = {
-    "default": {
-        "BACKEND": "channels.layers.InMemoryChannelLayer",
-    },
-}
 
+class TestWebSockets:
+    @pytest.fixture(autouse=True)
+    def anyio_backend(self) -> str:
+        return "asyncio"
 
-@override_settings(CHANNEL_LAYERS=TEST_CHANNEL_LAYERS)
-class TestWebSockets(TestCase):
+    @pytest.mark.anyio
     async def test_no_auth(self) -> None:
         communicator = WebsocketCommunicator(application, "/ws/status/")
         connected, _ = await communicator.connect()
-        self.assertFalse(connected)
+        assert not connected
         await communicator.disconnect()
 
-    @mock.patch("paperless.consumers.StatusConsumer.close")
-    @mock.patch("paperless.consumers.StatusConsumer._authenticated")
-    async def test_close_on_no_auth(self, _authenticated, mock_close) -> None:
-        _authenticated.return_value = True
+    @pytest.mark.anyio
+    async def test_close_on_no_auth(self, mocker: MockerFixture) -> None:
+        mock_auth = mocker.patch(
+            "paperless.consumers.StatusConsumer._authenticated",
+            return_value=True,
+        )
+        mock_close = mocker.patch(
+            "paperless.consumers.StatusConsumer.close",
+            new_callable=mocker.AsyncMock,
+        )
 
         communicator = WebsocketCommunicator(application, "/ws/status/")
         connected, _ = await communicator.connect()
-        self.assertTrue(connected)
-
-        message = {"type": "status_update", "data": {"task_id": "test"}}
-
-        _authenticated.return_value = False
+        assert connected
 
+        mock_auth.return_value = False
         channel_layer = get_channel_layer()
+        assert channel_layer is not None
+
         await channel_layer.group_send(
             "status_updates",
-            message,
+            {"type": "status_update", "data": {"task_id": "test"}},
         )
         await communicator.receive_nothing()
-
-        mock_close.assert_called_once()
+        mock_close.assert_awaited_once()
         mock_close.reset_mock()
 
-        message = {
-            "type": "document_updated",
-            "data": {"document_id": 10, "modified": "2026-02-17T00:00:00Z"},
-        }
-
         await channel_layer.group_send(
             "status_updates",
-            message,
+            {
+                "type": "document_updated",
+                "data": {"document_id": 10, "modified": "2026-02-17T00:00:00Z"},
+            },
         )
         await communicator.receive_nothing()
-
-        mock_close.assert_called_once()
+        mock_close.assert_awaited_once()
         mock_close.reset_mock()
 
-        message = {"type": "documents_deleted", "data": {"documents": [1, 2, 3]}}
-
         await channel_layer.group_send(
             "status_updates",
-            message,
+            {"type": "documents_deleted", "data": {"documents": [1, 2, 3]}},
         )
         await communicator.receive_nothing()
+        mock_close.assert_awaited_once()
 
-        mock_close.assert_called_once()
-
-    @mock.patch("paperless.consumers.StatusConsumer._authenticated")
-    async def test_auth(self, _authenticated) -> None:
-        _authenticated.return_value = True
-
-        communicator = WebsocketCommunicator(application, "/ws/status/")
-        connected, _ = await communicator.connect()
-        self.assertTrue(connected)
-
-        await communicator.disconnect()
-
-    @mock.patch("paperless.consumers.StatusConsumer._authenticated")
-    async def test_receive_status_update(self, _authenticated) -> None:
-        _authenticated.return_value = True
-
-        communicator = WebsocketCommunicator(application, "/ws/status/")
-        connected, _ = await communicator.connect()
-        self.assertTrue(connected)
-
-        message = {"type": "status_update", "data": {"task_id": "test"}}
-
-        channel_layer = get_channel_layer()
-        await channel_layer.group_send(
-            "status_updates",
-            message,
+    @pytest.mark.anyio
+    async def test_auth(self, mocker: MockerFixture) -> None:
+        mocker.patch(
+            "paperless.consumers.StatusConsumer._authenticated",
+            return_value=True,
         )
 
-        response = await communicator.receive_json_from()
-
-        self.assertEqual(response, message)
+        communicator = WebsocketCommunicator(application, "/ws/status/")
+        connected, _ = await communicator.connect()
+        assert connected
 
         await communicator.disconnect()
 
-    async def test_status_update_check_perms(self) -> None:
+    @pytest.mark.anyio
+    async def test_receive_status_update(self, mocker: MockerFixture) -> None:
+        mocker.patch(
+            "paperless.consumers.StatusConsumer._authenticated",
+            return_value=True,
+        )
+
         communicator = WebsocketCommunicator(application, "/ws/status/")
-
-        communicator.scope["user"] = mock.Mock()
-        communicator.scope["user"].is_authenticated = True
-        communicator.scope["user"].is_superuser = False
-        communicator.scope["user"].id = 1
-
         connected, _ = await communicator.connect()
-        self.assertTrue(connected)
+        assert connected
 
-        # Test as owner
+        message = {"type": "status_update", "data": {"task_id": "test"}}
+        channel_layer = get_channel_layer()
+        assert channel_layer is not None
+        await channel_layer.group_send("status_updates", message)
+
+        assert await communicator.receive_json_from() == message
+
+        await communicator.disconnect()
+
+    @pytest.mark.anyio
+    async def test_status_update_check_perms(self, mocker: MockerFixture) -> None:
+        user = mocker.MagicMock()
+        user.is_authenticated = True
+        user.is_superuser = False
+        user.id = 1
+
+        communicator = WebsocketCommunicator(application, "/ws/status/")
+        communicator.scope["user"] = user  # type: ignore[typeddict-unknown-key]
+        connected, _ = await communicator.connect()
+        assert connected
+
+        channel_layer = get_channel_layer()
+        assert channel_layer is not None
+
+        # Message received as owner
         message = {"type": "status_update", "data": {"task_id": "test", "owner_id": 1}}
-        channel_layer = get_channel_layer()
-        await channel_layer.group_send(
-            "status_updates",
-            message,
-        )
-        response = await communicator.receive_json_from()
-        self.assertEqual(response, message)
+        await channel_layer.group_send("status_updates", message)
+        assert await communicator.receive_json_from() == message
 
-        # Test with a group that the user belongs to
-        communicator.scope["user"].groups.filter.return_value.exists.return_value = True
+        # Message received via group membership
+        user.groups.filter.return_value.aexists = mocker.AsyncMock(return_value=True)
         message = {
             "type": "status_update",
             "data": {"task_id": "test", "owner_id": 2, "groups_can_view": [1]},
         }
-        channel_layer = get_channel_layer()
-        await channel_layer.group_send(
-            "status_updates",
-            message,
-        )
-        response = await communicator.receive_json_from()
-        self.assertEqual(response, message)
+        await channel_layer.group_send("status_updates", message)
+        assert await communicator.receive_json_from() == message
 
-        # Test with a different owner_id
+        # Message not received for different owner with no group match
+        user.groups.filter.return_value.aexists = mocker.AsyncMock(return_value=False)
         message = {"type": "status_update", "data": {"task_id": "test", "owner_id": 2}}
-        channel_layer = get_channel_layer()
-        await channel_layer.group_send(
-            "status_updates",
-            message,
-        )
-        response = await communicator.receive_nothing()
-        self.assertNotEqual(response, message)
+        await channel_layer.group_send("status_updates", message)
+        assert await communicator.receive_nothing()
+
         await communicator.disconnect()
 
-    @mock.patch("paperless.consumers.StatusConsumer._authenticated")
-    async def test_receive_documents_deleted(self, _authenticated) -> None:
-        _authenticated.return_value = True
+    @pytest.mark.anyio
+    async def test_receive_documents_deleted(self, mocker: MockerFixture) -> None:
+        mocker.patch(
+            "paperless.consumers.StatusConsumer._authenticated",
+            return_value=True,
+        )
 
         communicator = WebsocketCommunicator(application, "/ws/status/")
         connected, _ = await communicator.connect()
-        self.assertTrue(connected)
+        assert connected
 
         message = {"type": "documents_deleted", "data": {"documents": [1, 2, 3]}}
-
         channel_layer = get_channel_layer()
-        await channel_layer.group_send(
-            "status_updates",
-            message,
-        )
+        assert channel_layer is not None
+        await channel_layer.group_send("status_updates", message)
 
-        response = await communicator.receive_json_from()
-
-        self.assertEqual(response, message)
+        assert await communicator.receive_json_from() == message
 
         await communicator.disconnect()
 
-    @mock.patch("paperless.consumers.StatusConsumer._can_view")
-    @mock.patch("paperless.consumers.StatusConsumer._authenticated")
-    async def test_receive_document_updated(self, _authenticated, _can_view) -> None:
-        _authenticated.return_value = True
-        _can_view.return_value = True
+    @pytest.mark.anyio
+    async def test_receive_document_updated(self, mocker: MockerFixture) -> None:
+        mocker.patch(
+            "paperless.consumers.StatusConsumer._authenticated",
+            return_value=True,
+        )
+        mocker.patch(
+            "paperless.consumers.StatusConsumer._can_view",
+            return_value=True,
+        )
 
         communicator = WebsocketCommunicator(application, "/ws/status/")
         connected, _ = await communicator.connect()
-        self.assertTrue(connected)
+        assert connected
 
         message = {
             "type": "document_updated",
@@ -192,67 +181,52 @@ class TestWebSockets(TestCase):
                 "groups_can_view": [],
             },
         }
-
         channel_layer = get_channel_layer()
         assert channel_layer is not None
-        await channel_layer.group_send(
-            "status_updates",
-            message,
-        )
+        await channel_layer.group_send("status_updates", message)
 
-        response = await communicator.receive_json_from()
-
-        self.assertEqual(response, message)
+        assert await communicator.receive_json_from() == message
 
         await communicator.disconnect()
 
-    @mock.patch("channels.layers.InMemoryChannelLayer.group_send")
-    def test_manager_send_progress(self, mock_group_send) -> None:
+    def test_manager_send_progress(self, mocker: MockerFixture) -> None:
+        mock_group_send = mocker.patch(
+            "channels.layers.InMemoryChannelLayer.group_send",
+        )
+
         with ProgressManager(task_id="test") as manager:
             manager.send_progress(
                 ProgressStatusOptions.STARTED,
                 "Test message",
                 1,
                 10,
-                extra_args={
-                    "foo": "bar",
-                },
+                extra_args={"foo": "bar"},
             )
 
-        message = mock_group_send.call_args[0][1]
-
-        self.assertEqual(
-            message,
-            {
-                "type": "status_update",
-                "data": {
-                    "filename": None,
-                    "task_id": "test",
-                    "current_progress": 1,
-                    "max_progress": 10,
-                    "status": ProgressStatusOptions.STARTED,
-                    "message": "Test message",
-                    "foo": "bar",
-                },
+        assert mock_group_send.call_args[0][1] == {
+            "type": "status_update",
+            "data": {
+                "filename": None,
+                "task_id": "test",
+                "current_progress": 1,
+                "max_progress": 10,
+                "status": ProgressStatusOptions.STARTED,
+                "message": "Test message",
+                "foo": "bar",
             },
+        }
+
+    def test_manager_send_documents_deleted(self, mocker: MockerFixture) -> None:
+        mock_group_send = mocker.patch(
+            "channels.layers.InMemoryChannelLayer.group_send",
         )
 
-    @mock.patch("channels.layers.InMemoryChannelLayer.group_send")
-    def test_manager_send_documents_deleted(
-        self,
-        mock_group_send: mock.MagicMock,
-    ) -> None:
         with DocumentsStatusManager() as manager:
             manager.send_documents_deleted([1, 2, 3])
 
-        message = mock_group_send.call_args[0][1]
-
-        self.assertEqual(
-            message,
-            {
-                "type": "documents_deleted",
-                "data": {
-                    "documents": [1, 2, 3],
-                },
+        assert mock_group_send.call_args[0][1] == {
+            "type": "documents_deleted",
+            "data": {
+                "documents": [1, 2, 3],
             },
-        )
+        }

src/paperless_ai/client.py

@@ -7,7 +7,6 @@ if TYPE_CHECKING:
     from llama_index.llms.openai import OpenAI
 
 from paperless.config import AIConfig
-from paperless.network import validate_outbound_http_url
 from paperless_ai.base_model import DocumentClassifierSchema
 
 logger = logging.getLogger("paperless_ai.client")
@@ -26,28 +25,17 @@ class AIClient:
         if self.settings.llm_backend == "ollama":
             from llama_index.llms.ollama import Ollama
 
-            endpoint = self.settings.llm_endpoint or "http://localhost:11434"
-            validate_outbound_http_url(
-                endpoint,
-                allow_internal=self.settings.llm_allow_internal_endpoints,
-            )
             return Ollama(
                 model=self.settings.llm_model or "llama3.1",
-                base_url=endpoint,
+                base_url=self.settings.llm_endpoint or "http://localhost:11434",
                 request_timeout=120,
             )
         elif self.settings.llm_backend == "openai":
             from llama_index.llms.openai import OpenAI
 
-            endpoint = self.settings.llm_endpoint or None
-            if endpoint:
-                validate_outbound_http_url(
-                    endpoint,
-                    allow_internal=self.settings.llm_allow_internal_endpoints,
-                )
             return OpenAI(
                 model=self.settings.llm_model or "gpt-3.5-turbo",
-                api_base=endpoint,
+                api_base=self.settings.llm_endpoint or None,
                 api_key=self.settings.llm_api_key,
             )
         else:

src/paperless_ai/embedding.py

@@ -12,7 +12,6 @@ from documents.models import Document
 from documents.models import Note
 from paperless.config import AIConfig
 from paperless.models import LLMEmbeddingBackend
-from paperless.network import validate_outbound_http_url
 
 
 def get_embedding_model() -> "BaseEmbedding":
@@ -22,16 +21,10 @@ def get_embedding_model() -> "BaseEmbedding":
         case LLMEmbeddingBackend.OPENAI:
             from llama_index.embeddings.openai import OpenAIEmbedding
 
-            endpoint = config.llm_endpoint or None
-            if endpoint:
-                validate_outbound_http_url(
-                    endpoint,
-                    allow_internal=config.llm_allow_internal_endpoints,
-                )
             return OpenAIEmbedding(
                 model=config.llm_embedding_model or "text-embedding-3-small",
                 api_key=config.llm_api_key,
-                api_base=endpoint,
+                api_base=config.llm_endpoint or None,
             )
         case LLMEmbeddingBackend.HUGGINGFACE:
             from llama_index.embeddings.huggingface import HuggingFaceEmbedding

src/paperless_ai/tests/test_client.py

@@ -12,7 +12,6 @@ from paperless_ai.client import AIClient
 def mock_ai_config():
     with patch("paperless_ai.client.AIConfig") as MockAIConfig:
         mock_config = MagicMock()
-        mock_config.llm_allow_internal_endpoints = True
         MockAIConfig.return_value = mock_config
         yield mock_config
 
@@ -60,17 +59,6 @@ def test_get_llm_openai(mock_ai_config, mock_openai_llm):
     assert client.llm == mock_openai_llm.return_value
 
 
-def test_get_llm_openai_blocks_internal_endpoint_when_disallowed(mock_ai_config):
-    mock_ai_config.llm_backend = "openai"
-    mock_ai_config.llm_model = "test_model"
-    mock_ai_config.llm_api_key = "test_api_key"
-    mock_ai_config.llm_endpoint = "http://127.0.0.1:1234"
-    mock_ai_config.llm_allow_internal_endpoints = False
-
-    with pytest.raises(ValueError, match="non-public address"):
-        AIClient()
-
-
 def test_get_llm_unsupported_backend(mock_ai_config):
     mock_ai_config.llm_backend = "unsupported"
 

src/paperless_ai/tests/test_embedding.py

@@ -15,7 +15,6 @@ from paperless_ai.embedding import get_embedding_model
 @pytest.fixture
 def mock_ai_config():
     with patch("paperless_ai.embedding.AIConfig") as MockAIConfig:
-        MockAIConfig.return_value.llm_allow_internal_endpoints = True
         yield MockAIConfig
 
 
@@ -78,19 +77,6 @@ def test_get_embedding_model_openai(mock_ai_config):
         assert model == MockOpenAIEmbedding.return_value
 
 
-def test_get_embedding_model_openai_blocks_internal_endpoint_when_disallowed(
-    mock_ai_config,
-):
-    mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.OPENAI
-    mock_ai_config.return_value.llm_embedding_model = "text-embedding-3-small"
-    mock_ai_config.return_value.llm_api_key = "test_api_key"
-    mock_ai_config.return_value.llm_endpoint = "http://127.0.0.1:11434"
-    mock_ai_config.return_value.llm_allow_internal_endpoints = False
-
-    with pytest.raises(ValueError, match="non-public address"):
-        get_embedding_model()
-
-
 def test_get_embedding_model_huggingface(mock_ai_config):
     mock_ai_config.return_value.llm_embedding_backend = LLMEmbeddingBackend.HUGGINGFACE
     mock_ai_config.return_value.llm_embedding_model = (

src/paperless_remote/parsers.py

@@ -1,118 +0,0 @@
-from pathlib import Path
-
-from django.conf import settings
-
-from paperless_tesseract.parsers import RasterisedDocumentParser
-
-
-class RemoteEngineConfig:
-    def __init__(
-        self,
-        engine: str,
-        api_key: str | None = None,
-        endpoint: str | None = None,
-    ):
-        self.engine = engine
-        self.api_key = api_key
-        self.endpoint = endpoint
-
-    def engine_is_valid(self):
-        valid = self.engine in ["azureai"] and self.api_key is not None
-        if self.engine == "azureai":
-            valid = valid and self.endpoint is not None
-        return valid
-
-
-class RemoteDocumentParser(RasterisedDocumentParser):
-    """
-    This parser uses a remote OCR engine to parse documents. Currently, it supports Azure AI Vision
-    as this is the only service that provides a remote OCR API with text-embedded PDF output.
-    """
-
-    logging_name = "paperless.parsing.remote"
-
-    def get_settings(self) -> RemoteEngineConfig:
-        """
-        Returns the configuration for the remote OCR engine, loaded from Django settings.
-        """
-        return RemoteEngineConfig(
-            engine=settings.REMOTE_OCR_ENGINE,
-            api_key=settings.REMOTE_OCR_API_KEY,
-            endpoint=settings.REMOTE_OCR_ENDPOINT,
-        )
-
-    def supported_mime_types(self):
-        if self.settings.engine_is_valid():
-            return {
-                "application/pdf": ".pdf",
-                "image/png": ".png",
-                "image/jpeg": ".jpg",
-                "image/tiff": ".tiff",
-                "image/bmp": ".bmp",
-                "image/gif": ".gif",
-                "image/webp": ".webp",
-            }
-        else:
-            return {}
-
-    def azure_ai_vision_parse(
-        self,
-        file: Path,
-    ) -> str | None:
-        """
-        Uses Azure AI Vision to parse the document and return the text content.
-        It requests a searchable PDF output with embedded text.
-        The PDF is saved to the archive_path attribute.
-        Returns the text content extracted from the document.
-        If the parsing fails, it returns None.
-        """
-        from azure.ai.documentintelligence import DocumentIntelligenceClient
-        from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
-        from azure.ai.documentintelligence.models import AnalyzeOutputOption
-        from azure.ai.documentintelligence.models import DocumentContentFormat
-        from azure.core.credentials import AzureKeyCredential
-
-        client = DocumentIntelligenceClient(
-            endpoint=self.settings.endpoint,
-            credential=AzureKeyCredential(self.settings.api_key),
-        )
-
-        try:
-            with file.open("rb") as f:
-                analyze_request = AnalyzeDocumentRequest(bytes_source=f.read())
-                poller = client.begin_analyze_document(
-                    model_id="prebuilt-read",
-                    body=analyze_request,
-                    output_content_format=DocumentContentFormat.TEXT,
-                    output=[AnalyzeOutputOption.PDF],  # request searchable PDF output
-                    content_type="application/json",
-                )
-
-            poller.wait()
-            result_id = poller.details["operation_id"]
-            result = poller.result()
-
-            # Download the PDF with embedded text
-            self.archive_path = self.tempdir / "archive.pdf"
-            with self.archive_path.open("wb") as f:
-                for chunk in client.get_analyze_result_pdf(
-                    model_id="prebuilt-read",
-                    result_id=result_id,
-                ):
-                    f.write(chunk)
-            return result.content
-        except Exception as e:
-            self.log.error(f"Azure AI Vision parsing failed: {e}")
-        finally:
-            client.close()
-
-        return None
-
-    def parse(self, document_path: Path, mime_type, file_name=None):
-        if not self.settings.engine_is_valid():
-            self.log.warning(
-                "No valid remote parser engine is configured, content will be empty.",
-            )
-            self.text = ""
-        elif self.settings.engine == "azureai":
-            self.text = self.azure_ai_vision_parse(document_path)

src/paperless_remote/signals.py

@@ -1,16 +1,36 @@
-def get_parser(*args, **kwargs):
-    from paperless_remote.parsers import RemoteDocumentParser
+from __future__ import annotations
 
+from typing import Any
+
+
+def get_parser(*args: Any, **kwargs: Any) -> Any:
+    from paperless.parsers.remote import RemoteDocumentParser
+
+    # The new RemoteDocumentParser does not accept the progress_callback
+    # kwarg injected by the old signal-based consumer.  logging_group is
+    # forwarded as a positional arg.
+    # Phase 4 will replace this signal path with the new ParserRegistry.
+    kwargs.pop("progress_callback", None)
     return RemoteDocumentParser(*args, **kwargs)
 
 
-def get_supported_mime_types():
-    from paperless_remote.parsers import RemoteDocumentParser
+def get_supported_mime_types() -> dict[str, str]:
+    from django.conf import settings
 
-    return RemoteDocumentParser(None).supported_mime_types()
+    from paperless.parsers.remote import RemoteDocumentParser
+    from paperless.parsers.remote import RemoteEngineConfig
+
+    config = RemoteEngineConfig(
+        engine=settings.REMOTE_OCR_ENGINE,
+        api_key=settings.REMOTE_OCR_API_KEY,
+        endpoint=settings.REMOTE_OCR_ENDPOINT,
+    )
+    if not config.engine_is_valid():
+        return {}
+    return RemoteDocumentParser.supported_mime_types()
 
 
-def remote_consumer_declaration(sender, **kwargs):
+def remote_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
     return {
         "parser": get_parser,
         "weight": 5,

src/paperless_remote/tests/test_parser.py

@@ -1,131 +0,0 @@
-import uuid
-from pathlib import Path
-from unittest import mock
-
-from django.test import TestCase
-from django.test import override_settings
-
-from documents.tests.utils import DirectoriesMixin
-from documents.tests.utils import FileSystemAssertsMixin
-from paperless_remote.parsers import RemoteDocumentParser
-from paperless_remote.signals import get_parser
-
-
-class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
-    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
-
-    def assertContainsStrings(self, content: str, strings: list[str]) -> None:
-        # Asserts that all strings appear in content, in the given order.
-        indices = []
-        for s in strings:
-            if s in content:
-                indices.append(content.index(s))
-            else:
-                self.fail(f"'{s}' is not in '{content}'")
-        self.assertListEqual(indices, sorted(indices))
-
-    @mock.patch("paperless_tesseract.parsers.run_subprocess")
-    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
-    def test_get_text_with_azure(self, mock_client_cls, mock_subprocess) -> None:
-        # Arrange mock Azure client
-        mock_client = mock.Mock()
-        mock_client_cls.return_value = mock_client
-
-        # Simulate poller result and its `.details`
-        mock_poller = mock.Mock()
-        mock_poller.wait.return_value = None
-        mock_poller.details = {"operation_id": "fake-op-id"}
-        mock_client.begin_analyze_document.return_value = mock_poller
-        mock_poller.result.return_value.content = "This is a test document."
-
-        # Return dummy PDF bytes
-        mock_client.get_analyze_result_pdf.return_value = [
-            b"%PDF-",
-            b"1.7 ",
-            b"FAKEPDF",
-        ]
-
-        # Simulate pdftotext by writing dummy text to sidecar file
-        def fake_run(cmd, *args, **kwargs) -> None:
-            with Path(cmd[-1]).open("w", encoding="utf-8") as f:
-                f.write("This is a test document.")
-
-        mock_subprocess.side_effect = fake_run
-
-        with override_settings(
-            REMOTE_OCR_ENGINE="azureai",
-            REMOTE_OCR_API_KEY="somekey",
-            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
-        ):
-            parser = get_parser(uuid.uuid4())
-            parser.parse(
-                self.SAMPLE_FILES / "simple-digital.pdf",
-                "application/pdf",
-            )
-
-            self.assertContainsStrings(
-                parser.text.strip(),
-                ["This is a test document."],
-            )
-
-    @mock.patch("azure.ai.documentintelligence.DocumentIntelligenceClient")
-    def test_get_text_with_azure_error_logged_and_returns_none(
-        self,
-        mock_client_cls,
-    ) -> None:
-        mock_client = mock.Mock()
-        mock_client.begin_analyze_document.side_effect = RuntimeError("fail")
-        mock_client_cls.return_value = mock_client
-
-        with override_settings(
-            REMOTE_OCR_ENGINE="azureai",
-            REMOTE_OCR_API_KEY="somekey",
-            REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
-        ):
-            parser = get_parser(uuid.uuid4())
-            with mock.patch.object(parser.log, "error") as mock_log_error:
-                parser.parse(
-                    self.SAMPLE_FILES / "simple-digital.pdf",
-                    "application/pdf",
-                )
-
-        self.assertIsNone(parser.text)
-        mock_client.begin_analyze_document.assert_called_once()
-        mock_client.close.assert_called_once()
-        mock_log_error.assert_called_once()
-        self.assertIn(
-            "Azure AI Vision parsing failed",
-            mock_log_error.call_args[0][0],
-        )
-
-    @override_settings(
-        REMOTE_OCR_ENGINE="azureai",
-        REMOTE_OCR_API_KEY="key",
-        REMOTE_OCR_ENDPOINT="https://endpoint.cognitiveservices.azure.com",
-    )
-    def test_supported_mime_types_valid_config(self) -> None:
-        parser = RemoteDocumentParser(uuid.uuid4())
-        expected_types = {
-            "application/pdf": ".pdf",
-            "image/png": ".png",
-            "image/jpeg": ".jpg",
-            "image/tiff": ".tiff",
-            "image/bmp": ".bmp",
-            "image/gif": ".gif",
-            "image/webp": ".webp",
-        }
-        self.assertEqual(parser.supported_mime_types(), expected_types)
-
-    def test_supported_mime_types_invalid_config(self) -> None:
-        parser = get_parser(uuid.uuid4())
-        self.assertEqual(parser.supported_mime_types(), {})
-
-    @override_settings(
-        REMOTE_OCR_ENGINE=None,
-        REMOTE_OCR_API_KEY=None,
-        REMOTE_OCR_ENDPOINT=None,
-    )
-    def test_parse_with_invalid_config(self) -> None:
-        parser = get_parser(uuid.uuid4())
-        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
-        self.assertEqual(parser.text, "")

src/paperless_tesseract/parsers.py

@@ -221,7 +221,7 @@ class RasterisedDocumentParser(DocumentParser):
         if TYPE_CHECKING:
             assert isinstance(self.settings, OcrConfig)
         ocrmypdf_args = {
-            "input_file": input_file,
+            "input_file_or_options": input_file,
             "output_file": output_file,
             # need to use threads, since this will be run in daemonized
             # processes via the task library.
@@ -285,7 +285,7 @@ class RasterisedDocumentParser(DocumentParser):
                     "for compatibility with img2pdf",
                 )
                 # Replace the input file with the non-alpha
-                ocrmypdf_args["input_file"] = self.remove_alpha(input_file)
+                ocrmypdf_args["input_file_or_options"] = self.remove_alpha(input_file)
 
             if dpi:
                 self.log.debug(f"Detected DPI for image {input_file}: {dpi}")

src/paperless_tesseract/tests/test_parser.py

@@ -778,7 +778,7 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
             safe_fallback=False,
         )
 
-        self.assertEqual(params["input_file"], "input.pdf")
+        self.assertEqual(params["input_file_or_options"], "input.pdf")
         self.assertEqual(params["output_file"], "output.pdf")
         self.assertEqual(params["sidecar"], "sidecar.txt")
 

src/paperless_text/parsers.py

@@ -1,50 +0,0 @@
-from pathlib import Path
-
-from django.conf import settings
-from PIL import Image
-from PIL import ImageDraw
-from PIL import ImageFont
-
-from documents.parsers import DocumentParser
-
-
-class TextDocumentParser(DocumentParser):
-    """
-    This parser directly parses a text document (.txt, .md, or .csv)
-    """
-
-    logging_name = "paperless.parsing.text"
-
-    def get_thumbnail(self, document_path: Path, mime_type, file_name=None) -> Path:
-        # Avoid reading entire file into memory
-        max_chars = 100_000
-        file_size_limit = 50 * 1024 * 1024
-
-        if document_path.stat().st_size > file_size_limit:
-            text = "[File too large to preview]"
-        else:
-            with Path(document_path).open("r", encoding="utf-8", errors="replace") as f:
-                text = f.read(max_chars)
-
-        img = Image.new("RGB", (500, 700), color="white")
-        draw = ImageDraw.Draw(img)
-        font = ImageFont.truetype(
-            font=settings.THUMBNAIL_FONT_NAME,
-            size=20,
-            layout_engine=ImageFont.Layout.BASIC,
-        )
-        draw.multiline_text((5, 5), text, font=font, fill="black", spacing=4)
-
-        out_path = self.tempdir / "thumb.webp"
-        img.save(out_path, format="WEBP")
-
-        return out_path
-
-    def parse(self, document_path, mime_type, file_name=None) -> None:
-        self.text = self.read_file_handle_unicode_errors(document_path)
-
-    def get_settings(self) -> None:
-        """
-        This parser does not implement additional settings yet
-        """
-        return None

src/paperless_text/signals.py

@@ -1,10 +1,20 @@
-def get_parser(*args, **kwargs):
-    from paperless_text.parsers import TextDocumentParser
+from __future__ import annotations
 
+from typing import Any
+
+
+def get_parser(*args: Any, **kwargs: Any) -> Any:
+    from paperless.parsers.text import TextDocumentParser
+
+    # The new TextDocumentParser does not accept the progress_callback
+    # kwarg injected by the old signal-based consumer.  logging_group is
+    # forwarded as a positional arg.
+    # Phase 4 will replace this signal path with the new ParserRegistry.
+    kwargs.pop("progress_callback", None)
     return TextDocumentParser(*args, **kwargs)
 
 
-def text_consumer_declaration(sender, **kwargs):
+def text_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
     return {
         "parser": get_parser,
         "weight": 10,

src/paperless_text/tests/conftest.py

@@ -1,30 +0,0 @@
-from collections.abc import Generator
-from pathlib import Path
-
-import pytest
-
-from paperless_text.parsers import TextDocumentParser
-
-
-@pytest.fixture(scope="session")
-def sample_dir() -> Path:
-    return (Path(__file__).parent / Path("samples")).resolve()
-
-
-@pytest.fixture()
-def text_parser() -> Generator[TextDocumentParser, None, None]:
-    try:
-        parser = TextDocumentParser(logging_group=None)
-        yield parser
-    finally:
-        parser.cleanup()
-
-
-@pytest.fixture(scope="session")
-def sample_txt_file(sample_dir: Path) -> Path:
-    return sample_dir / "test.txt"
-
-
-@pytest.fixture(scope="session")
-def malformed_txt_file(sample_dir: Path) -> Path:
-    return sample_dir / "decode_error.txt"

src/paperless_text/tests/test_parser.py

@@ -1,69 +0,0 @@
-import tempfile
-from pathlib import Path
-
-from paperless_text.parsers import TextDocumentParser
-
-
-class TestTextParser:
-    def test_thumbnail(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        # just make sure that it does not crash
-        f = text_parser.get_thumbnail(sample_txt_file, "text/plain")
-        assert f.exists()
-        assert f.is_file()
-
-    def test_parse(
-        self,
-        text_parser: TextDocumentParser,
-        sample_txt_file: Path,
-    ) -> None:
-        text_parser.parse(sample_txt_file, "text/plain")
-
-        assert text_parser.get_text() == "This is a test file.\n"
-        assert text_parser.get_archive_path() is None
-
-    def test_parse_invalid_bytes(
-        self,
-        text_parser: TextDocumentParser,
-        malformed_txt_file: Path,
-    ) -> None:
-        """
-        GIVEN:
-            - Text file which contains invalid UTF bytes
-        WHEN:
-            - The file is parsed
-        THEN:
-            - Parsing continues
-            - Invalid bytes are removed
-        """
-
-        text_parser.parse(malformed_txt_file, "text/plain")
-
-        assert text_parser.get_text() == "Pantothens<EFBFBD>ure\n"
-        assert text_parser.get_archive_path() is None
-
-    def test_thumbnail_large_file(self, text_parser: TextDocumentParser) -> None:
-        """
-        GIVEN:
-            - A very large text file (>50MB)
-        WHEN:
-            - A thumbnail is requested
-        THEN:
-            - A thumbnail is created without reading the entire file into memory
-        """
-        with tempfile.NamedTemporaryFile(
-            delete=False,
-            mode="w",
-            encoding="utf-8",
-            suffix=".txt",
-        ) as tmp:
-            tmp.write("A" * (51 * 1024 * 1024))  # 51 MB of 'A'
-            large_file = Path(tmp.name)
-
-            thumb = text_parser.get_thumbnail(large_file, "text/plain")
-            assert thumb.exists()
-            assert thumb.is_file()
-            large_file.unlink()

src/paperless_tika/tests/conftest.py

@@ -12,6 +12,7 @@ def tika_parser() -> Generator[TikaDocumentParser, None, None]:
         parser = TikaDocumentParser(logging_group=None)
         yield parser
     finally:
+        # TODO(stumpylog): Cleanup once all parsers are handled
         parser.cleanup()
 
 

uv.lock

@@ -831,6 +831,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2d/82/e5d2c1c67d19841e9edc74954c827444ae826978499bde3dfc1d007c8c11/deepmerge-2.0-py3-none-any.whl", hash = "sha256:6de9ce507115cff0bed95ff0ce9ecc31088ef50cbdf09bc90a09349a318b3d00", size = 13475, upload-time = "2024-08-30T05:31:48.659Z" },
 ]
 
+[[package]]
+name = "defusedxml"
+version = "0.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0f/d5/c66da9b79e5bdb124974bfe172b4daf3c984ebd9c2a06e2b8a4dc7331c72/defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69", size = 75520, upload-time = "2021-03-08T10:59:26.269Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61", size = 25604, upload-time = "2021-03-08T10:59:24.45Z" },
+]
+
 [[package]]
 name = "deprecated"
 version = "1.3.1"
@@ -1172,14 +1181,14 @@ wheels = [
 
 [[package]]
 name = "drf-spectacular-sidecar"
-version = "2026.1.1"
+version = "2026.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/1e/81/c7b0e3ccbd5a039c4f4fcfecf88391a666ca1406a953886e2f39295b1c90/drf_spectacular_sidecar-2026.1.1.tar.gz", hash = "sha256:6f7c173a8ddbbbdafc7a27e028614b65f07a89ca90f996a432d57460463b56be", size = 2468060, upload-time = "2026-01-01T11:27:12.682Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/aa/42/2f8c1b2846399d47094ec414bc0d6a7cce7ba95fd6545a97285eee89f7f1/drf_spectacular_sidecar-2026.3.1.tar.gz", hash = "sha256:5b7fedad66e3851f2f442480792c08115d79217959d01645b93d3d2258938be1", size = 2461501, upload-time = "2026-03-01T11:31:19.708Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/db/96/38725edda526f3e9e597f531beeec94b0ef433d9494f06a13b7636eecb6e/drf_spectacular_sidecar-2026.1.1-py3-none-any.whl", hash = "sha256:af8df62f1b594ec280351336d837eaf2402ab25a6bc2a1fad7aee9935821070f", size = 2489520, upload-time = "2026-01-01T11:27:11.056Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/28/2d5e64d101ebc5180674fcaf7b5a35e398e2f8d9688b2e8d52b0e1394e7d/drf_spectacular_sidecar-2026.3.1-py3-none-any.whl", hash = "sha256:864edb83e022e13e3941c325c3cc0c954c843fa2e1d0bc95e81887664b2d3dad", size = 2481725, upload-time = "2026-03-01T11:31:18.469Z" },
 ]
 
 [[package]]
@@ -1230,11 +1239,11 @@ wheels = [
 
 [[package]]
 name = "faker"
-version = "40.5.1"
+version = "40.8.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/03/2a/96fff3edcb10f6505143448a4b91535f77b74865cec45be52690ee280443/faker-40.5.1.tar.gz", hash = "sha256:70222361cd82aa10cb86066d1a4e8f47f2bcdc919615c412045a69c4e6da0cd3", size = 1952684, upload-time = "2026-02-23T21:34:38.362Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/70/03/14428edc541467c460d363f6e94bee9acc271f3e62470630fc9a647d0cf2/faker-40.8.0.tar.gz", hash = "sha256:936a3c9be6c004433f20aa4d99095df5dec82b8c7ad07459756041f8c1728875", size = 1956493, upload-time = "2026-03-04T16:18:48.161Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/4d/a9/1eed4db92d0aec2f9bfdf1faae0ab0418b5e121dda5701f118a7a4f0cd6a/faker-40.5.1-py3-none-any.whl", hash = "sha256:c69640c1e13bad49b4bcebcbf1b52f9f1a872b6ea186c248ada34d798f1661bf", size = 1987053, upload-time = "2026-02-23T21:34:36.418Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/3b/c6348f1e285e75b069085b18110a4e6325b763a5d35d5e204356fc7c20b3/faker-40.8.0-py3-none-any.whl", hash = "sha256:eb21bdba18f7a8375382eb94fb436fce07046893dc94cb20817d28deb0c3d579", size = 1989124, upload-time = "2026-03-04T16:18:46.45Z" },
 ]
 
 [[package]]
@@ -1251,11 +1260,11 @@ wheels = [
 
 [[package]]
 name = "filelock"
-version = "3.20.3"
+version = "3.25.2"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/1d/65/ce7f1b70157833bf3cb851b556a37d4547ceafc158aa9b34b36782f23696/filelock-3.20.3.tar.gz", hash = "sha256:18c57ee915c7ec61cff0ecf7f0f869936c7c30191bb0cf406f1341778d0834e1", size = 19485, upload-time = "2026-01-09T17:55:05.421Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/94/b8/00651a0f559862f3bb7d6f7477b192afe3f583cc5e26403b44e59a55ab34/filelock-3.25.2.tar.gz", hash = "sha256:b64ece2b38f4ca29dd3e810287aa8c48182bbecd1ae6e9ae126c9b35f1382694", size = 40480, upload-time = "2026-03-11T20:45:38.487Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b5/36/7fb70f04bf00bc646cd5bb45aa9eddb15e19437a28b8fb2b4a5249fac770/filelock-3.20.3-py3-none-any.whl", hash = "sha256:4b0dda527ee31078689fc205ec4f1c1bf7d56cf88b6dc9426c4f230e46c2dce1", size = 16701, upload-time = "2026-01-09T17:55:04.334Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/a5/842ae8f0c08b61d6484b52f99a03510a3a72d23141942d216ebe81fefbce/filelock-3.25.2-py3-none-any.whl", hash = "sha256:ca8afb0da15f229774c9ad1b455ed96e85a81373065fb10446672f64444ddf70", size = 26759, upload-time = "2026-03-11T20:45:37.437Z" },
 ]
 
 [[package]]
@@ -1283,6 +1292,59 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a6/ff/ee2f67c0ff146ec98b5df1df637b2bc2d17beeb05df9f427a67bd7a7d79c/flower-2.0.1-py2.py3-none-any.whl", hash = "sha256:9db2c621eeefbc844c8dd88be64aef61e84e2deb29b271e02ab2b5b9f01068e2", size = 383553, upload-time = "2023-08-13T14:37:41.552Z" },
 ]
 
+[[package]]
+name = "fonttools"
+version = "4.62.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5a/96/686339e0fda8142b7ebed39af53f4a5694602a729662f42a6209e3be91d0/fonttools-4.62.0.tar.gz", hash = "sha256:0dc477c12b8076b4eb9af2e440421b0433ffa9e1dcb39e0640a6c94665ed1098", size = 3579521, upload-time = "2026-03-09T16:50:06.217Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e4/33/63d79ca41020dd460b51f1e0f58ad1ff0a36b7bcbdf8f3971d52836581e9/fonttools-4.62.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:196cafef9aeec5258425bd31a4e9a414b2ee0d1557bca184d7923d3d3bcd90f9", size = 2870816, upload-time = "2026-03-09T16:48:32.39Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/7a/9aeec114bc9fc00d757a41f092f7107863d372e684a5b5724c043654477c/fonttools-4.62.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:153afc3012ff8761b1733e8fbe5d98623409774c44ffd88fbcb780e240c11d13", size = 2416127, upload-time = "2026-03-09T16:48:34.627Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/71/12cfd8ae0478b7158ffa8850786781f67e73c00fd897ef9d053415c5f88b/fonttools-4.62.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:13b663fb197334de84db790353d59da2a7288fd14e9be329f5debc63ec0500a5", size = 5100678, upload-time = "2026-03-09T16:48:36.454Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/d7/8e4845993ee233c2023d11babe9b3dae7d30333da1d792eeccebcb77baab/fonttools-4.62.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:591220d5333264b1df0d3285adbdfe2af4f6a45bbf9ca2b485f97c9f577c49ff", size = 5070859, upload-time = "2026-03-09T16:48:38.786Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/a0/287ae04cd883a52e7bb1d92dfc4997dcffb54173761c751106845fa9e316/fonttools-4.62.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:579f35c121528a50c96bf6fcb6a393e81e7f896d4326bf40e379f1c971603db9", size = 5076689, upload-time = "2026-03-09T16:48:41.886Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/4e/a2377ad26c36fcd3e671a1c316ea5ed83107de1588e2d897a98349363bc7/fonttools-4.62.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:44956b003151d5a289eba6c71fe590d63509267c37e26de1766ba15d9c589582", size = 5202053, upload-time = "2026-03-09T16:48:43.867Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/9d/7ad1ffc080619f67d0b1e0fa6a0578f0be077404f13fd8e448d1616a94a3/fonttools-4.62.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:22bde4dc12a9e09b5ced77f3b5053d96cf10c4976c6ac0dee293418ef289d221", size = 2870004, upload-time = "2026-03-09T16:48:50.837Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/8b/ba59069a490f61b737e064c3129453dbd28ee38e81d56af0d04d7e6b4de4/fonttools-4.62.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7199c73b326bad892f1cb53ffdd002128bfd58a89b8f662204fbf1daf8d62e85", size = 2414662, upload-time = "2026-03-09T16:48:53.295Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/8c/c52a4310de58deeac7e9ea800892aec09b00bb3eb0c53265b31ec02be115/fonttools-4.62.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d732938633681d6e2324e601b79e93f7f72395ec8681f9cdae5a8c08bc167e72", size = 5032975, upload-time = "2026-03-09T16:48:55.718Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/a1/d16318232964d786907b9b3613b8409f74cf0be2da400854509d3a864e43/fonttools-4.62.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:31a804c16d76038cc4e3826e07678efb0a02dc4f15396ea8e07088adbfb2578e", size = 4988544, upload-time = "2026-03-09T16:48:57.715Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/8d/7e745ca3e65852adc5e52a83dc213fe1b07d61cb5b394970fcd4b1199d1e/fonttools-4.62.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:090e74ac86e68c20150e665ef8e7e0c20cb9f8b395302c9419fa2e4d332c3b51", size = 4971296, upload-time = "2026-03-09T16:48:59.678Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/d4/b717a4874175146029ca1517e85474b1af80c9d9a306fc3161e71485eea5/fonttools-4.62.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:8f086120e8be9e99ca1288aa5ce519833f93fe0ec6ebad2380c1dee18781f0b5", size = 5122503, upload-time = "2026-03-09T16:49:02.464Z" },
+    { url = "https://files.pythonhosted.org/packages/82/c7/985c1670aa6d82ef270f04cde11394c168f2002700353bd2bde405e59b8f/fonttools-4.62.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:274c8b8a87e439faf565d3bcd3f9f9e31bca7740755776a4a90a4bfeaa722efa", size = 2864929, upload-time = "2026-03-09T16:49:09.331Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/dc/c409c8ceec0d3119e9ab0b7b1a2e3c76d1f4d66e4a9db5c59e6b7652e7df/fonttools-4.62.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:93e27131a5a0ae82aaadcffe309b1bae195f6711689722af026862bede05c07c", size = 2412586, upload-time = "2026-03-09T16:49:11.378Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/ac/8e300dbf7b4d135287c261ffd92ede02d9f48f0d2db14665fbc8b059588a/fonttools-4.62.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:83c6524c5b93bad9c2939d88e619fedc62e913c19e673f25d5ab74e7a5d074e5", size = 5013708, upload-time = "2026-03-09T16:49:14.063Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/bc/60d93477b653eeb1ddf5f9ec34be689b79234d82dbdded269ac0252715b8/fonttools-4.62.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:106aec9226f9498fc5345125ff7200842c01eda273ae038f5049b0916907acee", size = 4964355, upload-time = "2026-03-09T16:49:16.515Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/eb/6dc62bcc3c3598c28a3ecb77e69018869c3e109bd83031d4973c059d318b/fonttools-4.62.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:15d86b96c79013320f13bc1b15f94789edb376c0a2d22fb6088f33637e8dfcbc", size = 4953472, upload-time = "2026-03-09T16:49:18.494Z" },
+    { url = "https://files.pythonhosted.org/packages/82/b3/3af7592d9b254b7b7fec018135f8776bfa0d1ad335476c2791b1334dc5e4/fonttools-4.62.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f16c07e5250d5d71d0f990a59460bc5620c3cc456121f2cfb5b60475699905f", size = 5094701, upload-time = "2026-03-09T16:49:21.67Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/64/61f69298aa6e7c363dcf00dd6371a654676900abe27d1effd1a74b43e5d0/fonttools-4.62.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:4fa5a9c716e2f75ef34b5a5c2ca0ee4848d795daa7e6792bf30fd4abf8993449", size = 2864222, upload-time = "2026-03-09T16:49:28.285Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/57/6b08756fe4455336b1fe160ab3c11fccc90768ccb6ee03fb0b45851aace4/fonttools-4.62.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:625f5cbeb0b8f4e42343eaeb4bc2786718ddd84760a2f5e55fdd3db049047c00", size = 2410674, upload-time = "2026-03-09T16:49:30.504Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/86/db65b63bb1b824b63e602e9be21b18741ddc99bcf5a7850f9181159ae107/fonttools-4.62.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6247e58b96b982709cd569a91a2ba935d406dccf17b6aa615afaed37ac3856aa", size = 4999387, upload-time = "2026-03-09T16:49:32.593Z" },
+    { url = "https://files.pythonhosted.org/packages/86/c8/c6669e42d2f4efd60d38a3252cebbb28851f968890efb2b9b15f9d1092b0/fonttools-4.62.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:840632ea9c1eab7b7f01c369e408c0721c287dfd7500ab937398430689852fd1", size = 4912506, upload-time = "2026-03-09T16:49:34.927Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/49/0ae552aa098edd0ec548413fbf818f52ceb70535016215094a5ce9bf8f70/fonttools-4.62.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:28a9ea2a7467a816d1bec22658b0cce4443ac60abac3e293bdee78beb74588f3", size = 4951202, upload-time = "2026-03-09T16:49:37.1Z" },
+    { url = "https://files.pythonhosted.org/packages/71/65/ae38fc8a4cea6f162d74cf11f58e9aeef1baa7d0e3d1376dabd336c129e5/fonttools-4.62.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5ae611294f768d413949fd12693a8cba0e6332fbc1e07aba60121be35eac68d0", size = 5060758, upload-time = "2026-03-09T16:49:39.464Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/65/f47f9b3db1ec156a1f222f1089ba076b2cc9ee1d024a8b0a60c54258517e/fonttools-4.62.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:0361a7d41d86937f1f752717c19f719d0fde064d3011038f9f19bdf5fc2f5c95", size = 2947079, upload-time = "2026-03-09T16:49:46.471Z" },
+    { url = "https://files.pythonhosted.org/packages/52/73/bc62e5058a0c22cf02b1e0169ef0c3ca6c3247216d719f95bead3c05a991/fonttools-4.62.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:d4108c12773b3c97aa592311557c405d5b4fc03db2b969ed928fcf68e7b3c887", size = 2448802, upload-time = "2026-03-09T16:49:48.328Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/df/bfaa0e845884935355670e6e68f137185ab87295f8bc838db575e4a66064/fonttools-4.62.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b448075f32708e8fb377fe7687f769a5f51a027172c591ba9a58693631b077a8", size = 5137378, upload-time = "2026-03-09T16:49:50.223Z" },
+    { url = "https://files.pythonhosted.org/packages/32/32/04f616979a18b48b52e634988b93d847b6346260faf85ecccaf7e2e9057f/fonttools-4.62.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5f1fa8cc9f1a56a3e33ee6b954d6d9235e6b9d11eb7a6c9dfe2c2f829dc24db", size = 4920714, upload-time = "2026-03-09T16:49:53.172Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/2e/274e16689c1dfee5c68302cd7c444213cfddd23cf4620374419625037ec6/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f8c8ea812f82db1e884b9cdb663080453e28f0f9a1f5027a5adb59c4cc8d38d1", size = 5016012, upload-time = "2026-03-09T16:49:55.762Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/0c/b08117270626e7117ac2f89d732fdd4386ec37d2ab3a944462d29e6f89a1/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:03c6068adfdc67c565d217e92386b1cdd951abd4240d65180cec62fa74ba31b2", size = 5042766, upload-time = "2026-03-09T16:49:57.726Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/57/c2487c281dde03abb2dec244fd67059b8d118bd30a653cbf69e94084cb23/fonttools-4.62.0-py3-none-any.whl", hash = "sha256:75064f19a10c50c74b336aa5ebe7b1f89fd0fb5255807bfd4b0c6317098f4af3", size = 1152427, upload-time = "2026-03-09T16:50:04.074Z" },
+]
+
+[[package]]
+name = "fpdf2"
+version = "2.8.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.8.0"
@@ -1393,74 +1455,74 @@ wheels = [
 
 [[package]]
 name = "granian"
-version = "2.7.0"
+version = "2.7.2"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/43/75/bdea4ab49a02772a3007e667284764081d401169e96d0270d95509e3e240/granian-2.7.0.tar.gz", hash = "sha256:bee8e8a81a259e6f08613c973062df9db5f8451b521bb0259ed8f27d3e2bab23", size = 127963, upload-time = "2026-02-02T11:39:57.525Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/57/19/d4ea523715ba8dd2ed295932cc3dda6bb197060f78aada6e886ff08587b2/granian-2.7.2.tar.gz", hash = "sha256:cdae2f3a26fa998d41fefad58f1d1c84a0b035a6cc9377addd81b51ba82f927f", size = 128969, upload-time = "2026-02-24T23:04:23.314Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8a/28/a3ee3f2220c0b9045f8caa2a2cb7484618961b7500f88594349a7889d391/granian-2.7.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:e76afb483d7f42a0b911bdb447d282f70ad7a96caabd4c99cdc300117c5f8977", size = 4580966, upload-time = "2026-02-02T11:38:14.077Z" },
-    { url = "https://files.pythonhosted.org/packages/1b/60/b53da9c255f6853a5516d0f8a3e7325c24123f0f7e77856558c49810f4ce/granian-2.7.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:628523302274f95ca967f295a9aa7bc4ade5e1eced42afc60d06dfe20f2da07a", size = 4210344, upload-time = "2026-02-02T11:38:15.34Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/bb/c3380106565bc99edfb90baafa1a8081a4334709ce0200d207ddda36275e/granian-2.7.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a62560b64a17e1cbae61038285d5fa8a32613ada9a46f05047dc607ea7d38f23", size = 5130258, upload-time = "2026-02-02T11:38:17.175Z" },
-    { url = "https://files.pythonhosted.org/packages/a2/8f/2c3348d6d33807e3b818ac07366b5251e811ce2548fbe82e0b55982d8a13/granian-2.7.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:47b8e0e9497d24466d6511443cc18f22f18405aab5a7e2fece1dd38206af88c4", size = 4576496, upload-time = "2026-02-02T11:38:18.577Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/71/d1d146170a23f3523d8629b47f849b30ba0d513eb519188ce5d7bfd1b916/granian-2.7.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc6039c61a07b2d36462c487b66b131ae3fd862bdc8fb81d6e5c206c1a2b683c", size = 4975062, upload-time = "2026-02-02T11:38:20.084Z" },
-    { url = "https://files.pythonhosted.org/packages/16/f9/f3acbf8c41cd10ff81109bd9078d3228f23e52bab8673763c65739a87e30/granian-2.7.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:f3b0442beb11b035ee09959726f44b3730d0b55688110defd1d9a9a6c7486955", size = 4827755, upload-time = "2026-02-02T11:38:21.817Z" },
-    { url = "https://files.pythonhosted.org/packages/9f/f8/503135b89539feea2be495b47858c22409ba77ffcb71920ae0727c674189/granian-2.7.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:741d0b58a5133cc5902b3129a8a4c55143f0f8769a80e7aa80caadc64c9f1d8b", size = 4939033, upload-time = "2026-02-02T11:38:23.033Z" },
-    { url = "https://files.pythonhosted.org/packages/99/90/aaabe2c1162d07a6af55532b6f616199aa237805ef1d732fa78d9883d217/granian-2.7.0-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:02a6fe6a19f290b70bc23feeb3809511becdaff2263b0469f02c28772af97652", size = 5292980, upload-time = "2026-02-02T11:38:24.823Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/aa/d1eb7342676893ab0ec1e66cceca4450bec3f29c488db2a92af5b4211d4d/granian-2.7.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:8239b1a661271428c3e358e4bdcaaaf877a432cc593e93fc6b5a612ae521b06a", size = 5087230, upload-time = "2026-02-02T11:38:26.09Z" },
-    { url = "https://files.pythonhosted.org/packages/97/1a/b6d7840bfd9cd9bed627b138e6e8e49d1961997adba30ee39ad75d07ed58/granian-2.7.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:d9c42562dcbf52848d0a9d0db58f8f2e790586eb0c363b8ad1b30fe0bd362117", size = 4572728, upload-time = "2026-02-02T11:38:30.143Z" },
-    { url = "https://files.pythonhosted.org/packages/15/93/f8f7224d9eaaaf4dbf493035a85287fa2e27c17e5f7aacc01821d8aa66b4/granian-2.7.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a3421bd5c90430073e1f3f88fc63bc8d0a8ee547a9a5c06d577a281f384160bd", size = 4195034, upload-time = "2026-02-02T11:38:32.007Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/db/66843a35e1b6345da2a1c71839fb9aa7eb0f17d380fbf4cb5c7e06eb6f85/granian-2.7.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8b8057dc81772932e208f2327b5e347459eb78896118e27af9845801e267cec5", size = 5123768, upload-time = "2026-02-02T11:38:33.449Z" },
-    { url = "https://files.pythonhosted.org/packages/10/ce/631c5c1f7a4e6b8c98ec857b3e6795fe64e474b6f48df388ac701a21f3fe/granian-2.7.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1e5e70f438b1a4787d76566770e98bf7732407efa02802f38f10c960247107d7", size = 4562424, upload-time = "2026-02-02T11:38:34.815Z" },
-    { url = "https://files.pythonhosted.org/packages/28/41/19bdfa3719e22c4dcf6fa1a53323551a37aa58a4ca7a768db6a0ba714ab0/granian-2.7.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:213dd224a47c7bfcbb91718c7eeb56d6067825a28dcae50f537964e2dafb729a", size = 5006002, upload-time = "2026-02-02T11:38:36.76Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/5b/3b40f489e2449eb58df93ad38f42d1a6c2910502a4bc8017c047e16d637c/granian-2.7.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:bb5be27c0265268d43bab9a878ac27a20b4288843ffc9fda1009b8226673f629", size = 4825073, upload-time = "2026-02-02T11:38:37.998Z" },
-    { url = "https://files.pythonhosted.org/packages/04/92/b6de6f8c4146409efb58aee75277b810d54de03a1687d33f1f3f1feb3395/granian-2.7.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a6ff95aede82903c06eb560a32b10e9235fdafc4568c8fe7dcac28d62be5ffa2", size = 4928628, upload-time = "2026-02-02T11:38:39.481Z" },
-    { url = "https://files.pythonhosted.org/packages/39/21/d8a191dcfbf8422b868ab847829670075ba3e4325611e0a9fd2dc909a142/granian-2.7.0-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:e44f0c1676b27582df26d47cf466fedebd72f520edc2025f125c83ff58af77f9", size = 5282898, upload-time = "2026-02-02T11:38:40.815Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/46/2746f1a4f0f093576fb64b63c3f022f254c6d2c4cc66d37dd881608397ce/granian-2.7.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:9241b72f95ceb57e2bbce55e0f61c250c1c02e9d2f8531b027dd3dc204209fdd", size = 5118453, upload-time = "2026-02-02T11:38:42.716Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/df/b68626242fb4913df0968ee5662f5a394857b3d6fc4ee17c94be69664491/granian-2.7.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:bc61451791c8963232e4921c6805e7c2e366635e1e658267b1854889116ff6d7", size = 4572200, upload-time = "2026-02-02T11:38:46.194Z" },
-    { url = "https://files.pythonhosted.org/packages/c0/15/2fe28bca0751d9dc46e5c7e9e4b0c4fd1a55e3e8ba062f28292322ee160b/granian-2.7.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e274a0d6a01c475b9135212106ca5b69f5ec2f67f4ca6ce812d185d80255cdf5", size = 4195415, upload-time = "2026-02-02T11:38:47.78Z" },
-    { url = "https://files.pythonhosted.org/packages/07/2a/d4dc40e58a55835cac5296f5090cc3ce2d43332ad486bbf78b3a00e46199/granian-2.7.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34bd28075adae3453c596ee20089e0288379e3fdf1cec8bafff89bb175ea0eb4", size = 5122981, upload-time = "2026-02-02T11:38:49.55Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/fe/8c79837df620dc0eca6a8b799505910cbba2d85d92ccc58d1c549f7027be/granian-2.7.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f526583b72cf9e6ca9a4849c781ed546f44005f0ad4b5c7eb1090e1ebec209bf", size = 4561440, upload-time = "2026-02-02T11:38:50.799Z" },
-    { url = "https://files.pythonhosted.org/packages/4f/e7/d7abfaa9829ff50cddc27919bd3ce5a335402ebbbaa650e96fe579136674/granian-2.7.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95ac07d5314e03e667210349dfc76124d69726731007c24716e21a2554cc15ca", size = 5005076, upload-time = "2026-02-02T11:38:52.157Z" },
-    { url = "https://files.pythonhosted.org/packages/1a/45/108afaa0636c93b6a8ff12810787e4a1ea27fffe59f12ca0de7c784b119a/granian-2.7.0-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:f6812e342c41ca80e1b34fb6c9a7e51a4bbd14f59025bd1bb59d45a39e02b8d5", size = 4825142, upload-time = "2026-02-02T11:38:53.506Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/eb/cedf4675b1047490f819ce8bd1ee1ea74b6c772ae9d9dd1c117ae690a3eb/granian-2.7.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:7a4099ba59885123405699a5313757556ff106f90336dccdf4ceda76f32657d0", size = 4927830, upload-time = "2026-02-02T11:38:54.92Z" },
-    { url = "https://files.pythonhosted.org/packages/f9/b5/2d7a2e03ba29a6915ad41502e2870899b9eb54861e3d06ad8470c5e70b41/granian-2.7.0-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:c487731fbae86808410e88c587eb4071213812c5f52570b7981bf07a1b84be25", size = 5282142, upload-time = "2026-02-02T11:38:56.445Z" },
-    { url = "https://files.pythonhosted.org/packages/a9/e7/c851b2e2351727186b4bc4a35df832e2e97e4f77b8a93dfdb6daa098cf9e/granian-2.7.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:ca4877ebf8873488ba72a299206621bd0c6febb8f091f3da62117c1fe344501f", size = 5117907, upload-time = "2026-02-02T11:38:57.852Z" },
-    { url = "https://files.pythonhosted.org/packages/e1/2f/c9bcd4aa36d3092fe88a623e60aa89bd4ff16836803a633b8b454946a845/granian-2.7.0-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:e1df8e4669b4fb69b373b2ab40a10a8c511eeb41838d65adb375d1c0e4e7454c", size = 4493110, upload-time = "2026-02-02T11:39:01.294Z" },
-    { url = "https://files.pythonhosted.org/packages/6a/b4/02d11870255920d35f8eab390e509d3688fe0018011bb606aa00057b778f/granian-2.7.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:6331ed9d3eb06cfba737dfb8efa3f0a8b4d4312a5af91c0a67bfbaa078b62eb4", size = 4122388, upload-time = "2026-02-02T11:39:02.509Z" },
-    { url = "https://files.pythonhosted.org/packages/98/50/dfad5a414a2e3e14c30cd0d54cef1dab4874a67c1e6f8b1124d9998ed8b2/granian-2.7.0-cp313-cp313t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:093e1c277eddba00eaa94ca82ff7a9ab57b0554cd7013e5b2f3468635dbe520d", size = 4379344, upload-time = "2026-02-02T11:39:04.489Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/53/ef086af03ef31aa3c1dbff2da5928a9b5dd1f48d8ebee18dd6628951ae9e/granian-2.7.0-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8e8e317bdc9ca9905d0b20f665f8fe31080c7f13d90675439113932bb3272c24", size = 5069172, upload-time = "2026-02-02T11:39:05.757Z" },
-    { url = "https://files.pythonhosted.org/packages/c3/57/117864ea46c6cbcbeff733a4da736e814b06d6634beeb201b9db176bd6be/granian-2.7.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:391e8589265178fd7f444b6711b6dda157a6b66059a15bf1033ffceeaf26918c", size = 4848246, upload-time = "2026-02-02T11:39:07.048Z" },
-    { url = "https://files.pythonhosted.org/packages/60/da/2d45b7b6638a77362228d6770a61fa2bc3feae6c52a80993c230f344b197/granian-2.7.0-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:49b6873f4a8ee7a1ea627ff98d67ecdd644cfc18aab475b2e15f651dbcbe4140", size = 4669023, upload-time = "2026-02-02T11:39:09.612Z" },
-    { url = "https://files.pythonhosted.org/packages/22/69/49e54eb6ed67ccf471c19d4c65f64197dd5a416d501620519e28ea92c82e/granian-2.7.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:39778147c7527de0bcda12cd9c38863d4e6a80d3a8a96ddeb6fe2d1342f337db", size = 4896002, upload-time = "2026-02-02T11:39:10.996Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/f1/a864a78029265d06a6fd61c760c8facf032be0d345deca5081718cbb006f/granian-2.7.0-cp313-cp313t-musllinux_1_1_armv7l.whl", hash = "sha256:8135d0a4574dc5a0acf3a815fc6cad5bbe9075ef86df2c091ec34fbd21639c1c", size = 5239945, upload-time = "2026-02-02T11:39:12.726Z" },
-    { url = "https://files.pythonhosted.org/packages/26/33/feef40e4570b771d815c1ddd1008ccc9c0e81ce5a015deded6788e919f18/granian-2.7.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:47df2d9e50f22fa820b34fd38ceeeedc0b97994fa164425fa30e746759db8a44", size = 5078968, upload-time = "2026-02-02T11:39:14.048Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/6a/b8d58474bbcbca450f030fd41b65c94ae0afb5e8f58c39fbea2df4efee2b/granian-2.7.0-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:23c6531b75c94c7b533812aed4f40dc93008c406cfa5629ec93397cd0f6770cb", size = 4569780, upload-time = "2026-02-02T11:39:16.671Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/dc/a8b11425ebdf6cb58e1084fdb7759d853ca7f0b00376e4bb66300322f5d3/granian-2.7.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:e4939b86f2b7918202ce56cb01c2efe20a393c742d41640b444e82c8b444b614", size = 4195285, upload-time = "2026-02-02T11:39:18.596Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/b5/6cc0b94f997d93f4b1510b2d953f07a7f1d16a143d60b53e0e50b887fa12/granian-2.7.0-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38fa10adf3c4d50e31a08401e6701ee2488613d905bb316cad456e5ebad5aa81", size = 5121311, upload-time = "2026-02-02T11:39:20.092Z" },
-    { url = "https://files.pythonhosted.org/packages/f4/f9/df3d862874cf4b233f97253bb78991ae4f31179a5581beaa41a2100e3bce/granian-2.7.0-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9b366a9fd713a20321e668768b122b7b0140bfaeb3cb0557b6cb11dce827a4fb", size = 4557737, upload-time = "2026-02-02T11:39:21.992Z" },
-    { url = "https://files.pythonhosted.org/packages/c7/7f/e3063368345f39188afe5baa1ab62fdd951097656cd83bec3964f91f6e66/granian-2.7.0-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a916413e0dcd5c6eaf7f7413a6d899f7ba53a988d08e3b3c7ab2e0b5fa687559", size = 5004108, upload-time = "2026-02-02T11:39:23.306Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/eb/892bcc0cfc44ed791795bab251e0b6ed767397182bac134d9f0fcecc552e/granian-2.7.0-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:e315adf24162294d35ca4bed66c8f66ac15a0696f2cb462e729122d148f6d958", size = 4823143, upload-time = "2026-02-02T11:39:24.696Z" },
-    { url = "https://files.pythonhosted.org/packages/b3/e0/ff8528bf620b6da7833171f6d30bfe4b4b1d6e7d155b634bd17590e0c4b4/granian-2.7.0-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:486f8785e716f76f96534aaba25acd5dee1a8398725ffd2a55f0833689c75933", size = 4926328, upload-time = "2026-02-02T11:39:26.111Z" },
-    { url = "https://files.pythonhosted.org/packages/02/f7/fb0a761d39245295660703a42e9448f3c04ce1f26b2f62e044d179167880/granian-2.7.0-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:0e5e2c1c6ff1501e3675e5237096b90b767f506bb0ef88594310b7b9eaa95532", size = 5281190, upload-time = "2026-02-02T11:39:27.68Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/d8/860e7e96ea109c6db431c8284040d265758bded35f9ce2de05f3969d7c0c/granian-2.7.0-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:d4418b417f9c2162b4fa9ec41ec34ed3e8ed891463bb058873034222be53542f", size = 5117989, upload-time = "2026-02-02T11:39:29.008Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/9a/500ab01ae273870e8fc056956cc49716707b4a0e76fb2b5993258e1494f7/granian-2.7.0-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:b4367c088c00bdc38a8a495282070010914931edb4c488499f290c91018d9e80", size = 4492656, upload-time = "2026-02-02T11:39:31.614Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/26/86dc5a6fff60ee0cc38c2fcd1a0d4cebd52e6764a9f752a20458001ca57e/granian-2.7.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:c8f3df224284ed1ff673f61de652337d7721100bf4cfc336b2047005b0edb2e0", size = 4122201, upload-time = "2026-02-02T11:39:33.162Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/60/887dc5a099135ff449adcdea9a2aa38f39673baf99de9acb78077b701432/granian-2.7.0-cp314-cp314t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6682c08b0d82ad75f8e9d1571254630133e1563c49f0600c2e2dc26cec743ae7", size = 4377489, upload-time = "2026-02-02T11:39:34.532Z" },
-    { url = "https://files.pythonhosted.org/packages/5a/6b/68c12f8c4c1f1c109bf55d66beeb37a817fd908af5d5d9b48afcbdc3e623/granian-2.7.0-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d6ccc3bdc2248775b6bd292d7d37a1bff79eb1aaf931f3a217ea9fb9a6fe7ca4", size = 5067294, upload-time = "2026-02-02T11:39:35.84Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/4f/be4f9c129f5f80f52654f257abe91f647defec020fa134b3600013b7219d/granian-2.7.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5431272a4d6f49a200aeb7b01010a3785b93b9bd8cd813d98ed29c8e9ba1c476", size = 4848356, upload-time = "2026-02-02T11:39:37.443Z" },
-    { url = "https://files.pythonhosted.org/packages/d7/aa/f6efcfb435f370a6f3626bd5837465bfb71950f6b3cb3c74e54b176c72e2/granian-2.7.0-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:790b150255576775672f26dbcbd6eb05f70260dd661b91ce462f6f3846db9501", size = 4669022, upload-time = "2026-02-02T11:39:38.782Z" },
-    { url = "https://files.pythonhosted.org/packages/1d/36/e86050c476046ef1f0aae0eb86d098fa787abfc8887a131c82baccc7565e/granian-2.7.0-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:ce9be999273c181e4b65efbbd82a5bc6f223f1db3463660514d1dc229c8ba760", size = 4895567, upload-time = "2026-02-02T11:39:40.144Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/5e/25283ff7fc12fcf42ae8a5687243119739cf4b0bf5ccb1c32d11d37987b1/granian-2.7.0-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:319b34f18ed3162354513acb5a9e8cee720ac166cd88fe05f0f057703eb47e4f", size = 5238652, upload-time = "2026-02-02T11:39:41.648Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/60/06148781120e086c7437aa9513198025ea1eb847cb2e244d5e2b9801782e/granian-2.7.0-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:b01bed8ad748840e7ab49373f642076f3bc459e39937a4ce11c5be03e67cdfd9", size = 5079018, upload-time = "2026-02-02T11:39:43.309Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/0b/39ebf1b791bbd4049239ecfee8f072321211879e5617a023921961be1d55/granian-2.7.0-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:24a1f6a894bea95ef0e603bebacbccd19c319c0da493bb4fde8b94b8629f3dc8", size = 4581648, upload-time = "2026-02-02T11:39:45.991Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/cd/4642192520478bba4cd547124d92607c958a0786864ebe378f3008b40048/granian-2.7.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:c2799497ac896cffea85512983c5d9eb4ae51ebacd7a9a5fd3d2ac81f1755fac", size = 4214257, upload-time = "2026-02-02T11:39:47.507Z" },
-    { url = "https://files.pythonhosted.org/packages/e2/3f/615f93753c3b682219fe546196fc9eb3a045d846e57883312c97de4d785a/granian-2.7.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b66a15d004136e641706e0e5522b3509151e2027a0677cf4fa97d049d9ddfa41", size = 4979656, upload-time = "2026-02-02T11:39:48.838Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/68/1f2c36a964f93bfe8d6189431b8425acc591b735e47d8898b2e70c478398/granian-2.7.0-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:de5a6fa93d2138ba2372d20d97b87c1af75fa16a59a93841745326825c3ddf83", size = 4844448, upload-time = "2026-02-02T11:39:50.5Z" },
-    { url = "https://files.pythonhosted.org/packages/df/23/d8c83fe6a6656026c734c2ea771cbcdec6f0010e749f8ab0db1bfc8a3dfe/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:aacda2ad46724490c4cd811b8dcadff2260603a3e95ca0d8c33552d791a3c6ac", size = 4930755, upload-time = "2026-02-02T11:39:51.866Z" },
-    { url = "https://files.pythonhosted.org/packages/20/e5/2a86ee18544185e72fc50b50985b6bfb4504f7835875d2636f573e100071/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:7efb5ebdb308ed1685a80cded6ea51447753e8afe92c21fc3abf9a06a9eb5d2e", size = 5295728, upload-time = "2026-02-02T11:39:53.364Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/bd/0d47d17769601c56d876b289456f27799611571227b99ad300e221600bbd/granian-2.7.0-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:ae96b75420d01d9a7dbe1bd84f1898b2b0ade6883db59bfe2b233d7c28c6b0df", size = 5095149, upload-time = "2026-02-02T11:39:54.767Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/58/dcf0e8a54b9a7f8b7482ed617bca08503a47eb6b702aea73cda9efd2c81c/granian-2.7.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:3a0d33ada95a1421e5a22d447d918e5615ff0aa37f12de5b84455afe89970875", size = 6522860, upload-time = "2026-02-24T23:02:15.901Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/dd/398de0f273fdcf0e96bd70d8cd97364625176990e67457f11e23f95772bd/granian-2.7.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ee26f0258cc1b6ccf87c7bdcee6d1f90710505522fc9880ec02b299fb15679ad", size = 6135934, upload-time = "2026-02-24T23:02:18.52Z" },
+    { url = "https://files.pythonhosted.org/packages/67/b7/7bf635bbdfb88dfc6591fa2ce5c3837ab9535e57e197a780c4a338363de7/granian-2.7.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f52338cfab08b8cdaadaa5b93665e0be5b4c4f718fbd132d76ceacacb9ff864e", size = 7138393, upload-time = "2026-02-24T23:02:19.911Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/90/e424fd8a703add1e8922390503be8d057882b35b42ba51796157aabd659b/granian-2.7.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6e377d03a638fecb6949ab05c8fd4a76f892993aed17c602d179bfd56aebc2de", size = 6467189, upload-time = "2026-02-24T23:02:21.896Z" },
+    { url = "https://files.pythonhosted.org/packages/65/9a/5de24d7e2dba1aa9fbac6f0a80dace975cfac1b7c7624ece21da75a38987/granian-2.7.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f742f3ca1797a746fae4a9337fe5d966460c957fa8efeaccf464b872e158d3d", size = 6870813, upload-time = "2026-02-24T23:02:23.972Z" },
+    { url = "https://files.pythonhosted.org/packages/ac/cd/a604e38237857f4ad4262eadc409f94fe08fed3e86fa0b8734479cc5bfb1/granian-2.7.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:ca4402e8f28a958f0c0f6ebff94cd0b04ca79690aded785648a438bc3c875ba3", size = 7046583, upload-time = "2026-02-24T23:02:25.94Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/ad/79eaae0cddd90c4e191b37674cedd8f4863b44465cb435b10396d0f12c82/granian-2.7.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1f9a899123b0d084783626e5225608094f1d2f6fc81b3a7c77ab8daac33ab74a", size = 7121958, upload-time = "2026-02-24T23:02:27.641Z" },
+    { url = "https://files.pythonhosted.org/packages/ca/51/e5c923b1baa003f5b4b7fc148be6f8d2e3cabe55d41040fe8139da52e31b/granian-2.7.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:56ba4bef79d0ae3736328038deed2b5d281b11672bc0b08ffc8ce6210e406ef8", size = 7303047, upload-time = "2026-02-24T23:02:30.863Z" },
+    { url = "https://files.pythonhosted.org/packages/06/c0/ebd68144a3ce9ead1a3192ac02e1c26e4874df1257435ce6137adf92fedb/granian-2.7.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:ea46e3f43d94715aa89d1f2f5754753d46e6b653d561b82b0291e62a31bdfb35", size = 7011349, upload-time = "2026-02-24T23:02:32.887Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/ed/37f5d7d887ec9159dd8f5b1c9c38cee711d51016d203959f2d51c536a33b/granian-2.7.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a836f3f8ebfe61cb25d9afb655f2e5d3851154fd2ad97d47bb4fb202817212fc", size = 6451593, upload-time = "2026-02-24T23:02:36.203Z" },
+    { url = "https://files.pythonhosted.org/packages/1e/06/84ee67a68504836a52c48ec3b4b2b406cbd927c9b43aae89d82db8d097a0/granian-2.7.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:09b1c543ba30886dea515a156baf6d857bbb8b57dbfd8b012c578b93c80ef0c3", size = 6101239, upload-time = "2026-02-24T23:02:37.636Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/50/ece7dc8efe144542cd626b88b1475b649e2eaa3eb5f7541ca57390151b05/granian-2.7.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6d334d4fbefb97001e78aa8067deafb107b867c102ba2120b4b2ec989fa58a89", size = 7079443, upload-time = "2026-02-24T23:02:39.651Z" },
+    { url = "https://files.pythonhosted.org/packages/7e/e8/0f37b531d3cc96b8538cca2dc86eda92102e0ee345b30aa689354194a4cb/granian-2.7.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c86081d8c87989db69650e9d0e50ed925b8cd5dad21e0a86aa72d7a45f45925", size = 6428683, upload-time = "2026-02-24T23:02:41.827Z" },
+    { url = "https://files.pythonhosted.org/packages/47/09/228626706554b389407270e2a6b19b7dee06d6890e8c01a39c6a785827fd/granian-2.7.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d9eda33dca2c8bc6471bb6e9e25863077bca3877a1bba4069cd5e0ee2de41765", size = 6959520, upload-time = "2026-02-24T23:02:43.488Z" },
+    { url = "https://files.pythonhosted.org/packages/61/c0/a639ceabd59b8acae2d71b5c918fcb2d42f8ef98994eedcf9a8b6813731d/granian-2.7.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:9cf69aaff6f632074ffbe7c1ee214e50f64be36101b7cb8253eeec1d460f2dba", size = 6991548, upload-time = "2026-02-24T23:02:44.954Z" },
+    { url = "https://files.pythonhosted.org/packages/b1/99/a35ed838a3095dcad02ae3944d19ebafe1d5a98cdc72bb61835fb5faf933/granian-2.7.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:f761a748cc7f3843b430422d2539da679daf5d3ef0259a101b90d5e55a0aafa7", size = 7121475, upload-time = "2026-02-24T23:02:46.991Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/24/3952c464432b904ec1cf537d2bd80d2dfde85524fa428ab9db2b5afe653c/granian-2.7.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:41c7b8390b78647fe34662ed7296e1465dad4a5112af9b0ecf8e367083d6c76a", size = 7243647, upload-time = "2026-02-24T23:02:49.165Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/fa/ab39e39c6b78eab6b42cf5bb36f56badde2aaafc3807f03f781d00e7861a/granian-2.7.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:a052ed466da5922cb443435a95a0c751566943278a6f22cef3d2e19d4e7ecdea", size = 7048915, upload-time = "2026-02-24T23:02:50.773Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/bc/cf0bc29f583096a842cf0f26ae2fe40c72ed5286d4548be99ecfcdbb17e2/granian-2.7.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:76b840ff13dde8838fd33cd096f2e7cadf2c21a499a67f695f53de57deab6ff8", size = 6440868, upload-time = "2026-02-24T23:02:53.619Z" },
+    { url = "https://files.pythonhosted.org/packages/2f/0d/bae1dcd2182ba5d9a5df33eb50b56dc5bbe67e31033d822e079aa8c1ff30/granian-2.7.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:00ccc8d7284bc7360f310179d0b4d17e5ca3077bbe24427e9e9310df397e3831", size = 6097336, upload-time = "2026-02-24T23:02:55.185Z" },
+    { url = "https://files.pythonhosted.org/packages/65/7d/3e0a7f32b0ad5faa1d847c51191391552fa239821c95fc7c022688985df2/granian-2.7.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:675987c1b321dc8af593db8639e00c25277449b32e8c1b2ddd46b35f28d9fac4", size = 7098742, upload-time = "2026-02-24T23:02:57.898Z" },
+    { url = "https://files.pythonhosted.org/packages/89/41/3b44386d636ac6467f0f13f45474c71fc3b90a4f0ba8b536de91b2845a09/granian-2.7.2-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:681c6fbe3354aaa6251e6191ec89f5174ac3b9fbc4b4db606fea456d01969fcb", size = 6430667, upload-time = "2026-02-24T23:02:59.789Z" },
+    { url = "https://files.pythonhosted.org/packages/52/70/7b24e187aed3fb7ac2b29d2480a045559a509ef9fec54cffb8694a2d94af/granian-2.7.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e5c9ae65af5e572dca27d8ca0da4c5180b08473ac47e6f5329699e9455a5cc3", size = 6948424, upload-time = "2026-02-24T23:03:01.406Z" },
+    { url = "https://files.pythonhosted.org/packages/fa/4c/cb74c367f9efb874f2c8433fe9bf3e824f05cf719f2251d40e29e07f08c0/granian-2.7.2-cp313-cp313-manylinux_2_28_aarch64.whl", hash = "sha256:e37fab2be919ceb195db00d7f49ec220444b1ecaa07c03f7c1c874cacff9de83", size = 7000407, upload-time = "2026-02-24T23:03:03.214Z" },
+    { url = "https://files.pythonhosted.org/packages/58/98/dfed3966ed7fbd3aae56e123598f90dc206484092b8373d0a71e2d8b82a8/granian-2.7.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:8ec167ab30f5396b5caaff16820a39f4e91986d2fe5bdc02992a03c2b2b2b313", size = 7121626, upload-time = "2026-02-24T23:03:05.349Z" },
+    { url = "https://files.pythonhosted.org/packages/39/82/acec732a345cd03b2f6e48ac04b66b7b8b61f5c50eb08d7421fc8c56591a/granian-2.7.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:63f426d793f2116d23be265dd826bec1e623680baf94cc270fe08923113a86ba", size = 7253447, upload-time = "2026-02-24T23:03:06.986Z" },
+    { url = "https://files.pythonhosted.org/packages/c5/2b/64779e69b08c1ff1bfc09a4ede904ab761ff63f936c275710886057c52f7/granian-2.7.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:1617cbb4efe3112f07fb6762cf81d2d9fe4bdb78971d1fd0a310f8b132f6a51e", size = 7053005, upload-time = "2026-02-24T23:03:09.021Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/49/9eb88875d709db7e7844e1c681546448dab5ff5651cd1c1d80ac4b1de4e3/granian-2.7.2-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:016c5857c8baedeab7eb065f98417f5ea26bb72b0f7e0544fe76071efc5ab255", size = 6401748, upload-time = "2026-02-24T23:03:12.802Z" },
+    { url = "https://files.pythonhosted.org/packages/e3/80/85726ad9999ed89cb6a32f7f57eb50ce7261459d9c30c3b194ae4c5aa2c5/granian-2.7.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:dcbe01fa141adf3f90964e86a959e250754aa7c6dad8fa7a855e6fd382de4c13", size = 6101265, upload-time = "2026-02-24T23:03:14.435Z" },
+    { url = "https://files.pythonhosted.org/packages/07/82/0df56a42b9f4c327d0e0b052f43369127e1b565b9e66bf2c9488f1c8d759/granian-2.7.2-cp313-cp313t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:283ba23817a685784b66f45423d2f25715fdc076c8ffb43c49a807ee56a0ffc0", size = 6249488, upload-time = "2026-02-24T23:03:16.387Z" },
+    { url = "https://files.pythonhosted.org/packages/ef/cc/d83a351560a3d6377672636129c52f06f8393f5831c5ee0f06f274883ea6/granian-2.7.2-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3258419c741897273ce155568b5a9cbacb7700a00516e87119a90f7d520d6783", size = 7104734, upload-time = "2026-02-24T23:03:17.993Z" },
+    { url = "https://files.pythonhosted.org/packages/84/d1/539907ee96d0ee2bcceabb4a6a9643b75378d6dfea09b7a9e4fd22cdf977/granian-2.7.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a196125c4837491c139c9cc83541b48c408c92b9cfbbf004fd28717f9c02ad21", size = 6785504, upload-time = "2026-02-24T23:03:19.763Z" },
+    { url = "https://files.pythonhosted.org/packages/86/bf/4b6f45882f8341e7c6cb824d693deb94c306be6525b483c76fb373d1e749/granian-2.7.2-cp313-cp313t-manylinux_2_28_aarch64.whl", hash = "sha256:746555ac8a2dcd9257bfe7ad58f1d7a60892bc4613df6a7d8f736692b3bb3b88", size = 6902790, upload-time = "2026-02-24T23:03:22.215Z" },
+    { url = "https://files.pythonhosted.org/packages/44/b8/832970d2d4b144b87be39f5b9dfd31fdb17f298dc238a0b2100c95002cf8/granian-2.7.2-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:5ac1843c6084933a54a07d9dcae643365f1d83aaff3fd4f2676ea301185e4e8b", size = 7082682, upload-time = "2026-02-24T23:03:23.875Z" },
+    { url = "https://files.pythonhosted.org/packages/38/bc/1521dbf026d1c9d2465cd54e016efd8ff6e1e72eff521071dab20dd61c44/granian-2.7.2-cp313-cp313t-musllinux_1_1_armv7l.whl", hash = "sha256:3612eb6a3f4351dd2c4df246ed0d21056c0556a6b1ed772dd865310aa55a9ba9", size = 7264742, upload-time = "2026-02-24T23:03:25.562Z" },
+    { url = "https://files.pythonhosted.org/packages/19/ae/00884ab77045a2f54db90932f9d1ca522201e2a6b2cf2a9b38840db0fd54/granian-2.7.2-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:34708b145e31b4538e0556704a07454a76d6776c55c5bc3a1335e80ef6b3bae3", size = 7062571, upload-time = "2026-02-24T23:03:27.278Z" },
+    { url = "https://files.pythonhosted.org/packages/69/4a/8ce622f4f7d58e035d121b9957dd5a8929028dc99cfc5d2bf7f2aa28912c/granian-2.7.2-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:592806c28c491f9c1d1501bac706ecf5e72b73969f20f912678d53308786d658", size = 6442041, upload-time = "2026-02-24T23:03:30.986Z" },
+    { url = "https://files.pythonhosted.org/packages/27/62/7d36ed38a40a68c2856b6d2a6fedd40833e7f82eb90ba0d03f2d69ffadf5/granian-2.7.2-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c9dcde3968b921654bde999468e97d03031f28668bc1fc145c81d8bedb0fb2a4", size = 6100793, upload-time = "2026-02-24T23:03:32.734Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/c5/17fea68f4cb280c217cbd65534664722c9c9b0138c2754e20c235d70b5f4/granian-2.7.2-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6d4d78408283ec51f0fb00557856b4593947ad5b48287c04e1c22764a0ac28a5", size = 7119810, upload-time = "2026-02-24T23:03:34.807Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/76/35e240d107e0f158662652fd61191de4fb0c2c080e3786ca8f16c71547b7/granian-2.7.2-cp314-cp314-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66d28b078e8087f794b83822055f95caf93d83b23f47f4efcd5e2f0f7a5d8a81", size = 6450789, upload-time = "2026-02-24T23:03:36.81Z" },
+    { url = "https://files.pythonhosted.org/packages/4c/55/a6d08cfecc808149a910e51c57883ab26fad69d922dc2e76fb2d87469e2d/granian-2.7.2-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4ff7a93123ab339ba6cad51cc7141f8880ec47b152ce2491595bb08edda20106", size = 6902672, upload-time = "2026-02-24T23:03:38.655Z" },
+    { url = "https://files.pythonhosted.org/packages/98/2e/c86d95f324248fcc5dcaf034c9f688b32f7a488f0b2a4a25e6673776107f/granian-2.7.2-cp314-cp314-manylinux_2_28_aarch64.whl", hash = "sha256:a52effb9889f0944f0353afd6ce5a9d9aa83826d44bbf3c8013e978a3d6ef7b7", size = 6964399, upload-time = "2026-02-24T23:03:40.459Z" },
+    { url = "https://files.pythonhosted.org/packages/37/4b/44fde33fe10245a3fba76bf843c387fad2d548244345115b9d87e1c40994/granian-2.7.2-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:76c987c3ca78bf7666ab053c3ed7e3af405af91b2e5ce2f1cf92634c1581e238", size = 7034929, upload-time = "2026-02-24T23:03:42.149Z" },
+    { url = "https://files.pythonhosted.org/packages/90/76/38d205cb527046241a9ee4f51048bf44101c626ad4d2af16dd9d14dc1db6/granian-2.7.2-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:6590f8092c2bb6614e561ba771f084cbf72ecbc38dbf9849762ac38718085c29", size = 7259609, upload-time = "2026-02-24T23:03:43.852Z" },
+    { url = "https://files.pythonhosted.org/packages/00/37/04245c7259e65f1083ce193875c6c44da4c98604d3b00a264a74dd4f042b/granian-2.7.2-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:7c1ce9b0c9446b680e9545e7fc95a75f0c53a25dedcf924b1750c3e5ba5bf908", size = 7073161, upload-time = "2026-02-24T23:03:45.655Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/07/0e56fb4f178e14b4c1fa1f6f00586ca81761ccbe2d8803f2c12b6b17a7d6/granian-2.7.2-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:a698d9b662d5648c8ae3dc01ad01688e1a8afc3525e431e7cddb841c53e5e291", size = 6415279, upload-time = "2026-02-24T23:03:48.932Z" },
+    { url = "https://files.pythonhosted.org/packages/27/bc/3e69305bf34806cd852f4683deec844a2cb9a4d8888d7f172b507f6080a8/granian-2.7.2-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:17516095b520b3c039ddbe41a6beb2c59d554b668cc229d36d82c93154a799af", size = 6090528, upload-time = "2026-02-24T23:03:50.52Z" },
+    { url = "https://files.pythonhosted.org/packages/ec/10/7d58a922b44417a6207c0a3230b0841cd7385a36fc518ac15fed16ebf6f7/granian-2.7.2-cp314-cp314t-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:96b0fd9eac60f939b3cbe44c8f32a42fdb7c1a1a9e07ca89e7795cdc7a606beb", size = 6252291, upload-time = "2026-02-24T23:03:52.248Z" },
+    { url = "https://files.pythonhosted.org/packages/54/56/65776c6d759dcef9cce15bc11bdea2c64fe668088faf35d87916bd88f595/granian-2.7.2-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e50fb13e053384b8bd3823d4967606c6fd89f2b0d20e64de3ae212b85ffdfed2", size = 7106748, upload-time = "2026-02-24T23:03:53.994Z" },
+    { url = "https://files.pythonhosted.org/packages/81/ee/d9ed836316607401f158ac264a3f770469d1b1edbf119402777a9eff1833/granian-2.7.2-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9bb1ef13125bc05ab2e18869ed311beaeb085a4c4c195d55d0865f5753a4c0b4", size = 6778883, upload-time = "2026-02-24T23:03:55.574Z" },
+    { url = "https://files.pythonhosted.org/packages/a1/46/eabab80e07a14527c336dec6d902329399f3ba2b82dc94b6435651021359/granian-2.7.2-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:b1c77189335070c6ba6b8d158518fde4c50f892753620f0b22a7552ad4347143", size = 6903426, upload-time = "2026-02-24T23:03:57.296Z" },
+    { url = "https://files.pythonhosted.org/packages/24/8a/8ce186826066f6d453316229383a5be3b0b8a4130146c21f321ee64fe2cb/granian-2.7.2-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:1777166c3c853eed4440adb3cbbf34bba2b77d595bfc143a5826904a80b22f34", size = 7083877, upload-time = "2026-02-24T23:03:59.425Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/eb/91ed4646ce1c920ad39db0bcddb6f4755e1823002b14fb026104e3eb8bce/granian-2.7.2-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:0ffac19208ae548f3647c849579b803beaed2b50dfb0f3790ad26daac0033484", size = 7267282, upload-time = "2026-02-24T23:04:01.218Z" },
+    { url = "https://files.pythonhosted.org/packages/49/2f/58cba479254530ab09132e150e4ab55362f6e875d9e82b6790477843e0aa/granian-2.7.2-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:82f34e78c1297bf5a1b6a5097e30428db98b59fce60a7387977b794855c0c3bc", size = 7054941, upload-time = "2026-02-24T23:04:03.211Z" },
+    { url = "https://files.pythonhosted.org/packages/59/71/f21b26c7dc7a8bc9d8288552c9c12128e73f1c3f04799b6e28a0a269b9b0/granian-2.7.2-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:5613ee8c1233a79e56e1735e19c8c70af22a8c6b5808d7c1423dc5387bee4c05", size = 6504773, upload-time = "2026-02-24T23:04:06.498Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/68/282fbf5418f9348f657f505dc744cdca70ac850d39a805b21395211bf099/granian-2.7.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:0cd6fee79f585de2e1a90b6a311f62b3768c7cda649bc0e02908157ffa2553cc", size = 6138096, upload-time = "2026-02-24T23:04:09.138Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/e0/b578709020f84c07ad2ca88f77ac67fd2c62e6b16f93ff8c8d65b7d99296/granian-2.7.2-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e94c825f8b327114f7062d158c502a540ef5819f809e10158f0edddddaf41bb9", size = 6900043, upload-time = "2026-02-24T23:04:11.015Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/2f/a2671cc160f29ccf8e605eb8fa113c01051b0d7947048c5b29eb4e603384/granian-2.7.2-pp311-pypy311_pp73-manylinux_2_28_aarch64.whl", hash = "sha256:a6adea5fb8a537d18f3f2b848023151063bc45896415fdebfeb0bf0663d5a03b", size = 7040211, upload-time = "2026-02-24T23:04:13.31Z" },
+    { url = "https://files.pythonhosted.org/packages/36/ce/df9bba3b211cda2d47535bb21bc040007e021e8c8adc20ce36619f903bc4/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:2392ab03cb92b1b2d4363f450b2d875177e10f0e22d67a4423052e6885e430f2", size = 7118085, upload-time = "2026-02-24T23:04:15.05Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/87/37124b2ee0cddce6ba438b0ff879ddae094ae2c92b24b28ffbe35110931f/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:406c0bb1f5bf55c72cfbfdfd2ccec21299eb3f7b311d85c4889dde357fd36f33", size = 7314667, upload-time = "2026-02-24T23:04:16.783Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/ac/8b142ed352bc525e3c97440aab312928beebc735927b0cf979692bfcda3b/granian-2.7.2-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:362a6001daa2ce62532a49df407fe545076052ef29289a76d5760064d820f48b", size = 7004934, upload-time = "2026-02-24T23:04:19.059Z" },
 ]
 
 [package.optional-dependencies]
@@ -2722,10 +2784,11 @@ wheels = [
 
 [[package]]
 name = "ocrmypdf"
-version = "16.13.0"
+version = "17.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecation", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fpdf2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "img2pdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "packaging", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pdfminer-six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2733,11 +2796,14 @@ dependencies = [
     { name = "pikepdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pluggy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pypdfium2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "rich", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "uharfbuzz", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8c/52/be1aaece0703a736757d8957c0d4f19c37561054169b501eb0e7132f15e5/ocrmypdf-16.13.0.tar.gz", hash = "sha256:29d37e915234ce717374863a9cc5dd32d29e063dfe60c51380dda71254c88248", size = 7042247, upload-time = "2025-12-24T07:58:35.86Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/fe/60bdc79529be1ad8b151d426ed2020d5ac90328c54e9ba92bd808e1535c1/ocrmypdf-17.3.0.tar.gz", hash = "sha256:4022f13aad3f405e330056a07aa8bd63714b48b414693831b56e2cf2c325f52d", size = 7378015, upload-time = "2026-02-21T09:30:07.207Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/b1/e2e7ad98de0d3ee05b44dbc3f78ccb158a620f3add82d00c85490120e7f2/ocrmypdf-16.13.0-py3-none-any.whl", hash = "sha256:fad8a6f7cc52cdc6225095c401a1766c778c47efe9f1e854ae4dc64a550a3d37", size = 165377, upload-time = "2025-12-24T07:58:33.925Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/b1/b7ae057a1bcb1495067ee3c4d48c1ce5fc66addd9492307c5a0ff799a7f2/ocrmypdf-17.3.0-py3-none-any.whl", hash = "sha256:c8882e7864954d3db6bcee49cc9f261b65bff66b7e5925eb68a1c281f41cad23", size = 488130, upload-time = "2026-02-21T09:30:05.236Z" },
 ]
 
 [[package]]
@@ -2958,10 +3024,10 @@ requires-dist = [
     { name = "djangorestframework", specifier = "~=3.16" },
     { name = "djangorestframework-guardian", specifier = "~=0.4.0" },
     { name = "drf-spectacular", specifier = "~=0.28" },
-    { name = "drf-spectacular-sidecar", specifier = "~=2026.1.1" },
+    { name = "drf-spectacular-sidecar", specifier = "~=2026.3.1" },
     { name = "drf-writable-nested", specifier = "~=0.7.1" },
     { name = "faiss-cpu", specifier = ">=1.10" },
-    { name = "filelock", specifier = "~=3.20.3" },
+    { name = "filelock", specifier = "~=3.25.2" },
     { name = "flower", specifier = "~=2.0.1" },
     { name = "gotenberg-client", specifier = "~=0.13.1" },
     { name = "granian", extras = ["uvloop"], marker = "extra == 'webserver'", specifier = "~=2.7.0" },
@@ -2978,7 +3044,7 @@ requires-dist = [
     { name = "llama-index-vector-stores-faiss", specifier = ">=0.5.2" },
     { name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
     { name = "nltk", specifier = "~=3.9.1" },
-    { name = "ocrmypdf", specifier = "~=16.13.0" },
+    { name = "ocrmypdf", specifier = "~=17.3.0" },
     { name = "openai", specifier = ">=1.76" },
     { name = "pathvalidate", specifier = "~=3.3.1" },
     { name = "pdf2image", specifier = "~=1.17.0" },
@@ -2995,7 +3061,7 @@ requires-dist = [
     { name = "rapidfuzz", specifier = "~=3.14.0" },
     { name = "redis", extras = ["hiredis"], specifier = "~=5.2.1" },
     { name = "regex", specifier = ">=2025.9.18" },
-    { name = "scikit-learn", specifier = "~=1.7.0" },
+    { name = "scikit-learn", specifier = "~=1.8.0" },
     { name = "sentence-transformers", specifier = ">=4.1" },
     { name = "setproctitle", specifier = "~=1.3.4" },
     { name = "tika-client", specifier = "~=0.10.0" },
@@ -3011,7 +3077,7 @@ provides-extras = ["mariadb", "postgres", "webserver"]
 dev = [
     { name = "daphne" },
     { name = "factory-boy", specifier = "~=3.3.1" },
-    { name = "faker", specifier = "~=40.5.1" },
+    { name = "faker", specifier = "~=40.8.0" },
     { name = "imagehash" },
     { name = "prek", specifier = "~=0.3.0" },
     { name = "pytest", specifier = "~=9.0.0" },
@@ -3034,7 +3100,7 @@ lint = [
 testing = [
     { name = "daphne" },
     { name = "factory-boy", specifier = "~=3.3.1" },
-    { name = "faker", specifier = "~=40.5.1" },
+    { name = "faker", specifier = "~=40.8.0" },
     { name = "imagehash" },
     { name = "pytest", specifier = "~=9.0.0" },
     { name = "pytest-cov", specifier = "~=7.0.0" },
@@ -3656,16 +3722,40 @@ wheels = [
 ]
 
 [[package]]
-name = "pyrefly"
-version = "0.54.0"
+name = "pypdfium2"
+version = "5.6.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/81/44/c10b16a302fda90d0af1328f880b232761b510eab546616a7be2fdf35a57/pyrefly-0.54.0.tar.gz", hash = "sha256:c6663be64d492f0d2f2a411ada9f28a6792163d34133639378b7f3dd9a8dca94", size = 5098893, upload-time = "2026-02-23T15:44:35.111Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/3b/01/be763b9081c7eb823196e7d13d9c145bf75ac43f3c1466de81c21c24b381/pypdfium2-5.6.0.tar.gz", hash = "sha256:bcb9368acfe3547054698abbdae68ba0cbd2d3bda8e8ee437e061deef061976d", size = 270714, upload-time = "2026-03-08T01:05:06.5Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5f/99/8fdcdb4e55f0227fdd9f6abce36b619bab1ecb0662b83b66adc8cba3c788/pyrefly-0.54.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:58a3f092b6dc25ef79b2dc6c69a40f36784ca157c312bfc0baea463926a9db6d", size = 12223973, upload-time = "2026-02-23T15:44:14.278Z" },
-    { url = "https://files.pythonhosted.org/packages/90/35/c2aaf87a76003ad27b286594d2e5178f811eaa15bfe3d98dba2b47d56dd1/pyrefly-0.54.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:615081414106dd95873bc39c3a4bed68754c6cc24a8177ac51d22f88f88d3eb3", size = 11785585, upload-time = "2026-02-23T15:44:17.468Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/4a/ced02691ed67e5a897714979196f08ad279ec7ec7f63c45e00a75a7f3c0e/pyrefly-0.54.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0cbcaf20f5fe585079079a95205c1f3cd4542d17228cdf1df560288880623b70", size = 33381977, upload-time = "2026-02-23T15:44:19.736Z" },
-    { url = "https://files.pythonhosted.org/packages/0b/ce/72a117ed437c8f6950862181014b41e36f3c3997580e29b772b71e78d587/pyrefly-0.54.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66d5da116c0d34acfbd66663addd3ca8aa78a636f6692a66e078126d3620a883", size = 35962821, upload-time = "2026-02-23T15:44:22.357Z" },
-    { url = "https://files.pythonhosted.org/packages/85/de/89013f5ae0a35d2b6b01274a92a35ee91431ea001050edf0a16748d39875/pyrefly-0.54.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ef3ac27f1a4baaf67aead64287d3163350844794aca6315ad1a9650b16ec26a", size = 38496689, upload-time = "2026-02-23T15:44:25.236Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/f6/9f9e190fe0e5a6b86b82f83bd8b5d3490348766062381140ca5cad8e00b1/pypdfium2-5.6.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e468c38997573f0e86f03273c2c1fbdea999de52ba43fee96acaa2f6b2ad35f7", size = 3412541, upload-time = "2026-03-08T01:04:25.45Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/8d/e57492cb2228ba56ed57de1ff044c8ac114b46905f8b1445c33299ba0488/pypdfium2-5.6.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:ad3abddc5805424f962e383253ccad6a0d1d2ebd86afa9a9e1b9ca659773cd0d", size = 3592320, upload-time = "2026-03-08T01:04:27.509Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/8a/8ab82e33e9c551494cbe1526ea250ca8cc4e9e98d6a4fc6b6f8d959aa1d1/pypdfium2-5.6.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6b5eb9eae5c45076395454522ca26add72ba8bd1fe473e1e4721aa58521470c", size = 3596450, upload-time = "2026-03-08T01:04:29.183Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/b5/602a792282312ccb158cc63849528079d94b0a11efdc61f2a359edfb41e9/pypdfium2-5.6.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:258624da8ef45cdc426e11b33e9d83f9fb723c1c201c6e0f4ab5a85966c6b876", size = 3325442, upload-time = "2026-03-08T01:04:30.886Z" },
+    { url = "https://files.pythonhosted.org/packages/81/1f/9e48ec05ed8d19d736c2d1f23c1bd0f20673f02ef846a2576c69e237f15d/pypdfium2-5.6.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e9367451c8a00931d6612db0822525a18c06f649d562cd323a719e46ac19c9bb", size = 3727434, upload-time = "2026-03-08T01:04:33.619Z" },
+    { url = "https://files.pythonhosted.org/packages/33/90/0efd020928b4edbd65f4f3c2af0c84e20b43a3ada8fa6d04f999a97afe7a/pypdfium2-5.6.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a757869f891eac1cc1372e38a4aa01adac8abc8fe2a8a4e2ebf50595e3bf5937", size = 4139029, upload-time = "2026-03-08T01:04:36.08Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/49/a640b288a48dab1752281dd9b72c0679fccea107874e80a65a606b00efa9/pypdfium2-5.6.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:515be355222cc57ae9e62cd5c7c350b8e0c863efc539f80c7d75e2811ba45cb6", size = 3646387, upload-time = "2026-03-08T01:04:38.151Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/3b/a344c19c01021eeb5d830c102e4fc9b1602f19c04aa7d11abbe2d188fd8e/pypdfium2-5.6.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1c4753c7caf7d004211d7f57a21f10d127f5e0e5510a14d24bc073e7220a3ea", size = 3097212, upload-time = "2026-03-08T01:04:40.776Z" },
+    { url = "https://files.pythonhosted.org/packages/50/96/e48e13789ace22aeb9b7510904a1b1493ec588196e11bbacc122da330b3d/pypdfium2-5.6.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c49729090281fdd85775fb8912c10bd19e99178efaa98f145ab06e7ce68554d2", size = 2965026, upload-time = "2026-03-08T01:04:42.857Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/06/3100e44d4935f73af8f5d633d3bd40f0d36d606027085a0ef1f0566a6320/pypdfium2-5.6.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a4a1749a8d4afd62924a8d95cfa4f2e26fc32957ce34ac3b674be6f127ed252e", size = 4131431, upload-time = "2026-03-08T01:04:44.982Z" },
+    { url = "https://files.pythonhosted.org/packages/64/ef/d8df63569ce9a66c8496057782eb8af78e0d28667922d62ec958434e3d4b/pypdfium2-5.6.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:36469ebd0fdffb7130ce45ed9c44f8232d91571c89eb851bd1633c64b6f6114f", size = 3747469, upload-time = "2026-03-08T01:04:46.702Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/47/fd2c6a67a49fade1acd719fbd11f7c375e7219912923ef2de0ea0ac1544e/pypdfium2-5.6.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:9da900df09be3cf546b637a127a7b6428fb22d705951d731269e25fd3adef457", size = 4337578, upload-time = "2026-03-08T01:04:49.007Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/f5/836c83e54b01e09478c4d6bf4912651d6053c932250fcee953f5c72d8e4a/pypdfium2-5.6.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:45fccd5622233c5ec91a885770ae7dd4004d4320ac05a4ad8fa03a66dea40244", size = 4376104, upload-time = "2026-03-08T01:04:51.04Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/7f/b940b6a1664daf8f9bad87c6c99b84effa3611615b8708d10392dc33036c/pypdfium2-5.6.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:282dc030e767cd61bd0299f9d581052b91188e2b87561489057a8e7963e7e0cb", size = 3929824, upload-time = "2026-03-08T01:04:53.544Z" },
+    { url = "https://files.pythonhosted.org/packages/88/79/00267d92a6a58c229e364d474f5698efe446e0c7f4f152f58d0138715e99/pypdfium2-5.6.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:a1c1dfe950382c76a7bba1ba160ec5e40df8dd26b04a1124ae268fda55bc4cbe", size = 4270201, upload-time = "2026-03-08T01:04:55.81Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/ab/b127f38aba41746bdf9ace15ba08411d7ef6ecba1326d529ba414eb1ed50/pypdfium2-5.6.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:43b0341ca6feb6c92e4b7a9eb4813e5466f5f5e8b6baeb14df0a94d5f312c00b", size = 4180793, upload-time = "2026-03-08T01:04:57.961Z" },
+]
+
+[[package]]
+name = "pyrefly"
+version = "0.55.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bf/c4/76e0797215e62d007f81f86c9c4fb5d6202685a3f5e70810f3fd94294f92/pyrefly-0.55.0.tar.gz", hash = "sha256:434c3282532dd4525c4840f2040ed0eb79b0ec8224fe18d957956b15471f2441", size = 5135682, upload-time = "2026-03-03T00:46:38.122Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/39/b0/16e50cf716784513648e23e726a24f71f9544aa4f86103032dcaa5ff71a2/pyrefly-0.55.0-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:49aafcefe5e2dd4256147db93e5b0ada42bff7d9a60db70e03d1f7055338eec9", size = 12210073, upload-time = "2026-03-03T00:46:15.51Z" },
+    { url = "https://files.pythonhosted.org/packages/3a/ad/89500c01bac3083383011600370289fbc67700c5be46e781787392628a3a/pyrefly-0.55.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:2827426e6b28397c13badb93c0ede0fb0f48046a7a89e3d774cda04e8e2067cd", size = 11767474, upload-time = "2026-03-03T00:46:18.003Z" },
+    { url = "https://files.pythonhosted.org/packages/78/68/4c66b260f817f304ead11176ff13985625f7c269e653304b4bdb546551af/pyrefly-0.55.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7346b2d64dc575bd61aa3bca854fbf8b5a19a471cbdb45e0ca1e09861b63488c", size = 33260395, upload-time = "2026-03-03T00:46:20.509Z" },
+    { url = "https://files.pythonhosted.org/packages/47/09/10bd48c9f860064f29f412954126a827d60f6451512224912c265e26bbe6/pyrefly-0.55.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:233b861b4cff008b1aff62f4f941577ed752e4d0060834229eb9b6826e6973c9", size = 35848269, upload-time = "2026-03-03T00:46:23.418Z" },
+    { url = "https://files.pythonhosted.org/packages/a9/39/bc65cdd5243eb2dfea25dd1321f9a5a93e8d9c3a308501c4c6c05d011585/pyrefly-0.55.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f5aa85657d76da1d25d081a49f0e33c8fc3ec91c1a0f185a8ed393a5a3d9e178", size = 38449820, upload-time = "2026-03-03T00:46:26.309Z" },
 ]
 
 [[package]]
@@ -4283,7 +4373,7 @@ wheels = [
 
 [[package]]
 name = "scikit-learn"
-version = "1.7.2"
+version = "1.8.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "joblib", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -4291,28 +4381,32 @@ dependencies = [
     { name = "scipy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "threadpoolctl", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/0e/d4/40988bf3b8e34feec1d0e6a051446b1f66225f8529b9309becaeef62b6c4/scikit_learn-1.8.0.tar.gz", hash = "sha256:9bccbb3b40e3de10351f8f5068e105d0f4083b1a65fa07b6634fbc401a6287fd", size = 7335585, upload-time = "2025-12-10T07:08:53.618Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/43/83/564e141eef908a5863a54da8ca342a137f45a0bfb71d1d79704c9894c9d1/scikit_learn-1.7.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:c7509693451651cd7361d30ce4e86a1347493554f172b1c72a39300fa2aea79e", size = 9331967, upload-time = "2025-09-09T08:20:32.421Z" },
-    { url = "https://files.pythonhosted.org/packages/18/d6/ba863a4171ac9d7314c4d3fc251f015704a2caeee41ced89f321c049ed83/scikit_learn-1.7.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:0486c8f827c2e7b64837c731c8feff72c0bd2b998067a8a9cbc10643c31f0fe1", size = 8648645, upload-time = "2025-09-09T08:20:34.436Z" },
-    { url = "https://files.pythonhosted.org/packages/ef/0e/97dbca66347b8cf0ea8b529e6bb9367e337ba2e8be0ef5c1a545232abfde/scikit_learn-1.7.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:89877e19a80c7b11a2891a27c21c4894fb18e2c2e077815bcade10d34287b20d", size = 9715424, upload-time = "2025-09-09T08:20:36.776Z" },
-    { url = "https://files.pythonhosted.org/packages/f7/32/1f3b22e3207e1d2c883a7e09abb956362e7d1bd2f14458c7de258a26ac15/scikit_learn-1.7.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8da8bf89d4d79aaec192d2bda62f9b56ae4e5b4ef93b6a56b5de4977e375c1f1", size = 9509234, upload-time = "2025-09-09T08:20:38.957Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/aa/3996e2196075689afb9fce0410ebdb4a09099d7964d061d7213700204409/scikit_learn-1.7.2-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:8d91a97fa2b706943822398ab943cde71858a50245e31bc71dba62aab1d60a96", size = 9259818, upload-time = "2025-09-09T08:20:43.19Z" },
-    { url = "https://files.pythonhosted.org/packages/43/5d/779320063e88af9c4a7c2cf463ff11c21ac9c8bd730c4a294b0000b666c9/scikit_learn-1.7.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:acbc0f5fd2edd3432a22c69bed78e837c70cf896cd7993d71d51ba6708507476", size = 8636997, upload-time = "2025-09-09T08:20:45.468Z" },
-    { url = "https://files.pythonhosted.org/packages/5c/d0/0c577d9325b05594fdd33aa970bf53fb673f051a45496842caee13cfd7fe/scikit_learn-1.7.2-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5bf3d930aee75a65478df91ac1225ff89cd28e9ac7bd1196853a9229b6adb0b", size = 9478381, upload-time = "2025-09-09T08:20:47.982Z" },
-    { url = "https://files.pythonhosted.org/packages/82/70/8bf44b933837ba8494ca0fc9a9ab60f1c13b062ad0197f60a56e2fc4c43e/scikit_learn-1.7.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b4d6e9deed1a47aca9fe2f267ab8e8fe82ee20b4526b2c0cd9e135cea10feb44", size = 9300296, upload-time = "2025-09-09T08:20:50.366Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/93/a3038cb0293037fd335f77f31fe053b89c72f17b1c8908c576c29d953e84/scikit_learn-1.7.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0b7dacaa05e5d76759fb071558a8b5130f4845166d88654a0f9bdf3eb57851b7", size = 9212382, upload-time = "2025-09-09T08:20:54.731Z" },
-    { url = "https://files.pythonhosted.org/packages/40/dd/9a88879b0c1104259136146e4742026b52df8540c39fec21a6383f8292c7/scikit_learn-1.7.2-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:abebbd61ad9e1deed54cca45caea8ad5f79e1b93173dece40bb8e0c658dbe6fe", size = 8592042, upload-time = "2025-09-09T08:20:57.313Z" },
-    { url = "https://files.pythonhosted.org/packages/46/af/c5e286471b7d10871b811b72ae794ac5fe2989c0a2df07f0ec723030f5f5/scikit_learn-1.7.2-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:502c18e39849c0ea1a5d681af1dbcf15f6cce601aebb657aabbfe84133c1907f", size = 9434180, upload-time = "2025-09-09T08:20:59.671Z" },
-    { url = "https://files.pythonhosted.org/packages/f1/fd/df59faa53312d585023b2da27e866524ffb8faf87a68516c23896c718320/scikit_learn-1.7.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7a4c328a71785382fe3fe676a9ecf2c86189249beff90bf85e22bdb7efaf9ae0", size = 9283660, upload-time = "2025-09-09T08:21:01.71Z" },
-    { url = "https://files.pythonhosted.org/packages/55/87/ef5eb1f267084532c8e4aef98a28b6ffe7425acbfd64b5e2f2e066bc29b3/scikit_learn-1.7.2-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:9acb6c5e867447b4e1390930e3944a005e2cb115922e693c08a323421a6966e8", size = 9558731, upload-time = "2025-09-09T08:21:06.381Z" },
-    { url = "https://files.pythonhosted.org/packages/93/f8/6c1e3fc14b10118068d7938878a9f3f4e6d7b74a8ddb1e5bed65159ccda8/scikit_learn-1.7.2-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:2a41e2a0ef45063e654152ec9d8bcfc39f7afce35b08902bfe290c2498a67a6a", size = 9038852, upload-time = "2025-09-09T08:21:08.628Z" },
-    { url = "https://files.pythonhosted.org/packages/83/87/066cafc896ee540c34becf95d30375fe5cbe93c3b75a0ee9aa852cd60021/scikit_learn-1.7.2-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:98335fb98509b73385b3ab2bd0639b1f610541d3988ee675c670371d6a87aa7c", size = 9527094, upload-time = "2025-09-09T08:21:11.486Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/2b/4903e1ccafa1f6453b1ab78413938c8800633988c838aa0be386cbb33072/scikit_learn-1.7.2-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:191e5550980d45449126e23ed1d5e9e24b2c68329ee1f691a3987476e115e09c", size = 9367436, upload-time = "2025-09-09T08:21:13.602Z" },
-    { url = "https://files.pythonhosted.org/packages/d9/82/dee5acf66837852e8e68df6d8d3a6cb22d3df997b733b032f513d95205b7/scikit_learn-1.7.2-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fa8f63940e29c82d1e67a45d5297bdebbcb585f5a5a50c4914cc2e852ab77f33", size = 9208906, upload-time = "2025-09-09T08:21:18.557Z" },
-    { url = "https://files.pythonhosted.org/packages/3c/30/9029e54e17b87cb7d50d51a5926429c683d5b4c1732f0507a6c3bed9bf65/scikit_learn-1.7.2-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:f95dc55b7902b91331fa4e5845dd5bde0580c9cd9612b1b2791b7e80c3d32615", size = 8627836, upload-time = "2025-09-09T08:21:20.695Z" },
-    { url = "https://files.pythonhosted.org/packages/60/18/4a52c635c71b536879f4b971c2cedf32c35ee78f48367885ed8025d1f7ee/scikit_learn-1.7.2-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9656e4a53e54578ad10a434dc1f993330568cfee176dff07112b8785fb413106", size = 9426236, upload-time = "2025-09-09T08:21:22.645Z" },
-    { url = "https://files.pythonhosted.org/packages/99/7e/290362f6ab582128c53445458a5befd471ed1ea37953d5bcf80604619250/scikit_learn-1.7.2-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:96dc05a854add0e50d3f47a1ef21a10a595016da5b007c7d9cd9d0bffd1fcc61", size = 9312593, upload-time = "2025-09-09T08:21:24.65Z" },
+    { url = "https://files.pythonhosted.org/packages/c9/92/53ea2181da8ac6bf27170191028aee7251f8f841f8d3edbfdcaf2008fde9/scikit_learn-1.8.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:146b4d36f800c013d267b29168813f7a03a43ecd2895d04861f1240b564421da", size = 8595835, upload-time = "2025-12-10T07:07:39.385Z" },
+    { url = "https://files.pythonhosted.org/packages/01/18/d154dc1638803adf987910cdd07097d9c526663a55666a97c124d09fb96a/scikit_learn-1.8.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:f984ca4b14914e6b4094c5d52a32ea16b49832c03bd17a110f004db3c223e8e1", size = 8080381, upload-time = "2025-12-10T07:07:41.93Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/44/226142fcb7b7101e64fdee5f49dbe6288d4c7af8abf593237b70fca080a4/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5e30adb87f0cc81c7690a84f7932dd66be5bac57cfe16b91cb9151683a4a2d3b", size = 8799632, upload-time = "2025-12-10T07:07:43.899Z" },
+    { url = "https://files.pythonhosted.org/packages/36/4d/4a67f30778a45d542bbea5db2dbfa1e9e100bf9ba64aefe34215ba9f11f6/scikit_learn-1.8.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ada8121bcb4dac28d930febc791a69f7cb1673c8495e5eee274190b73a4559c1", size = 9103788, upload-time = "2025-12-10T07:07:45.982Z" },
+    { url = "https://files.pythonhosted.org/packages/90/74/e6a7cc4b820e95cc38cf36cd74d5aa2b42e8ffc2d21fe5a9a9c45c1c7630/scikit_learn-1.8.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:5fb63362b5a7ddab88e52b6dbb47dac3fd7dafeee740dc6c8d8a446ddedade8e", size = 8548242, upload-time = "2025-12-10T07:07:51.568Z" },
+    { url = "https://files.pythonhosted.org/packages/49/d8/9be608c6024d021041c7f0b3928d4749a706f4e2c3832bbede4fb4f58c95/scikit_learn-1.8.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:5025ce924beccb28298246e589c691fe1b8c1c96507e6d27d12c5fadd85bfd76", size = 8079075, upload-time = "2025-12-10T07:07:53.697Z" },
+    { url = "https://files.pythonhosted.org/packages/dd/47/f187b4636ff80cc63f21cd40b7b2d177134acaa10f6bb73746130ee8c2e5/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4496bb2cf7a43ce1a2d7524a79e40bc5da45cf598dbf9545b7e8316ccba47bb4", size = 8660492, upload-time = "2025-12-10T07:07:55.574Z" },
+    { url = "https://files.pythonhosted.org/packages/97/74/b7a304feb2b49df9fafa9382d4d09061a96ee9a9449a7cbea7988dda0828/scikit_learn-1.8.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a0bcfe4d0d14aec44921545fd2af2338c7471de9cb701f1da4c9d85906ab847a", size = 8931904, upload-time = "2025-12-10T07:07:57.666Z" },
+    { url = "https://files.pythonhosted.org/packages/03/aa/e22e0768512ce9255eba34775be2e85c2048da73da1193e841707f8f039c/scikit_learn-1.8.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:0d6ae97234d5d7079dc0040990a6f7aeb97cb7fa7e8945f1999a429b23569e0a", size = 8513770, upload-time = "2025-12-10T07:08:03.251Z" },
+    { url = "https://files.pythonhosted.org/packages/58/37/31b83b2594105f61a381fc74ca19e8780ee923be2d496fcd8d2e1147bd99/scikit_learn-1.8.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:edec98c5e7c128328124a029bceb09eda2d526997780fef8d65e9a69eead963e", size = 8044458, upload-time = "2025-12-10T07:08:05.336Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/5a/3f1caed8765f33eabb723596666da4ebbf43d11e96550fb18bdec42b467b/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:74b66d8689d52ed04c271e1329f0c61635bcaf5b926db9b12d58914cdc01fe57", size = 8610341, upload-time = "2025-12-10T07:08:07.732Z" },
+    { url = "https://files.pythonhosted.org/packages/38/cf/06896db3f71c75902a8e9943b444a56e727418f6b4b4a90c98c934f51ed4/scikit_learn-1.8.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8fdf95767f989b0cfedb85f7ed8ca215d4be728031f56ff5a519ee1e3276dc2e", size = 8900022, upload-time = "2025-12-10T07:08:09.862Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/7d/a630359fc9dcc95496588c8d8e3245cc8fd81980251079bc09c70d41d951/scikit_learn-1.8.0-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:7cc267b6108f0a1499a734167282c00c4ebf61328566b55ef262d48e9849c735", size = 8826045, upload-time = "2025-12-10T07:08:15.215Z" },
+    { url = "https://files.pythonhosted.org/packages/cc/56/a0c86f6930cfcd1c7054a2bc417e26960bb88d32444fe7f71d5c2cfae891/scikit_learn-1.8.0-cp313-cp313t-macosx_12_0_arm64.whl", hash = "sha256:fe1c011a640a9f0791146011dfd3c7d9669785f9fed2b2a5f9e207536cf5c2fd", size = 8420324, upload-time = "2025-12-10T07:08:17.561Z" },
+    { url = "https://files.pythonhosted.org/packages/46/1e/05962ea1cebc1cf3876667ecb14c283ef755bf409993c5946ade3b77e303/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:72358cce49465d140cc4e7792015bb1f0296a9742d5622c67e31399b75468b9e", size = 8680651, upload-time = "2025-12-10T07:08:19.952Z" },
+    { url = "https://files.pythonhosted.org/packages/fe/56/a85473cd75f200c9759e3a5f0bcab2d116c92a8a02ee08ccd73b870f8bb4/scikit_learn-1.8.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:80832434a6cc114f5219211eec13dcbc16c2bac0e31ef64c6d346cde3cf054cb", size = 8925045, upload-time = "2025-12-10T07:08:22.11Z" },
+    { url = "https://files.pythonhosted.org/packages/24/05/1af2c186174cc92dcab2233f327336058c077d38f6fe2aceb08e6ab4d509/scikit_learn-1.8.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:c22a2da7a198c28dd1a6e1136f19c830beab7fdca5b3e5c8bba8394f8a5c45b3", size = 8528667, upload-time = "2025-12-10T07:08:27.541Z" },
+    { url = "https://files.pythonhosted.org/packages/a8/25/01c0af38fe969473fb292bba9dc2b8f9b451f3112ff242c647fee3d0dfe7/scikit_learn-1.8.0-cp314-cp314-macosx_12_0_arm64.whl", hash = "sha256:6b595b07a03069a2b1740dc08c2299993850ea81cce4fe19b2421e0c970de6b7", size = 8066524, upload-time = "2025-12-10T07:08:29.822Z" },
+    { url = "https://files.pythonhosted.org/packages/be/ce/a0623350aa0b68647333940ee46fe45086c6060ec604874e38e9ab7d8e6c/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:29ffc74089f3d5e87dfca4c2c8450f88bdc61b0fc6ed5d267f3988f19a1309f6", size = 8657133, upload-time = "2025-12-10T07:08:31.865Z" },
+    { url = "https://files.pythonhosted.org/packages/b8/cb/861b41341d6f1245e6ca80b1c1a8c4dfce43255b03df034429089ca2a2c5/scikit_learn-1.8.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:fb65db5d7531bccf3a4f6bec3462223bea71384e2cda41da0f10b7c292b9e7c4", size = 8923223, upload-time = "2025-12-10T07:08:34.166Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/d1/ef294ca754826daa043b2a104e59960abfab4cf653891037d19dd5b6f3cf/scikit_learn-1.8.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:4511be56637e46c25721e83d1a9cea9614e7badc7040c4d573d75fbe257d6fd7", size = 8848305, upload-time = "2025-12-10T07:08:41.013Z" },
+    { url = "https://files.pythonhosted.org/packages/5b/e2/b1f8b05138ee813b8e1a4149f2f0d289547e60851fd1bb268886915adbda/scikit_learn-1.8.0-cp314-cp314t-macosx_12_0_arm64.whl", hash = "sha256:a69525355a641bf8ef136a7fa447672fb54fe8d60cab5538d9eb7c6438543fb9", size = 8432257, upload-time = "2025-12-10T07:08:42.873Z" },
+    { url = "https://files.pythonhosted.org/packages/26/11/c32b2138a85dcb0c99f6afd13a70a951bfdff8a6ab42d8160522542fb647/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c2656924ec73e5939c76ac4c8b026fc203b83d8900362eb2599d8aee80e4880f", size = 8678673, upload-time = "2025-12-10T07:08:45.362Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/57/51f2384575bdec454f4fe4e7a919d696c9ebce914590abf3e52d47607ab8/scikit_learn-1.8.0-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15fc3b5d19cc2be65404786857f2e13c70c83dd4782676dd6814e3b89dc8f5b9", size = 8922467, upload-time = "2025-12-10T07:08:47.408Z" },
 ]
 
 [[package]]
@@ -4809,18 +4903,16 @@ wheels = [
 
 [[package]]
 name = "tornado"
-version = "6.5.4"
+version = "6.5.5"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/37/1d/0a336abf618272d53f62ebe274f712e213f5a03c0b2339575430b8362ef2/tornado-6.5.4.tar.gz", hash = "sha256:a22fa9047405d03260b483980635f0b041989d8bcc9a313f8fe18b411d84b1d7", size = 513632, upload-time = "2025-12-15T19:21:03.836Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f8/f1/3173dfa4a18db4a9b03e5d55325559dab51ee653763bb8745a75af491286/tornado-6.5.5.tar.gz", hash = "sha256:192b8f3ea91bd7f1f50c06955416ed76c6b72f96779b962f07f911b91e8d30e9", size = 516006, upload-time = "2026-03-10T21:31:02.067Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ab/a9/e94a9d5224107d7ce3cc1fab8d5dc97f5ea351ccc6322ee4fb661da94e35/tornado-6.5.4-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:d6241c1a16b1c9e4cc28148b1cda97dd1c6cb4fb7068ac1bedc610768dff0ba9", size = 443909, upload-time = "2025-12-15T19:20:48.382Z" },
-    { url = "https://files.pythonhosted.org/packages/db/7e/f7b8d8c4453f305a51f80dbb49014257bb7d28ccb4bbb8dd328ea995ecad/tornado-6.5.4-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:2d50f63dda1d2cac3ae1fa23d254e16b5e38153758470e9956cbc3d813d40843", size = 442163, upload-time = "2025-12-15T19:20:49.791Z" },
-    { url = "https://files.pythonhosted.org/packages/ba/b5/206f82d51e1bfa940ba366a8d2f83904b15942c45a78dd978b599870ab44/tornado-6.5.4-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d1cf66105dc6acb5af613c054955b8137e34a03698aa53272dbda4afe252be17", size = 445746, upload-time = "2025-12-15T19:20:51.491Z" },
-    { url = "https://files.pythonhosted.org/packages/8e/9d/1a3338e0bd30ada6ad4356c13a0a6c35fbc859063fa7eddb309183364ac1/tornado-6.5.4-cp39-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:50ff0a58b0dc97939d29da29cd624da010e7f804746621c78d14b80238669335", size = 445083, upload-time = "2025-12-15T19:20:52.778Z" },
-    { url = "https://files.pythonhosted.org/packages/50/d4/e51d52047e7eb9a582da59f32125d17c0482d065afd5d3bc435ff2120dc5/tornado-6.5.4-cp39-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e5fb5e04efa54cf0baabdd10061eb4148e0be137166146fff835745f59ab9f7f", size = 445315, upload-time = "2025-12-15T19:20:53.996Z" },
-    { url = "https://files.pythonhosted.org/packages/27/07/2273972f69ca63dbc139694a3fc4684edec3ea3f9efabf77ed32483b875c/tornado-6.5.4-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9c86b1643b33a4cd415f8d0fe53045f913bf07b4a3ef646b735a6a86047dda84", size = 446003, upload-time = "2025-12-15T19:20:56.101Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/83/41c52e47502bf7260044413b6770d1a48dda2f0246f95ee1384a3cd9c44a/tornado-6.5.4-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:6eb82872335a53dd063a4f10917b3efd28270b56a33db69009606a0312660a6f", size = 445412, upload-time = "2025-12-15T19:20:57.398Z" },
-    { url = "https://files.pythonhosted.org/packages/10/c7/bc96917f06cbee182d44735d4ecde9c432e25b84f4c2086143013e7b9e52/tornado-6.5.4-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6076d5dda368c9328ff41ab5d9dd3608e695e8225d1cd0fd1e006f05da3635a8", size = 445392, upload-time = "2025-12-15T19:20:58.692Z" },
+    { url = "https://files.pythonhosted.org/packages/59/8c/77f5097695f4dd8255ecbd08b2a1ed8ba8b953d337804dd7080f199e12bf/tornado-6.5.5-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:487dc9cc380e29f58c7ab88f9e27cdeef04b2140862e5076a66fb6bb68bb1bfa", size = 445983, upload-time = "2026-03-10T21:30:44.28Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/5e/7625b76cd10f98f1516c36ce0346de62061156352353ef2da44e5c21523c/tornado-6.5.5-cp39-abi3-macosx_10_9_x86_64.whl", hash = "sha256:65a7f1d46d4bb41df1ac99f5fcb685fb25c7e61613742d5108b010975a9a6521", size = 444246, upload-time = "2026-03-10T21:30:46.571Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/04/7b5705d5b3c0fab088f434f9c83edac1573830ca49ccf29fb83bf7178eec/tornado-6.5.5-cp39-abi3-manylinux1_x86_64.manylinux_2_28_x86_64.manylinux_2_5_x86_64.whl", hash = "sha256:e74c92e8e65086b338fd56333fb9a68b9f6f2fe7ad532645a290a464bcf46be5", size = 447229, upload-time = "2026-03-10T21:30:48.273Z" },
+    { url = "https://files.pythonhosted.org/packages/34/01/74e034a30ef59afb4097ef8659515e96a39d910b712a89af76f5e4e1f93c/tornado-6.5.5-cp39-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:435319e9e340276428bbdb4e7fa732c2d399386d1de5686cb331ec8eee754f07", size = 448192, upload-time = "2026-03-10T21:30:51.22Z" },
+    { url = "https://files.pythonhosted.org/packages/be/00/fe9e02c5a96429fce1a1d15a517f5d8444f9c412e0bb9eadfbe3b0fc55bf/tornado-6.5.5-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:3f54aa540bdbfee7b9eb268ead60e7d199de5021facd276819c193c0fb28ea4e", size = 448039, upload-time = "2026-03-10T21:30:53.52Z" },
+    { url = "https://files.pythonhosted.org/packages/82/9e/656ee4cec0398b1d18d0f1eb6372c41c6b889722641d84948351ae19556d/tornado-6.5.5-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:36abed1754faeb80fbd6e64db2758091e1320f6bba74a4cf8c09cd18ccce8aca", size = 447445, upload-time = "2026-03-10T21:30:55.541Z" },
 ]
 
 [[package]]
@@ -5141,6 +5233,23 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b1/5e/512aeb40fd819f4660d00f96f5c7371ee36fc8c6b605128c5ee59e0b28c6/u_msgpack_python-2.8.0-py2.py3-none-any.whl", hash = "sha256:1d853d33e78b72c4228a2025b4db28cda81214076e5b0422ed0ae1b1b2bb586a", size = 10590, upload-time = "2023-05-18T09:28:10.323Z" },
 ]
 
+[[package]]
+name = "uharfbuzz"
+version = "0.53.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/1c/8d/7c82298bfa5c96f018541661bc2ccdf90dfe397bb2724db46725bf495466/uharfbuzz-0.53.3.tar.gz", hash = "sha256:9a87175c14d1361322ce2a3504e63c6b66062934a5edf47266aed5b33416806c", size = 1714488, upload-time = "2026-01-24T13:10:43.693Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/88/5df9337adb60d7b1ad150b162bbc5c56d783d15546714085d92b9531f8f3/uharfbuzz-0.53.3-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:d977e41a501d9e8af3f2c329d75031037ee79634bc29ca3872e9115c44e67d25", size = 2722639, upload-time = "2026-01-24T13:10:22.436Z" },
+    { url = "https://files.pythonhosted.org/packages/39/c4/8b4b050e77d6cb9a84af509e5796734f0e687bd02ad11757a581bd6f197d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:21d512c94aa992691aaf5b433deaca7e51f4ea54c68b99f535974073364f806f", size = 1647506, upload-time = "2026-01-24T13:10:24.16Z" },
+    { url = "https://files.pythonhosted.org/packages/30/ff/8e7cf78d525604f3e0a43b9468263fcf2acb5d208a3979c3bfa8dc61112d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dca9a2e071c0c59ba8f382356f31a2518ac3dc7cc77e4f3519defc454c5b9a97", size = 1706448, upload-time = "2026-01-24T13:10:25.729Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/a0/739471cdd52723ecc9fc80f36fb92c706a87265dc258521c1b14d99414f7/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1191a74ddcf18ec721161b6b33a8ab31b0c6a2b15c6724a9b663127bf7f07d2e", size = 2664628, upload-time = "2026-01-24T13:10:27.814Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/4a/63a81e9eef922b9f26bd948b518b73704d01a8d8e83324b2f99084ab7af0/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:35ec3b600b3f63e7659792f9bd43e1ffb389d3d2aac8285f269d11efbe04787d", size = 2757384, upload-time = "2026-01-24T13:10:29.669Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/d2/27be1201488323d0ff0c99fb966a0522b2736f79bd5a5b7b99526fca3d98/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:6f0ad2812303d2c7ccff596fd6c9d5629874f3a83f30255e11639c9b7ba4e89d", size = 1335822, upload-time = "2026-01-24T13:10:34.774Z" },
+    { url = "https://files.pythonhosted.org/packages/70/99/53e39bcd4dec5981eb70a6a76285a862c8a76b80cd52e8f40fe51adab032/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:757d9ed1841912e8f229319f335cf7dd25a2fd377e444bda9deb720617192e12", size = 1237560, upload-time = "2026-01-24T13:10:36.971Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/2b/04d8cde466acfe70373d4f489da5c6eab0aba07d50442dd21217cb0fd167/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d3a0b824811bd1be129356818e6cdbf0e4b056bb60aa9a5eb270bff9d21f24c", size = 1497923, upload-time = "2026-01-24T13:10:38.743Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/01/a250521491bc995609275e0062c552b16f437a3ce15de83250176245093e/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9211d798b2921a99b8c34e810676137f66372d3b5447765b72d969bdfa6abe6a", size = 1556794, upload-time = "2026-01-24T13:10:40.262Z" },
+]
+
 [[package]]
 name = "ujson"
 version = "5.11.0"