fix: add RasterisedDocumentParser to new-style parser shim checks

The new RasterisedDocumentParser uses __enter__/__exit__ for resource
management instead of cleanup(). Update all existing new-style shims to
include it in the isinstance checks:

- documents/consumer.py: _parser_cleanup(), parser_is_new_style
- documents/tasks.py: parser_is_new_style, finally cleanup branch
  (also adds RemoteDocumentParser which was missing from the latter)
- documents/management/commands/document_thumbnails.py: adds new-style
  handling from scratch (enter/exit + 2-arg get_thumbnail signature)

Fix stale import paths in three test files that were still importing
from paperless_tesseract.parsers instead of paperless.parsers.tesseract.

Fix two registry tests that used application/pdf as a proxy for "no
handler" — now that RasterisedDocumentParser is registered, PDF always
has a handler, so switch to a truly unsupported MIME type.

Signal infrastructure and shims remain intact; this is plumbing only.

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

.github/dependabot.yml

@@ -157,6 +157,9 @@ updates:
       postgres:
         patterns:
           - "docker.io/library/postgres*"
+      greenmail:
+        patterns:
+          - "docker.io/greenmail*"
   - package-ecosystem: "pre-commit" # See documentation for possible values
     directory: "/" # Location of package manifests
     schedule:

.github/workflows/ci-docker.yml

@@ -119,7 +119,7 @@ jobs:
           sudo rm -rf "$AGENT_TOOLSDIRECTORY"
       - name: Docker metadata
         id: docker-meta
-        uses: docker/metadata-action@v5.10.0
+        uses: docker/metadata-action@v6.0.0
         with:
           images: |
             ${{ env.REGISTRY }}/${{ steps.repo.outputs.name }}
@@ -130,7 +130,7 @@ jobs:
             type=semver,pattern={{major}}.{{minor}}
       - name: Build and push by digest
         id: build
-        uses: docker/build-push-action@v6.19.2
+        uses: docker/build-push-action@v7.0.0
         with:
           context: .
           file: ./Dockerfile
@@ -201,7 +201,7 @@ jobs:
           password: ${{ secrets.QUAY_ROBOT_TOKEN }}
       - name: Docker metadata
         id: docker-meta
-        uses: docker/metadata-action@v5.10.0
+        uses: docker/metadata-action@v6.0.0
         with:
           images: |
             ${{ env.REGISTRY }}/${{ needs.build-arch.outputs.repository }}

.pre-commit-config.yaml

@@ -50,7 +50,7 @@ repos:
           - 'prettier-plugin-organize-imports@4.3.0'
   # Python hooks
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.15.5
+    rev: v0.15.6
     hooks:
       - id: ruff-check
       - id: ruff-format

docker/compose/docker-compose.ci-test.yml

@@ -18,13 +18,13 @@ services:
       - "--log-level=warn"
       - "--log-format=text"
   tika:
-    image: docker.io/apache/tika:latest
+    image: docker.io/apache/tika:3.2.3.0
     hostname: tika
     container_name: tika
     network_mode: host
     restart: unless-stopped
   greenmail:
-    image: greenmail/standalone:2.1.8
+    image: docker.io/greenmail/standalone:2.1.8
     hostname: greenmail
     container_name: greenmail
     environment:

pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
   # WARNING: django does not use semver.
   #          Only patch versions are guaranteed to not introduce breaking changes.
   "django~=5.2.10",
-  "django-allauth[mfa,socialaccount]~=65.14.0",
+  "django-allauth[mfa,socialaccount]~=65.15.0",
   "django-auditlog~=3.4.1",
   "django-cachalot~=2.9.0",
   "django-celery-results~=2.6.0",
@@ -248,15 +248,13 @@ lint.per-file-ignores."docker/wait-for-redis.py" = [
 lint.per-file-ignores."src/documents/models.py" = [
   "SIM115",
 ]
-lint.per-file-ignores."src/paperless_tesseract/tests/test_parser.py" = [
-  "RUF001",
-]
+
 lint.isort.force-single-line = true
 
 [tool.codespell]
 write-changes = true
 ignore-words-list = "criterias,afterall,valeu,ureue,equest,ure,assertIn,Oktober,commitish"
-skip = "src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/documents/tests/samples/*,*.po,*.json"
+skip = "src-ui/src/locale/*,src-ui/pnpm-lock.yaml,src-ui/e2e/*,src/paperless_mail/tests/samples/*,src/paperless/tests/samples/mail/*,src/documents/tests/samples/*,*.po,*.json"
 
 [tool.pytest]
 minversion = "9.0"

src-ui/package.json

@@ -21,7 +21,7 @@
     "@angular/platform-browser-dynamic": "~21.2.4",
     "@angular/router": "~21.2.4",
     "@ng-bootstrap/ng-bootstrap": "^20.0.0",
-    "@ng-select/ng-select": "^21.4.1",
+    "@ng-select/ng-select": "^21.5.2",
     "@ngneat/dirty-check-forms": "^3.0.3",
     "@popperjs/core": "^2.11.8",
     "bootstrap": "^5.3.8",
@@ -55,13 +55,13 @@
     "@codecov/webpack-plugin": "^1.9.1",
     "@playwright/test": "^1.58.2",
     "@types/jest": "^30.0.0",
-    "@types/node": "^25.3.3",
-    "@typescript-eslint/eslint-plugin": "^8.54.0",
-    "@typescript-eslint/parser": "^8.54.0",
-    "@typescript-eslint/utils": "^8.54.0",
-    "eslint": "^10.0.2",
-    "jest": "30.2.0",
-    "jest-environment-jsdom": "^30.2.0",
+    "@types/node": "^25.4.0",
+    "@typescript-eslint/eslint-plugin": "^8.57.0",
+    "@typescript-eslint/parser": "^8.57.0",
+    "@typescript-eslint/utils": "^8.57.0",
+    "eslint": "^10.0.3",
+    "jest": "30.3.0",
+    "jest-environment-jsdom": "^30.3.0",
     "jest-junit": "^16.0.0",
     "jest-preset-angular": "^16.1.1",
     "jest-websocket-mock": "^2.5.0",

src/documents/consumer.py

@@ -51,8 +51,12 @@ 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 import ParserContext
+from paperless.parsers.mail import MailDocumentParser
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.tesseract import RasterisedDocumentParser
 from paperless.parsers.text import TextDocumentParser
-from paperless_mail.parsers import MailDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
 
@@ -67,7 +71,16 @@ def _parser_cleanup(parser: DocumentParser) -> None:
 
     TODO(stumpylog): Remove me in the future
     """
-    if isinstance(parser, TextDocumentParser):
+    if isinstance(
+        parser,
+        (
+            MailDocumentParser,
+            RasterisedDocumentParser,
+            RemoteDocumentParser,
+            TextDocumentParser,
+            TikaDocumentParser,
+        ),
+    ):
         parser.__exit__(None, None, None)
     else:
         parser.cleanup()
@@ -448,6 +461,23 @@ class ConsumerPlugin(
             progress_callback=progress_callback,
         )
 
+        parser_is_new_style = isinstance(
+            document_parser,
+            (
+                MailDocumentParser,
+                RasterisedDocumentParser,
+                RemoteDocumentParser,
+                TextDocumentParser,
+                TikaDocumentParser,
+            ),
+        )
+
+        # New-style parsers use __enter__/__exit__ for resource management.
+        # _parser_cleanup (below) handles __exit__; call __enter__ here.
+        # TODO(stumpylog): Remove me in the future
+        if parser_is_new_style:
+            document_parser.__enter__()
+
         self.log.debug(f"Parser: {type(document_parser).__name__}")
 
         # Parse the document. This may take some time.
@@ -466,17 +496,12 @@ class ConsumerPlugin(
                 ConsumerStatusShortMessage.PARSING_DOCUMENT,
             )
             self.log.debug(f"Parsing {self.filename}...")
-            if (
-                isinstance(document_parser, MailDocumentParser)
-                and self.input_doc.mailrule_id
-            ):
-                document_parser.parse(
-                    self.working_copy,
-                    mime_type,
-                    self.filename,
-                    self.input_doc.mailrule_id,
+
+            # TODO(stumpylog): Remove me in the future when all parsers use new protocol
+            if parser_is_new_style:
+                document_parser.configure(
+                    ParserContext(mailrule_id=self.input_doc.mailrule_id),
                 )
-            elif isinstance(document_parser, TextDocumentParser):
                 # TODO(stumpylog): Remove me in the future
                 document_parser.parse(self.working_copy, mime_type)
             else:
@@ -489,8 +514,8 @@ class ConsumerPlugin(
                 ProgressStatusOptions.WORKING,
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
-            if isinstance(document_parser, TextDocumentParser):
-                # TODO(stumpylog): Remove me in the future
+            # TODO(stumpylog): Remove me in the future when all parsers use new protocol
+            if parser_is_new_style:
                 thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
             else:
                 thumbnail = document_parser.get_thumbnail(

src/documents/management/commands/document_thumbnails.py

@@ -4,6 +4,11 @@ import shutil
 from documents.management.commands.base import PaperlessCommand
 from documents.models import Document
 from documents.parsers import get_parser_class_for_mime_type
+from paperless.parsers.mail import MailDocumentParser
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.tesseract import RasterisedDocumentParser
+from paperless.parsers.text import TextDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 
 logger = logging.getLogger("paperless.management.thumbnails")
 
@@ -22,16 +27,38 @@ def _process_document(doc_id: int) -> None:
 
     parser = parser_class(logging_group=None)
 
+    parser_is_new_style = isinstance(
+        parser,
+        (
+            MailDocumentParser,
+            RasterisedDocumentParser,
+            RemoteDocumentParser,
+            TextDocumentParser,
+            TikaDocumentParser,
+        ),
+    )
+
+    # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+    if parser_is_new_style:
+        parser.__enter__()
+
     try:
-        thumb = parser.get_thumbnail(
-            document.source_path,
-            document.mime_type,
-            document.get_public_filename(),
-        )
+        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+        if parser_is_new_style:
+            thumb = parser.get_thumbnail(document.source_path, document.mime_type)
+        else:
+            thumb = parser.get_thumbnail(
+                document.source_path,
+                document.mime_type,
+                document.get_public_filename(),
+            )
         shutil.move(thumb, document.thumbnail_path)
     finally:
         # TODO(stumpylog): Cleanup once all parsers are handled
-        parser.cleanup()
+        if parser_is_new_style:
+            parser.__exit__(None, None, None)
+        else:
+            parser.cleanup()
 
 
 class Command(PaperlessCommand):

src/documents/tasks.py

@@ -65,6 +65,12 @@ from documents.signals.handlers import run_workflows
 from documents.signals.handlers import send_websocket_document_updated
 from documents.workflows.utils import get_workflows_for_trigger
 from paperless.config import AIConfig
+from paperless.parsers import ParserContext
+from paperless.parsers.mail import MailDocumentParser
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.tesseract import RasterisedDocumentParser
+from paperless.parsers.text import TextDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 from paperless_ai.indexing import llm_index_add_or_update_document
 from paperless_ai.indexing import llm_index_remove_document
 from paperless_ai.indexing import update_llm_index
@@ -304,7 +310,9 @@ def update_document_content_maybe_archive_file(document_id) -> None:
 
     mime_type = document.mime_type
 
-    parser_class: type[DocumentParser] = get_parser_class_for_mime_type(mime_type)
+    parser_class: type[DocumentParser] | None = get_parser_class_for_mime_type(
+        mime_type,
+    )
 
     if not parser_class:
         logger.error(
@@ -315,14 +323,42 @@ def update_document_content_maybe_archive_file(document_id) -> None:
 
     parser: DocumentParser = parser_class(logging_group=uuid.uuid4())
 
-    try:
-        parser.parse(document.source_path, mime_type, document.get_public_filename())
+    parser_is_new_style = isinstance(
+        parser,
+        (
+            MailDocumentParser,
+            RasterisedDocumentParser,
+            RemoteDocumentParser,
+            TextDocumentParser,
+            TikaDocumentParser,
+        ),
+    )
 
-        thumbnail = parser.get_thumbnail(
-            document.source_path,
-            mime_type,
-            document.get_public_filename(),
-        )
+    # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+    if parser_is_new_style:
+        parser.__enter__()
+
+    try:
+        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+        if parser_is_new_style:
+            parser.configure(ParserContext())
+            parser.parse(document.source_path, mime_type)
+        else:
+            parser.parse(
+                document.source_path,
+                mime_type,
+                document.get_public_filename(),
+            )
+
+        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+        if parser_is_new_style:
+            thumbnail = parser.get_thumbnail(document.source_path, mime_type)
+        else:
+            thumbnail = parser.get_thumbnail(
+                document.source_path,
+                mime_type,
+                document.get_public_filename(),
+            )
 
         with transaction.atomic():
             oldDocument = Document.objects.get(pk=document.pk)
@@ -403,8 +439,20 @@ 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()
+        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
+        if isinstance(
+            parser,
+            (
+                MailDocumentParser,
+                RasterisedDocumentParser,
+                RemoteDocumentParser,
+                TextDocumentParser,
+                TikaDocumentParser,
+            ),
+        ):
+            parser.__exit__(None, None, None)
+        else:
+            parser.cleanup()
 
 
 @shared_task

src/documents/tests/test_api_status.py

@@ -101,13 +101,17 @@ class TestSystemStatus(APITestCase):
             - The response contains the correct install type
         """
         self.client.force_login(self.user)
-        os.environ["PNGX_CONTAINERIZED"] = "1"
-        response = self.client.get(self.ENDPOINT)
-        self.assertEqual(response.status_code, status.HTTP_200_OK)
-        self.assertEqual(response.data["install_type"], "docker")
-        os.environ["KUBERNETES_SERVICE_HOST"] = "http://localhost"
-        response = self.client.get(self.ENDPOINT)
-        self.assertEqual(response.data["install_type"], "kubernetes")
+        with mock.patch.dict(os.environ, {"PNGX_CONTAINERIZED": "1"}, clear=False):
+            response = self.client.get(self.ENDPOINT)
+            self.assertEqual(response.status_code, status.HTTP_200_OK)
+            self.assertEqual(response.data["install_type"], "docker")
+        with mock.patch.dict(
+            os.environ,
+            {"PNGX_CONTAINERIZED": "1", "KUBERNETES_SERVICE_HOST": "http://localhost"},
+            clear=False,
+        ):
+            response = self.client.get(self.ENDPOINT)
+            self.assertEqual(response.data["install_type"], "kubernetes")
 
     @mock.patch("redis.Redis.execute_command")
     def test_system_status_redis_ping(self, mock_ping) -> None:

src/documents/tests/test_consumer.py

@@ -36,7 +36,6 @@ from documents.tests.utils import DummyProgressManager
 from documents.tests.utils import FileSystemAssertsMixin
 from documents.tests.utils import GetConsumerMixin
 from paperless_mail.models import MailRule
-from paperless_mail.parsers import MailDocumentParser
 
 
 class _BaseTestParser(DocumentParser):
@@ -1091,7 +1090,7 @@ class TestConsumer(
             self.assertEqual(command[1], "--replace-input")
 
     @mock.patch("paperless_mail.models.MailRule.objects.get")
-    @mock.patch("paperless_mail.parsers.MailDocumentParser.parse")
+    @mock.patch("paperless.parsers.mail.MailDocumentParser.parse")
     @mock.patch("documents.parsers.document_consumer_declaration.send")
     def test_mail_parser_receives_mailrule(
         self,
@@ -1107,11 +1106,13 @@ class TestConsumer(
         THEN:
             - The mail parser should receive the mail rule
         """
+        from paperless_mail.signals import get_parser as mail_get_parser
+
         mock_consumer_declaration_send.return_value = [
             (
                 None,
                 {
-                    "parser": MailDocumentParser,
+                    "parser": mail_get_parser,
                     "mime_types": {"message/rfc822": ".eml"},
                     "weight": 0,
                 },
@@ -1123,9 +1124,10 @@ class TestConsumer(
         with self.get_consumer(
             filepath=(
                 Path(__file__).parent.parent.parent
-                / Path("paperless_mail")
+                / Path("paperless")
                 / Path("tests")
                 / Path("samples")
+                / Path("mail")
             ).resolve()
             / "html.eml",
             source=DocumentSource.MailFetch,
@@ -1136,12 +1138,10 @@ class TestConsumer(
                 ConsumerError,
             ):
                 consumer.run()
-                mock_mail_parser_parse.assert_called_once_with(
-                    consumer.working_copy,
-                    "message/rfc822",
-                    file_name="sample.pdf",
-                    mailrule=mock_mailrule_get.return_value,
-                )
+            mock_mail_parser_parse.assert_called_once_with(
+                consumer.working_copy,
+                "message/rfc822",
+            )
 
 
 @mock.patch("documents.consumer.magic.from_file", fake_magic_from_file)

src/documents/tests/test_parsers.py

@@ -9,9 +9,9 @@ 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.tesseract import RasterisedDocumentParser
 from paperless.parsers.text import TextDocumentParser
-from paperless_tesseract.parsers import RasterisedDocumentParser
-from paperless_tika.parsers import TikaDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 
 
 class TestParserDiscovery(TestCase):

src/documents/views.py

@@ -7,6 +7,7 @@ import tempfile
 import zipfile
 from collections import defaultdict
 from collections import deque
+from contextlib import nullcontext
 from datetime import datetime
 from pathlib import Path
 from time import mktime
@@ -225,6 +226,7 @@ from paperless.celery import app as celery_app
 from paperless.config import AIConfig
 from paperless.config import GeneralConfig
 from paperless.models import ApplicationConfiguration
+from paperless.parsers import ParserProtocol
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -1084,9 +1086,11 @@ class DocumentViewSet(
         parser_class = get_parser_class_for_mime_type(mime_type)
         if parser_class:
             parser = parser_class(progress_callback=None, logging_group=None)
+            cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
 
             try:
-                return parser.extract_metadata(file, mime_type)
+                with cm:
+                    return parser.extract_metadata(file, mime_type)
             except Exception:  # pragma: no cover
                 logger.exception(f"Issue getting metadata for {file}")
                 # TODO: cover GPG errors, remove later.

src/locale/en_US/LC_MESSAGES/django.po

@@ -2,7 +2,7 @@ msgid ""
 msgstr ""
 "Project-Id-Version: paperless-ngx\n"
 "Report-Msgid-Bugs-To: \n"
-"POT-Creation-Date: 2026-03-12 15:43+0000\n"
+"POT-Creation-Date: 2026-03-17 22:44+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1339,7 +1339,7 @@ msgstr ""
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2556 documents/views.py:3565
+#: documents/serialisers.py:2556 documents/views.py:3569
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1603,20 +1603,20 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:3577
+#: documents/views.py:3581
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:3620
+#: documents/views.py:3624
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:3677
+#: documents/views.py:3681
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:3687
+#: documents/views.py:3691
 msgid "The share link bundle is unavailable."
 msgstr ""
 

src/paperless/parsers/__init__.py

@@ -35,6 +35,7 @@ Usage example (third-party parser)::
 
 from __future__ import annotations
 
+from dataclasses import dataclass
 from typing import TYPE_CHECKING
 from typing import Protocol
 from typing import Self
@@ -48,6 +49,7 @@ if TYPE_CHECKING:
 
 __all__ = [
     "MetadataEntry",
+    "ParserContext",
     "ParserProtocol",
 ]
 
@@ -73,6 +75,44 @@ class MetadataEntry(TypedDict):
     """String representation of the field value."""
 
 
+@dataclass(frozen=True, slots=True)
+class ParserContext:
+    """Immutable context passed to a parser before parse().
+
+    The consumer assembles this from the ingestion event and Django
+    settings, then calls ``parser.configure(context)`` before
+    ``parser.parse()``.  Parsers read only the fields relevant to them;
+    unneeded fields are ignored.
+
+    ``frozen=True`` prevents accidental mutation after the consumer
+    hands the context off.  ``slots=True`` keeps instances lightweight.
+
+    Fields
+    ------
+    mailrule_id : int | None
+        Primary key of the ``MailRule`` that triggered this ingestion,
+        or ``None`` when the document did not arrive via a mail rule.
+        Used by ``MailDocumentParser`` to select the PDF layout.
+
+    Notes
+    -----
+    Future fields (not yet implemented):
+
+    * ``output_type`` — PDF/A variant for archive generation
+      (replaces ``settings.OCR_OUTPUT_TYPE`` reads inside parsers).
+    * ``ocr_mode`` — skip-text, redo, force, etc.
+      (replaces ``settings.OCR_MODE`` reads inside parsers).
+    * ``ocr_language`` — Tesseract language string.
+      (replaces ``settings.OCR_LANGUAGE`` reads inside parsers).
+
+    When those fields are added the consumer will read from Django
+    settings once and populate them here, decoupling parsers from
+    ``settings.*`` entirely.
+    """
+
+    mailrule_id: int | None = None
+
+
 @runtime_checkable
 class ParserProtocol(Protocol):
     """Structural contract for all Paperless-ngx document parsers.
@@ -191,6 +231,21 @@ class ParserProtocol(Protocol):
     # Core parsing interface
     # ------------------------------------------------------------------
 
+    def configure(self, context: ParserContext) -> None:
+        """Apply source context before parse().
+
+        Called by the consumer after instantiation and before parse().
+        The default implementation is a no-op; parsers override only the
+        fields they need.
+
+        Parameters
+        ----------
+        context:
+            Immutable context assembled by the consumer for this
+            specific ingestion event.
+        """
+        ...
+
     def parse(
         self,
         document_path: Path,

src/paperless/parsers/mail.py

@@ -0,0 +1,834 @@
+"""
+Built-in mail document parser.
+
+Handles message/rfc822 (EML) MIME type by:
+- Parsing the email using imap_tools
+- Generating a PDF via Gotenberg (for display and archive)
+- Extracting text via Tika for HTML content
+- Extracting metadata from email headers
+
+The parser always produces a PDF because EML files cannot be rendered
+natively in a browser (requires_pdf_rendition=True).
+"""
+
+from __future__ import annotations
+
+import logging
+import re
+import shutil
+import tempfile
+from html import escape
+from pathlib import Path
+from typing import TYPE_CHECKING
+from typing import Self
+
+from bleach import clean
+from bleach import linkify
+from django.conf import settings
+from django.utils import timezone
+from django.utils.timezone import is_naive
+from django.utils.timezone import make_aware
+from gotenberg_client import GotenbergClient
+from gotenberg_client.constants import A4
+from gotenberg_client.options import Measurement
+from gotenberg_client.options import MeasurementUnitType
+from gotenberg_client.options import PageMarginsType
+from gotenberg_client.options import PdfAFormat
+from humanize import naturalsize
+from imap_tools import MailAttachment
+from imap_tools import MailMessage
+from tika_client import TikaClient
+
+from documents.parsers import ParseError
+from documents.parsers import make_thumbnail_from_pdf
+from paperless.models import OutputTypeChoices
+from paperless.version import __full_version_str__
+from paperless_mail.models import MailRule
+
+if TYPE_CHECKING:
+    import datetime
+    from types import TracebackType
+
+    from paperless.parsers import MetadataEntry
+    from paperless.parsers import ParserContext
+
+logger = logging.getLogger("paperless.parsing.mail")
+
+_SUPPORTED_MIME_TYPES: dict[str, str] = {
+    "message/rfc822": ".eml",
+}
+
+
+class MailDocumentParser:
+    """Parse .eml email files for Paperless-ngx.
+
+    Uses imap_tools to parse .eml files, generates a PDF using Gotenberg,
+    and sends the HTML part to a Tika server for text extraction.  Because
+    EML files cannot be rendered natively in a browser, the parser always
+    produces a PDF rendition (requires_pdf_rendition=True).
+
+    Pass a ``ParserContext`` to ``configure()`` before ``parse()`` to
+    apply mail-rule-specific PDF layout options:
+
+        parser.configure(ParserContext(mailrule_id=rule.pk))
+        parser.parse(path, mime_type)
+
+    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 Mail 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 mail parser produces a display PDF
+            (requires_pdf_rendition=True), not an optional OCR 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 True — EML files cannot be rendered natively in a browser,
+            so a PDF conversion is always required for display.
+        """
+        return True
+
+    # ------------------------------------------------------------------
+    # 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
+        self._date: datetime.datetime | None = None
+        self._archive_path: Path | None = None
+        self._mailrule_id: int | 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 configure(self, context: ParserContext) -> None:
+        self._mailrule_id = context.mailrule_id
+
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
+        """Parse the given .eml into formatted text and a PDF archive.
+
+        Call ``configure(ParserContext(mailrule_id=...))`` before this method
+        to apply mail-rule-specific PDF layout options.  The ``produce_archive``
+        flag is accepted for protocol compatibility but is always honoured —
+        the mail parser always produces a PDF since EML files cannot be
+        displayed natively.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the .eml file.
+        mime_type:
+            Detected MIME type of the document (should be "message/rfc822").
+        produce_archive:
+            Accepted for protocol compatibility. The PDF rendition is always
+            produced since EML files cannot be displayed natively in a browser.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If the file cannot be parsed or PDF generation fails.
+        """
+
+        def strip_text(text: str) -> str:
+            """Reduces the spacing of the given text string."""
+            text = re.sub(r"\s+", " ", text)
+            text = re.sub(r"(\n *)+", "\n", text)
+            return text.strip()
+
+        def build_formatted_text(mail_message: MailMessage) -> str:
+            """Constructs a formatted string based on the given email."""
+            fmt_text = f"Subject: {mail_message.subject}\n\n"
+            fmt_text += f"From: {mail_message.from_values.full if mail_message.from_values else ''}\n\n"
+            to_list = [address.full for address in mail_message.to_values]
+            fmt_text += f"To: {', '.join(to_list)}\n\n"
+            if mail_message.cc_values:
+                fmt_text += (
+                    f"CC: {', '.join(address.full for address in mail.cc_values)}\n\n"
+                )
+            if mail_message.bcc_values:
+                fmt_text += (
+                    f"BCC: {', '.join(address.full for address in mail.bcc_values)}\n\n"
+                )
+            if mail_message.attachments:
+                att = []
+                for a in mail.attachments:
+                    attachment_size = naturalsize(a.size, binary=True, format="%.2f")
+                    att.append(
+                        f"{a.filename} ({attachment_size})",
+                    )
+                fmt_text += f"Attachments: {', '.join(att)}\n\n"
+
+            if mail.html:
+                fmt_text += "HTML content: " + strip_text(self.tika_parse(mail.html))
+
+            fmt_text += f"\n\n{strip_text(mail.text)}"
+
+            return fmt_text
+
+        logger.debug("Parsing file %s into an email", document_path.name)
+        mail = self.parse_file_to_message(document_path)
+
+        logger.debug("Building formatted text from email")
+        self._text = build_formatted_text(mail)
+
+        if is_naive(mail.date):
+            self._date = make_aware(mail.date)
+        else:
+            self._date = mail.date
+
+        logger.debug("Creating a PDF from the email")
+        if self._mailrule_id:
+            rule = MailRule.objects.get(pk=self._mailrule_id)
+            self._archive_path = self.generate_pdf(
+                mail,
+                MailRule.PdfLayout(rule.pdf_layout),
+            )
+        else:
+            self._archive_path = self.generate_pdf(mail)
+
+    # ------------------------------------------------------------------
+    # 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
+            Date from the email headers, or None if not detected.
+        """
+        return self._date
+
+    def get_archive_path(self) -> Path | None:
+        """Return the path to the generated archive PDF, or None.
+
+        Returns
+        -------
+        Path | None
+            Path to the PDF produced by Gotenberg, or None if parse has not
+            been called yet.
+        """
+        return self._archive_path
+
+    # ------------------------------------------------------------------
+    # Thumbnail and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(
+        self,
+        document_path: Path,
+        mime_type: str,
+        file_name: str | None = None,
+    ) -> Path:
+        """Generate a thumbnail from the PDF rendition of the email.
+
+        Converts the document to PDF first if not already done.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+        mime_type:
+            Detected MIME type of the document.
+        file_name:
+            Kept for backward compatibility; not used.
+
+        Returns
+        -------
+        Path
+            Path to the generated WebP thumbnail inside the temporary directory.
+        """
+        if not self._archive_path:
+            self._archive_path = self.generate_pdf(
+                self.parse_file_to_message(document_path),
+            )
+
+        return make_thumbnail_from_pdf(
+            self._archive_path,
+            self._tempdir,
+        )
+
+    def get_page_count(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> int | None:
+        """Return the number of pages in the document.
+
+        Counts pages in the archive PDF produced by a preceding parse()
+        call.  Returns ``None`` if parse() has not been called yet or if
+        no archive was produced.
+
+        Returns
+        -------
+        int | None
+            Page count of the archive PDF, or ``None``.
+        """
+        if self._archive_path is not None:
+            from paperless.parsers.utils import get_page_count_for_pdf
+
+            return get_page_count_for_pdf(self._archive_path, log=logger)
+        return None
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        """Extract metadata from the email headers.
+
+        Returns email headers as metadata entries with prefix "header",
+        plus summary entries for attachments and date.
+
+        Returns
+        -------
+        list[MetadataEntry]
+            Sorted list of metadata entries, or ``[]`` on parse failure.
+        """
+        result: list[MetadataEntry] = []
+
+        try:
+            mail = self.parse_file_to_message(document_path)
+        except ParseError as e:
+            logger.warning(
+                "Error while fetching document metadata for %s: %s",
+                document_path,
+                e,
+            )
+            return result
+
+        for key, header_values in mail.headers.items():
+            value = ", ".join(header_values)
+            try:
+                value.encode("utf-8")
+            except UnicodeEncodeError as e:  # pragma: no cover
+                logger.debug("Skipping header %s: %s", key, e)
+                continue
+
+            result.append(
+                {
+                    "namespace": "",
+                    "prefix": "header",
+                    "key": key,
+                    "value": value,
+                },
+            )
+
+        result.append(
+            {
+                "namespace": "",
+                "prefix": "",
+                "key": "attachments",
+                "value": ", ".join(
+                    f"{attachment.filename}"
+                    f"({naturalsize(attachment.size, binary=True, format='%.2f')})"
+                    for attachment in mail.attachments
+                ),
+            },
+        )
+
+        result.append(
+            {
+                "namespace": "",
+                "prefix": "",
+                "key": "date",
+                "value": mail.date.strftime("%Y-%m-%d %H:%M:%S %Z"),
+            },
+        )
+
+        result.sort(key=lambda item: (item["prefix"], item["key"]))
+        return result
+
+    # ------------------------------------------------------------------
+    # Email-specific methods
+    # ------------------------------------------------------------------
+
+    def _settings_to_gotenberg_pdfa(self) -> PdfAFormat | None:
+        """Convert the OCR output type setting to a Gotenberg PdfAFormat."""
+        if settings.OCR_OUTPUT_TYPE in {
+            OutputTypeChoices.PDF_A,
+            OutputTypeChoices.PDF_A2,
+        }:
+            return PdfAFormat.A2b
+        elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:  # pragma: no cover
+            logger.warning(
+                "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
+            )
+            return PdfAFormat.A2b
+        elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:  # pragma: no cover
+            return PdfAFormat.A3b
+        return None
+
+    @staticmethod
+    def parse_file_to_message(filepath: Path) -> MailMessage:
+        """Parse the given .eml file into a MailMessage object.
+
+        Parameters
+        ----------
+        filepath:
+            Path to the .eml file.
+
+        Returns
+        -------
+        MailMessage
+            Parsed mail message.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If the file cannot be parsed or is missing required fields.
+        """
+        try:
+            with filepath.open("rb") as eml:
+                parsed = MailMessage.from_bytes(eml.read())
+                if parsed.from_values is None:
+                    raise ParseError(
+                        f"Could not parse {filepath}: Missing 'from'",
+                    )
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse {filepath}: {err}",
+            ) from err
+
+        return parsed
+
+    def tika_parse(self, html: str) -> str:
+        """Send HTML content to the Tika server for text extraction.
+
+        Parameters
+        ----------
+        html:
+            HTML string to parse.
+
+        Returns
+        -------
+        str
+            Extracted plain text.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If the Tika server cannot be reached or returns an error.
+        """
+        logger.info("Sending content to Tika server")
+
+        try:
+            with TikaClient(tika_url=settings.TIKA_ENDPOINT) as client:
+                parsed = client.tika.as_text.from_buffer(html, "text/html")
+
+                if parsed.content is not None:
+                    return parsed.content.strip()
+                return ""
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse content with tika server at "
+                f"{settings.TIKA_ENDPOINT}: {err}",
+            ) from err
+
+    def generate_pdf(
+        self,
+        mail_message: MailMessage,
+        pdf_layout: MailRule.PdfLayout | None = None,
+    ) -> Path:
+        """Generate a PDF from the email message.
+
+        Creates separate PDFs for the email body and HTML content, then
+        merges them according to the requested layout.
+
+        Parameters
+        ----------
+        mail_message:
+            Parsed email message.
+        pdf_layout:
+            Layout option for the PDF. Falls back to the
+            EMAIL_PARSE_DEFAULT_LAYOUT setting if not provided.
+
+        Returns
+        -------
+        Path
+            Path to the generated PDF inside the temporary directory.
+        """
+        archive_path = Path(self._tempdir) / "merged.pdf"
+
+        mail_pdf_file = self.generate_pdf_from_mail(mail_message)
+
+        if pdf_layout is None:
+            pdf_layout = MailRule.PdfLayout(settings.EMAIL_PARSE_DEFAULT_LAYOUT)
+
+        # If no HTML content, create the PDF from the message.
+        # Otherwise, create 2 PDFs and merge them with Gotenberg.
+        if not mail_message.html:
+            archive_path.write_bytes(mail_pdf_file.read_bytes())
+        else:
+            pdf_of_html_content = self.generate_pdf_from_html(
+                mail_message.html,
+                mail_message.attachments,
+            )
+
+            logger.debug("Merging email text and HTML content into single PDF")
+
+            with (
+                GotenbergClient(
+                    host=settings.TIKA_GOTENBERG_ENDPOINT,
+                    timeout=settings.CELERY_TASK_TIME_LIMIT,
+                ) as client,
+                client.merge.merge() as route,
+            ):
+                # Configure requested PDF/A formatting, if any
+                pdf_a_format = self._settings_to_gotenberg_pdfa()
+                if pdf_a_format is not None:
+                    route.pdf_format(pdf_a_format)
+
+                match pdf_layout:
+                    case MailRule.PdfLayout.HTML_TEXT:
+                        route.merge([pdf_of_html_content, mail_pdf_file])
+                    case MailRule.PdfLayout.HTML_ONLY:
+                        route.merge([pdf_of_html_content])
+                    case MailRule.PdfLayout.TEXT_ONLY:
+                        route.merge([mail_pdf_file])
+                    case MailRule.PdfLayout.TEXT_HTML | _:
+                        route.merge([mail_pdf_file, pdf_of_html_content])
+
+                try:
+                    response = route.run()
+                    archive_path.write_bytes(response.content)
+                except Exception as err:
+                    raise ParseError(
+                        f"Error while merging email HTML into PDF: {err}",
+                    ) from err
+
+        return archive_path
+
+    def mail_to_html(self, mail: MailMessage) -> Path:
+        """Convert the given email into an HTML file using a template.
+
+        Parameters
+        ----------
+        mail:
+            Parsed mail message.
+
+        Returns
+        -------
+        Path
+            Path to the rendered HTML file inside the temporary directory.
+        """
+
+        def clean_html(text: str) -> str:
+            """Attempt to clean, escape, and linkify the given HTML string."""
+            if isinstance(text, list):
+                text = "\n".join([str(e) for e in text])
+            if not isinstance(text, str):
+                text = str(text)
+            text = escape(text)
+            text = clean(text)
+            text = linkify(text, parse_email=True)
+            text = text.replace("\n", "<br>")
+            return text
+
+        data = {}
+
+        data["subject"] = clean_html(mail.subject)
+        if data["subject"]:
+            data["subject_label"] = "Subject"
+        data["from"] = clean_html(mail.from_values.full if mail.from_values else "")
+        if data["from"]:
+            data["from_label"] = "From"
+        data["to"] = clean_html(", ".join(address.full for address in mail.to_values))
+        if data["to"]:
+            data["to_label"] = "To"
+        data["cc"] = clean_html(", ".join(address.full for address in mail.cc_values))
+        if data["cc"]:
+            data["cc_label"] = "CC"
+        data["bcc"] = clean_html(", ".join(address.full for address in mail.bcc_values))
+        if data["bcc"]:
+            data["bcc_label"] = "BCC"
+
+        att = []
+        for a in mail.attachments:
+            att.append(
+                f"{a.filename} ({naturalsize(a.size, binary=True, format='%.2f')})",
+            )
+        data["attachments"] = clean_html(", ".join(att))
+        if data["attachments"]:
+            data["attachments_label"] = "Attachments"
+
+        data["date"] = clean_html(
+            timezone.localtime(mail.date).strftime("%Y-%m-%d %H:%M"),
+        )
+        data["content"] = clean_html(mail.text.strip())
+
+        from django.template.loader import render_to_string
+
+        html_file = Path(self._tempdir) / "email_as_html.html"
+        html_file.write_text(render_to_string("email_msg_template.html", context=data))
+
+        return html_file
+
+    def generate_pdf_from_mail(self, mail: MailMessage) -> Path:
+        """Create a PDF from the email body using an HTML template and Gotenberg.
+
+        Parameters
+        ----------
+        mail:
+            Parsed mail message.
+
+        Returns
+        -------
+        Path
+            Path to the generated PDF inside the temporary directory.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If Gotenberg returns an error.
+        """
+        logger.info("Converting mail to PDF")
+
+        css_file = (
+            Path(__file__).parent.parent.parent
+            / "paperless_mail"
+            / "templates"
+            / "output.css"
+        )
+        email_html_file = self.mail_to_html(mail)
+
+        with (
+            GotenbergClient(
+                host=settings.TIKA_GOTENBERG_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client,
+            client.chromium.html_to_pdf() as route,
+        ):
+            # Configure requested PDF/A formatting, if any
+            pdf_a_format = self._settings_to_gotenberg_pdfa()
+            if pdf_a_format is not None:
+                route.pdf_format(pdf_a_format)
+
+            try:
+                response = (
+                    route.index(email_html_file)
+                    .resource(css_file)
+                    .margins(
+                        PageMarginsType(
+                            top=Measurement(0.1, MeasurementUnitType.Inches),
+                            bottom=Measurement(0.1, MeasurementUnitType.Inches),
+                            left=Measurement(0.1, MeasurementUnitType.Inches),
+                            right=Measurement(0.1, MeasurementUnitType.Inches),
+                        ),
+                    )
+                    .size(A4)
+                    .scale(1.0)
+                    .run()
+                )
+            except Exception as err:
+                raise ParseError(
+                    f"Error while converting email to PDF: {err}",
+                ) from err
+
+        email_as_pdf_file = Path(self._tempdir) / "email_as_pdf.pdf"
+        email_as_pdf_file.write_bytes(response.content)
+
+        return email_as_pdf_file
+
+    def generate_pdf_from_html(
+        self,
+        orig_html: str,
+        attachments: list[MailAttachment],
+    ) -> Path:
+        """Generate a PDF from the HTML content of the email.
+
+        Parameters
+        ----------
+        orig_html:
+            Raw HTML string from the email body.
+        attachments:
+            List of email attachments (used as inline resources).
+
+        Returns
+        -------
+        Path
+            Path to the generated PDF inside the temporary directory.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If Gotenberg returns an error.
+        """
+
+        def clean_html_script(text: str) -> str:
+            compiled_open = re.compile(re.escape("<script"), re.IGNORECASE)
+            text = compiled_open.sub("<div hidden ", text)
+
+            compiled_close = re.compile(re.escape("</script"), re.IGNORECASE)
+            text = compiled_close.sub("</div", text)
+            return text
+
+        logger.info("Converting message html to PDF")
+
+        tempdir = Path(self._tempdir)
+
+        html_clean = clean_html_script(orig_html)
+        html_clean_file = tempdir / "index.html"
+        html_clean_file.write_text(html_clean)
+
+        with (
+            GotenbergClient(
+                host=settings.TIKA_GOTENBERG_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ) as client,
+            client.chromium.html_to_pdf() as route,
+        ):
+            # Configure requested PDF/A formatting, if any
+            pdf_a_format = self._settings_to_gotenberg_pdfa()
+            if pdf_a_format is not None:
+                route.pdf_format(pdf_a_format)
+
+            # Add attachments as resources, cleaning the filename and replacing
+            # it in the index file for inclusion
+            for attachment in attachments:
+                # Clean the attachment name to be valid
+                name_cid = f"cid:{attachment.content_id}"
+                name_clean = "".join(e for e in name_cid if e.isalnum())
+
+                # Write attachment payload to a temp file
+                temp_file = tempdir / name_clean
+                temp_file.write_bytes(attachment.payload)
+
+                route.resource(temp_file)
+
+                # Replace as needed the name with the clean name
+                html_clean = html_clean.replace(name_cid, name_clean)
+
+            # Now store the cleaned up HTML version
+            html_clean_file = tempdir / "index.html"
+            html_clean_file.write_text(html_clean)
+            # This is our index file, the main page basically
+            route.index(html_clean_file)
+
+            # Set page size, margins
+            route.margins(
+                PageMarginsType(
+                    top=Measurement(0.1, MeasurementUnitType.Inches),
+                    bottom=Measurement(0.1, MeasurementUnitType.Inches),
+                    left=Measurement(0.1, MeasurementUnitType.Inches),
+                    right=Measurement(0.1, MeasurementUnitType.Inches),
+                ),
+            ).size(A4).scale(1.0)
+
+            try:
+                response = route.run()
+
+            except Exception as err:
+                raise ParseError(
+                    f"Error while converting document to PDF: {err}",
+                ) from err
+
+        html_pdf = tempdir / "html.pdf"
+        html_pdf.write_bytes(response.content)
+        return html_pdf

src/paperless/parsers/registry.py

@@ -193,9 +193,17 @@ class ParserRegistry:
         that log output is predictable; scoring determines which parser wins
         at runtime regardless of registration order.
         """
+        from paperless.parsers.mail import MailDocumentParser
+        from paperless.parsers.remote import RemoteDocumentParser
+        from paperless.parsers.tesseract import RasterisedDocumentParser
         from paperless.parsers.text import TextDocumentParser
+        from paperless.parsers.tika import TikaDocumentParser
 
         self.register_builtin(TextDocumentParser)
+        self.register_builtin(RemoteDocumentParser)
+        self.register_builtin(TikaDocumentParser)
+        self.register_builtin(MailDocumentParser)
+        self.register_builtin(RasterisedDocumentParser)
 
     # ------------------------------------------------------------------
     # Discovery

src/paperless/parsers/remote.py

@@ -0,0 +1,433 @@
+"""
+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
+    from paperless.parsers import ParserContext
+
+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 configure(self, context: ParserContext) -> None:
+        pass
+
+    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/tesseract.py

@@ -1,13 +1,18 @@
+from __future__ import annotations
+
+import logging
 import os
 import re
+import shutil
 import tempfile
 from pathlib import Path
 from typing import TYPE_CHECKING
+from typing import Any
+from typing import Self
 
 from django.conf import settings
 from PIL import Image
 
-from documents.parsers import DocumentParser
 from documents.parsers import ParseError
 from documents.parsers import make_thumbnail_from_pdf
 from documents.utils import maybe_override_pixel_limit
@@ -16,6 +21,28 @@ from paperless.config import OcrConfig
 from paperless.models import ArchiveFileChoices
 from paperless.models import CleanChoices
 from paperless.models import ModeChoices
+from paperless.parsers.utils import read_file_handle_unicode_errors
+from paperless.version import __full_version_str__
+
+if TYPE_CHECKING:
+    import datetime
+    from types import TracebackType
+
+    from paperless.parsers import MetadataEntry
+    from paperless.parsers import ParserContext
+
+logger = logging.getLogger("paperless.parsing.tesseract")
+
+_SUPPORTED_MIME_TYPES: dict[str, str] = {
+    "application/pdf": ".pdf",
+    "image/jpeg": ".jpg",
+    "image/png": ".png",
+    "image/tiff": ".tif",
+    "image/gif": ".gif",
+    "image/bmp": ".bmp",
+    "image/webp": ".webp",
+    "image/heic": ".heic",
+}
 
 
 class NoTextFoundException(Exception):
@@ -26,81 +53,125 @@ class RtlLanguageException(Exception):
     pass
 
 
-class RasterisedDocumentParser(DocumentParser):
+class RasterisedDocumentParser:
     """
     This parser uses Tesseract to try and get some text out of a rasterised
     image, whether it's a PDF, or other graphical format (JPEG, TIFF, etc.)
     """
 
-    logging_name = "paperless.parsing.tesseract"
+    name: str = "Paperless-ngx Tesseract OCR Parser"
+    version: str = __full_version_str__
+    author: str = "Paperless-ngx Contributors"
+    url: str = "https://github.com/paperless-ngx/paperless-ngx"
 
-    def get_settings(self) -> OcrConfig:
-        """
-        This parser uses the OCR configuration settings to parse documents
-        """
-        return OcrConfig()
+    # ------------------------------------------------------------------
+    # Class methods
+    # ------------------------------------------------------------------
 
-    def get_page_count(self, document_path, mime_type):
-        page_count = None
-        if mime_type == "application/pdf":
-            try:
-                import pikepdf
+    @classmethod
+    def supported_mime_types(cls) -> dict[str, str]:
+        return _SUPPORTED_MIME_TYPES
 
-                with pikepdf.Pdf.open(document_path) as pdf:
-                    page_count = len(pdf.pages)
-            except Exception as e:
-                self.log.warning(
-                    f"Unable to determine PDF page count {document_path}: {e}",
-                )
-        return page_count
+    @classmethod
+    def score(
+        cls,
+        mime_type: str,
+        filename: str,
+        path: Path | None = None,
+    ) -> int | None:
+        if mime_type in _SUPPORTED_MIME_TYPES:
+            return 10
+        return None
 
-    def extract_metadata(self, document_path, mime_type):
-        result = []
-        if mime_type == "application/pdf":
-            import pikepdf
+    # ------------------------------------------------------------------
+    # Properties
+    # ------------------------------------------------------------------
 
-            namespace_pattern = re.compile(r"\{(.*)\}(.*)")
+    @property
+    def can_produce_archive(self) -> bool:
+        return True
 
-            pdf = pikepdf.open(document_path)
-            meta = pdf.open_metadata()
-            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:  # pragma: no cover
-                        continue
-                    namespace = m.group(1)
-                    key_value = m.group(2)
-                    try:
-                        namespace.encode("utf-8")
-                        key_value.encode("utf-8")
-                    except UnicodeEncodeError as e:  # pragma: no cover
-                        self.log.debug(f"Skipping metadata key {key}: {e}")
-                        continue
-                    result.append(
-                        {
-                            "namespace": namespace,
-                            "prefix": meta.REVERSE_NS[namespace],
-                            "key": key_value,
-                            "value": value,
-                        },
-                    )
-                except Exception as e:
-                    self.log.warning(
-                        f"Error while reading metadata {key}: {value}. Error: {e}",
-                    )
-        return result
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        return False
 
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
+    # ------------------------------------------------------------------
+    # 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.settings = OcrConfig()
+        self.archive_path: Path | None = None
+        self.text: str | None = None
+        self.date: datetime.datetime | None = None
+        self.log = logger
+
+    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 configure(self, context: ParserContext) -> None:
+        pass
+
+    # ------------------------------------------------------------------
+    # Result accessors
+    # ------------------------------------------------------------------
+
+    def get_text(self) -> str | None:
+        return self.text
+
+    def get_date(self) -> datetime.datetime | None:
+        return self.date
+
+    def get_archive_path(self) -> Path | None:
+        return self.archive_path
+
+    # ------------------------------------------------------------------
+    # Thumbnail, page count, and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
         return make_thumbnail_from_pdf(
-            self.archive_path or document_path,
+            self.archive_path or Path(document_path),
             self.tempdir,
-            self.logging_group,
         )
 
-    def is_image(self, mime_type) -> bool:
+    def get_page_count(self, document_path: Path, mime_type: str) -> int | None:
+        if mime_type == "application/pdf":
+            from paperless.parsers.utils import get_page_count_for_pdf
+
+            return get_page_count_for_pdf(Path(document_path), log=self.log)
+        return None
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        if mime_type != "application/pdf":
+            return []
+
+        from paperless.parsers.utils import extract_pdf_metadata
+
+        return extract_pdf_metadata(Path(document_path), log=self.log)
+
+    def is_image(self, mime_type: str) -> bool:
         return mime_type in [
             "image/png",
             "image/jpeg",
@@ -111,25 +182,25 @@ class RasterisedDocumentParser(DocumentParser):
             "image/heic",
         ]
 
-    def has_alpha(self, image) -> bool:
+    def has_alpha(self, image: Path) -> bool:
         with Image.open(image) as im:
             return im.mode in ("RGBA", "LA")
 
-    def remove_alpha(self, image_path: str) -> Path:
+    def remove_alpha(self, image_path: Path) -> Path:
         no_alpha_image = Path(self.tempdir) / "image-no-alpha"
         run_subprocess(
             [
                 settings.CONVERT_BINARY,
                 "-alpha",
                 "off",
-                image_path,
-                no_alpha_image,
+                str(image_path),
+                str(no_alpha_image),
             ],
             logger=self.log,
         )
         return no_alpha_image
 
-    def get_dpi(self, image) -> int | None:
+    def get_dpi(self, image: Path) -> int | None:
         try:
             with Image.open(image) as im:
                 x, _ = im.info["dpi"]
@@ -138,7 +209,7 @@ class RasterisedDocumentParser(DocumentParser):
             self.log.warning(f"Error while getting DPI from image {image}: {e}")
             return None
 
-    def calculate_a4_dpi(self, image) -> int | None:
+    def calculate_a4_dpi(self, image: Path) -> int | None:
         try:
             with Image.open(image) as im:
                 width, _ = im.size
@@ -156,6 +227,7 @@ class RasterisedDocumentParser(DocumentParser):
         sidecar_file: Path | None,
         pdf_file: Path,
     ) -> str | None:
+        text: str | None = None
         # When re-doing OCR, the sidecar contains ONLY the new text, not
         # the whole text, so do not utilize it in that case
         if (
@@ -163,7 +235,7 @@ class RasterisedDocumentParser(DocumentParser):
             and sidecar_file.is_file()
             and self.settings.mode != "redo"
         ):
-            text = self.read_file_handle_unicode_errors(sidecar_file)
+            text = read_file_handle_unicode_errors(sidecar_file)
 
             if "[OCR skipped on page" not in text:
                 # This happens when there's already text in the input file.
@@ -191,12 +263,12 @@ class RasterisedDocumentParser(DocumentParser):
                         "-layout",
                         "-enc",
                         "UTF-8",
-                        pdf_file,
+                        str(pdf_file),
                         tmp.name,
                     ],
                     logger=self.log,
                 )
-                text = self.read_file_handle_unicode_errors(Path(tmp.name))
+                text = read_file_handle_unicode_errors(Path(tmp.name))
 
             return post_process_text(text)
 
@@ -211,16 +283,14 @@ class RasterisedDocumentParser(DocumentParser):
 
     def construct_ocrmypdf_parameters(
         self,
-        input_file,
-        mime_type,
-        output_file,
-        sidecar_file,
+        input_file: Path,
+        mime_type: str,
+        output_file: Path,
+        sidecar_file: Path,
         *,
-        safe_fallback=False,
-    ):
-        if TYPE_CHECKING:
-            assert isinstance(self.settings, OcrConfig)
-        ocrmypdf_args = {
+        safe_fallback: bool = False,
+    ) -> dict[str, Any]:
+        ocrmypdf_args: dict[str, Any] = {
             "input_file_or_options": input_file,
             "output_file": output_file,
             # need to use threads, since this will be run in daemonized
@@ -330,7 +400,13 @@ class RasterisedDocumentParser(DocumentParser):
 
         return ocrmypdf_args
 
-    def parse(self, document_path: Path, mime_type, file_name=None) -> None:
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
         # This forces tesseract to use one core per page.
         os.environ["OMP_THREAD_LIMIT"] = "1"
         VALID_TEXT_LENGTH = 50
@@ -458,7 +534,7 @@ class RasterisedDocumentParser(DocumentParser):
                 self.text = ""
 
 
-def post_process_text(text):
+def post_process_text(text: str | None) -> str | None:
     if not text:
         return None
 

src/paperless/parsers/text.py

@@ -27,6 +27,7 @@ if TYPE_CHECKING:
     from types import TracebackType
 
     from paperless.parsers import MetadataEntry
+    from paperless.parsers import ParserContext
 
 logger = logging.getLogger("paperless.parsing.text")
 
@@ -156,6 +157,9 @@ class TextDocumentParser:
     # Core parsing interface
     # ------------------------------------------------------------------
 
+    def configure(self, context: ParserContext) -> None:
+        pass
+
     def parse(
         self,
         document_path: Path,

src/paperless/parsers/tika.py

@@ -0,0 +1,452 @@
+"""
+Built-in Tika document parser.
+
+Handles Office documents (DOCX, ODT, XLS, XLSX, PPT, PPTX, RTF, etc.) by
+sending them to an Apache Tika server for text extraction and a Gotenberg
+server for PDF conversion.  Because the source formats cannot be rendered by
+a browser natively, the parser always produces a PDF rendition for display.
+"""
+
+from __future__ import annotations
+
+import logging
+import shutil
+import tempfile
+from contextlib import ExitStack
+from pathlib import Path
+from typing import TYPE_CHECKING
+from typing import Self
+
+import httpx
+from django.conf import settings
+from django.utils import timezone
+from gotenberg_client import GotenbergClient
+from gotenberg_client.options import PdfAFormat
+from tika_client import TikaClient
+
+from documents.parsers import ParseError
+from documents.parsers import make_thumbnail_from_pdf
+from paperless.config import OutputTypeConfig
+from paperless.models import OutputTypeChoices
+from paperless.version import __full_version_str__
+
+if TYPE_CHECKING:
+    import datetime
+    from types import TracebackType
+
+    from paperless.parsers import MetadataEntry
+    from paperless.parsers import ParserContext
+
+logger = logging.getLogger("paperless.parsing.tika")
+
+_SUPPORTED_MIME_TYPES: dict[str, str] = {
+    "application/msword": ".doc",
+    "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
+    "application/vnd.ms-excel": ".xls",
+    "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+    "application/vnd.ms-powerpoint": ".ppt",
+    "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
+    "application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
+    "application/vnd.oasis.opendocument.presentation": ".odp",
+    "application/vnd.oasis.opendocument.spreadsheet": ".ods",
+    "application/vnd.oasis.opendocument.text": ".odt",
+    "application/vnd.oasis.opendocument.graphics": ".odg",
+    "text/rtf": ".rtf",
+}
+
+
+class TikaDocumentParser:
+    """Parse Office documents via Apache Tika and Gotenberg for Paperless-ngx.
+
+    Text extraction is handled by the Tika server.  PDF conversion for display
+    is handled by Gotenberg (LibreOffice route).  Because the source formats
+    cannot be rendered by a browser natively, ``requires_pdf_rendition`` is
+    True and the PDF is always produced regardless of the ``produce_archive``
+    flag passed to ``parse``.
+
+    Both ``TikaClient`` and ``GotenbergClient`` are opened once in
+    ``__enter__`` via an ``ExitStack`` and shared across ``parse``,
+    ``extract_metadata``, and ``_convert_to_pdf`` calls, then closed via
+    ``ExitStack.close()`` in ``__exit__``.  The parser must always be used
+    as a context manager.
+
+    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 Tika 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.
+
+        Returns ``None`` when Tika integration is disabled so the registry
+        skips this parser entirely.
+
+        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 TIKA_ENABLED and the MIME type is supported, otherwise None.
+        """
+        if not settings.TIKA_ENABLED:
+            return 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 — Tika produces a display PDF, not an OCR 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 True — Office formats cannot be rendered natively in a
+            browser, so a PDF conversion is always required for display.
+        """
+        return True
+
+    # ------------------------------------------------------------------
+    # 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
+        self._date: datetime.datetime | None = None
+        self._archive_path: Path | None = None
+        self._exit_stack = ExitStack()
+        self._tika_client: TikaClient | None = None
+        self._gotenberg_client: GotenbergClient | None = None
+
+    def __enter__(self) -> Self:
+        self._tika_client = self._exit_stack.enter_context(
+            TikaClient(
+                tika_url=settings.TIKA_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ),
+        )
+        self._gotenberg_client = self._exit_stack.enter_context(
+            GotenbergClient(
+                host=settings.TIKA_GOTENBERG_ENDPOINT,
+                timeout=settings.CELERY_TASK_TIME_LIMIT,
+            ),
+        )
+        return self
+
+    def __exit__(
+        self,
+        exc_type: type[BaseException] | None,
+        exc_val: BaseException | None,
+        exc_tb: TracebackType | None,
+    ) -> None:
+        self._exit_stack.close()
+        logger.debug("Cleaning up temporary directory %s", self._tempdir)
+        shutil.rmtree(self._tempdir, ignore_errors=True)
+
+    # ------------------------------------------------------------------
+    # Core parsing interface
+    # ------------------------------------------------------------------
+
+    def configure(self, context: ParserContext) -> None:
+        pass
+
+    def parse(
+        self,
+        document_path: Path,
+        mime_type: str,
+        *,
+        produce_archive: bool = True,
+    ) -> None:
+        """Send the document to Tika for text extraction and Gotenberg for PDF.
+
+        Because ``requires_pdf_rendition`` is True the PDF conversion is
+        always performed — the ``produce_archive`` flag is intentionally
+        ignored.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the document file to parse.
+        mime_type:
+            Detected MIME type of the document.
+        produce_archive:
+            Accepted for protocol compatibility but ignored; the PDF rendition
+            is always produced since the source format cannot be displayed
+            natively in the browser.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If Tika or Gotenberg returns an error.
+        """
+        if TYPE_CHECKING:
+            assert self._tika_client is not None
+
+        logger.info("Sending %s to Tika server", document_path)
+
+        try:
+            try:
+                parsed = self._tika_client.tika.as_text.from_file(
+                    document_path,
+                    mime_type,
+                )
+            except httpx.HTTPStatusError as err:
+                # Workaround https://issues.apache.org/jira/browse/TIKA-4110
+                # Tika fails with some files as multi-part form data
+                if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
+                    parsed = self._tika_client.tika.as_text.from_buffer(
+                        document_path.read_bytes(),
+                        mime_type,
+                    )
+                else:  # pragma: no cover
+                    raise
+        except Exception as err:
+            raise ParseError(
+                f"Could not parse {document_path} with tika server at "
+                f"{settings.TIKA_ENDPOINT}: {err}",
+            ) from err
+
+        self._text = parsed.content
+        if self._text is not None:
+            self._text = self._text.strip()
+
+        self._date = parsed.created
+        if self._date is not None and timezone.is_naive(self._date):
+            self._date = timezone.make_aware(self._date)
+
+        # Always convert — requires_pdf_rendition=True means the browser
+        # cannot display the source format natively.
+        self._archive_path = self._convert_to_pdf(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
+            Creation date from Tika metadata, or None if not detected.
+        """
+        return self._date
+
+    def get_archive_path(self) -> Path | None:
+        """Return the path to the generated PDF rendition, or None.
+
+        Returns
+        -------
+        Path | None
+            Path to the PDF produced by Gotenberg, or None if parse has not
+            been called yet.
+        """
+        return self._archive_path
+
+    # ------------------------------------------------------------------
+    # Thumbnail and metadata
+    # ------------------------------------------------------------------
+
+    def get_thumbnail(self, document_path: Path, mime_type: str) -> Path:
+        """Generate a thumbnail from the PDF rendition of the document.
+
+        Converts the document to PDF first if not already done.
+
+        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.
+        """
+        if self._archive_path is None:
+            self._archive_path = self._convert_to_pdf(document_path)
+        return make_thumbnail_from_pdf(self._archive_path, self._tempdir)
+
+    def get_page_count(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> int | None:
+        """Return the number of pages in the document.
+
+        Counts pages in the archive PDF produced by a preceding parse()
+        call.  Returns ``None`` if parse() has not been called yet or if
+        no archive was produced.
+
+        Returns
+        -------
+        int | None
+            Page count of the archive PDF, or ``None``.
+        """
+        if self._archive_path is not None:
+            from paperless.parsers.utils import get_page_count_for_pdf
+
+            return get_page_count_for_pdf(self._archive_path, log=logger)
+        return None
+
+    def extract_metadata(
+        self,
+        document_path: Path,
+        mime_type: str,
+    ) -> list[MetadataEntry]:
+        """Extract format-specific metadata via the Tika metadata endpoint.
+
+        Returns
+        -------
+        list[MetadataEntry]
+            All key/value pairs returned by Tika, or ``[]`` on error.
+        """
+        if TYPE_CHECKING:
+            assert self._tika_client is not None
+
+        try:
+            parsed = self._tika_client.metadata.from_file(document_path, mime_type)
+            return [
+                {
+                    "namespace": "",
+                    "prefix": "",
+                    "key": key,
+                    "value": parsed.data[key],
+                }
+                for key in parsed.data
+            ]
+        except Exception as e:
+            logger.warning(
+                "Error while fetching document metadata for %s: %s",
+                document_path,
+                e,
+            )
+            return []
+
+    # ------------------------------------------------------------------
+    # Private helpers
+    # ------------------------------------------------------------------
+
+    def _convert_to_pdf(self, document_path: Path) -> Path:
+        """Convert the document to PDF using Gotenberg's LibreOffice route.
+
+        Parameters
+        ----------
+        document_path:
+            Absolute path to the source document.
+
+        Returns
+        -------
+        Path
+            Path to the generated PDF inside the temporary directory.
+
+        Raises
+        ------
+        documents.parsers.ParseError
+            If Gotenberg returns an error.
+        """
+        if TYPE_CHECKING:
+            assert self._gotenberg_client is not None
+
+        pdf_path = self._tempdir / "convert.pdf"
+
+        logger.info("Converting %s to PDF as %s", document_path, pdf_path)
+
+        with self._gotenberg_client.libre_office.to_pdf() as route:
+            # Set the output format of the resulting PDF.
+            # OutputTypeConfig reads the database-stored ApplicationConfiguration
+            # first, then falls back to the PAPERLESS_OCR_OUTPUT_TYPE env var.
+            output_type = OutputTypeConfig().output_type
+            if output_type in {
+                OutputTypeChoices.PDF_A,
+                OutputTypeChoices.PDF_A2,
+            }:
+                route.pdf_format(PdfAFormat.A2b)
+            elif output_type == OutputTypeChoices.PDF_A1:
+                logger.warning(
+                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
+                )
+                route.pdf_format(PdfAFormat.A2b)
+            elif output_type == OutputTypeChoices.PDF_A3:
+                route.pdf_format(PdfAFormat.A3b)
+
+            route.convert(document_path)
+
+            try:
+                response = route.run()
+                pdf_path.write_bytes(response.content)
+                return pdf_path
+            except Exception as err:
+                raise ParseError(
+                    f"Error while converting document to PDF: {err}",
+                ) from err

src/paperless/parsers/utils.py

@@ -0,0 +1,158 @@
+"""
+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 read_file_handle_unicode_errors(
+    filepath: Path,
+    log: logging.Logger | None = None,
+) -> str:
+    """Read a file as UTF-8 text, replacing invalid bytes rather than raising.
+
+    Parameters
+    ----------
+    filepath:
+        Absolute path to the file to read.
+    log:
+        Logger to use for warnings.  Falls back to the module-level logger
+        when omitted.
+
+    Returns
+    -------
+    str
+        File content as a string, with any invalid UTF-8 sequences replaced
+        by the Unicode replacement character.
+    """
+    _log = log or logger
+    try:
+        return filepath.read_text(encoding="utf-8")
+    except UnicodeDecodeError as e:
+        _log.warning("Unicode error during text reading, continuing: %s", e)
+        return filepath.read_bytes().decode("utf-8", errors="replace")
+
+
+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

@@ -248,7 +248,9 @@ class ApplicationConfigurationSerializer(serializers.ModelSerializer):
                 allow_internal=settings.LLM_ALLOW_INTERNAL_ENDPOINTS,
             )
         except ValueError as e:
-            raise serializers.ValidationError(str(e)) from e
+            raise serializers.ValidationError(
+                f"Invalid LLM endpoint: {e.args[0]}, see logs for details",
+            ) from e
 
         return value
 

src/paperless/tests/parsers/conftest.py

@@ -6,15 +6,29 @@ so it is easy to see which files belong to which test module.
 
 from __future__ import annotations
 
+from contextlib import contextmanager
 from typing import TYPE_CHECKING
 
 import pytest
+from django.test import override_settings
 
+from paperless.parsers.mail import MailDocumentParser
+from paperless.parsers.remote import RemoteDocumentParser
+from paperless.parsers.tesseract import RasterisedDocumentParser
 from paperless.parsers.text import TextDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 
 if TYPE_CHECKING:
+    from collections.abc import Callable
     from collections.abc import Generator
     from pathlib import Path
+    from unittest.mock import MagicMock
+
+    from pytest_django.fixtures import SettingsWrapper
+    from pytest_mock import MockerFixture
+
+    #: Type for the ``make_tesseract_parser`` fixture factory.
+    MakeTesseractParser = Callable[..., Generator[RasterisedDocumentParser, None, None]]
 
 
 # ------------------------------------------------------------------
@@ -74,3 +88,713 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
     """
     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
+
+
+# ------------------------------------------------------------------
+# Tika parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def tika_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the Tika parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/tika/``
+    """
+    return samples_dir / "tika"
+
+
+@pytest.fixture(scope="session")
+def sample_odt_file(tika_samples_dir: Path) -> Path:
+    """Path to a sample ODT file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tika/sample.odt``.
+    """
+    return tika_samples_dir / "sample.odt"
+
+
+@pytest.fixture(scope="session")
+def sample_docx_file(tika_samples_dir: Path) -> Path:
+    """Path to a sample DOCX file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tika/sample.docx``.
+    """
+    return tika_samples_dir / "sample.docx"
+
+
+@pytest.fixture(scope="session")
+def sample_doc_file(tika_samples_dir: Path) -> Path:
+    """Path to a sample DOC file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tika/sample.doc``.
+    """
+    return tika_samples_dir / "sample.doc"
+
+
+@pytest.fixture(scope="session")
+def sample_broken_odt(tika_samples_dir: Path) -> Path:
+    """Path to a broken ODT file that triggers the multi-part fallback.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tika/multi-part-broken.odt``.
+    """
+    return tika_samples_dir / "multi-part-broken.odt"
+
+
+# ------------------------------------------------------------------
+# Tika parser instance
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def tika_parser() -> Generator[TikaDocumentParser, None, None]:
+    """Yield a TikaDocumentParser and clean up its temporary directory afterwards.
+
+    Yields
+    ------
+    TikaDocumentParser
+        A ready-to-use parser instance.
+    """
+    with TikaDocumentParser() as parser:
+        yield parser
+
+
+# ------------------------------------------------------------------
+# Mail parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def mail_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the mail parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/mail/``
+    """
+    return samples_dir / "mail"
+
+
+@pytest.fixture(scope="session")
+def broken_email_file(mail_samples_dir: Path) -> Path:
+    """Path to a broken/malformed EML sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/broken.eml``.
+    """
+    return mail_samples_dir / "broken.eml"
+
+
+@pytest.fixture(scope="session")
+def simple_txt_email_file(mail_samples_dir: Path) -> Path:
+    """Path to a plain-text email sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/simple_text.eml``.
+    """
+    return mail_samples_dir / "simple_text.eml"
+
+
+@pytest.fixture(scope="session")
+def simple_txt_email_pdf_file(mail_samples_dir: Path) -> Path:
+    """Path to the expected PDF rendition of the plain-text email.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/simple_text.eml.pdf``.
+    """
+    return mail_samples_dir / "simple_text.eml.pdf"
+
+
+@pytest.fixture(scope="session")
+def simple_txt_email_thumbnail_file(mail_samples_dir: Path) -> Path:
+    """Path to the expected thumbnail for the plain-text email.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/simple_text.eml.pdf.webp``.
+    """
+    return mail_samples_dir / "simple_text.eml.pdf.webp"
+
+
+@pytest.fixture(scope="session")
+def html_email_file(mail_samples_dir: Path) -> Path:
+    """Path to an HTML email sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/html.eml``.
+    """
+    return mail_samples_dir / "html.eml"
+
+
+@pytest.fixture(scope="session")
+def html_email_pdf_file(mail_samples_dir: Path) -> Path:
+    """Path to the expected PDF rendition of the HTML email.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/html.eml.pdf``.
+    """
+    return mail_samples_dir / "html.eml.pdf"
+
+
+@pytest.fixture(scope="session")
+def html_email_thumbnail_file(mail_samples_dir: Path) -> Path:
+    """Path to the expected thumbnail for the HTML email.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/html.eml.pdf.webp``.
+    """
+    return mail_samples_dir / "html.eml.pdf.webp"
+
+
+@pytest.fixture(scope="session")
+def html_email_html_file(mail_samples_dir: Path) -> Path:
+    """Path to the HTML body of the HTML email sample.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/html.eml.html``.
+    """
+    return mail_samples_dir / "html.eml.html"
+
+
+@pytest.fixture(scope="session")
+def merged_pdf_first(mail_samples_dir: Path) -> Path:
+    """Path to the first PDF used in PDF-merge tests.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/first.pdf``.
+    """
+    return mail_samples_dir / "first.pdf"
+
+
+@pytest.fixture(scope="session")
+def merged_pdf_second(mail_samples_dir: Path) -> Path:
+    """Path to the second PDF used in PDF-merge tests.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``mail/second.pdf``.
+    """
+    return mail_samples_dir / "second.pdf"
+
+
+# ------------------------------------------------------------------
+# Mail parser instance
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def mail_parser() -> Generator[MailDocumentParser, None, None]:
+    """Yield a MailDocumentParser and clean up its temporary directory afterwards.
+
+    Yields
+    ------
+    MailDocumentParser
+        A ready-to-use parser instance.
+    """
+    with MailDocumentParser() as parser:
+        yield parser
+
+
+@pytest.fixture(scope="session")
+def nginx_base_url() -> Generator[str, None, None]:
+    """
+    The base URL for the nginx HTTP server we expect to be alive
+    """
+    yield "http://localhost:8080"
+
+
+# ------------------------------------------------------------------
+# Tesseract parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def tesseract_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the tesseract parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/tesseract/``
+    """
+    return samples_dir / "tesseract"
+
+
+@pytest.fixture(scope="session")
+def document_webp_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a WebP document sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/document.webp``.
+    """
+    return tesseract_samples_dir / "document.webp"
+
+
+@pytest.fixture(scope="session")
+def encrypted_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to an encrypted PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/encrypted.pdf``.
+    """
+    return tesseract_samples_dir / "encrypted.pdf"
+
+
+@pytest.fixture(scope="session")
+def multi_page_digital_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page digital PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-digital.pdf``.
+    """
+    return tesseract_samples_dir / "multi-page-digital.pdf"
+
+
+@pytest.fixture(scope="session")
+def multi_page_images_alpha_rgb_tiff_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page TIFF with alpha channel in RGB.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-images-alpha-rgb.tiff``.
+    """
+    return tesseract_samples_dir / "multi-page-images-alpha-rgb.tiff"
+
+
+@pytest.fixture(scope="session")
+def multi_page_images_alpha_tiff_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page TIFF with alpha channel.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-images-alpha.tiff``.
+    """
+    return tesseract_samples_dir / "multi-page-images-alpha.tiff"
+
+
+@pytest.fixture(scope="session")
+def multi_page_images_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page PDF with images.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-images.pdf``.
+    """
+    return tesseract_samples_dir / "multi-page-images.pdf"
+
+
+@pytest.fixture(scope="session")
+def multi_page_images_tiff_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page TIFF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-images.tiff``.
+    """
+    return tesseract_samples_dir / "multi-page-images.tiff"
+
+
+@pytest.fixture(scope="session")
+def multi_page_mixed_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a multi-page mixed PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/multi-page-mixed.pdf``.
+    """
+    return tesseract_samples_dir / "multi-page-mixed.pdf"
+
+
+@pytest.fixture(scope="session")
+def no_text_alpha_png_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a PNG with alpha channel and no text.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/no-text-alpha.png``.
+    """
+    return tesseract_samples_dir / "no-text-alpha.png"
+
+
+@pytest.fixture(scope="session")
+def rotated_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a rotated PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/rotated.pdf``.
+    """
+    return tesseract_samples_dir / "rotated.pdf"
+
+
+@pytest.fixture(scope="session")
+def rtl_test_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to an RTL test PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/rtl-test.pdf``.
+    """
+    return tesseract_samples_dir / "rtl-test.pdf"
+
+
+@pytest.fixture(scope="session")
+def signed_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a signed PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/signed.pdf``.
+    """
+    return tesseract_samples_dir / "signed.pdf"
+
+
+@pytest.fixture(scope="session")
+def simple_alpha_png_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple PNG with alpha channel.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple-alpha.png``.
+    """
+    return tesseract_samples_dir / "simple-alpha.png"
+
+
+@pytest.fixture(scope="session")
+def simple_digital_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple digital PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple-digital.pdf``.
+    """
+    return tesseract_samples_dir / "simple-digital.pdf"
+
+
+@pytest.fixture(scope="session")
+def simple_no_dpi_png_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple PNG without DPI information.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple-no-dpi.png``.
+    """
+    return tesseract_samples_dir / "simple-no-dpi.png"
+
+
+@pytest.fixture(scope="session")
+def simple_bmp_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple BMP sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.bmp``.
+    """
+    return tesseract_samples_dir / "simple.bmp"
+
+
+@pytest.fixture(scope="session")
+def simple_gif_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple GIF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.gif``.
+    """
+    return tesseract_samples_dir / "simple.gif"
+
+
+@pytest.fixture(scope="session")
+def simple_heic_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple HEIC sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.heic``.
+    """
+    return tesseract_samples_dir / "simple.heic"
+
+
+@pytest.fixture(scope="session")
+def simple_jpg_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple JPG sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.jpg``.
+    """
+    return tesseract_samples_dir / "simple.jpg"
+
+
+@pytest.fixture(scope="session")
+def simple_png_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple PNG sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.png``.
+    """
+    return tesseract_samples_dir / "simple.png"
+
+
+@pytest.fixture(scope="session")
+def simple_tif_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a simple TIF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/simple.tif``.
+    """
+    return tesseract_samples_dir / "simple.tif"
+
+
+@pytest.fixture(scope="session")
+def single_page_mixed_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a single-page mixed PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/single-page-mixed.pdf``.
+    """
+    return tesseract_samples_dir / "single-page-mixed.pdf"
+
+
+@pytest.fixture(scope="session")
+def with_form_pdf_file(tesseract_samples_dir: Path) -> Path:
+    """Path to a PDF with form sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``tesseract/with-form.pdf``.
+    """
+    return tesseract_samples_dir / "with-form.pdf"
+
+
+# ------------------------------------------------------------------
+# Tesseract parser instance and settings helpers
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def null_app_config(mocker: MockerFixture) -> MagicMock:
+    """Return a MagicMock with all OcrConfig fields set to None.
+
+    This allows the parser to fall back to Django settings instead of
+    hitting the database.
+
+    Returns
+    -------
+    MagicMock
+        Mock config with all fields as None
+    """
+    return mocker.MagicMock(
+        output_type=None,
+        pages=None,
+        language=None,
+        mode=None,
+        skip_archive_file=None,
+        image_dpi=None,
+        unpaper_clean=None,
+        deskew=None,
+        rotate_pages=None,
+        rotate_pages_threshold=None,
+        max_image_pixels=None,
+        color_conversion_strategy=None,
+        user_args=None,
+    )
+
+
+@pytest.fixture()
+def tesseract_parser(
+    mocker: MockerFixture,
+    null_app_config: MagicMock,
+) -> Generator[RasterisedDocumentParser, None, None]:
+    """Yield a RasterisedDocumentParser and clean up its temporary directory afterwards.
+
+    Patches the config system to avoid database access.
+
+    Yields
+    ------
+    RasterisedDocumentParser
+        A ready-to-use parser instance.
+    """
+    mocker.patch(
+        "paperless.config.BaseConfig._get_config_instance",
+        return_value=null_app_config,
+    )
+    with RasterisedDocumentParser() as parser:
+        yield parser
+
+
+@pytest.fixture()
+def make_tesseract_parser(
+    mocker: MockerFixture,
+    null_app_config: MagicMock,
+) -> MakeTesseractParser:
+    """Return a factory for creating RasterisedDocumentParser with Django settings overrides.
+
+    This fixture is useful for tests that need to create parsers with different
+    settings configurations.
+
+    Returns
+    -------
+    Callable[..., contextmanager[RasterisedDocumentParser]]
+        A context manager factory that accepts Django settings overrides
+    """
+    mocker.patch(
+        "paperless.config.BaseConfig._get_config_instance",
+        return_value=null_app_config,
+    )
+
+    @contextmanager
+    def _make_parser(**django_settings_overrides):
+        with override_settings(**django_settings_overrides):
+            with RasterisedDocumentParser() as parser:
+                yield parser
+
+    return _make_parser

src/paperless/tests/parsers/test_mail_parser.py

@@ -12,7 +12,64 @@ from pytest_httpx import HTTPXMock
 from pytest_mock import MockerFixture
 
 from documents.parsers import ParseError
-from paperless_mail.parsers import MailDocumentParser
+from paperless.parsers import ParserContext
+from paperless.parsers import ParserProtocol
+from paperless.parsers.mail import MailDocumentParser
+
+
+class TestMailParserProtocol:
+    """Verify that MailDocumentParser satisfies the ParserProtocol contract."""
+
+    def test_isinstance_satisfies_protocol(
+        self,
+        mail_parser: MailDocumentParser,
+    ) -> None:
+        assert isinstance(mail_parser, ParserProtocol)
+
+    def test_supported_mime_types(self) -> None:
+        mime_types = MailDocumentParser.supported_mime_types()
+        assert isinstance(mime_types, dict)
+        assert "message/rfc822" in mime_types
+
+    @pytest.mark.parametrize(
+        ("mime_type", "expected"),
+        [
+            ("message/rfc822", 10),
+            ("application/pdf", None),
+            ("text/plain", None),
+        ],
+    )
+    def test_score(self, mime_type: str, expected: int | None) -> None:
+        assert MailDocumentParser.score(mime_type, "email.eml") == expected
+
+    def test_can_produce_archive_is_false(
+        self,
+        mail_parser: MailDocumentParser,
+    ) -> None:
+        assert mail_parser.can_produce_archive is False
+
+    def test_requires_pdf_rendition_is_true(
+        self,
+        mail_parser: MailDocumentParser,
+    ) -> None:
+        assert mail_parser.requires_pdf_rendition is True
+
+    def test_get_page_count_returns_none_without_archive(
+        self,
+        mail_parser: MailDocumentParser,
+        html_email_file: Path,
+    ) -> None:
+        assert mail_parser.get_page_count(html_email_file, "message/rfc822") is None
+
+    def test_get_page_count_returns_int_with_pdf_archive(
+        self,
+        mail_parser: MailDocumentParser,
+        simple_txt_email_pdf_file: Path,
+    ) -> None:
+        mail_parser._archive_path = simple_txt_email_pdf_file
+        count = mail_parser.get_page_count(simple_txt_email_pdf_file, "message/rfc822")
+        assert isinstance(count, int)
+        assert count > 0
 
 
 class TestEmailFileParsing:
@@ -24,7 +81,7 @@ class TestEmailFileParsing:
     def test_parse_error_missing_file(
         self,
         mail_parser: MailDocumentParser,
-        sample_dir: Path,
+        mail_samples_dir: Path,
     ) -> None:
         """
         GIVEN:
@@ -35,7 +92,7 @@ class TestEmailFileParsing:
             - An Exception is thrown
         """
         # Check if exception is raised when parsing fails.
-        test_file = sample_dir / "doesntexist.eml"
+        test_file = mail_samples_dir / "doesntexist.eml"
 
         assert not test_file.exists()
 
@@ -246,12 +303,12 @@ class TestEmailThumbnailGenerate:
         """
         mocked_return = "Passing the return value through.."
         mock_make_thumbnail_from_pdf = mocker.patch(
-            "paperless_mail.parsers.make_thumbnail_from_pdf",
+            "paperless.parsers.mail.make_thumbnail_from_pdf",
         )
         mock_make_thumbnail_from_pdf.return_value = mocked_return
 
         mock_generate_pdf = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf",
         )
         mock_generate_pdf.return_value = "Mocked return value.."
 
@@ -260,8 +317,7 @@ class TestEmailThumbnailGenerate:
         mock_generate_pdf.assert_called_once()
         mock_make_thumbnail_from_pdf.assert_called_once_with(
             "Mocked return value..",
-            mail_parser.tempdir,
-            None,
+            mail_parser._tempdir,
         )
 
         assert mocked_return == thumb
@@ -373,7 +429,7 @@ class TestParser:
         """
         # Validate parsing returns the expected results
         mock_generate_pdf = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf",
         )
 
         mail_parser.parse(simple_txt_email_file, "message/rfc822")
@@ -385,7 +441,7 @@ class TestParser:
             "BCC: fdf@fvf.de\n\n"
             "\n\nThis is just a simple Text Mail."
         )
-        assert text_expected == mail_parser.text
+        assert text_expected == mail_parser.get_text()
         assert (
             datetime.datetime(
                 2022,
@@ -396,7 +452,7 @@ class TestParser:
                 43,
                 tzinfo=datetime.timezone(datetime.timedelta(seconds=7200)),
             )
-            == mail_parser.date
+            == mail_parser.get_date()
         )
 
         # Just check if tried to generate archive, the unittest for generate_pdf() goes deeper.
@@ -419,7 +475,7 @@ class TestParser:
         """
 
         mock_generate_pdf = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf",
         )
 
         # Validate parsing returns the expected results
@@ -443,7 +499,7 @@ class TestParser:
         mail_parser.parse(html_email_file, "message/rfc822")
 
         mock_generate_pdf.assert_called_once()
-        assert text_expected == mail_parser.text
+        assert text_expected == mail_parser.get_text()
         assert (
             datetime.datetime(
                 2022,
@@ -454,7 +510,7 @@ class TestParser:
                 19,
                 tzinfo=datetime.timezone(datetime.timedelta(seconds=7200)),
             )
-            == mail_parser.date
+            == mail_parser.get_date()
         )
 
     def test_generate_pdf_parse_error(
@@ -501,7 +557,7 @@ class TestParser:
 
         mail_parser.parse(simple_txt_email_file, "message/rfc822")
 
-        assert mail_parser.archive_path is not None
+        assert mail_parser.get_archive_path() is not None
 
     @pytest.mark.httpx_mock(can_send_already_matched_responses=True)
     def test_generate_pdf_html_email(
@@ -542,7 +598,7 @@ class TestParser:
         )
         mail_parser.parse(html_email_file, "message/rfc822")
 
-        assert mail_parser.archive_path is not None
+        assert mail_parser.get_archive_path() is not None
 
     def test_generate_pdf_html_email_html_to_pdf_failure(
         self,
@@ -712,10 +768,10 @@ class TestParser:
 
         def test_layout_option(layout_option, expected_calls, expected_pdf_names):
             mock_mailrule_get.return_value = mock.Mock(pdf_layout=layout_option)
+            mail_parser.configure(ParserContext(mailrule_id=1))
             mail_parser.parse(
                 document_path=html_email_file,
                 mime_type="message/rfc822",
-                mailrule_id=1,
             )
             args, _ = mock_merge_route.call_args
             assert len(args[0]) == expected_calls

src/paperless/tests/parsers/test_mail_parser_live.py

@@ -11,7 +11,7 @@ from PIL import Image
 from pytest_mock import MockerFixture
 
 from documents.tests.utils import util_call_with_backoff
-from paperless_mail.parsers import MailDocumentParser
+from paperless.parsers.mail import MailDocumentParser
 
 
 def extract_text(pdf_path: Path) -> str:
@@ -159,7 +159,7 @@ class TestParserLive:
             - The returned thumbnail image file shall match the expected hash
         """
         mock_generate_pdf = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf",
         )
         mock_generate_pdf.return_value = simple_txt_email_pdf_file
 
@@ -216,10 +216,10 @@ class TestParserLive:
             - The merged PDF shall contain text from both source PDFs
         """
         mock_generate_pdf_from_html = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf_from_html",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf_from_html",
         )
         mock_generate_pdf_from_mail = mocker.patch(
-            "paperless_mail.parsers.MailDocumentParser.generate_pdf_from_mail",
+            "paperless.parsers.mail.MailDocumentParser.generate_pdf_from_mail",
         )
         mock_generate_pdf_from_mail.return_value = merged_pdf_first
         mock_generate_pdf_from_html.return_value = merged_pdf_second

src/paperless/tests/parsers/test_remote_parser.py

@@ -0,0 +1,497 @@
+"""
+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 ParserContext
+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.configure(ParserContext())
+        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_unsupported_type_when_not_configured(
+        self,
+    ) -> None:
+        """With remote off and a truly unsupported MIME type, registry returns None."""
+        from paperless.parsers.registry import ParserRegistry
+
+        registry = ParserRegistry()
+        registry.register_defaults()
+        parser_cls = registry.get_parser_for_file(
+            "application/x-unknown-format",
+            "doc.xyz",
+        )
+
+        assert parser_cls is None

src/paperless/tests/parsers/test_tesseract_custom_settings.py

@@ -10,7 +10,7 @@ from paperless.models import CleanChoices
 from paperless.models import ColorConvertChoices
 from paperless.models import ModeChoices
 from paperless.models import OutputTypeChoices
-from paperless_tesseract.parsers import RasterisedDocumentParser
+from paperless.parsers.tesseract import RasterisedDocumentParser
 
 
 class TestParserSettingsFromDb(DirectoriesMixin, FileSystemAssertsMixin, TestCase):

src/paperless/tests/parsers/test_text_parser.py

@@ -12,6 +12,7 @@ from pathlib import Path
 
 import pytest
 
+from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
 from paperless.parsers.text import TextDocumentParser
 
@@ -93,6 +94,7 @@ class TestTextParserParse:
         text_parser: TextDocumentParser,
         sample_txt_file: Path,
     ) -> None:
+        text_parser.configure(ParserContext())
         text_parser.parse(sample_txt_file, "text/plain")
 
         assert text_parser.get_text() == "This is a test file.\n"
@@ -102,6 +104,7 @@ class TestTextParserParse:
         text_parser: TextDocumentParser,
         sample_txt_file: Path,
     ) -> None:
+        text_parser.configure(ParserContext())
         text_parser.parse(sample_txt_file, "text/plain")
 
         assert text_parser.get_archive_path() is None
@@ -111,6 +114,7 @@ class TestTextParserParse:
         text_parser: TextDocumentParser,
         sample_txt_file: Path,
     ) -> None:
+        text_parser.configure(ParserContext())
         text_parser.parse(sample_txt_file, "text/plain")
 
         assert text_parser.get_date() is None
@@ -129,6 +133,7 @@ class TestTextParserParse:
             - Parsing succeeds
             - Invalid bytes are replaced with the Unicode replacement character
         """
+        text_parser.configure(ParserContext())
         text_parser.parse(malformed_txt_file, "text/plain")
 
         assert text_parser.get_text() == "Pantothens\ufffdure\n"
@@ -251,6 +256,9 @@ class TestTextParserRegistry:
         from paperless.parsers.registry import get_parser_registry
 
         registry = get_parser_registry()
-        parser_cls = registry.get_parser_for_file("application/pdf", "doc.pdf")
+        parser_cls = registry.get_parser_for_file(
+            "application/x-unknown-format",
+            "doc.xyz",
+        )
 
         assert parser_cls is None

src/paperless/tests/parsers/test_tika_liva.py

@@ -4,7 +4,7 @@ from pathlib import Path
 import pytest
 
 from documents.tests.utils import util_call_with_backoff
-from paperless_tika.parsers import TikaDocumentParser
+from paperless.parsers.tika import TikaDocumentParser
 
 
 @pytest.mark.skipif(
@@ -42,14 +42,15 @@ class TestTikaParserAgainstServer:
         )
 
         assert (
-            tika_parser.text
+            tika_parser.get_text()
             == "This is an ODT test document, created September 14, 2022"
         )
-        assert tika_parser.archive_path is not None
-        assert b"PDF-" in tika_parser.archive_path.read_bytes()[:10]
+        archive = tika_parser.get_archive_path()
+        assert archive is not None
+        assert b"PDF-" in archive.read_bytes()[:10]
 
         # TODO: Unsure what can set the Creation-Date field in a document, enable when possible
-        # self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
+        # self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
 
     def test_basic_parse_docx(
         self,
@@ -74,14 +75,15 @@ class TestTikaParserAgainstServer:
         )
 
         assert (
-            tika_parser.text
+            tika_parser.get_text()
             == "This is an DOCX test document, also made September 14, 2022"
         )
-        assert tika_parser.archive_path is not None
-        with Path(tika_parser.archive_path).open("rb") as f:
+        archive = tika_parser.get_archive_path()
+        assert archive is not None
+        with archive.open("rb") as f:
             assert b"PDF-" in f.read()[:10]
 
-        # self.assertEqual(tika_parser.date, datetime.datetime(2022, 9, 14))
+        # self.assertEqual(tika_parser.get_date(), datetime.datetime(2022, 9, 14))
 
     def test_basic_parse_doc(
         self,
@@ -102,13 +104,12 @@ class TestTikaParserAgainstServer:
             [sample_doc_file, "application/msword"],
         )
 
-        assert tika_parser.text is not None
-        assert (
-            "This is a test document, saved in the older .doc format"
-            in tika_parser.text
-        )
-        assert tika_parser.archive_path is not None
-        with Path(tika_parser.archive_path).open("rb") as f:
+        text = tika_parser.get_text()
+        assert text is not None
+        assert "This is a test document, saved in the older .doc format" in text
+        archive = tika_parser.get_archive_path()
+        assert archive is not None
+        with archive.open("rb") as f:
             assert b"PDF-" in f.read()[:10]
 
     def test_tika_fails_multi_part(
@@ -133,6 +134,7 @@ class TestTikaParserAgainstServer:
             [sample_broken_odt, "application/vnd.oasis.opendocument.text"],
         )
 
-        assert tika_parser.archive_path is not None
-        with Path(tika_parser.archive_path).open("rb") as f:
+        archive = tika_parser.get_archive_path()
+        assert archive is not None
+        with archive.open("rb") as f:
             assert b"PDF-" in f.read()[:10]

src/paperless/tests/parsers/test_tika_parser.py

@@ -9,7 +9,80 @@ from pytest_django.fixtures import SettingsWrapper
 from pytest_httpx import HTTPXMock
 
 from documents.parsers import ParseError
-from paperless_tika.parsers import TikaDocumentParser
+from paperless.parsers import ParserContext
+from paperless.parsers import ParserProtocol
+from paperless.parsers.tika import TikaDocumentParser
+
+
+class TestTikaParserRegistryInterface:
+    """Verify that TikaDocumentParser satisfies the ParserProtocol contract."""
+
+    def test_satisfies_parser_protocol(self) -> None:
+        assert isinstance(TikaDocumentParser(), ParserProtocol)
+
+    def test_supported_mime_types_is_classmethod(self) -> None:
+        mime_types = TikaDocumentParser.supported_mime_types()
+        assert isinstance(mime_types, dict)
+        assert len(mime_types) > 0
+
+    def test_score_returns_none_when_tika_disabled(
+        self,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.TIKA_ENABLED = False
+        result = TikaDocumentParser.score(
+            "application/vnd.oasis.opendocument.text",
+            "sample.odt",
+        )
+        assert result is None
+
+    def test_score_returns_int_when_tika_enabled(
+        self,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.TIKA_ENABLED = True
+        result = TikaDocumentParser.score(
+            "application/vnd.oasis.opendocument.text",
+            "sample.odt",
+        )
+        assert isinstance(result, int)
+
+    def test_score_returns_none_for_unsupported_mime(
+        self,
+        settings: SettingsWrapper,
+    ) -> None:
+        settings.TIKA_ENABLED = True
+        result = TikaDocumentParser.score("application/pdf", "doc.pdf")
+        assert result is None
+
+    def test_can_produce_archive_is_false(self) -> None:
+        assert TikaDocumentParser().can_produce_archive is False
+
+    def test_requires_pdf_rendition_is_true(self) -> None:
+        assert TikaDocumentParser().requires_pdf_rendition is True
+
+    def test_get_page_count_returns_none_without_archive(
+        self,
+        tika_parser: TikaDocumentParser,
+        sample_odt_file: Path,
+    ) -> None:
+        assert (
+            tika_parser.get_page_count(
+                sample_odt_file,
+                "application/vnd.oasis.opendocument.text",
+            )
+            is None
+        )
+
+    def test_get_page_count_returns_int_with_pdf_archive(
+        self,
+        tika_parser: TikaDocumentParser,
+        sample_pdf_file: Path,
+    ) -> None:
+        tika_parser._archive_path = sample_pdf_file
+        count = tika_parser.get_page_count(sample_pdf_file, "application/pdf")
+        assert isinstance(count, int)
+        assert count > 0
 
 
 @pytest.mark.django_db()
@@ -34,14 +107,15 @@ class TestTikaParser:
         # Pretend convert to PDF response
         httpx_mock.add_response(content=b"PDF document")
 
+        tika_parser.configure(ParserContext())
         tika_parser.parse(sample_odt_file, "application/vnd.oasis.opendocument.text")
 
-        assert tika_parser.text == "the content"
-        assert tika_parser.archive_path is not None
-        with Path(tika_parser.archive_path).open("rb") as f:
+        assert tika_parser.get_text() == "the content"
+        assert tika_parser.get_archive_path() is not None
+        with Path(tika_parser.get_archive_path()).open("rb") as f:
             assert f.read() == b"PDF document"
 
-        assert tika_parser.date == datetime.datetime(
+        assert tika_parser.get_date() == datetime.datetime(
             2020,
             11,
             21,
@@ -89,7 +163,7 @@ class TestTikaParser:
         httpx_mock.add_response(status_code=HTTPStatus.INTERNAL_SERVER_ERROR)
 
         with pytest.raises(ParseError):
-            tika_parser.convert_to_pdf(sample_odt_file, None)
+            tika_parser._convert_to_pdf(sample_odt_file)
 
     @pytest.mark.parametrize(
         ("setting_value", "expected_form_value"),
@@ -106,7 +180,6 @@ class TestTikaParser:
         expected_form_value: str,
         httpx_mock: HTTPXMock,
         settings: SettingsWrapper,
-        tika_parser: TikaDocumentParser,
         sample_odt_file: Path,
     ) -> None:
         """
@@ -117,6 +190,8 @@ class TestTikaParser:
         THEN:
             - Request to Gotenberg contains the expected PDF/A format string
         """
+        # Parser must be created after the setting is changed so that
+        # OutputTypeConfig reads the correct value at __init__ time.
         settings.OCR_OUTPUT_TYPE = setting_value
         httpx_mock.add_response(
             status_code=codes.OK,
@@ -124,7 +199,8 @@ class TestTikaParser:
             method="POST",
         )
 
-        tika_parser.convert_to_pdf(sample_odt_file, None)
+        with TikaDocumentParser() as parser:
+            parser._convert_to_pdf(sample_odt_file)
 
         request = httpx_mock.get_request()
 

src/paperless/tests/test_registry.py

@@ -18,6 +18,7 @@ from unittest.mock import patch
 
 import pytest
 
+from paperless.parsers import ParserContext
 from paperless.parsers import ParserProtocol
 from paperless.parsers.registry import ParserRegistry
 from paperless.parsers.registry import get_parser_registry
@@ -103,6 +104,11 @@ def dummy_parser_cls() -> type:
         ) -> list:
             return []
 
+        def configure(self, context: ParserContext) -> None:
+            """
+            Required to exist, but doesn't need to do anything
+            """
+
         def __enter__(self) -> Self:
             return self
 
@@ -144,6 +150,7 @@ class TestParserProtocol:
     @pytest.mark.parametrize(
         "missing_method",
         [
+            pytest.param("configure", id="missing-configure"),
             pytest.param("parse", id="missing-parse"),
             pytest.param("get_text", id="missing-get_text"),
             pytest.param("get_thumbnail", id="missing-get_thumbnail"),

src/paperless_ai/tests/conftest.py

@@ -0,0 +1,10 @@
+from pathlib import Path
+
+import pytest
+from pytest_django.fixtures import SettingsWrapper
+
+
+@pytest.fixture
+def temp_llm_index_dir(tmp_path: Path, settings: SettingsWrapper):
+    settings.LLM_INDEX_DIR = tmp_path
+    return tmp_path

src/paperless_ai/tests/test_ai_indexing.py

@@ -13,14 +13,6 @@ from documents.models import PaperlessTask
 from paperless_ai import indexing
 
 
-@pytest.fixture
-def temp_llm_index_dir(tmp_path):
-    original_dir = indexing.settings.LLM_INDEX_DIR
-    indexing.settings.LLM_INDEX_DIR = tmp_path
-    yield tmp_path
-    indexing.settings.LLM_INDEX_DIR = original_dir
-
-
 @pytest.fixture
 def real_document(db):
     return Document.objects.create(

src/paperless_ai/tests/test_embedding.py

@@ -3,7 +3,6 @@ from unittest.mock import MagicMock
 from unittest.mock import patch
 
 import pytest
-from django.conf import settings
 
 from documents.models import Document
 from paperless.models import LLMEmbeddingBackend
@@ -19,14 +18,6 @@ def mock_ai_config():
         yield MockAIConfig
 
 
-@pytest.fixture
-def temp_llm_index_dir(tmp_path):
-    original_dir = settings.LLM_INDEX_DIR
-    settings.LLM_INDEX_DIR = tmp_path
-    yield tmp_path
-    settings.LLM_INDEX_DIR = original_dir
-
-
 @pytest.fixture
 def mock_document():
     doc = MagicMock(spec=Document)

src/paperless_mail/parsers.py

@@ -1,481 +0,0 @@
-import re
-from html import escape
-from pathlib import Path
-
-from bleach import clean
-from bleach import linkify
-from django.conf import settings
-from django.utils import timezone
-from django.utils.timezone import is_naive
-from django.utils.timezone import make_aware
-from gotenberg_client import GotenbergClient
-from gotenberg_client.constants import A4
-from gotenberg_client.options import Measurement
-from gotenberg_client.options import MeasurementUnitType
-from gotenberg_client.options import PageMarginsType
-from gotenberg_client.options import PdfAFormat
-from humanize import naturalsize
-from imap_tools import MailAttachment
-from imap_tools import MailMessage
-from tika_client import TikaClient
-
-from documents.parsers import DocumentParser
-from documents.parsers import ParseError
-from documents.parsers import make_thumbnail_from_pdf
-from paperless.models import OutputTypeChoices
-from paperless_mail.models import MailRule
-
-
-class MailDocumentParser(DocumentParser):
-    """
-    This parser uses imap_tools to parse .eml files, generates pdf using
-    Gotenberg and sends the html part to a Tika server for text extraction.
-    """
-
-    logging_name = "paperless.parsing.mail"
-
-    def _settings_to_gotenberg_pdfa(self) -> PdfAFormat | None:
-        """
-        Converts our requested PDF/A output into the Gotenberg API
-        format
-        """
-        if settings.OCR_OUTPUT_TYPE in {
-            OutputTypeChoices.PDF_A,
-            OutputTypeChoices.PDF_A2,
-        }:
-            return PdfAFormat.A2b
-        elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:  # pragma: no cover
-            self.log.warning(
-                "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
-            )
-            return PdfAFormat.A2b
-        elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:  # pragma: no cover
-            return PdfAFormat.A3b
-        return None
-
-    def get_thumbnail(
-        self,
-        document_path: Path,
-        mime_type: str,
-        file_name=None,
-    ) -> Path:
-        if not self.archive_path:
-            self.archive_path = self.generate_pdf(
-                self.parse_file_to_message(document_path),
-            )
-
-        return make_thumbnail_from_pdf(
-            self.archive_path,
-            self.tempdir,
-            self.logging_group,
-        )
-
-    def extract_metadata(self, document_path: Path, mime_type: str):
-        result = []
-
-        try:
-            mail = self.parse_file_to_message(document_path)
-        except ParseError as e:
-            self.log.warning(
-                f"Error while fetching document metadata for {document_path}: {e}",
-            )
-            return result
-
-        for key, value in mail.headers.items():
-            value = ", ".join(i for i in value)
-            try:
-                value.encode("utf-8")
-            except UnicodeEncodeError as e:  # pragma: no cover
-                self.log.debug(f"Skipping header {key}: {e}")
-                continue
-
-            result.append(
-                {
-                    "namespace": "",
-                    "prefix": "header",
-                    "key": key,
-                    "value": value,
-                },
-            )
-
-        result.append(
-            {
-                "namespace": "",
-                "prefix": "",
-                "key": "attachments",
-                "value": ", ".join(
-                    f"{attachment.filename}"
-                    f"({naturalsize(attachment.size, binary=True, format='%.2f')})"
-                    for attachment in mail.attachments
-                ),
-            },
-        )
-
-        result.append(
-            {
-                "namespace": "",
-                "prefix": "",
-                "key": "date",
-                "value": mail.date.strftime("%Y-%m-%d %H:%M:%S %Z"),
-            },
-        )
-
-        result.sort(key=lambda item: (item["prefix"], item["key"]))
-        return result
-
-    def parse(
-        self,
-        document_path: Path,
-        mime_type: str,
-        file_name=None,
-        mailrule_id: int | None = None,
-    ) -> None:
-        """
-        Parses the given .eml into formatted text, based on the decoded email.
-
-        """
-
-        def strip_text(text: str):
-            """
-            Reduces the spacing of the given text string
-            """
-            text = re.sub(r"\s+", " ", text)
-            text = re.sub(r"(\n *)+", "\n", text)
-            return text.strip()
-
-        def build_formatted_text(mail_message: MailMessage) -> str:
-            """
-            Constructs a formatted string, based on the given email.  Basically tries
-            to get most of the email content, included front matter, into a nice string
-            """
-            fmt_text = f"Subject: {mail_message.subject}\n\n"
-            fmt_text += f"From: {mail_message.from_values.full}\n\n"
-            to_list = [address.full for address in mail_message.to_values]
-            fmt_text += f"To: {', '.join(to_list)}\n\n"
-            if mail_message.cc_values:
-                fmt_text += (
-                    f"CC: {', '.join(address.full for address in mail.cc_values)}\n\n"
-                )
-            if mail_message.bcc_values:
-                fmt_text += (
-                    f"BCC: {', '.join(address.full for address in mail.bcc_values)}\n\n"
-                )
-            if mail_message.attachments:
-                att = []
-                for a in mail.attachments:
-                    attachment_size = naturalsize(a.size, binary=True, format="%.2f")
-                    att.append(
-                        f"{a.filename} ({attachment_size})",
-                    )
-                fmt_text += f"Attachments: {', '.join(att)}\n\n"
-
-            if mail.html:
-                fmt_text += "HTML content: " + strip_text(self.tika_parse(mail.html))
-
-            fmt_text += f"\n\n{strip_text(mail.text)}"
-
-            return fmt_text
-
-        self.log.debug(f"Parsing file {document_path.name} into an email")
-        mail = self.parse_file_to_message(document_path)
-
-        self.log.debug("Building formatted text from email")
-        self.text = build_formatted_text(mail)
-
-        if is_naive(mail.date):
-            self.date = make_aware(mail.date)
-        else:
-            self.date = mail.date
-
-        self.log.debug("Creating a PDF from the email")
-        if mailrule_id:
-            rule = MailRule.objects.get(pk=mailrule_id)
-            self.archive_path = self.generate_pdf(mail, rule.pdf_layout)
-        else:
-            self.archive_path = self.generate_pdf(mail)
-
-    @staticmethod
-    def parse_file_to_message(filepath: Path) -> MailMessage:
-        """
-        Parses the given .eml file into a MailMessage object
-        """
-        try:
-            with filepath.open("rb") as eml:
-                parsed = MailMessage.from_bytes(eml.read())
-                if parsed.from_values is None:
-                    raise ParseError(
-                        f"Could not parse {filepath}: Missing 'from'",
-                    )
-        except Exception as err:
-            raise ParseError(
-                f"Could not parse {filepath}: {err}",
-            ) from err
-
-        return parsed
-
-    def tika_parse(self, html: str):
-        self.log.info("Sending content to Tika server")
-
-        try:
-            with TikaClient(tika_url=settings.TIKA_ENDPOINT) as client:
-                parsed = client.tika.as_text.from_buffer(html, "text/html")
-
-                if parsed.content is not None:
-                    return parsed.content.strip()
-                return ""
-        except Exception as err:
-            raise ParseError(
-                f"Could not parse content with tika server at "
-                f"{settings.TIKA_ENDPOINT}: {err}",
-            ) from err
-
-    def generate_pdf(
-        self,
-        mail_message: MailMessage,
-        pdf_layout: MailRule.PdfLayout | None = None,
-    ) -> Path:
-        archive_path = Path(self.tempdir) / "merged.pdf"
-
-        mail_pdf_file = self.generate_pdf_from_mail(mail_message)
-
-        pdf_layout = (
-            pdf_layout or settings.EMAIL_PARSE_DEFAULT_LAYOUT
-        )  # EMAIL_PARSE_DEFAULT_LAYOUT is a MailRule.PdfLayout
-
-        # If no HTML content, create the PDF from the message
-        # Otherwise, create 2 PDFs and merge them with Gotenberg
-        if not mail_message.html:
-            archive_path.write_bytes(mail_pdf_file.read_bytes())
-        else:
-            pdf_of_html_content = self.generate_pdf_from_html(
-                mail_message.html,
-                mail_message.attachments,
-            )
-
-            self.log.debug("Merging email text and HTML content into single PDF")
-
-            with (
-                GotenbergClient(
-                    host=settings.TIKA_GOTENBERG_ENDPOINT,
-                    timeout=settings.CELERY_TASK_TIME_LIMIT,
-                ) as client,
-                client.merge.merge() as route,
-            ):
-                # Configure requested PDF/A formatting, if any
-                pdf_a_format = self._settings_to_gotenberg_pdfa()
-                if pdf_a_format is not None:
-                    route.pdf_format(pdf_a_format)
-
-                match pdf_layout:
-                    case MailRule.PdfLayout.HTML_TEXT:
-                        route.merge([pdf_of_html_content, mail_pdf_file])
-                    case MailRule.PdfLayout.HTML_ONLY:
-                        route.merge([pdf_of_html_content])
-                    case MailRule.PdfLayout.TEXT_ONLY:
-                        route.merge([mail_pdf_file])
-                    case MailRule.PdfLayout.TEXT_HTML | _:
-                        route.merge([mail_pdf_file, pdf_of_html_content])
-
-                try:
-                    response = route.run()
-                    archive_path.write_bytes(response.content)
-                except Exception as err:
-                    raise ParseError(
-                        f"Error while merging email HTML into PDF: {err}",
-                    ) from err
-
-        return archive_path
-
-    def mail_to_html(self, mail: MailMessage) -> Path:
-        """
-        Converts the given email into an HTML file, formatted
-        based on the given template
-        """
-
-        def clean_html(text: str) -> str:
-            """
-            Attempts to clean, escape and linkify the given HTML string
-            """
-            if isinstance(text, list):
-                text = "\n".join([str(e) for e in text])
-            if not isinstance(text, str):
-                text = str(text)
-            text = escape(text)
-            text = clean(text)
-            text = linkify(text, parse_email=True)
-            text = text.replace("\n", "<br>")
-            return text
-
-        data = {}
-
-        data["subject"] = clean_html(mail.subject)
-        if data["subject"]:
-            data["subject_label"] = "Subject"
-        data["from"] = clean_html(mail.from_values.full)
-        if data["from"]:
-            data["from_label"] = "From"
-        data["to"] = clean_html(", ".join(address.full for address in mail.to_values))
-        if data["to"]:
-            data["to_label"] = "To"
-        data["cc"] = clean_html(", ".join(address.full for address in mail.cc_values))
-        if data["cc"]:
-            data["cc_label"] = "CC"
-        data["bcc"] = clean_html(", ".join(address.full for address in mail.bcc_values))
-        if data["bcc"]:
-            data["bcc_label"] = "BCC"
-
-        att = []
-        for a in mail.attachments:
-            att.append(
-                f"{a.filename} ({naturalsize(a.size, binary=True, format='%.2f')})",
-            )
-        data["attachments"] = clean_html(", ".join(att))
-        if data["attachments"]:
-            data["attachments_label"] = "Attachments"
-
-        data["date"] = clean_html(
-            timezone.localtime(mail.date).strftime("%Y-%m-%d %H:%M"),
-        )
-        data["content"] = clean_html(mail.text.strip())
-
-        from django.template.loader import render_to_string
-
-        html_file = Path(self.tempdir) / "email_as_html.html"
-        html_file.write_text(render_to_string("email_msg_template.html", context=data))
-
-        return html_file
-
-    def generate_pdf_from_mail(self, mail: MailMessage) -> Path:
-        """
-        Creates a PDF based on the given email, using the email's values in a
-        an HTML template
-        """
-        self.log.info("Converting mail to PDF")
-
-        css_file = Path(__file__).parent / "templates" / "output.css"
-        email_html_file = self.mail_to_html(mail)
-
-        with (
-            GotenbergClient(
-                host=settings.TIKA_GOTENBERG_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ) as client,
-            client.chromium.html_to_pdf() as route,
-        ):
-            # Configure requested PDF/A formatting, if any
-            pdf_a_format = self._settings_to_gotenberg_pdfa()
-            if pdf_a_format is not None:
-                route.pdf_format(pdf_a_format)
-
-            try:
-                response = (
-                    route.index(email_html_file)
-                    .resource(css_file)
-                    .margins(
-                        PageMarginsType(
-                            top=Measurement(0.1, MeasurementUnitType.Inches),
-                            bottom=Measurement(0.1, MeasurementUnitType.Inches),
-                            left=Measurement(0.1, MeasurementUnitType.Inches),
-                            right=Measurement(0.1, MeasurementUnitType.Inches),
-                        ),
-                    )
-                    .size(A4)
-                    .scale(1.0)
-                    .run()
-                )
-            except Exception as err:
-                raise ParseError(
-                    f"Error while converting email to PDF: {err}",
-                ) from err
-
-        email_as_pdf_file = Path(self.tempdir) / "email_as_pdf.pdf"
-        email_as_pdf_file.write_bytes(response.content)
-
-        return email_as_pdf_file
-
-    def generate_pdf_from_html(
-        self,
-        orig_html: str,
-        attachments: list[MailAttachment],
-    ) -> Path:
-        """
-        Generates a PDF file based on the HTML and attachments of the email
-        """
-
-        def clean_html_script(text: str):
-            compiled_open = re.compile(re.escape("<script"), re.IGNORECASE)
-            text = compiled_open.sub("<div hidden ", text)
-
-            compiled_close = re.compile(re.escape("</script"), re.IGNORECASE)
-            text = compiled_close.sub("</div", text)
-            return text
-
-        self.log.info("Converting message html to PDF")
-
-        tempdir = Path(self.tempdir)
-
-        html_clean = clean_html_script(orig_html)
-        html_clean_file = tempdir / "index.html"
-        html_clean_file.write_text(html_clean)
-
-        with (
-            GotenbergClient(
-                host=settings.TIKA_GOTENBERG_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ) as client,
-            client.chromium.html_to_pdf() as route,
-        ):
-            # Configure requested PDF/A formatting, if any
-            pdf_a_format = self._settings_to_gotenberg_pdfa()
-            if pdf_a_format is not None:
-                route.pdf_format(pdf_a_format)
-
-            # Add attachments as resources, cleaning the filename and replacing
-            # it in the index file for inclusion
-            for attachment in attachments:
-                # Clean the attachment name to be valid
-                name_cid = f"cid:{attachment.content_id}"
-                name_clean = "".join(e for e in name_cid if e.isalnum())
-
-                # Write attachment payload to a temp file
-                temp_file = tempdir / name_clean
-                temp_file.write_bytes(attachment.payload)
-
-                route.resource(temp_file)
-
-                # Replace as needed the name with the clean name
-                html_clean = html_clean.replace(name_cid, name_clean)
-
-            # Now store the cleaned up HTML version
-            html_clean_file = tempdir / "index.html"
-            html_clean_file.write_text(html_clean)
-            # This is our index file, the main page basically
-            route.index(html_clean_file)
-
-            # Set page size, margins
-            route.margins(
-                PageMarginsType(
-                    top=Measurement(0.1, MeasurementUnitType.Inches),
-                    bottom=Measurement(0.1, MeasurementUnitType.Inches),
-                    left=Measurement(0.1, MeasurementUnitType.Inches),
-                    right=Measurement(0.1, MeasurementUnitType.Inches),
-                ),
-            ).size(A4).scale(1.0)
-
-            try:
-                response = route.run()
-
-            except Exception as err:
-                raise ParseError(
-                    f"Error while converting document to PDF: {err}",
-                ) from err
-
-        html_pdf = tempdir / "html.pdf"
-        html_pdf.write_bytes(response.content)
-        return html_pdf
-
-    def get_settings(self) -> None:
-        """
-        This parser does not implement additional settings yet
-        """
-        return None

src/paperless_mail/signals.py

@@ -1,7 +1,12 @@
 def get_parser(*args, **kwargs):
-    from paperless_mail.parsers import MailDocumentParser
+    from paperless.parsers.mail import MailDocumentParser
 
-    return MailDocumentParser(*args, **kwargs)
+    # MailDocumentParser accepts no constructor args in the new-style protocol.
+    # Pop legacy args that arrive from the signal-based consumer path.
+    # Phase 4 will replace this signal path with the ParserRegistry.
+    kwargs.pop("logging_group", None)
+    kwargs.pop("progress_callback", None)
+    return MailDocumentParser()
 
 
 def mail_consumer_declaration(sender, **kwargs):

src/paperless_mail/tests/conftest.py

@@ -1,71 +1,9 @@
 from collections.abc import Generator
-from pathlib import Path
 
 import pytest
 
 from paperless_mail.mail import MailAccountHandler
 from paperless_mail.models import MailAccount
-from paperless_mail.parsers import MailDocumentParser
-
-
-@pytest.fixture(scope="session")
-def sample_dir() -> Path:
-    return (Path(__file__).parent / Path("samples")).resolve()
-
-
-@pytest.fixture(scope="session")
-def broken_email_file(sample_dir: Path) -> Path:
-    return sample_dir / "broken.eml"
-
-
-@pytest.fixture(scope="session")
-def simple_txt_email_file(sample_dir: Path) -> Path:
-    return sample_dir / "simple_text.eml"
-
-
-@pytest.fixture(scope="session")
-def simple_txt_email_pdf_file(sample_dir: Path) -> Path:
-    return sample_dir / "simple_text.eml.pdf"
-
-
-@pytest.fixture(scope="session")
-def simple_txt_email_thumbnail_file(sample_dir: Path) -> Path:
-    return sample_dir / "simple_text.eml.pdf.webp"
-
-
-@pytest.fixture(scope="session")
-def html_email_file(sample_dir: Path) -> Path:
-    return sample_dir / "html.eml"
-
-
-@pytest.fixture(scope="session")
-def html_email_pdf_file(sample_dir: Path) -> Path:
-    return sample_dir / "html.eml.pdf"
-
-
-@pytest.fixture(scope="session")
-def html_email_thumbnail_file(sample_dir: Path) -> Path:
-    return sample_dir / "html.eml.pdf.webp"
-
-
-@pytest.fixture(scope="session")
-def html_email_html_file(sample_dir: Path) -> Path:
-    return sample_dir / "html.eml.html"
-
-
-@pytest.fixture(scope="session")
-def merged_pdf_first(sample_dir: Path) -> Path:
-    return sample_dir / "first.pdf"
-
-
-@pytest.fixture(scope="session")
-def merged_pdf_second(sample_dir: Path) -> Path:
-    return sample_dir / "second.pdf"
-
-
-@pytest.fixture()
-def mail_parser() -> MailDocumentParser:
-    return MailDocumentParser(logging_group=None)
 
 
 @pytest.fixture()
@@ -89,11 +27,3 @@ def greenmail_mail_account(db: None) -> Generator[MailAccount, None, None]:
 @pytest.fixture()
 def mail_account_handler() -> MailAccountHandler:
     return MailAccountHandler()
-
-
-@pytest.fixture(scope="session")
-def nginx_base_url() -> Generator[str, None, None]:
-    """
-    The base URL for the nginx HTTP server we expect to be alive
-    """
-    yield "http://localhost:8080"

src/paperless_mail/tests/test_mail_oauth.py

@@ -1,7 +1,6 @@
 from datetime import timedelta
 from unittest import mock
 
-from django.conf import settings
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
 from django.test import TestCase
@@ -16,6 +15,13 @@ from paperless_mail.models import MailAccount
 from paperless_mail.oauth import PaperlessMailOAuth2Manager
 
 
+@override_settings(
+    OAUTH_CALLBACK_BASE_URL="http://localhost:8000",
+    GMAIL_OAUTH_CLIENT_ID="test_gmail_client_id",
+    GMAIL_OAUTH_CLIENT_SECRET="test_gmail_client_secret",
+    OUTLOOK_OAUTH_CLIENT_ID="test_outlook_client_id",
+    OUTLOOK_OAUTH_CLIENT_SECRET="test_outlook_client_secret",
+)
 class TestMailOAuth(
     TestCase,
 ):
@@ -31,12 +37,6 @@ class TestMailOAuth(
         self.user.save()
         self.client.force_login(self.user)
         self.mail_account_handler = MailAccountHandler()
-        # Mock settings
-        settings.OAUTH_CALLBACK_BASE_URL = "http://localhost:8000"
-        settings.GMAIL_OAUTH_CLIENT_ID = "test_gmail_client_id"
-        settings.GMAIL_OAUTH_CLIENT_SECRET = "test_gmail_client_secret"
-        settings.OUTLOOK_OAUTH_CLIENT_ID = "test_outlook_client_id"
-        settings.OUTLOOK_OAUTH_CLIENT_SECRET = "test_outlook_client_secret"
         super().setUp()
 
     def test_generate_paths(self) -> None:

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/signals.py

@@ -1,10 +1,23 @@
-def get_parser(*args, **kwargs):
-    from paperless_tesseract.parsers import RasterisedDocumentParser
+from __future__ import annotations
 
+from typing import Any
+
+
+def get_parser(*args: Any, **kwargs: Any) -> Any:
+    from paperless.parsers.tesseract import RasterisedDocumentParser
+
+    # RasterisedDocumentParser accepts logging_group for constructor compatibility but
+    # does not store or use it (no legacy DocumentParser base class).
+    # progress_callback is also not used.  Both may arrive as a positional arg
+    # (consumer) or a keyword arg (views); *args absorbs the positional form,
+    # kwargs.pop handles the keyword form.  Phase 4 will replace this signal
+    # path with the new ParserRegistry so the shim can be removed at that point.
+    kwargs.pop("logging_group", None)
+    kwargs.pop("progress_callback", None)
     return RasterisedDocumentParser(*args, **kwargs)
 
 
-def tesseract_consumer_declaration(sender, **kwargs):
+def tesseract_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
     return {
         "parser": get_parser,
         "weight": 0,

src/paperless_tesseract/tests/test_parser.py

@@ -1,924 +0,0 @@
-import shutil
-import tempfile
-import unicodedata
-import uuid
-from pathlib import Path
-from unittest import mock
-
-from django.test import TestCase
-from django.test import override_settings
-from ocrmypdf import SubprocessOutputError
-
-from documents.parsers import ParseError
-from documents.parsers import run_convert
-from documents.tests.utils import DirectoriesMixin
-from documents.tests.utils import FileSystemAssertsMixin
-from paperless_tesseract.parsers import RasterisedDocumentParser
-from paperless_tesseract.parsers import post_process_text
-
-
-class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
-    SAMPLE_FILES = Path(__file__).resolve().parent / "samples"
-
-    def assertContainsStrings(self, content, strings) -> 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))
-
-    def test_post_process_text(self) -> None:
-        text_cases = [
-            ("simple     string", "simple string"),
-            ("simple    newline\n   testing string", "simple newline\ntesting string"),
-            (
-                "utf-8   строка с пробелами в конце  ",
-                "utf-8 строка с пробелами в конце",
-            ),
-        ]
-
-        for source, result in text_cases:
-            actual_result = post_process_text(source)
-            self.assertEqual(
-                result,
-                actual_result,
-                f"strip_exceess_whitespace({source}) != '{result}', but '{actual_result}'",
-            )
-
-    def test_get_text_from_pdf(self) -> None:
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        text = parser.extract_text(
-            None,
-            self.SAMPLE_FILES / "simple-digital.pdf",
-        )
-
-        self.assertContainsStrings(text.strip(), ["This is a test document."])
-
-    def test_get_page_count(self) -> None:
-        """
-        GIVEN:
-            - PDF file with a single page
-            - PDF file with multiple pages
-        WHEN:
-            - The number of pages is requested
-        THEN:
-            - The method returns 1 as the expected number of pages
-            - The method returns the correct number of pages (6)
-        """
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        page_count = parser.get_page_count(
-            str(self.SAMPLE_FILES / "simple-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertEqual(page_count, 1)
-
-        page_count = parser.get_page_count(
-            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
-            "application/pdf",
-        )
-        self.assertEqual(page_count, 6)
-
-    def test_get_page_count_password_protected(self) -> None:
-        """
-        GIVEN:
-            - Password protected PDF file
-        WHEN:
-            - The number of pages is requested
-        THEN:
-            - The method returns None
-        """
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        with self.assertLogs("paperless.parsing.tesseract", level="WARNING") as cm:
-            page_count = parser.get_page_count(
-                str(self.SAMPLE_FILES / "password-protected.pdf"),
-                "application/pdf",
-            )
-            self.assertEqual(page_count, None)
-            self.assertIn("Unable to determine PDF page count", cm.output[0])
-
-    def test_thumbnail(self) -> None:
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        thumb = parser.get_thumbnail(
-            str(self.SAMPLE_FILES / "simple-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(thumb)
-
-    @mock.patch("documents.parsers.run_convert")
-    def test_thumbnail_fallback(self, m) -> None:
-        def call_convert(input_file, output_file, **kwargs) -> None:
-            if ".pdf" in str(input_file):
-                raise ParseError("Does not compute.")
-            else:
-                run_convert(input_file=input_file, output_file=output_file, **kwargs)
-
-        m.side_effect = call_convert
-
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        thumb = parser.get_thumbnail(
-            str(self.SAMPLE_FILES / "simple-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(thumb)
-
-    def test_thumbnail_encrypted(self) -> None:
-        parser = RasterisedDocumentParser(uuid.uuid4())
-        thumb = parser.get_thumbnail(
-            str(self.SAMPLE_FILES / "encrypted.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(thumb)
-
-    def test_get_dpi(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        dpi = parser.get_dpi(str(self.SAMPLE_FILES / "simple-no-dpi.png"))
-        self.assertEqual(dpi, None)
-
-        dpi = parser.get_dpi(str(self.SAMPLE_FILES / "simple.png"))
-        self.assertEqual(dpi, 72)
-
-    def test_simple_digital(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "simple-digital.pdf"),
-            "application/pdf",
-        )
-
-        self.assertIsFile(parser.archive_path)
-
-        self.assertContainsStrings(parser.get_text(), ["This is a test document."])
-
-    def test_with_form(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "with-form.pdf"),
-            "application/pdf",
-        )
-
-        self.assertIsFile(parser.archive_path)
-
-        self.assertContainsStrings(
-            parser.get_text(),
-            ["Please enter your name in here:", "This is a PDF document with a form."],
-        )
-
-    @override_settings(OCR_MODE="redo")
-    def test_with_form_error(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "with-form.pdf"),
-            "application/pdf",
-        )
-
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text(),
-            ["Please enter your name in here:", "This is a PDF document with a form."],
-        )
-
-    @override_settings(OCR_MODE="skip")
-    def test_signed(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(str(self.SAMPLE_FILES / "signed.pdf"), "application/pdf")
-
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text(),
-            [
-                "This is a digitally signed PDF, created with Acrobat Pro for the Paperless project to enable",
-                "automated testing of signed/encrypted PDFs",
-            ],
-        )
-
-    @override_settings(OCR_MODE="skip")
-    def test_encrypted(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "encrypted.pdf"),
-            "application/pdf",
-        )
-
-        self.assertIsNone(parser.archive_path)
-        self.assertEqual(parser.get_text(), "")
-
-    @override_settings(OCR_MODE="redo")
-    def test_with_form_error_notext(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "with-form.pdf"),
-            "application/pdf",
-        )
-
-        self.assertContainsStrings(
-            parser.get_text(),
-            ["Please enter your name in here:", "This is a PDF document with a form."],
-        )
-
-    @override_settings(OCR_MODE="force")
-    def test_with_form_force(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "with-form.pdf"),
-            "application/pdf",
-        )
-
-        self.assertContainsStrings(
-            parser.get_text(),
-            ["Please enter your name in here:", "This is a PDF document with a form."],
-        )
-
-    def test_image_simple(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(str(self.SAMPLE_FILES / "simple.png"), "image/png")
-
-        self.assertIsFile(parser.archive_path)
-
-        self.assertContainsStrings(parser.get_text(), ["This is a test document."])
-
-    def test_image_simple_alpha(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        with tempfile.TemporaryDirectory() as tempdir:
-            # Copy sample file to temp directory, as the parsing changes the file
-            # and this makes it modified to Git
-            sample_file = self.SAMPLE_FILES / "simple-alpha.png"
-            dest_file = Path(tempdir) / "simple-alpha.png"
-            shutil.copy(sample_file, dest_file)
-
-            parser.parse(str(dest_file), "image/png")
-
-            self.assertIsFile(parser.archive_path)
-
-            self.assertContainsStrings(parser.get_text(), ["This is a test document."])
-
-    def test_image_calc_a4_dpi(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        dpi = parser.calculate_a4_dpi(
-            str(self.SAMPLE_FILES / "simple-no-dpi.png"),
-        )
-
-        self.assertEqual(dpi, 62)
-
-    @mock.patch("paperless_tesseract.parsers.RasterisedDocumentParser.calculate_a4_dpi")
-    def test_image_dpi_fail(self, m) -> None:
-        m.return_value = None
-        parser = RasterisedDocumentParser(None)
-
-        def f() -> None:
-            parser.parse(
-                str(self.SAMPLE_FILES / "simple-no-dpi.png"),
-                "image/png",
-            )
-
-        self.assertRaises(ParseError, f)
-
-    @override_settings(OCR_IMAGE_DPI=72, MAX_IMAGE_PIXELS=0)
-    def test_image_no_dpi_default(self) -> None:
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(str(self.SAMPLE_FILES / "simple-no-dpi.png"), "image/png")
-
-        self.assertIsFile(parser.archive_path)
-
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["this is a test document."],
-        )
-
-    def test_multi_page(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_PAGES=2, OCR_MODE="skip")
-    def test_multi_page_pages_skip(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_PAGES=2, OCR_MODE="redo")
-    def test_multi_page_pages_redo(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_PAGES=2, OCR_MODE="force")
-    def test_multi_page_pages_force(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_MODE="skip")
-    def test_multi_page_analog_pages_skip(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_PAGES=2, OCR_MODE="redo")
-    def test_multi_page_analog_pages_redo(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR of only pages 1 and 2 requested
-            - OCR mode set to redo
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text of page 1 and 2 extracted
-            - An archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(parser.get_text().lower(), ["page 1", "page 2"])
-        self.assertNotIn("page 3", parser.get_text().lower())
-
-    @override_settings(OCR_PAGES=1, OCR_MODE="force")
-    def test_multi_page_analog_pages_force(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR of only page 1 requested
-            - OCR mode set to force
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Only text of page 1 is extracted
-            - An archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(parser.get_text().lower(), ["page 1"])
-        self.assertNotIn("page 2", parser.get_text().lower())
-        self.assertNotIn("page 3", parser.get_text().lower())
-
-    @override_settings(OCR_MODE="skip_noarchive")
-    def test_skip_noarchive_withtext(self) -> None:
-        """
-        GIVEN:
-            - File with existing text layer
-            - OCR mode set to skip_noarchive
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - No archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_MODE="skip_noarchive")
-    def test_skip_noarchive_notext(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR mode set to skip_noarchive
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - An archive file is created with the OCRd text
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-        self.assertIsNotNone(parser.archive_path)
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="never")
-    def test_skip_archive_never_withtext(self) -> None:
-        """
-        GIVEN:
-            - File with existing text layer
-            - OCR_SKIP_ARCHIVE_FILE set to never
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from text layer is extracted
-            - Archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNotNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="never")
-    def test_skip_archive_never_withimages(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR_SKIP_ARCHIVE_FILE set to never
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - Archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNotNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="with_text")
-    def test_skip_archive_withtext_withtext(self) -> None:
-        """
-        GIVEN:
-            - File with existing text layer
-            - OCR_SKIP_ARCHIVE_FILE set to with_text
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from text layer is extracted
-            - No archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="with_text")
-    def test_skip_archive_withtext_withimages(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR_SKIP_ARCHIVE_FILE set to with_text
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - Archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNotNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="always")
-    def test_skip_archive_always_withtext(self) -> None:
-        """
-        GIVEN:
-            - File with existing text layer
-            - OCR_SKIP_ARCHIVE_FILE set to always
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from text layer is extracted
-            - No archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-digital.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_SKIP_ARCHIVE_FILE="always")
-    def test_skip_archive_always_withimages(self) -> None:
-        """
-        GIVEN:
-            - File with text contained in images but no text layer
-            - OCR_SKIP_ARCHIVE_FILE set to always
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - No archive file is created
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    @override_settings(OCR_MODE="skip")
-    def test_multi_page_mixed(self) -> None:
-        """
-        GIVEN:
-            - File with some text contained in images and some in text layer
-            - OCR mode set to skip
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - An archive file is created with the OCRd text and the original text
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNotNone(parser.archive_path)
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3", "page 4", "page 5", "page 6"],
-        )
-
-        with (parser.tempdir / "sidecar.txt").open() as f:
-            sidecar = f.read()
-
-        self.assertIn("[OCR skipped on page(s) 4-6]", sidecar)
-
-    @override_settings(OCR_MODE="redo")
-    def test_single_page_mixed(self) -> None:
-        """
-        GIVEN:
-            - File with some text contained in images and some in text layer
-            - Text and images are mixed on the same page
-            - OCR mode set to redo
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - Full content of the file is parsed (not just the image text)
-            - An archive file is created with the OCRd text and the original text
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "single-page-mixed.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNotNone(parser.archive_path)
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            [
-                "this is some normal text, present on page 1 of the document.",
-                "this is some text, but in an image, also on page 1.",
-                "this is further text on page 1.",
-            ],
-        )
-
-        with (parser.tempdir / "sidecar.txt").open() as f:
-            sidecar = f.read().lower()
-
-        self.assertIn("this is some text, but in an image, also on page 1.", sidecar)
-        self.assertNotIn(
-            "this is some normal text, present on page 1 of the document.",
-            sidecar,
-        )
-
-    @override_settings(OCR_MODE="skip_noarchive")
-    def test_multi_page_mixed_no_archive(self) -> None:
-        """
-        GIVEN:
-            - File with some text contained in images and some in text layer
-            - OCR mode set to skip_noarchive
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from images is extracted
-            - No archive file is created as original file contains text
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-mixed.pdf"),
-            "application/pdf",
-        )
-        self.assertIsNone(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 4", "page 5", "page 6"],
-        )
-
-    @override_settings(OCR_MODE="skip", OCR_ROTATE_PAGES=True)
-    def test_rotate(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "rotated.pdf"), "application/pdf")
-        self.assertContainsStrings(
-            parser.get_text(),
-            [
-                "This is the text that appears on the first page. It’s a lot of text.",
-                "Even if the pages are rotated, OCRmyPDF still gets the job done.",
-                "This is a really weird file with lots of nonsense text.",
-                "If you read this, it’s your own fault. Also check your screen orientation.",
-            ],
-        )
-
-    def test_multi_page_tiff(self) -> None:
-        """
-        GIVEN:
-            - Multi-page TIFF image
-        WHEN:
-            - Image is parsed
-        THEN:
-            - Text from all pages extracted
-        """
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "multi-page-images.tiff"),
-            "image/tiff",
-        )
-        self.assertIsFile(parser.archive_path)
-        self.assertContainsStrings(
-            parser.get_text().lower(),
-            ["page 1", "page 2", "page 3"],
-        )
-
-    def test_multi_page_tiff_alpha(self) -> None:
-        """
-        GIVEN:
-            - Multi-page TIFF image
-            - Image include an alpha channel
-        WHEN:
-            - Image is parsed
-        THEN:
-            - Text from all pages extracted
-        """
-        parser = RasterisedDocumentParser(None)
-        sample_file = self.SAMPLE_FILES / "multi-page-images-alpha.tiff"
-        with tempfile.NamedTemporaryFile() as tmp_file:
-            shutil.copy(sample_file, tmp_file.name)
-            parser.parse(
-                tmp_file.name,
-                "image/tiff",
-            )
-            self.assertIsFile(parser.archive_path)
-            self.assertContainsStrings(
-                parser.get_text().lower(),
-                ["page 1", "page 2", "page 3"],
-            )
-
-    def test_multi_page_tiff_alpha_srgb(self) -> None:
-        """
-        GIVEN:
-            - Multi-page TIFF image
-            - Image include an alpha channel
-            - Image is srgb colorspace
-        WHEN:
-            - Image is parsed
-        THEN:
-            - Text from all pages extracted
-        """
-        parser = RasterisedDocumentParser(None)
-        sample_file = str(
-            self.SAMPLE_FILES / "multi-page-images-alpha-rgb.tiff",
-        )
-        with tempfile.NamedTemporaryFile() as tmp_file:
-            shutil.copy(sample_file, tmp_file.name)
-            parser.parse(
-                tmp_file.name,
-                "image/tiff",
-            )
-            self.assertIsFile(parser.archive_path)
-            self.assertContainsStrings(
-                parser.get_text().lower(),
-                ["page 1", "page 2", "page 3"],
-            )
-
-    def test_ocrmypdf_parameters(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        params = parser.construct_ocrmypdf_parameters(
-            input_file="input.pdf",
-            output_file="output.pdf",
-            sidecar_file="sidecar.txt",
-            mime_type="application/pdf",
-            safe_fallback=False,
-        )
-
-        self.assertEqual(params["input_file_or_options"], "input.pdf")
-        self.assertEqual(params["output_file"], "output.pdf")
-        self.assertEqual(params["sidecar"], "sidecar.txt")
-
-        with override_settings(OCR_CLEAN="none"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertNotIn("clean", params)
-            self.assertNotIn("clean_final", params)
-
-        with override_settings(OCR_CLEAN="clean"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertTrue(params["clean"])
-            self.assertNotIn("clean_final", params)
-
-        with override_settings(OCR_CLEAN="clean-final", OCR_MODE="skip"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertTrue(params["clean_final"])
-            self.assertNotIn("clean", params)
-
-        with override_settings(OCR_CLEAN="clean-final", OCR_MODE="redo"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertTrue(params["clean"])
-            self.assertNotIn("clean_final", params)
-
-        with override_settings(OCR_DESKEW=True, OCR_MODE="skip"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertTrue(params["deskew"])
-
-        with override_settings(OCR_DESKEW=True, OCR_MODE="redo"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertNotIn("deskew", params)
-
-        with override_settings(OCR_DESKEW=False, OCR_MODE="skip"):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertNotIn("deskew", params)
-
-        with override_settings(OCR_MAX_IMAGE_PIXELS=1_000_001.0):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertIn("max_image_mpixels", params)
-            self.assertAlmostEqual(params["max_image_mpixels"], 1, places=4)
-
-        with override_settings(OCR_MAX_IMAGE_PIXELS=-1_000_001.0):
-            parser = RasterisedDocumentParser(None)
-            params = parser.construct_ocrmypdf_parameters("", "", "", "")
-            self.assertNotIn("max_image_mpixels", params)
-
-    def test_rtl_language_detection(self) -> None:
-        """
-        GIVEN:
-            - File with text in an RTL language
-        WHEN:
-            - Document is parsed
-        THEN:
-            - Text from the document is extracted
-        """
-        parser = RasterisedDocumentParser(None)
-
-        parser.parse(
-            str(self.SAMPLE_FILES / "rtl-test.pdf"),
-            "application/pdf",
-        )
-
-        # OCR output for RTL text varies across platforms/versions due to
-        # bidi controls and presentation forms; normalize before assertion.
-        normalized_text = "".join(
-            char
-            for char in unicodedata.normalize("NFKC", parser.get_text())
-            if unicodedata.category(char) != "Cf" and not char.isspace()
-        )
-
-        self.assertIn("ةرازو", normalized_text)
-        self.assertTrue(
-            any(token in normalized_text for token in ("ةیلخادلا", "الاخليد")),
-        )
-
-    @mock.patch("ocrmypdf.ocr")
-    def test_gs_rendering_error(self, m) -> None:
-        m.side_effect = SubprocessOutputError("Ghostscript PDF/A rendering failed")
-        parser = RasterisedDocumentParser(None)
-
-        self.assertRaises(
-            ParseError,
-            parser.parse,
-            str(self.SAMPLE_FILES / "simple-digital.pdf"),
-            "application/pdf",
-        )
-
-
-class TestParserFileTypes(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
-    SAMPLE_FILES = Path(__file__).parent / "samples"
-
-    def test_bmp(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "simple.bmp"), "image/bmp")
-        self.assertIsFile(parser.archive_path)
-        self.assertIn("this is a test document", parser.get_text().lower())
-
-    def test_jpg(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "simple.jpg"), "image/jpeg")
-        self.assertIsFile(parser.archive_path)
-        self.assertIn("this is a test document", parser.get_text().lower())
-
-    def test_heic(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "simple.heic"), "image/heic")
-        self.assertIsFile(parser.archive_path)
-        self.assertIn("pizza", parser.get_text().lower())
-
-    @override_settings(OCR_IMAGE_DPI=200)
-    def test_gif(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "simple.gif"), "image/gif")
-        self.assertIsFile(parser.archive_path)
-        self.assertIn("this is a test document", parser.get_text().lower())
-
-    def test_tiff(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(str(self.SAMPLE_FILES / "simple.tif"), "image/tiff")
-        self.assertIsFile(parser.archive_path)
-        self.assertIn("this is a test document", parser.get_text().lower())
-
-    @override_settings(OCR_IMAGE_DPI=72)
-    def test_webp(self) -> None:
-        parser = RasterisedDocumentParser(None)
-        parser.parse(
-            str(self.SAMPLE_FILES / "document.webp"),
-            "image/webp",
-        )
-        self.assertIsFile(parser.archive_path)
-        # Older tesseracts consistently mangle the space between "a webp",
-        # tesseract 5.3.0 seems to do a better job, so we're accepting both
-        self.assertRegex(
-            parser.get_text().lower(),
-            r"this is a ?webp document, created 11/14/2022.",
-        )

src/paperless_text/signals.py

@@ -1,16 +1,23 @@
-def get_parser(*args, **kwargs):
+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 legacy logging_group /
-    # progress_callback kwargs injected by the old signal-based consumer.
-    # These are dropped here; Phase 4 will replace this signal path with the
-    # new ParserRegistry so the shim can be removed at that point.
+    # TextDocumentParser accepts logging_group for constructor compatibility but
+    # does not store or use it (no legacy DocumentParser base class).
+    # progress_callback is also not used.  Both may arrive as a positional arg
+    # (consumer) or a keyword arg (views); *args absorbs the positional form,
+    # kwargs.pop handles the keyword form.  Phase 4 will replace this signal
+    # path with the new ParserRegistry so the shim can be removed at that point.
     kwargs.pop("logging_group", None)
     kwargs.pop("progress_callback", None)
-    return TextDocumentParser()
+    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_tika/parsers.py

@@ -1,136 +0,0 @@
-from pathlib import Path
-
-import httpx
-from django.conf import settings
-from django.utils import timezone
-from gotenberg_client import GotenbergClient
-from gotenberg_client.options import PdfAFormat
-from tika_client import TikaClient
-
-from documents.parsers import DocumentParser
-from documents.parsers import ParseError
-from documents.parsers import make_thumbnail_from_pdf
-from paperless.config import OutputTypeConfig
-from paperless.models import OutputTypeChoices
-
-
-class TikaDocumentParser(DocumentParser):
-    """
-    This parser sends documents to a local tika server
-    """
-
-    logging_name = "paperless.parsing.tika"
-
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        if not self.archive_path:
-            self.archive_path = self.convert_to_pdf(document_path, file_name)
-
-        return make_thumbnail_from_pdf(
-            self.archive_path,
-            self.tempdir,
-            self.logging_group,
-        )
-
-    def extract_metadata(self, document_path, mime_type):
-        try:
-            with TikaClient(
-                tika_url=settings.TIKA_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ) as client:
-                parsed = client.metadata.from_file(document_path, mime_type)
-                return [
-                    {
-                        "namespace": "",
-                        "prefix": "",
-                        "key": key,
-                        "value": parsed.data[key],
-                    }
-                    for key in parsed.data
-                ]
-        except Exception as e:
-            self.log.warning(
-                f"Error while fetching document metadata for {document_path}: {e}",
-            )
-            return []
-
-    def parse(self, document_path: Path, mime_type: str, file_name=None) -> None:
-        self.log.info(f"Sending {document_path} to Tika server")
-
-        try:
-            with TikaClient(
-                tika_url=settings.TIKA_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ) as client:
-                try:
-                    parsed = client.tika.as_text.from_file(document_path, mime_type)
-                except httpx.HTTPStatusError as err:
-                    # Workaround https://issues.apache.org/jira/browse/TIKA-4110
-                    # Tika fails with some files as multi-part form data
-                    if err.response.status_code == httpx.codes.INTERNAL_SERVER_ERROR:
-                        parsed = client.tika.as_text.from_buffer(
-                            document_path.read_bytes(),
-                            mime_type,
-                        )
-                    else:  # pragma: no cover
-                        raise
-        except Exception as err:
-            raise ParseError(
-                f"Could not parse {document_path} with tika server at "
-                f"{settings.TIKA_ENDPOINT}: {err}",
-            ) from err
-
-        self.text = parsed.content
-        if self.text is not None:
-            self.text = self.text.strip()
-
-        self.date = parsed.created
-        if self.date is not None and timezone.is_naive(self.date):
-            self.date = timezone.make_aware(self.date)
-
-        self.archive_path = self.convert_to_pdf(document_path, file_name)
-
-    def convert_to_pdf(self, document_path: Path, file_name):
-        pdf_path = Path(self.tempdir) / "convert.pdf"
-
-        self.log.info(f"Converting {document_path} to PDF as {pdf_path}")
-
-        with (
-            GotenbergClient(
-                host=settings.TIKA_GOTENBERG_ENDPOINT,
-                timeout=settings.CELERY_TASK_TIME_LIMIT,
-            ) as client,
-            client.libre_office.to_pdf() as route,
-        ):
-            # Set the output format of the resulting PDF
-            if settings.OCR_OUTPUT_TYPE in {
-                OutputTypeChoices.PDF_A,
-                OutputTypeChoices.PDF_A2,
-            }:
-                route.pdf_format(PdfAFormat.A2b)
-            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A1:
-                self.log.warning(
-                    "Gotenberg does not support PDF/A-1a, choosing PDF/A-2b instead",
-                )
-                route.pdf_format(PdfAFormat.A2b)
-            elif settings.OCR_OUTPUT_TYPE == OutputTypeChoices.PDF_A3:
-                route.pdf_format(PdfAFormat.A3b)
-
-            route.convert(document_path)
-
-            try:
-                response = route.run()
-
-                pdf_path.write_bytes(response.content)
-
-                return pdf_path
-
-            except Exception as err:
-                raise ParseError(
-                    f"Error while converting document to PDF: {err}",
-                ) from err
-
-    def get_settings(self) -> OutputTypeConfig:
-        """
-        This parser only uses the PDF output type configuration currently
-        """
-        return OutputTypeConfig()

src/paperless_tika/signals.py

@@ -1,7 +1,15 @@
 def get_parser(*args, **kwargs):
-    from paperless_tika.parsers import TikaDocumentParser
+    from paperless.parsers.tika import TikaDocumentParser
 
-    return TikaDocumentParser(*args, **kwargs)
+    # TikaDocumentParser accepts logging_group for constructor compatibility but
+    # does not store or use it (no legacy DocumentParser base class).
+    # progress_callback is also not used.  Both may arrive as a positional arg
+    # (consumer) or a keyword arg (views); *args absorbs the positional form,
+    # kwargs.pop handles the keyword form.  Phase 4 will replace this signal
+    # path with the new ParserRegistry so the shim can be removed at that point.
+    kwargs.pop("logging_group", None)
+    kwargs.pop("progress_callback", None)
+    return TikaDocumentParser()
 
 
 def tika_consumer_declaration(sender, **kwargs):

src/paperless_tika/tests/conftest.py

@@ -1,41 +0,0 @@
-from collections.abc import Generator
-from pathlib import Path
-
-import pytest
-
-from paperless_tika.parsers import TikaDocumentParser
-
-
-@pytest.fixture()
-def tika_parser() -> Generator[TikaDocumentParser, None, None]:
-    try:
-        parser = TikaDocumentParser(logging_group=None)
-        yield parser
-    finally:
-        # TODO(stumpylog): Cleanup once all parsers are handled
-        parser.cleanup()
-
-
-@pytest.fixture(scope="session")
-def sample_dir() -> Path:
-    return (Path(__file__).parent / Path("samples")).resolve()
-
-
-@pytest.fixture(scope="session")
-def sample_odt_file(sample_dir: Path) -> Path:
-    return sample_dir / "sample.odt"
-
-
-@pytest.fixture(scope="session")
-def sample_docx_file(sample_dir: Path) -> Path:
-    return sample_dir / "sample.docx"
-
-
-@pytest.fixture(scope="session")
-def sample_doc_file(sample_dir: Path) -> Path:
-    return sample_dir / "sample.doc"
-
-
-@pytest.fixture(scope="session")
-def sample_broken_odt(sample_dir: Path) -> Path:
-    return sample_dir / "multi-part-broken.odt"

uv.lock

@@ -897,15 +897,15 @@ wheels = [
 
 [[package]]
 name = "django-allauth"
-version = "65.14.1"
+version = "65.15.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "asgiref", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "django", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/fb/02/549b6f41ba3e55d4e2cf8e181cdf57b50035a3c0bdddb710a7df0b24efb0/django_allauth-65.14.1.tar.gz", hash = "sha256:2467656d0adc835607e407847054979ab5a943778f6eb8980ed2a29eee6c5790", size = 1993088, upload-time = "2026-02-07T22:36:52.279Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/84/c1/d3385f4c3169c1d6eea3c63aed0f36af51478c1d72e46db12bb1a08f8034/django_allauth-65.15.0.tar.gz", hash = "sha256:b404d48cf0c3ee14dacc834c541f30adedba2ff1c433980ecc494d6cb0b395a8", size = 2215709, upload-time = "2026-03-09T13:51:28.675Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/28/80/05e2b3fffb80260af2dbb179d186929d7531bc9331974ba774d1d8eb3e38/django_allauth-65.14.1-py3-none-any.whl", hash = "sha256:204d8a07f217c41769a62aa4c7ae7afeb2886c841bebda6964e613e5be72e8b3", size = 1793120, upload-time = "2026-02-07T22:37:03.486Z" },
+    { url = "https://files.pythonhosted.org/packages/75/b8/c8411339171bd8bc075c09ef190fb42195e9a2149e5c5026e094fe62fce0/django_allauth-65.15.0-py3-none-any.whl", hash = "sha256:ad9fc49c49a9368eaa5bb95456b76e2a4f377b3c6862ee8443507816578c098d", size = 2022994, upload-time = "2026-03-09T13:51:19.711Z" },
 ]
 
 [package.optional-dependencies]
@@ -2148,7 +2148,7 @@ wheels = [
 
 [[package]]
 name = "llama-index-core"
-version = "0.14.15"
+version = "0.14.16"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiohttp", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2180,9 +2180,9 @@ dependencies = [
     { name = "typing-inspect", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "wrapt", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/0c/4f/7c714bdf94dd229707b43e7f8cedf3aed0a99938fd46a9ad8a418c199988/llama_index_core-0.14.15.tar.gz", hash = "sha256:3766aeeb95921b3a2af8c2a51d844f75f404215336e1639098e3652db52c68ce", size = 11593505, upload-time = "2026-02-18T19:05:48.274Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/13/cb/1d7383f9f4520bb1d921c34f18c147b4b270007135212cedfa240edcd4c3/llama_index_core-0.14.16.tar.gz", hash = "sha256:cf2b7e4b798cb5ebad19c935174c200595c7ecff84a83793540cc27b03636a52", size = 11599715, upload-time = "2026-03-10T19:19:52.476Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/9e/262f6465ee4fffa40698b3cc2177e377ce7d945d3bd8b7d9c6b09448625d/llama_index_core-0.14.15-py3-none-any.whl", hash = "sha256:e02b321c10673871a38aaefdc4a93d5ae8ec324cad4408683189e5a1aa1e3d52", size = 11937002, upload-time = "2026-02-18T19:05:45.855Z" },
+    { url = "https://files.pythonhosted.org/packages/b4/f5/a33839bae0bd07e4030969bdba1ac90665e359ae88c56c296991ae16b8a8/llama_index_core-0.14.16-py3-none-any.whl", hash = "sha256:0cc273ebc44d51ad636217661a25f9cd02fb2d0440641430f105da3ae9f43a6b", size = 11944927, upload-time = "2026-03-10T19:19:48.043Z" },
 ]
 
 [[package]]
@@ -2821,7 +2821,7 @@ wheels = [
 
 [[package]]
 name = "openai"
-version = "2.24.0"
+version = "2.26.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "anyio", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2833,9 +2833,9 @@ dependencies = [
     { name = "tqdm", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/55/13/17e87641b89b74552ed408a92b231283786523edddc95f3545809fab673c/openai-2.24.0.tar.gz", hash = "sha256:1e5769f540dbd01cb33bc4716a23e67b9d695161a734aff9c5f925e2bf99a673", size = 658717, upload-time = "2026-02-24T20:02:07.958Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d7/91/2a06c4e9597c338cac1e5e5a8dd6f29e1836fc229c4c523529dca387fda8/openai-2.26.0.tar.gz", hash = "sha256:b41f37c140ae0034a6e92b0c509376d907f3a66109935fba2c1b471a7c05a8fb", size = 666702, upload-time = "2026-03-05T23:17:35.874Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/c9/30/844dc675ee6902579b8eef01ed23917cc9319a1c9c0c14ec6e39340c96d0/openai-2.24.0-py3-none-any.whl", hash = "sha256:fed30480d7d6c884303287bde864980a4b137b60553ffbcf9ab4a233b7a73d94", size = 1120122, upload-time = "2026-02-24T20:02:05.669Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/2e/3f73e8ca53718952222cacd0cf7eecc9db439d020f0c1fe7ae717e4e199a/openai-2.26.0-py3-none-any.whl", hash = "sha256:6151bf8f83802f036117f06cc8a57b3a4da60da9926826cc96747888b57f394f", size = 1136409, upload-time = "2026-03-05T23:17:34.072Z" },
 ]
 
 [[package]]
@@ -3008,7 +3008,7 @@ requires-dist = [
     { name = "concurrent-log-handler", specifier = "~=0.9.25" },
     { name = "dateparser", specifier = "~=1.2" },
     { name = "django", specifier = "~=5.2.10" },
-    { name = "django-allauth", extras = ["mfa", "socialaccount"], specifier = "~=65.14.0" },
+    { name = "django-allauth", extras = ["mfa", "socialaccount"], specifier = "~=65.15.0" },
     { name = "django-auditlog", specifier = "~=3.4.1" },
     { name = "django-cachalot", specifier = "~=2.9.0" },
     { name = "django-celery-results", specifier = "~=2.6.0" },
@@ -3548,11 +3548,11 @@ sdist = { url = "https://files.pythonhosted.org/packages/1d/c7/28220d37e041fe1df
 
 [[package]]
 name = "pyasn1"
-version = "0.6.2"
+version = "0.6.3"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fe/b6/6e630dff89739fcd427e3f72b3d905ce0acb85a45d4ec3e2678718a3487f/pyasn1-0.6.2.tar.gz", hash = "sha256:9b59a2b25ba7e4f8197db7686c09fb33e658b98339fadb826e9512629017833b", size = 146586, upload-time = "2026-01-16T18:04:18.534Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/5c/5f/6583902b6f79b399c9c40674ac384fd9cd77805f9e6205075f828ef11fb2/pyasn1-0.6.3.tar.gz", hash = "sha256:697a8ecd6d98891189184ca1fa05d1bb00e2f84b5977c481452050549c8a72cf", size = 148685, upload-time = "2026-03-17T01:06:53.382Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/44/b5/a96872e5184f354da9c84ae119971a0a4c221fe9b27a4d94bd43f2596727/pyasn1-0.6.2-py3-none-any.whl", hash = "sha256:1eb26d860996a18e9b6ed05e7aae0e9fc21619fcee6af91cca9bad4fbea224bf", size = 83371, upload-time = "2026-01-16T18:04:17.174Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/a0/7d793dce3fa811fe047d6ae2431c672364b462850c6235ae306c0efd025f/pyasn1-0.6.3-py3-none-any.whl", hash = "sha256:a80184d120f0864a52a073acc6fc642847d0be408e7c7252f31390c0f4eadcde", size = 83997, upload-time = "2026-03-17T01:06:52.036Z" },
 ]
 
 [[package]]
@@ -4754,11 +4754,11 @@ wheels = [
 
 [[package]]
 name = "tinytag"
-version = "2.2.0"
+version = "2.2.1"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/98/07/fb260bac73119f369a10e884016516d07cd760b5068e703773f83dd5e7bf/tinytag-2.2.0.tar.gz", hash = "sha256:f15b082510f6e0fc717e597edc8759d6f2d3ff6194ac0f3bcd675a9a09d9b798", size = 38120, upload-time = "2025-12-15T21:10:19.093Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/96/59/8a8cb2331e2602b53e4dc06960f57d1387a2b18e7efd24e5f9cb60ea4925/tinytag-2.2.1.tar.gz", hash = "sha256:e6d06610ebe7cd66fd07be2d3b9495914ab32654a5e47657bb8cd44c2484523c", size = 38214, upload-time = "2026-03-15T18:48:01.11Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b1/e2/9818fcebb348237389d2ac2fea97cf2b2638378a0866105a45ae9be49728/tinytag-2.2.0-py3-none-any.whl", hash = "sha256:d2cf3ef8ee0f6c854663f77d9d5f8159ee1c834c70f5ea4f214ddc4af8148f79", size = 32861, upload-time = "2025-12-15T21:10:17.63Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/34/d50e338631baaf65ec5396e70085e5de0b52b24b28db1ffbc1c6e82190dc/tinytag-2.2.1-py3-none-any.whl", hash = "sha256:ed8b1e6d25367937e3321e054f4974f9abfde1a3e0a538824c87da377130c2b6", size = 32927, upload-time = "2026-03-15T18:47:59.613Z" },
 ]
 
 [[package]]
@@ -5104,11 +5104,11 @@ wheels = [
 
 [[package]]
 name = "types-python-dateutil"
-version = "2.9.0.20260124"
+version = "2.9.0.20260305"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/fe/41/4f8eb1ce08688a9e3e23709ed07089ccdeaf95b93745bfb768c6da71197d/types_python_dateutil-2.9.0.20260124.tar.gz", hash = "sha256:7d2db9f860820c30e5b8152bfe78dbdf795f7d1c6176057424e8b3fdd1f581af", size = 16596, upload-time = "2026-01-24T03:18:42.975Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/1d/c7/025c624f347e10476b439a6619a95f1d200250ea88e7ccea6e09e48a7544/types_python_dateutil-2.9.0.20260305.tar.gz", hash = "sha256:389717c9f64d8f769f36d55a01873915b37e97e52ce21928198d210fbd393c8b", size = 16885, upload-time = "2026-03-05T04:00:47.409Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5a/c2/aa5e3f4103cc8b1dcf92432415dde75d70021d634ecfd95b2e913cf43e17/types_python_dateutil-2.9.0.20260124-py3-none-any.whl", hash = "sha256:f802977ae08bf2260142e7ca1ab9d4403772a254409f7bbdf652229997124951", size = 18266, upload-time = "2026-01-24T03:18:42.155Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/77/8c0d1ec97f0d9707ad3d8fa270ab8964e7b31b076d2f641c94987395cc75/types_python_dateutil-2.9.0.20260305-py3-none-any.whl", hash = "sha256:a3be9ca444d38cadabd756cfbb29780d8b338ae2a3020e73c266a83cc3025dd7", size = 18419, upload-time = "2026-03-05T04:00:46.392Z" },
 ]
 
 [[package]]
@@ -5252,55 +5252,59 @@ wheels = [
 
 [[package]]
 name = "ujson"
-version = "5.11.0"
+version = "5.12.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/43/d9/3f17e3c5773fb4941c68d9a37a47b1a79c9649d6c56aefbed87cc409d18a/ujson-5.11.0.tar.gz", hash = "sha256:e204ae6f909f099ba6b6b942131cee359ddda2b6e4ea39c12eb8b991fe2010e0", size = 7156583, upload-time = "2025-08-20T11:57:02.452Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/cb/3e/c35530c5ffc25b71c59ae0cd7b8f99df37313daa162ce1e2f7925f7c2877/ujson-5.12.0.tar.gz", hash = "sha256:14b2e1eb528d77bc0f4c5bd1a7ebc05e02b5b41beefb7e8567c9675b8b13bcf4", size = 7158451, upload-time = "2026-03-11T22:19:30.397Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/da/ea/80346b826349d60ca4d612a47cdf3533694e49b45e9d1c07071bb867a184/ujson-5.11.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:d7c46cb0fe5e7056b9acb748a4c35aa1b428025853032540bb7e41f46767321f", size = 55248, upload-time = "2025-08-20T11:55:19.033Z" },
-    { url = "https://files.pythonhosted.org/packages/57/df/b53e747562c89515e18156513cc7c8ced2e5e3fd6c654acaa8752ffd7cd9/ujson-5.11.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d8951bb7a505ab2a700e26f691bdfacf395bc7e3111e3416d325b513eea03a58", size = 53156, upload-time = "2025-08-20T11:55:20.174Z" },
-    { url = "https://files.pythonhosted.org/packages/41/b8/ab67ec8c01b8a3721fd13e5cb9d85ab2a6066a3a5e9148d661a6870d6293/ujson-5.11.0-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:952c0be400229940248c0f5356514123d428cba1946af6fa2bbd7503395fef26", size = 57657, upload-time = "2025-08-20T11:55:21.296Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/c7/fb84f27cd80a2c7e2d3c6012367aecade0da936790429801803fa8d4bffc/ujson-5.11.0-cp311-cp311-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:94fcae844f1e302f6f8095c5d1c45a2f0bfb928cccf9f1b99e3ace634b980a2a", size = 59779, upload-time = "2025-08-20T11:55:22.772Z" },
-    { url = "https://files.pythonhosted.org/packages/5d/7c/48706f7c1e917ecb97ddcfb7b1d756040b86ed38290e28579d63bd3fcc48/ujson-5.11.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7e0ec1646db172beb8d3df4c32a9d78015e671d2000af548252769e33079d9a6", size = 57284, upload-time = "2025-08-20T11:55:24.01Z" },
-    { url = "https://files.pythonhosted.org/packages/ec/ce/48877c6eb4afddfd6bd1db6be34456538c07ca2d6ed233d3f6c6efc2efe8/ujson-5.11.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:da473b23e3a54448b008d33f742bcd6d5fb2a897e42d1fc6e7bf306ea5d18b1b", size = 1036395, upload-time = "2025-08-20T11:55:25.725Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/7a/2c20dc97ad70cd7c31ad0596ba8e2cf8794d77191ba4d1e0bded69865477/ujson-5.11.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:aa6b3d4f1c0d3f82930f4cbd7fe46d905a4a9205a7c13279789c1263faf06dba", size = 1195731, upload-time = "2025-08-20T11:55:27.915Z" },
-    { url = "https://files.pythonhosted.org/packages/15/f5/ca454f2f6a2c840394b6f162fff2801450803f4ff56c7af8ce37640b8a2a/ujson-5.11.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:4843f3ab4fe1cc596bb7e02228ef4c25d35b4bb0809d6a260852a4bfcab37ba3", size = 1088710, upload-time = "2025-08-20T11:55:29.426Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/ef/a9cb1fce38f699123ff012161599fb9f2ff3f8d482b4b18c43a2dc35073f/ujson-5.11.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7895f0d2d53bd6aea11743bd56e3cb82d729980636cd0ed9b89418bf66591702", size = 55434, upload-time = "2025-08-20T11:55:34.987Z" },
-    { url = "https://files.pythonhosted.org/packages/b1/05/dba51a00eb30bd947791b173766cbed3492269c150a7771d2750000c965f/ujson-5.11.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:12b5e7e22a1fe01058000d1b317d3b65cc3daf61bd2ea7a2b76721fe160fa74d", size = 53190, upload-time = "2025-08-20T11:55:36.384Z" },
-    { url = "https://files.pythonhosted.org/packages/03/3c/fd11a224f73fbffa299fb9644e425f38b38b30231f7923a088dd513aabb4/ujson-5.11.0-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0180a480a7d099082501cad1fe85252e4d4bf926b40960fb3d9e87a3a6fbbc80", size = 57600, upload-time = "2025-08-20T11:55:37.692Z" },
-    { url = "https://files.pythonhosted.org/packages/55/b9/405103cae24899df688a3431c776e00528bd4799e7d68820e7ebcf824f92/ujson-5.11.0-cp312-cp312-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:fa79fdb47701942c2132a9dd2297a1a85941d966d8c87bfd9e29b0cf423f26cc", size = 59791, upload-time = "2025-08-20T11:55:38.877Z" },
-    { url = "https://files.pythonhosted.org/packages/17/7b/2dcbc2bbfdbf68f2368fb21ab0f6735e872290bb604c75f6e06b81edcb3f/ujson-5.11.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8254e858437c00f17cb72e7a644fc42dad0ebb21ea981b71df6e84b1072aaa7c", size = 57356, upload-time = "2025-08-20T11:55:40.036Z" },
-    { url = "https://files.pythonhosted.org/packages/d1/71/fea2ca18986a366c750767b694430d5ded6b20b6985fddca72f74af38a4c/ujson-5.11.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:1aa8a2ab482f09f6c10fba37112af5f957689a79ea598399c85009f2f29898b5", size = 1036313, upload-time = "2025-08-20T11:55:41.408Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/bb/d4220bd7532eac6288d8115db51710fa2d7d271250797b0bfba9f1e755af/ujson-5.11.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a638425d3c6eed0318df663df44480f4a40dc87cc7c6da44d221418312f6413b", size = 1195782, upload-time = "2025-08-20T11:55:43.357Z" },
-    { url = "https://files.pythonhosted.org/packages/80/47/226e540aa38878ce1194454385701d82df538ccb5ff8db2cf1641dde849a/ujson-5.11.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:7e3cff632c1d78023b15f7e3a81c3745cd3f94c044d1e8fa8efbd6b161997bbc", size = 1088817, upload-time = "2025-08-20T11:55:45.262Z" },
-    { url = "https://files.pythonhosted.org/packages/1c/ec/2de9dd371d52c377abc05d2b725645326c4562fc87296a8907c7bcdf2db7/ujson-5.11.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:109f59885041b14ee9569bf0bb3f98579c3fa0652317b355669939e5fc5ede53", size = 55435, upload-time = "2025-08-20T11:55:50.243Z" },
-    { url = "https://files.pythonhosted.org/packages/5b/a4/f611f816eac3a581d8a4372f6967c3ed41eddbae4008d1d77f223f1a4e0a/ujson-5.11.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a31c6b8004438e8c20fc55ac1c0e07dad42941db24176fe9acf2815971f8e752", size = 53193, upload-time = "2025-08-20T11:55:51.373Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/c5/c161940967184de96f5cbbbcce45b562a4bf851d60f4c677704b1770136d/ujson-5.11.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:78c684fb21255b9b90320ba7e199780f653e03f6c2528663768965f4126a5b50", size = 57603, upload-time = "2025-08-20T11:55:52.583Z" },
-    { url = "https://files.pythonhosted.org/packages/2b/d6/c7b2444238f5b2e2d0e3dab300b9ddc3606e4b1f0e4bed5a48157cebc792/ujson-5.11.0-cp313-cp313-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:4c9f5d6a27d035dd90a146f7761c2272cf7103de5127c9ab9c4cd39ea61e878a", size = 59794, upload-time = "2025-08-20T11:55:53.69Z" },
-    { url = "https://files.pythonhosted.org/packages/fe/a3/292551f936d3d02d9af148f53e1bc04306b00a7cf1fcbb86fa0d1c887242/ujson-5.11.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:837da4d27fed5fdc1b630bd18f519744b23a0b5ada1bbde1a36ba463f2900c03", size = 57363, upload-time = "2025-08-20T11:55:54.843Z" },
-    { url = "https://files.pythonhosted.org/packages/90/a6/82cfa70448831b1a9e73f882225980b5c689bf539ec6400b31656a60ea46/ujson-5.11.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:787aff4a84da301b7f3bac09bc696e2e5670df829c6f8ecf39916b4e7e24e701", size = 1036311, upload-time = "2025-08-20T11:55:56.197Z" },
-    { url = "https://files.pythonhosted.org/packages/84/5c/96e2266be50f21e9b27acaee8ca8f23ea0b85cb998c33d4f53147687839b/ujson-5.11.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:6dd703c3e86dc6f7044c5ac0b3ae079ed96bf297974598116aa5fb7f655c3a60", size = 1195783, upload-time = "2025-08-20T11:55:58.081Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/20/78abe3d808cf3bb3e76f71fca46cd208317bf461c905d79f0d26b9df20f1/ujson-5.11.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:3772e4fe6b0c1e025ba3c50841a0ca4786825a4894c8411bf8d3afe3a8061328", size = 1088822, upload-time = "2025-08-20T11:55:59.469Z" },
-    { url = "https://files.pythonhosted.org/packages/28/08/4518146f4984d112764b1dfa6fb7bad691c44a401adadaa5e23ccd930053/ujson-5.11.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:65724738c73645db88f70ba1f2e6fb678f913281804d5da2fd02c8c5839af302", size = 55462, upload-time = "2025-08-20T11:56:04.873Z" },
-    { url = "https://files.pythonhosted.org/packages/29/37/2107b9a62168867a692654d8766b81bd2fd1e1ba13e2ec90555861e02b0c/ujson-5.11.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:29113c003ca33ab71b1b480bde952fbab2a0b6b03a4ee4c3d71687cdcbd1a29d", size = 53246, upload-time = "2025-08-20T11:56:06.054Z" },
-    { url = "https://files.pythonhosted.org/packages/9b/f8/25583c70f83788edbe3ca62ce6c1b79eff465d78dec5eb2b2b56b3e98b33/ujson-5.11.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c44c703842024d796b4c78542a6fcd5c3cb948b9fc2a73ee65b9c86a22ee3638", size = 57631, upload-time = "2025-08-20T11:56:07.374Z" },
-    { url = "https://files.pythonhosted.org/packages/ed/ca/19b3a632933a09d696f10dc1b0dfa1d692e65ad507d12340116ce4f67967/ujson-5.11.0-cp314-cp314-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:e750c436fb90edf85585f5c62a35b35082502383840962c6983403d1bd96a02c", size = 59877, upload-time = "2025-08-20T11:56:08.534Z" },
-    { url = "https://files.pythonhosted.org/packages/55/7a/4572af5324ad4b2bfdd2321e898a527050290147b4ea337a79a0e4e87ec7/ujson-5.11.0-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:f278b31a7c52eb0947b2db55a5133fbc46b6f0ef49972cd1a80843b72e135aba", size = 57363, upload-time = "2025-08-20T11:56:09.758Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/71/a2b8c19cf4e1efe53cf439cdf7198ac60ae15471d2f1040b490c1f0f831f/ujson-5.11.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:ab2cb8351d976e788669c8281465d44d4e94413718af497b4e7342d7b2f78018", size = 1036394, upload-time = "2025-08-20T11:56:11.168Z" },
-    { url = "https://files.pythonhosted.org/packages/7a/3e/7b98668cba3bb3735929c31b999b374ebc02c19dfa98dfebaeeb5c8597ca/ujson-5.11.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:090b4d11b380ae25453100b722d0609d5051ffe98f80ec52853ccf8249dfd840", size = 1195837, upload-time = "2025-08-20T11:56:12.6Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/ea/8870f208c20b43571a5c409ebb2fe9b9dba5f494e9e60f9314ac01ea8f78/ujson-5.11.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:80017e870d882d5517d28995b62e4e518a894f932f1e242cbc802a2fd64d365c", size = 1088837, upload-time = "2025-08-20T11:56:14.15Z" },
-    { url = "https://files.pythonhosted.org/packages/6e/cd/e9809b064a89fe5c4184649adeb13c1b98652db3f8518980b04227358574/ujson-5.11.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:de6e88f62796372fba1de973c11138f197d3e0e1d80bcb2b8aae1e826096d433", size = 55759, upload-time = "2025-08-20T11:56:18.882Z" },
-    { url = "https://files.pythonhosted.org/packages/1b/be/ae26a6321179ebbb3a2e2685b9007c71bcda41ad7a77bbbe164005e956fc/ujson-5.11.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:49e56ef8066f11b80d620985ae36869a3ff7e4b74c3b6129182ec5d1df0255f3", size = 53634, upload-time = "2025-08-20T11:56:20.012Z" },
-    { url = "https://files.pythonhosted.org/packages/ae/e9/fb4a220ee6939db099f4cfeeae796ecb91e7584ad4d445d4ca7f994a9135/ujson-5.11.0-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1a325fd2c3a056cf6c8e023f74a0c478dd282a93141356ae7f16d5309f5ff823", size = 58547, upload-time = "2025-08-20T11:56:21.175Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/f8/fc4b952b8f5fea09ea3397a0bd0ad019e474b204cabcb947cead5d4d1ffc/ujson-5.11.0-cp314-cp314t-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:a0af6574fc1d9d53f4ff371f58c96673e6d988ed2b5bf666a6143c782fa007e9", size = 60489, upload-time = "2025-08-20T11:56:22.342Z" },
-    { url = "https://files.pythonhosted.org/packages/2e/e5/af5491dfda4f8b77e24cf3da68ee0d1552f99a13e5c622f4cef1380925c3/ujson-5.11.0-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:10f29e71ecf4ecd93a6610bd8efa8e7b6467454a363c3d6416db65de883eb076", size = 58035, upload-time = "2025-08-20T11:56:23.92Z" },
-    { url = "https://files.pythonhosted.org/packages/c4/09/0945349dd41f25cc8c38d78ace49f14c5052c5bbb7257d2f466fa7bdb533/ujson-5.11.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:1a0a9b76a89827a592656fe12e000cf4f12da9692f51a841a4a07aa4c7ecc41c", size = 1037212, upload-time = "2025-08-20T11:56:25.274Z" },
-    { url = "https://files.pythonhosted.org/packages/49/44/8e04496acb3d5a1cbee3a54828d9652f67a37523efa3d3b18a347339680a/ujson-5.11.0-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:b16930f6a0753cdc7d637b33b4e8f10d5e351e1fb83872ba6375f1e87be39746", size = 1196500, upload-time = "2025-08-20T11:56:27.517Z" },
-    { url = "https://files.pythonhosted.org/packages/64/ae/4bc825860d679a0f208a19af2f39206dfd804ace2403330fdc3170334a2f/ujson-5.11.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:04c41afc195fd477a59db3a84d5b83a871bd648ef371cf8c6f43072d89144eef", size = 1089487, upload-time = "2025-08-20T11:56:29.07Z" },
-    { url = "https://files.pythonhosted.org/packages/50/17/30275aa2933430d8c0c4ead951cc4fdb922f575a349aa0b48a6f35449e97/ujson-5.11.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:abae0fb58cc820092a0e9e8ba0051ac4583958495bfa5262a12f628249e3b362", size = 51206, upload-time = "2025-08-20T11:56:48.797Z" },
-    { url = "https://files.pythonhosted.org/packages/c3/15/42b3924258eac2551f8f33fa4e35da20a06a53857ccf3d4deb5e5d7c0b6c/ujson-5.11.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:fac6c0649d6b7c3682a0a6e18d3de6857977378dce8d419f57a0b20e3d775b39", size = 48907, upload-time = "2025-08-20T11:56:50.136Z" },
-    { url = "https://files.pythonhosted.org/packages/94/7e/0519ff7955aba581d1fe1fb1ca0e452471250455d182f686db5ac9e46119/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4b42c115c7c6012506e8168315150d1e3f76e7ba0f4f95616f4ee599a1372bbc", size = 50319, upload-time = "2025-08-20T11:56:51.63Z" },
-    { url = "https://files.pythonhosted.org/packages/74/cf/209d90506b7d6c5873f82c5a226d7aad1a1da153364e9ebf61eff0740c33/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:86baf341d90b566d61a394869ce77188cc8668f76d7bb2c311d77a00f4bdf844", size = 56584, upload-time = "2025-08-20T11:56:52.89Z" },
-    { url = "https://files.pythonhosted.org/packages/e9/97/bd939bb76943cb0e1d2b692d7e68629f51c711ef60425fa5bb6968037ecd/ujson-5.11.0-pp311-pypy311_pp73-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4598bf3965fc1a936bd84034312bcbe00ba87880ef1ee33e33c1e88f2c398b49", size = 51588, upload-time = "2025-08-20T11:56:54.054Z" },
+    { url = "https://files.pythonhosted.org/packages/10/22/fd22e2f6766bae934d3050517ca47d463016bd8688508d1ecc1baa18a7ad/ujson-5.12.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:58a11cb49482f1a095a2bd9a1d81dd7c8fb5d2357f959ece85db4e46a825fd00", size = 56139, upload-time = "2026-03-11T22:18:04.591Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/fd/6839adff4fc0164cbcecafa2857ba08a6eaeedd7e098d6713cb899a91383/ujson-5.12.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:9b3cf13facf6f77c283af0e1713e5e8c47a0fe295af81326cb3cb4380212e797", size = 53836, upload-time = "2026-03-11T22:18:05.662Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/b0/0c19faac62d68ceeffa83a08dc3d71b8462cf5064d0e7e0b15ba19898dad/ujson-5.12.0-cp311-cp311-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fb94245a715b4d6e24689de12772b85329a1f9946cbf6187923a64ecdea39e65", size = 57851, upload-time = "2026-03-11T22:18:06.744Z" },
+    { url = "https://files.pythonhosted.org/packages/04/f6/e7fd283788de73b86e99e08256726bb385923249c21dcd306e59d532a1a1/ujson-5.12.0-cp311-cp311-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:0fe6b8b8968e11dd9b2348bd508f0f57cf49ab3512064b36bc4117328218718e", size = 59906, upload-time = "2026-03-11T22:18:07.791Z" },
+    { url = "https://files.pythonhosted.org/packages/d7/3a/b100735a2b43ee6e8fe4c883768e362f53576f964d4ea841991060aeaf35/ujson-5.12.0-cp311-cp311-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:89e302abd3749f6d6699691747969a5d85f7c73081d5ed7e2624c7bd9721a2ab", size = 57409, upload-time = "2026-03-11T22:18:08.79Z" },
+    { url = "https://files.pythonhosted.org/packages/5c/fa/f97cc20c99ca304662191b883ae13ae02912ca7244710016ba0cb8a5be34/ujson-5.12.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:0727363b05ab05ee737a28f6200dc4078bce6b0508e10bd8aab507995a15df61", size = 1037339, upload-time = "2026-03-11T22:18:10.424Z" },
+    { url = "https://files.pythonhosted.org/packages/10/7a/53ddeda0ffe1420db2f9999897b3cbb920fbcff1849d1f22b196d0f34785/ujson-5.12.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:b62cb9a7501e1f5c9ffe190485501349c33e8862dde4377df774e40b8166871f", size = 1196625, upload-time = "2026-03-11T22:18:11.82Z" },
+    { url = "https://files.pythonhosted.org/packages/0d/1a/4c64a6bef522e9baf195dd5be151bc815cd4896c50c6e2489599edcda85f/ujson-5.12.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:a6ec5bf6bc361f2f0f9644907a36ce527715b488988a8df534120e5c34eeda94", size = 1089669, upload-time = "2026-03-11T22:18:13.343Z" },
+    { url = "https://files.pythonhosted.org/packages/84/f6/ac763d2108d28f3a40bb3ae7d2fafab52ca31b36c2908a4ad02cd3ceba2a/ujson-5.12.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:09b4beff9cc91d445d5818632907b85fb06943b61cb346919ce202668bf6794a", size = 56326, upload-time = "2026-03-11T22:18:18.467Z" },
+    { url = "https://files.pythonhosted.org/packages/25/46/d0b3af64dcdc549f9996521c8be6d860ac843a18a190ffc8affeb7259687/ujson-5.12.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ca0c7ce828bb76ab78b3991904b477c2fd0f711d7815c252d1ef28ff9450b052", size = 53910, upload-time = "2026-03-11T22:18:19.502Z" },
+    { url = "https://files.pythonhosted.org/packages/9a/10/853c723bcabc3e9825a079019055fc99e71b85c6bae600607a2b9d31d18d/ujson-5.12.0-cp312-cp312-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a2d79c6635ccffcbfc1d5c045874ba36b594589be81d50d43472570bb8de9c57", size = 57754, upload-time = "2026-03-11T22:18:20.874Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/c6/6e024830d988f521f144ead641981c1f7a82c17ad1927c22de3242565f5c/ujson-5.12.0-cp312-cp312-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:7e07f6f644d2c44d53b7a320a084eef98063651912c1b9449b5f45fcbdc6ccd2", size = 59936, upload-time = "2026-03-11T22:18:21.924Z" },
+    { url = "https://files.pythonhosted.org/packages/34/c9/c5f236af5abe06b720b40b88819d00d10182d2247b1664e487b3ed9229cf/ujson-5.12.0-cp312-cp312-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:085b6ce182cdd6657481c7c4003a417e0655c4f6e58b76f26ee18f0ae21db827", size = 57463, upload-time = "2026-03-11T22:18:22.924Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/04/41342d9ef68e793a87d84e4531a150c2b682f3bcedfe59a7a5e3f73e9213/ujson-5.12.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:16b4fe9c97dc605f5e1887a9e1224287291e35c56cbc379f8aa44b6b7bcfe2bb", size = 1037239, upload-time = "2026-03-11T22:18:24.04Z" },
+    { url = "https://files.pythonhosted.org/packages/d4/81/dc2b7617d5812670d4ff4a42f6dd77926430ee52df0dedb2aec7990b2034/ujson-5.12.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:0d2e8db5ade3736a163906154ca686203acc7d1d30736cbf577c730d13653d84", size = 1196713, upload-time = "2026-03-11T22:18:25.391Z" },
+    { url = "https://files.pythonhosted.org/packages/b6/9c/80acff0504f92459ed69e80a176286e32ca0147ac6a8252cd0659aad3227/ujson-5.12.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:93bc91fdadcf046da37a214eaa714574e7e9b1913568e93bb09527b2ceb7f759", size = 1089742, upload-time = "2026-03-11T22:18:26.738Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/f1/0ef0eeab1db8493e1833c8b440fe32cf7538f7afa6e7f7c7e9f62cef464d/ujson-5.12.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:15d416440148f3e56b9b244fdaf8a09fcf5a72e4944b8e119f5bf60417a2bfc8", size = 56331, upload-time = "2026-03-11T22:18:31.539Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/2f/9159f6f399b3f572d20847a2b80d133e3a03c14712b0da4971a36879fb64/ujson-5.12.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:e0dd3676ea0837cd70ea1879765e9e9f6be063be0436de9b3ea4b775caf83654", size = 53910, upload-time = "2026-03-11T22:18:32.829Z" },
+    { url = "https://files.pythonhosted.org/packages/e5/a9/f96376818d71495d1a4be19a0ab6acf0cc01dd8826553734c3d4dac685b2/ujson-5.12.0-cp313-cp313-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7bbf05c38debc90d1a195b11340cc85cb43ab3e753dc47558a3a84a38cbc72da", size = 57757, upload-time = "2026-03-11T22:18:33.866Z" },
+    { url = "https://files.pythonhosted.org/packages/98/8d/dd4a151caac6fdcb77f024fbe7f09d465ebf347a628ed6dd581a0a7f6364/ujson-5.12.0-cp313-cp313-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:3c2f947e55d3c7cfe124dd4521ee481516f3007d13c6ad4bf6aeb722e190eb1b", size = 59940, upload-time = "2026-03-11T22:18:35.276Z" },
+    { url = "https://files.pythonhosted.org/packages/c7/17/0d36c2fee0a8d8dc37b011ccd5bbdcfaff8b8ec2bcfc5be998661cdc935b/ujson-5.12.0-cp313-cp313-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2ea6206043385343aff0b7da65cf73677f6f5e50de8f1c879e557f4298cac36a", size = 57465, upload-time = "2026-03-11T22:18:36.644Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/04/b0ee4a4b643a01ba398441da1e357480595edb37c6c94c508dbe0eb9eb60/ujson-5.12.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:bb349dbba57c76eec25e5917e07f35aabaf0a33b9e67fc13d188002500106487", size = 1037236, upload-time = "2026-03-11T22:18:37.743Z" },
+    { url = "https://files.pythonhosted.org/packages/2d/08/0e7780d0bbb48fe57ded91f550144bcc99c03b5360bf2886dd0dae0ea8f5/ujson-5.12.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:937794042342006f707837f38d721426b11b0774d327a2a45c0bd389eb750a87", size = 1196717, upload-time = "2026-03-11T22:18:39.101Z" },
+    { url = "https://files.pythonhosted.org/packages/ba/4c/e0e34107715bb4dd2d4dcc1ce244d2f074638837adf38aff85a37506efe4/ujson-5.12.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6ad57654570464eb1b040b5c353dee442608e06cff9102b8fcb105565a44c9ed", size = 1089748, upload-time = "2026-03-11T22:18:40.473Z" },
+    { url = "https://files.pythonhosted.org/packages/10/bd/9a8d693254bada62bfea75a507e014afcfdb6b9d047b6f8dd134bfefaf67/ujson-5.12.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:85833bca01aa5cae326ac759276dc175c5fa3f7b3733b7d543cf27f2df12d1ef", size = 56499, upload-time = "2026-03-11T22:18:45.431Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/2d/285a83df8176e18dcd675d1a4cff8f7620f003f30903ea43929406e98986/ujson-5.12.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:d22cad98c2a10bbf6aa083a8980db6ed90d4285a841c4de892890c2b28286ef9", size = 53998, upload-time = "2026-03-11T22:18:47.184Z" },
+    { url = "https://files.pythonhosted.org/packages/bf/8b/e2f09e16dabfa91f6a84555df34a4329fa7621e92ed054d170b9054b9bb2/ujson-5.12.0-cp314-cp314-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:99cc80facad240b0c2fb5a633044420878aac87a8e7c348b9486450cba93f27c", size = 57783, upload-time = "2026-03-11T22:18:48.271Z" },
+    { url = "https://files.pythonhosted.org/packages/68/fb/ba1d06f3658a0c36d0ab3869ec3914f202bad0a9bde92654e41516c7bb13/ujson-5.12.0-cp314-cp314-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:d1831c07bd4dce53c4b666fa846c7eba4b7c414f2e641a4585b7f50b72f502dc", size = 60011, upload-time = "2026-03-11T22:18:49.284Z" },
+    { url = "https://files.pythonhosted.org/packages/64/2b/3e322bf82d926d9857206cd5820438d78392d1f523dacecb8bd899952f73/ujson-5.12.0-cp314-cp314-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0e00cec383eab2406c9e006bd4edb55d284e94bb943fda558326048178d26961", size = 57465, upload-time = "2026-03-11T22:18:50.584Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/fd/af72d69603f9885e5136509a529a4f6d88bf652b457263ff96aefcd3ab7d/ujson-5.12.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:f19b3af31d02a2e79c5f9a6deaab0fb3c116456aeb9277d11720ad433de6dfc6", size = 1037275, upload-time = "2026-03-11T22:18:51.998Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/a7/a2411ec81aef7872578e56304c3e41b3a544a9809e95c8e1df46923fc40b/ujson-5.12.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:bacbd3c69862478cbe1c7ed4325caedec580d8acf31b8ee1b9a1e02a56295cad", size = 1196758, upload-time = "2026-03-11T22:18:53.548Z" },
+    { url = "https://files.pythonhosted.org/packages/ed/85/aa18ae175dd03a118555aa14304d4f466f9db61b924c97c6f84388ecacb1/ujson-5.12.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:94c5f1621cbcab83c03be46441f090b68b9f307b6c7ec44d4e3f6d5997383df4", size = 1089760, upload-time = "2026-03-11T22:18:55.336Z" },
+    { url = "https://files.pythonhosted.org/packages/c3/71/9b4dacb177d3509077e50497222d39eec04c8b41edb1471efc764d645237/ujson-5.12.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:7ddb08b3c2f9213df1f2e3eb2fbea4963d80ec0f8de21f0b59898e34f3b3d96d", size = 56845, upload-time = "2026-03-11T22:18:59.629Z" },
+    { url = "https://files.pythonhosted.org/packages/24/c2/8abffa3be1f3d605c4a62445fab232b3e7681512ce941c6b23014f404d36/ujson-5.12.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:0a3ae28f0b209be5af50b54ca3e2123a3de3a57d87b75f1e5aa3d7961e041983", size = 54463, upload-time = "2026-03-11T22:19:00.697Z" },
+    { url = "https://files.pythonhosted.org/packages/db/2e/60114a35d1d6796eb428f7affcba00a921831ff604a37d9142c3d8bbe5c5/ujson-5.12.0-cp314-cp314t-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d30ad4359413c8821cc7b3707f7ca38aa8bc852ba3b9c5a759ee2d7740157315", size = 58689, upload-time = "2026-03-11T22:19:01.739Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/ad/010925c2116c21ce119f9c2ff18d01f48a19ade3ff4c5795da03ce5829fc/ujson-5.12.0-cp314-cp314t-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:02f93da7a4115e24f886b04fd56df1ee8741c2ce4ea491b7ab3152f744ad8f8e", size = 60618, upload-time = "2026-03-11T22:19:03.101Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/74/db7f638bf20282b1dccf454386cbd483faaaed3cdbb9cb27e06f74bb109e/ujson-5.12.0-cp314-cp314t-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3ff4ede90ed771140caa7e1890de17431763a483c54b3c1f88bd30f0cc1affc0", size = 58151, upload-time = "2026-03-11T22:19:04.175Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/7e/3ebaecfa70a2e8ce623db8e21bd5cb05d42a5ef943bcbb3309d71b5de68d/ujson-5.12.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:a7bf9cc97f05048ac8f3e02cd58f0fe62b901453c24345bfde287f4305dcc31c", size = 1038117, upload-time = "2026-03-11T22:19:05.558Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/aa/e073eda7f0036c2973b28db7bb99faba17a932e7b52d801f9bb3e726271f/ujson-5.12.0-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:2324d9a0502317ffc35d38e153c1b2fa9610ae03775c9d0f8d0cca7b8572b04e", size = 1197434, upload-time = "2026-03-11T22:19:06.92Z" },
+    { url = "https://files.pythonhosted.org/packages/1c/01/b9a13f058fdd50c746b192c4447ca8d6352e696dcda912ccee10f032ff85/ujson-5.12.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:50524f4f6a1c839714dbaff5386a1afb245d2d5ec8213a01fbc99cea7307811e", size = 1090401, upload-time = "2026-03-11T22:19:08.383Z" },
+    { url = "https://files.pythonhosted.org/packages/95/3c/5ee154d505d1aad2debc4ba38b1a60ae1949b26cdb5fa070e85e320d6b64/ujson-5.12.0-graalpy312-graalpy250_312_native-macosx_10_13_x86_64.whl", hash = "sha256:bf85a00ac3b56a1e7a19c5be7b02b5180a0895ac4d3c234d717a55e86960691c", size = 54494, upload-time = "2026-03-11T22:19:13.035Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/b3/9496ec399ec921e434a93b340bd5052999030b7ac364be4cbe5365ac6b20/ujson-5.12.0-graalpy312-graalpy250_312_native-macosx_11_0_arm64.whl", hash = "sha256:64df53eef4ac857eb5816a56e2885ccf0d7dff6333c94065c93b39c51063e01d", size = 57999, upload-time = "2026-03-11T22:19:14.385Z" },
+    { url = "https://files.pythonhosted.org/packages/0e/da/e9ae98133336e7c0d50b43626c3f2327937cecfa354d844e02ac17379ed1/ujson-5.12.0-graalpy312-graalpy250_312_native-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6c0aed6a4439994c9666fb8a5b6c4eac94d4ef6ddc95f9b806a599ef83547e3b", size = 54518, upload-time = "2026-03-11T22:19:15.4Z" },
+    { url = "https://files.pythonhosted.org/packages/58/10/978d89dded6bb1558cd46ba78f4351198bd2346db8a8ee1a94119022ce40/ujson-5.12.0-graalpy312-graalpy250_312_native-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:efae5df7a8cc8bdb1037b0f786b044ce281081441df5418c3a0f0e1f86fe7bb3", size = 55736, upload-time = "2026-03-11T22:19:16.496Z" },
+    { url = "https://files.pythonhosted.org/packages/19/fa/f4a957dddb99bd68c8be91928c0b6fefa7aa8aafc92c93f5d1e8b32f6702/ujson-5.12.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:871c0e5102e47995b0e37e8df7819a894a6c3da0d097545cd1f9f1f7d7079927", size = 52145, upload-time = "2026-03-11T22:19:18.566Z" },
+    { url = "https://files.pythonhosted.org/packages/55/6e/50b5cf612de1ca06c7effdc5a5d7e815774dee85a5858f1882c425553b82/ujson-5.12.0-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:56ba3f7abbd6b0bb282a544dc38406d1a188d8bb9164f49fdb9c2fee62cb29da", size = 49577, upload-time = "2026-03-11T22:19:19.627Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/24/b6713fa9897774502cd4c2d6955bb4933349f7d84c3aa805531c382a4209/ujson-5.12.0-pp311-pypy311_pp73-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:9c5a52987a990eb1bae55f9000994f1afdb0326c154fb089992f839ab3c30688", size = 50807, upload-time = "2026-03-11T22:19:20.778Z" },
+    { url = "https://files.pythonhosted.org/packages/1f/b6/c0e0f7901180ef80d16f3a4bccb5dc8b01515a717336a62928963a07b80b/ujson-5.12.0-pp311-pypy311_pp73-manylinux_2_24_i686.manylinux_2_28_i686.whl", hash = "sha256:adf28d13a33f9d750fe7a78fb481cac298fa257d8863d8727b2ea4455ea41235", size = 56972, upload-time = "2026-03-11T22:19:21.84Z" },
+    { url = "https://files.pythonhosted.org/packages/02/a9/05d91b4295ea7239151eb08cf240e5a2ba969012fda50bc27bcb1ea9cd71/ujson-5.12.0-pp311-pypy311_pp73-manylinux_2_24_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:51acc750ec7a2df786cdc868fb16fa04abd6269a01d58cf59bafc57978773d8e", size = 52045, upload-time = "2026-03-11T22:19:22.879Z" },
 ]
 
 [[package]]
@@ -5639,7 +5643,7 @@ wheels = [
 
 [[package]]
 name = "zensical"
-version = "0.0.24"
+version = "0.0.26"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "click", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -5649,18 +5653,18 @@ dependencies = [
     { name = "pymdown-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pyyaml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/3b/96/9c6cbdd7b351d1023cdbbcf7872d4cb118b0334cfe5821b99e0dd18e3f00/zensical-0.0.24.tar.gz", hash = "sha256:b5d99e225329bf4f98c8022bdf0a0ee9588c2fada7b4df1b7b896fcc62b37ec3", size = 3840688, upload-time = "2026-02-26T09:43:44.557Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/d5/1f/0a0b1ce8e0553a9dabaedc736d0f34b11fc33d71ff46bce44d674996d41f/zensical-0.0.26.tar.gz", hash = "sha256:f4d9c8403df25fbb3d6dd9577122dc2f23c73a2d16ab778bb7d40370dd71e987", size = 3841473, upload-time = "2026-03-11T09:51:38.838Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8e/aa/b8201af30e376a67566f044a1c56210edac5ae923fd986a836d2cf593c9c/zensical-0.0.24-cp310-abi3-macosx_10_12_x86_64.whl", hash = "sha256:d390c5453a5541ca35d4f9e1796df942b6612c546e3153dd928236d3b758409a", size = 12263407, upload-time = "2026-02-26T09:43:14.716Z" },
-    { url = "https://files.pythonhosted.org/packages/78/8e/3d910214471ade604fd39b080db3696864acc23678b5b4b8475c7dbfd2ce/zensical-0.0.24-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:81ac072869cf4d280853765b2bfb688653da0dfb9408f3ab15aca96455ab8223", size = 12142610, upload-time = "2026-02-26T09:43:17.546Z" },
-    { url = "https://files.pythonhosted.org/packages/cf/d7/eb0983640aa0419ddf670298cfbcf8b75629b6484925429b857851e00784/zensical-0.0.24-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b5eb1dfa84cae8e960bfa2c6851d2bc8e9710c4c4c683bd3aaf23185f646ae46", size = 12508380, upload-time = "2026-02-26T09:43:20.114Z" },
-    { url = "https://files.pythonhosted.org/packages/a3/04/4405b9e6f937a75db19f0d875798a7eb70817d6a3bec2a2d289a2d5e8aea/zensical-0.0.24-cp310-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:57d7c9e589da99c1879a1c703e67c85eaa6be4661cdc6ce6534f7bb3575983f4", size = 12440807, upload-time = "2026-02-26T09:43:22.679Z" },
-    { url = "https://files.pythonhosted.org/packages/12/dc/a7ca2a4224b3072a2c2998b6611ad7fd4f8f131ceae7aa23238d97d26e22/zensical-0.0.24-cp310-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:42fcc121c3095734b078a95a0dae4d4924fb8fbf16bf730456146ad6cab48ad0", size = 12782727, upload-time = "2026-02-26T09:43:25.347Z" },
-    { url = "https://files.pythonhosted.org/packages/42/37/22f1727da356ed3fcbd31f68d4a477f15c232997c87e270cfffb927459ac/zensical-0.0.24-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:832d4a2a051b9f49561031a2986ace502326f82d9a401ddf125530d30025fdd4", size = 12547616, upload-time = "2026-02-26T09:43:28.031Z" },
-    { url = "https://files.pythonhosted.org/packages/6d/ff/c75ff111b8e12157901d00752beef9d691dbb5a034b6a77359972262416a/zensical-0.0.24-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:e5fea3bb61238dba9f930f52669db67b0c26be98e1c8386a05eb2b1e3cb875dc", size = 12684883, upload-time = "2026-02-26T09:43:30.642Z" },
-    { url = "https://files.pythonhosted.org/packages/b9/92/4f6ea066382e3d068d3cadbed99e9a71af25e46c84a403e0f747960472a2/zensical-0.0.24-cp310-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:75eef0428eec2958590633fdc82dc2a58af124879e29573aa7e153b662978073", size = 12713825, upload-time = "2026-02-26T09:43:33.273Z" },
-    { url = "https://files.pythonhosted.org/packages/bc/fb/bf735b19bce0034b1f3b8e1c50b2896ebbd0c5d92d462777e759e78bb083/zensical-0.0.24-cp310-abi3-musllinux_1_2_i686.whl", hash = "sha256:3c6b39659156394ff805b4831dac108c839483d9efa4c9b901eaa913efee1ac7", size = 12854318, upload-time = "2026-02-26T09:43:35.632Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/28/0ddab6c1237e3625e7763ff666806f31e5760bb36d18624135a6bb6e8643/zensical-0.0.24-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:9eef82865a18b3ca4c3cd13e245dff09a865d1da3c861e2fc86eaa9253a90f02", size = 12818270, upload-time = "2026-02-26T09:43:37.749Z" },
+    { url = "https://files.pythonhosted.org/packages/41/58/fa3d9538ff1ea8cf4a193edbf47254f374fa7983fcfa876bb4336d72c53a/zensical-0.0.26-cp310-abi3-macosx_10_12_x86_64.whl", hash = "sha256:7823b25afe7d36099253aa59d643abaac940f80fd015d4a37954210c87d3da56", size = 12263607, upload-time = "2026-03-11T09:50:49.202Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/6e/44a3b21bd3569b9cad203364d73a956768d28a879e4c2be91bd889f74d2c/zensical-0.0.26-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:c0254814382cdd3769bc7689180d09bf41de8879871dd736dc52d5f141e8ada7", size = 12144562, upload-time = "2026-03-11T09:50:53.685Z" },
+    { url = "https://files.pythonhosted.org/packages/07/ae/31b9885745b3e7ef23a3ae7f175b879807288d11b3fb7e2d3c119c916258/zensical-0.0.26-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1c8e601b2bbd239e564b04cf235eefb9777e7dfc7e1857b8871d6cdcfb577aa0", size = 12506728, upload-time = "2026-03-11T09:50:57.775Z" },
+    { url = "https://files.pythonhosted.org/packages/bd/93/f5291e2c47076474f181f6eef35ef0428117d3f192da4358c0511e2ce09e/zensical-0.0.26-cp310-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2dc43c7e6c25d9724fc0450f0273ca4e5e2506eeb7f89f52f1405a592896ca3b", size = 12454975, upload-time = "2026-03-11T09:51:01.514Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/2e/61cac4f2ebad31dab768eb02753ffde9e56d4d34b8f876b949bf516fbd50/zensical-0.0.26-cp310-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:24ed236d1254cc474c19227eaa3670a1ccf921af53134ec5542b05853bdcd59c", size = 12791930, upload-time = "2026-03-11T09:51:05.162Z" },
+    { url = "https://files.pythonhosted.org/packages/02/86/51995d1ed2dd6ad8a1a70bcdf3c5eb16b50e62ea70e638d454a6b9061c4d/zensical-0.0.26-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1110147710d1dd025d932c4a7eada836bdf079c91b70fb0ae5b202e14b094617", size = 12548166, upload-time = "2026-03-11T09:51:09.218Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/93/decbafdbfc77170cbc3851464632390846e9aaf45e743c8dd5a24d5673e9/zensical-0.0.26-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:7d21596a785428cdebc20859bd94a05334abe14ad24f1bb9cd80d19219e3c220", size = 12682103, upload-time = "2026-03-11T09:51:12.68Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/e2/391d2d08dde621177da069a796a886b549fefb15734aeeb6e696af99b662/zensical-0.0.26-cp310-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:680a3c7bb71499b4da784d6072e44b3d7b8c0df3ce9bbd9974e24bd8058c2736", size = 12724219, upload-time = "2026-03-11T09:51:17.32Z" },
+    { url = "https://files.pythonhosted.org/packages/80/2a/21b40c5c40a67da8a841f278d61dbd8d5e035e489de6fe1cef5f4e211b4f/zensical-0.0.26-cp310-abi3-musllinux_1_2_i686.whl", hash = "sha256:e3294a79f98218b6fc2219232e166aa0932ae4dad58f6c8dbc0dbe0ecbff9c25", size = 12862117, upload-time = "2026-03-11T09:51:22.161Z" },
+    { url = "https://files.pythonhosted.org/packages/51/76/e1910d6d75d207654c867b8efbda6822dedda9fed3601bf4a864a1f4fe26/zensical-0.0.26-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:630229587df1fb47be184a4a69d0772ce59a44cd2c481ae9f7e8852fffaff11e", size = 12815714, upload-time = "2026-03-11T09:51:26.24Z" },
 ]
 
 [[package]]