Chore(deps): Bump cbor2 in the uv group across 1 directory

Bumps the uv group with 1 update in the / directory: [cbor2](https://github.com/agronholm/cbor2).


Updates `cbor2` from 5.8.0 to 5.9.0
- [Release notes](https://github.com/agronholm/cbor2/releases)
- [Commits](https://github.com/agronholm/cbor2/compare/5.8.0...5.9.0)

---
updated-dependencies:
- dependency-name: cbor2
  dependency-version: 5.9.0
  dependency-type: indirect
  dependency-group: uv
...

Signed-off-by: dependabot[bot] <support@github.com>

.mypy-baseline.txt

@@ -2437,17 +2437,3 @@ src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "Non
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "unpaper_clean"  [union-attr]
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "unpaper_clean"  [union-attr]
 src/paperless_tesseract/tests/test_parser_custom_settings.py:0: error: Item "None" of "ApplicationConfiguration | None" has no attribute "user_args"  [union-attr]
-src/paperless_text/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_text/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_text/parsers.py:0: error: Incompatible types in assignment (expression has type "str", variable has type "None")  [assignment]
-src/paperless_text/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_text/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Argument 1 to "make_thumbnail_from_pdf" has incompatible type "None"; expected "Path"  [arg-type]
-src/paperless_tika/parsers.py:0: error: Function is missing a return type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Function is missing a type annotation for one or more arguments  [no-untyped-def]
-src/paperless_tika/parsers.py:0: error: Incompatible types in assignment (expression has type "str | None", variable has type "None")  [assignment]
-src/paperless_tika/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]
-src/paperless_tika/signals.py:0: error: Function is missing a type annotation  [no-untyped-def]

pyproject.toml

@@ -269,10 +269,6 @@ testpaths = [
   "src/documents/tests/",
   "src/paperless/tests/",
   "src/paperless_mail/tests/",
-  "src/paperless_tesseract/tests/",
-  "src/paperless_tika/tests",
-  "src/paperless_text/tests/",
-  "src/paperless_remote/tests/",
   "src/paperless_ai/tests",
 ]
 

src/documents/checks.py

@@ -3,25 +3,20 @@ from django.core.checks import Error
 from django.core.checks import Warning
 from django.core.checks import register
 
-from documents.signals import document_consumer_declaration
 from documents.templating.utils import convert_format_str_to_template_format
+from paperless.parsers.registry import get_parser_registry
 
 
 @register()
 def parser_check(app_configs, **kwargs):
-    parsers = []
-    for response in document_consumer_declaration.send(None):
-        parsers.append(response[1])
-
-    if len(parsers) == 0:
+    if not get_parser_registry().all_parsers():
         return [
             Error(
                 "No parsers found. This is a bug. The consumer won't be "
                 "able to consume any documents without parsers.",
             ),
         ]
-    else:
-        return []
+    return []
 
 
 @register()

src/documents/consumer.py

@@ -32,9 +32,7 @@ from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import WorkflowTrigger
-from documents.parsers import DocumentParser
 from documents.parsers import ParseError
-from documents.parsers import get_parser_class_for_mime_type
 from documents.permissions import set_permissions_for_object
 from documents.plugins.base import AlwaysRunPluginMixin
 from documents.plugins.base import ConsumeTaskPlugin
@@ -52,40 +50,12 @@ 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.parsers.tika import TikaDocumentParser
+from paperless.parsers import ParserProtocol
+from paperless.parsers.registry import get_parser_registry
 
 LOGGING_NAME: Final[str] = "paperless.consumer"
 
 
-def _parser_cleanup(parser: DocumentParser) -> None:
-    """
-    Call cleanup on a parser, handling the new-style context-manager parsers.
-
-    New-style parsers (e.g. TextDocumentParser) use __exit__ for teardown
-    instead of a cleanup() method.  This shim will be removed once all existing parsers
-    have switched to the new style and this consumer is updated to use it
-
-    TODO(stumpylog): Remove me in the future
-    """
-    if isinstance(
-        parser,
-        (
-            MailDocumentParser,
-            RasterisedDocumentParser,
-            RemoteDocumentParser,
-            TextDocumentParser,
-            TikaDocumentParser,
-        ),
-    ):
-        parser.__exit__(None, None, None)
-    else:
-        parser.cleanup()
-
-
 class WorkflowTriggerPlugin(
     NoCleanupPluginMixin,
     NoSetupPluginMixin,
@@ -422,8 +392,12 @@ class ConsumerPlugin(
                     self.log.error(f"Error attempting to clean PDF: {e}")
 
             # Based on the mime type, get the parser for that type
-            parser_class: type[DocumentParser] | None = get_parser_class_for_mime_type(
-                mime_type,
+            parser_class: type[ParserProtocol] | None = (
+                get_parser_registry().get_parser_for_file(
+                    mime_type,
+                    self.filename,
+                    self.working_copy,
+                )
             )
             if not parser_class:
                 tempdir.cleanup()
@@ -446,313 +420,275 @@ class ConsumerPlugin(
                 tempdir.cleanup()
             raise
 
-        def progress_callback(
-            current_progress,
-            max_progress,
-        ) -> None:  # pragma: no cover
-            # recalculate progress to be within 20 and 80
-            p = int((current_progress / max_progress) * 50 + 20)
-            self._send_progress(p, 100, ProgressStatusOptions.WORKING)
-
         # This doesn't parse the document yet, but gives us a parser.
-
-        document_parser: DocumentParser = parser_class(
-            self.logging_group,
-            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.
-
-        text = None
-        date = None
-        thumbnail = None
-        archive_path = None
-        page_count = None
-
-        try:
-            self._send_progress(
-                20,
-                100,
-                ProgressStatusOptions.WORKING,
-                ConsumerStatusShortMessage.PARSING_DOCUMENT,
+        with parser_class() as document_parser:
+            document_parser.configure(
+                ParserContext(mailrule_id=self.input_doc.mailrule_id),
             )
-            self.log.debug(f"Parsing {self.filename}...")
 
-            # 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),
-                )
-                # TODO(stumpylog): Remove me in the future
-                document_parser.parse(self.working_copy, mime_type)
-            else:
-                document_parser.parse(self.working_copy, mime_type, self.filename)
+            self.log.debug(f"Parser: {document_parser.name} v{document_parser.version}")
 
-            self.log.debug(f"Generating thumbnail for {self.filename}...")
-            self._send_progress(
-                70,
-                100,
-                ProgressStatusOptions.WORKING,
-                ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
-            )
-            # 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(
-                    self.working_copy,
-                    mime_type,
-                    self.filename,
-                )
+            # Parse the document. This may take some time.
 
-            text = document_parser.get_text()
-            date = document_parser.get_date()
-            if date is None:
+            text = None
+            date = None
+            thumbnail = None
+            archive_path = None
+            page_count = None
+
+            try:
                 self._send_progress(
-                    90,
+                    20,
                     100,
                     ProgressStatusOptions.WORKING,
-                    ConsumerStatusShortMessage.PARSE_DATE,
+                    ConsumerStatusShortMessage.PARSING_DOCUMENT,
                 )
-                with get_date_parser() as date_parser:
-                    date = next(date_parser.parse(self.filename, text), None)
-            archive_path = document_parser.get_archive_path()
-            page_count = document_parser.get_page_count(self.working_copy, mime_type)
+                self.log.debug(f"Parsing {self.filename}...")
 
-        except ParseError as e:
-            _parser_cleanup(document_parser)
-            if tempdir:
-                tempdir.cleanup()
-            self._fail(
-                str(e),
-                f"Error occurred while consuming document {self.filename}: {e}",
-                exc_info=True,
-                exception=e,
-            )
-        except Exception as e:
-            _parser_cleanup(document_parser)
-            if tempdir:
-                tempdir.cleanup()
-            self._fail(
-                str(e),
-                f"Unexpected error while consuming document {self.filename}: {e}",
-                exc_info=True,
-                exception=e,
-            )
+                document_parser.parse(self.working_copy, mime_type)
 
-        # Prepare the document classifier.
+                self.log.debug(f"Generating thumbnail for {self.filename}...")
+                self._send_progress(
+                    70,
+                    100,
+                    ProgressStatusOptions.WORKING,
+                    ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
+                )
+                thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
 
-        # TODO: I don't really like to do this here, but this way we avoid
-        #   reloading the classifier multiple times, since there are multiple
-        #   post-consume hooks that all require the classifier.
-
-        classifier = load_classifier()
-
-        self._send_progress(
-            95,
-            100,
-            ProgressStatusOptions.WORKING,
-            ConsumerStatusShortMessage.SAVE_DOCUMENT,
-        )
-        # now that everything is done, we can start to store the document
-        # in the system. This will be a transaction and reasonably fast.
-        try:
-            with transaction.atomic():
-                # store the document.
-                if self.input_doc.root_document_id:
-                    # If this is a new version of an existing document, we need
-                    # to make sure we're not creating a new document, but updating
-                    # the existing one.
-                    root_doc = Document.objects.get(
-                        pk=self.input_doc.root_document_id,
+                text = document_parser.get_text()
+                date = document_parser.get_date()
+                if date is None:
+                    self._send_progress(
+                        90,
+                        100,
+                        ProgressStatusOptions.WORKING,
+                        ConsumerStatusShortMessage.PARSE_DATE,
                     )
-                    original_document = self._create_version_from_root(
-                        root_doc,
-                        text=text,
-                        page_count=page_count,
-                        mime_type=mime_type,
-                    )
-                    actor = None
+                    with get_date_parser() as date_parser:
+                        date = next(date_parser.parse(self.filename, text), None)
+                archive_path = document_parser.get_archive_path()
+                page_count = document_parser.get_page_count(
+                    self.working_copy,
+                    mime_type,
+                )
 
-                    # Save the new version, potentially creating an audit log entry for the version addition if enabled.
-                    if (
-                        settings.AUDIT_LOG_ENABLED
-                        and self.metadata.actor_id is not None
-                    ):
-                        actor = User.objects.filter(pk=self.metadata.actor_id).first()
-                        if actor is not None:
-                            from auditlog.context import (  # type: ignore[import-untyped]
-                                set_actor,
-                            )
+            except ParseError as e:
+                if tempdir:
+                    tempdir.cleanup()
+                self._fail(
+                    str(e),
+                    f"Error occurred while consuming document {self.filename}: {e}",
+                    exc_info=True,
+                    exception=e,
+                )
+            except Exception as e:
+                if tempdir:
+                    tempdir.cleanup()
+                self._fail(
+                    str(e),
+                    f"Unexpected error while consuming document {self.filename}: {e}",
+                    exc_info=True,
+                    exception=e,
+                )
 
-                            with set_actor(actor):
+            # Prepare the document classifier.
+
+            # TODO: I don't really like to do this here, but this way we avoid
+            #   reloading the classifier multiple times, since there are multiple
+            #   post-consume hooks that all require the classifier.
+
+            classifier = load_classifier()
+
+            self._send_progress(
+                95,
+                100,
+                ProgressStatusOptions.WORKING,
+                ConsumerStatusShortMessage.SAVE_DOCUMENT,
+            )
+            # now that everything is done, we can start to store the document
+            # in the system. This will be a transaction and reasonably fast.
+            try:
+                with transaction.atomic():
+                    # store the document.
+                    if self.input_doc.root_document_id:
+                        # If this is a new version of an existing document, we need
+                        # to make sure we're not creating a new document, but updating
+                        # the existing one.
+                        root_doc = Document.objects.get(
+                            pk=self.input_doc.root_document_id,
+                        )
+                        original_document = self._create_version_from_root(
+                            root_doc,
+                            text=text,
+                            page_count=page_count,
+                            mime_type=mime_type,
+                        )
+                        actor = None
+
+                        # Save the new version, potentially creating an audit log entry for the version addition if enabled.
+                        if (
+                            settings.AUDIT_LOG_ENABLED
+                            and self.metadata.actor_id is not None
+                        ):
+                            actor = User.objects.filter(
+                                pk=self.metadata.actor_id,
+                            ).first()
+                            if actor is not None:
+                                from auditlog.context import (  # type: ignore[import-untyped]
+                                    set_actor,
+                                )
+
+                                with set_actor(actor):
+                                    original_document.save()
+                            else:
                                 original_document.save()
                         else:
                             original_document.save()
+
+                        # Create a log entry for the version addition, if enabled
+                        if settings.AUDIT_LOG_ENABLED:
+                            from auditlog.models import (  # type: ignore[import-untyped]
+                                LogEntry,
+                            )
+
+                            LogEntry.objects.log_create(
+                                instance=root_doc,
+                                changes={
+                                    "Version Added": ["None", original_document.id],
+                                },
+                                action=LogEntry.Action.UPDATE,
+                                actor=actor,
+                                additional_data={
+                                    "reason": "Version added",
+                                    "version_id": original_document.id,
+                                },
+                            )
+                        document = original_document
                     else:
-                        original_document.save()
-
-                    # Create a log entry for the version addition, if enabled
-                    if settings.AUDIT_LOG_ENABLED:
-                        from auditlog.models import (  # type: ignore[import-untyped]
-                            LogEntry,
+                        document = self._store(
+                            text=text,
+                            date=date,
+                            page_count=page_count,
+                            mime_type=mime_type,
                         )
 
-                        LogEntry.objects.log_create(
-                            instance=root_doc,
-                            changes={
-                                "Version Added": ["None", original_document.id],
-                            },
-                            action=LogEntry.Action.UPDATE,
-                            actor=actor,
-                            additional_data={
-                                "reason": "Version added",
-                                "version_id": original_document.id,
-                            },
-                        )
-                    document = original_document
-                else:
-                    document = self._store(
-                        text=text,
-                        date=date,
-                        page_count=page_count,
-                        mime_type=mime_type,
-                    )
+                    # If we get here, it was successful. Proceed with post-consume
+                    # hooks. If they fail, nothing will get changed.
 
-                # If we get here, it was successful. Proceed with post-consume
-                # hooks. If they fail, nothing will get changed.
-
-                document_consumption_finished.send(
-                    sender=self.__class__,
-                    document=document,
-                    logging_group=self.logging_group,
-                    classifier=classifier,
-                    original_file=self.unmodified_original
-                    if self.unmodified_original
-                    else self.working_copy,
-                )
-
-                # After everything is in the database, copy the files into
-                # place. If this fails, we'll also rollback the transaction.
-                with FileLock(settings.MEDIA_LOCK):
-                    generated_filename = generate_unique_filename(document)
-                    if (
-                        len(str(generated_filename))
-                        > Document.MAX_STORED_FILENAME_LENGTH
-                    ):
-                        self.log.warning(
-                            "Generated source filename exceeds db path limit, falling back to default naming",
-                        )
-                        generated_filename = generate_filename(
-                            document,
-                            use_format=False,
-                        )
-                    document.filename = generated_filename
-                    create_source_path_directory(document.source_path)
-
-                    self._write(
-                        self.unmodified_original
-                        if self.unmodified_original is not None
+                    document_consumption_finished.send(
+                        sender=self.__class__,
+                        document=document,
+                        logging_group=self.logging_group,
+                        classifier=classifier,
+                        original_file=self.unmodified_original
+                        if self.unmodified_original
                         else self.working_copy,
-                        document.source_path,
                     )
 
-                    self._write(
-                        thumbnail,
-                        document.thumbnail_path,
-                    )
-
-                    if archive_path and Path(archive_path).is_file():
-                        generated_archive_filename = generate_unique_filename(
-                            document,
-                            archive_filename=True,
-                        )
+                    # After everything is in the database, copy the files into
+                    # place. If this fails, we'll also rollback the transaction.
+                    with FileLock(settings.MEDIA_LOCK):
+                        generated_filename = generate_unique_filename(document)
                         if (
-                            len(str(generated_archive_filename))
+                            len(str(generated_filename))
                             > Document.MAX_STORED_FILENAME_LENGTH
                         ):
                             self.log.warning(
-                                "Generated archive filename exceeds db path limit, falling back to default naming",
+                                "Generated source filename exceeds db path limit, falling back to default naming",
                             )
-                            generated_archive_filename = generate_filename(
+                            generated_filename = generate_filename(
                                 document,
-                                archive_filename=True,
                                 use_format=False,
                             )
-                        document.archive_filename = generated_archive_filename
-                        create_source_path_directory(document.archive_path)
+                        document.filename = generated_filename
+                        create_source_path_directory(document.source_path)
+
                         self._write(
-                            archive_path,
-                            document.archive_path,
+                            self.unmodified_original
+                            if self.unmodified_original is not None
+                            else self.working_copy,
+                            document.source_path,
                         )
 
-                        with Path(archive_path).open("rb") as f:
-                            document.archive_checksum = hashlib.md5(
-                                f.read(),
-                            ).hexdigest()
+                        self._write(
+                            thumbnail,
+                            document.thumbnail_path,
+                        )
 
-                # Don't save with the lock active. Saving will cause the file
-                # renaming logic to acquire the lock as well.
-                # This triggers things like file renaming
-                document.save()
+                        if archive_path and Path(archive_path).is_file():
+                            generated_archive_filename = generate_unique_filename(
+                                document,
+                                archive_filename=True,
+                            )
+                            if (
+                                len(str(generated_archive_filename))
+                                > Document.MAX_STORED_FILENAME_LENGTH
+                            ):
+                                self.log.warning(
+                                    "Generated archive filename exceeds db path limit, falling back to default naming",
+                                )
+                                generated_archive_filename = generate_filename(
+                                    document,
+                                    archive_filename=True,
+                                    use_format=False,
+                                )
+                            document.archive_filename = generated_archive_filename
+                            create_source_path_directory(document.archive_path)
+                            self._write(
+                                archive_path,
+                                document.archive_path,
+                            )
 
-                if document.root_document_id:
-                    document_updated.send(
-                        sender=self.__class__,
-                        document=document.root_document,
-                    )
+                            with Path(archive_path).open("rb") as f:
+                                document.archive_checksum = hashlib.md5(
+                                    f.read(),
+                                ).hexdigest()
 
-                # Delete the file only if it was successfully consumed
-                self.log.debug(f"Deleting original file {self.input_doc.original_file}")
-                self.input_doc.original_file.unlink()
-                self.log.debug(f"Deleting working copy {self.working_copy}")
-                self.working_copy.unlink()
-                if self.unmodified_original is not None:  # pragma: no cover
+                    # Don't save with the lock active. Saving will cause the file
+                    # renaming logic to acquire the lock as well.
+                    # This triggers things like file renaming
+                    document.save()
+
+                    if document.root_document_id:
+                        document_updated.send(
+                            sender=self.__class__,
+                            document=document.root_document,
+                        )
+
+                    # Delete the file only if it was successfully consumed
                     self.log.debug(
-                        f"Deleting unmodified original file {self.unmodified_original}",
+                        f"Deleting original file {self.input_doc.original_file}",
                     )
-                    self.unmodified_original.unlink()
+                    self.input_doc.original_file.unlink()
+                    self.log.debug(f"Deleting working copy {self.working_copy}")
+                    self.working_copy.unlink()
+                    if self.unmodified_original is not None:  # pragma: no cover
+                        self.log.debug(
+                            f"Deleting unmodified original file {self.unmodified_original}",
+                        )
+                        self.unmodified_original.unlink()
 
-                # https://github.com/jonaswinkler/paperless-ng/discussions/1037
-                shadow_file = (
-                    Path(self.input_doc.original_file).parent
-                    / f"._{Path(self.input_doc.original_file).name}"
+                    # https://github.com/jonaswinkler/paperless-ng/discussions/1037
+                    shadow_file = (
+                        Path(self.input_doc.original_file).parent
+                        / f"._{Path(self.input_doc.original_file).name}"
+                    )
+
+                    if Path(shadow_file).is_file():
+                        self.log.debug(f"Deleting shadow file {shadow_file}")
+                        Path(shadow_file).unlink()
+
+            except Exception as e:
+                self._fail(
+                    str(e),
+                    f"The following error occurred while storing document "
+                    f"{self.filename} after parsing: {e}",
+                    exc_info=True,
+                    exception=e,
                 )
-
-                if Path(shadow_file).is_file():
-                    self.log.debug(f"Deleting shadow file {shadow_file}")
-                    Path(shadow_file).unlink()
-
-        except Exception as e:
-            self._fail(
-                str(e),
-                f"The following error occurred while storing document "
-                f"{self.filename} after parsing: {e}",
-                exc_info=True,
-                exception=e,
-            )
-        finally:
-            _parser_cleanup(document_parser)
-            tempdir.cleanup()
+            finally:
+                tempdir.cleanup()
 
         self.run_post_consume_script(document)
 

src/documents/management/commands/document_thumbnails.py

@@ -3,19 +3,18 @@ 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
+from paperless.parsers.registry import get_parser_registry
 
 logger = logging.getLogger("paperless.management.thumbnails")
 
 
 def _process_document(doc_id: int) -> None:
     document: Document = Document.objects.get(id=doc_id)
-    parser_class = get_parser_class_for_mime_type(document.mime_type)
+    parser_class = get_parser_registry().get_parser_for_file(
+        document.mime_type,
+        document.original_filename or "",
+        document.source_path,
+    )
 
     if parser_class is None:
         logger.warning(
@@ -25,40 +24,9 @@ def _process_document(doc_id: int) -> None:
         )
         return
 
-    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:
-        # 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(),
-            )
+    with parser_class() as parser:
+        thumb = parser.get_thumbnail(document.source_path, document.mime_type)
         shutil.move(thumb, document.thumbnail_path)
-    finally:
-        # TODO(stumpylog): Cleanup once all parsers are handled
-        if parser_is_new_style:
-            parser.__exit__(None, None, None)
-        else:
-            parser.cleanup()
 
 
 class Command(PaperlessCommand):

src/documents/parsers.py

@@ -3,84 +3,47 @@ from __future__ import annotations
 import logging
 import mimetypes
 import os
-import re
 import shutil
 import subprocess
 import tempfile
-from functools import lru_cache
 from pathlib import Path
 from typing import TYPE_CHECKING
 
 from django.conf import settings
 
 from documents.loggers import LoggingMixin
-from documents.signals import document_consumer_declaration
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless.parsers.registry import get_parser_registry
 
 if TYPE_CHECKING:
     import datetime
 
-# This regular expression will try to find dates in the document at
-# hand and will match the following formats:
-# - XX.YY.ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX/YY/ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX-YY-ZZZZ with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ.XX.YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ/XX/YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - ZZZZ-XX-YY with XX + YY being 1 or 2 and ZZZZ being 2 or 4 digits
-# - XX. MONTH ZZZZ with XX being 1 or 2 and ZZZZ being 2 or 4 digits
-# - MONTH ZZZZ, with ZZZZ being 4 digits
-# - MONTH XX, ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits
-# - XX MON ZZZZ with XX being 1 or 2 and ZZZZ being 4 digits. MONTH is 3 letters
-# - XXPP MONTH ZZZZ with XX being 1 or 2 and PP being 2 letters and ZZZZ being 4 digits
-
-# TODO: isn't there a date parsing library for this?
-
-DATE_REGEX = re.compile(
-    r"(\b|(?!=([_-])))(\d{1,2})[\.\/-](\d{1,2})[\.\/-](\d{4}|\d{2})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{4}|\d{2})[\.\/-](\d{1,2})[\.\/-](\d{1,2})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{1,2}[\. ]+[a-zéûäëčžúřěáíóńźçŞğü]{3,9} \d{4}|[a-zéûäëčžúřěáíóńźçŞğü]{3,9} \d{1,2}, \d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))([^\W\d_]{3,9} \d{1,2}, (\d{4}))(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))([^\W\d_]{3,9} \d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\d{1,2}[^ 0-9]{2}[\. ]+[^ ]{3,9}[ \.\/-]\d{4})(\b|(?=([_-])))|"
-    r"(\b|(?!=([_-])))(\b\d{1,2}[ \.\/-][a-zéûäëčžúřěáíóńźçŞğü]{3}[ \.\/-]\d{4})(\b|(?=([_-])))",
-    re.IGNORECASE,
-)
-
-
 logger = logging.getLogger("paperless.parsing")
 
 
-@lru_cache(maxsize=8)
 def is_mime_type_supported(mime_type: str) -> bool:
     """
     Returns True if the mime type is supported, False otherwise
     """
-    return get_parser_class_for_mime_type(mime_type) is not None
+    return get_parser_registry().get_parser_for_file(mime_type, "") is not None
 
 
-@lru_cache(maxsize=8)
 def get_default_file_extension(mime_type: str) -> str:
     """
     Returns the default file extension for a mimetype, or
     an empty string if it could not be determined
     """
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        if mime_type in supported_mime_types:
-            return supported_mime_types[mime_type]
+    parser_class = get_parser_registry().get_parser_for_file(mime_type, "")
+    if parser_class is not None:
+        supported = parser_class.supported_mime_types()
+        if mime_type in supported:
+            return supported[mime_type]
 
     ext = mimetypes.guess_extension(mime_type)
-    if ext:
-        return ext
-    else:
-        return ""
+    return ext if ext else ""
 
 
-@lru_cache(maxsize=8)
 def is_file_ext_supported(ext: str) -> bool:
     """
     Returns True if the file extension is supported, False otherwise
@@ -94,44 +57,17 @@ def is_file_ext_supported(ext: str) -> bool:
 
 def get_supported_file_extensions() -> set[str]:
     extensions = set()
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        for mime_type in supported_mime_types:
+    for parser_class in get_parser_registry().all_parsers():
+        for mime_type, ext in parser_class.supported_mime_types().items():
             extensions.update(mimetypes.guess_all_extensions(mime_type))
             # Python's stdlib might be behind, so also add what the parser
             # says is the default extension
             # This makes image/webp supported on Python < 3.11
-            extensions.add(supported_mime_types[mime_type])
+            extensions.add(ext)
 
     return extensions
 
 
-def get_parser_class_for_mime_type(mime_type: str) -> type[DocumentParser] | None:
-    """
-    Returns the best parser (by weight) for the given mimetype or
-    None if no parser exists
-    """
-
-    options = []
-
-    for response in document_consumer_declaration.send(None):
-        parser_declaration = response[1]
-        supported_mime_types = parser_declaration["mime_types"]
-
-        if mime_type in supported_mime_types:
-            options.append(parser_declaration)
-
-    if not options:
-        return None
-
-    best_parser = sorted(options, key=lambda _: _["weight"], reverse=True)[0]
-
-    # Return the parser with the highest weight.
-    return best_parser["parser"]
-
-
 def run_convert(
     input_file,
     output_file,

src/documents/signals/__init__.py

@@ -2,5 +2,4 @@ from django.dispatch import Signal
 
 document_consumption_started = Signal()
 document_consumption_finished = Signal()
-document_consumer_declaration = Signal()
 document_updated = Signal()

src/documents/tasks.py

@@ -52,8 +52,6 @@ from documents.models import StoragePath
 from documents.models import Tag
 from documents.models import WorkflowRun
 from documents.models import WorkflowTrigger
-from documents.parsers import DocumentParser
-from documents.parsers import get_parser_class_for_mime_type
 from documents.plugins.base import ConsumeTaskPlugin
 from documents.plugins.base import ProgressManager
 from documents.plugins.base import StopConsumeTaskError
@@ -66,11 +64,7 @@ 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.parsers.registry import get_parser_registry
 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
@@ -310,8 +304,10 @@ def update_document_content_maybe_archive_file(document_id) -> None:
 
     mime_type = document.mime_type
 
-    parser_class: type[DocumentParser] | None = get_parser_class_for_mime_type(
+    parser_class = get_parser_registry().get_parser_for_file(
         mime_type,
+        document.original_filename or "",
+        document.source_path,
     )
 
     if not parser_class:
@@ -321,138 +317,92 @@ def update_document_content_maybe_archive_file(document_id) -> None:
         )
         return
 
-    parser: DocumentParser = parser_class(logging_group=uuid.uuid4())
+    with parser_class() as parser:
+        parser.configure(ParserContext())
 
-    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:
-        # TODO(stumpylog): Remove branch in the future when all parsers use new protocol
-        if parser_is_new_style:
-            parser.configure(ParserContext())
+        try:
             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)
-            if parser.get_archive_path():
-                with Path(parser.get_archive_path()).open("rb") as f:
-                    checksum = hashlib.md5(f.read()).hexdigest()
-                # I'm going to save first so that in case the file move
-                # fails, the database is rolled back.
-                # We also don't use save() since that triggers the filehandling
-                # logic, and we don't want that yet (file not yet in place)
-                document.archive_filename = generate_unique_filename(
-                    document,
-                    archive_filename=True,
-                )
-                Document.objects.filter(pk=document.pk).update(
-                    archive_checksum=checksum,
-                    content=parser.get_text(),
-                    archive_filename=document.archive_filename,
-                )
-                newDocument = Document.objects.get(pk=document.pk)
-                if settings.AUDIT_LOG_ENABLED:
-                    LogEntry.objects.log_create(
-                        instance=oldDocument,
-                        changes={
-                            "content": [oldDocument.content, newDocument.content],
-                            "archive_checksum": [
-                                oldDocument.archive_checksum,
-                                newDocument.archive_checksum,
-                            ],
-                            "archive_filename": [
-                                oldDocument.archive_filename,
-                                newDocument.archive_filename,
-                            ],
-                        },
-                        additional_data={
-                            "reason": "Update document content",
-                        },
-                        action=LogEntry.Action.UPDATE,
-                    )
-            else:
-                Document.objects.filter(pk=document.pk).update(
-                    content=parser.get_text(),
-                )
-
-                if settings.AUDIT_LOG_ENABLED:
-                    LogEntry.objects.log_create(
-                        instance=oldDocument,
-                        changes={
-                            "content": [oldDocument.content, parser.get_text()],
-                        },
-                        additional_data={
-                            "reason": "Update document content",
-                        },
-                        action=LogEntry.Action.UPDATE,
-                    )
-
-            with FileLock(settings.MEDIA_LOCK):
+            with transaction.atomic():
+                oldDocument = Document.objects.get(pk=document.pk)
                 if parser.get_archive_path():
-                    create_source_path_directory(document.archive_path)
-                    shutil.move(parser.get_archive_path(), document.archive_path)
-                shutil.move(thumbnail, document.thumbnail_path)
+                    with Path(parser.get_archive_path()).open("rb") as f:
+                        checksum = hashlib.md5(f.read()).hexdigest()
+                    # I'm going to save first so that in case the file move
+                    # fails, the database is rolled back.
+                    # We also don't use save() since that triggers the filehandling
+                    # logic, and we don't want that yet (file not yet in place)
+                    document.archive_filename = generate_unique_filename(
+                        document,
+                        archive_filename=True,
+                    )
+                    Document.objects.filter(pk=document.pk).update(
+                        archive_checksum=checksum,
+                        content=parser.get_text(),
+                        archive_filename=document.archive_filename,
+                    )
+                    newDocument = Document.objects.get(pk=document.pk)
+                    if settings.AUDIT_LOG_ENABLED:
+                        LogEntry.objects.log_create(
+                            instance=oldDocument,
+                            changes={
+                                "content": [oldDocument.content, newDocument.content],
+                                "archive_checksum": [
+                                    oldDocument.archive_checksum,
+                                    newDocument.archive_checksum,
+                                ],
+                                "archive_filename": [
+                                    oldDocument.archive_filename,
+                                    newDocument.archive_filename,
+                                ],
+                            },
+                            additional_data={
+                                "reason": "Update document content",
+                            },
+                            action=LogEntry.Action.UPDATE,
+                        )
+                else:
+                    Document.objects.filter(pk=document.pk).update(
+                        content=parser.get_text(),
+                    )
 
-        document.refresh_from_db()
-        logger.info(
-            f"Updating index for document {document_id} ({document.archive_checksum})",
-        )
-        with index.open_index_writer() as writer:
-            index.update_document(writer, document)
+                    if settings.AUDIT_LOG_ENABLED:
+                        LogEntry.objects.log_create(
+                            instance=oldDocument,
+                            changes={
+                                "content": [oldDocument.content, parser.get_text()],
+                            },
+                            additional_data={
+                                "reason": "Update document content",
+                            },
+                            action=LogEntry.Action.UPDATE,
+                        )
 
-        ai_config = AIConfig()
-        if ai_config.llm_index_enabled:
-            llm_index_add_or_update_document(document)
+                with FileLock(settings.MEDIA_LOCK):
+                    if parser.get_archive_path():
+                        create_source_path_directory(document.archive_path)
+                        shutil.move(parser.get_archive_path(), document.archive_path)
+                    shutil.move(thumbnail, document.thumbnail_path)
 
-        clear_document_caches(document.pk)
+            document.refresh_from_db()
+            logger.info(
+                f"Updating index for document {document_id} ({document.archive_checksum})",
+            )
+            with index.open_index_writer() as writer:
+                index.update_document(writer, document)
 
-    except Exception:
-        logger.exception(
-            f"Error while parsing document {document} (ID: {document_id})",
-        )
-    finally:
-        # 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()
+            ai_config = AIConfig()
+            if ai_config.llm_index_enabled:
+                llm_index_add_or_update_document(document)
+
+            clear_document_caches(document.pk)
+
+        except Exception:
+            logger.exception(
+                f"Error while parsing document {document} (ID: {document_id})",
+            )
 
 
 @shared_task

src/documents/tests/test_checks.py

@@ -13,8 +13,10 @@ class TestDocumentChecks(TestCase):
     def test_parser_check(self) -> None:
         self.assertEqual(parser_check(None), [])
 
-        with mock.patch("documents.checks.document_consumer_declaration.send") as m:
-            m.return_value = []
+        with mock.patch("documents.checks.get_parser_registry") as mock_registry_fn:
+            mock_registry = mock.MagicMock()
+            mock_registry.all_parsers.return_value = []
+            mock_registry_fn.return_value = mock_registry
 
             self.assertEqual(
                 parser_check(None),

src/documents/tests/test_consumer.py

@@ -27,7 +27,6 @@ from documents.models import Document
 from documents.models import DocumentType
 from documents.models import StoragePath
 from documents.models import Tag
-from documents.parsers import DocumentParser
 from documents.parsers import ParseError
 from documents.plugins.helpers import ProgressStatusOptions
 from documents.tasks import sanity_check
@@ -38,62 +37,106 @@ from documents.tests.utils import GetConsumerMixin
 from paperless_mail.models import MailRule
 
 
-class _BaseTestParser(DocumentParser):
-    def get_settings(self) -> None:
+class _BaseNewStyleParser:
+    """Minimal ParserProtocol implementation for use in consumer tests."""
+
+    name: str = "test-parser"
+    version: str = "0.1"
+    author: str = "test"
+    url: str = "test"
+
+    @classmethod
+    def supported_mime_types(cls) -> dict:
+        return {
+            "application/pdf": ".pdf",
+            "image/png": ".png",
+            "message/rfc822": ".eml",
+        }
+
+    @classmethod
+    def score(cls, mime_type: str, filename: str, path=None):
+        return 0 if mime_type in cls.supported_mime_types() else None
+
+    @property
+    def can_produce_archive(self) -> bool:
+        return True
+
+    @property
+    def requires_pdf_rendition(self) -> bool:
+        return False
+
+    def __init__(self) -> None:
+        self._tmpdir: Path | None = None
+        self._text: str | None = None
+        self._archive: Path | None = None
+        self._thumb: Path | None = None
+
+    def __enter__(self):
+        self._tmpdir = Path(
+            tempfile.mkdtemp(prefix="paperless-test-", dir=settings.SCRATCH_DIR),
+        )
+        _, thumb = tempfile.mkstemp(suffix=".webp", dir=self._tmpdir)
+        self._thumb = Path(thumb)
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb) -> None:
+        if self._tmpdir and self._tmpdir.exists():
+            shutil.rmtree(self._tmpdir, ignore_errors=True)
+
+    def configure(self, context) -> None:
         """
-        This parser does not implement additional settings yet
+        Test parser doesn't do anything with context
         """
+
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        raise NotImplementedError
+
+    def get_text(self) -> str | None:
+        return self._text
+
+    def get_date(self):
         return None
 
+    def get_archive_path(self):
+        return self._archive
 
-class DummyParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir, archive_path) -> None:
-        super().__init__(logging_group, None)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
-        self.archive_path = archive_path
+    def get_thumbnail(self, document_path, mime_type) -> Path:
+        return self._thumb
 
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
+    def get_page_count(self, document_path, mime_type):
+        return None
 
-    def parse(self, document_path, mime_type, file_name=None) -> None:
-        self.text = "The Text"
+    def extract_metadata(self, document_path, mime_type) -> list:
+        return []
 
 
-class CopyParser(_BaseTestParser):
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
+class DummyParser(_BaseNewStyleParser):
+    _ARCHIVE_SRC = (
+        Path(__file__).parent / "samples" / "documents" / "archive" / "0000001.pdf"
+    )
 
-    def __init__(self, logging_group, progress_callback=None) -> None:
-        super().__init__(logging_group, progress_callback)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=self.tempdir)
-
-    def parse(self, document_path, mime_type, file_name=None) -> None:
-        self.text = "The text"
-        self.archive_path = Path(self.tempdir / "archive.pdf")
-        shutil.copy(document_path, self.archive_path)
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        self._text = "The Text"
+        if produce_archive and self._tmpdir:
+            self._archive = self._tmpdir / "archive.pdf"
+            shutil.copy(self._ARCHIVE_SRC, self._archive)
 
 
-class FaultyParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir) -> None:
-        super().__init__(logging_group)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
+class CopyParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
+        self._text = "The text"
+        if produce_archive and self._tmpdir:
+            self._archive = self._tmpdir / "archive.pdf"
+            shutil.copy(document_path, self._archive)
 
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
 
-    def parse(self, document_path, mime_type, file_name=None):
+class FaultyParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         raise ParseError("Does not compute.")
 
 
-class FaultyGenericExceptionParser(_BaseTestParser):
-    def __init__(self, logging_group, scratch_dir) -> None:
-        super().__init__(logging_group)
-        _, self.fake_thumb = tempfile.mkstemp(suffix=".webp", dir=scratch_dir)
-
-    def get_thumbnail(self, document_path, mime_type, file_name=None):
-        return self.fake_thumb
-
-    def parse(self, document_path, mime_type, file_name=None):
+class FaultyGenericExceptionParser(_BaseNewStyleParser):
+    def parse(self, document_path, mime_type, *, produce_archive: bool = True) -> None:
         raise Exception("Generic exception.")
 
 
@@ -147,38 +190,12 @@ class TestConsumer(
         self.assertEqual(payload["data"]["max_progress"], last_progress_max)
         self.assertEqual(payload["data"]["status"], last_status)
 
-    def make_dummy_parser(self, logging_group, progress_callback=None):
-        return DummyParser(
-            logging_group,
-            self.dirs.scratch_dir,
-            self.get_test_archive_file(),
-        )
-
-    def make_faulty_parser(self, logging_group, progress_callback=None):
-        return FaultyParser(logging_group, self.dirs.scratch_dir)
-
-    def make_faulty_generic_exception_parser(
-        self,
-        logging_group,
-        progress_callback=None,
-    ):
-        return FaultyGenericExceptionParser(logging_group, self.dirs.scratch_dir)
-
     def setUp(self) -> None:
         super().setUp()
 
-        patcher = mock.patch("documents.parsers.document_consumer_declaration.send")
-        m = patcher.start()
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_dummy_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        patcher = mock.patch("documents.consumer.get_parser_registry")
+        mock_registry = patcher.start()
+        mock_registry.return_value.get_parser_for_file.return_value = DummyParser
         self.addCleanup(patcher.stop)
 
     def get_test_file(self):
@@ -547,9 +564,9 @@ class TestConsumer(
             ) as consumer:
                 consumer.run()
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testNoParsers(self, m) -> None:
-        m.return_value = []
+        m.return_value.get_parser_for_file.return_value = None
 
         with self.assertRaisesMessage(
             ConsumerError,
@@ -560,18 +577,9 @@ class TestConsumer(
 
         self._assert_first_last_send_progress(last_status="FAILED")
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testFaultyParser(self, m) -> None:
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_faulty_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = FaultyParser
 
         with self.get_consumer(self.get_test_file()) as consumer:
             with self.assertRaisesMessage(
@@ -582,18 +590,9 @@ class TestConsumer(
 
         self._assert_first_last_send_progress(last_status="FAILED")
 
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def testGenericParserException(self, m) -> None:
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": self.make_faulty_generic_exception_parser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = FaultyGenericExceptionParser
 
         with self.get_consumer(self.get_test_file()) as consumer:
             with self.assertRaisesMessage(
@@ -1017,7 +1016,7 @@ class TestConsumer(
         self._assert_first_last_send_progress()
 
     @override_settings(FILENAME_FORMAT="{title}")
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def test_similar_filenames(self, m) -> None:
         shutil.copy(
             Path(__file__).parent / "samples" / "simple.pdf",
@@ -1031,16 +1030,7 @@ class TestConsumer(
             Path(__file__).parent / "samples" / "simple-noalpha.png",
             settings.CONSUMPTION_DIR / "simple.png.pdf",
         )
-        m.return_value = [
-            (
-                None,
-                {
-                    "parser": CopyParser,
-                    "mime_types": {"application/pdf": ".pdf", "image/png": ".png"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        m.return_value.get_parser_for_file.return_value = CopyParser
 
         with self.get_consumer(settings.CONSUMPTION_DIR / "simple.png") as consumer:
             consumer.run()
@@ -1068,8 +1058,10 @@ class TestConsumer(
 
         sanity_check()
 
+    @mock.patch("documents.consumer.get_parser_registry")
     @mock.patch("documents.consumer.run_subprocess")
-    def test_try_to_clean_invalid_pdf(self, m) -> None:
+    def test_try_to_clean_invalid_pdf(self, m, mock_registry) -> None:
+        mock_registry.return_value.get_parser_for_file.return_value = None
         shutil.copy(
             Path(__file__).parent / "samples" / "invalid_pdf.pdf",
             settings.CONSUMPTION_DIR / "invalid_pdf.pdf",
@@ -1091,10 +1083,10 @@ class TestConsumer(
 
     @mock.patch("paperless_mail.models.MailRule.objects.get")
     @mock.patch("paperless.parsers.mail.MailDocumentParser.parse")
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
+    @mock.patch("documents.consumer.get_parser_registry")
     def test_mail_parser_receives_mailrule(
         self,
-        mock_consumer_declaration_send: mock.Mock,
+        mock_get_parser_registry: mock.Mock,
         mock_mail_parser_parse: mock.Mock,
         mock_mailrule_get: mock.Mock,
     ) -> None:
@@ -1106,18 +1098,11 @@ class TestConsumer(
         THEN:
             - The mail parser should receive the mail rule
         """
-        from paperless_mail.signals import get_parser as mail_get_parser
+        from paperless.parsers.mail import MailDocumentParser
 
-        mock_consumer_declaration_send.return_value = [
-            (
-                None,
-                {
-                    "parser": mail_get_parser,
-                    "mime_types": {"message/rfc822": ".eml"},
-                    "weight": 0,
-                },
-            ),
-        ]
+        mock_get_parser_registry.return_value.get_parser_for_file.return_value = (
+            MailDocumentParser
+        )
         mock_mailrule_get.return_value = mock.Mock(
             pdf_layout=MailRule.PdfLayout.HTML_ONLY,
         )

src/documents/tests/test_parsers.py

@@ -1,132 +1,16 @@
-from tempfile import TemporaryDirectory
-from unittest import mock
-
-from django.apps import apps
 from django.test import TestCase
 from django.test import override_settings
 
 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.registry import get_parser_registry
+from paperless.parsers.registry import reset_parser_registry
 from paperless.parsers.tesseract import RasterisedDocumentParser
 from paperless.parsers.text import TextDocumentParser
 from paperless.parsers.tika import TikaDocumentParser
 
 
-class TestParserDiscovery(TestCase):
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_1_parser(self, m, *args) -> None:
-        """
-        GIVEN:
-            - Parser declared for a given mimetype
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - Declared parser class is returned
-        """
-
-        class DummyParser:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertEqual(get_parser_class_for_mime_type("application/pdf"), DummyParser)
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_n_parsers(self, m, *args) -> None:
-        """
-        GIVEN:
-            - Two parsers declared for a given mimetype
-            - Second parser has a higher weight
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - Second parser class is returned
-        """
-
-        class DummyParser1:
-            pass
-
-        class DummyParser2:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser1,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-            (
-                None,
-                {
-                    "weight": 1,
-                    "parser": DummyParser2,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertEqual(
-            get_parser_class_for_mime_type("application/pdf"),
-            DummyParser2,
-        )
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_0_parsers(self, m, *args) -> None:
-        """
-        GIVEN:
-            - No parsers are declared
-        WHEN:
-            - Attempt to get parser for the mimetype
-        THEN:
-            - No parser class is returned
-        """
-        m.return_value = []
-        with TemporaryDirectory():
-            self.assertIsNone(get_parser_class_for_mime_type("application/pdf"))
-
-    @mock.patch("documents.parsers.document_consumer_declaration.send")
-    def test_get_parser_class_no_valid_parser(self, m, *args) -> None:
-        """
-        GIVEN:
-            - No parser declared for a given mimetype
-            - Parser declared for a different mimetype
-        WHEN:
-            - Attempt to get parser for the given mimetype
-        THEN:
-            - No parser class is returned
-        """
-
-        class DummyParser:
-            pass
-
-        m.return_value = (
-            (
-                None,
-                {
-                    "weight": 0,
-                    "parser": DummyParser,
-                    "mime_types": {"application/pdf": ".pdf"},
-                },
-            ),
-        )
-
-        self.assertIsNone(get_parser_class_for_mime_type("image/tiff"))
-
-
 class TestParserAvailability(TestCase):
     def test_tesseract_parser(self) -> None:
         """
@@ -151,7 +35,7 @@ class TestParserAvailability(TestCase):
             self.assertIn(ext, supported_exts)
             self.assertEqual(get_default_file_extension(mime_type), ext)
             self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
+                get_parser_registry().get_parser_for_file(mime_type, "")(),
                 RasterisedDocumentParser,
             )
 
@@ -175,7 +59,7 @@ class TestParserAvailability(TestCase):
             self.assertIn(ext, supported_exts)
             self.assertEqual(get_default_file_extension(mime_type), ext)
             self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
+                get_parser_registry().get_parser_for_file(mime_type, "")(),
                 TextDocumentParser,
             )
 
@@ -198,22 +82,23 @@ class TestParserAvailability(TestCase):
             ),
         ]
 
-        # Force the app ready to notice the settings override
-        with override_settings(TIKA_ENABLED=True, INSTALLED_APPS=["paperless_tika"]):
-            app = apps.get_app_config("paperless_tika")
-            app.ready()
+        self.addCleanup(reset_parser_registry)
+
+        # Reset and rebuild the registry with Tika enabled.
+        with override_settings(TIKA_ENABLED=True):
+            reset_parser_registry()
             supported_exts = get_supported_file_extensions()
 
-        for mime_type, ext in supported_mimes_and_exts:
-            self.assertIn(ext, supported_exts)
-            self.assertEqual(get_default_file_extension(mime_type), ext)
-            self.assertIsInstance(
-                get_parser_class_for_mime_type(mime_type)(logging_group=None),
-                TikaDocumentParser,
-            )
+            for mime_type, ext in supported_mimes_and_exts:
+                self.assertIn(ext, supported_exts)
+                self.assertEqual(get_default_file_extension(mime_type), ext)
+                self.assertIsInstance(
+                    get_parser_registry().get_parser_for_file(mime_type, "")(),
+                    TikaDocumentParser,
+                )
 
     def test_no_parser_for_mime(self) -> None:
-        self.assertIsNone(get_parser_class_for_mime_type("text/sdgsdf"))
+        self.assertIsNone(get_parser_registry().get_parser_for_file("text/sdgsdf", ""))
 
     def test_default_extension(self) -> None:
         # Test no parser declared still returns a an extension

src/documents/views.py

@@ -7,7 +7,6 @@ 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
@@ -159,7 +158,6 @@ from documents.models import UiSettings
 from documents.models import Workflow
 from documents.models import WorkflowAction
 from documents.models import WorkflowTrigger
-from documents.parsers import get_parser_class_for_mime_type
 from documents.permissions import AcknowledgeTasksPermissions
 from documents.permissions import PaperlessAdminPermissions
 from documents.permissions import PaperlessNotePermissions
@@ -227,7 +225,7 @@ 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.parsers.registry import get_parser_registry
 from paperless.serialisers import GroupSerializer
 from paperless.serialisers import UserSerializer
 from paperless.views import StandardPagination
@@ -1084,17 +1082,17 @@ class DocumentViewSet(
         if not Path(file).is_file():
             return None
 
-        parser_class = get_parser_class_for_mime_type(mime_type)
+        parser_class = get_parser_registry().get_parser_for_file(
+            mime_type,
+            Path(file).name,
+            Path(file),
+        )
         if parser_class:
-            parser = parser_class(progress_callback=None, logging_group=None)
-            cm = parser if isinstance(parser, ParserProtocol) else nullcontext(parser)
-
             try:
-                with cm:
+                with parser_class() as parser:
                     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.
                 return []
         else:  # pragma: no cover
             logger.warning(f"No parser for {mime_type}")

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: 2026-03-21 09:25+0000\n"
+"POT-Creation-Date: 2026-03-22 13:54+0000\n"
 "PO-Revision-Date: 2022-02-17 04:17\n"
 "Last-Translator: \n"
 "Language-Team: English\n"
@@ -1300,7 +1300,7 @@ msgid "workflow runs"
 msgstr ""
 
 #: documents/serialisers.py:463 documents/serialisers.py:815
-#: documents/serialisers.py:2501 documents/views.py:1992
+#: documents/serialisers.py:2501 documents/views.py:1990
 #: paperless_mail/serialisers.py:143
 msgid "Insufficient permissions."
 msgstr ""
@@ -1341,7 +1341,7 @@ msgstr ""
 msgid "Duplicate document identifiers are not allowed."
 msgstr ""
 
-#: documents/serialisers.py:2587 documents/views.py:3598
+#: documents/serialisers.py:2587 documents/views.py:3596
 #, python-format
 msgid "Documents not found: %(ids)s"
 msgstr ""
@@ -1605,24 +1605,24 @@ msgstr ""
 msgid "Unable to parse URI {value}"
 msgstr ""
 
-#: documents/views.py:1985
+#: documents/views.py:1983
 msgid "Invalid more_like_id"
 msgstr ""
 
-#: documents/views.py:3610
+#: documents/views.py:3608
 #, python-format
 msgid "Insufficient permissions to share document %(id)s."
 msgstr ""
 
-#: documents/views.py:3653
+#: documents/views.py:3651
 msgid "Bundle is already being processed."
 msgstr ""
 
-#: documents/views.py:3710
+#: documents/views.py:3708
 msgid "The share link bundle is still being prepared. Please try again later."
 msgstr ""
 
-#: documents/views.py:3720
+#: documents/views.py:3718
 msgid "The share link bundle is unavailable."
 msgstr ""
 
@@ -1862,151 +1862,151 @@ msgstr ""
 msgid "paperless application settings"
 msgstr ""
 
-#: paperless/settings/__init__.py:521
+#: paperless/settings/__init__.py:518
 msgid "English (US)"
 msgstr ""
 
-#: paperless/settings/__init__.py:522
+#: paperless/settings/__init__.py:519
 msgid "Arabic"
 msgstr ""
 
-#: paperless/settings/__init__.py:523
+#: paperless/settings/__init__.py:520
 msgid "Afrikaans"
 msgstr ""
 
-#: paperless/settings/__init__.py:524
+#: paperless/settings/__init__.py:521
 msgid "Belarusian"
 msgstr ""
 
-#: paperless/settings/__init__.py:525
+#: paperless/settings/__init__.py:522
 msgid "Bulgarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:526
+#: paperless/settings/__init__.py:523
 msgid "Catalan"
 msgstr ""
 
-#: paperless/settings/__init__.py:527
+#: paperless/settings/__init__.py:524
 msgid "Czech"
 msgstr ""
 
-#: paperless/settings/__init__.py:528
+#: paperless/settings/__init__.py:525
 msgid "Danish"
 msgstr ""
 
-#: paperless/settings/__init__.py:529
+#: paperless/settings/__init__.py:526
 msgid "German"
 msgstr ""
 
-#: paperless/settings/__init__.py:530
+#: paperless/settings/__init__.py:527
 msgid "Greek"
 msgstr ""
 
-#: paperless/settings/__init__.py:531
+#: paperless/settings/__init__.py:528
 msgid "English (GB)"
 msgstr ""
 
-#: paperless/settings/__init__.py:532
+#: paperless/settings/__init__.py:529
 msgid "Spanish"
 msgstr ""
 
-#: paperless/settings/__init__.py:533
+#: paperless/settings/__init__.py:530
 msgid "Persian"
 msgstr ""
 
-#: paperless/settings/__init__.py:534
+#: paperless/settings/__init__.py:531
 msgid "Finnish"
 msgstr ""
 
-#: paperless/settings/__init__.py:535
+#: paperless/settings/__init__.py:532
 msgid "French"
 msgstr ""
 
-#: paperless/settings/__init__.py:536
+#: paperless/settings/__init__.py:533
 msgid "Hungarian"
 msgstr ""
 
-#: paperless/settings/__init__.py:537
+#: paperless/settings/__init__.py:534
 msgid "Indonesian"
 msgstr ""
 
-#: paperless/settings/__init__.py:538
+#: paperless/settings/__init__.py:535
 msgid "Italian"
 msgstr ""
 
-#: paperless/settings/__init__.py:539
+#: paperless/settings/__init__.py:536
 msgid "Japanese"
 msgstr ""
 
-#: paperless/settings/__init__.py:540
+#: paperless/settings/__init__.py:537
 msgid "Korean"
 msgstr ""
 
-#: paperless/settings/__init__.py:541
+#: paperless/settings/__init__.py:538
 msgid "Luxembourgish"
 msgstr ""
 
-#: paperless/settings/__init__.py:542
+#: paperless/settings/__init__.py:539
 msgid "Norwegian"
 msgstr ""
 
-#: paperless/settings/__init__.py:543
+#: paperless/settings/__init__.py:540
 msgid "Dutch"
 msgstr ""
 
-#: paperless/settings/__init__.py:544
+#: paperless/settings/__init__.py:541
 msgid "Polish"
 msgstr ""
 
-#: paperless/settings/__init__.py:545
+#: paperless/settings/__init__.py:542
 msgid "Portuguese (Brazil)"
 msgstr ""
 
-#: paperless/settings/__init__.py:546
+#: paperless/settings/__init__.py:543
 msgid "Portuguese"
 msgstr ""
 
-#: paperless/settings/__init__.py:547
+#: paperless/settings/__init__.py:544
 msgid "Romanian"
 msgstr ""
 
-#: paperless/settings/__init__.py:548
+#: paperless/settings/__init__.py:545
 msgid "Russian"
 msgstr ""
 
-#: paperless/settings/__init__.py:549
+#: paperless/settings/__init__.py:546
 msgid "Slovak"
 msgstr ""
 
-#: paperless/settings/__init__.py:550
+#: paperless/settings/__init__.py:547
 msgid "Slovenian"
 msgstr ""
 
-#: paperless/settings/__init__.py:551
+#: paperless/settings/__init__.py:548
 msgid "Serbian"
 msgstr ""
 
-#: paperless/settings/__init__.py:552
+#: paperless/settings/__init__.py:549
 msgid "Swedish"
 msgstr ""
 
-#: paperless/settings/__init__.py:553
+#: paperless/settings/__init__.py:550
 msgid "Turkish"
 msgstr ""
 
-#: paperless/settings/__init__.py:554
+#: paperless/settings/__init__.py:551
 msgid "Ukrainian"
 msgstr ""
 
-#: paperless/settings/__init__.py:555
+#: paperless/settings/__init__.py:552
 msgid "Vietnamese"
 msgstr ""
 
-#: paperless/settings/__init__.py:556
+#: paperless/settings/__init__.py:553
 msgid "Chinese Simplified"
 msgstr ""
 
-#: paperless/settings/__init__.py:557
+#: paperless/settings/__init__.py:554
 msgid "Chinese Traditional"
 msgstr ""
 
@@ -2052,7 +2052,7 @@ msgid ""
 "process all matching rules that you have defined."
 msgstr ""
 
-#: paperless_mail/apps.py:11
+#: paperless_mail/apps.py:8
 msgid "Paperless mail"
 msgstr ""
 

src/paperless/checks.py

@@ -3,6 +3,7 @@ import os
 import pwd
 import shutil
 import stat
+import subprocess
 from pathlib import Path
 
 from django.conf import settings
@@ -299,3 +300,62 @@ def check_deprecated_db_settings(
         )
 
     return warnings
+
+
+@register()
+def check_remote_parser_configured(app_configs, **kwargs) -> list[Error]:
+    if settings.REMOTE_OCR_ENGINE == "azureai" and not (
+        settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
+    ):
+        return [
+            Error(
+                "Azure AI remote parser requires endpoint and API key to be configured.",
+            ),
+        ]
+
+    return []
+
+
+def get_tesseract_langs():
+    proc = subprocess.run(
+        [shutil.which("tesseract"), "--list-langs"],
+        capture_output=True,
+    )
+
+    # Decode bytes to string, split on newlines, trim out the header
+    proc_lines = proc.stdout.decode("utf8", errors="ignore").strip().split("\n")[1:]
+
+    return [x.strip() for x in proc_lines]
+
+
+@register()
+def check_default_language_available(app_configs, **kwargs):
+    errs = []
+
+    if not settings.OCR_LANGUAGE:
+        errs.append(
+            Warning(
+                "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE. "
+                "This means that tesseract will fallback to english.",
+            ),
+        )
+        return errs
+
+    # binaries_check in paperless will check and report if this doesn't exist
+    # So skip trying to do anything here and let that handle missing binaries
+    if shutil.which("tesseract") is not None:
+        installed_langs = get_tesseract_langs()
+
+        specified_langs = [x.strip() for x in settings.OCR_LANGUAGE.split("+")]
+
+        for lang in specified_langs:
+            if lang not in installed_langs:
+                errs.append(
+                    Error(
+                        f"The selected ocr language {lang} is "
+                        f"not installed. Paperless cannot OCR your documents "
+                        f"without it. Please fix PAPERLESS_OCR_LANGUAGE.",
+                    ),
+                )
+
+    return errs

src/paperless/parsers/registry.py

@@ -33,6 +33,7 @@ name, version, author, url, supported_mime_types (callable), score (callable).
 from __future__ import annotations
 
 import logging
+import threading
 from importlib.metadata import entry_points
 from typing import TYPE_CHECKING
 
@@ -49,6 +50,7 @@ logger = logging.getLogger("paperless.parsers.registry")
 
 _registry: ParserRegistry | None = None
 _discovery_complete: bool = False
+_lock = threading.Lock()
 
 # Attribute names that every registered external parser class must expose.
 _REQUIRED_ATTRS: tuple[str, ...] = (
@@ -74,7 +76,6 @@ def get_parser_registry() -> ParserRegistry:
     1. Creates a new ParserRegistry.
     2. Calls register_defaults to install built-in parsers.
     3. Calls discover to load third-party plugins via importlib.metadata entrypoints.
-    4. Calls log_summary to emit a startup summary.
 
     Subsequent calls return the same instance immediately.
 
@@ -85,14 +86,15 @@ def get_parser_registry() -> ParserRegistry:
     """
     global _registry, _discovery_complete
 
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
+    with _lock:
+        if _registry is None:
+            r = ParserRegistry()
+            r.register_defaults()
+            _registry = r
 
-    if not _discovery_complete:
-        _registry.discover()
-        _registry.log_summary()
-        _discovery_complete = True
+        if not _discovery_complete:
+            _registry.discover()
+            _discovery_complete = True
 
     return _registry
 
@@ -113,9 +115,11 @@ def init_builtin_parsers() -> None:
     """
     global _registry
 
-    if _registry is None:
-        _registry = ParserRegistry()
-        _registry.register_defaults()
+    with _lock:
+        if _registry is None:
+            r = ParserRegistry()
+            r.register_defaults()
+            _registry = r
 
 
 def reset_parser_registry() -> None:
@@ -304,6 +308,23 @@ class ParserRegistry:
                 getattr(cls, "url", "unknown"),
             )
 
+    # ------------------------------------------------------------------
+    # Inspection helpers
+    # ------------------------------------------------------------------
+
+    def all_parsers(self) -> list[type[ParserProtocol]]:
+        """Return all registered parser classes (external first, then builtins).
+
+        Used by compatibility wrappers that need to iterate every parser to
+        compute the full set of supported MIME types and file extensions.
+
+        Returns
+        -------
+        list[type[ParserProtocol]]
+            External parsers followed by built-in parsers.
+        """
+        return [*self._external, *self._builtins]
+
     # ------------------------------------------------------------------
     # Parser resolution
     # ------------------------------------------------------------------
@@ -334,7 +355,7 @@ class ParserRegistry:
         mime_type:
             The detected MIME type of the file.
         filename:
-            The original filename, including extension.
+            The original filename, including extension.  May be empty in some cases
         path:
             Optional filesystem path to the file. Forwarded to each
             parser's score method.

src/paperless/settings/__init__.py

@@ -121,10 +121,7 @@ INSTALLED_APPS = [
     "django_extensions",
     "paperless",
     "documents.apps.DocumentsConfig",
-    "paperless_tesseract.apps.PaperlessTesseractConfig",
-    "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
-    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -974,8 +971,8 @@ TIKA_GOTENBERG_ENDPOINT = os.getenv(
     "http://localhost:3000",
 )
 
-if TIKA_ENABLED:
-    INSTALLED_APPS.append("paperless_tika.apps.PaperlessTikaConfig")
+# Tika parser is now integrated into the main parser registry
+# No separate Django app needed
 
 AUDIT_LOG_ENABLED = get_bool_from_env("PAPERLESS_AUDIT_LOG_ENABLED", "true")
 if AUDIT_LOG_ENABLED:

src/paperless/tests/parsers/conftest.py

@@ -90,35 +90,6 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
         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
 # ------------------------------------------------------------------

src/paperless/tests/parsers/test_remote_parser.py

@@ -277,20 +277,20 @@ class TestRemoteParserParse:
     def test_parse_returns_text_from_azure(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_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,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         archive = remote_parser.get_archive_path()
         assert archive is not None
@@ -300,11 +300,11 @@ class TestRemoteParserParse:
     def test_parse_closes_client_on_success(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
         remote_parser.configure(ParserContext())
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         azure_client.close.assert_called_once()
 
@@ -312,9 +312,9 @@ class TestRemoteParserParse:
     def test_parse_sets_empty_text_when_not_configured(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_text() == ""
         assert remote_parser.get_archive_path() is None
@@ -328,10 +328,10 @@ class TestRemoteParserParse:
     def test_get_date_always_none(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         assert remote_parser.get_date() is None
 
@@ -345,33 +345,33 @@ class TestRemoteParserParseError:
     def test_parse_returns_none_on_azure_error(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
         failing_azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_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,
+        simple_digital_pdf_file: Path,
         failing_azure_client: Mock,
     ) -> None:
-        remote_parser.parse(sample_pdf_file, "application/pdf")
+        remote_parser.parse(simple_digital_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,
+        simple_digital_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")
+        remote_parser.parse(simple_digital_pdf_file, "application/pdf")
 
         mock_log.error.assert_called_once()
         assert "Azure AI Vision parsing failed" in mock_log.error.call_args[0][0]
@@ -386,18 +386,18 @@ class TestRemoteParserPageCount:
     def test_page_count_for_pdf(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        count = remote_parser.get_page_count(sample_pdf_file, "application/pdf")
+        count = remote_parser.get_page_count(simple_digital_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,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        count = remote_parser.get_page_count(sample_pdf_file, "image/png")
+        count = remote_parser.get_page_count(simple_digital_pdf_file, "image/png")
         assert count is None
 
     def test_page_count_returns_none_for_invalid_pdf(
@@ -420,25 +420,31 @@ class TestRemoteParserMetadata:
     def test_extract_metadata_non_pdf_returns_empty(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "image/png")
+        result = remote_parser.extract_metadata(simple_digital_pdf_file, "image/png")
         assert result == []
 
     def test_extract_metadata_pdf_returns_list(
         self,
         remote_parser: RemoteDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        result = remote_parser.extract_metadata(
+            simple_digital_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,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        result = remote_parser.extract_metadata(sample_pdf_file, "application/pdf")
+        result = remote_parser.extract_metadata(
+            simple_digital_pdf_file,
+            "application/pdf",
+        )
         for entry in result:
             assert "namespace" in entry
             assert "prefix" in entry

src/paperless/tests/parsers/test_tika_parser.py

@@ -77,10 +77,10 @@ class TestTikaParserRegistryInterface:
     def test_get_page_count_returns_int_with_pdf_archive(
         self,
         tika_parser: TikaDocumentParser,
-        sample_pdf_file: Path,
+        simple_digital_pdf_file: Path,
     ) -> None:
-        tika_parser._archive_path = sample_pdf_file
-        count = tika_parser.get_page_count(sample_pdf_file, "application/pdf")
+        tika_parser._archive_path = simple_digital_pdf_file
+        count = tika_parser.get_page_count(simple_digital_pdf_file, "application/pdf")
         assert isinstance(count, int)
         assert count > 0
 

src/paperless/tests/test_checks.py

@@ -5,6 +5,7 @@ from pathlib import Path
 from unittest import mock
 
 import pytest
+from django.core.checks import ERROR
 from django.core.checks import Error
 from django.core.checks import Warning
 from pytest_django.fixtures import SettingsWrapper
@@ -12,7 +13,9 @@ from pytest_mock import MockerFixture
 
 from paperless.checks import audit_log_check
 from paperless.checks import binaries_check
+from paperless.checks import check_default_language_available
 from paperless.checks import check_deprecated_db_settings
+from paperless.checks import check_remote_parser_configured
 from paperless.checks import check_v3_minimum_upgrade_version
 from paperless.checks import debug_mode_check
 from paperless.checks import paths_check
@@ -626,3 +629,116 @@ class TestV3MinimumUpgradeVersionCheck:
         conn.introspection.table_names.side_effect = OperationalError("DB unavailable")
         mocker.patch.dict("paperless.checks.connections", {"default": conn})
         assert check_v3_minimum_upgrade_version(None) == []
+
+
+class TestRemoteParserChecks:
+    def test_no_engine(self, settings: SettingsWrapper) -> None:
+        settings.REMOTE_OCR_ENGINE = None
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 0
+
+    def test_azure_no_endpoint(self, settings: SettingsWrapper) -> None:
+
+        settings.REMOTE_OCR_ENGINE = "azureai"
+        settings.REMOTE_OCR_API_KEY = "somekey"
+        settings.REMOTE_OCR_ENDPOINT = None
+
+        msgs = check_remote_parser_configured(None)
+
+        assert len(msgs) == 1
+
+        msg = msgs[0]
+
+        assert (
+            "Azure AI remote parser requires endpoint and API key to be configured."
+            in msg.msg
+        )
+
+
+class TestTesseractChecks:
+    def test_default_language(self) -> None:
+        check_default_language_available(None)
+
+    def test_no_language(self, settings: SettingsWrapper) -> None:
+
+        settings.OCR_LANGUAGE = ""
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert (
+            "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE" in msg.msg
+        )
+
+    def test_invalid_language(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+
+        settings.OCR_LANGUAGE = "ita"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["deu", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert msg.level == ERROR
+        assert "The selected ocr language ita is not installed" in msg.msg
+
+    def test_multi_part_language(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - An OCR language which is multi part (ie chi-sim)
+            - The language is correctly formatted
+        WHEN:
+            - Installed packages are checked
+        THEN:
+            - No errors are reported
+        """
+
+        settings.OCR_LANGUAGE = "chi_sim"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["chi_sim", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 0
+
+    def test_multi_part_language_bad_format(
+        self,
+        settings: SettingsWrapper,
+        mocker: MockerFixture,
+    ) -> None:
+        """
+        GIVEN:
+            - An OCR language which is multi part (ie chi-sim)
+            - The language is correctly NOT formatted
+        WHEN:
+            - Installed packages are checked
+        THEN:
+            - No errors are reported
+        """
+        settings.OCR_LANGUAGE = "chi-sim"
+
+        tesser_lang_mock = mocker.patch("paperless.checks.get_tesseract_langs")
+        tesser_lang_mock.return_value = ["chi_sim", "eng"]
+
+        msgs = check_default_language_available(None)
+
+        assert len(msgs) == 1
+        msg = msgs[0]
+
+        assert msg.level == ERROR
+        assert "The selected ocr language chi-sim is not installed" in msg.msg

src/paperless_mail/apps.py

@@ -1,18 +1,8 @@
 from django.apps import AppConfig
-from django.conf import settings
 from django.utils.translation import gettext_lazy as _
 
-from paperless_mail.signals import mail_consumer_declaration
-
 
 class PaperlessMailConfig(AppConfig):
     name = "paperless_mail"
 
     verbose_name = _("Paperless mail")
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        if settings.TIKA_ENABLED:
-            document_consumer_declaration.connect(mail_consumer_declaration)
-        AppConfig.ready(self)

src/paperless_mail/signals.py

@@ -1,19 +0,0 @@
-def get_parser(*args, **kwargs):
-    from paperless.parsers.mail import MailDocumentParser
-
-    # 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):
-    return {
-        "parser": get_parser,
-        "weight": 20,
-        "mime_types": {
-            "message/rfc822": ".eml",
-        },
-    }

src/paperless_remote/__init__.py

@@ -1,4 +0,0 @@
-# this is here so that django finds the checks.
-from paperless_remote.checks import check_remote_parser_configured
-
-__all__ = ["check_remote_parser_configured"]

src/paperless_remote/apps.py

@@ -1,14 +0,0 @@
-from django.apps import AppConfig
-
-from paperless_remote.signals import remote_consumer_declaration
-
-
-class PaperlessRemoteParserConfig(AppConfig):
-    name = "paperless_remote"
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        document_consumer_declaration.connect(remote_consumer_declaration)
-
-        AppConfig.ready(self)

src/paperless_remote/checks.py

@@ -1,17 +0,0 @@
-from django.conf import settings
-from django.core.checks import Error
-from django.core.checks import register
-
-
-@register()
-def check_remote_parser_configured(app_configs, **kwargs):
-    if settings.REMOTE_OCR_ENGINE == "azureai" and not (
-        settings.REMOTE_OCR_ENDPOINT and settings.REMOTE_OCR_API_KEY
-    ):
-        return [
-            Error(
-                "Azure AI remote parser requires endpoint and API key to be configured.",
-            ),
-        ]
-
-    return []

src/paperless_remote/signals.py

@@ -1,38 +0,0 @@
-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() -> dict[str, str]:
-    from django.conf import settings
-
-    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: Any, **kwargs: Any) -> dict[str, Any]:
-    return {
-        "parser": get_parser,
-        "weight": 5,
-        "mime_types": get_supported_mime_types(),
-    }

src/paperless_remote/tests/test_checks.py

@@ -1,24 +0,0 @@
-from unittest import TestCase
-
-from django.test import override_settings
-
-from paperless_remote import check_remote_parser_configured
-
-
-class TestChecks(TestCase):
-    @override_settings(REMOTE_OCR_ENGINE=None)
-    def test_no_engine(self) -> None:
-        msgs = check_remote_parser_configured(None)
-        self.assertEqual(len(msgs), 0)
-
-    @override_settings(REMOTE_OCR_ENGINE="azureai")
-    @override_settings(REMOTE_OCR_API_KEY="somekey")
-    @override_settings(REMOTE_OCR_ENDPOINT=None)
-    def test_azure_no_endpoint(self) -> None:
-        msgs = check_remote_parser_configured(None)
-        self.assertEqual(len(msgs), 1)
-        self.assertTrue(
-            msgs[0].msg.startswith(
-                "Azure AI remote parser requires endpoint and API key to be configured.",
-            ),
-        )

src/paperless_tesseract/__init__.py

@@ -1,5 +0,0 @@
-# this is here so that django finds the checks.
-from paperless_tesseract.checks import check_default_language_available
-from paperless_tesseract.checks import get_tesseract_langs
-
-__all__ = ["check_default_language_available", "get_tesseract_langs"]

src/paperless_tesseract/apps.py

@@ -1,14 +0,0 @@
-from django.apps import AppConfig
-
-from paperless_tesseract.signals import tesseract_consumer_declaration
-
-
-class PaperlessTesseractConfig(AppConfig):
-    name = "paperless_tesseract"
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        document_consumer_declaration.connect(tesseract_consumer_declaration)
-
-        AppConfig.ready(self)

src/paperless_tesseract/checks.py

@@ -1,52 +0,0 @@
-import shutil
-import subprocess
-
-from django.conf import settings
-from django.core.checks import Error
-from django.core.checks import Warning
-from django.core.checks import register
-
-
-def get_tesseract_langs():
-    proc = subprocess.run(
-        [shutil.which("tesseract"), "--list-langs"],
-        capture_output=True,
-    )
-
-    # Decode bytes to string, split on newlines, trim out the header
-    proc_lines = proc.stdout.decode("utf8", errors="ignore").strip().split("\n")[1:]
-
-    return [x.strip() for x in proc_lines]
-
-
-@register()
-def check_default_language_available(app_configs, **kwargs):
-    errs = []
-
-    if not settings.OCR_LANGUAGE:
-        errs.append(
-            Warning(
-                "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE. "
-                "This means that tesseract will fallback to english.",
-            ),
-        )
-        return errs
-
-    # binaries_check in paperless will check and report if this doesn't exist
-    # So skip trying to do anything here and let that handle missing binaries
-    if shutil.which("tesseract") is not None:
-        installed_langs = get_tesseract_langs()
-
-        specified_langs = [x.strip() for x in settings.OCR_LANGUAGE.split("+")]
-
-        for lang in specified_langs:
-            if lang not in installed_langs:
-                errs.append(
-                    Error(
-                        f"The selected ocr language {lang} is "
-                        f"not installed. Paperless cannot OCR your documents "
-                        f"without it. Please fix PAPERLESS_OCR_LANGUAGE.",
-                    ),
-                )
-
-    return errs

src/paperless_tesseract/signals.py

@@ -1,34 +0,0 @@
-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: Any, **kwargs: Any) -> dict[str, Any]:
-    return {
-        "parser": get_parser,
-        "weight": 0,
-        "mime_types": {
-            "application/pdf": ".pdf",
-            "image/jpeg": ".jpg",
-            "image/png": ".png",
-            "image/tiff": ".tif",
-            "image/gif": ".gif",
-            "image/bmp": ".bmp",
-            "image/webp": ".webp",
-            "image/heic": ".heic",
-        },
-    }

src/paperless_tesseract/tests/test_checks.py

@@ -1,67 +0,0 @@
-from unittest import mock
-
-from django.core.checks import ERROR
-from django.test import TestCase
-from django.test import override_settings
-
-from paperless_tesseract import check_default_language_available
-
-
-class TestChecks(TestCase):
-    def test_default_language(self) -> None:
-        check_default_language_available(None)
-
-    @override_settings(OCR_LANGUAGE="")
-    def test_no_language(self) -> None:
-        msgs = check_default_language_available(None)
-        self.assertEqual(len(msgs), 1)
-        self.assertTrue(
-            msgs[0].msg.startswith(
-                "No OCR language has been specified with PAPERLESS_OCR_LANGUAGE",
-            ),
-        )
-
-    @override_settings(OCR_LANGUAGE="ita")
-    @mock.patch("paperless_tesseract.checks.get_tesseract_langs")
-    def test_invalid_language(self, m) -> None:
-        m.return_value = ["deu", "eng"]
-        msgs = check_default_language_available(None)
-        self.assertEqual(len(msgs), 1)
-        self.assertEqual(msgs[0].level, ERROR)
-
-    @override_settings(OCR_LANGUAGE="chi_sim")
-    @mock.patch("paperless_tesseract.checks.get_tesseract_langs")
-    def test_multi_part_language(self, m) -> None:
-        """
-        GIVEN:
-            - An OCR language which is multi part (ie chi-sim)
-            - The language is correctly formatted
-        WHEN:
-            - Installed packages are checked
-        THEN:
-            - No errors are reported
-        """
-        m.return_value = ["chi_sim", "eng"]
-
-        msgs = check_default_language_available(None)
-
-        self.assertEqual(len(msgs), 0)
-
-    @override_settings(OCR_LANGUAGE="chi-sim")
-    @mock.patch("paperless_tesseract.checks.get_tesseract_langs")
-    def test_multi_part_language_bad_format(self, m) -> None:
-        """
-        GIVEN:
-            - An OCR language which is multi part (ie chi-sim)
-            - The language is correctly NOT formatted
-        WHEN:
-            - Installed packages are checked
-        THEN:
-            - No errors are reported
-        """
-        m.return_value = ["chi_sim", "eng"]
-
-        msgs = check_default_language_available(None)
-
-        self.assertEqual(len(msgs), 1)
-        self.assertEqual(msgs[0].level, ERROR)

src/paperless_text/apps.py

@@ -1,14 +0,0 @@
-from django.apps import AppConfig
-
-from paperless_text.signals import text_consumer_declaration
-
-
-class PaperlessTextConfig(AppConfig):
-    name = "paperless_text"
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        document_consumer_declaration.connect(text_consumer_declaration)
-
-        AppConfig.ready(self)

src/paperless_text/signals.py

@@ -1,29 +0,0 @@
-from __future__ import annotations
-
-from typing import Any
-
-
-def get_parser(*args: Any, **kwargs: Any) -> Any:
-    from paperless.parsers.text import TextDocumentParser
-
-    # 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(*args, **kwargs)
-
-
-def text_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
-    return {
-        "parser": get_parser,
-        "weight": 10,
-        "mime_types": {
-            "text/plain": ".txt",
-            "text/csv": ".csv",
-            "application/csv": ".csv",
-        },
-    }

src/paperless_tika/apps.py

@@ -1,15 +0,0 @@
-from django.apps import AppConfig
-from django.conf import settings
-
-from paperless_tika.signals import tika_consumer_declaration
-
-
-class PaperlessTikaConfig(AppConfig):
-    name = "paperless_tika"
-
-    def ready(self) -> None:
-        from documents.signals import document_consumer_declaration
-
-        if settings.TIKA_ENABLED:
-            document_consumer_declaration.connect(tika_consumer_declaration)
-        AppConfig.ready(self)

src/paperless_tika/signals.py

@@ -1,33 +0,0 @@
-def get_parser(*args, **kwargs):
-    from paperless.parsers.tika import TikaDocumentParser
-
-    # 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):
-    return {
-        "parser": get_parser,
-        "weight": 10,
-        "mime_types": {
-            "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",
-        },
-    }

uv.lock

@@ -361,31 +361,31 @@ wheels = [
 
 [[package]]
 name = "cbor2"
-version = "5.8.0"
+version = "5.9.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/d9/8e/8b4fdde28e42ffcd741a37f4ffa9fb59cd4fe01625b544dfcfd9ccb54f01/cbor2-5.8.0.tar.gz", hash = "sha256:b19c35fcae9688ac01ef75bad5db27300c2537eb4ee00ed07e05d8456a0d4931", size = 107825, upload-time = "2025-12-30T18:44:22.455Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/bd/cb/09939728be094d155b5d4ac262e39877875f5f7e36eea66beb359f647bd0/cbor2-5.9.0.tar.gz", hash = "sha256:85c7a46279ac8f226e1059275221e6b3d0e370d2bb6bd0500f9780781615bcea", size = 111231, upload-time = "2026-03-22T15:56:50.638Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/88/4b/623435ef9b98e86b6956a41863d39ff4fe4d67983948b5834f55499681dd/cbor2-5.8.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:18ac191640093e6c7fbcb174c006ffec4106c3d8ab788e70272c1c4d933cbe11", size = 69875, upload-time = "2025-12-30T18:43:35.888Z" },
-    { url = "https://files.pythonhosted.org/packages/58/17/f664201080b2a7d0f57c16c8e9e5922013b92f202e294863ec7e75b7ff7f/cbor2-5.8.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fddee9103a17d7bed5753f0c7fc6663faa506eb953e50d8287804eccf7b048e6", size = 268316, upload-time = "2025-12-30T18:43:37.161Z" },
-    { url = "https://files.pythonhosted.org/packages/d0/e1/072745b4ff01afe9df2cd627f8fc51a1acedb5d3d1253765625d2929db91/cbor2-5.8.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8d2ea26fad620aba5e88d7541be8b10c5034a55db9a23809b7cb49f36803f05b", size = 258874, upload-time = "2025-12-30T18:43:38.878Z" },
-    { url = "https://files.pythonhosted.org/packages/a7/10/61c262b886d22b62c56e8aac6d10fa06d0953c997879ab882a31a624952b/cbor2-5.8.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:de68b4b310b072b082d317adc4c5e6910173a6d9455412e6183d72c778d1f54c", size = 261971, upload-time = "2025-12-30T18:43:40.401Z" },
-    { url = "https://files.pythonhosted.org/packages/7e/42/b7862f5e64364b10ad120ea53e87ec7e891fb268cb99c572348e647cf7e9/cbor2-5.8.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:418d2cf0e03e90160fa1474c05a40fe228bbb4a92d1628bdbbd13a48527cb34d", size = 254151, upload-time = "2025-12-30T18:43:41.938Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/4f/3a16e3e8fd7e5fd86751a4f1aad218a8d19a96e75ec3989c3e95a8fe1d8f/cbor2-5.8.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:4b3f91fa699a5ce22470e973601c62dd9d55dc3ca20ee446516ac075fcab27c9", size = 70270, upload-time = "2025-12-30T18:43:46.005Z" },
-    { url = "https://files.pythonhosted.org/packages/38/81/0d0cf0796fe8081492a61c45278f03def21a929535a492dd97c8438f5dbe/cbor2-5.8.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:518c118a5e00001854adb51f3164e647aa99b6a9877d2a733a28cb5c0a4d6857", size = 286242, upload-time = "2025-12-30T18:43:47.026Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/a9/fdab6c10190cfb8d639e01f2b168f2406fc847a2a6bc00e7de78c3381d0a/cbor2-5.8.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:cff2a1999e49cd51c23d1b6786a012127fd8f722c5946e82bd7ab3eb307443f3", size = 285412, upload-time = "2025-12-30T18:43:48.563Z" },
-    { url = "https://files.pythonhosted.org/packages/31/59/746a8e630996217a3afd523f583fcf7e3d16640d63f9a03f0f4e4f74b5b1/cbor2-5.8.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:4c4492160212374973cdc14e46f0565f2462721ef922b40f7ea11e7d613dfb2a", size = 278041, upload-time = "2025-12-30T18:43:49.92Z" },
-    { url = "https://files.pythonhosted.org/packages/0f/a3/f3bbeb6dedd45c6e0cddd627ea790dea295eaf82c83f0e2159b733365ebd/cbor2-5.8.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:546c7c7c4c6bcdc54a59242e0e82cea8f332b17b4465ae628718fef1fce401ca", size = 278185, upload-time = "2025-12-30T18:43:51.192Z" },
-    { url = "https://files.pythonhosted.org/packages/a6/0d/5a3f20bafaefeb2c1903d961416f051c0950f0d09e7297a3aa6941596b29/cbor2-5.8.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:6d8d104480845e2f28c6165b4c961bbe58d08cb5638f368375cfcae051c28015", size = 70332, upload-time = "2025-12-30T18:43:54.694Z" },
-    { url = "https://files.pythonhosted.org/packages/57/66/177a3f089e69db69c987453ab4934086408c3338551e4984734597be9f80/cbor2-5.8.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:43efee947e5ab67d406d6e0dc61b5dee9d2f5e89ae176f90677a3741a20ca2e7", size = 285985, upload-time = "2025-12-30T18:43:55.733Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/8e/9e17b8e4ed80a2ce97e2dfa5915c169dbb31599409ddb830f514b57f96cc/cbor2-5.8.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:be7ae582f50be539e09c134966d0fd63723fc4789b8dff1f6c2e3f24ae3eaf32", size = 285173, upload-time = "2025-12-30T18:43:57.321Z" },
-    { url = "https://files.pythonhosted.org/packages/cc/33/9f92e107d78f88ac22723ac15d0259d220ba98c1d855e51796317f4c4114/cbor2-5.8.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:50f5c709561a71ea7970b4cd2bf9eda4eccacc0aac212577080fdfe64183e7f5", size = 278395, upload-time = "2025-12-30T18:43:58.497Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/3f/46b80050a4a35ce5cf7903693864a9fdea7213567dc8faa6e25cb375c182/cbor2-5.8.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a6790ecc73aa93e76d2d9076fc42bf91a9e69f2295e5fa702e776dbe986465bd", size = 278330, upload-time = "2025-12-30T18:43:59.656Z" },
-    { url = "https://files.pythonhosted.org/packages/4b/0c/0654233d7543ac8a50f4785f172430ddc97538ba418eb305d6e529d1a120/cbor2-5.8.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:ad72381477133046ce217617d839ea4e9454f8b77d9a6351b229e214102daeb7", size = 70710, upload-time = "2025-12-30T18:44:03.209Z" },
-    { url = "https://files.pythonhosted.org/packages/84/62/4671d24e557d7f5a74a01b422c538925140c0495e57decde7e566f91d029/cbor2-5.8.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6da25190fad3434ce99876b11d4ca6b8828df6ca232cf7344cd14ae1166fb718", size = 285005, upload-time = "2025-12-30T18:44:05.109Z" },
-    { url = "https://files.pythonhosted.org/packages/87/85/0c67d763a08e848c9a80d7e4723ba497cce676f41bc7ca1828ae90a0a872/cbor2-5.8.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c13919e3a24c5a6d286551fa288848a4cedc3e507c58a722ccd134e461217d99", size = 282435, upload-time = "2025-12-30T18:44:06.465Z" },
-    { url = "https://files.pythonhosted.org/packages/b2/01/0650972b4dbfbebcfbe37cbba7fc3cd9019a8da6397ab3446e07175e342b/cbor2-5.8.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:f8c40d32e5972047a777f9bf730870828f3cf1c43b3eb96fd0429c57a1d3b9e6", size = 277493, upload-time = "2025-12-30T18:44:07.609Z" },
-    { url = "https://files.pythonhosted.org/packages/b3/6c/7704a4f32adc7f10f3b41ec067f500a4458f7606397af5e4cf2d368fd288/cbor2-5.8.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:7627894bc0b3d5d0807f31e3107e11b996205470c4429dc2bb4ef8bfe7f64e1e", size = 276085, upload-time = "2025-12-30T18:44:09.021Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/4f/101071f880b4da05771128c0b89f41e334cff044dee05fb013c8f4be661c/cbor2-5.8.0-py3-none-any.whl", hash = "sha256:3727d80f539567b03a7aa11890e57798c67092c38df9e6c23abb059e0f65069c", size = 24374, upload-time = "2025-12-30T18:44:21.476Z" },
+    { url = "https://files.pythonhosted.org/packages/43/aa/317c7118b8dda4c9563125c1a12c70c5b41e36677964a49c72b1aac061ec/cbor2-5.9.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:0485d3372fc832c5e16d4eb45fa1a20fc53e806e6c29a1d2b0d3e176cedd52b9", size = 70578, upload-time = "2026-03-22T15:56:03.835Z" },
+    { url = "https://files.pythonhosted.org/packages/31/43/fe29b1f897770011a5e7497f4523c2712282ee4a6cbf775ea6383fb7afb9/cbor2-5.9.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:a9d6e4e0f988b0e766509a8071975a8ee99f930e14a524620bf38083106158d2", size = 268738, upload-time = "2026-03-22T15:56:05.222Z" },
+    { url = "https://files.pythonhosted.org/packages/0a/1a/e494568f3d8aafbcdfe361df44c3bcf5cdab5183e25ea08e3d3f9fcf4075/cbor2-5.9.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5326336f633cc89dfe543c78829c16c3a6449c2c03277d1ddba99086c3323363", size = 262571, upload-time = "2026-03-22T15:56:06.411Z" },
+    { url = "https://files.pythonhosted.org/packages/42/2e/92acd6f87382fd44a34d9d7e85cc45372e6ba664040b72d1d9df648b25d0/cbor2-5.9.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:5e702b02d42a5ace45425b595ffe70fe35aebaf9a3cdfdc2c758b6189c744422", size = 262356, upload-time = "2026-03-22T15:56:08.236Z" },
+    { url = "https://files.pythonhosted.org/packages/3f/68/52c039a28688baeeb78b0be7483855e6c66ea05884a937444deede0c87b8/cbor2-5.9.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:2372d357d403e7912f104ff085950ffc82a5854d6d717f1ca1ce16a40a0ef5a7", size = 257604, upload-time = "2026-03-22T15:56:09.835Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/39/72d8a5a4b06565561ec28f4fcb41aff7bb77f51705c01f00b8254a2aca4f/cbor2-5.9.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:1f223dffb1bcdd2764665f04c1152943d9daa4bc124a576cd8dee1cad4264313", size = 71223, upload-time = "2026-03-22T15:56:13.68Z" },
+    { url = "https://files.pythonhosted.org/packages/09/fd/7ddf3d3153b54c69c3be77172b8d9aa3a9d74f62a7fbde614d53eaeed9a4/cbor2-5.9.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ae6c706ac1d85a0b3cb3395308fd0c4d55e3202b4760773675957e93cdff45fc", size = 287865, upload-time = "2026-03-22T15:56:14.813Z" },
+    { url = "https://files.pythonhosted.org/packages/db/9d/7ede2cc42f9bb4260492e7d29d2aab781eacbbcfb09d983de1e695077199/cbor2-5.9.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:4cd43d8fc374b31643b2830910f28177a606a7bc84975a62675dd3f2e320fc7b", size = 288246, upload-time = "2026-03-22T15:56:16.113Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/9d/588ebc7c5bc5843f609b05fe07be8575c7dec987735b0bbc908ac9c1264a/cbor2-5.9.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:4aa07b392cc3d76fb31c08a46a226b58c320d1c172ff3073e864409ced7bc50f", size = 280214, upload-time = "2026-03-22T15:56:17.519Z" },
+    { url = "https://files.pythonhosted.org/packages/f7/a1/6fc8f4b15c6a27e7fbb7966c30c2b4b18c274a3221fa2f5e6235502d34bc/cbor2-5.9.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:971d425b3a23b75953d8853d5f9911bdeefa09d759ee3b5e6b07b5ff3cbd9073", size = 282162, upload-time = "2026-03-22T15:56:18.975Z" },
+    { url = "https://files.pythonhosted.org/packages/81/c5/4901e21a8afe9448fd947b11e8f383903207cd6dd0800e5f5a386838de5b/cbor2-5.9.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:fbb06f34aa645b4deca66643bba3d400d20c15312d1fe88d429be60c1ab50f27", size = 71284, upload-time = "2026-03-22T15:56:22.836Z" },
+    { url = "https://files.pythonhosted.org/packages/1b/10/df643a381aebc3f05486de4813662bc58accb640fc3275cb276a75e89694/cbor2-5.9.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ac684fe195c39821fca70d18afbf748f728aefbfbf88456018d299e559b8cae0", size = 287682, upload-time = "2026-03-22T15:56:24.024Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/0c/8aa6b766059ae4a0ca1ec3ff96fe3823a69a7be880dba2e249f7fbe2700b/cbor2-5.9.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2a54fbb32cb828c214f7f333a707e4aec61182e7efdc06ea5d9596d3ecee624a", size = 288009, upload-time = "2026-03-22T15:56:25.305Z" },
+    { url = "https://files.pythonhosted.org/packages/74/07/6236bc25c183a9cf7e8062e5dddf9eae9b0b14ebf14a58a69fe5a1e872c6/cbor2-5.9.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:4753a6d1bc71054d9179557bc65740860f185095ccb401d46637fff028a5b3ec", size = 280437, upload-time = "2026-03-22T15:56:26.479Z" },
+    { url = "https://files.pythonhosted.org/packages/4e/0a/84328d23c3c68874ac6497edb9b1900579a1028efa54734df3f1762bbc15/cbor2-5.9.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:380e534482b843e43442b87d8777a7bf9bed20cb7526f89b780c3400f617304b", size = 282247, upload-time = "2026-03-22T15:56:28.644Z" },
+    { url = "https://files.pythonhosted.org/packages/08/7d/9ccc36d10ef96e6038e48046ebe1ce35a1e7814da0e1e204d09e6ef09b8d/cbor2-5.9.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:23606d31ba1368bd1b6602e3020ee88fe9523ca80e8630faf6b2fc904fd84560", size = 71500, upload-time = "2026-03-22T15:56:31.876Z" },
+    { url = "https://files.pythonhosted.org/packages/70/e1/a6cca2cc72e13f00030c6a649f57ae703eb2c620806ab70c40db8eab33fa/cbor2-5.9.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:0322296b9d52f55880e300ba8ba09ecf644303b99b51138bbb1c0fb644fa7c3e", size = 286953, upload-time = "2026-03-22T15:56:33.292Z" },
+    { url = "https://files.pythonhosted.org/packages/08/3c/24cd5ef488a957d90e016f200a3aad820e4c2f85edd61c9fe4523007a1ee/cbor2-5.9.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:422817286c1d0ce947fb2f7eca9212b39bddd7231e8b452e2d2cc52f15332dba", size = 285454, upload-time = "2026-03-22T15:56:34.703Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/35/dca96818494c0ba47cdd73e8d809b27fa91f8fa0ce32a068a09237687454/cbor2-5.9.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:9a4907e0c3035bb8836116854ed8e56d8aef23909d601fa59706320897ec2551", size = 279441, upload-time = "2026-03-22T15:56:35.888Z" },
+    { url = "https://files.pythonhosted.org/packages/a4/44/d3362378b16e53cf7e535a3f5aed8476e2109068154e24e31981ef5bde9e/cbor2-5.9.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:fb7afe77f8d269e42d7c4b515c6fd14f1ccc0625379fb6829b269f493d16eddd", size = 279673, upload-time = "2026-03-22T15:56:37.08Z" },
+    { url = "https://files.pythonhosted.org/packages/42/ff/b83492b096fbef26e9cb62c1a4bf2d3cef579ea7b33138c6c37c4ae66f67/cbor2-5.9.0-py3-none-any.whl", hash = "sha256:27695cbd70c90b8de5c4a284642c2836449b14e2c2e07e3ffe0744cb7669a01b", size = 24627, upload-time = "2026-03-22T15:56:48.847Z" },
 ]
 
 [[package]]