Fix: text parser get_parser forwards logging_group, drops progress_callback

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

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

pyproject.toml

@@ -60,7 +60,7 @@ dependencies = [
   "llama-index-llms-openai>=0.6.13",
   "llama-index-vector-stores-faiss>=0.5.2",
   "nltk~=3.9.1",
-  "ocrmypdf~=16.13.0",
+  "ocrmypdf~=17.3.0",
   "openai>=1.76",
   "pathvalidate~=3.3.1",
   "pdf2image~=1.17.0",

src/documents/consumer.py

@@ -51,6 +51,7 @@ from documents.templating.workflows import parse_w_workflow_placeholders
 from documents.utils import copy_basic_file_stats
 from documents.utils import copy_file_with_basic_stats
 from documents.utils import run_subprocess
+from paperless.parsers.remote import RemoteDocumentParser
 from paperless.parsers.text import TextDocumentParser
 from paperless_mail.parsers import MailDocumentParser
 
@@ -67,7 +68,7 @@ def _parser_cleanup(parser: DocumentParser) -> None:
 
     TODO(stumpylog): Remove me in the future
     """
-    if isinstance(parser, TextDocumentParser):
+    if isinstance(parser, (TextDocumentParser, RemoteDocumentParser)):
         parser.__exit__(None, None, None)
     else:
         parser.cleanup()
@@ -476,7 +477,10 @@ class ConsumerPlugin(
                     self.filename,
                     self.input_doc.mailrule_id,
                 )
-            elif isinstance(document_parser, TextDocumentParser):
+            elif isinstance(
+                document_parser,
+                (TextDocumentParser, RemoteDocumentParser),
+            ):
                 # TODO(stumpylog): Remove me in the future
                 document_parser.parse(self.working_copy, mime_type)
             else:
@@ -489,7 +493,7 @@ class ConsumerPlugin(
                 ProgressStatusOptions.WORKING,
                 ConsumerStatusShortMessage.GENERATING_THUMBNAIL,
             )
-            if isinstance(document_parser, TextDocumentParser):
+            if isinstance(document_parser, (TextDocumentParser, RemoteDocumentParser)):
                 # TODO(stumpylog): Remove me in the future
                 thumbnail = document_parser.get_thumbnail(self.working_copy, mime_type)
             else:

src/paperless/parsers/registry.py

@@ -193,9 +193,11 @@ class ParserRegistry:
         that log output is predictable; scoring determines which parser wins
         at runtime regardless of registration order.
         """
+        from paperless.parsers.remote import RemoteDocumentParser
         from paperless.parsers.text import TextDocumentParser
 
         self.register_builtin(TextDocumentParser)
+        self.register_builtin(RemoteDocumentParser)
 
     # ------------------------------------------------------------------
     # Discovery

src/paperless/parsers/remote.py

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

src/paperless/parsers/utils.py

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

src/paperless/tests/parsers/conftest.py

@@ -10,12 +10,15 @@ from typing import TYPE_CHECKING
 
 import pytest
 
+from paperless.parsers.remote import RemoteDocumentParser
 from paperless.parsers.text import TextDocumentParser
 
 if TYPE_CHECKING:
     from collections.abc import Generator
     from pathlib import Path
 
+    from pytest_django.fixtures import SettingsWrapper
+
 
 # ------------------------------------------------------------------
 # Text parser sample files
@@ -74,3 +77,89 @@ def text_parser() -> Generator[TextDocumentParser, None, None]:
     """
     with TextDocumentParser() as parser:
         yield parser
+
+
+# ------------------------------------------------------------------
+# Remote parser sample files
+# ------------------------------------------------------------------
+
+
+@pytest.fixture(scope="session")
+def remote_samples_dir(samples_dir: Path) -> Path:
+    """Absolute path to the remote parser sample files directory.
+
+    Returns
+    -------
+    Path
+        ``<samples_dir>/remote/``
+    """
+    return samples_dir / "remote"
+
+
+@pytest.fixture(scope="session")
+def sample_pdf_file(remote_samples_dir: Path) -> Path:
+    """Path to a simple digital PDF sample file.
+
+    Returns
+    -------
+    Path
+        Absolute path to ``remote/simple-digital.pdf``.
+    """
+    return remote_samples_dir / "simple-digital.pdf"
+
+
+# ------------------------------------------------------------------
+# Remote parser instance
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def remote_parser() -> Generator[RemoteDocumentParser, None, None]:
+    """Yield a RemoteDocumentParser and clean up its temporary directory afterwards.
+
+    Yields
+    ------
+    RemoteDocumentParser
+        A ready-to-use parser instance.
+    """
+    with RemoteDocumentParser() as parser:
+        yield parser
+
+
+# ------------------------------------------------------------------
+# Remote parser settings helpers
+# ------------------------------------------------------------------
+
+
+@pytest.fixture()
+def azure_settings(settings: SettingsWrapper) -> SettingsWrapper:
+    """Configure Django settings for a valid Azure AI OCR engine.
+
+    Sets ``REMOTE_OCR_ENGINE``, ``REMOTE_OCR_API_KEY``, and
+    ``REMOTE_OCR_ENDPOINT`` to test values.  Settings are restored
+    automatically after the test by pytest-django.
+
+    Returns
+    -------
+    SettingsWrapper
+        The modified settings object (for chaining further overrides).
+    """
+    settings.REMOTE_OCR_ENGINE = "azureai"
+    settings.REMOTE_OCR_API_KEY = "test-api-key"
+    settings.REMOTE_OCR_ENDPOINT = "https://test.cognitiveservices.azure.com"
+    return settings
+
+
+@pytest.fixture()
+def no_engine_settings(settings: SettingsWrapper) -> SettingsWrapper:
+    """Configure Django settings with no remote engine configured.
+
+    Returns
+    -------
+    SettingsWrapper
+        The modified settings object.
+    """
+    settings.REMOTE_OCR_ENGINE = None
+    settings.REMOTE_OCR_API_KEY = None
+    settings.REMOTE_OCR_ENDPOINT = None
+    return settings

src/paperless/tests/parsers/test_remote_parser.py

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

src/paperless_remote/parsers.py

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

src/paperless_remote/signals.py

@@ -1,16 +1,36 @@
-def get_parser(*args, **kwargs):
+from __future__ import annotations
-    from paperless_remote.parsers import RemoteDocumentParser
 
+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():
+def get_supported_mime_types() -> dict[str, str]:
-    from paperless_remote.parsers import RemoteDocumentParser
+    from django.conf import settings
 
-    return RemoteDocumentParser(None).supported_mime_types()
+    from paperless.parsers.remote import RemoteDocumentParser
+    from paperless.parsers.remote import RemoteEngineConfig
+
+    config = RemoteEngineConfig(
+        engine=settings.REMOTE_OCR_ENGINE,
+        api_key=settings.REMOTE_OCR_API_KEY,
+        endpoint=settings.REMOTE_OCR_ENDPOINT,
+    )
+    if not config.engine_is_valid():
+        return {}
+    return RemoteDocumentParser.supported_mime_types()
 
 
-def remote_consumer_declaration(sender, **kwargs):
+def remote_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
     return {
         "parser": get_parser,
         "weight": 5,

src/paperless_remote/tests/test_parser.py

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

src/paperless_tesseract/parsers.py

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

src/paperless_tesseract/tests/test_parser.py

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

src/paperless_text/signals.py

@@ -1,16 +1,20 @@
-def get_parser(*args, **kwargs):
+from __future__ import annotations
+
+from typing import Any
+
+
+def get_parser(*args: Any, **kwargs: Any) -> Any:
     from paperless.parsers.text import TextDocumentParser
 
-    # The new TextDocumentParser does not accept the legacy logging_group /
+    # The new TextDocumentParser does not accept the progress_callback
-    # progress_callback kwargs injected by the old signal-based consumer.
+    # kwarg injected by the old signal-based consumer.  logging_group is
-    # These are dropped here; Phase 4 will replace this signal path with the
+    # forwarded as a positional arg.
-    # new ParserRegistry so the shim can be removed at that point.
+    # Phase 4 will replace this signal path with the new ParserRegistry.
-    kwargs.pop("logging_group", None)
     kwargs.pop("progress_callback", None)
-    return TextDocumentParser()
+    return TextDocumentParser(*args, **kwargs)
 
 
-def text_consumer_declaration(sender, **kwargs):
+def text_consumer_declaration(sender: Any, **kwargs: Any) -> dict[str, Any]:
     return {
         "parser": get_parser,
         "weight": 10,

uv.lock

@@ -831,6 +831,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2d/82/e5d2c1c67d19841e9edc74954c827444ae826978499bde3dfc1d007c8c11/deepmerge-2.0-py3-none-any.whl", hash = "sha256:6de9ce507115cff0bed95ff0ce9ecc31088ef50cbdf09bc90a09349a318b3d00", size = 13475, upload-time = "2024-08-30T05:31:48.659Z" },
 ]
 
+[[package]]
+name = "defusedxml"
+version = "0.7.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/0f/d5/c66da9b79e5bdb124974bfe172b4daf3c984ebd9c2a06e2b8a4dc7331c72/defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69", size = 75520, upload-time = "2021-03-08T10:59:26.269Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/07/6c/aa3f2f849e01cb6a001cd8554a88d4c77c5c1a31c95bdf1cf9301e6d9ef4/defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61", size = 25604, upload-time = "2021-03-08T10:59:24.45Z" },
+]
+
 [[package]]
 name = "deprecated"
 version = "1.3.1"
@@ -1283,6 +1292,59 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/a6/ff/ee2f67c0ff146ec98b5df1df637b2bc2d17beeb05df9f427a67bd7a7d79c/flower-2.0.1-py2.py3-none-any.whl", hash = "sha256:9db2c621eeefbc844c8dd88be64aef61e84e2deb29b271e02ab2b5b9f01068e2", size = 383553, upload-time = "2023-08-13T14:37:41.552Z" },
 ]
 
+[[package]]
+name = "fonttools"
+version = "4.62.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/5a/96/686339e0fda8142b7ebed39af53f4a5694602a729662f42a6209e3be91d0/fonttools-4.62.0.tar.gz", hash = "sha256:0dc477c12b8076b4eb9af2e440421b0433ffa9e1dcb39e0640a6c94665ed1098", size = 3579521, upload-time = "2026-03-09T16:50:06.217Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e4/33/63d79ca41020dd460b51f1e0f58ad1ff0a36b7bcbdf8f3971d52836581e9/fonttools-4.62.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:196cafef9aeec5258425bd31a4e9a414b2ee0d1557bca184d7923d3d3bcd90f9", size = 2870816, upload-time = "2026-03-09T16:48:32.39Z" },
+    { url = "https://files.pythonhosted.org/packages/c0/7a/9aeec114bc9fc00d757a41f092f7107863d372e684a5b5724c043654477c/fonttools-4.62.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:153afc3012ff8761b1733e8fbe5d98623409774c44ffd88fbcb780e240c11d13", size = 2416127, upload-time = "2026-03-09T16:48:34.627Z" },
+    { url = "https://files.pythonhosted.org/packages/5a/71/12cfd8ae0478b7158ffa8850786781f67e73c00fd897ef9d053415c5f88b/fonttools-4.62.0-cp311-cp311-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:13b663fb197334de84db790353d59da2a7288fd14e9be329f5debc63ec0500a5", size = 5100678, upload-time = "2026-03-09T16:48:36.454Z" },
+    { url = "https://files.pythonhosted.org/packages/8a/d7/8e4845993ee233c2023d11babe9b3dae7d30333da1d792eeccebcb77baab/fonttools-4.62.0-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:591220d5333264b1df0d3285adbdfe2af4f6a45bbf9ca2b485f97c9f577c49ff", size = 5070859, upload-time = "2026-03-09T16:48:38.786Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/a0/287ae04cd883a52e7bb1d92dfc4997dcffb54173761c751106845fa9e316/fonttools-4.62.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:579f35c121528a50c96bf6fcb6a393e81e7f896d4326bf40e379f1c971603db9", size = 5076689, upload-time = "2026-03-09T16:48:41.886Z" },
+    { url = "https://files.pythonhosted.org/packages/6d/4e/a2377ad26c36fcd3e671a1c316ea5ed83107de1588e2d897a98349363bc7/fonttools-4.62.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:44956b003151d5a289eba6c71fe590d63509267c37e26de1766ba15d9c589582", size = 5202053, upload-time = "2026-03-09T16:48:43.867Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/9d/7ad1ffc080619f67d0b1e0fa6a0578f0be077404f13fd8e448d1616a94a3/fonttools-4.62.0-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:22bde4dc12a9e09b5ced77f3b5053d96cf10c4976c6ac0dee293418ef289d221", size = 2870004, upload-time = "2026-03-09T16:48:50.837Z" },
+    { url = "https://files.pythonhosted.org/packages/4d/8b/ba59069a490f61b737e064c3129453dbd28ee38e81d56af0d04d7e6b4de4/fonttools-4.62.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:7199c73b326bad892f1cb53ffdd002128bfd58a89b8f662204fbf1daf8d62e85", size = 2414662, upload-time = "2026-03-09T16:48:53.295Z" },
+    { url = "https://files.pythonhosted.org/packages/8c/8c/c52a4310de58deeac7e9ea800892aec09b00bb3eb0c53265b31ec02be115/fonttools-4.62.0-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d732938633681d6e2324e601b79e93f7f72395ec8681f9cdae5a8c08bc167e72", size = 5032975, upload-time = "2026-03-09T16:48:55.718Z" },
+    { url = "https://files.pythonhosted.org/packages/0b/a1/d16318232964d786907b9b3613b8409f74cf0be2da400854509d3a864e43/fonttools-4.62.0-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:31a804c16d76038cc4e3826e07678efb0a02dc4f15396ea8e07088adbfb2578e", size = 4988544, upload-time = "2026-03-09T16:48:57.715Z" },
+    { url = "https://files.pythonhosted.org/packages/b2/8d/7e745ca3e65852adc5e52a83dc213fe1b07d61cb5b394970fcd4b1199d1e/fonttools-4.62.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:090e74ac86e68c20150e665ef8e7e0c20cb9f8b395302c9419fa2e4d332c3b51", size = 4971296, upload-time = "2026-03-09T16:48:59.678Z" },
+    { url = "https://files.pythonhosted.org/packages/e6/d4/b717a4874175146029ca1517e85474b1af80c9d9a306fc3161e71485eea5/fonttools-4.62.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:8f086120e8be9e99ca1288aa5ce519833f93fe0ec6ebad2380c1dee18781f0b5", size = 5122503, upload-time = "2026-03-09T16:49:02.464Z" },
+    { url = "https://files.pythonhosted.org/packages/82/c7/985c1670aa6d82ef270f04cde11394c168f2002700353bd2bde405e59b8f/fonttools-4.62.0-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:274c8b8a87e439faf565d3bcd3f9f9e31bca7740755776a4a90a4bfeaa722efa", size = 2864929, upload-time = "2026-03-09T16:49:09.331Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/dc/c409c8ceec0d3119e9ab0b7b1a2e3c76d1f4d66e4a9db5c59e6b7652e7df/fonttools-4.62.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:93e27131a5a0ae82aaadcffe309b1bae195f6711689722af026862bede05c07c", size = 2412586, upload-time = "2026-03-09T16:49:11.378Z" },
+    { url = "https://files.pythonhosted.org/packages/5f/ac/8e300dbf7b4d135287c261ffd92ede02d9f48f0d2db14665fbc8b059588a/fonttools-4.62.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:83c6524c5b93bad9c2939d88e619fedc62e913c19e673f25d5ab74e7a5d074e5", size = 5013708, upload-time = "2026-03-09T16:49:14.063Z" },
+    { url = "https://files.pythonhosted.org/packages/fb/bc/60d93477b653eeb1ddf5f9ec34be689b79234d82dbdded269ac0252715b8/fonttools-4.62.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:106aec9226f9498fc5345125ff7200842c01eda273ae038f5049b0916907acee", size = 4964355, upload-time = "2026-03-09T16:49:16.515Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/eb/6dc62bcc3c3598c28a3ecb77e69018869c3e109bd83031d4973c059d318b/fonttools-4.62.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:15d86b96c79013320f13bc1b15f94789edb376c0a2d22fb6088f33637e8dfcbc", size = 4953472, upload-time = "2026-03-09T16:49:18.494Z" },
+    { url = "https://files.pythonhosted.org/packages/82/b3/3af7592d9b254b7b7fec018135f8776bfa0d1ad335476c2791b1334dc5e4/fonttools-4.62.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4f16c07e5250d5d71d0f990a59460bc5620c3cc456121f2cfb5b60475699905f", size = 5094701, upload-time = "2026-03-09T16:49:21.67Z" },
+    { url = "https://files.pythonhosted.org/packages/1a/64/61f69298aa6e7c363dcf00dd6371a654676900abe27d1effd1a74b43e5d0/fonttools-4.62.0-cp314-cp314-macosx_10_15_universal2.whl", hash = "sha256:4fa5a9c716e2f75ef34b5a5c2ca0ee4848d795daa7e6792bf30fd4abf8993449", size = 2864222, upload-time = "2026-03-09T16:49:28.285Z" },
+    { url = "https://files.pythonhosted.org/packages/c6/57/6b08756fe4455336b1fe160ab3c11fccc90768ccb6ee03fb0b45851aace4/fonttools-4.62.0-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:625f5cbeb0b8f4e42343eaeb4bc2786718ddd84760a2f5e55fdd3db049047c00", size = 2410674, upload-time = "2026-03-09T16:49:30.504Z" },
+    { url = "https://files.pythonhosted.org/packages/6f/86/db65b63bb1b824b63e602e9be21b18741ddc99bcf5a7850f9181159ae107/fonttools-4.62.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6247e58b96b982709cd569a91a2ba935d406dccf17b6aa615afaed37ac3856aa", size = 4999387, upload-time = "2026-03-09T16:49:32.593Z" },
+    { url = "https://files.pythonhosted.org/packages/86/c8/c6669e42d2f4efd60d38a3252cebbb28851f968890efb2b9b15f9d1092b0/fonttools-4.62.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:840632ea9c1eab7b7f01c369e408c0721c287dfd7500ab937398430689852fd1", size = 4912506, upload-time = "2026-03-09T16:49:34.927Z" },
+    { url = "https://files.pythonhosted.org/packages/2e/49/0ae552aa098edd0ec548413fbf818f52ceb70535016215094a5ce9bf8f70/fonttools-4.62.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:28a9ea2a7467a816d1bec22658b0cce4443ac60abac3e293bdee78beb74588f3", size = 4951202, upload-time = "2026-03-09T16:49:37.1Z" },
+    { url = "https://files.pythonhosted.org/packages/71/65/ae38fc8a4cea6f162d74cf11f58e9aeef1baa7d0e3d1376dabd336c129e5/fonttools-4.62.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:5ae611294f768d413949fd12693a8cba0e6332fbc1e07aba60121be35eac68d0", size = 5060758, upload-time = "2026-03-09T16:49:39.464Z" },
+    { url = "https://files.pythonhosted.org/packages/f8/65/f47f9b3db1ec156a1f222f1089ba076b2cc9ee1d024a8b0a60c54258517e/fonttools-4.62.0-cp314-cp314t-macosx_10_15_universal2.whl", hash = "sha256:0361a7d41d86937f1f752717c19f719d0fde064d3011038f9f19bdf5fc2f5c95", size = 2947079, upload-time = "2026-03-09T16:49:46.471Z" },
+    { url = "https://files.pythonhosted.org/packages/52/73/bc62e5058a0c22cf02b1e0169ef0c3ca6c3247216d719f95bead3c05a991/fonttools-4.62.0-cp314-cp314t-macosx_10_15_x86_64.whl", hash = "sha256:d4108c12773b3c97aa592311557c405d5b4fc03db2b969ed928fcf68e7b3c887", size = 2448802, upload-time = "2026-03-09T16:49:48.328Z" },
+    { url = "https://files.pythonhosted.org/packages/2b/df/bfaa0e845884935355670e6e68f137185ab87295f8bc838db575e4a66064/fonttools-4.62.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b448075f32708e8fb377fe7687f769a5f51a027172c591ba9a58693631b077a8", size = 5137378, upload-time = "2026-03-09T16:49:50.223Z" },
+    { url = "https://files.pythonhosted.org/packages/32/32/04f616979a18b48b52e634988b93d847b6346260faf85ecccaf7e2e9057f/fonttools-4.62.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:e5f1fa8cc9f1a56a3e33ee6b954d6d9235e6b9d11eb7a6c9dfe2c2f829dc24db", size = 4920714, upload-time = "2026-03-09T16:49:53.172Z" },
+    { url = "https://files.pythonhosted.org/packages/3b/2e/274e16689c1dfee5c68302cd7c444213cfddd23cf4620374419625037ec6/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:f8c8ea812f82db1e884b9cdb663080453e28f0f9a1f5027a5adb59c4cc8d38d1", size = 5016012, upload-time = "2026-03-09T16:49:55.762Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/0c/b08117270626e7117ac2f89d732fdd4386ec37d2ab3a944462d29e6f89a1/fonttools-4.62.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:03c6068adfdc67c565d217e92386b1cdd951abd4240d65180cec62fa74ba31b2", size = 5042766, upload-time = "2026-03-09T16:49:57.726Z" },
+    { url = "https://files.pythonhosted.org/packages/9c/57/c2487c281dde03abb2dec244fd67059b8d118bd30a653cbf69e94084cb23/fonttools-4.62.0-py3-none-any.whl", hash = "sha256:75064f19a10c50c74b336aa5ebe7b1f89fd0fb5255807bfd4b0c6317098f4af3", size = 1152427, upload-time = "2026-03-09T16:50:04.074Z" },
+]
+
+[[package]]
+name = "fpdf2"
+version = "2.8.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "defusedxml", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fonttools", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/27/f2/72feae0b2827ed38013e4307b14f95bf0b3d124adfef4d38a7d57533f7be/fpdf2-2.8.7.tar.gz", hash = "sha256:7060ccee5a9c7ab0a271fb765a36a23639f83ef8996c34e3d46af0a17ede57f9", size = 362351, upload-time = "2026-02-28T05:39:16.456Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/66/0a/cf50ecffa1e3747ed9380a3adfc829259f1f86b3fdbd9e505af789003141/fpdf2-2.8.7-py3-none-any.whl", hash = "sha256:d391fc508a3ce02fc43a577c830cda4fe6f37646f2d143d489839940932fbc19", size = 327056, upload-time = "2026-02-28T05:39:14.619Z" },
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.8.0"
@@ -2722,10 +2784,11 @@ wheels = [
 
 [[package]]
 name = "ocrmypdf"
-version = "16.13.0"
+version = "17.3.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "deprecation", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "fpdf2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "img2pdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "packaging", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pdfminer-six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2733,11 +2796,14 @@ dependencies = [
     { name = "pikepdf", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pillow", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "pluggy", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pydantic", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "pypdfium2", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "rich", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
+    { name = "uharfbuzz", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8c/52/be1aaece0703a736757d8957c0d4f19c37561054169b501eb0e7132f15e5/ocrmypdf-16.13.0.tar.gz", hash = "sha256:29d37e915234ce717374863a9cc5dd32d29e063dfe60c51380dda71254c88248", size = 7042247, upload-time = "2025-12-24T07:58:35.86Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/fa/fe/60bdc79529be1ad8b151d426ed2020d5ac90328c54e9ba92bd808e1535c1/ocrmypdf-17.3.0.tar.gz", hash = "sha256:4022f13aad3f405e330056a07aa8bd63714b48b414693831b56e2cf2c325f52d", size = 7378015, upload-time = "2026-02-21T09:30:07.207Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/41/b1/e2e7ad98de0d3ee05b44dbc3f78ccb158a620f3add82d00c85490120e7f2/ocrmypdf-16.13.0-py3-none-any.whl", hash = "sha256:fad8a6f7cc52cdc6225095c401a1766c778c47efe9f1e854ae4dc64a550a3d37", size = 165377, upload-time = "2025-12-24T07:58:33.925Z" },
+    { url = "https://files.pythonhosted.org/packages/3d/b1/b7ae057a1bcb1495067ee3c4d48c1ce5fc66addd9492307c5a0ff799a7f2/ocrmypdf-17.3.0-py3-none-any.whl", hash = "sha256:c8882e7864954d3db6bcee49cc9f261b65bff66b7e5925eb68a1c281f41cad23", size = 488130, upload-time = "2026-02-21T09:30:05.236Z" },
 ]
 
 [[package]]
@@ -2978,7 +3044,7 @@ requires-dist = [
     { name = "llama-index-vector-stores-faiss", specifier = ">=0.5.2" },
     { name = "mysqlclient", marker = "extra == 'mariadb'", specifier = "~=2.2.7" },
     { name = "nltk", specifier = "~=3.9.1" },
-    { name = "ocrmypdf", specifier = "~=16.13.0" },
+    { name = "ocrmypdf", specifier = "~=17.3.0" },
     { name = "openai", specifier = ">=1.76" },
     { name = "pathvalidate", specifier = "~=3.3.1" },
     { name = "pdf2image", specifier = "~=1.17.0" },
@@ -3655,6 +3721,30 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/d1/81/ef2b1dfd1862567d573a4fdbc9f969067621764fbb74338496840a1d2977/pyopenssl-25.3.0-py3-none-any.whl", hash = "sha256:1fda6fc034d5e3d179d39e59c1895c9faeaf40a79de5fc4cbbfbe0d36f4a77b6", size = 57268, upload-time = "2025-09-17T00:32:19.474Z" },
 ]
 
+[[package]]
+name = "pypdfium2"
+version = "5.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/3b/01/be763b9081c7eb823196e7d13d9c145bf75ac43f3c1466de81c21c24b381/pypdfium2-5.6.0.tar.gz", hash = "sha256:bcb9368acfe3547054698abbdae68ba0cbd2d3bda8e8ee437e061deef061976d", size = 270714, upload-time = "2026-03-08T01:05:06.5Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6e/f6/9f9e190fe0e5a6b86b82f83bd8b5d3490348766062381140ca5cad8e00b1/pypdfium2-5.6.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e468c38997573f0e86f03273c2c1fbdea999de52ba43fee96acaa2f6b2ad35f7", size = 3412541, upload-time = "2026-03-08T01:04:25.45Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/8d/e57492cb2228ba56ed57de1ff044c8ac114b46905f8b1445c33299ba0488/pypdfium2-5.6.0-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:ad3abddc5805424f962e383253ccad6a0d1d2ebd86afa9a9e1b9ca659773cd0d", size = 3592320, upload-time = "2026-03-08T01:04:27.509Z" },
+    { url = "https://files.pythonhosted.org/packages/f9/8a/8ab82e33e9c551494cbe1526ea250ca8cc4e9e98d6a4fc6b6f8d959aa1d1/pypdfium2-5.6.0-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6b5eb9eae5c45076395454522ca26add72ba8bd1fe473e1e4721aa58521470c", size = 3596450, upload-time = "2026-03-08T01:04:29.183Z" },
+    { url = "https://files.pythonhosted.org/packages/f5/b5/602a792282312ccb158cc63849528079d94b0a11efdc61f2a359edfb41e9/pypdfium2-5.6.0-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:258624da8ef45cdc426e11b33e9d83f9fb723c1c201c6e0f4ab5a85966c6b876", size = 3325442, upload-time = "2026-03-08T01:04:30.886Z" },
+    { url = "https://files.pythonhosted.org/packages/81/1f/9e48ec05ed8d19d736c2d1f23c1bd0f20673f02ef846a2576c69e237f15d/pypdfium2-5.6.0-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e9367451c8a00931d6612db0822525a18c06f649d562cd323a719e46ac19c9bb", size = 3727434, upload-time = "2026-03-08T01:04:33.619Z" },
+    { url = "https://files.pythonhosted.org/packages/33/90/0efd020928b4edbd65f4f3c2af0c84e20b43a3ada8fa6d04f999a97afe7a/pypdfium2-5.6.0-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a757869f891eac1cc1372e38a4aa01adac8abc8fe2a8a4e2ebf50595e3bf5937", size = 4139029, upload-time = "2026-03-08T01:04:36.08Z" },
+    { url = "https://files.pythonhosted.org/packages/ff/49/a640b288a48dab1752281dd9b72c0679fccea107874e80a65a606b00efa9/pypdfium2-5.6.0-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:515be355222cc57ae9e62cd5c7c350b8e0c863efc539f80c7d75e2811ba45cb6", size = 3646387, upload-time = "2026-03-08T01:04:38.151Z" },
+    { url = "https://files.pythonhosted.org/packages/b0/3b/a344c19c01021eeb5d830c102e4fc9b1602f19c04aa7d11abbe2d188fd8e/pypdfium2-5.6.0-py3-none-manylinux_2_27_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1c4753c7caf7d004211d7f57a21f10d127f5e0e5510a14d24bc073e7220a3ea", size = 3097212, upload-time = "2026-03-08T01:04:40.776Z" },
+    { url = "https://files.pythonhosted.org/packages/50/96/e48e13789ace22aeb9b7510904a1b1493ec588196e11bbacc122da330b3d/pypdfium2-5.6.0-py3-none-manylinux_2_38_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:c49729090281fdd85775fb8912c10bd19e99178efaa98f145ab06e7ce68554d2", size = 2965026, upload-time = "2026-03-08T01:04:42.857Z" },
+    { url = "https://files.pythonhosted.org/packages/cb/06/3100e44d4935f73af8f5d633d3bd40f0d36d606027085a0ef1f0566a6320/pypdfium2-5.6.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:a4a1749a8d4afd62924a8d95cfa4f2e26fc32957ce34ac3b674be6f127ed252e", size = 4131431, upload-time = "2026-03-08T01:04:44.982Z" },
+    { url = "https://files.pythonhosted.org/packages/64/ef/d8df63569ce9a66c8496057782eb8af78e0d28667922d62ec958434e3d4b/pypdfium2-5.6.0-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:36469ebd0fdffb7130ce45ed9c44f8232d91571c89eb851bd1633c64b6f6114f", size = 3747469, upload-time = "2026-03-08T01:04:46.702Z" },
+    { url = "https://files.pythonhosted.org/packages/a6/47/fd2c6a67a49fade1acd719fbd11f7c375e7219912923ef2de0ea0ac1544e/pypdfium2-5.6.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:9da900df09be3cf546b637a127a7b6428fb22d705951d731269e25fd3adef457", size = 4337578, upload-time = "2026-03-08T01:04:49.007Z" },
+    { url = "https://files.pythonhosted.org/packages/6b/f5/836c83e54b01e09478c4d6bf4912651d6053c932250fcee953f5c72d8e4a/pypdfium2-5.6.0-py3-none-musllinux_1_2_ppc64le.whl", hash = "sha256:45fccd5622233c5ec91a885770ae7dd4004d4320ac05a4ad8fa03a66dea40244", size = 4376104, upload-time = "2026-03-08T01:04:51.04Z" },
+    { url = "https://files.pythonhosted.org/packages/6e/7f/b940b6a1664daf8f9bad87c6c99b84effa3611615b8708d10392dc33036c/pypdfium2-5.6.0-py3-none-musllinux_1_2_riscv64.whl", hash = "sha256:282dc030e767cd61bd0299f9d581052b91188e2b87561489057a8e7963e7e0cb", size = 3929824, upload-time = "2026-03-08T01:04:53.544Z" },
+    { url = "https://files.pythonhosted.org/packages/88/79/00267d92a6a58c229e364d474f5698efe446e0c7f4f152f58d0138715e99/pypdfium2-5.6.0-py3-none-musllinux_1_2_s390x.whl", hash = "sha256:a1c1dfe950382c76a7bba1ba160ec5e40df8dd26b04a1124ae268fda55bc4cbe", size = 4270201, upload-time = "2026-03-08T01:04:55.81Z" },
+    { url = "https://files.pythonhosted.org/packages/e1/ab/b127f38aba41746bdf9ace15ba08411d7ef6ecba1326d529ba414eb1ed50/pypdfium2-5.6.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:43b0341ca6feb6c92e4b7a9eb4813e5466f5f5e8b6baeb14df0a94d5f312c00b", size = 4180793, upload-time = "2026-03-08T01:04:57.961Z" },
+]
+
 [[package]]
 name = "pyrefly"
 version = "0.55.0"
@@ -5143,6 +5233,23 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b1/5e/512aeb40fd819f4660d00f96f5c7371ee36fc8c6b605128c5ee59e0b28c6/u_msgpack_python-2.8.0-py2.py3-none-any.whl", hash = "sha256:1d853d33e78b72c4228a2025b4db28cda81214076e5b0422ed0ae1b1b2bb586a", size = 10590, upload-time = "2023-05-18T09:28:10.323Z" },
 ]
 
+[[package]]
+name = "uharfbuzz"
+version = "0.53.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/1c/8d/7c82298bfa5c96f018541661bc2ccdf90dfe397bb2724db46725bf495466/uharfbuzz-0.53.3.tar.gz", hash = "sha256:9a87175c14d1361322ce2a3504e63c6b66062934a5edf47266aed5b33416806c", size = 1714488, upload-time = "2026-01-24T13:10:43.693Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/51/88/5df9337adb60d7b1ad150b162bbc5c56d783d15546714085d92b9531f8f3/uharfbuzz-0.53.3-cp310-abi3-macosx_10_9_universal2.whl", hash = "sha256:d977e41a501d9e8af3f2c329d75031037ee79634bc29ca3872e9115c44e67d25", size = 2722639, upload-time = "2026-01-24T13:10:22.436Z" },
+    { url = "https://files.pythonhosted.org/packages/39/c4/8b4b050e77d6cb9a84af509e5796734f0e687bd02ad11757a581bd6f197d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:21d512c94aa992691aaf5b433deaca7e51f4ea54c68b99f535974073364f806f", size = 1647506, upload-time = "2026-01-24T13:10:24.16Z" },
+    { url = "https://files.pythonhosted.org/packages/30/ff/8e7cf78d525604f3e0a43b9468263fcf2acb5d208a3979c3bfa8dc61112d/uharfbuzz-0.53.3-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:dca9a2e071c0c59ba8f382356f31a2518ac3dc7cc77e4f3519defc454c5b9a97", size = 1706448, upload-time = "2026-01-24T13:10:25.729Z" },
+    { url = "https://files.pythonhosted.org/packages/9b/a0/739471cdd52723ecc9fc80f36fb92c706a87265dc258521c1b14d99414f7/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:1191a74ddcf18ec721161b6b33a8ab31b0c6a2b15c6724a9b663127bf7f07d2e", size = 2664628, upload-time = "2026-01-24T13:10:27.814Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/4a/63a81e9eef922b9f26bd948b518b73704d01a8d8e83324b2f99084ab7af0/uharfbuzz-0.53.3-cp310-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:35ec3b600b3f63e7659792f9bd43e1ffb389d3d2aac8285f269d11efbe04787d", size = 2757384, upload-time = "2026-01-24T13:10:29.669Z" },
+    { url = "https://files.pythonhosted.org/packages/e2/d2/27be1201488323d0ff0c99fb966a0522b2736f79bd5a5b7b99526fca3d98/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:6f0ad2812303d2c7ccff596fd6c9d5629874f3a83f30255e11639c9b7ba4e89d", size = 1335822, upload-time = "2026-01-24T13:10:34.774Z" },
+    { url = "https://files.pythonhosted.org/packages/70/99/53e39bcd4dec5981eb70a6a76285a862c8a76b80cd52e8f40fe51adab032/uharfbuzz-0.53.3-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:757d9ed1841912e8f229319f335cf7dd25a2fd377e444bda9deb720617192e12", size = 1237560, upload-time = "2026-01-24T13:10:36.971Z" },
+    { url = "https://files.pythonhosted.org/packages/aa/2b/04d8cde466acfe70373d4f489da5c6eab0aba07d50442dd21217cb0fd167/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:5d3a0b824811bd1be129356818e6cdbf0e4b056bb60aa9a5eb270bff9d21f24c", size = 1497923, upload-time = "2026-01-24T13:10:38.743Z" },
+    { url = "https://files.pythonhosted.org/packages/f3/01/a250521491bc995609275e0062c552b16f437a3ce15de83250176245093e/uharfbuzz-0.53.3-pp311-pypy311_pp73-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9211d798b2921a99b8c34e810676137f66372d3b5447765b72d969bdfa6abe6a", size = 1556794, upload-time = "2026-01-24T13:10:40.262Z" },
+]
+
 [[package]]
 name = "ujson"
 version = "5.11.0"