Revert "Documentation: add note about logo file visibility and exif data"

This reverts commit 43b4f36026.

docs/configuration.md

@@ -1759,11 +1759,6 @@ started by the container.
 
 : Path to an image file in the /media/logo directory, must include 'logo', e.g. `/logo/Atari_logo.svg`
 
-!!! note
-
-    The logo file will be viewable by anyone with access to the Paperless instance login page,
-    so consider your choice of logo carefully and removing exif data from images before uploading.
-
 #### [`PAPERLESS_ENABLE_UPDATE_CHECK=<bool>`](#PAPERLESS_ENABLE_UPDATE_CHECK) {#PAPERLESS_ENABLE_UPDATE_CHECK}
 
 !!! note
@@ -1805,23 +1800,3 @@ password. All of these options come from their similarly-named [Django settings]
 #### [`PAPERLESS_EMAIL_USE_SSL=<bool>`](#PAPERLESS_EMAIL_USE_SSL) {#PAPERLESS_EMAIL_USE_SSL}
 
 : Defaults to false.
-
-## Remote OCR
-
-#### [`PAPERLESS_REMOTE_OCR_ENGINE=<str>`](#PAPERLESS_REMOTE_OCR_ENGINE) {#PAPERLESS_REMOTE_OCR_ENGINE}
-
-: The remote OCR engine to use. Currently only Azure AI is supported as "azureai".
-
-    Defaults to None, which disables remote OCR.
-
-#### [`PAPERLESS_REMOTE_OCR_API_KEY=<str>`](#PAPERLESS_REMOTE_OCR_API_KEY) {#PAPERLESS_REMOTE_OCR_API_KEY}
-
-: The API key to use for the remote OCR engine.
-
-    Defaults to None.
-
-#### [`PAPERLESS_REMOTE_OCR_ENDPOINT=<str>`](#PAPERLESS_REMOTE_OCR_ENDPOINT) {#PAPERLESS_REMOTE_OCR_ENDPOINT}
-
-: The endpoint to use for the remote OCR engine. This is required for Azure AI.
-
-    Defaults to None.

docs/index.md

@@ -25,10 +25,9 @@ physical documents into a searchable online archive so you can keep, well, _less
 ## Features
 
 -   **Organize and index** your scanned documents with tags, correspondents, types, and more.
--   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way.
 -   Performs **OCR** on your documents, adding searchable and selectable text, even to documents scanned with only images.
-    -   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
+-   Utilizes the open-source Tesseract engine to recognize more than 100 languages.
-    -   _New!_ Supports remote OCR with Azure AI (opt-in).
 -   Documents are saved as PDF/A format which is designed for long term storage, alongside the unaltered originals.
 -   Uses machine-learning to automatically add tags, correspondents and document types to your documents.
 -   Supports PDF documents, images, plain text files, Office documents (Word, Excel, PowerPoint, and LibreOffice equivalents)[^1] and more.

docs/usage.md

@@ -878,21 +878,6 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
-## Remote OCR
-
-!!! important
-
-    This feature is disabled by default and will always remain strictly "opt-in".
-
-Paperless-ngx supports performing OCR on documents using remote services. At the moment, this is limited to
-[Microsoft's Azure "Document Intelligence" service](https://azure.microsoft.com/en-us/products/ai-services/ai-document-intelligence).
-This is of course a paid service (with a free tier) which requires an Azure account and subscription. Azure AI is not affiliated with
-Paperless-ngx in any way. When enabled, Paperless-ngx will automatically send appropriate documents to Azure for OCR processing, bypassing
-the local OCR engine. See the [configuration](configuration.md#PAPERLESS_REMOTE_OCR_ENGINE) options for more details.
-
-Additionally, when using a commercial service with this feature, consider both potential costs as well as any associated file size
-or page limitations (e.g. with a free tier).
-
 ## Architecture
 
 Paperless-ngx consists of the following components:

pyproject.toml

@@ -15,7 +15,6 @@ classifiers = [
 # This will allow testing to not install a webserver, mysql, etc
 
 dependencies = [
-  "azure-ai-documentintelligence>=1.0.2",
   "babel>=2.17",
   "bleach~=6.2.0",
   "celery[redis]~=5.5.1",
@@ -234,7 +233,6 @@ testpaths = [
   "src/paperless_tesseract/tests/",
   "src/paperless_tika/tests",
   "src/paperless_text/tests/",
-  "src/paperless_remote/tests/",
 ]
 addopts = [
   "--pythonwarnings=all",

src-ui/src/app/components/manage/tag-list/tag-list.component.spec.ts

@@ -71,20 +71,4 @@ describe('TagListComponent', () => {
       'Do you really want to delete the tag "Tag1"?'
     )
   })
-
-  it('should filter out child tags if name filter is empty, otherwise show all', () => {
-    const tags = [
-      { id: 1, name: 'Tag1', parent: null },
-      { id: 2, name: 'Tag2', parent: 1 },
-      { id: 3, name: 'Tag3', parent: null },
-    ]
-    component['_nameFilter'] = null // Simulate empty name filter
-    const filtered = component.filterData(tags as any)
-    expect(filtered.length).toBe(2)
-    expect(filtered.find((t) => t.id === 2)).toBeUndefined()
-
-    component['_nameFilter'] = 'Tag2' // Simulate non-empty name filter
-    const filteredWithName = component.filterData(tags as any)
-    expect(filteredWithName.length).toBe(3)
-  })
 })

src-ui/src/app/components/manage/tag-list/tag-list.component.ts

@@ -62,8 +62,6 @@ export class TagListComponent extends ManagementListComponent<Tag> {
   }
 
   filterData(data: Tag[]) {
-    return this.nameFilter?.length
+    return data.filter((tag) => !tag.parent)
-      ? [...data]
-      : data.filter((tag) => !tag.parent)
   }
 }

src/documents/management/commands/document_consumer.py

@@ -82,13 +82,6 @@ def _is_ignored(filepath: Path) -> bool:
 
 
 def _consume(filepath: Path) -> None:
-    # Check permissions early
-    try:
-        filepath.stat()
-    except (PermissionError, OSError):
-        logger.warning(f"Not consuming file {filepath}: Permission denied.")
-        return
-
     if filepath.is_dir() or _is_ignored(filepath):
         return
 
@@ -330,12 +323,7 @@ class Command(BaseCommand):
 
                         # Also make sure the file exists still, some scanners might write a
                         # temporary file first
-                        try:
+                        file_still_exists = filepath.exists() and filepath.is_file()
-                            file_still_exists = filepath.exists() and filepath.is_file()
-                        except (PermissionError, OSError):  # pragma: no cover
-                            # If we can't check, let it fail in the _consume function
-                            file_still_exists = True
-                            continue
 
                         if waited_long_enough and file_still_exists:
                             _consume(filepath)

src/documents/tests/test_api_app_config.py

@@ -1,4 +1,6 @@
 import json
+from fractions import Fraction
+from io import BytesIO
 from pathlib import Path
 
 from django.contrib.auth.models import User
@@ -6,6 +8,11 @@ from django.core.files.uploadedfile import SimpleUploadedFile
 from rest_framework import status
 from rest_framework.test import APITestCase
 
+try:
+    from PIL import Image
+except ModuleNotFoundError:  # pragma: no cover - Pillow is required in production
+    Image = None  # type: ignore[assignment]
+
 from documents.tests.utils import DirectoriesMixin
 from paperless.models import ApplicationConfiguration
 from paperless.models import ColorConvertChoices
@@ -190,6 +197,74 @@ class TestApiAppConfig(DirectoriesMixin, APITestCase):
         )
         self.assertFalse(Path(old_logo.path).exists())
 
+    def test_api_strips_metadata_from_logo_upload(self):
+        """
+        GIVEN:
+            - An image file containing EXIF metadata including GPS coordinates
+        WHEN:
+            - Uploaded via PATCH to app config
+        THEN:
+            - Stored logo no longer contains EXIF metadata
+        """
+        if Image is None:
+            self.skipTest("Pillow is not installed")
+
+        if not hasattr(Image, "Exif"):
+            self.skipTest("Current Pillow version cannot create EXIF metadata")
+
+        assert Image is not None
+
+        exif = Image.Exif()
+        exif[0x010E] = "Test description"  # ImageDescription
+        exif[0x8825] = {
+            1: "N",  # GPSLatitudeRef
+            2: (Fraction(51, 1), Fraction(30, 1), Fraction(0, 1)),
+            3: "E",  # GPSLongitudeRef
+            4: (Fraction(0, 1), Fraction(7, 1), Fraction(0, 1)),
+        }
+
+        buffer = BytesIO()
+        Image.new("RGB", (8, 8), "white").save(buffer, format="JPEG", exif=exif)
+        buffer.seek(0)
+
+        with Image.open(BytesIO(buffer.getvalue())) as uploaded_image:
+            self.assertGreater(len(uploaded_image.getexif()), 0)
+
+        response = self.client.patch(
+            f"{self.ENDPOINT}1/",
+            {
+                "app_logo": SimpleUploadedFile(
+                    name="with_exif.jpg",
+                    content=buffer.getvalue(),
+                    content_type="image/jpeg",
+                ),
+            },
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_200_OK)
+
+        config = ApplicationConfiguration.objects.first()
+        stored_logo = Path(config.app_logo.path)
+        self.assertTrue(stored_logo.exists())
+
+        with Image.open(stored_logo) as sanitized:
+            sanitized_exif = sanitized.getexif()
+            self.assertNotEqual(sanitized_exif.get(0x010E), "Test description")
+
+            gps_ifd = None
+            if hasattr(sanitized_exif, "get_ifd"):
+                try:
+                    gps_ifd = sanitized_exif.get_ifd(0x8825)
+                except KeyError:
+                    gps_ifd = None
+            else:
+                gps_ifd = sanitized_exif.get(0x8825)
+
+            if gps_ifd is not None:
+                self.assertEqual(len(gps_ifd), 0, "GPS metadata should be cleared")
+
+            self.assertNotIn("exif", sanitized.info)
+
     def test_api_rejects_malicious_svg_logo(self):
         """
         GIVEN:

src/documents/tests/test_management_consumer.py

@@ -209,26 +209,6 @@ class TestConsumer(DirectoriesMixin, ConsumerThreadMixin, TransactionTestCase):
         # assert that we have an error logged with this invalid file.
         error_logger.assert_called_once()
 
-    @mock.patch("documents.management.commands.document_consumer.logger.warning")
-    def test_permission_error_on_prechecks(self, warning_logger):
-        filepath = Path(self.dirs.consumption_dir) / "selinux.txt"
-        filepath.touch()
-
-        original_stat = Path.stat
-
-        def raising_stat(self, *args, **kwargs):
-            if self == filepath:
-                raise PermissionError("Permission denied")
-            return original_stat(self, *args, **kwargs)
-
-        with mock.patch("pathlib.Path.stat", new=raising_stat):
-            document_consumer._consume(filepath)
-
-        warning_logger.assert_called_once()
-        (args, _) = warning_logger.call_args
-        self.assertIn("Permission denied", args[0])
-        self.consume_file_mock.assert_not_called()
-
     @override_settings(CONSUMPTION_DIR="does_not_exist")
     def test_consumption_directory_invalid(self):
         self.assertRaises(CommandError, call_command, "document_consumer", "--oneshot")

src/paperless/serialisers.py

@@ -1,4 +1,5 @@
 import logging
+from io import BytesIO
 
 import magic
 from allauth.mfa.adapter import get_adapter as get_mfa_adapter
@@ -9,6 +10,10 @@ from allauth.socialaccount.models import SocialApp
 from django.contrib.auth.models import Group
 from django.contrib.auth.models import Permission
 from django.contrib.auth.models import User
+from django.core.files.uploadedfile import SimpleUploadedFile
+from PIL import Image
+from PIL import ImageOps
+from PIL import UnidentifiedImageError
 from rest_framework import serializers
 from rest_framework.authtoken.serializers import AuthTokenSerializer
 
@@ -19,6 +24,102 @@ from paperless_mail.serialisers import ObfuscatedPasswordField
 logger = logging.getLogger("paperless.settings")
 
 
+def strip_image_metadata(uploaded_file, mime_type: str | None):
+    """Return a copy of ``uploaded_file`` with EXIF/ICC metadata removed."""
+
+    if uploaded_file is None:
+        return uploaded_file
+
+    original_position = uploaded_file.tell() if hasattr(uploaded_file, "tell") else None
+    image = None
+
+    sanitized = None
+
+    try:
+        if hasattr(uploaded_file, "seek"):
+            uploaded_file.seek(0)
+        image = Image.open(uploaded_file)
+        image.load()
+    except (UnidentifiedImageError, OSError):
+        if hasattr(uploaded_file, "seek") and original_position is not None:
+            uploaded_file.seek(original_position)
+        return uploaded_file
+
+    try:
+        image_format = (image.format or "").upper()
+        image = ImageOps.exif_transpose(image)
+
+        if image_format not in {"JPEG", "JPG", "PNG"}:
+            if hasattr(uploaded_file, "seek") and original_position is not None:
+                uploaded_file.seek(original_position)
+            return uploaded_file
+
+        if hasattr(image, "info"):
+            image.info.pop("exif", None)
+            image.info.pop("icc_profile", None)
+            image.info.pop("comment", None)
+
+        if image_format in {"JPEG", "JPG"}:
+            sanitized = image.convert("RGB")
+            save_kwargs = {
+                "format": "JPEG",
+                "quality": 95,
+                "subsampling": 0,
+                "optimize": True,
+                "exif": b"",
+            }
+        else:  # PNG
+            target_mode = (
+                "RGBA"
+                if ("A" in image.mode or image.info.get("transparency"))
+                else "RGB"
+            )
+            sanitized = image.convert(target_mode)
+            save_kwargs = {
+                "format": "PNG",
+                "optimize": True,
+            }
+
+        buffer = BytesIO()
+        try:
+            sanitized.save(buffer, **save_kwargs)
+        except (OSError, ValueError):
+            buffer = BytesIO()
+            if image_format in {"JPEG", "JPG"}:
+                sanitized.save(
+                    buffer,
+                    format="JPEG",
+                    quality=90,
+                    subsampling=0,
+                    exif=b"",
+                )
+            else:
+                sanitized.save(
+                    buffer,
+                    format="PNG",
+                )
+
+        buffer.seek(0)
+
+        if hasattr(uploaded_file, "close"):
+            try:
+                uploaded_file.close()
+            except Exception:
+                pass
+
+        content_type = getattr(uploaded_file, "content_type", None) or mime_type
+        return SimpleUploadedFile(
+            name=getattr(uploaded_file, "name", "logo"),
+            content=buffer.getvalue(),
+            content_type=content_type,
+        )
+    finally:
+        if sanitized is not None:
+            sanitized.close()
+        if image is not None:
+            image.close()
+
+
 class PaperlessAuthTokenSerializer(AuthTokenSerializer):
     code = serializers.CharField(
         label="MFA Code",
@@ -209,9 +310,22 @@ class ApplicationConfigurationSerializer(serializers.ModelSerializer):
         return super().update(instance, validated_data)
 
     def validate_app_logo(self, file):
-        if file and magic.from_buffer(file.read(2048), mime=True) == "image/svg+xml":
+        if not file:
+            return file
+
+        if hasattr(file, "seek"):
+            file.seek(0)
+        mime_type = magic.from_buffer(file.read(2048), mime=True)
+        if hasattr(file, "seek"):
+            file.seek(0)
+
+        if mime_type == "image/svg+xml":
             reject_dangerous_svg(file)
-        return file
+            if hasattr(file, "seek"):
+                file.seek(0)
+            return file
+
+        return strip_image_metadata(file, mime_type)
 
     class Meta:
         model = ApplicationConfiguration

src/paperless/settings.py

@@ -322,7 +322,6 @@ INSTALLED_APPS = [
     "paperless_tesseract.apps.PaperlessTesseractConfig",
     "paperless_text.apps.PaperlessTextConfig",
     "paperless_mail.apps.PaperlessMailConfig",
-    "paperless_remote.apps.PaperlessRemoteParserConfig",
     "django.contrib.admin",
     "rest_framework",
     "rest_framework.authtoken",
@@ -1390,10 +1389,3 @@ WEBHOOKS_ALLOW_INTERNAL_REQUESTS = __get_boolean(
     "PAPERLESS_WEBHOOKS_ALLOW_INTERNAL_REQUESTS",
     "true",
 )
-
-###############################################################################
-# Remote Parser                                                               #
-###############################################################################
-REMOTE_OCR_ENGINE = os.getenv("PAPERLESS_REMOTE_OCR_ENGINE")
-REMOTE_OCR_API_KEY = os.getenv("PAPERLESS_REMOTE_OCR_API_KEY")
-REMOTE_OCR_ENDPOINT = os.getenv("PAPERLESS_REMOTE_OCR_ENDPOINT")

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):
-        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/parsers.py

@@ -1,113 +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),
-        )
-
-        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)
-
-        client.close()
-        return result.content
-
-    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

@@ -1,18 +0,0 @@
-def get_parser(*args, **kwargs):
-    from paperless_remote.parsers import RemoteDocumentParser
-
-    return RemoteDocumentParser(*args, **kwargs)
-
-
-def get_supported_mime_types():
-    from paperless_remote.parsers import RemoteDocumentParser
-
-    return RemoteDocumentParser(None).supported_mime_types()
-
-
-def remote_consumer_declaration(sender, **kwargs):
-    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):
-        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):
-        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_remote/tests/test_parser.py

@@ -1,101 +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]):
-        # 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):
-        # 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):
-            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."],
-            )
-
-    @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):
-        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):
-        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):
-        parser = get_parser(uuid.uuid4())
-        parser.parse(self.SAMPLE_FILES / "simple-digital.pdf", "application/pdf")
-        self.assertEqual(parser.text, "")

uv.lock

@@ -95,34 +95,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/af/cc/55a32a2c98022d88812b5986d2a92c4ff3ee087e83b712ebc703bba452bf/Automat-24.8.1-py3-none-any.whl", hash = "sha256:bf029a7bc3da1e2c24da2343e7598affaa9f10bf0ab63ff808566ce90551e02a", size = 42585, upload-time = "2024-08-19T17:31:56.729Z" },
 ]
 
-[[package]]
-name = "azure-ai-documentintelligence"
-version = "1.0.2"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "azure-core", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "isodate", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/44/7b/8115cd713e2caa5e44def85f2b7ebd02a74ae74d7113ba20bdd41fd6dd80/azure_ai_documentintelligence-1.0.2.tar.gz", hash = "sha256:4d75a2513f2839365ebabc0e0e1772f5601b3a8c9a71e75da12440da13b63484", size = 170940 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/d9/75/c9ec040f23082f54ffb1977ff8f364c2d21c79a640a13d1c1809e7fd6b1a/azure_ai_documentintelligence-1.0.2-py3-none-any.whl", hash = "sha256:e1fb446abbdeccc9759d897898a0fe13141ed29f9ad11fc705f951925822ed59", size = 106005 },
-]
-
-[[package]]
-name = "azure-core"
-version = "1.33.0"
-source = { registry = "https://pypi.org/simple" }
-dependencies = [
-    { name = "requests", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "six", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-    { name = "typing-extensions", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
-]
-sdist = { url = "https://files.pythonhosted.org/packages/75/aa/7c9db8edd626f1a7d99d09ef7926f6f4fb34d5f9fa00dc394afdfe8e2a80/azure_core-1.33.0.tar.gz", hash = "sha256:f367aa07b5e3005fec2c1e184b882b0b039910733907d001c20fb08ebb8c0eb9", size = 295633 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/07/b7/76b7e144aa53bd206bf1ce34fa75350472c3f69bf30e5c8c18bc9881035d/azure_core-1.33.0-py3-none-any.whl", hash = "sha256:9b5b6d0223a1d38c37500e6971118c1e0f13f54951e6893968b38910bc9cda8f", size = 207071 },
-]
-
 [[package]]
 name = "babel"
 version = "2.17.0"
@@ -1440,15 +1412,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/fc/4e5a141c3f7c7bed550ac1f69e599e92b6be449dd4677ec09f325cad0955/inotifyrecursive-0.3.5-py3-none-any.whl", hash = "sha256:7e5f4a2e1dc2bef0efa3b5f6b339c41fb4599055a2b54909d020e9e932cc8d2f", size = 8009, upload-time = "2020-11-20T12:38:46.981Z" },
 ]
 
-[[package]]
-name = "isodate"
-version = "0.7.2"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/54/4d/e940025e2ce31a8ce1202635910747e5a87cc3a6a6bb2d00973375014749/isodate-0.7.2.tar.gz", hash = "sha256:4cd1aa0f43ca76f4a6c6c0292a85f40b35ec2e43e315b59f06e6d32171a953e6", size = 29705 }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/15/aa/0aca39a37d3c7eb941ba736ede56d689e7be91cab5d9ca846bde3999eba6/isodate-0.7.2-py3-none-any.whl", hash = "sha256:28009937d8031054830160fce6d409ed342816b543597cece116d966c6d99e15", size = 22320 },
-]
-
 [[package]]
 name = "jinja2"
 version = "3.1.6"
@@ -2069,7 +2032,6 @@ name = "paperless-ngx"
 version = "2.18.4"
 source = { virtual = "." }
 dependencies = [
-    { name = "azure-ai-documentintelligence", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "babel", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "bleach", marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
     { name = "celery", extra = ["redis"], marker = "sys_platform == 'darwin' or sys_platform == 'linux'" },
@@ -2207,7 +2169,6 @@ typing = [
 
 [package.metadata]
 requires-dist = [
-    { name = "azure-ai-documentintelligence", specifier = ">=1.0.2" },
     { name = "babel", specifier = ">=2.17" },
     { name = "bleach", specifier = "~=6.2.0" },
     { name = "celery", extras = ["redis"], specifier = "~=5.5.1" },