Update test_parser.py

docs/index.md

@@ -25,9 +25,10 @@ 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.
+-   _Your_ data is stored locally on _your_ server and is never transmitted or shared in any way, unless you explicitly choose to do so.
 -   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

@@ -841,7 +841,7 @@ how regularly you intend to scan documents and use paperless.
     performed the task associated with the document, move it to the
     inbox.
 
-## Remove OCR
+## Remote OCR
 
 !!! important
 

src/paperless_remote/parsers.py

@@ -25,14 +25,15 @@ class RemoteEngineConfig:
 
 class RemoteDocumentParser(RasterisedDocumentParser):
     """
-    This parser uses a remote ocr engine to parse documents
+    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:
         """
-        This parser uses the OCR configuration settings to parse documents
+        Returns the configuration for the remote OCR engine, loaded from Django settings.
         """
         return RemoteEngineConfig(
             engine=settings.REMOTE_OCR_ENGINE,
@@ -59,7 +60,11 @@ class RemoteDocumentParser(RasterisedDocumentParser):
         file: Path,
     ) -> str | None:
         """
-        This method uses the Azure AI Vision API to parse documents
+        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

src/paperless_remote/tests/test_parser.py

@@ -88,11 +88,6 @@ class TestParser(DirectoriesMixin, FileSystemAssertsMixin, TestCase):
 
     def test_supported_mime_types_invalid_config(self):
         parser = get_parser(uuid.uuid4())
-        # with override_settings(
-        #     REMOTE_OCR_ENGINE=None,
-        #     REMOTE_OCR_API_KEY=None,
-        #     REMOTE_OCR_ENDPOINT=None,
-        # ):
         self.assertEqual(parser.supported_mime_types(), [])
 
     @override_settings(