✅(backend) add tests for document import feature

Added comprehensive tests covering DocSpec converter service,
converter orchestration, and document creation with file uploads.

Tests validate DOCX and Markdown conversion workflows, error
handling, service availability, and edge cases including empty
files and Unicode filenames.

Signed-off-by: Stephan Meijer <[email protected]>

Author: StephanMeijer

src/backend/core/api/serializers.py

@@ -11,11 +11,11 @@
 from django.utils.text import slugify
 from django.utils.translation import gettext_lazy as _
 
-from core.services import mime_types
 import magic
 from rest_framework import serializers
 
 from core import choices, enums, models, utils, validators
+from core.services import mime_types
 from core.services.ai_services import AI_ACTIONS
 from core.services.converter_services import (
     ConversionError,
@@ -465,9 +465,7 @@ def create(self, validated_data):
 
         try:
             document_content = Converter().convert(
-                validated_data["content"],
-                mime_types.MARKDOWN,
-                mime_types.YJS
+                validated_data["content"], mime_types.MARKDOWN, mime_types.YJS
             )
         except ConversionError as err:
             raise serializers.ValidationError(

src/backend/core/api/viewsets.py

@@ -37,15 +37,19 @@
 from rest_framework.permissions import AllowAny
 
 from core import authentication, choices, enums, models
+from core.services import mime_types
 from core.services.ai_services import AIService
 from core.services.collaboration_services import CollaborationService
 from core.services.converter_services import (
     ConversionError,
+    Converter,
+)
+from core.services.converter_services import (
     ServiceUnavailableError as YProviderServiceUnavailableError,
+)
+from core.services.converter_services import (
     ValidationError as YProviderValidationError,
-    Converter,
 )
-from core.services import mime_types
 from core.tasks.mail import send_ask_for_access_mail
 from core.utils import extract_attachments, filter_descendants
 
@@ -515,7 +519,7 @@ def perform_create(self, serializer):
                 converted_content = converter.convert(
                     file_content,
                     content_type=uploaded_file.content_type,
-                    accept=mime_types.YJS
+                    accept=mime_types.YJS,
                 )
                 serializer.validated_data["content"] = converted_content
                 serializer.validated_data["title"] = uploaded_file.name

src/backend/core/services/converter_services.py

@@ -1,14 +1,15 @@
 """Y-Provider API services."""
 
+import typing
 from base64 import b64encode
 
 from django.conf import settings
 
 import requests
-import typing
 
 from core.services import mime_types
 
+
 class ConversionError(Exception):
     """Base exception for conversion-related errors."""
 
@@ -22,28 +23,33 @@ class ServiceUnavailableError(ConversionError):
 
 
 class ConverterProtocol(typing.Protocol):
-    def convert(self, text, content_type, accept): ...
+    """Protocol for converter classes."""
+
+    def convert(self, text, content_type, accept):
+        """Convert content from one format to another."""
 
 
 class Converter:
+    """Orchestrates conversion between different formats using specialized converters."""
+
     docspec: ConverterProtocol
     ydoc: ConverterProtocol
 
     def __init__(self):
         self.docspec = DocSpecConverter()
         self.ydoc = YdocConverter()
 
-    def convert(self, input, content_type, accept):
+    def convert(self, data, content_type, accept):
         """Convert input into other formats using external microservices."""
-        
+
         if content_type == mime_types.DOCX and accept == mime_types.YJS:
             return self.convert(
-                self.docspec.convert(input, mime_types.DOCX, mime_types.BLOCKNOTE),
+                self.docspec.convert(data, mime_types.DOCX, mime_types.BLOCKNOTE),
                 mime_types.BLOCKNOTE,
-                mime_types.YJS
+                mime_types.YJS,
             )
-        
-        return self.ydoc.convert(input, content_type, accept)
+
+        return self.ydoc.convert(data, content_type, accept)
 
 
 class DocSpecConverter:
@@ -61,15 +67,17 @@ def _request(self, url, data, content_type):
         )
         response.raise_for_status()
         return response
-    
+
     def convert(self, data, content_type, accept):
         """Convert a Document to BlockNote."""
         if not data:
             raise ValidationError("Input data cannot be empty")
-        
+
         if content_type != mime_types.DOCX or accept != mime_types.BLOCKNOTE:
-            raise ValidationError(f"Conversion from {content_type} to {accept} is not supported.")
-        
+            raise ValidationError(
+                f"Conversion from {content_type} to {accept} is not supported."
+            )
+
         try:
             return self._request(settings.DOCSPEC_API_URL, data, content_type).content
         except requests.RequestException as err:
@@ -103,9 +111,7 @@ def _request(self, url, data, content_type, accept):
         response.raise_for_status()
         return response
 
-    def convert(
-        self, text, content_type=mime_types.MARKDOWN, accept=mime_types.YJS
-    ):
+    def convert(self, text, content_type=mime_types.MARKDOWN, accept=mime_types.YJS):
         """Convert a Markdown text into our internal format using an external microservice."""
 
         if not text:

src/backend/core/services/mime_types.py

@@ -1,3 +1,5 @@
+"""MIME type constants for document conversion."""
+
 BLOCKNOTE = "application/vnd.blocknote+json"
 YJS = "application/vnd.yjs.doc"
 MARKDOWN = "text/markdown"

src/backend/core/tests/documents/test_api_documents_create_for_owner.py

@@ -16,6 +16,7 @@
 from core import factories
 from core.api.serializers import ServerCreateDocumentSerializer
 from core.models import Document, Invitation, User
+from core.services import mime_types
 from core.services.converter_services import ConversionError, YdocConverter
 
 pytestmark = pytest.mark.django_db
@@ -191,7 +192,9 @@ def test_api_documents_create_for_owner_existing(mock_convert_md):
 
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     document = Document.objects.get()
     assert response.json() == {"id": str(document.id)}
@@ -236,7 +239,9 @@ def test_api_documents_create_for_owner_new_user(mock_convert_md):
 
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     document = Document.objects.get()
     assert response.json() == {"id": str(document.id)}
@@ -297,7 +302,9 @@ def test_api_documents_create_for_owner_existing_user_email_no_sub_with_fallback
 
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     document = Document.objects.get()
     assert response.json() == {"id": str(document.id)}
@@ -393,7 +400,9 @@ def test_api_documents_create_for_owner_new_user_no_sub_no_fallback_allow_duplic
         HTTP_AUTHORIZATION="Bearer DummyToken",
     )
     assert response.status_code == 201
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     document = Document.objects.get()
     assert response.json() == {"id": str(document.id)}
@@ -474,7 +483,9 @@ def test_api_documents_create_for_owner_with_default_language(
     )
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
     assert mock_send.call_args[0][3] == "de-de"
 
 
@@ -501,7 +512,9 @@ def test_api_documents_create_for_owner_with_custom_language(mock_convert_md):
 
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     assert len(mail.outbox) == 1
     email = mail.outbox[0]
@@ -537,7 +550,9 @@ def test_api_documents_create_for_owner_with_custom_subject_and_message(
 
     assert response.status_code == 201
 
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     assert len(mail.outbox) == 1
     email = mail.outbox[0]
@@ -571,7 +586,9 @@ def test_api_documents_create_for_owner_with_converter_exception(
         format="json",
         HTTP_AUTHORIZATION="Bearer DummyToken",
     )
-    mock_convert_md.assert_called_once_with("Document content")
+    mock_convert_md.assert_called_once_with(
+        "Document content", mime_types.MARKDOWN, mime_types.YJS
+    )
 
     assert response.status_code == 400
     assert response.json() == {"content": ["Could not convert content"]}