🐛(back) validate document content in serializer

We recently extract images url in the content. For this, we assume that
the document content is always in base64. We enforce this assumption by
checking if it's a valide base64 in the serializer.

Author: lunika

CHANGELOG.md

@@ -8,6 +8,10 @@ and this project adheres to
 
 ## [Unreleased]
 
+## Fixed
+
+- 🐛(back) validate document content in serializer #822
+
 ## [3.0.0] - 2025-03-28
 
 ## Added

src/backend/core/api/serializers.py

@@ -1,6 +1,8 @@
 """Client serializers for the impress core app."""
 
+import binascii
 import mimetypes
+from base64 import b64decode
 
 from django.conf import settings
 from django.db.models import Q
@@ -299,6 +301,18 @@ def validate_id(self, value):
 
         return value
 
+    def validate_content(self, value):
+        """Validate the content field."""
+        if not value:
+            return None
+
+        try:
+            b64decode(value, validate=True)
+        except binascii.Error as err:
+            raise serializers.ValidationError("Invalid base64 content.") from err
+
+        return value
+
     def save(self, **kwargs):
         """
         Process the content field to extract attachment keys and update the document's

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

@@ -328,3 +328,22 @@ def test_api_documents_update_administrator_or_owner_of_another(via, mock_user_t
     other_document.refresh_from_db()
     other_document_values = serializers.DocumentSerializer(instance=other_document).data
     assert other_document_values == old_document_values
+
+
+def test_api_documents_update_invalid_content():
+    """
+    Updating a document with a non base64 encoded content should raise a validation error.
+    """
+    user = factories.UserFactory(with_owned_document=True)
+    client = APIClient()
+    client.force_login(user)
+
+    document = factories.DocumentFactory(users=[[user, "owner"]])
+
+    response = client.put(
+        f"/api/v1.0/documents/{document.id!s}/",
+        {"content": "invalid content"},
+        format="json",
+    )
+    assert response.status_code == 400
+    assert response.json() == {"content": ["Invalid base64 content."]}