✨(documents) add content field as an S3 object

The content field is a writable property on the model which is persisted
in object storage. We take advantage of the versioning, robustness and
scalability of S3.

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

@@ -28,6 +28,7 @@ def test_api_documents_retrieve_anonymous_public():
         "accesses": [],
         "title": document.title,
         "is_public": True,
+        "content": {"foo": document.content["foo"]},
     }
 
 
@@ -69,6 +70,7 @@ def test_api_documents_retrieve_authenticated_unrelated_public():
         "accesses": [],
         "title": document.title,
         "is_public": True,
+        "content": {"foo": document.content["foo"]},
     }
 
 
@@ -132,6 +134,7 @@ def test_api_documents_retrieve_authenticated_related_direct():
     assert response.json() == {
         "id": str(document.id),
         "title": document.title,
+        "content": {"foo": document.content["foo"]},
         "abilities": document.get_abilities(user),
         "is_public": document.is_public,
     }
@@ -246,6 +249,7 @@ def test_api_documents_retrieve_authenticated_related_team_members(
     assert response.json() == {
         "id": str(document.id),
         "title": document.title,
+        "content": {"foo": document.content["foo"]},
         "abilities": document.get_abilities(user),
         "is_public": False,
     }
@@ -343,6 +347,7 @@ def test_api_documents_retrieve_authenticated_related_team_administrators(
     assert response.json() == {
         "id": str(document.id),
         "title": document.title,
+        "content": {"foo": document.content["foo"]},
         "abilities": document.get_abilities(user),
         "is_public": False,
     }
@@ -444,6 +449,7 @@ def test_api_documents_retrieve_authenticated_related_team_owners(
     assert response.json() == {
         "id": str(document.id),
         "title": document.title,
+        "content": {"foo": document.content["foo"]},
         "abilities": document.get_abilities(user),
         "is_public": False,
     }

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

@@ -6,7 +6,7 @@ import random
 import pytest
 from rest_framework.test import APIClient
 
-from core import factories
+from core import factories, models
 from core.api import serializers
 from core.tests.conftest import TEAM, USER, VIA
 
@@ -138,7 +138,7 @@ def test_api_documents_update_authenticated_administrator_or_owner(
     )
     assert response.status_code == 200
 
-    document.refresh_from_db()
+    document = models.Document.objects.get(pk=document.pk)
     document_values = serializers.DocumentSerializer(instance=document).data
     for key, value in document_values.items():
         if key in ["id", "accesses"]:
@@ -175,7 +175,7 @@ def test_api_documents_update_authenticated_owners(via, mock_user_get_teams):
     )
 
     assert response.status_code == 200
-    document.refresh_from_db()
+    document = models.Document.objects.get(pk=document.pk)
     document_values = serializers.DocumentSerializer(instance=document).data
     for key, value in document_values.items():
         if key in ["id", "accesses"]:

src/backend/core/tests/test_models_documents.py

@@ -3,8 +3,10 @@ Unit tests for the Document model
 """
 from django.contrib.auth.models import AnonymousUser
 from django.core.exceptions import ValidationError
+from django.core.files.storage import default_storage
 
 import pytest
+import requests
 
 from core import factories, models
 
@@ -159,3 +161,47 @@ def test_models_documents_get_abilities_preset_role(django_assert_num_queries):
         "manage_accesses": False,
         "partial_update": False,
     }
+
+
+def test_models_documents_file_upload_to_minio():
+    """Validate read/write from/to minio"""
+    document = factories.DocumentFactory()
+    document.content = {"foé": "çar"}
+    document.save()
+
+    # Check that the file exists in MinIO:
+    file_key = str(document.pk)
+    # - through the storage backend
+    assert default_storage.exists(file_key) is True
+    # - directly from minio
+    signed_url = default_storage.url(file_key)
+    response = requests.get(signed_url, timeout=1)
+    assert response.json() == {"foé": "çar"}
+
+
+def test_models_documents_version_duplicate():
+    """A new version should be created in object storage only if the content has changed."""
+    document = factories.DocumentFactory()
+
+    file_key = str(document.pk)
+    response = default_storage.connection.meta.client.list_object_versions(
+        Bucket=default_storage.bucket_name, Prefix=file_key
+    )
+    assert len(response["Versions"]) == 1
+
+    # Save again with the same content
+    document.save()
+
+    response = default_storage.connection.meta.client.list_object_versions(
+        Bucket=default_storage.bucket_name, Prefix=file_key
+    )
+    assert len(response["Versions"]) == 1
+
+    # Save modified content
+    document.content = {"foo": "spam"}
+    document.save()
+
+    response = default_storage.connection.meta.client.list_object_versions(
+        Bucket=default_storage.bucket_name, Prefix=file_key
+    )
+    assert len(response["Versions"]) == 2