✨(backend) add indexed search feature flag

Add setting FEATURES_INDEXED_SEARCH that allows to disable the
search of indexed files while using the indexation tools.

Signed-off-by: Fabre Florian <ffabre@hybird.org>

docs/env.md

@@ -42,6 +42,7 @@ This document lists all configurable environment variables for the Drive applica
 | `EMAIL_USE_SSL` | Use SSL for SMTP connection | `False` |
 | `EMAIL_USE_TLS` | Use TLS for SMTP connection | `False` |
 | `FEATURES_ALPHA` | Enable alpha features | `False` |
+| `FEATURES_INDEXED_SEARCH` | Enable the search of indexed files through the API | `True` |
 | `FRONTEND_THEME` | Frontend theme configuration | `None` |
 | `FRONTEND_FEEDBACK_BUTTON_SHOW` | Show feedback button | `False` |
 | `FRONTEND_FEEDBACK_BUTTON_IDLE` | Make feedback button idle (e.g. to bind to external library) | `False` |

docs/setup-find.md

@@ -15,7 +15,7 @@ See [how-to-use-indexer.md](how-to-use-indexer.md) for details.
 
 ## Configure settings of Drive
 
-Add those Django settings the Drive application to enable the feature.
+Add those Django settings the Drive application to enable the indexation feature.
 
 ```python
 SEARCH_INDEXER_CLASS="core.services.search_indexers.SearchIndexer"
@@ -43,3 +43,9 @@ OIDC_STORE_ACCESS_TOKEN = True  # Store the access token in the session
 OIDC_STORE_REFRESH_TOKEN = True  # Store the encrypted refresh token in the session
 OIDC_STORE_REFRESH_TOKEN_KEY = "your-32-byte-encryption-key=="  # Must be a valid Fernet key (32 url-safe base64-encoded bytes)
 ```
+
+And to enable the search of indexed files through the API, add this feature flag (default=True)
+
+```python
+FEATURES_INDEXED_SEARCH=True
+```

env.d/development/common

@@ -80,6 +80,9 @@ SEARCH_INDEXER_SECRET=find-api-key-for-driv-with-exactly-50-chars-length   # Key
 SEARCH_INDEXER_URL="http://find:8000/api/v1.0/documents/index/"
 SEARCH_INDEXER_QUERY_URL="http://find:8000/api/v1.0/documents/search/"
 
+# Enables the search of indexed files through the API
+FEATURES_INDEXED_SEARCH=True
+
 # Store OIDC tokens in the session
 # OIDC_STORE_ACCESS_TOKEN = True
 # OIDC_STORE_REFRESH_TOKEN = True # Store the encrypted refresh token in the session.

src/backend/core/api/viewsets.py

@@ -1097,7 +1097,7 @@ class ItemViewSet(
         Applies filtering based on request parameter 'q' from `SearchItemFilter`.
         Depending of the configuration it can be:
          - A fulltext search through the opensearch indexation app "find" if the backend is
-           enabled (see SEARCH_INDEXER_CLASS)
+           enabled (see SEARCH_INDEXER_CLASS) and the feature flag INDEXED_SEARCH_ENABLED is True
          - A filtering by the model fields 'title' & 'type'.
         """
         queryset = self.queryset
@@ -1136,7 +1136,8 @@ class ItemViewSet(
 
         queryset = queryset.filter(path_list)
 
-        if indexer:
+        # use indexed search ONLY when the feature flag is enabled
+        if indexer and settings.FEATURES_INDEXED_SEARCH is True:
             # When the indexer is configured pop "title" from queryset search and use
             # fulltext results instead.
             return self._indexed_search(

src/backend/core/services/search_indexers.py

@@ -278,7 +278,8 @@ class SearchIndexer(BaseItemIndexer):
         mimetype = item.mimetype or ""
 
         if mimetype.startswith("text/"):
-            return default_storage.open(item.file_key, "rb").read().decode()
+            with default_storage.open(item.file_key, "rb") as fd:
+                return fd.read().decode()
 
         raise SuspiciousFileOperation(f"Unrecognized mimetype {mimetype}")
 

src/backend/core/tests/items/test_api_items_search_fulltext.py

@@ -437,3 +437,36 @@ def test_api_items_search_pagination_endpoint_is_none(
         assert content["count"] == expected["count"]
         assert content["previous"] == previous_url
         assert content["next"] == next_url
+
+
+def test_api_items_search_feature_disabled(indexer_settings):
+    """Should not use indexed search if the feature is disabled"""
+    indexer_settings.FEATURES_INDEXED_SEARCH = False
+
+    assert get_file_indexer() is not None
+
+    user = factories.UserFactory()
+
+    client = APIClient()
+    client.force_login(user)
+
+    docs = factories.ItemFactory.create_batch(
+        5,
+        title="alpha",
+        users=[user],
+        parent=user.get_main_workspace(),
+    )
+
+    response = client.get(
+        "/api/v1.0/items/search/",
+        data={
+            "title": "alpha",
+        },
+    )
+
+    assert response.status_code == 200
+
+    content = response.json()
+    results = content.pop("results")
+
+    assert [r["id"] for r in results] == [str(d.pk) for d in docs]

src/backend/drive/settings.py

@@ -159,6 +159,10 @@ class Base(Configuration):
         },
     }
 
+    FEATURES_INDEXED_SEARCH = values.BooleanValue(
+        default=True, environ_name="FEATURES_INDEXED_SEARCH", environ_prefix=None
+    )
+
     # Posthog
     POSTHOG_KEY = SecretFileValue(None, environ_name="POSTHOG_KEY", environ_prefix=None)
     POSTHOG_HOST = values.Value(
@@ -1052,6 +1056,8 @@ class Test(Base):
 
     CELERY_TASK_ALWAYS_EAGER = values.BooleanValue(True)
 
+    FEATURES_INDEXED_SEARCH = True
+
     SEARCH_INDEXER_CLASS = None
     OIDC_STORE_ACCESS_TOKEN = False
     OIDC_STORE_REFRESH_TOKEN = False