✨(backend) implement Find feature flags

For beta testing purposes we need to be able to activate
Find hybrid search to some users, Find full-text search
to some others and leave remaining users on basic DRF
title search.

Signed-off-by: charles <[email protected]>

src/backend/core/api/viewsets.py

@@ -32,6 +32,7 @@ from django.utils.translation import gettext_lazy as _
 
 import requests
 import rest_framework as drf
+import waffle
 from botocore.exceptions import ClientError
 from csp.constants import NONE
 from csp.decorators import csp_update
@@ -63,6 +64,7 @@ from core.services.search_indexers import (
 from core.tasks.mail import send_ask_for_access_mail
 from core.utils import extract_attachments, filter_descendants
 
+from ..enums import SearchType
 from . import permissions, serializers, utils
 from .filters import (
     DocumentFilter,
@@ -1181,6 +1183,10 @@ class DocumentViewSet(
         """
         params = serializers.SearchDocumentSerializer(data=request.query_params)
         params.is_valid(raise_exception=True)
+        search_type = self._get_search_type()
+
+        if search_type == SearchType.TITLE:
+            return self._title_search(request, params.validated_data, *args, **kwargs)
 
         indexer = get_document_indexer()
         if indexer is None:
@@ -1188,17 +1194,29 @@ class DocumentViewSet(
             return self._title_search(request, params.validated_data, *args, **kwargs)
 
         try:
-            return self._search_with_indexer(indexer, request, params=params)
+            return self._search_with_indexer(
+                indexer, request, params=params, search_type=search_type
+            )
         except requests.exceptions.RequestException as e:
             logger.error("Error while searching documents with indexer: %s", e)
             # fallback on title search if the indexer is not reached
-            return self._title_search(
-                request, params.validated_data, *args, **kwargs
-            )
+            return self._title_search(request, params.validated_data, *args, **kwargs)
 
+    def _get_search_type(self) -> SearchType:
+        """
+        Returns the search type to use for the search endpoint based on feature flags.
+        If a user has both flags activated the most advanced search is used
+        (HYBRID > FULL_TEXT > TITLE).
+        A user with no flag will default to the basic title search.
+        """
+        if waffle.flag_is_active(self.request, "flag_find_hybrid_search"):
+            return SearchType.HYBRID
+        if waffle.flag_is_active(self.request, "flag_find_full_text_search"):
+            return SearchType.FULL_TEXT
+        return SearchType.TITLE
 
     @staticmethod
-    def _search_with_indexer(indexer, request, params):
+    def _search_with_indexer(indexer, request, params, search_type):
         """
         Returns a list of documents matching the query (q) according to the configured indexer.
         """
@@ -1206,6 +1224,7 @@ class DocumentViewSet(
 
         results = indexer.search(
             q=params.validated_data["q"],
+            search_type=search_type,
             token=request.session.get("oidc_access_token"),
             path=(
                 params.validated_data["path"]

src/backend/core/enums.py

@@ -3,7 +3,7 @@ Core application enums declaration
 """
 
 import re
-from enum import StrEnum
+from enum import Enum, StrEnum
 
 from django.conf import global_settings, settings
 from django.db import models
@@ -46,3 +46,15 @@ class DocumentAttachmentStatus(StrEnum):
 
     PROCESSING = "processing"
     READY = "ready"
+
+
+class SearchType(str, Enum):
+    """
+    Defines the possible search types for a document search query.
+        - TITLE: DRF based search in the title of the documents only.
+        - HYBRID and FULL_TEXT: more advanced search based on Find indexer.
+    """
+
+    TITLE = "title"
+    HYBRID = "hybrid"
+    FULL_TEXT = "full-text"

src/backend/core/services/search_indexers.py

@@ -13,6 +13,7 @@ from django.utils.module_loading import import_string
 import requests
 
 from core import models, utils
+from core.enums import SearchType
 
 logger = logging.getLogger(__name__)
 
@@ -68,7 +69,7 @@ def get_batch_accesses_by_users_and_teams(paths):
     return dict(access_by_document_path)
 
 
-def get_visited_document_ids_of(queryset, user):
+def get_visited_document_ids_of(queryset, user) -> tuple[str, ...]:
     """
     Returns the ids of the documents that have a linktrace to the user and NOT owned.
     It will be use to limit the opensearch responses to the public documents already
@@ -92,7 +93,7 @@ def get_visited_document_ids_of(queryset, user):
         .distinct("pk")
     )
 
-    return [str(id) for id in docs.values_list("pk", flat=True)]
+    return tuple(str(id) for id in docs.values_list("pk", flat=True))
 
 
 class BaseDocumentIndexer(ABC):
@@ -181,8 +182,16 @@ class BaseDocumentIndexer(ABC):
         Must be implemented by subclasses.
         """
 
-    # pylint: disable-next=too-many-arguments,too-many-positional-arguments
-    def search(self, q, token, visited=(), nb_results=None, path=None):
+    # pylint: disable=too-many-arguments, too-many-positional-arguments
+    def search(  # noqa : PLR0913
+        self,
+        q: str,
+        token: str,
+        visited: tuple[str, ...] = (),
+        nb_results: int = None,
+        path: str = None,
+        search_type: SearchType = None,
+    ):
         """
         Search for documents in Find app.
         Ensure the same default ordering as "Docs" list : -updated_at
@@ -200,6 +209,8 @@ class BaseDocumentIndexer(ABC):
                 Defaults to 50 if not specified.
             path (str, optional):
                 The parent path to search descendants of.
+            search_type:
+                hybrid or full-text search
         """
         nb_results = nb_results or self.search_limit
         results = self.search_query(
@@ -211,6 +222,7 @@ class BaseDocumentIndexer(ABC):
                 "order_by": "updated_at",
                 "order_direction": "desc",
                 "path": path,
+                "search_type": search_type,
             },
             token=token,
         )
@@ -231,10 +243,29 @@ class FindDocumentIndexer(BaseDocumentIndexer):
     Document indexer that indexes and searches documents with La Suite Find app.
     """
 
-    # pylint: disable=too-many-arguments,too-many-positional-arguments
-    def search(self, q, token, visited=(), nb_results=None, path=None):
+    # pylint: disable=too-many-arguments, too-many-positional-arguments
+    def search(  # noqa : PLR0913
+        self,
+        q: str,
+        token: str,
+        visited: tuple[()] = (),
+        nb_results: int = None,
+        path: str = None,
+        search_type: SearchType = None,
+    ):
         """format Find search results"""
-        search_results = super().search(q, token, visited, nb_results, path)
+        search_results = (
+            super()
+            .search(
+                q=q,
+                token=token,
+                visited=visited,
+                nb_results=nb_results,
+                path=path,
+                search_type=search_type,
+            )
+            .get("results", [])
+        )
         return [
             {
                 **hit["_source"],

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

@@ -9,14 +9,23 @@ import responses
 from faker import Faker
 from rest_framework import response as drf_response
 from rest_framework.test import APIClient
+from waffle.testutils import override_flag
 
 from core import factories
+from core.enums import SearchType
 from core.services.search_indexers import get_document_indexer
 
 fake = Faker()
 pytestmark = pytest.mark.django_db
 
 
+@pytest.fixture(autouse=True)
+def enable_flag_find_hybrid_search():
+    """Enable flag_find_hybrid_search for all tests in this module."""
+    with override_flag("flag_find_hybrid_search", active=True):
+        yield
+
+
 @mock.patch("core.services.search_indexers.FindDocumentIndexer.search_query")
 @responses.activate
 def test_api_documents_search_anonymous(search_query, indexer_settings):
@@ -46,6 +55,7 @@ def test_api_documents_search_anonymous(search_query, indexer_settings):
             "order_by": "updated_at",
             "order_direction": "desc",
             "path": None,
+            "search_type": SearchType.HYBRID,
         },
         "token": None,
     }

src/backend/core/tests/test_services_find_document_indexer.py

@@ -12,6 +12,7 @@ from django.db import transaction
 import pytest
 
 from core import factories, models
+from core.enums import SearchType
 from core.services.search_indexers import FindDocumentIndexer
 
 pytestmark = pytest.mark.django_db
@@ -473,8 +474,14 @@ def test_find_document_indexer_search(mock_search_query):
     nb_results = 10
     path = "/some/path/"
     visited = ["doc-123"]
+    search_type = SearchType.HYBRID
     results = FindDocumentIndexer().search(
-        q=q, token=token, nb_results=nb_results, path=path, visited=visited
+        q=q,
+        token=token,
+        nb_results=nb_results,
+        path=path,
+        visited=visited,
+        search_type=search_type,
     )
 
     mock_search_query.assert_called_once()
@@ -487,6 +494,7 @@ def test_find_document_indexer_search(mock_search_query):
         "order_by": "updated_at",
         "order_direction": "desc",
         "path": path,
+        "search_type": search_type,
     }
 
     assert len(results) == 2

src/backend/core/tests/test_services_search_indexers.py

@@ -494,7 +494,7 @@ def test_get_visited_document_ids_of():
     factories.UserDocumentAccessFactory(user=user, document=doc2)
 
     # The second document have an access for the user
-    assert get_visited_document_ids_of(queryset, user) == [str(doc1.pk)]
+    assert get_visited_document_ids_of(queryset, user) == (str(doc1.pk),)
 
 
 @pytest.mark.usefixtures("indexer_settings")
@@ -528,7 +528,7 @@ def test_get_visited_document_ids_of_deleted():
     doc_deleted.soft_delete()
 
     # Only the first document is not deleted
-    assert get_visited_document_ids_of(queryset, user) == [str(doc.pk)]
+    assert get_visited_document_ids_of(queryset, user) == (str(doc.pk),)
 
 
 @responses.activate
@@ -548,7 +548,7 @@ def test_services_search_indexers_search_errors(indexer_settings):
     )
 
     with pytest.raises(HTTPError):
-        FindDocumentIndexer().search("alpha", token="mytoken")
+        FindDocumentIndexer().search(q="alpha", token="mytoken")
 
 
 @patch("requests.post")
@@ -572,7 +572,7 @@ def test_services_search_indexers_search(mock_post, indexer_settings):
 
     visited = get_visited_document_ids_of(models.Document.objects.all(), user)
 
-    indexer.search("alpha", visited=visited, token="mytoken")
+    indexer.search(q="alpha", visited=visited, token="mytoken")
 
     args, kwargs = mock_post.call_args
 
@@ -613,7 +613,7 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
 
     visited = get_visited_document_ids_of(models.Document.objects.all(), user)
 
-    indexer.search("alpha", visited=visited, token="mytoken")
+    indexer.search(q="alpha", visited=visited, token="mytoken")
 
     args, kwargs = mock_post.call_args
 
@@ -621,7 +621,7 @@ def test_services_search_indexers_search_nb_results(mock_post, indexer_settings)
     assert kwargs.get("json")["nb_results"] == 25
 
     # The argument overrides the setting value
-    indexer.search("alpha", visited=visited, token="mytoken", nb_results=109)
+    indexer.search(q="alpha", visited=visited, token="mytoken", nb_results=109)
 
     args, kwargs = mock_post.call_args