✨(backend) adapt to Find new search pagination

Use nb_results instead of page/page_size argument for /search API.

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

Author: joehybird

src/backend/core/api/viewsets.py

@@ -1105,8 +1105,6 @@ def _search_fulltext(self, indexer, request, params):
             text=text,
             token=access_token,
             visited=get_visited_document_ids_of(queryset, user),
-            page=1,
-            page_size=100,
         )
 
         docs_by_uuid = {str(d.pk): d for d in queryset.filter(pk__in=results)}

src/backend/core/services/search_indexers.py

@@ -110,6 +110,7 @@ def __init__(self):
         self.indexer_url = settings.SEARCH_INDEXER_URL
         self.indexer_secret = settings.SEARCH_INDEXER_SECRET
         self.search_url = settings.SEARCH_INDEXER_QUERY_URL
+        self.search_limit = settings.SEARCH_INDEXER_QUERY_LIMIT
 
         if not self.indexer_url:
             raise ImproperlyConfigured(
@@ -184,7 +185,7 @@ def push(self, data):
         """
 
     # pylint: disable-next=too-many-arguments,too-many-positional-arguments
-    def search(self, text, token, visited=(), page=1, page_size=50):
+    def search(self, text, token, visited=(), nb_results=None):
         """
         Search for documents in Find app.
         Ensure the same default ordering as "Docs" list : -updated_at
@@ -197,20 +198,17 @@ def search(self, text, token, visited=(), page=1, page_size=50):
             visited (list, optional):
                 List of ids of active public documents with LinkTrace
                 Defaults to settings.SEARCH_INDEXER_BATCH_SIZE.
-            page (int, optional):
-                The page number to retrieve.
-                Defaults to 1 if not specified.
-            page_size (int, optional):
-                The number of results to return per page.
+            nb_results (int, optional):
+                The number of results to return.
                 Defaults to 50 if not specified.
         """
+        nb_results = nb_results or self.search_limit
         response = self.search_query(
             data={
                 "q": text,
                 "visited": visited,
                 "services": ["docs"],
-                "page_number": page,
-                "page_size": page_size,
+                "nb_results": nb_results,
                 "order_by": "updated_at",
                 "order_direction": "desc",
             },

src/backend/core/tasks/search.py

@@ -23,11 +23,9 @@ def document_indexer_task(document_id):
     """Celery Task : Sends indexation query for a document."""
     indexer = get_document_indexer()
 
-    if indexer is None:
-        return
-
-    logger.info("Start document %s indexation", document_id)
-    indexer.index(models.Document.objects.filter(pk=document_id))
+    if indexer:
+        logger.info("Start document %s indexation", document_id)
+        indexer.index(models.Document.objects.filter(pk=document_id))
 
 
 def batch_indexer_throttle_acquire(timeout: int = 0, atomic: bool = True):

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

@@ -326,8 +326,7 @@ def test_api_documents_search_pagination(
             "q": "alpha",
             "visited": [],
             "services": ["docs"],
-            "page_number": 1,
-            "page_size": 100,
+            "nb_results": 50,
             "order_by": "updated_at",
             "order_direction": "desc",
         }

src/backend/core/tests/test_services_search_indexers.py

@@ -588,10 +588,48 @@ def test_services_search_indexers_search(mock_post, indexer_settings):
     assert query_data["q"] == "alpha"
     assert sorted(query_data["visited"]) == sorted([str(doc1.pk), str(doc2.pk)])
     assert query_data["services"] == ["docs"]
-    assert query_data["page_number"] == 1
-    assert query_data["page_size"] == 50
+    assert query_data["nb_results"] == 50
     assert query_data["order_by"] == "updated_at"
     assert query_data["order_direction"] == "desc"
 
     assert kwargs.get("headers") == {"Authorization": "Bearer mytoken"}
     assert kwargs.get("timeout") == 10
+
+
+@patch("requests.post")
+def test_services_search_indexers_search_nb_results(mock_post, indexer_settings):
+    """
+    Find API call should have nb_results == SEARCH_INDEXER_QUERY_LIMIT
+    or the given nb_results argument.
+    """
+    indexer_settings.SEARCH_INDEXER_QUERY_LIMIT = 25
+
+    user = factories.UserFactory()
+    indexer = SearchIndexer()
+
+    mock_response = mock_post.return_value
+    mock_response.raise_for_status.return_value = None  # No error
+
+    doc1, doc2, _ = factories.DocumentFactory.create_batch(3)
+
+    create_link = partial(models.LinkTrace.objects.create, user=user, is_masked=False)
+
+    create_link(document=doc1)
+    create_link(document=doc2)
+
+    visited = get_visited_document_ids_of(models.Document.objects.all(), user)
+
+    indexer.search("alpha", visited=visited, token="mytoken")
+
+    args, kwargs = mock_post.call_args
+
+    assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
+    assert kwargs.get("json")["nb_results"] == 25
+
+    # The argument overrides the setting value
+    indexer.search("alpha", visited=visited, token="mytoken", nb_results=109)
+
+    args, kwargs = mock_post.call_args
+
+    assert args[0] == indexer_settings.SEARCH_INDEXER_QUERY_URL
+    assert kwargs.get("json")["nb_results"] == 109

src/backend/impress/settings.py

@@ -120,6 +120,9 @@ class Base(Configuration):
     SEARCH_INDEXER_QUERY_URL = values.Value(
         default=None, environ_name="SEARCH_INDEXER_QUERY_URL", environ_prefix=None
     )
+    SEARCH_INDEXER_QUERY_LIMIT = values.PositiveIntegerValue(
+        default=50, environ_name="SEARCH_INDEXER_QUERY_LIMIT", environ_prefix=None
+    )
 
     # Static files (CSS, JavaScript, Images)
     STATIC_URL = "/static/"