✨(backend) add async triggers to enable document indexation with find

On document content or permission changes, start a celery job that will call the
indexation API of the app "Find".

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

src/backend/core/services/search_indexers.py

@@ -5,6 +5,7 @@ from abc import ABC, abstractmethod
 from collections import defaultdict
 
 from django.conf import settings
+from django.contrib.auth.models import AnonymousUser
 
 import requests
 
@@ -18,11 +19,13 @@ def get_batch_accesses_by_users_and_teams(paths):
     Get accesses related to a list of document paths,
     grouped by users and teams, including all ancestor paths.
     """
-    print("paths: ", paths)
-    ancestor_map = utils.get_ancestor_to_descendants_map(paths, steplen=models.Document.steplen)
+    # print("paths: ", paths)
+    ancestor_map = utils.get_ancestor_to_descendants_map(
+        paths, steplen=models.Document.steplen
+    )
     ancestor_paths = list(ancestor_map.keys())
-    print("ancestor map: ", ancestor_map)
-    print("ancestor paths: ", ancestor_paths)
+    # print("ancestor map: ", ancestor_map)
+    # print("ancestor paths: ", ancestor_paths)
 
     access_qs = models.DocumentAccess.objects.filter(
         document__path__in=ancestor_paths
@@ -44,6 +47,22 @@ def get_batch_accesses_by_users_and_teams(paths):
     return dict(access_by_document_path)
 
 
+def get_visited_document_ids_of(user):
+    if isinstance(user, AnonymousUser):
+        return []
+
+    # TODO : exclude links when user already have a specific access to the doc
+    qs = models.LinkTrace.objects.filter(
+        user=user
+    ).exclude(
+        document__accesses__user=user,
+    )
+
+    return list({
+        str(id) for id in qs.values_list("document_id", flat=True)
+    })
+
+
 class BaseDocumentIndexer(ABC):
     """
     Base class for document indexers.
@@ -84,6 +103,7 @@ class BaseDocumentIndexer(ABC):
             serialized_batch = [
                 self.serialize_document(document, accesses_by_document_path)
                 for document in documents_batch
+                if document.content
             ]
             self.push(serialized_batch)
 
@@ -103,6 +123,38 @@ class BaseDocumentIndexer(ABC):
         Must be implemented by subclasses.
         """
 
+    def search(self, text, user, token):
+        """
+        Search for documents in Find app.
+        """
+        visited_ids = get_visited_document_ids_of(user)
+
+        response = self.search_query(data={
+            "q": text,
+            "visited": visited_ids,
+            "services": ["docs"],
+        }, token=token)
+
+        print(response)
+
+        return self.format_response(response)
+
+    @abstractmethod
+    def search_query(self, data, token) -> dict:
+        """
+        Retreive documents from the Find app API.
+
+        Must be implemented by subclasses.
+        """
+
+    @abstractmethod
+    def format_response(self, data: dict):
+        """
+        Convert the JSON response from Find app as document queryset.
+
+        Must be implemented by subclasses.
+        """
+
 
 class FindDocumentIndexer(BaseDocumentIndexer):
     """
@@ -121,10 +173,12 @@ class FindDocumentIndexer(BaseDocumentIndexer):
             dict: A JSON-serializable dictionary.
         """
         doc_path = document.path
-        text_content = utils.base64_yjs_to_text(document.content)
+        doc_content = document.content
+        text_content = utils.base64_yjs_to_text(doc_content) if doc_content else ""
+
         return {
             "id": str(document.id),
-            "title": document.title,
+            "title": document.title or "",
             "content": text_content,
             "depth": document.depth,
             "path": document.path,
@@ -138,6 +192,46 @@ class FindDocumentIndexer(BaseDocumentIndexer):
             "is_active": not bool(document.ancestors_deleted_at),
         }
 
+    def search_query(self, data, token) -> requests.Response:
+        """
+        Retrieve documents from the Find app API.
+
+        Args:
+            data (dict): search data
+            token (str): OICD token
+
+        Returns:
+            dict: A JSON-serializable dictionary.
+        """
+        url = getattr(settings, "SEARCH_INDEXER_QUERY_URL", None)
+
+        if not url:
+            raise RuntimeError(
+                "SEARCH_INDEXER_QUERY_URL must be set in Django settings before indexing."
+            )
+
+        try:
+            response = requests.post(
+                url,
+                json=data,
+                headers={"Authorization": f"Bearer {token}"},
+                timeout=10,
+            )
+            response.raise_for_status()
+            return response.json()
+        except requests.exceptions.HTTPError as e:
+            logger.error("HTTPError: %s", e)
+            logger.error("Response content: %s", response.text)  # type: ignore
+            raise
+
+    def format_response(self, data: dict):
+        """
+        Retrieve documents ids from Find app response and return a queryset.
+        """
+        return models.Document.objects.filter(pk__in=[
+            d['_id'] for d in data
+        ])
+
     def push(self, data):
         """
         Push a batch of documents to the Find backend.
@@ -156,6 +250,7 @@ class FindDocumentIndexer(BaseDocumentIndexer):
             raise RuntimeError(
                 "SEARCH_INDEXER_SECRET must be set in Django settings before indexing."
             )
+
         try:
             response = requests.post(
                 url,