✨(backend) refactor indexation signals and fix circular import issues

Signed-off-by: Fabre Florian <[email protected]>

Author: joehybird

CHANGELOG.md

@@ -32,6 +32,8 @@ and this project adheres to
 ### Added
 
 - ✨(api) add API route to fetch document content #1206
+- ✨(backend) add async indexation of documents with Find API #1276
+- ✨(api) add API route to search indexed documents in Find #1276
 
 ### Changed
 

src/backend/core/apps.py

@@ -1,11 +1,19 @@
 """Impress Core application"""
-# from django.apps import AppConfig
-# from django.utils.translation import gettext_lazy as _
 
+from django.apps import AppConfig
+from django.utils.translation import gettext_lazy as _
 
-# class CoreConfig(AppConfig):
-#     """Configuration class for the impress core app."""
 
-#     name = "core"
-#     app_label = "core"
-#     verbose_name = _("impress core application")
+class CoreConfig(AppConfig):
+    """Configuration class for the impress core app."""
+
+    name = "core"
+    app_label = "core"
+    verbose_name = _("Impress core application")
+
+    def ready(self):
+        """
+        Import signals when the app is ready.
+        """
+        # pylint: disable=import-outside-toplevel, unused-import
+        from . import signals  # noqa: PLC0415

src/backend/core/models.py

@@ -20,9 +20,7 @@
 from django.core.files.storage import default_storage
 from django.core.mail import send_mail
 from django.db import models, transaction
-from django.db.models import signals
 from django.db.models.functions import Left, Length
-from django.dispatch import receiver
 from django.template.loader import render_to_string
 from django.utils import timezone
 from django.utils.functional import cached_property
@@ -41,7 +39,6 @@
     RoleChoices,
     get_equivalent_link_definition,
 )
-from .tasks.find import trigger_document_indexer
 from .validators import sub_validator
 
 logger = getLogger(__name__)
@@ -950,16 +947,6 @@ def restore(self):
             )
 
 
-@receiver(signals.post_save, sender=Document)
-def document_post_save(sender, instance, **kwargs):  # pylint: disable=unused-argument
-    """
-    Asynchronous call to the document indexer at the end of the transaction.
-    Note : Within the transaction we can have an empty content and a serialization
-    error.
-    """
-    trigger_document_indexer(instance, on_commit=True)
-
-
 class LinkTrace(BaseModel):
     """
     Relation model to trace accesses to a document via a link by a logged-in user.
@@ -1185,15 +1172,6 @@ def get_abilities(self, user):
         }
 
 
-@receiver(signals.post_save, sender=DocumentAccess)
-def document_access_post_save(sender, instance, created, **kwargs):  # pylint: disable=unused-argument
-    """
-    Asynchronous call to the document indexer at the end of the transaction.
-    """
-    if not created:
-        trigger_document_indexer(instance.document, on_commit=True)
-
-
 class DocumentAskForAccess(BaseModel):
     """Relation model to ask for access to a document."""
 

src/backend/core/signals.py

@@ -0,0 +1,28 @@
+"""
+Declare and configure the signals for the impress core application
+"""
+
+from django.db.models import signals
+from django.dispatch import receiver
+
+from . import models
+from .tasks.find import trigger_document_indexer
+
+
+@receiver(signals.post_save, sender=models.Document)
+def document_post_save(sender, instance, **kwargs):  # pylint: disable=unused-argument
+    """
+    Asynchronous call to the document indexer at the end of the transaction.
+    Note : Within the transaction we can have an empty content and a serialization
+    error.
+    """
+    trigger_document_indexer(instance, on_commit=True)
+
+
+@receiver(signals.post_save, sender=models.DocumentAccess)
+def document_access_post_save(sender, instance, created, **kwargs):  # pylint: disable=unused-argument
+    """
+    Asynchronous call to the document indexer at the end of the transaction.
+    """
+    if not created:
+        trigger_document_indexer(instance.document, on_commit=True)

src/backend/core/tasks/find.py

@@ -7,12 +7,6 @@
 from django.core.cache import cache
 from django.db import transaction
 
-from core import models
-from core.services.search_indexers import (
-    get_batch_accesses_by_users_and_teams,
-    get_document_indexer_class,
-)
-
 from impress.celery_app import app
 
 logger = getLogger(__file__)
@@ -52,6 +46,13 @@ def document_indexer_task(document_id):
         logger.info("Skip document %s indexation", document_id)
         return
 
+    # pylint: disable=import-outside-toplevel
+    from core import models  # noqa: PLC0415
+    from core.services.search_indexers import (  # noqa: PLC0415
+        get_batch_accesses_by_users_and_teams,
+        get_document_indexer_class,
+    )
+
     doc = models.Document.objects.get(pk=document_id)
     indexer = get_document_indexer_class()()
     accesses = get_batch_accesses_by_users_and_teams((doc.path,))

src/backend/core/tests/test_models_documents.py

@@ -3,11 +3,11 @@
 """
 # pylint: disable=too-many-lines
 
-from operator import itemgetter
 import random
 import smtplib
 import time
 from logging import Logger
+from operator import itemgetter
 from unittest import mock
 
 from django.contrib.auth.models import AnonymousUser
@@ -1445,13 +1445,13 @@ def test_models_documents_post_save_indexer(mock_push, settings):
 
     indexer = FindDocumentIndexer()
 
-    assert sorted(data, key=itemgetter('id')) == sorted(
+    assert sorted(data, key=itemgetter("id")) == sorted(
         [
             indexer.serialize_document(doc1, accesses),
             indexer.serialize_document(doc2, accesses),
             indexer.serialize_document(doc3, accesses),
         ],
-        key=itemgetter('id'),
+        key=itemgetter("id"),
     )
 
     # The debounce counters should be reset

src/backend/core/tests/test_services_search_indexers.py

@@ -36,7 +36,6 @@ def format_response(self, data: dict):
         return {}
 
 
-
 @pytest.fixture(name="fake_indexer_settings")
 def fake_indexer_settings_fixture(settings):
     """Fixture to switch the indexer to the FakeDocumentIndexer."""
@@ -103,6 +102,7 @@ def test_services_search_indexer_class(fake_indexer_settings):
         "core.tests.test_services_search_indexers.FakeDocumentIndexer"
     )
 
+
 def test_services_search_indexer_url_is_none(settings):
     """
     Indexer should raise RuntimeError if SEARCH_INDEXER_URL is None or empty.