Integrate find

CHANGELOG.md

@@ -20,6 +20,7 @@ and this project adheres to
 - ✨(frontend) Add stat for Crisp #1824
 - ✨(auth) add silent login #1690
 - 🔧(project) add DJANGO_EMAIL_URL_APP environment variable #1825
+- ✨ integrate Find search
 
 ### Changed
 

README.md

@@ -147,6 +147,10 @@ $ make frontend-test
 $ make frontend-lint
 ```
 
+Backend tests can be run without docker with the env files
+`env.d/development/common` and `env.d/development/common.test`.
+`common.test` must overwrite some variables in `common`.
+
 **Adding content**
 
 You can create a basic demo site by running this command:

docs/search.md

@@ -15,7 +15,7 @@ See [how-to-use-indexer.md](how-to-use-indexer.md) for details.
 
 ## Configure settings of Docs
 
-Add those Django settings the Docs application to enable the feature.
+Add those Django settings to the Docs application to enable the feature.
 
 ```shell
 SEARCH_INDEXER_CLASS="core.services.search_indexers.FindDocumentIndexer"

env.d/development/common

@@ -52,8 +52,8 @@ OIDC_REDIRECT_ALLOWED_HOSTS="localhost:8083,localhost:3000"
 OIDC_AUTH_REQUEST_EXTRA_PARAMS={"acr_values": "eidas1"}
 
 # Store OIDC tokens in the session. Needed by search/ endpoint.
-# OIDC_STORE_ACCESS_TOKEN = True
-# OIDC_STORE_REFRESH_TOKEN = True # Store the encrypted refresh token in the session.
+OIDC_STORE_ACCESS_TOKEN=True
+OIDC_STORE_REFRESH_TOKEN=True # Store the encrypted refresh token in the session.
 
 # Must be a valid Fernet key (32 url-safe base64-encoded bytes)
 # To create one, use the bin/fernetkey command.
@@ -82,8 +82,9 @@ DOCSPEC_API_URL=http://docspec:4000/conversion
 # Theme customization
 THEME_CUSTOMIZATION_CACHE_TIMEOUT=15
 
-# Indexer (disabled)
-# SEARCH_INDEXER_CLASS="core.services.search_indexers.SearchIndexer"
+# Indexer
+SEARCH_INDEXER_CLASS=core.services.search_indexers.FindDocumentIndexer
 SEARCH_INDEXER_SECRET=find-api-key-for-docs-with-exactly-50-chars-length  # Key generated by create_demo in Find app.
-SEARCH_INDEXER_URL="http://find:8000/api/v1.0/documents/index/"
-SEARCH_INDEXER_QUERY_URL="http://find:8000/api/v1.0/documents/search/"
+SEARCH_INDEXER_URL=http://find:8000/api/v1.0/documents/index/
+SEARCH_INDEXER_QUERY_URL=http://find:8000/api/v1.0/documents/search/
+SEARCH_INDEXER_QUERY_LIMIT=50

env.d/development/common.test

@@ -0,0 +1,7 @@
+# Test environment configuration for running tests without docker
+# Base configuration is loaded from 'common' file
+
+DJANGO_SETTINGS_MODULE=impress.settings
+DJANGO_CONFIGURATION=Test
+DB_PORT=15432
+AWS_S3_ENDPOINT_URL=http://localhost:9000

src/backend/core/api/permissions.py

@@ -12,6 +12,7 @@
 ACTION_FOR_METHOD_TO_PERMISSION = {
     "versions_detail": {"DELETE": "versions_destroy", "GET": "versions_retrieve"},
     "children": {"GET": "children_list", "POST": "children_create"},
+    "search": {"GET": "retrieve"},
 }
 
 

src/backend/core/api/serializers.py

@@ -980,8 +980,5 @@ def get_abilities(self, thread):
 class SearchDocumentSerializer(serializers.Serializer):
     """Serializer for fulltext search requests through Find application"""
 
-    q = serializers.CharField(required=True, allow_blank=False, trim_whitespace=True)
-    page_size = serializers.IntegerField(
-        required=False, min_value=1, max_value=50, default=20
-    )
-    page = serializers.IntegerField(required=False, min_value=1, default=1)
+    q = serializers.CharField(required=True, allow_blank=True, trim_whitespace=True)
+    path = serializers.CharField(required=False, allow_blank=False)

src/backend/core/api/viewsets.py

@@ -64,7 +64,11 @@
 from core.utils import extract_attachments, filter_descendants
 
 from . import permissions, serializers, utils
-from .filters import DocumentFilter, ListDocumentFilter, UserSearchFilter
+from .filters import (
+    DocumentFilter,
+    ListDocumentFilter,
+    UserSearchFilter,
+)
 from .throttling import (
     DocumentThrottle,
     UserListThrottleBurst,
@@ -459,14 +463,12 @@ def list(self, request, *args, **kwargs):
         It performs early filtering on model fields, annotates user roles, and removes
         descendant documents to keep only the highest ancestors readable by the current user.
         """
-        user = self.request.user
+        user = request.user
 
         # Not calling filter_queryset. We do our own cooking.
         queryset = self.get_queryset()
 
-        filterset = ListDocumentFilter(
-            self.request.GET, queryset=queryset, request=self.request
-        )
+        filterset = ListDocumentFilter(request.GET, queryset=queryset, request=request)
         if not filterset.is_valid():
             raise drf.exceptions.ValidationError(filterset.errors)
         filter_data = filterset.form.cleaned_data
@@ -956,26 +958,6 @@ def all(self, request, *args, **kwargs):
 
         return self.get_response_for_queryset(queryset)
 
-    @drf.decorators.action(
-        detail=True,
-        methods=["get"],
-        ordering=["path"],
-    )
-    def descendants(self, request, *args, **kwargs):
-        """Handle listing descendants of a document"""
-        document = self.get_object()
-
-        queryset = document.get_descendants().filter(ancestors_deleted_at__isnull=True)
-        queryset = self.filter_queryset(queryset)
-
-        filterset = DocumentFilter(request.GET, queryset=queryset)
-        if not filterset.is_valid():
-            raise drf.exceptions.ValidationError(filterset.errors)
-
-        queryset = filterset.qs
-
-        return self.get_response_for_queryset(queryset)
-
     @drf.decorators.action(
         detail=True,
         methods=["get"],
@@ -1183,57 +1165,6 @@ def duplicate(self, request, *args, **kwargs):
             {"id": str(duplicated_document.id)}, status=status.HTTP_201_CREATED
         )
 
-    def _search_simple(self, request, text):
-        """
-        Returns a queryset filtered by the content of the document title
-        """
-        # As the 'list' view we get a prefiltered queryset (deleted docs are excluded)
-        queryset = self.get_queryset()
-        filterset = DocumentFilter({"title": text}, queryset=queryset)
-
-        if not filterset.is_valid():
-            raise drf.exceptions.ValidationError(filterset.errors)
-
-        queryset = filterset.filter_queryset(queryset)
-
-        return self.get_response_for_queryset(
-            queryset.order_by("-updated_at"),
-            context={
-                "request": request,
-            },
-        )
-
-    def _search_fulltext(self, indexer, request, params):
-        """
-        Returns a queryset from the results the fulltext search of Find
-        """
-        access_token = request.session.get("oidc_access_token")
-        user = request.user
-        text = params.validated_data["q"]
-        queryset = models.Document.objects.all()
-
-        # Retrieve the documents ids from Find.
-        results = indexer.search(
-            text=text,
-            token=access_token,
-            visited=get_visited_document_ids_of(queryset, user),
-        )
-
-        docs_by_uuid = {str(d.pk): d for d in queryset.filter(pk__in=results)}
-        ordered_docs = [docs_by_uuid[id] for id in results]
-
-        page = self.paginate_queryset(ordered_docs)
-
-        serializer = self.get_serializer(
-            page if page else ordered_docs,
-            many=True,
-            context={
-                "request": request,
-            },
-        )
-
-        return self.get_paginated_response(serializer.data)
-
     @drf.decorators.action(detail=False, methods=["get"], url_path="search")
     @method_decorator(refresh_oidc_access_token)
     def search(self, request, *args, **kwargs):
@@ -1252,13 +1183,82 @@ def search(self, request, *args, **kwargs):
         params.is_valid(raise_exception=True)
 
         indexer = get_document_indexer()
-
         if indexer:
-            return self._search_fulltext(indexer, request, params=params)
+            return self._search_with_indexer(indexer, request, params=params)
+
+        # The indexer is not configured, we fallback on title search
+        return self.title_search(request, params.validated_data, *args, **kwargs)
 
-        # The indexer is not configured, we fallback on a simple icontains filter by the
-        # model field 'title'.
-        return self._search_simple(request, text=params.validated_data["q"])
+    @staticmethod
+    def _search_with_indexer(indexer, request, params):
+        """
+        Returns a list of documents matching the query (q) according to the configured indexer.
+        """
+        queryset = models.Document.objects.all()
+        user_query = params.validated_data["q"]
+
+        results = indexer.search(
+            q=user_query if user_query != "" else "*",
+            token=request.session.get("oidc_access_token"),
+            path=(
+                params.validated_data["path"]
+                if "path" in params.validated_data
+                else None
+            ),
+            visited=get_visited_document_ids_of(queryset, request.user),
+        )
+
+        return drf_response.Response(
+            {
+                "count": len(results),
+                "next": None,
+                "previous": None,
+                "results": results,
+            }
+        )
+
+    def title_search(self, request, validated_data, *args, **kwargs):
+        """
+        Fallback search by title when indexer is not configured.
+        If path is provided, list descendants, otherwise list all documents.
+        """
+        request.GET = request.GET.copy()
+        request.GET["title"] = validated_data["q"]
+        if not "path" in request.GET or not request.GET["path"]:
+            return self.list(request, *args, **kwargs)
+        return self._list_descendants(request)
+
+    def _list_descendants(self, request):
+        """
+        List all documents whose path starts with the provided path parameter.
+        Includes the parent document itself.
+        Used internally by the search endpoint when path filtering is requested.
+        """
+        # Get parent document without access filtering
+        parent_path = request.GET["path"]
+        try:
+            parent = models.Document.objects.get(path=parent_path)
+        except models.Document.DoesNotExist as exc:
+            raise drf.exceptions.NotFound("Document not found from path.") from exc
+
+        # Check object-level permissions using DocumentPermission logic
+        self.check_object_permissions(request, parent)
+
+        # Get descendants and include the parent, ordered by path
+        queryset = (
+            parent.get_descendants(include_self=True)
+            .filter(ancestors_deleted_at__isnull=True)
+            .order_by("path")
+        )
+        queryset = self.filter_queryset(queryset)
+
+        # filter by title
+        filterset = DocumentFilter(request.GET, queryset=queryset)
+        if not filterset.is_valid():
+            raise drf.exceptions.ValidationError(filterset.errors)
+
+        queryset = filterset.qs
+        return self.get_response_for_queryset(queryset)
 
     @drf.decorators.action(detail=True, methods=["get"], url_path="versions")
     def versions_list(self, request, *args, **kwargs):