mirror of
https://github.com/suitenumerique/docs.git
synced 2026-09-08 10:47:54 +02:00
Integrate Find (#1834)
## Purpose integrate Find to Docs ## Proposal - [x] ✨ add a `useSeachDocs` hook in charged of calling the search endpoint. - [x] ✨ add a optional `path` param to the `search` route. This param represents the parent document path in case of a sub-documents (descendants) search. - [x] ⚡️return Indexer results directly without DB calls to retrieve the Document objects. All informations necessary for display are indexed in Find. We can skip the DB calls and improve performance. - [x] ♻️ refactor react `DocSearchContent` components. `DocSearchContent` and `DocSearchSubContent` are now merged a unique component handling all search scenarios and relying on the unique `search` route. - [x] 🔥remove pagination logic in the Indexer. Removing the DB calls also removes the DRF queryset object which handles the pagination. Also we consider pagination not to be necessary for search v1. - [x] 🔥remove the `document/<document_id>/descendants` route. This route is not used anymore. The logic of finding the descendants are moved to the internal `_list_descendants` method. This method is based on the parent `path` instead of the parent `id` which has some consequence about the user access management. Relying on the path prevents the use of the `self.get_object()` method which used to handle the user access logic. - [x] ✨handle fallback logic on DRF based title search in case of non-configured, badly configured or failing at run time indexer. - [x] ✨handle language extension in `title` field. Find returns titles with a language extension (ex: `{ title.fr: "rapport d'activité" }` instead of `{ "title": "rapport d'activité" }`. - [x] 🔧 add a `common.test` file to allow running the tests without docker - [x] ♻️ rename `SearchIndexer` -> `FindDocumentIndexer`. This class has to do with Find in particular and the convention is more coherent with `BaseDocumentIndexer` - [x] ♻️ rename `SEARCH_INDEXER_URL` -> `INDEXING_URL` and `SEARCH_INDEXER_QUERY_URL` -> `SEARCH_URL`. I found the original names very confusing. - [x] 🔧 update the environment variables to activate the FindDocumentIndexer. - [x] ✨automate the generation of encryption key during bootstrap. OIDC_STORE_REFRESH_TOKEN_KEY is a mandatory secret key. We can not push it on Github and we want any contributor to be able to run the app by only running the `make bootstrap`. We chose to generate and wright it into the `common.local` during bootstrap. ## External contributions Thank you for your contribution! 🎉 Please ensure the following items are checked before submitting your pull request: - [x] I have read and followed the [contributing guidelines](https://github.com/suitenumerique/docs/blob/main/CONTRIBUTING.md) - [x] I have read and agreed to the [Code of Conduct](https://github.com/suitenumerique/docs/blob/main/CODE_OF_CONDUCT.md) - [x] I have signed off my commits with `git commit --signoff` (DCO compliance) - [x] I have signed my commits with my SSH or GPG key (`git commit -S`) - [x] My commit messages follow the required format: `<gitmoji>(type) title description` - [x] I have added a changelog entry under `## [Unreleased]` section (if noticeable change) - [x] I have added corresponding tests for new features or bug fixes (if applicable) --------- Signed-off-by: charles <charles.englebert@protonmail.com>
This commit is contained in:
Charles Englebert
@@ -72,7 +72,11 @@ from core.utils import (
|
||||
)
|
||||
|
||||
from . import permissions, serializers, utils
|
||||
from .filters import DocumentFilter, ListDocumentFilter, UserSearchFilter
|
||||
from .filters import (
|
||||
DocumentFilter,
|
||||
ListDocumentFilter,
|
||||
UserSearchFilter,
|
||||
)
|
||||
from .throttling import (
|
||||
DocumentThrottle,
|
||||
UserListThrottleBurst,
|
||||
@@ -604,20 +608,18 @@ class DocumentViewSet(
|
||||
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
|
||||
|
||||
# Filter as early as possible on fields that are available on the model
|
||||
for field in ["is_creator_me", "title"]:
|
||||
for field in ["is_creator_me", "title", "q"]:
|
||||
queryset = filterset.filters[field].filter(queryset, filter_data[field])
|
||||
|
||||
queryset = queryset.annotate_user_roles(user)
|
||||
@@ -1084,7 +1086,7 @@ class DocumentViewSet(
|
||||
filter_data = filterset.form.cleaned_data
|
||||
|
||||
# Filter as early as possible on fields that are available on the model
|
||||
for field in ["is_creator_me", "title"]:
|
||||
for field in ["is_creator_me", "title", "q"]:
|
||||
queryset = filterset.filters[field].filter(queryset, filter_data[field])
|
||||
|
||||
queryset = queryset.annotate_user_roles(user)
|
||||
@@ -1107,7 +1109,11 @@ class DocumentViewSet(
|
||||
ordering=["path"],
|
||||
)
|
||||
def descendants(self, request, *args, **kwargs):
|
||||
"""Handle listing descendants of a document"""
|
||||
"""Deprecated endpoint to list descendants of a document."""
|
||||
logger.warning(
|
||||
"The 'descendants' endpoint is deprecated and will be removed in a future release. "
|
||||
"The search endpoint should be used for all document retrieval use cases."
|
||||
)
|
||||
document = self.get_object()
|
||||
|
||||
queryset = document.get_descendants().filter(ancestors_deleted_at__isnull=True)
|
||||
@@ -1397,82 +1403,103 @@ class DocumentViewSet(
|
||||
|
||||
return duplicated_document
|
||||
|
||||
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):
|
||||
"""
|
||||
Returns a DRF response containing the filtered, annotated and ordered document list.
|
||||
Returns an ordered list of documents best matching the search query parameter 'q'.
|
||||
|
||||
Applies filtering based on request parameter 'q' from `SearchDocumentSerializer`.
|
||||
Depending of the configuration it can be:
|
||||
- A fulltext search through the opensearch indexation app "find" if the backend is
|
||||
enabled (see SEARCH_INDEXER_CLASS)
|
||||
- A filtering by the model field 'title'.
|
||||
|
||||
The ordering is always by the most recent first.
|
||||
It depends on a search configurable Search Indexer. If no Search Indexer is configured
|
||||
or if it is not reachable, the function falls back to a basic title search.
|
||||
"""
|
||||
params = serializers.SearchDocumentSerializer(data=request.query_params)
|
||||
params.is_valid(raise_exception=True)
|
||||
|
||||
indexer = get_document_indexer()
|
||||
if indexer is None:
|
||||
# fallback on title search if the indexer is not configured
|
||||
return self._title_search(request, params.validated_data, *args, **kwargs)
|
||||
|
||||
if indexer:
|
||||
return self._search_fulltext(indexer, request, params=params)
|
||||
try:
|
||||
return self._search_with_indexer(indexer, request, params=params)
|
||||
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)
|
||||
|
||||
# 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()
|
||||
|
||||
results = indexer.search(
|
||||
q=params.validated_data["q"],
|
||||
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 method when no indexer is configured.
|
||||
Only searches in the title field of documents.
|
||||
"""
|
||||
if not validated_data.get("path"):
|
||||
return self.list(request, *args, **kwargs)
|
||||
|
||||
return self._list_descendants(request, validated_data)
|
||||
|
||||
def _list_descendants(self, request, validated_data):
|
||||
"""
|
||||
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 = validated_data["path"]
|
||||
try:
|
||||
parent = models.Document.objects.annotate_user_roles(request.user).get(
|
||||
path=parent_path
|
||||
)
|
||||
except models.Document.DoesNotExist as exc:
|
||||
raise drf.exceptions.NotFound("Document not found from path.") from exc
|
||||
|
||||
abilities = parent.get_abilities(request.user)
|
||||
if not abilities.get("search"):
|
||||
raise drf.exceptions.PermissionDenied(
|
||||
"You do not have permission to search within this document."
|
||||
)
|
||||
|
||||
# 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):
|
||||
|
||||
Reference in New Issue
Block a user